From rosuav at gmail.com  Sat Apr  1 03:50:36 2023
From: rosuav at gmail.com (Chris Angelico)
Date: Sat, 1 Apr 2023 18:50:36 +1100
Subject: Windows installer from python source code without access to
 source code
In-Reply-To: <ZCeTioOFo80Z2b8i@anomaly>
References: <6b7e32a0-77a4-1d53-a7d3-0ca9887da30b@tompassin.net>
 <D06C0607-F259-4195-A843-0FDED7063411@sbcglobal.net>
 <CAPTjJmrPqmM1wXzStaM538U=mX4T1A9s7f4xoY4psXBhBv-BfA@mail.gmail.com>
 <ZCeTioOFo80Z2b8i@anomaly>
Message-ID: <CAPTjJmpPfMdt_Fr-kPGba3k1sFmuTLPH8M_2PcF2z9S03GWMaQ@mail.gmail.com>

On Sat, 1 Apr 2023 at 13:16, <2QdxY4RzWzUUiLuE at potatochowder.com> wrote:
>
> On 2023-04-01 at 10:49:18 +1100,
> Chris Angelico <rosuav at gmail.com> wrote:
>
> > [...] I don't have access to the Gmail source code but I'm using the
> > service [...]
>
> You have access to Gmail's front end source code.  Your web browser runs
> it every time you use the service (and probably while you aren't using
> the service, too).

Yes, and I'm talking about their back end source code, which I most
definitely do NOT have access to, and therefore cannot copy.

> My educated guess is that Google expended some
> effort to hinder you from looking at and/or analyzing (or do you say
> analysing?) that code, and that their lawyers will come knocking at your
> metaphorical door if they so much as think you are using that code in
> some way other than running it inside your web browser.  If only this
> situation were a cruel April Fool's Day joke.

They haven't done very much, I happen to know this relating to other
services. From what I can tell, Google's front ends aren't very well
protected, for the simple reason that they're quite useless without
the corresponding back ends.

> You don't have access to Gmail's back end source code.
>
> Many/Most web apps follow this pattern to varying degrees.  I do not
> know whether this setup meets the OP's requirements.

Exactly. That's why I pointed it out. This is the only way to truly
protect your source code: Don't give it out.

ChrisA

From jschwar at sbcglobal.net  Sat Apr  1 05:24:44 2023
From: jschwar at sbcglobal.net (Jim Schwartz)
Date: Sat, 1 Apr 2023 04:24:44 -0500
Subject: Windows installer from python source code without access to
 source code
In-Reply-To: <CAPTjJmrPqmM1wXzStaM538U=mX4T1A9s7f4xoY4psXBhBv-BfA@mail.gmail.com>
References: <CAPTjJmrPqmM1wXzStaM538U=mX4T1A9s7f4xoY4psXBhBv-BfA@mail.gmail.com>
Message-ID: <D803DFC2-9103-4C97-B0C5-BFA8980C022E@sbcglobal.net>

I am writing an app but I?m not sure I?ll sell it yet. I have it in a private GitHub location and GitHub prompts me for a license. I don?t really understand licenses so I just picked Apache 2.0. Maybe I?m going too far with my worry about which license I pick. I?m not selling it now so it doesn?t matter. I have to do a lot more work before I get to that point  

Sent from my iPhone

> On Mar 31, 2023, at 6:52 PM, Chris Angelico <rosuav at gmail.com> wrote:
> 
> ?On Sat, 1 Apr 2023 at 10:34, Jim Schwartz <jschwar at sbcglobal.net> wrote:
>> 
>> Yea. You?re right. I probably need a lawyer someday. Thanks.
>> 
> 
> If your needs are basic, you shouldn't need a lawyer. Copyright law
> and treaties DO protect you. But it's important to be aware that no
> amount of legal protection - whether you hire a lawyer or not, and
> whether you identify copyright and license or not - will stop people
> from copying your code. NOTHING will stop people from copying your
> code if they have access to it. All you can do is discourage them.
> 
> So that brings us back to the original question: Why protect your
> *source code* specifically? There are two extremes available to
> everyone:
> 
> 1) Distribute the source code. Let everyone see it. Stick a license on
> it that permits them to use it, modify it, distribute modified
> versions. Set your code free and let it be used.
> 
> 2) Don't distribute the program *at all*. Don't distribute the source
> OR the binary. Instead, permit people to *access* the program - which,
> in today's world, usually means a web service.
> 
> Both of these are very popular and work well. I don't have access to
> the Gmail source code but I'm using the service. I don't have access
> to the Twitch.tv source code but I'm using the service. Meanwhile, I
> have Python programs running on a Debian system using the Linux
> kernel, invoked using bash, served from an ext4 mass storage device,
> etc, etc. I have the binary code for all of these, and I'm legally
> guaranteed access to the source if I want it, so there's no incentive
> to steal it.
> 
> The middle ground of "distribute binaries but stop people from
> accessing the source" is a much narrower use-case, and I would say
> that it's not actually a single use-case but a family of them, each
> with different needs and requirements. So it's essential to know what
> you're actually trying to protect, and why.
> 
> ChrisA
> -- 
> https://mail.python.org/mailman/listinfo/python-list


From barry at barrys-emacs.org  Sat Apr  1 05:52:53 2023
From: barry at barrys-emacs.org (Barry Scott)
Date: Sat, 1 Apr 2023 10:52:53 +0100
Subject: Python not showing correct version
In-Reply-To: <CACL+1avoH4YT6eTH4bpSPPKpAK7X2ciX+FpQ_PR-6sU_Py4+fg@mail.gmail.com>
References: <CANvxP8M8nPBCm2cehEG1UahP=SoOHiZYpazY_pmXhtUWsOYS6g@mail.gmail.com>
 <CANvxP8M89NK+QY2YodnjZmojUMFOnwVSVT27mLgKh-jXgv4AMw@mail.gmail.com>
 <D26A4D1C-EF05-4C9D-9E52-8DD3148FCA4F@barrys-emacs.org>
 <CANvxP8PNFGFx7x7nSH-DyrCD+1F7=fH-aGjMPm1uPWnqFY7J4g@mail.gmail.com>
 <CACL+1avZZxOQMJ78QNMFZJCKgNEHMBkUxfuyA0f+PW7g-7-kkg@mail.gmail.com>
 <34dcfb4d-28ed-0d26-8816-826fd63c1848@tompassin.net>
 <CACL+1avoH4YT6eTH4bpSPPKpAK7X2ciX+FpQ_PR-6sU_Py4+fg@mail.gmail.com>
Message-ID: <4F251711-2F64-4B29-8E23-16E792C23009@barrys-emacs.org>



> On 31 Mar 2023, at 22:02, Eryk Sun <eryksun at gmail.com> wrote:
> 
> 
> The OP installed the standard Python 3.8 distribution, which does
> install the launcher by default. The launcher can run all installed
> versions, including store app installations. By default it runs the
> highest available version, which will probably be the 3.10 store app
> in the OP's case. To make 3.8 the default without having to remove
> 3.10, set the environment variables "PY_PYTHON=3.8" and
> "PY_PYTHON3=3.8" in the user environment.

I find user environment on windows to be less flexible to work with then
adding a py.ini. On my Windows 11 I added %userprofile%\AppData\Local\py.ini.
To make python 3.8 the default that py.exe uses put this in py.ini:

[defaults]
python=3.8-64
python3=3.8-64

Barry


> -- 
> https://mail.python.org/mailman/listinfo/python-list
> 


From nulla.epistola at web.de  Sat Apr  1 06:09:57 2023
From: nulla.epistola at web.de (Sibylle Koczian)
Date: Sat, 1 Apr 2023 12:09:57 +0200
Subject: Ole version set as default
In-Reply-To: <CAJz1ufN3jkPA0+9vHYMs+YM0AUwH96-M-ru3ycRQAfUd6Wdp0A@mail.gmail.com>
References: <CAJz1ufN3jkPA0+9vHYMs+YM0AUwH96-M-ru3ycRQAfUd6Wdp0A@mail.gmail.com>
Message-ID: <e3f67c00-dce7-c8dc-0e96-5f05e6317755@web.de>

Am 29.03.2023 um 18:46 schrieb Pranav Bhardwaj:
> Dear sir,
>                 I am Pranav Bhardwaj and I stuck in a problem. My problem is
> that in my system I have python 3.11.2 but when I type python in my command
> prompt, my command prompt show that python version 2.7.13 as a default. And
> I can't be able to find python 2.7.13 in my system in any file and I tried
> various methods to set python 3.11.2 as a default but can't be able to do
> so. I tried to change environment variables, try to find and delete python
> 2.7.13 , try to set python 3.11.2 as default, but I can't be able to do so.
> So can you help me how can I solve this problem?

Which OS is this? And what happens if you enter "python3" in your 
command prompt?

HTH
Sibylle


From rosuav at gmail.com  Sat Apr  1 06:26:20 2023
From: rosuav at gmail.com (Chris Angelico)
Date: Sat, 1 Apr 2023 21:26:20 +1100
Subject: Windows installer from python source code without access to
 source code
In-Reply-To: <D803DFC2-9103-4C97-B0C5-BFA8980C022E@sbcglobal.net>
References: <CAPTjJmrPqmM1wXzStaM538U=mX4T1A9s7f4xoY4psXBhBv-BfA@mail.gmail.com>
 <D803DFC2-9103-4C97-B0C5-BFA8980C022E@sbcglobal.net>
Message-ID: <CAPTjJmqj7K4KntNYk3--oA=P6H5pwn4AHu0tH=mnPnwho4Kqjw@mail.gmail.com>

On Sat, 1 Apr 2023 at 20:24, Jim Schwartz <jschwar at sbcglobal.net> wrote:
>
> I am writing an app but I?m not sure I?ll sell it yet. I have it in a private GitHub location and GitHub prompts me for a license. I don?t really understand licenses so I just picked Apache 2.0. Maybe I?m going too far with my worry about which license I pick. I?m not selling it now so it doesn?t matter. I have to do a lot more work before I get to that point
>

When you put license terms on something, that is a *legal statement*.
Read the license you're applying and don't just pick for the sake of
picking. By applying this license, you are granting legal permission
for anyone to redistribute your code in source or object form.

On the plus side, you've just made all questions of obfuscating your
source code completely irrelevant :)

ChrisA

From jschwar at sbcglobal.net  Sat Apr  1 07:59:50 2023
From: jschwar at sbcglobal.net (Jim Schwartz)
Date: Sat, 1 Apr 2023 06:59:50 -0500
Subject: Windows Gui Frontend
References: <027401d96491$7736dce0$65a496a0$.ref@sbcglobal.net>
Message-ID: <027401d96491$7736dce0$65a496a0$@sbcglobal.net>

I have another question.  I have an app written in python, but I want to add
a windows GUI front end to it.  Can this be done in python?  What packages
would allow me to do that?

 

Thanks.


From list1 at tompassin.net  Sat Apr  1 08:51:43 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Sat, 1 Apr 2023 08:51:43 -0400
Subject: Windows installer from python source code without access to
 source code
In-Reply-To: <D803DFC2-9103-4C97-B0C5-BFA8980C022E@sbcglobal.net>
References: <CAPTjJmrPqmM1wXzStaM538U=mX4T1A9s7f4xoY4psXBhBv-BfA@mail.gmail.com>
 <D803DFC2-9103-4C97-B0C5-BFA8980C022E@sbcglobal.net>
Message-ID: <aba4c3c0-cf66-d7ee-9662-f90e975a5d84@tompassin.net>

On 4/1/2023 5:24 AM, Jim Schwartz wrote:
> I am writing an app but I?m not sure I?ll sell it yet. I have it in a private GitHub location and GitHub prompts me for a license. I don?t really understand licenses so I just picked Apache 2.0. Maybe I?m going too far with my worry about which license I pick. I?m not selling it now so it doesn?t matter. I have to do a lot more work before I get to that point

You can dual-license it - one license for free uses, one for commercial 
users.  But read GitHub's terms of service to make sure your repo is 
going to continue to qualify - you might need to start paying them if 
your code goes commercial.


From eryksun at gmail.com  Sat Apr  1 11:08:49 2023
From: eryksun at gmail.com (Eryk Sun)
Date: Sat, 1 Apr 2023 10:08:49 -0500
Subject: Python not showing correct version
In-Reply-To: <4F251711-2F64-4B29-8E23-16E792C23009@barrys-emacs.org>
References: <CANvxP8M8nPBCm2cehEG1UahP=SoOHiZYpazY_pmXhtUWsOYS6g@mail.gmail.com>
 <CANvxP8M89NK+QY2YodnjZmojUMFOnwVSVT27mLgKh-jXgv4AMw@mail.gmail.com>
 <D26A4D1C-EF05-4C9D-9E52-8DD3148FCA4F@barrys-emacs.org>
 <CANvxP8PNFGFx7x7nSH-DyrCD+1F7=fH-aGjMPm1uPWnqFY7J4g@mail.gmail.com>
 <CACL+1avZZxOQMJ78QNMFZJCKgNEHMBkUxfuyA0f+PW7g-7-kkg@mail.gmail.com>
 <34dcfb4d-28ed-0d26-8816-826fd63c1848@tompassin.net>
 <CACL+1avoH4YT6eTH4bpSPPKpAK7X2ciX+FpQ_PR-6sU_Py4+fg@mail.gmail.com>
 <4F251711-2F64-4B29-8E23-16E792C23009@barrys-emacs.org>
Message-ID: <CACL+1atR2TinU7LY=4kCo14T8AoeWiE5VVXrhcRiZmN_pNHdQg@mail.gmail.com>

On 4/1/23, Barry Scott <barry at barrys-emacs.org> wrote:
>
> I find user environment on windows to be less flexible to work with then
> adding a py.ini. On my Windows 11 I added
> %userprofile%\AppData\Local\py.ini.
> To make python 3.8 the default that py.exe uses put this in py.ini:
>
> [defaults]
> python=3.8-64
> python3=3.8-64

Using "py.ini" has the advantage that launcher always reads the file.
The value of the environment variables, on the other hand, may be
stale. If you keep a lot of shells running, it would be tedious to
have to manually update the PY_PYTHON* variables in each shell. That
said, it should be rare that one needs to change the persisted default
versions. For temporary changes, the PY_PYTHON* environment variables
are more flexible and take precedence over "py.ini".

If one doesn't use "py.ini" to set the defaults, it's easy to modify
the persisted user environment using "setx.exe"[^1]. For example:

    setx.exe PY_PYTHON 3.8
    setx.exe PY_PYTHON3 3.8

setx.exe broadcasts a WM_SETTINGCHANGE "Environment" window message,
which causes Explorer to update its environment. Thus any program run
from Explorer will see the new values. A program launched in a new tab
in Windows Terminal also gets a fresh environment. However, existing
CLI shells (CMD, PowerShell, bash), and programs started by them, will
still have the old environment values. The latter is where using
"py.ini" to set the defaults has the advantage.

---

[^1]: Note that "setx.exe" should never be used to set the persisted
user or machine "Path" value to the current %PATH%. When loading the
environment, the user "Path" gets appended to the machine "Path".
Setting the entire expanded and concatenated value to one or the other
leads to a bloated, redundant PATH value, and it also loses the
flexible configuration based on REG_EXPAND_SZ values.

From list1 at tompassin.net  Sat Apr  1 08:59:39 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Sat, 1 Apr 2023 08:59:39 -0400
Subject: Windows Gui Frontend
In-Reply-To: <027401d96491$7736dce0$65a496a0$@sbcglobal.net>
References: <027401d96491$7736dce0$65a496a0$.ref@sbcglobal.net>
 <027401d96491$7736dce0$65a496a0$@sbcglobal.net>
Message-ID: <f4c60ac0-b7e6-0471-1ab0-043869cb9287@tompassin.net>

On 4/1/2023 7:59 AM, Jim Schwartz wrote:
> I have another question.  I have an app written in python, but I want to add
> a windows GUI front end to it.  Can this be done in python?  What packages
> would allow me to do that?

WxWindows, Tk, and PyQt are some of the common ones. Be aware that GUI 
programming can soak up a lot of your time, so be prepared.

If you want it to work on Linux as well (always a good idea), you will 
need to pay attention to file locations, paths, and path separators as well.


From eryksun at gmail.com  Sat Apr  1 11:37:34 2023
From: eryksun at gmail.com (Eryk Sun)
Date: Sat, 1 Apr 2023 10:37:34 -0500
Subject: Windows Gui Frontend
In-Reply-To: <027401d96491$7736dce0$65a496a0$@sbcglobal.net>
References: <027401d96491$7736dce0$65a496a0$.ref@sbcglobal.net>
 <027401d96491$7736dce0$65a496a0$@sbcglobal.net>
Message-ID: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>

On 4/1/23, Jim Schwartz <jschwar at sbcglobal.net> wrote:
> I have another question.  I have an app written in python, but I want to
> add a windows GUI front end to it.  Can this be done in python?  What
> packages would allow me to do that?

Here are a few of the GUI toolkit libraries in common use:

    * tkinter (Tk)
    * PyQt (Qt)
    * PySide (Qt)
    * wxPython (wxWidgets)
    * PyGObject (GTK)

tkinter is included in Python's standard library.

From jschwar at sbcglobal.net  Sat Apr  1 13:21:55 2023
From: jschwar at sbcglobal.net (Jim Schwartz)
Date: Sat, 1 Apr 2023 12:21:55 -0500
Subject: Windows Gui Frontend
In-Reply-To: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
Message-ID: <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>

Are there any ide?s that will let me design the screen and convert it to python?  I doubt it because it was mentioned that this is time consuming. 

Thanks for the responses everyone. I appreciate it. 

Sent from my iPhone

> On Apr 1, 2023, at 10:37 AM, Eryk Sun <eryksun at gmail.com> wrote:
> 
> ?On 4/1/23, Jim Schwartz <jschwar at sbcglobal.net> wrote:
>> I have another question.  I have an app written in python, but I want to
>> add a windows GUI front end to it.  Can this be done in python?  What
>> packages would allow me to do that?
> 
> Here are a few of the GUI toolkit libraries in common use:
> 
>    * tkinter (Tk)
>    * PyQt (Qt)
>    * PySide (Qt)
>    * wxPython (wxWidgets)
>    * PyGObject (GTK)
> 
> tkinter is included in Python's standard library.


From list1 at tompassin.net  Sat Apr  1 13:28:42 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Sat, 1 Apr 2023 13:28:42 -0400
Subject: Windows Gui Frontend
In-Reply-To: <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
Message-ID: <9660a85e-00bd-5c6c-6be0-de6f4b6c8615@tompassin.net>

On 4/1/2023 1:21 PM, Jim Schwartz wrote:
> Are there any ide?s that will let me design the screen and convert it to python?  I doubt it because it was mentioned that this is time consuming.

Depends on what you mean by "let me design the screen", but Pyside 
(which I think is now called Pyside2) may be suitable.  It is part the 
Qt framework.


> Thanks for the responses everyone. I appreciate it.
> 
> Sent from my iPhone
> 
>> On Apr 1, 2023, at 10:37 AM, Eryk Sun <eryksun at gmail.com> wrote:
>>
>> ?On 4/1/23, Jim Schwartz <jschwar at sbcglobal.net> wrote:
>>> I have another question.  I have an app written in python, but I want to
>>> add a windows GUI front end to it.  Can this be done in python?  What
>>> packages would allow me to do that?
>>
>> Here are a few of the GUI toolkit libraries in common use:
>>
>>     * tkinter (Tk)
>>     * PyQt (Qt)
>>     * PySide (Qt)
>>     * wxPython (wxWidgets)
>>     * PyGObject (GTK)
>>
>> tkinter is included in Python's standard library.
> 


From ikorot01 at gmail.com  Sat Apr  1 13:30:08 2023
From: ikorot01 at gmail.com (Igor Korot)
Date: Sat, 1 Apr 2023 12:30:08 -0500
Subject: Windows Gui Frontend
In-Reply-To: <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
Message-ID: <CA+FnnTwatby55V2tzBJ=6f8HJFg_Fzk4aF_ZrPCDUR+xy1LDJg@mail.gmail.com>

Hi,

On Sat, Apr 1, 2023 at 12:24?PM Jim Schwartz <jschwar at sbcglobal.net> wrote:
>
> Are there any ide?s that will let me design the screen and convert it to python?  I doubt it because it was mentioned that this is time consuming.

Look at wxGlade (a project designed for wxWidgets).
You will design you layout and then just save it as a py file.

No conversion needed.
And it's pretty straightforward. And very easy.
You can do it in 5 min or less..

Thank you.

I'm sure other libraries mentioned have their own RAD tool.

>
> Thanks for the responses everyone. I appreciate it.
>
> Sent from my iPhone
>
> > On Apr 1, 2023, at 10:37 AM, Eryk Sun <eryksun at gmail.com> wrote:
> >
> > ?On 4/1/23, Jim Schwartz <jschwar at sbcglobal.net> wrote:
> >> I have another question.  I have an app written in python, but I want to
> >> add a windows GUI front end to it.  Can this be done in python?  What
> >> packages would allow me to do that?
> >
> > Here are a few of the GUI toolkit libraries in common use:
> >
> >    * tkinter (Tk)
> >    * PyQt (Qt)
> >    * PySide (Qt)
> >    * wxPython (wxWidgets)
> >    * PyGObject (GTK)
> >
> > tkinter is included in Python's standard library.
>
> --
> https://mail.python.org/mailman/listinfo/python-list

From eryksun at gmail.com  Sat Apr  1 13:34:27 2023
From: eryksun at gmail.com (Eryk Sun)
Date: Sat, 1 Apr 2023 12:34:27 -0500
Subject: Windows Gui Frontend
In-Reply-To: <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
Message-ID: <CACL+1ascwkBZKN2ixB-LSEJ3xuCTRomL4BL5eYGvYTMXj5Xk9w@mail.gmail.com>

On 4/1/23, Jim Schwartz <jschwar at sbcglobal.net> wrote:
> Are there any ide?s that will let me design the screen and convert it to
> python?  I doubt it because it was mentioned that this is time consuming.
>
> Thanks for the responses everyone. I appreciate it.

For Qt, the WYSIWYG UI editor is Qt Designer. The basics are covered
in the following PySide tutorial:

https://www.pythonguis.com/pyside2-tutorial

From list1 at tompassin.net  Sat Apr  1 13:37:38 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Sat, 1 Apr 2023 13:37:38 -0400
Subject: Windows Gui Frontend
In-Reply-To: <9660a85e-00bd-5c6c-6be0-de6f4b6c8615@tompassin.net>
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
 <9660a85e-00bd-5c6c-6be0-de6f4b6c8615@tompassin.net>
Message-ID: <b30a977a-ca32-83e6-409f-f0fdf913dc4c@tompassin.net>

On 4/1/2023 1:28 PM, Thomas Passin wrote:
> On 4/1/2023 1:21 PM, Jim Schwartz wrote:
>> Are there any ide?s that will let me design the screen and convert it 
>> to python?? I doubt it because it was mentioned that this is time 
>> consuming.
> 
> Depends on what you mean by "let me design the screen", but Pyside 
> (which I think is now called Pyside2) may be suitable.? It is part the 
> Qt framework.

I should have added that in my experience, the screen layout of controls 
is not the hardest and most time-consuming part of developing GUIs.  The 
hard part is getting the screen elements and other components to do what 
you want in the way that you want it.

For example, the Tk.Text class can be used as a fairly full-featured 
editor, but try figuring out how to highlight part of the text - not so 
obvious.  Or say you decide you want to have a button flash when 
clicked, but you don't like the standard flash effect and want to change 
it.  Those are a few of the kinds of things that you have to deal with 
and that soak up the time.  It's not usually screen design.

>>
>> Sent from my iPhone
>>
>>> On Apr 1, 2023, at 10:37 AM, Eryk Sun <eryksun at gmail.com> wrote:
>>>
>>> ?On 4/1/23, Jim Schwartz <jschwar at sbcglobal.net> wrote:
>>>> I have another question.? I have an app written in python, but I 
>>>> want to
>>>> add a windows GUI front end to it.? Can this be done in python?? What
>>>> packages would allow me to do that?
>>>
>>> Here are a few of the GUI toolkit libraries in common use:
>>>
>>> ??? * tkinter (Tk)
>>> ??? * PyQt (Qt)
>>> ??? * PySide (Qt)
>>> ??? * wxPython (wxWidgets)
>>> ??? * PyGObject (GTK)
>>>
>>> tkinter is included in Python's standard library.
>>
> 


From ikorot01 at gmail.com  Sat Apr  1 13:47:33 2023
From: ikorot01 at gmail.com (Igor Korot)
Date: Sat, 1 Apr 2023 12:47:33 -0500
Subject: Windows Gui Frontend
In-Reply-To: <b30a977a-ca32-83e6-409f-f0fdf913dc4c@tompassin.net>
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
 <9660a85e-00bd-5c6c-6be0-de6f4b6c8615@tompassin.net>
 <b30a977a-ca32-83e6-409f-f0fdf913dc4c@tompassin.net>
Message-ID: <CA+FnnTyVFrS1G=y5DT1HTtGgm8KWYOY=pFd-bP6xw8cxHiPxMQ@mail.gmail.com>

Hi, Thomas,

On Sat, Apr 1, 2023 at 12:40?PM Thomas Passin <list1 at tompassin.net> wrote:
>
> On 4/1/2023 1:28 PM, Thomas Passin wrote:
> > On 4/1/2023 1:21 PM, Jim Schwartz wrote:
> >> Are there any ide?s that will let me design the screen and convert it
> >> to python?  I doubt it because it was mentioned that this is time
> >> consuming.
> >
> > Depends on what you mean by "let me design the screen", but Pyside
> > (which I think is now called Pyside2) may be suitable.  It is part the
> > Qt framework.
>
> I should have added that in my experience, the screen layout of controls
> is not the hardest and most time-consuming part of developing GUIs.  The
> hard part is getting the screen elements and other components to do what
> you want in the way that you want it.
>
> For example, the Tk.Text class can be used as a fairly full-featured
> editor, but try figuring out how to highlight part of the text - not so
> obvious.  Or say you decide you want to have a button flash when
> clicked, but you don't like the standard flash effect and want to change
> it.  Those are a few of the kinds of things that you have to deal with
> and that soak up the time.  It's not usually screen design.

I suggest going with wxPython/wxGlade.

Thank you.

>
> >>
> >> Sent from my iPhone
> >>
> >>> On Apr 1, 2023, at 10:37 AM, Eryk Sun <eryksun at gmail.com> wrote:
> >>>
> >>> ?On 4/1/23, Jim Schwartz <jschwar at sbcglobal.net> wrote:
> >>>> I have another question.  I have an app written in python, but I
> >>>> want to
> >>>> add a windows GUI front end to it.  Can this be done in python?  What
> >>>> packages would allow me to do that?
> >>>
> >>> Here are a few of the GUI toolkit libraries in common use:
> >>>
> >>>     * tkinter (Tk)
> >>>     * PyQt (Qt)
> >>>     * PySide (Qt)
> >>>     * wxPython (wxWidgets)
> >>>     * PyGObject (GTK)
> >>>
> >>> tkinter is included in Python's standard library.
> >>
> >
>
> --
> https://mail.python.org/mailman/listinfo/python-list

From maillist at schwertberger.de  Sat Apr  1 13:47:50 2023
From: maillist at schwertberger.de (Dietmar Schwertberger)
Date: Sat, 1 Apr 2023 19:47:50 +0200
Subject: Windows Gui Frontend
In-Reply-To: <CA+FnnTwatby55V2tzBJ=6f8HJFg_Fzk4aF_ZrPCDUR+xy1LDJg@mail.gmail.com>
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
 <CA+FnnTwatby55V2tzBJ=6f8HJFg_Fzk4aF_ZrPCDUR+xy1LDJg@mail.gmail.com>
Message-ID: <54420baf-d4f8-b64e-bd3c-f331e6cb3c73@schwertberger.de>

On 01.04.2023 19:30, Igor Korot wrote:
> Look at wxGlade (a project designed for wxWidgets). You will design 
> you layout and then just save it as a py file.

wxGlade also includes a tutorial to get you started with wxPython 
itself. You should be able create basic GUIs within a few hours.
See https://discuss.wxpython.org/ for support on wxPython and the 
wxGlade mailing list.

Regards,

Dietmar


From ericfahlgren at gmail.com  Sat Apr  1 14:33:32 2023
From: ericfahlgren at gmail.com (Eric Fahlgren)
Date: Sat, 1 Apr 2023 11:33:32 -0700
Subject: [Python-Dev] Small lament...
In-Reply-To: <CANc-5Uz0_ESeo1NY-VUXd_YB=gnkp53ofSbghEzfpOXQNf11ug@mail.gmail.com>
References: <CANc-5Uz0_ESeo1NY-VUXd_YB=gnkp53ofSbghEzfpOXQNf11ug@mail.gmail.com>
Message-ID: <CAP2Qz+WwR205SmNL28yYmJ+oStQO3SprdKS+MH+GqdgPzXoavQ@mail.gmail.com>

Oh, man, it has been a while.  The last one I remember is PEP 404 (if you
can find it :) ), dated 2011 and it wasn't an April Fool's...

On Sat, Apr 1, 2023 at 11:23?AM Skip Montanaro <skip.montanaro at gmail.com>
wrote:

> Just wanted to throw this out there... I lament the loss of waking up on
> April 1st to see a creative April Fool's Day joke on one or both of these
> lists, often from our FLUFL... Maybe such frivolity still happens, just not in
> the Python ecosystem? I know you can still import "this" or
> "antigravity", but those are now old (both introduced before 2010). When
> was the last time a clever easter egg was introduced or an April Fool's Day
> joke played?
>
> ?\_(?)_/?
>
> Skip
>
> _______________________________________________
> Python-Dev mailing list -- python-dev at python.org
> To unsubscribe send an email to python-dev-leave at python.org
> https://mail.python.org/mailman3/lists/python-dev.python.org/
> Message archived at
> https://mail.python.org/archives/list/python-dev at python.org/message/Q62W2Q6R6XMX57WK2CUGEENHMT3C3REF/
> Code of Conduct: http://python.org/psf/codeofconduct/
>

From mats at wichmann.us  Sat Apr  1 14:47:51 2023
From: mats at wichmann.us (Mats Wichmann)
Date: Sat, 1 Apr 2023 12:47:51 -0600
Subject: Windows Gui Frontend
In-Reply-To: <CACL+1ascwkBZKN2ixB-LSEJ3xuCTRomL4BL5eYGvYTMXj5Xk9w@mail.gmail.com>
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
 <CACL+1ascwkBZKN2ixB-LSEJ3xuCTRomL4BL5eYGvYTMXj5Xk9w@mail.gmail.com>
Message-ID: <29adf712-50c9-e705-e993-ee361b6bd80b@wichmann.us>

On 4/1/23 11:34, Eryk Sun wrote:
> On 4/1/23, Jim Schwartz <jschwar at sbcglobal.net> wrote:
>> Are there any ide?s that will let me design the screen and convert it to
>> python?  I doubt it because it was mentioned that this is time consuming.
>>
>> Thanks for the responses everyone. I appreciate it.
> 
> For Qt, the WYSIWYG UI editor is Qt Designer. The basics are covered
> in the following PySide tutorial:
> 
> https://www.pythonguis.com/pyside2-tutorial

Also here is a decent tutorial:

https://realpython.com/qt-designer-python/



From eryksun at gmail.com  Sat Apr  1 15:23:12 2023
From: eryksun at gmail.com (Eryk Sun)
Date: Sat, 1 Apr 2023 14:23:12 -0500
Subject: [Python-Dev] Small lament...
In-Reply-To: <CANc-5Uz0_ESeo1NY-VUXd_YB=gnkp53ofSbghEzfpOXQNf11ug@mail.gmail.com>
References: <CANc-5Uz0_ESeo1NY-VUXd_YB=gnkp53ofSbghEzfpOXQNf11ug@mail.gmail.com>
Message-ID: <CACL+1avDZ92UQvXtLiBWffQbMOZMTwxCPS1PqgfV-0JqP2mrWQ@mail.gmail.com>

On 4/1/23, Skip Montanaro <skip.montanaro at gmail.com> wrote:
> Just wanted to throw this out there... I lament the loss of waking up on
> April 1st to see a creative April Fool's Day joke on one or both of these
> lists, often from our FLUFL... Maybe such frivolity still happens, just not
> in the Python ecosystem?

I thought this one was funny:

https://github.com/python/cpython/issues/103172

From egon at frerich.eu  Sat Apr  1 15:16:28 2023
From: egon at frerich.eu (Egon Frerich)
Date: Sat, 1 Apr 2023 21:16:28 +0200
Subject: Windows Gui Frontend
In-Reply-To: <027401d96491$7736dce0$65a496a0$@sbcglobal.net>
References: <027401d96491$7736dce0$65a496a0$.ref@sbcglobal.net>
 <027401d96491$7736dce0$65a496a0$@sbcglobal.net>
Message-ID: <ba02849a-0273-8640-6237-44d0ed21f408@frerich.eu>

tkinter is part of python

e.

Am 01.04.23 um 13:59 schrieb Jim Schwartz:
> I have another question.  I have an app written in python, but I want to add
> a windows GUI front end to it.  Can this be done in python?  What packages
> would allow me to do that?
>
>   
>
> Thanks.
>

From jschwar at sbcglobal.net  Sat Apr  1 16:11:33 2023
From: jschwar at sbcglobal.net (Jim Schwartz)
Date: Sat, 1 Apr 2023 15:11:33 -0500
Subject: [Python-Dev] Small lament...
In-Reply-To: <CACL+1avDZ92UQvXtLiBWffQbMOZMTwxCPS1PqgfV-0JqP2mrWQ@mail.gmail.com>
References: <CANc-5Uz0_ESeo1NY-VUXd_YB=gnkp53ofSbghEzfpOXQNf11ug@mail.gmail.com>
 <CACL+1avDZ92UQvXtLiBWffQbMOZMTwxCPS1PqgfV-0JqP2mrWQ@mail.gmail.com>
Message-ID: <02a801d964d6$28a4fae0$79eef0a0$@sbcglobal.net>

Yea, it is funny.  I commented on it.

-----Original Message-----
From: Python-list <python-list-bounces+jschwar=sbcglobal.net at python.org> On
Behalf Of Eryk Sun
Sent: Saturday, April 1, 2023 2:23 PM
To: Skip Montanaro <skip.montanaro at gmail.com>
Cc: Python <python-list at python.org>; python-dev Dev <python-dev at python.org>
Subject: Re: [Python-Dev] Small lament...

On 4/1/23, Skip Montanaro <skip.montanaro at gmail.com> wrote:
> Just wanted to throw this out there... I lament the loss of waking up 
> on April 1st to see a creative April Fool's Day joke on one or both of 
> these lists, often from our FLUFL... Maybe such frivolity still 
> happens, just not in the Python ecosystem?

I thought this one was funny:

https://github.com/python/cpython/issues/103172
--
https://mail.python.org/mailman/listinfo/python-list


From barry at barrys-emacs.org  Sat Apr  1 17:11:56 2023
From: barry at barrys-emacs.org (Barry Scott)
Date: Sat, 1 Apr 2023 22:11:56 +0100
Subject: Windows Gui Frontend
In-Reply-To: <CA+FnnTyVFrS1G=y5DT1HTtGgm8KWYOY=pFd-bP6xw8cxHiPxMQ@mail.gmail.com>
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
 <9660a85e-00bd-5c6c-6be0-de6f4b6c8615@tompassin.net>
 <b30a977a-ca32-83e6-409f-f0fdf913dc4c@tompassin.net>
 <CA+FnnTyVFrS1G=y5DT1HTtGgm8KWYOY=pFd-bP6xw8cxHiPxMQ@mail.gmail.com>
Message-ID: <0A71B998-71D6-4E36-B551-5AA6824E7321@barrys-emacs.org>



> On 1 Apr 2023, at 18:47, Igor Korot <ikorot01 at gmail.com> wrote:
> 
> I suggest going with wxPython/wxGlade.

I ported all my wxPython code to PyQt and have not regretted it.

wxPython was (its been a while so may not be an issue now) far to
hard to make consistent across OS, my apps run on Linux, macOS and Windows.
I found that PyQt was easier to get working.

Barry


From list1 at tompassin.net  Sat Apr  1 17:33:16 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Sat, 1 Apr 2023 17:33:16 -0400
Subject: Windows Gui Frontend
In-Reply-To: <0A71B998-71D6-4E36-B551-5AA6824E7321@barrys-emacs.org>
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
 <9660a85e-00bd-5c6c-6be0-de6f4b6c8615@tompassin.net>
 <b30a977a-ca32-83e6-409f-f0fdf913dc4c@tompassin.net>
 <CA+FnnTyVFrS1G=y5DT1HTtGgm8KWYOY=pFd-bP6xw8cxHiPxMQ@mail.gmail.com>
 <0A71B998-71D6-4E36-B551-5AA6824E7321@barrys-emacs.org>
Message-ID: <e1bd85b5-575f-a921-5c1a-eec8aac99506@tompassin.net>

On 4/1/2023 5:11 PM, Barry Scott wrote:
> 
> 
>> On 1 Apr 2023, at 18:47, Igor Korot <ikorot01 at gmail.com> wrote:
>>
>> I suggest going with wxPython/wxGlade.
> 
> I ported all my wxPython code to PyQt and have not regretted it.
> 
> wxPython was (its been a while so may not be an issue now) far to
> hard to make consistent across OS, my apps run on Linux, macOS and Windows.
> I found that PyQt was easier to get working.
> 
> Barry
> 

Having worked with both, I'd rather use PyQt, although Tk might be 
easier to get a toy app going with.  Both editing windows and packing 
are easier for me to understand with PyQt, for one thing.

OTOH, Qt isn't free for commercial use and the OP seems to be 
speculating on coming up with a product to sell at some point.


From grant.b.edwards at gmail.com  Sat Apr  1 18:22:50 2023
From: grant.b.edwards at gmail.com (Grant Edwards)
Date: Sat, 01 Apr 2023 15:22:50 -0700 (PDT)
Subject: Windows Gui Frontend
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
 <9660a85e-00bd-5c6c-6be0-de6f4b6c8615@tompassin.net>
 <b30a977a-ca32-83e6-409f-f0fdf913dc4c@tompassin.net>
 <CA+FnnTyVFrS1G=y5DT1HTtGgm8KWYOY=pFd-bP6xw8cxHiPxMQ@mail.gmail.com>
 <0A71B998-71D6-4E36-B551-5AA6824E7321@barrys-emacs.org>
 <e1bd85b5-575f-a921-5c1a-eec8aac99506@tompassin.net>
Message-ID: <6428aeba.050a0220.b17f9.182c@mx.google.com>

On 2023-04-01, Thomas Passin <list1 at tompassin.net> wrote:

> Having worked with both, I'd rather use PyQt, although Tk might be 
> easier to get a toy app going with.  Both editing windows and packing 
> are easier for me to understand with PyQt, for one thing.

With tk it is _very_ easy to get small apps going. As the apps get
larger and more complex, I find it easier to use wxPython or pyGTK
(never tried pyQt).  However, if you want to package that small app
using cxfreeze (or whatever) tk tends to produce pretty large bundles
compared to others.

--
Grant



From learn2program at gmail.com  Sat Apr  1 19:13:36 2023
From: learn2program at gmail.com (Alan Gauld)
Date: Sun, 2 Apr 2023 00:13:36 +0100
Subject: Windows Gui Frontend
In-Reply-To: <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
Message-ID: <514b86e4-a956-cd9e-d45f-6dc0aee6d2a5@yahoo.co.uk>

On 01/04/2023 18:21, Jim Schwartz wrote:
> Are there any ide?s that will let me design the screen and convert it to python?  

There is nothing remotely like the VB or Delphi GUI builders.
There are some tools somewhat similar to the Java Swing and
FX GUI builders with varying degrees of bugginess.

And there are a few bespoke GUI type tools such as Dabo for
building specific types of applications.

But most Python GUI developers seem to prefer to just hard
code the Python, once you get used to it there's not much
time saving with the GUI tools.

The real time consuming stuff in building GUIs is getting
the basic design right and keeping all the controls,
keyboard bindings and menus in sync. State management
in other words.

I did a deep dive examination of GUI builders back around
v2.6 and came away less than enthused. Things may have
improved since then but I've seen no real evidence of
that.

-- 
Alan G
Author of the Learn to Program web site
http://www.alan-g.me.uk/
http://www.amazon.com/author/alan_gauld
Follow my photo-blog on Flickr at:
http://www.flickr.com/photos/alangauldphotos



From torriem at gmail.com  Sat Apr  1 21:19:17 2023
From: torriem at gmail.com (Michael Torrie)
Date: Sat, 1 Apr 2023 19:19:17 -0600
Subject: Windows Gui Frontend
In-Reply-To: <e1bd85b5-575f-a921-5c1a-eec8aac99506@tompassin.net>
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
 <9660a85e-00bd-5c6c-6be0-de6f4b6c8615@tompassin.net>
 <b30a977a-ca32-83e6-409f-f0fdf913dc4c@tompassin.net>
 <CA+FnnTyVFrS1G=y5DT1HTtGgm8KWYOY=pFd-bP6xw8cxHiPxMQ@mail.gmail.com>
 <0A71B998-71D6-4E36-B551-5AA6824E7321@barrys-emacs.org>
 <e1bd85b5-575f-a921-5c1a-eec8aac99506@tompassin.net>
Message-ID: <e4672e88-50b8-1844-c762-97c3bce53840@gmail.com>

On 4/1/23 15:33, Thomas Passin wrote:
> OTOH, Qt isn't free for commercial use and the OP seems to be 
> speculating on coming up with a product to sell at some point.

Careful. That's not actually true, even though the marketing team at Qt
lets people believe it is.  Qt is licensed under the LGPL, which you can
definitely use in a proprietary, close-source app, provided you use the
dynamically-linked version (which PySide does of course) and do not
modify it.

Qt's commerical licensing is very hostile to small companies, I can say
that much.  It's too bad really.  But the LGPL will work for most
companies, except for those that might wish to use the embedded version,
such as in cars where being able to abide by the terms of the LGPL
becomes difficult.



From Karsten.Hilbert at gmx.net  Sun Apr  2 04:42:06 2023
From: Karsten.Hilbert at gmx.net (Karsten Hilbert)
Date: Sun, 2 Apr 2023 10:42:06 +0200
Subject: Aw: Re: Windows Gui Frontend
In-Reply-To: <514b86e4-a956-cd9e-d45f-6dc0aee6d2a5@yahoo.co.uk>
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
 <514b86e4-a956-cd9e-d45f-6dc0aee6d2a5@yahoo.co.uk>
Message-ID: <trinity-22820d3b-25eb-4dd7-8052-15c1d1b398e5-1680424926864@3c-app-gmx-bap62>

> The real time consuming stuff in building GUIs is getting
> the basic design right and keeping all the controls,
> keyboard bindings and menus in sync. State management
> in other words.

And cominmg up with sensible design choices _at all_.

> I did a deep dive examination of GUI builders back around
> v2.6 and came away less than enthused. Things may have
> improved since then but I've seen no real evidence of
> that.

Is this available anywhere ?

What GUI builders do (for me) is to make creating the GUI in a WYSIWYM way.

Like LyX for LaTeX.

Karsten

From maillist at schwertberger.de  Sun Apr  2 07:09:03 2023
From: maillist at schwertberger.de (Dietmar Schwertberger)
Date: Sun, 2 Apr 2023 13:09:03 +0200
Subject: Windows Gui Frontend
In-Reply-To: <514b86e4-a956-cd9e-d45f-6dc0aee6d2a5@yahoo.co.uk>
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
 <514b86e4-a956-cd9e-d45f-6dc0aee6d2a5@yahoo.co.uk>
Message-ID: <fe7b3eec-3faf-c0ab-8196-d73ea5cc6e90@schwertberger.de>

On 02.04.2023 01:13, Alan Gauld wrote:
> I did a deep dive examination of GUI builders back around
> v2.6 and came away less than enthused. Things may have
> improved since then but I've seen no real evidence of
> that.
I also did evaluate all the GUI builder from time to time between
2000 and 2016 to find one that I could recommend to colleagues,
but could not find one. Then I started contributing to wxGlade
and I can say that since a few years it's as easy again to
build GUIs as it was with VB6.

I don't want to go back to coding GUIs manually. For most use
cases it's a waste of time and often it does not result in the
best GUI as it's not so easy to try out and rearrange elements.

Regards,

Dietmar

From torriem at gmail.com  Sun Apr  2 10:45:46 2023
From: torriem at gmail.com (Michael Torrie)
Date: Sun, 2 Apr 2023 08:45:46 -0600
Subject: Windows Gui Frontend
In-Reply-To: <fe7b3eec-3faf-c0ab-8196-d73ea5cc6e90@schwertberger.de>
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
 <514b86e4-a956-cd9e-d45f-6dc0aee6d2a5@yahoo.co.uk>
 <fe7b3eec-3faf-c0ab-8196-d73ea5cc6e90@schwertberger.de>
Message-ID: <dc374441-9ce1-3854-d70f-4847264a27bc@gmail.com>

On 4/2/23 05:09, Dietmar Schwertberger wrote:
> I also did evaluate all the GUI builder from time to time between
> 2000 and 2016 to find one that I could recommend to colleagues,
> but could not find one. Then I started contributing to wxGlade
> and I can say that since a few years it's as easy again to
> build GUIs as it was with VB6.
> 
> I don't want to go back to coding GUIs manually. For most use
> cases it's a waste of time and often it does not result in the
> best GUI as it's not so easy to try out and rearrange elements.

But any modern GUI toolkit has sizers and layout managers. If you're
manually placing elements you cannot deal with HiDPI or changing window
sizes.  Rearranging happens automatically when using sizers and layout
managers.

That said, the future of GUIs is declarative, using XAML or some other
domain-specific language like QML.  Examples of this include QtQuick
(the long-term direction Qt is heading), and the various dot Net GUI
toolkits now popular including MS' own MAUI, WPF, Avalonia.

GUI designer tools (Qt Creator, Visual Studio) can be used to assist and
help layout the skeleton, but ultimately the GUI is defined by code. And
it works very well, is adaptive, and can automatically size and
rearrange. If you want portability to mobile devices, this is where it's at.

I've tried wxGlade but never could get into it, or wxWidgets in general.
 I used to use GTK a lot and did use Glade back then, and dynamically
loaded the UI definition files at run time.  Lately used more Qt with
QtDesigner, and even extended Designer to support using some custom
widgets I made.

but the future of Qt is clearly QtQuick, so I've been learning that.
Has its warts, but in general I like the declarative paradigm.  It's a
learning curve.  Overall it's fairly powerful, flexible and portable.  I
have used the designer in Qt Creator a bit, but it's often faster and
just as intuitive to write it in QML, since you're going to be dropping
into QML frequently anyway to set properties (not unlike having to set
widget properties in Qt Designer.  So I guess it's 6s using the
graphical designer vs straight Qt.

From torriem at gmail.com  Sun Apr  2 10:46:34 2023
From: torriem at gmail.com (Michael Torrie)
Date: Sun, 2 Apr 2023 08:46:34 -0600
Subject: Windows Gui Frontend
In-Reply-To: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
References: <027401d96491$7736dce0$65a496a0$.ref@sbcglobal.net>
 <027401d96491$7736dce0$65a496a0$@sbcglobal.net>
 <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
Message-ID: <3194adf0-5c45-1732-af4a-5568931d3be3@gmail.com>

On 4/1/23 09:37, Eryk Sun wrote:
> Here are a few of the GUI toolkit libraries in common use:
> 
>     * tkinter (Tk)
>     * PyQt (Qt)
>     * PySide (Qt)
>     * wxPython (wxWidgets)
>     * PyGObject (GTK)
> 
> tkinter is included in Python's standard library.

Another good one is Kivy.  Especially if you ever want to target mobile
in the future.  https://kivy.org/

From maillist at schwertberger.de  Sun Apr  2 11:09:06 2023
From: maillist at schwertberger.de (Dietmar Schwertberger)
Date: Sun, 2 Apr 2023 17:09:06 +0200
Subject: Windows Gui Frontend
In-Reply-To: <dc374441-9ce1-3854-d70f-4847264a27bc@gmail.com>
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
 <514b86e4-a956-cd9e-d45f-6dc0aee6d2a5@yahoo.co.uk>
 <fe7b3eec-3faf-c0ab-8196-d73ea5cc6e90@schwertberger.de>
 <dc374441-9ce1-3854-d70f-4847264a27bc@gmail.com>
Message-ID: <3bf17b63-674c-9cdb-3d01-af2dc5e95da3@schwertberger.de>

On 02.04.2023 16:45, Michael Torrie wrote:
> But any modern GUI toolkit has sizers and layout managers. If you're
> manually placing elements you cannot deal with HiDPI or changing window
> sizes.  Rearranging happens automatically when using sizers and layout
> managers.

I did not talk about pixel placement with wxGlade. That's not supported.
It's of course using sizers and with a hierarchy of sizers it's much easier
to rearrange things than it would be with pixel placement.

> GUI designer tools (Qt Creator, Visual Studio) can be used to assist and
> help layout the skeleton, but ultimately the GUI is defined by code. And

That's what I hated with Qt Designer: it does not output Python code 
but? a .ui file.
This was the point where I could not recommend it to anyone.

> I've tried wxGlade but never could get into it, or wxWidgets in general.

Which version? Up to 0.7.2 I agree.

> but the future of Qt is clearly QtQuick, so I've been learning that.
> Has its warts, but in general I like the declarative paradigm.  It's a
> learning curve.  Overall it's fairly powerful, flexible and portable.  I
For me QtQuick and QML are a step backwards by some ten years when
it comes to development speed.
It's as much 'fun' as doing GUIs with HTML and JavaScript.
Unfortunately, The Qt Company refused to provide an API for QtQuick to
be able to use it without QML.
Anyway, desktop development has long moved out of their focus
(around 15 years ago when Nokia acquired Trolltech). It's not where
their commercial customers are.

Regards,

Dietmar

From torriem at gmail.com  Sun Apr  2 12:20:53 2023
From: torriem at gmail.com (Michael Torrie)
Date: Sun, 2 Apr 2023 10:20:53 -0600
Subject: Windows Gui Frontend
In-Reply-To: <3bf17b63-674c-9cdb-3d01-af2dc5e95da3@schwertberger.de>
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
 <514b86e4-a956-cd9e-d45f-6dc0aee6d2a5@yahoo.co.uk>
 <fe7b3eec-3faf-c0ab-8196-d73ea5cc6e90@schwertberger.de>
 <dc374441-9ce1-3854-d70f-4847264a27bc@gmail.com>
 <3bf17b63-674c-9cdb-3d01-af2dc5e95da3@schwertberger.de>
Message-ID: <cb46292c-abe2-70bc-dbb4-42ab329bde4f@gmail.com>

On 2023-04-02 9:09 a.m., Dietmar Schwertberger wrote:
> That's what I hated with Qt Designer: it does not output Python code 
> but? a .ui file.
> This was the point where I could not recommend it to anyone.

Well the thing is you don't need to generate Python code at all.  Qt
provides a UI loader class that loads the UI file at run time, builds
the objects in memory, and connects all your signals for you.  So much
nicer than code generation.



From torriem at gmail.com  Sun Apr  2 12:26:32 2023
From: torriem at gmail.com (Michael Torrie)
Date: Sun, 2 Apr 2023 10:26:32 -0600
Subject: Windows Gui Frontend
In-Reply-To: <3bf17b63-674c-9cdb-3d01-af2dc5e95da3@schwertberger.de>
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
 <514b86e4-a956-cd9e-d45f-6dc0aee6d2a5@yahoo.co.uk>
 <fe7b3eec-3faf-c0ab-8196-d73ea5cc6e90@schwertberger.de>
 <dc374441-9ce1-3854-d70f-4847264a27bc@gmail.com>
 <3bf17b63-674c-9cdb-3d01-af2dc5e95da3@schwertberger.de>
Message-ID: <93b76186-ec01-0d4a-4a03-e051d0e2beb8@gmail.com>

On 2023-04-02 9:09 a.m., Dietmar Schwertberger wrote:
>> I've tried wxGlade but never could get into it, or wxWidgets in general.
> 
> Which version? Up to 0.7.2 I agree.

Been a long time. I was initially turned off by the event handling
system of wx compared to the signals and slots of Gtk and Qt.

> For me QtQuick and QML are a step backwards by some ten years when
> it comes to development speed.
> It's as much 'fun' as doing GUIs with HTML and JavaScript.
> Unfortunately, The Qt Company refused to provide an API for QtQuick to
> be able to use it without QML.
> Anyway, desktop development has long moved out of their focus
> (around 15 years ago when Nokia acquired Trolltech). It's not where
> their commercial customers are.

There are a number of desktop apps built in QtQuick.  KDE is
transitioning to QtQuick and it's been alright, not without some
consistency issues.  The Cura slicer is another example of a complete
desktop app written in QtQuick which looks and feels quite nicely on all
platforms.

For me, more and more I need to be able to run on mobile as well as
desktop.  Qt, GTK, or wx are just not good fits when you need that kind
of portability.

But traditional Qt will be with us or decades yet.

From maillist at schwertberger.de  Sun Apr  2 13:52:05 2023
From: maillist at schwertberger.de (Dietmar Schwertberger)
Date: Sun, 2 Apr 2023 19:52:05 +0200
Subject: Windows Gui Frontend
In-Reply-To: <cb46292c-abe2-70bc-dbb4-42ab329bde4f@gmail.com>
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
 <514b86e4-a956-cd9e-d45f-6dc0aee6d2a5@yahoo.co.uk>
 <fe7b3eec-3faf-c0ab-8196-d73ea5cc6e90@schwertberger.de>
 <dc374441-9ce1-3854-d70f-4847264a27bc@gmail.com>
 <3bf17b63-674c-9cdb-3d01-af2dc5e95da3@schwertberger.de>
 <cb46292c-abe2-70bc-dbb4-42ab329bde4f@gmail.com>
Message-ID: <3c1e0abb-2bfb-33eb-5080-7b43c3f0cbec@schwertberger.de>

On 02.04.2023 18:20, Michael Torrie wrote:
>> Well the thing is you don't need to generate Python code at all.  Qt
>> provides a UI loader class that loads the UI file at run time, builds
>> the objects in memory, and connects all your signals for you.

I know, but having to load the .ui file is awkward.
Even worse, you lose things like code completion.


>    So much
> nicer than code generation.

I absolutely disagree on this.

Regards,

Dietmar


From maillist at schwertberger.de  Sun Apr  2 14:02:49 2023
From: maillist at schwertberger.de (Dietmar Schwertberger)
Date: Sun, 2 Apr 2023 20:02:49 +0200
Subject: Windows Gui Frontend
In-Reply-To: <93b76186-ec01-0d4a-4a03-e051d0e2beb8@gmail.com>
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
 <514b86e4-a956-cd9e-d45f-6dc0aee6d2a5@yahoo.co.uk>
 <fe7b3eec-3faf-c0ab-8196-d73ea5cc6e90@schwertberger.de>
 <dc374441-9ce1-3854-d70f-4847264a27bc@gmail.com>
 <3bf17b63-674c-9cdb-3d01-af2dc5e95da3@schwertberger.de>
 <93b76186-ec01-0d4a-4a03-e051d0e2beb8@gmail.com>
Message-ID: <781c6940-2499-5945-dce9-ef70cf2320eb@schwertberger.de>

On 02.04.2023 18:26, Michael Torrie wrote:
> Been a long time. I was initially turned off by the event handling
> system of wx compared to the signals and slots of Gtk and Qt.
When starting with Python GUIs in 1999, I evaluated both.
Qt event handling had an advantage for C++ where the wxWidgets
people had to use event tables. I don't know when wxWidgets
added dynamic event binding, but with wxPython I don't know
anything else than dynamic binding.


Regards,

Dietmar


From ikorot01 at gmail.com  Sun Apr  2 15:11:34 2023
From: ikorot01 at gmail.com (Igor Korot)
Date: Sun, 2 Apr 2023 14:11:34 -0500
Subject: Windows Gui Frontend
In-Reply-To: <781c6940-2499-5945-dce9-ef70cf2320eb@schwertberger.de>
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
 <514b86e4-a956-cd9e-d45f-6dc0aee6d2a5@yahoo.co.uk>
 <fe7b3eec-3faf-c0ab-8196-d73ea5cc6e90@schwertberger.de>
 <dc374441-9ce1-3854-d70f-4847264a27bc@gmail.com>
 <3bf17b63-674c-9cdb-3d01-af2dc5e95da3@schwertberger.de>
 <93b76186-ec01-0d4a-4a03-e051d0e2beb8@gmail.com>
 <781c6940-2499-5945-dce9-ef70cf2320eb@schwertberger.de>
Message-ID: <CA+FnnTz+67x5DCGoMbwnynxmAukyUheni3FDdMGth=hXm=Y6dg@mail.gmail.com>

Hi, Dietmer,

On Sun, Apr 2, 2023 at 1:14?PM Dietmar Schwertberger
<maillist at schwertberger.de> wrote:
>
> On 02.04.2023 18:26, Michael Torrie wrote:
> > Been a long time. I was initially turned off by the event handling
> > system of wx compared to the signals and slots of Gtk and Qt.
> When starting with Python GUIs in 1999, I evaluated both.
> Qt event handling had an advantage for C++ where the wxWidgets
> people had to use event tables. I don't know when wxWidgets
> added dynamic event binding, but with wxPython I don't know
> anything else than dynamic binding.

I think Bind() was added sometime in 2.9 as GSoC project.
And https://docs.wxwidgets.org/latest/classwx_evt_handler.html#a3b4a42f7263fd0a257a996a078ef802f
proves me correct: it is in "Since 2.9.0"

Thank you.

>
>
> Regards,
>
> Dietmar
>
> --
> https://mail.python.org/mailman/listinfo/python-list

From grant.b.edwards at gmail.com  Sun Apr  2 16:50:45 2023
From: grant.b.edwards at gmail.com (Grant Edwards)
Date: Sun, 02 Apr 2023 13:50:45 -0700 (PDT)
Subject: Windows Gui Frontend
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
 <514b86e4-a956-cd9e-d45f-6dc0aee6d2a5@yahoo.co.uk>
 <fe7b3eec-3faf-c0ab-8196-d73ea5cc6e90@schwertberger.de>
 <dc374441-9ce1-3854-d70f-4847264a27bc@gmail.com>
Message-ID: <6429eaa5.5d0a0220.85d9d.247e@mx.google.com>

On 2023-04-02, Michael Torrie <torriem at gmail.com> wrote:
> On 4/2/23 05:09, Dietmar Schwertberger wrote:
>> I also did evaluate all the GUI builder from time to time between
>> 2000 and 2016 to find one that I could recommend to colleagues,
>> but could not find one. Then I started contributing to wxGlade
>> and I can say that since a few years it's as easy again to
>> build GUIs as it was with VB6.
>
> [...]
>
> But any modern GUI toolkit has sizers and layout managers. If you're
> manually placing elements you cannot deal with HiDPI or changing window
> sizes.

Ah, that's the brilliant thing about VB6 apps! They only work properly
on machines with the same resoultion and display/font configuration as
the developer.

--
Grant


From PythonList at DancesWithMice.info  Sun Apr  2 18:33:35 2023
From: PythonList at DancesWithMice.info (dn)
Date: Mon, 3 Apr 2023 10:33:35 +1200
Subject: Windows Gui Frontend
In-Reply-To: <dc374441-9ce1-3854-d70f-4847264a27bc@gmail.com>
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
 <514b86e4-a956-cd9e-d45f-6dc0aee6d2a5@yahoo.co.uk>
 <fe7b3eec-3faf-c0ab-8196-d73ea5cc6e90@schwertberger.de>
 <dc374441-9ce1-3854-d70f-4847264a27bc@gmail.com>
Message-ID: <4d9d43b8-cdb7-12e9-ff8f-d7663e8da4fc@DancesWithMice.info>



On 03/04/2023 02.45, Michael Torrie wrote:
> On 4/2/23 05:09, Dietmar Schwertberger wrote:
>> I also did evaluate all the GUI builder from time to time between
>> 2000 and 2016 to find one that I could recommend to colleagues,
>> but could not find one. Then I started contributing to wxGlade
>> and I can say that since a few years it's as easy again to
>> build GUIs as it was with VB6.
>>
>> I don't want to go back to coding GUIs manually. For most use
>> cases it's a waste of time and often it does not result in the
>> best GUI as it's not so easy to try out and rearrange elements.
> 
> But any modern GUI toolkit has sizers and layout managers. If you're
> manually placing elements you cannot deal with HiDPI or changing window
> sizes.  Rearranging happens automatically when using sizers and layout
> managers.
> 
> That said, the future of GUIs is declarative, using XAML or some other
> domain-specific language like QML.  Examples of this include QtQuick
> (the long-term direction Qt is heading), and the various dot Net GUI
> toolkits now popular including MS' own MAUI, WPF, Avalonia.
> 
> GUI designer tools (Qt Creator, Visual Studio) can be used to assist and
> help layout the skeleton, but ultimately the GUI is defined by code. And
> it works very well, is adaptive, and can automatically size and
> rearrange. If you want portability to mobile devices, this is where it's at.
> 
> I've tried wxGlade but never could get into it, or wxWidgets in general.
>   I used to use GTK a lot and did use Glade back then, and dynamically
> loaded the UI definition files at run time.  Lately used more Qt with
> QtDesigner, and even extended Designer to support using some custom
> widgets I made.
> 
> but the future of Qt is clearly QtQuick, so I've been learning that.
> Has its warts, but in general I like the declarative paradigm.  It's a
> learning curve.  Overall it's fairly powerful, flexible and portable.  I
> have used the designer in Qt Creator a bit, but it's often faster and
> just as intuitive to write it in QML, since you're going to be dropping
> into QML frequently anyway to set properties (not unlike having to set
> widget properties in Qt Designer.  So I guess it's 6s using the
> graphical designer vs straight Qt.

Do the two approaches acknowledge each other and enable 'round tripping'?
ie to use the best?better tool for particular jobs (and to cope with 
later-maintenance) can one start using one approach, switch to using the 
other, and then go back to the first?

-- 
Regards,
=dn

From rolfblum at ewe.net  Mon Apr  3 05:09:55 2023
From: rolfblum at ewe.net (Rolf Blum)
Date: Mon, 3 Apr 2023 11:09:55 +0200
Subject: Windows Gui Frontend
In-Reply-To: <514b86e4-a956-cd9e-d45f-6dc0aee6d2a5@yahoo.co.uk>
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
 <514b86e4-a956-cd9e-d45f-6dc0aee6d2a5@yahoo.co.uk>
Message-ID: <0908f575-f8e7-c152-2eb2-ead7d70a9fdb@ewe.net>

Am 02.04.2023 um 01:13 schrieb Alan Gauld:
> On 01/04/2023 18:21, Jim Schwartz wrote:
>> Are there any ide?s that will let me design the screen and convert it to python?
> 
> There is nothing remotely like the VB or Delphi GUI builders.

The latest Delphi versions themself can create GUIs for Python. I use 
Delphi 10.4.2 (Sidney) Professional.

From pranavbhardwaj773 at gmail.com  Mon Apr  3 12:40:02 2023
From: pranavbhardwaj773 at gmail.com (Pranav Bhardwaj)
Date: Mon, 3 Apr 2023 22:10:02 +0530
Subject: Problem in using libraries
Message-ID: <CAJz1ufMHKGYm=wY743nXQyyEqkd0FKQE+uV9t1xyyJAvZ4r22w@mail.gmail.com>

Why can't I able to use python libraries such as numpy, nudenet, playsound,
in python 3.11.2

From pranavbhardwaj773 at gmail.com  Mon Apr  3 12:43:37 2023
From: pranavbhardwaj773 at gmail.com (Pranav Bhardwaj)
Date: Mon, 3 Apr 2023 22:13:37 +0530
Subject: Problem in using libraries
Message-ID: <CAJz1ufO+W7mM3zfhOyksBu6EtRSYGskYyhgv0do1T6LEjnYBpQ@mail.gmail.com>

Why can't I able to use python libraries such as numpy, nudenet, playsound,
pandas, etc in my python 3.11.2. It always through the error "import
'numpy' or any other libraries could not be resolved".

From barry at barrys-emacs.org  Mon Apr  3 13:05:16 2023
From: barry at barrys-emacs.org (Barry)
Date: Mon, 3 Apr 2023 18:05:16 +0100
Subject: Problem in using libraries
In-Reply-To: <CAJz1ufO+W7mM3zfhOyksBu6EtRSYGskYyhgv0do1T6LEjnYBpQ@mail.gmail.com>
References: <CAJz1ufO+W7mM3zfhOyksBu6EtRSYGskYyhgv0do1T6LEjnYBpQ@mail.gmail.com>
Message-ID: <50F3597C-722D-4909-8553-B90C9CF97EFF@barrys-emacs.org>



> On 3 Apr 2023, at 17:46, Pranav Bhardwaj <pranavbhardwaj773 at gmail.com> wrote:
> 
> ?Why can't I able to use python libraries such as numpy, nudenet, playsound,
> pandas, etc in my python 3.11.2. It always through the error "import
> 'numpy' or any other libraries could not be resolved".

You need to provide enough details for people to help you.

Include which OS you are using.
Where you got python from.
How you installed the libraries you are trying to use.
Commands and error messages you are seeing.

Barry


> -- 
> https://mail.python.org/mailman/listinfo/python-list
> 


From bowman at montana.com  Sat Apr  1 16:26:01 2023
From: bowman at montana.com (rbowman)
Date: 1 Apr 2023 20:26:01 GMT
Subject: Windows Gui Frontend
References: <027401d96491$7736dce0$65a496a0$.ref@sbcglobal.net>
 <027401d96491$7736dce0$65a496a0$@sbcglobal.net>
 <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <mailman.2501.1680363457.20444.python-list@python.org>
Message-ID: <k8riapF1ejnU1@mid.individual.net>

On Sat, 1 Apr 2023 10:37:34 -0500, Eryk Sun wrote:

> On 4/1/23, Jim Schwartz <jschwar at sbcglobal.net> wrote:
>> I have another question.  I have an app written in python, but I want
>> to add a windows GUI front end to it.  Can this be done in python? 
>> What packages would allow me to do that?
> 
> Here are a few of the GUI toolkit libraries in common use:
> 
>     * tkinter (Tk)
>     * PyQt (Qt)
>     * PySide (Qt)
>     * wxPython (wxWidgets)
>     * PyGObject (GTK)
> 
> tkinter is included in Python's standard library.

Not to go into a lot of history, if this is a commercial application, go 
with PySide rather than PyQt. They are very close, if not identical, until 
you get to licensing. 

From bowman at montana.com  Sat Apr  1 22:26:14 2023
From: bowman at montana.com (rbowman)
Date: 2 Apr 2023 02:26:14 GMT
Subject: Windows Gui Frontend
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
 <9660a85e-00bd-5c6c-6be0-de6f4b6c8615@tompassin.net>
 <b30a977a-ca32-83e6-409f-f0fdf913dc4c@tompassin.net>
 <CA+FnnTyVFrS1G=y5DT1HTtGgm8KWYOY=pFd-bP6xw8cxHiPxMQ@mail.gmail.com>
 <0A71B998-71D6-4E36-B551-5AA6824E7321@barrys-emacs.org>
 <e1bd85b5-575f-a921-5c1a-eec8aac99506@tompassin.net>
 <e4672e88-50b8-1844-c762-97c3bce53840@gmail.com>
 <mailman.2518.1680398363.20444.python-list@python.org>
Message-ID: <k8s7e6F3be4U9@mid.individual.net>

On Sat, 1 Apr 2023 19:19:17 -0600, Michael Torrie wrote:


> Qt's commerical licensing is very hostile to small companies, I can say
> that much.  It's too bad really.  But the LGPL will work for most
> companies, except for those that might wish to use the embedded version,
> such as in cars where being able to abide by the terms of the LGPL
> becomes difficult.

Even when the trolls had it the arcane requirements for commercial 
licensing drove many away. I sometimes think 'Side' is actually Finnish 
for 'up yours, Riverbank Computing'. 

From bowman at montana.com  Sun Apr  2 16:55:57 2023
From: bowman at montana.com (rbowman)
Date: 2 Apr 2023 20:55:57 GMT
Subject: Windows Gui Frontend
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
 <514b86e4-a956-cd9e-d45f-6dc0aee6d2a5@yahoo.co.uk>
 <fe7b3eec-3faf-c0ab-8196-d73ea5cc6e90@schwertberger.de>
 <dc374441-9ce1-3854-d70f-4847264a27bc@gmail.com>
 <3bf17b63-674c-9cdb-3d01-af2dc5e95da3@schwertberger.de>
 <cb46292c-abe2-70bc-dbb4-42ab329bde4f@gmail.com>
 <3c1e0abb-2bfb-33eb-5080-7b43c3f0cbec@schwertberger.de>
 <mailman.2526.1680457929.20444.python-list@python.org>
Message-ID: <k8u8etFel3hU1@mid.individual.net>

On Sun, 2 Apr 2023 19:52:05 +0200, Dietmar Schwertberger wrote:

> On 02.04.2023 18:20, Michael Torrie wrote:
>>> Well the thing is you don't need to generate Python code at all.  Qt
>>> provides a UI loader class that loads the UI file at run time, builds
>>> the objects in memory, and connects all your signals for you.
> 
> I know, but having to load the .ui file is awkward.
> Even worse, you lose things like code completion.

One advantage is customization. It's not Python but we use a GUI system 
that supports uids. The underlying data is the same but some clients may 
not want certain fields or want them labeled or arranged differently. 

From bowman at montana.com  Sun Apr  2 23:29:43 2023
From: bowman at montana.com (rbowman)
Date: 3 Apr 2023 03:29:43 GMT
Subject: Windows Gui Frontend
References: <CACL+1autFu+_eNHQt8P_ULC=p=yyAepe-etTvSCFjLOzsK2p4w@mail.gmail.com>
 <A29353BA-E20A-45A7-8408-A3AC7C2479BD@sbcglobal.net>
 <514b86e4-a956-cd9e-d45f-6dc0aee6d2a5@yahoo.co.uk>
 <fe7b3eec-3faf-c0ab-8196-d73ea5cc6e90@schwertberger.de>
 <dc374441-9ce1-3854-d70f-4847264a27bc@gmail.com>
 <6429eaa5.5d0a0220.85d9d.247e@mx.google.com>
 <mailman.2529.1680468663.20444.python-list@python.org>
Message-ID: <k8uvh7Fhml0U4@mid.individual.net>

On Sun, 02 Apr 2023 13:50:45 -0700 (PDT), Grant Edwards wrote:

> On 2023-04-02, Michael Torrie <torriem at gmail.com> wrote:
>> On 4/2/23 05:09, Dietmar Schwertberger wrote:
>>> I also did evaluate all the GUI builder from time to time between 2000
>>> and 2016 to find one that I could recommend to colleagues, but could
>>> not find one. Then I started contributing to wxGlade and I can say
>>> that since a few years it's as easy again to build GUIs as it was with
>>> VB6.
>>
>> [...]
>>
>> But any modern GUI toolkit has sizers and layout managers. If you're
>> manually placing elements you cannot deal with HiDPI or changing window
>> sizes.
> 
> Ah, that's the brilliant thing about VB6 apps! They only work properly
> on machines with the same resoultion and display/font configuration as
> the developer.

VB6 isn't the only thing that goes to hell in a hand basket when you start 
playing around with fonts and resolutions. If I were emperor of the world 
there would only be monospaced fonts and a limited selection of those.

From andreas.eisele at gmail.com  Sat Apr  1 11:16:46 2023
From: andreas.eisele at gmail.com (Andreas Eisele)
Date: Sat, 1 Apr 2023 08:16:46 -0700 (PDT)
Subject: built-in pow() vs. math.pow()
In-Reply-To: <831c6c1c-c4ee-4a59-bba8-d8c2df0e982cn@googlegroups.com>
References: <831c6c1c-c4ee-4a59-bba8-d8c2df0e982cn@googlegroups.com>
Message-ID: <f1b36be4-55d9-4aeb-b0b6-90ba7144b19en@googlegroups.com>

Andreas Eisele schrieb am Donnerstag, 30. M?rz 2023 um 11:16:02 UTC+2:
> I sometimes make use of the fact that the built-in pow() function has an optional third argument for modulo calculation, which is handy when dealing with tasks from number theory, very large numbers, problems from Project Euler, etc. I was unpleasantly surprised that math.pow() does not have this feature, hence "from math import *" overwrites the built-in pow() function with a function that lacks functionality. I am wondering for the rationale of this. Does math.pow() do anything that the built-in version can not do, and if not, why is it even there? 
> Thanks in advance for any enlightening comment on this. 
> Best regards, Andreas

Thanks a lot to all of you for the insightful replies! 
I now understand why math.pow() behaves the way it does and whoever tells me I should have read the doc of the math module before using it is 100% on point. 
BTW, there is another difference: built-in pow() deals with complex arguments, while functions in math won't accept them at all.
I also agree with the warning that importing * from any module is generally a bad idea, and I normally would not do it.  But here I had written a little tool that evaluates an expression given on the command line, and in this case having math functions available without further ado is very convenient, so it seemed appropriate to make an exeption to this rule.
I ended up assigning the built-in pow function to a different name before importing the math module, which is a good way to keep both variants accessible.
Best regards, and thanks again, Andreas

From skip.montanaro at gmail.com  Sat Apr  1 14:19:54 2023
From: skip.montanaro at gmail.com (Skip Montanaro)
Date: Sat, 1 Apr 2023 13:19:54 -0500
Subject: Small lament...
Message-ID: <CANc-5Uz0_ESeo1NY-VUXd_YB=gnkp53ofSbghEzfpOXQNf11ug@mail.gmail.com>

Just wanted to throw this out there... I lament the loss of waking up on
April 1st to see a creative April Fool's Day joke on one or both of these
lists, often from our FLUFL... Maybe such frivolity still happens, just not in
the Python ecosystem? I know you can still import "this" or "antigravity",
but those are now old (both introduced before 2010). When was the last time
a clever easter egg was introduced or an April Fool's Day joke played?

?\_(?)_/?

Skip

From jfong at ms4.hinet.net  Sat Apr  1 22:12:58 2023
From: jfong at ms4.hinet.net (Jach Feng)
Date: Sat, 1 Apr 2023 19:12:58 -0700 (PDT)
Subject: Windows Gui Frontend
In-Reply-To: <mailman.2497.1680350398.20444.python-list@python.org>
References: <AdlkkUjJgJTzo4kuRLCJVFRmFSG/2w==>
 <027401d96491$7736dce0$65a496a0$.ref@sbcglobal.net>
 <027401d96491$7736dce0$65a496a0$@sbcglobal.net>
 <mailman.2497.1680350398.20444.python-list@python.org>
Message-ID: <eea5fbbc-d452-42ab-b3c3-9ef9f6fb674en@googlegroups.com>

Jim Schwartz ? 2023?4?1? ?????8:00:19 [UTC+8] ??????
> I have another question. I have an app written in python, but I want to add 
> a windows GUI front end to it. Can this be done in python? What packages 
> would allow me to do that? 
> 
> 
> 
> Thanks.
There is a GUI Generator for tkinter
https://page.sourceforge.net/

--Jach

From aewindhorn at gmail.com  Sun Apr  2 15:05:04 2023
From: aewindhorn at gmail.com (windhorn)
Date: Sun, 2 Apr 2023 12:05:04 -0700 (PDT)
Subject: Python file location
In-Reply-To: <87355mpxrc.fsf@debian-BULLSEYE-live-builder-AMD64>
References: <4f75241c-3396-4b0d-a3c8-92895aaf3ef9n@googlegroups.com>
 <87355mpxrc.fsf@debian-BULLSEYE-live-builder-AMD64>
Message-ID: <56ad2eea-abe6-4a9a-8e09-bedfc74ce98an@googlegroups.com>

Thanks to all for suggestions.  Linux has "too much freedom" :-)

Regards,
Allen

From garyfallidis at gmail.com  Sun Apr  2 21:35:34 2023
From: garyfallidis at gmail.com (Eleftherios Garyfallidis)
Date: Sun, 2 Apr 2023 21:35:34 -0400
Subject: Hurry up! Book your spot for the DIPY Workshop in LA! April 24-28
 2023!!
Message-ID: <CAN6JmWPjAnPT46Fc3N=y-EK+4GT7yM8HLgk+GW5LVmTYH7P8tw@mail.gmail.com>

Dear all,

Only a few spots are left. Register now: https://dipy.org/workshops/latest
 !!!

The complete program for the highly anticipated workshop is updated and
available in the link above.


DIPY is a powerful software library for analyzing and processing diffusion
MRI data. It is an open-source project with a large and active
community of contributors who are dedicated to advancing the field of
medical imaging. The DIPY workshop provides an excellent opportunity
for individuals to learn how to use this software effectively. The workshop
covers a broad range of topics, from basic concepts to advanced
techniques, and provides hands-on experience with the software. By
attending the DIPY workshop, you will not only learn how to use this
powerful tool, but also gain a deeper understanding of diffusion imaging
and machine learning for imaging in general. The workshop is led by
expert instructors who have extensive experience in both diffusion imaging
and DIPY, so attendees can be confident that they are receiving
accurate and up-to-date information.



[image: image.png]



In summary, the workshop offers:


   -

   Hands-on tutorials - Every single day of the 5 days !!!
   -

   Guided practice sessions (bring your data - optional)
   -

   Personalized certificates of attendance
   -

   Effective networking opportunities with one-to-one follow ups
   -

   Comprehensive explanation of theoretical foundations with practical
   examples
   -

   Access to latest and established methods with code and interfaces
   -

   Pointers to move beyond the current challenges and navigate hard to do
   analyses
   -

   Multiple clinical use cases (AZ, Parkinson?s etc.)





See above one of the many highlights of the workshop. Building synthetic
b0s (with Synb0) in DIPY 1.7.0!  More highlights here
<https://dipy.org/workshops/dipy-workshop-2023#Highlight>.

Please allow us to finish this email with a testimonial from one of our
last in person workshops:

This one is from an expert neuropsychologist:

?In recent years, I've found that many scientific conferences have become
plagued with pitfalls such as repetitive content, superficial networking,
and a focus

on self-promotion rather than genuine knowledge exchange. Attendees often
leave these events with a sense of disillusionment, feeling that their time
could

have been better spent elsewhere. The DIPY workshop, however, was a breath
of fresh air in this sea of mediocrity. It was highly interactive,
engaging, and

hands-on, with a genuine emphasis on learning and collaboration. The
organizers went above and beyond to create a welcoming and supportive
environment,

encouraging researchers of all backgrounds and expertise levels to
contribute their ideas and gain valuable insights. By addressing the
shortcomings of

traditional conferences, the DIPY workshop has rekindled my enthusiasm for
scientific events and has set a new standard for what a truly productive
and

inspiring gathering should be.?

We kept our promise! Get your tickets!

See you in the workshop!

Eleftherios Garyfallidis, PhD

Associate Professor

Intelligent Systems Engineering

Indiana University

Luddy Hall 700 N Woodlawn

Bloomington, IN 47408

DIPY <http://dipy.org/> | FURY <https://fury.gl/>

From list1 at tompassin.net  Mon Apr  3 13:25:48 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Mon, 3 Apr 2023 13:25:48 -0400
Subject: Problem in using libraries
In-Reply-To: <CAJz1ufO+W7mM3zfhOyksBu6EtRSYGskYyhgv0do1T6LEjnYBpQ@mail.gmail.com>
References: <CAJz1ufO+W7mM3zfhOyksBu6EtRSYGskYyhgv0do1T6LEjnYBpQ@mail.gmail.com>
Message-ID: <1f02be62-1a33-72dc-e259-5c24be15801a@tompassin.net>

On 4/3/2023 12:43 PM, Pranav Bhardwaj wrote:
> Why can't I able to use python libraries such as numpy, nudenet, playsound,
> pandas, etc in my python 3.11.2. It always through the error "import
> 'numpy' or any other libraries could not be resolved".

You need to realize that no one can help you without some specific 
information.  You have not told us anything.  You might as well have 
said, if your car didn't start, "My car won't run.  Why can't I start it?.

Let's start with the most obvious thing - are those libraries installed? 
  If not, install them.  If you think they have been installed, then 
tell us how you installed them and how you know they have been 
successfully installed *for the version of python* you are trying to use.

Let's take numpy. The standard way to install it is using pip.  You have 
to make sure that you run the pip program that goes with the version of 
Python you plan to use.  I'm going to assume that if you type "py" 
(without quotes), you will get that version.  If not, use the command 
you have been using to run Python 3.11.

On my system:

C:\Users\tom>py -V
Python 3.10.9

C:\Users\tom>py -m pip show numpy
Name: numpy
Version: 1.23.4
Summary: NumPy is the fundamental package for array computing with Python.
Home-page: https://www.numpy.org
Author: Travis E. Oliphant et al.
Author-email:
License: BSD
Location: 
c:\users\tom\appdata\local\programs\python\python310\lib\site-packages
Requires:
Required-by: bokeh, causal-curve, cftime, contourpy, csaps, dcor, emd, 
frechetdist, imageio, localreg, matplotlib, mizani, netCDF4, numba, 
pandas, patsy, plotnine, pwlf, pyDOE, pygam, PyWavelets, scaleogram, 
scikit-image, scikit-learn, scipy, seaborn, sparse, statsforecast, 
statsmodels, tifffile

If a library is not installed (I'll use a non-existent library name) -

C:\Users\tom>py -m pip show numpyx
WARNING: Package(s) not found: numpyx

To install numpy with pip *for that version of Python* -

py -m pip install numpy   (or a form you may see sometimes: py -m 
install --user numpy)

Please reply with this information.

From 2QdxY4RzWzUUiLuE at potatochowder.com  Mon Apr  3 15:49:45 2023
From: 2QdxY4RzWzUUiLuE at potatochowder.com (2QdxY4RzWzUUiLuE at potatochowder.com)
Date: Mon, 3 Apr 2023 15:49:45 -0400
Subject: built-in pow() vs. math.pow()
In-Reply-To: <f1b36be4-55d9-4aeb-b0b6-90ba7144b19en@googlegroups.com>
References: <831c6c1c-c4ee-4a59-bba8-d8c2df0e982cn@googlegroups.com>
 <f1b36be4-55d9-4aeb-b0b6-90ba7144b19en@googlegroups.com>
Message-ID: <ZCst2Sqe1eK21LHT@anomaly>

On 2023-04-01 at 08:16:46 -0700,
Andreas Eisele <andreas.eisele at gmail.com> wrote:

> BTW, there is another difference: built-in pow() deals with complex
> arguments, while functions in math won't accept them at all.

See also <https://docs.python.org/3/library/cmath.html>.

From pranavbhardwaj773 at gmail.com  Mon Apr  3 13:25:55 2023
From: pranavbhardwaj773 at gmail.com (pranavbhardwaj773 at gmail.com)
Date: Mon, 3 Apr 2023 22:55:55 +0530
Subject: problems in using libraries
Message-ID: <2C2C8CB8-F09B-44B7-BA2C-CA9096CF0ACB@hxcore.ol>

   ?

   ?

   Sent from [1]Mail for Windows

   Why can't I able to use python libraries in my python 3.11.2. It always
   throw an error such as ?

   and

   and many more.

   I installed python from python official website and I installed libraries
   using cmd prompt by typing- pip install ?Library name?

References

   Visible links
   1. https://go.microsoft.com/fwlink/?LinkId=550986

From guido at python.org  Mon Apr  3 20:14:36 2023
From: guido at python.org (Guido van Rossum)
Date: Mon, 3 Apr 2023 17:14:36 -0700
Subject: [Python-Dev] Small lament...
In-Reply-To: <CANc-5Uz0_ESeo1NY-VUXd_YB=gnkp53ofSbghEzfpOXQNf11ug@mail.gmail.com>
References: <CANc-5Uz0_ESeo1NY-VUXd_YB=gnkp53ofSbghEzfpOXQNf11ug@mail.gmail.com>
Message-ID: <CAP7+vJKgaX4aT26wRjsxLRSjdLPrhGkYsPRWUzKxzaa68ULXFQ@mail.gmail.com>

A bit late, this reached my inbox:
https://peternorvig.medium.com/new-python-operators-9f31b56ddcc7

On Sat, Apr 1, 2023 at 11:23?AM Skip Montanaro <skip.montanaro at gmail.com>
wrote:

> Just wanted to throw this out there... I lament the loss of waking up on
> April 1st to see a creative April Fool's Day joke on one or both of these
> lists, often from our FLUFL... Maybe such frivolity still happens, just not in
> the Python ecosystem? I know you can still import "this" or
> "antigravity", but those are now old (both introduced before 2010). When
> was the last time a clever easter egg was introduced or an April Fool's Day
> joke played?
>
> ?\_(?)_/?
>
> Skip
>
> _______________________________________________
> Python-Dev mailing list -- python-dev at python.org
> To unsubscribe send an email to python-dev-leave at python.org
> https://mail.python.org/mailman3/lists/python-dev.python.org/
> Message archived at
> https://mail.python.org/archives/list/python-dev at python.org/message/Q62W2Q6R6XMX57WK2CUGEENHMT3C3REF/
> Code of Conduct: http://python.org/psf/codeofconduct/
>


-- 
--Guido van Rossum (python.org/~guido)
*Pronouns: he/him **(why is my pronoun here?)*
<http://feministing.com/2015/02/03/how-using-they-as-a-singular-pronoun-can-change-the-world/>

From barry at python.org  Mon Apr  3 20:31:29 2023
From: barry at python.org (Barry Warsaw)
Date: Mon, 3 Apr 2023 17:31:29 -0700
Subject: [Python-Dev] Small lament...
In-Reply-To: <CANc-5Uz0_ESeo1NY-VUXd_YB=gnkp53ofSbghEzfpOXQNf11ug@mail.gmail.com>
References: <CANc-5Uz0_ESeo1NY-VUXd_YB=gnkp53ofSbghEzfpOXQNf11ug@mail.gmail.com>
Message-ID: <B982DFFA-4AD2-45E3-A792-BD52823C131A@python.org>

I heard it on reasonably believable authority that the FLUFL took the year off.  Lamentable.

-Barry

> On Apr 1, 2023, at 11:19, Skip Montanaro <skip.montanaro at gmail.com> wrote:
> 
> Just wanted to throw this out there... I lament the loss of waking up on April 1st to see a creative April Fool's Day joke on one or both of these lists, often from our FLUFL... Maybe such frivolity still happens, just not in the Python ecosystem? I know you can still import "this" or "antigravity", but those are now old (both introduced before 2010). When was the last time a clever easter egg was introduced or an April Fool's Day joke played?
> 
> ?\_(?)_/?
> 
> Skip
> 
> _______________________________________________
> Python-Dev mailing list -- python-dev at python.org
> To unsubscribe send an email to python-dev-leave at python.org
> https://mail.python.org/mailman3/lists/python-dev.python.org/
> Message archived at https://mail.python.org/archives/list/python-dev at python.org/message/Q62W2Q6R6XMX57WK2CUGEENHMT3C3REF/
> Code of Conduct: http://python.org/psf/codeofconduct/

-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 833 bytes
Desc: Message signed with OpenPGP
URL: <https://mail.python.org/pipermail/python-list/attachments/20230403/1daa1b82/attachment.sig>

From avi.e.gross at gmail.com  Mon Apr  3 22:09:02 2023
From: avi.e.gross at gmail.com (avi.e.gross at gmail.com)
Date: Mon, 3 Apr 2023 22:09:02 -0400
Subject: [Python-Dev] Small lament...
In-Reply-To: <B982DFFA-4AD2-45E3-A792-BD52823C131A@python.org>
References: <CANc-5Uz0_ESeo1NY-VUXd_YB=gnkp53ofSbghEzfpOXQNf11ug@mail.gmail.com>
 <B982DFFA-4AD2-45E3-A792-BD52823C131A@python.org>
Message-ID: <003801d9669a$6d8a09a0$489e1ce0$@gmail.com>

Sadly, between Daylight Savings time and a  newer irrational PI ? Day, I am afraid some April Foolers got thrown off albeit some may shower us with nonsense  in May I.

-----Original Message-----
From: Python-list <python-list-bounces+avi.e.gross=gmail.com at python.org> On Behalf Of Barry Warsaw
Sent: Monday, April 3, 2023 8:31 PM
To: Skip Montanaro <skip.montanaro at gmail.com>
Cc: Python <python-list at python.org>; Python Dev <python-dev at python.org>
Subject: Re: [Python-Dev] Small lament...

I heard it on reasonably believable authority that the FLUFL took the year off.  Lamentable.

-Barry

> On Apr 1, 2023, at 11:19, Skip Montanaro <skip.montanaro at gmail.com> wrote:
> 
> Just wanted to throw this out there... I lament the loss of waking up on April 1st to see a creative April Fool's Day joke on one or both of these lists, often from our FLUFL... Maybe such frivolity still happens, just not in the Python ecosystem? I know you can still import "this" or "antigravity", but those are now old (both introduced before 2010). When was the last time a clever easter egg was introduced or an April Fool's Day joke played?
> 
> ?\_(?)_/?
> 
> Skip
> 
> _______________________________________________
> Python-Dev mailing list -- python-dev at python.org
> To unsubscribe send an email to python-dev-leave at python.org
> https://mail.python.org/mailman3/lists/python-dev.python.org/
> Message archived at https://mail.python.org/archives/list/python-dev at python.org/message/Q62W2Q6R6XMX57WK2CUGEENHMT3C3REF/
> Code of Conduct: http://python.org/psf/codeofconduct/



From list1 at tompassin.net  Mon Apr  3 22:16:44 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Mon, 3 Apr 2023 22:16:44 -0400
Subject: problems in using libraries
In-Reply-To: <2C2C8CB8-F09B-44B7-BA2C-CA9096CF0ACB@hxcore.ol>
References: <2C2C8CB8-F09B-44B7-BA2C-CA9096CF0ACB@hxcore.ol>
Message-ID: <9ca67f8b-9fc7-3d99-716f-79f3d53a4b1c@tompassin.net>

On 4/3/2023 1:25 PM, pranavbhardwaj773 at gmail.com wrote:
>      
> 
>      
> 
>     Sent from [1]Mail for Windows
> 
>     Why can't I able to use python libraries in my python 3.11.2. It always
>     throw an error such as
> 
>     and
> 
>     and many more.
> 
>     I installed python from python official website and I installed libraries
>     using cmd prompt by typing- pip install ?Library name?
You have not done what I suggested that you do in my last post.  As I 
recall from earlier messages, you have several versions of Python 
installed.  You have to be sure that when you run "pip" it is being run 
by the version of Python that you want.  I asked you to check that and 
gave you examples of how.

So please do that.


From PythonList at DancesWithMice.info  Mon Apr  3 22:30:47 2023
From: PythonList at DancesWithMice.info (dn)
Date: Tue, 4 Apr 2023 14:30:47 +1200
Subject: [Python-Dev] Small lament...
In-Reply-To: <CAP7+vJKgaX4aT26wRjsxLRSjdLPrhGkYsPRWUzKxzaa68ULXFQ@mail.gmail.com>
References: <CANc-5Uz0_ESeo1NY-VUXd_YB=gnkp53ofSbghEzfpOXQNf11ug@mail.gmail.com>
 <CAP7+vJKgaX4aT26wRjsxLRSjdLPrhGkYsPRWUzKxzaa68ULXFQ@mail.gmail.com>
Message-ID: <813ab8ad-3aae-59cf-acd5-b7b5e144852a@DancesWithMice.info>

On 04/04/2023 12.14, Guido van Rossum wrote:
> A bit late, this reached my inbox:
> https://peternorvig.medium.com/new-python-operators-9f31b56ddcc7

Did you notice that Peter Norvig's factorial-operator attempts to 
replace one of the very first diamond-grade provisions of [the] FLUFL?

Disgraceful behavior! So disrespectful!

Send him to the Spanish Inquisition...


Saying that, he (Peter) lost the opportunity to promote our new 
dev.movement. As he pointed-out, tests are likely to give one a false 
sense of security with regard to the correctness of code.

Accordingly, join us in the noTDD philosophy. Like NoSQL is schema-less, 
noTDD is scheme-less (we have NO idea what we're doing).

Don't be led-astray by tests. We're all [adult-]optimists here...


> On Sat, Apr 1, 2023 at 11:23?AM Skip Montanaro <skip.montanaro at gmail.com>
> wrote:
> 
>> Just wanted to throw this out there... I lament the loss of waking up on
>> April 1st to see a creative April Fool's Day joke on one or both of these
>> lists, often from our FLUFL... Maybe such frivolity still happens, just not in
>> the Python ecosystem? I know you can still import "this" or
>> "antigravity", but those are now old (both introduced before 2010). When
>> was the last time a clever easter egg was introduced or an April Fool's Day
>> joke played?
>>
>> ?\_(?)_/?
>>
>> Skip
>>
>> _______________________________________________
>> Python-Dev mailing list -- python-dev at python.org
>> To unsubscribe send an email to python-dev-leave at python.org
>> https://mail.python.org/mailman3/lists/python-dev.python.org/
>> Message archived at
>> https://mail.python.org/archives/list/python-dev at python.org/message/Q62W2Q6R6XMX57WK2CUGEENHMT3C3REF/
>> Code of Conduct: http://python.org/psf/codeofconduct/
>>
> 
> 

-- 
Regards,
=dn

From greg.ewing at canterbury.ac.nz  Tue Apr  4 04:22:50 2023
From: greg.ewing at canterbury.ac.nz (Greg Ewing)
Date: Tue, 4 Apr 2023 20:22:50 +1200
Subject: [Python-Dev] Small lament...
In-Reply-To: <mailman.2542.1680574147.20444.python-list@python.org>
References: <CANc-5Uz0_ESeo1NY-VUXd_YB=gnkp53ofSbghEzfpOXQNf11ug@mail.gmail.com>
 <B982DFFA-4AD2-45E3-A792-BD52823C131A@python.org>
 <003801d9669a$6d8a09a0$489e1ce0$@gmail.com>
 <mailman.2542.1680574147.20444.python-list@python.org>
Message-ID: <k9252tF2gpkU1@mid.individual.net>

On 4/04/23 2:09 pm, avi.e.gross at gmail.com wrote:
> Sadly, between Daylight Savings time and a  newer irrational PI ? Day, I am afraid some April Foolers got thrown off albeit some may shower us with nonsense  in May I.

Pi day isn't responsible, but it is because of changes to daylight
saving. The International Bureau of Weights and Measures announced
that, in order to gain a few more days of summer weather, all clocks
would be put back by 96 hours at midnight on 31 March 2023. So April 1
is now occurring on what would have been April 4. Expect the usual
torrent of silliness to arrive shortly.

-- 
Greg

From ssfirodia at gmail.com  Tue Apr  4 07:44:19 2023
From: ssfirodia at gmail.com (Sumeet Firodia)
Date: Tue, 4 Apr 2023 17:14:19 +0530
Subject: Python not showing correct version
In-Reply-To: <CACL+1atR2TinU7LY=4kCo14T8AoeWiE5VVXrhcRiZmN_pNHdQg@mail.gmail.com>
References: <CANvxP8M8nPBCm2cehEG1UahP=SoOHiZYpazY_pmXhtUWsOYS6g@mail.gmail.com>
 <CANvxP8M89NK+QY2YodnjZmojUMFOnwVSVT27mLgKh-jXgv4AMw@mail.gmail.com>
 <D26A4D1C-EF05-4C9D-9E52-8DD3148FCA4F@barrys-emacs.org>
 <CANvxP8PNFGFx7x7nSH-DyrCD+1F7=fH-aGjMPm1uPWnqFY7J4g@mail.gmail.com>
 <CACL+1avZZxOQMJ78QNMFZJCKgNEHMBkUxfuyA0f+PW7g-7-kkg@mail.gmail.com>
 <34dcfb4d-28ed-0d26-8816-826fd63c1848@tompassin.net>
 <CACL+1avoH4YT6eTH4bpSPPKpAK7X2ciX+FpQ_PR-6sU_Py4+fg@mail.gmail.com>
 <4F251711-2F64-4B29-8E23-16E792C23009@barrys-emacs.org>
 <CACL+1atR2TinU7LY=4kCo14T8AoeWiE5VVXrhcRiZmN_pNHdQg@mail.gmail.com>
Message-ID: <CANvxP8P9hpMpzHpmFBOD5tq8m76uktMiYaOjME34J4POLjM7DA@mail.gmail.com>

So I disabled the manage app execution for python 3.10, created the py.ini
file and executed   setx.exe PY_PYTHON 3.8,    setx.exe PY_PYTHON3 3.8.
After that i uninstalled 3.8 and reinstalled and now the version is showing
correctly.

Thanks everyone for the help.

Thanks
Sumeet

On Sat, 1 Apr 2023 at 20:40, Eryk Sun <eryksun at gmail.com> wrote:

> On 4/1/23, Barry Scott <barry at barrys-emacs.org> wrote:
> >
> > I find user environment on windows to be less flexible to work with then
> > adding a py.ini. On my Windows 11 I added
> > %userprofile%\AppData\Local\py.ini.
> > To make python 3.8 the default that py.exe uses put this in py.ini:
> >
> > [defaults]
> > python=3.8-64
> > python3=3.8-64
>
> Using "py.ini" has the advantage that launcher always reads the file.
> The value of the environment variables, on the other hand, may be
> stale. If you keep a lot of shells running, it would be tedious to
> have to manually update the PY_PYTHON* variables in each shell. That
> said, it should be rare that one needs to change the persisted default
> versions. For temporary changes, the PY_PYTHON* environment variables
> are more flexible and take precedence over "py.ini".
>
> If one doesn't use "py.ini" to set the defaults, it's easy to modify
> the persisted user environment using "setx.exe"[^1]. For example:
>
>     setx.exe PY_PYTHON 3.8
>     setx.exe PY_PYTHON3 3.8
>
> setx.exe broadcasts a WM_SETTINGCHANGE "Environment" window message,
> which causes Explorer to update its environment. Thus any program run
> from Explorer will see the new values. A program launched in a new tab
> in Windows Terminal also gets a fresh environment. However, existing
> CLI shells (CMD, PowerShell, bash), and programs started by them, will
> still have the old environment values. The latter is where using
> "py.ini" to set the defaults has the advantage.
>
> ---
>
> [^1]: Note that "setx.exe" should never be used to set the persisted
> user or machine "Path" value to the current %PATH%. When loading the
> environment, the user "Path" gets appended to the machine "Path".
> Setting the entire expanded and concatenated value to one or the other
> leads to a bloated, redundant PATH value, and it also loses the
> flexible configuration based on REG_EXPAND_SZ values.
> --
> https://mail.python.org/mailman/listinfo/python-list
>

From jschwar at sbcglobal.net  Tue Apr  4 11:25:34 2023
From: jschwar at sbcglobal.net (Jim Schwartz)
Date: Tue, 4 Apr 2023 10:25:34 -0500
Subject: Windows installer from python source code without access to
 source code
In-Reply-To: <CACL+1au+QFp=nLPM4AQcUBntN_3u80cgWc9cFGsi-_OyW44grA@mail.gmail.com>
References: <01fd01d963c8$547e9090$fd7bb1b0$.ref@sbcglobal.net>
 <01fd01d963c8$547e9090$fd7bb1b0$@sbcglobal.net>
 <CACL+1au+QFp=nLPM4AQcUBntN_3u80cgWc9cFGsi-_OyW44grA@mail.gmail.com>
Message-ID: <01a501d96709$b3f86f70$1be94e50$@sbcglobal.net>

Where can I download that cl program?  I've used gcc before, but I hear that cl can use a setup.py program to run the compile and link and create a windows .msi installer.  Is that true?  

-----Original Message-----
From: Eryk Sun <eryksun at gmail.com> 
Sent: Friday, March 31, 2023 12:55 PM
To: Jim Schwartz <jschwar at sbcglobal.net>
Cc: python-list at python.org
Subject: Re: Windows installer from python source code without access to source code

On 3/31/23, Jim Schwartz <jschwar at sbcglobal.net> wrote:
> I want a windows installer to install my application that's written in 
> python, but I don't want the end user to have access to my source code.

Cython can compile a script to C source code for a module or executable (--embed). The source can be compiled and linked normally.
For example, the following builds a "hello.exe" executable based on a "hello.py" script.

    > cython -3 --embed hello.py
    > set "PYI=C:\Program Files\Python311\include"
    > set "PYL=C:\Program Files\Python311\libs"
    > cl /I"%PYI%" hello.c /link /libpath:"%PYL%"
    > copy hello.exe embed
    > embed\hello.exe
    Hello, World!

I extracted the complete embeddable distribution of Python 3.11 into the "embed" directory. You can reduce the size of the installation, if needed, by minimizing the zipped standard library and removing pyd extensions and DLLs that your application doesn't use.

The generated "hello.c" is large and not particularly easy to read, but here are some snippets [...]:

    [...]
    /* Implementation of 'hello' */
    static PyObject *__pyx_builtin_print;
    static const char __pyx_k_main[] = "__main__";
    static const char __pyx_k_name[] = "__name__";
    static const char __pyx_k_test[] = "__test__";
    static const char __pyx_k_print[] = "print";
    static const char __pyx_k_Hello_World[] = "Hello, World!";
    [...]
      /* "hello.py":1
     * print("Hello, World!")             # <<<<<<<<<<<<<<
     */
      __pyx_tuple_ = PyTuple_Pack(1, __pyx_kp_u_Hello_World);
            if (unlikely(!__pyx_tuple_)) __PYX_ERR(0, 1, __pyx_L1_error)
    [...]
      /* "hello.py":1
     * print("Hello, World!")             # <<<<<<<<<<<<<<
     */
      __pyx_t_1 = __Pyx_PyObject_Call(__pyx_builtin_print, __pyx_tuple_,
                                      NULL);
            if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 1, __pyx_L1_error)
    [...]
    int wmain(int argc, wchar_t **argv) {
    [...]
        if (argc && argv)
            Py_SetProgramName(argv[0]);
        Py_Initialize();
        if (argc && argv)
            PySys_SetArgv(argc, argv);
    [...]
              m = PyInit_hello();
    [...]
        if (Py_FinalizeEx() < 0)
            return 2;
    [...]
        return 0;
    [...]


From loris.bennett at fu-berlin.de  Tue Apr  4 07:58:24 2023
From: loris.bennett at fu-berlin.de (Loris Bennett)
Date: Tue, 04 Apr 2023 13:58:24 +0200
Subject: When is logging.getLogger(__name__) needed?
References: <877cux2hy0.fsf@hornfels.zedat.fu-berlin.de>
 <3783122a-28d9-776d-b4d1-979cb1d3ac1d@web.de>
 <mailman.2474.1680276873.20444.python-list@python.org>
Message-ID: <87edozamfz.fsf@debian-BULLSEYE-live-builder-AMD64>

Peter Otten <__peter__ at web.de> writes:

> On 31/03/2023 15:01, Loris Bennett wrote:
[snip (53 lines)]

> Your problem has nothing to do with logging -- it's about visibility
> ("scope") of names:
>
>>>> def use_name():
> 	print(name)
>
>
>>>> def define_name():
> 	name = "Loris"
>
>
>>>> use_name()
> Traceback (most recent call last):
>   File "<pyshell#56>", line 1, in <module>
>     use_name()
>   File "<pyshell#52>", line 2, in use_name
>     print(name)
> NameError: name 'name' is not defined
>
> Binding (=assigning to) a name inside a function makes it local to that
> function. If you want a global (module-level) name you have to say so:
>
>>>> def define_name():
> 	global name
> 	name = "Peter"
>
>
>>>> define_name()
>>>> use_name()
> Peter

Thanks for the example and reminding me about Python's scopes.

With

    global name

    def use_name():
        print(name)

    def define_name():
        name = "Peter"

    define_name()
    use_name()

I was initially surprised by the following error:

    ~/tmp $ python3 global.py 
    Traceback (most recent call last):
      File "/home/loris/tmp/global.py", line 10, in <module>
        use_name()
      File "/home/loris/tmp/global.py", line 4, in use_name
        print(name)
    NameError: name 'name' is not defined

but I was misinterpreting 

  global name

to mean

  define a global variable 'name'

whereas it actually seems to mean more like

  use the global variable 'name'

Correct?

-- 
This signature is currently under constuction.

From dieter at handshake.de  Tue Apr  4 13:32:24 2023
From: dieter at handshake.de (Dieter Maurer)
Date: Tue, 4 Apr 2023 19:32:24 +0200
Subject: Problem in using libraries
In-Reply-To: <CAJz1ufO+W7mM3zfhOyksBu6EtRSYGskYyhgv0do1T6LEjnYBpQ@mail.gmail.com>
References: <CAJz1ufO+W7mM3zfhOyksBu6EtRSYGskYyhgv0do1T6LEjnYBpQ@mail.gmail.com>
Message-ID: <25644.24360.366268.46518@ixdm.fritz.box>

Pranav Bhardwaj wrote at 2023-4-3 22:13 +0530:
>Why can't I able to use python libraries such as numpy, nudenet, playsound,
>pandas, etc in my python 3.11.2. It always through the error "import
>'numpy' or any other libraries could not be resolved".

The "libraries" you speak of are extensions (i.e. not part of
the Python download).

Extensions are Python minor version specific.
You must install them for each Python minor version.
E.g. you can use an extension installation for Python 3.10 for
any Python 3.10.x,
but you must install it again for Python 3.11.

From barry at barrys-emacs.org  Tue Apr  4 14:25:24 2023
From: barry at barrys-emacs.org (Barry)
Date: Tue, 4 Apr 2023 19:25:24 +0100
Subject: Windows installer from python source code without access to
 source code
In-Reply-To: <01a501d96709$b3f86f70$1be94e50$@sbcglobal.net>
References: <01a501d96709$b3f86f70$1be94e50$@sbcglobal.net>
Message-ID: <79F9B803-CE16-418C-B5CA-E88155DD42C5@barrys-emacs.org>



> On 4 Apr 2023, at 16:28, Jim Schwartz <jschwar at sbcglobal.net> wrote:
> 
> ?Where can I download that cl program?  I've used gcc before, but I hear that cl can use a setup.py program to run the compile and link and create a windows .msi installer.  Is that true?  

It is part of visual studio C++.
Once you have that installed there are bat files that setup environment in the terminal.
Then you can use cl, nmake etc

Barry
> 
> -----Original Message-----
> From: Eryk Sun <eryksun at gmail.com> 
> Sent: Friday, March 31, 2023 12:55 PM
> To: Jim Schwartz <jschwar at sbcglobal.net>
> Cc: python-list at python.org
> Subject: Re: Windows installer from python source code without access to source code
> 
>> On 3/31/23, Jim Schwartz <jschwar at sbcglobal.net> wrote:
>> I want a windows installer to install my application that's written in 
>> python, but I don't want the end user to have access to my source code.
> 
> Cython can compile a script to C source code for a module or executable (--embed). The source can be compiled and linked normally.
> For example, the following builds a "hello.exe" executable based on a "hello.py" script.
> 
>> cython -3 --embed hello.py
>> set "PYI=C:\Program Files\Python311\include"
>> set "PYL=C:\Program Files\Python311\libs"
>> cl /I"%PYI%" hello.c /link /libpath:"%PYL%"
>> copy hello.exe embed
>> embed\hello.exe
>    Hello, World!
> 
> I extracted the complete embeddable distribution of Python 3.11 into the "embed" directory. You can reduce the size of the installation, if needed, by minimizing the zipped standard library and removing pyd extensions and DLLs that your application doesn't use.
> 
> The generated "hello.c" is large and not particularly easy to read, but here are some snippets [...]:
> 
>    [...]
>    /* Implementation of 'hello' */
>    static PyObject *__pyx_builtin_print;
>    static const char __pyx_k_main[] = "__main__";
>    static const char __pyx_k_name[] = "__name__";
>    static const char __pyx_k_test[] = "__test__";
>    static const char __pyx_k_print[] = "print";
>    static const char __pyx_k_Hello_World[] = "Hello, World!";
>    [...]
>      /* "hello.py":1
>     * print("Hello, World!")             # <<<<<<<<<<<<<<
>     */
>      __pyx_tuple_ = PyTuple_Pack(1, __pyx_kp_u_Hello_World);
>            if (unlikely(!__pyx_tuple_)) __PYX_ERR(0, 1, __pyx_L1_error)
>    [...]
>      /* "hello.py":1
>     * print("Hello, World!")             # <<<<<<<<<<<<<<
>     */
>      __pyx_t_1 = __Pyx_PyObject_Call(__pyx_builtin_print, __pyx_tuple_,
>                                      NULL);
>            if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 1, __pyx_L1_error)
>    [...]
>    int wmain(int argc, wchar_t **argv) {
>    [...]
>        if (argc && argv)
>            Py_SetProgramName(argv[0]);
>        Py_Initialize();
>        if (argc && argv)
>            PySys_SetArgv(argc, argv);
>    [...]
>              m = PyInit_hello();
>    [...]
>        if (Py_FinalizeEx() < 0)
>            return 2;
>    [...]
>        return 0;
>    [...]
> 
> -- 
> https://mail.python.org/mailman/listinfo/python-list
> 


From cafulque at gmail.com  Tue Apr  4 12:56:50 2023
From: cafulque at gmail.com (Carlos Fulqueris)
Date: Tue, 4 Apr 2023 13:56:50 -0300
Subject: Python's Plugins for NetBeans 16
Message-ID: <CAN71zOxbfRd0dnmXTcwnNZXQ3X_ZkJ1Sq_=cRUpFeFGk6=GXnw@mail.gmail.com>

Dear Python Support,

I'm looking for "Python Plugins for NetBeans 16". I already installed
Python 3.11.2 for Windows 11 and I can't find such plugins to create python
projects.

I would appreciate it if you tell me where to download these plugins or if
there is any other issue that I should do differently.

Thank you very much in advance.
Best to all.

Carlos Fulqueris
+54 911 2251 9302

From mats at wichmann.us  Tue Apr  4 17:27:50 2023
From: mats at wichmann.us (Mats Wichmann)
Date: Tue, 4 Apr 2023 15:27:50 -0600
Subject: Problem in using libraries
In-Reply-To: <CAJz1ufO+W7mM3zfhOyksBu6EtRSYGskYyhgv0do1T6LEjnYBpQ@mail.gmail.com>
References: <CAJz1ufO+W7mM3zfhOyksBu6EtRSYGskYyhgv0do1T6LEjnYBpQ@mail.gmail.com>
Message-ID: <38f28bdc-eb40-40fe-d791-10827b0e283d@wichmann.us>

On 4/3/23 10:43, Pranav Bhardwaj wrote:
> Why can't I able to use python libraries such as numpy, nudenet, playsound,
> pandas, etc in my python 3.11.2. It always through the error "import
> 'numpy' or any other libraries could not be resolved".

Will restate what others have said in the hopes it might be even more 
clear that way.

Python has an internal search path that it uses to find the module when 
you ask to "import".  If a module is not found, that means it's not in 
the search path ("it's always a path problem"). You installed it, sure - 
but it went somewhere else.

The search path is installation-specific (not just version-specific: for 
example if you have a system install of 3.10.x, and a virtualenv using 
the same 3.10.x, those will have different search paths). The search 
path can be amended or changed, but that's a different story.

If you're going to install with pip, use the same Python you're going to 
do your work with. Don't trust that a command named "pip" maps to the 
same installation as that Python command. For that, either use an 
activated virtualenv, or do "name-of-my-python -m pip install".  You can 
always check your work by doing "name-of-my-python -m pip list" - what 
does that particular installation see as installed?

Or - if you're using the classic set of "scientific" packages like numpy 
and pandas, you might look at installing it all using conda instead of 
pip: it to a large extent exists to help with getting those very common 
bundles of things set up without going through the wrestling match 
you're going though.

From thomas at python.org  Wed Apr  5 08:28:54 2023
From: thomas at python.org (Thomas Wouters)
Date: Wed, 5 Apr 2023 14:28:54 +0200
Subject: [RELEASE] Python 3.11.3, 3.10.11 and 3.12.0 alpha 7 released
Message-ID: <CAPdQG2q0QEQPBRfH_TKBBOsnqbvd9u15y9OV0XRADReFtPuVpA@mail.gmail.com>

It's time for another set of Python releases! *Python 3.11.3, 3.10.11 and
3.12 alpha 7 are now available*.

Python 3.12.0 alpha 7

The final alpha release of Python 3.12! The next release will be beta 1,
which is also the feature freeze. Last chance to get your new features and
API changes into 3.12!

https://www.python.org/downloads/release/python-3120a7/


*246 new commits since 3.12.0a6.*
Python 3.11.3

More bugfixes and security fixes for the best Python version (so far).

https://www.python.org/downloads/release/python-3113/


*167 new commits since 3.11.2*
Python 3.10.11

The final regular bugfix release for Python 3.10! It is now entering
security-fix-only mode. This also means this is the last version for which
we will ship Windows and macOS installers. If you rely on these binary
releases, it's time to upgrade to Python 3.11.

https://www.python.org/downloads/release/python-31011/


*121 new commits since 3.10.10.*
We hope you enjoy the new releases!

Thanks to all of the many volunteers who help make Python Development and
these releases possible! Please consider supporting our efforts by
volunteering yourself or through organization contributions to the Python
Software Foundation.

https://www.python.org/psf/

>From the release team,

Thomas Wouters @thomas
Pablo Galindo Salgado @pablogsal
?ukasz Langa @ambv
Ned Deily @nad
Steve Dower @steve.dower

From loris.bennett at fu-berlin.de  Wed Apr  5 08:45:03 2023
From: loris.bennett at fu-berlin.de (Loris Bennett)
Date: Wed, 05 Apr 2023 14:45:03 +0200
Subject: When is logging.getLogger(__name__) needed?
References: <877cux2hy0.fsf@hornfels.zedat.fu-berlin.de>
 <dd184814-69cb-3ce7-57f2-8e22eb8a02cf@DancesWithMice.info>
 <mailman.2483.1680301344.20444.python-list@python.org>
Message-ID: <87sfde7b1s.fsf@hornfels.zedat.fu-berlin.de>

dn <PythonList at DancesWithMice.info> writes:

> On 01/04/2023 02.01, Loris Bennett wrote:
>> Hi,
>> In my top level program file, main.py, I have
>>    def main_function():
>>        parser = argparse.ArgumentParser(description="my prog")
>>        ...
>>        args = parser.parse_args()
>>        config = configparser.ConfigParser()
>>        if args.config_file is None:
>>            config_file = DEFAULT_CONFIG_FILE
>>        else:
>>            config_file = args.config_file
>>        config.read(config_file)
>>        logging.config.fileConfig(fname=config_file)
>>        logger = logging.getLogger(__name__)
>>        do_some_stuff()
>>               my_class_instance = myprog.MyClass()
>>    def do_some_stuff():
>>        logger.info("Doing stuff")
>> This does not work, because 'logger' is not known in the function
>> 'do_some_stuff'.
>> However, if in 'my_prog/my_class.py' I have
>>    class MyClass:
>>        def __init__(self):
>>            logger.debug("created instance of MyClass")
>> this 'just works'.
>> I can add
>>    logger = logging.getLogger(__name__)
>> to 'do_some_stuff', but why is this necessary in this case but not
>> in
>> the class?
>> Or should I be doing this entirely differently?
>
> Yes: differently.
>
> To complement @Peter's response, two items for consideration:
>
> 1 once main_function() has completed, have it return logger and other
> such values/constructs. The target-identifiers on the LHS of the 
> function-call will thus be within the global scope.
>
> 2 if the purposes of main_function() are condensed-down to a few
> (English, or ..., language) phrases, the word "and" will feature, eg
> - configure env according to cmdLN args,
> - establish log(s),
> - do_some_stuff(),  ** AND **
> - instantiate MyClass.
>
> If these (and do_some_stuff(), like MyClass' methods) were split into
> separate functions* might you find it easier to see them as separate 
> sub-solutions? Each sub-solution would be able to contribute to the
> whole - the earlier ones as creating (outputting) a description, 
> constraint, or basis; which becomes input to a later function/method.

So if I want to modify the logging via the command line I might have the
following:

---------------------------------------------------------------------

#!/usr/bin/env python3

import argparse
import logging


def get_logger(log_level):
    """Get global logger"""

    logger = logging.getLogger('example')
    logger.setLevel(log_level)
    ch = logging.StreamHandler()
    formatter = logging.Formatter('%(levelname)s - %(message)s')
    ch.setFormatter(formatter)
    logger.addHandler(ch)

    return logger


def do_stuff():
    """Do some stuff"""

#    logger.info("Doing stuff!")


def main():
    """Main"""

    parser = argparse.ArgumentParser()
    parser.add_argument("--log-level", dest="log_level", type=int)
    args = parser.parse_args()

    print(f"log level: {args.log_level}")

    logger = get_logger(args.log_level)
    logger.debug("Logger!")
    do_stuff()


if __name__ == "__main__":
    main()

---------------------------------------------------------------------

How can I get logging for 'do_stuff' in this case without explicitly
passing 'logger' as an argument or using 'global'?

Somehow I am failing to understand how to get 'logger' defined
sufficiently high up in the program that all references 'lower down' in
the program will be automatically resolved. 

> * there is some debate amongst developers about whether "one function,
>   one purpose" should be a rule, a convention, or tossed in the
>  trash. YMMV!
>
> Personal view: SOLID's "Single" principle applies: there should be
> only one reason (hanging over the head of each method/function, like
> the Sword of Damocles) for it to change - or one 'user' who could
> demand a change to that function. In other words, an updated cmdLN
> option shouldn't affect a function which establishes logging, for
> example.
>
>
> Web.Refs:
> https://people.engr.tamu.edu/choe/choe/courses/20fall/315/lectures/slide23-solid.pdf
> https://www.hanselminutes.com/145/solid-principles-with-uncle-bob-robert-c-martin
> https://idioms.thefreedictionary.com/sword+of+Damocles
> https://en.wikipedia.org/wiki/Damocles

I don't really get the "one reason" idea and the Sword of Damocles
analogy.  The later to me is more like "there's always a downside",
since the perks of being king may mean someone might try to usurp the
throne and kill you.  Where is the "single principle" aspect?

However, the idea of "one responsibility" in the sense of "do only one
thing" seems relatively clear, especially if I think in terms of writing
unit tests.

Cheers,

Loris

-- 
This signature is currently under constuction.

From loris.bennett at fu-berlin.de  Wed Apr  5 09:06:22 2023
From: loris.bennett at fu-berlin.de (Loris Bennett)
Date: Wed, 05 Apr 2023 15:06:22 +0200
Subject: When is logging.getLogger(__name__) needed?
References: <877cux2hy0.fsf@hornfels.zedat.fu-berlin.de>
 <dd184814-69cb-3ce7-57f2-8e22eb8a02cf@DancesWithMice.info>
 <mailman.2483.1680301344.20444.python-list@python.org>
 <87sfde7b1s.fsf@hornfels.zedat.fu-berlin.de>
Message-ID: <87o7o27a29.fsf@hornfels.zedat.fu-berlin.de>

"Loris Bennett" <loris.bennett at fu-berlin.de> writes:

> dn <PythonList at DancesWithMice.info> writes:
>
>> On 01/04/2023 02.01, Loris Bennett wrote:
>>> Hi,
>>> In my top level program file, main.py, I have
>>>    def main_function():
>>>        parser = argparse.ArgumentParser(description="my prog")
>>>        ...
>>>        args = parser.parse_args()
>>>        config = configparser.ConfigParser()
>>>        if args.config_file is None:
>>>            config_file = DEFAULT_CONFIG_FILE
>>>        else:
>>>            config_file = args.config_file
>>>        config.read(config_file)
>>>        logging.config.fileConfig(fname=config_file)
>>>        logger = logging.getLogger(__name__)
>>>        do_some_stuff()
>>>               my_class_instance = myprog.MyClass()
>>>    def do_some_stuff():
>>>        logger.info("Doing stuff")
>>> This does not work, because 'logger' is not known in the function
>>> 'do_some_stuff'.
>>> However, if in 'my_prog/my_class.py' I have
>>>    class MyClass:
>>>        def __init__(self):
>>>            logger.debug("created instance of MyClass")
>>> this 'just works'.
>>> I can add
>>>    logger = logging.getLogger(__name__)
>>> to 'do_some_stuff', but why is this necessary in this case but not
>>> in
>>> the class?
>>> Or should I be doing this entirely differently?
>>
>> Yes: differently.
>>
>> To complement @Peter's response, two items for consideration:
>>
>> 1 once main_function() has completed, have it return logger and other
>> such values/constructs. The target-identifiers on the LHS of the 
>> function-call will thus be within the global scope.
>>
>> 2 if the purposes of main_function() are condensed-down to a few
>> (English, or ..., language) phrases, the word "and" will feature, eg
>> - configure env according to cmdLN args,
>> - establish log(s),
>> - do_some_stuff(),  ** AND **
>> - instantiate MyClass.
>>
>> If these (and do_some_stuff(), like MyClass' methods) were split into
>> separate functions* might you find it easier to see them as separate 
>> sub-solutions? Each sub-solution would be able to contribute to the
>> whole - the earlier ones as creating (outputting) a description, 
>> constraint, or basis; which becomes input to a later function/method.
>
> So if I want to modify the logging via the command line I might have the
> following:
>
> ---------------------------------------------------------------------
>
> #!/usr/bin/env python3
>
> import argparse
> import logging
>
>
> def get_logger(log_level):
>     """Get global logger"""
>
>     logger = logging.getLogger('example')
>     logger.setLevel(log_level)
>     ch = logging.StreamHandler()
>     formatter = logging.Formatter('%(levelname)s - %(message)s')
>     ch.setFormatter(formatter)
>     logger.addHandler(ch)
>
>     return logger
>
>
> def do_stuff():
>     """Do some stuff"""
>
> #    logger.info("Doing stuff!")

Looks like I just need 

  logger = logging.getLogger('example)
  logger.info("Doing stuff!")

>
> def main():
>     """Main"""
>
>     parser = argparse.ArgumentParser()
>     parser.add_argument("--log-level", dest="log_level", type=int)
>     args = parser.parse_args()
>
>     print(f"log level: {args.log_level}")
>
>     logger = get_logger(args.log_level)
>     logger.debug("Logger!")
>     do_stuff()
>
>
> if __name__ == "__main__":
>     main()
>
> ---------------------------------------------------------------------
>
> How can I get logging for 'do_stuff' in this case without explicitly
> passing 'logger' as an argument or using 'global'?
>
> Somehow I am failing to understand how to get 'logger' defined
> sufficiently high up in the program that all references 'lower down' in
> the program will be automatically resolved. 
>
>> * there is some debate amongst developers about whether "one function,
>>   one purpose" should be a rule, a convention, or tossed in the
>>  trash. YMMV!
>>
>> Personal view: SOLID's "Single" principle applies: there should be
>> only one reason (hanging over the head of each method/function, like
>> the Sword of Damocles) for it to change - or one 'user' who could
>> demand a change to that function. In other words, an updated cmdLN
>> option shouldn't affect a function which establishes logging, for
>> example.
>>
>>
>> Web.Refs:
>> https://people.engr.tamu.edu/choe/choe/courses/20fall/315/lectures/slide23-solid.pdf
>> https://www.hanselminutes.com/145/solid-principles-with-uncle-bob-robert-c-martin
>> https://idioms.thefreedictionary.com/sword+of+Damocles
>> https://en.wikipedia.org/wiki/Damocles
>
> I don't really get the "one reason" idea and the Sword of Damocles
> analogy.  The later to me is more like "there's always a downside",
> since the perks of being king may mean someone might try to usurp the
> throne and kill you.  Where is the "single principle" aspect?
>
> However, the idea of "one responsibility" in the sense of "do only one
> thing" seems relatively clear, especially if I think in terms of writing
> unit tests.
>
> Cheers,
>
> Loris
-- 
Dr. Loris Bennett (Herr/Mr)
ZEDAT, Freie Universit?t Berlin

From PythonList at DancesWithMice.info  Wed Apr  5 20:33:08 2023
From: PythonList at DancesWithMice.info (dn)
Date: Thu, 6 Apr 2023 12:33:08 +1200
Subject: When is logging.getLogger(__name__) needed?
In-Reply-To: <87o7o27a29.fsf@hornfels.zedat.fu-berlin.de>
References: <877cux2hy0.fsf@hornfels.zedat.fu-berlin.de>
 <dd184814-69cb-3ce7-57f2-8e22eb8a02cf@DancesWithMice.info>
 <mailman.2483.1680301344.20444.python-list@python.org>
 <87sfde7b1s.fsf@hornfels.zedat.fu-berlin.de>
 <87o7o27a29.fsf@hornfels.zedat.fu-berlin.de>
Message-ID: <34d45701-291d-3f08-2536-38b63b523b47@DancesWithMice.info>

Thank you for carefully considering suggestions (and implications) - and 
which will 'work' for you.

Further comment below (and with apologies that, unusually for me, there 
are many personal opinions mixed-in):-


On 06/04/2023 01.06, Loris Bennett wrote:
> "Loris Bennett" <loris.bennett at fu-berlin.de> writes:
>> dn <PythonList at DancesWithMice.info> writes:
>>> On 01/04/2023 02.01, Loris Bennett wrote:
>>>> Hi,
>>>> In my top level program file, main.py, I have
>>>>     def main_function():
>>>>         parser = argparse.ArgumentParser(description="my prog")
>>>>         ...
>>>>         args = parser.parse_args()
>>>>         config = configparser.ConfigParser()
>>>>         if args.config_file is None:
>>>>             config_file = DEFAULT_CONFIG_FILE
>>>>         else:
>>>>             config_file = args.config_file
>>>>         config.read(config_file)
>>>>         logging.config.fileConfig(fname=config_file)
>>>>         logger = logging.getLogger(__name__)
>>>>         do_some_stuff()
>>>>                my_class_instance = myprog.MyClass()
>>>>     def do_some_stuff():
>>>>         logger.info("Doing stuff")
>>>> This does not work, because 'logger' is not known in the function
>>>> 'do_some_stuff'.
>>>> However, if in 'my_prog/my_class.py' I have
>>>>     class MyClass:
>>>>         def __init__(self):
>>>>             logger.debug("created instance of MyClass")
>>>> this 'just works'.
>>>> I can add
>>>>     logger = logging.getLogger(__name__)
>>>> to 'do_some_stuff', but why is this necessary in this case but not
>>>> in
>>>> the class?
>>>> Or should I be doing this entirely differently?
>>>
>>> Yes: differently.
>>>
>>> To complement @Peter's response, two items for consideration:
>>>
>>> 1 once main_function() has completed, have it return logger and other
>>> such values/constructs. The target-identifiers on the LHS of the
>>> function-call will thus be within the global scope.
>>>
>>> 2 if the purposes of main_function() are condensed-down to a few
>>> (English, or ..., language) phrases, the word "and" will feature, eg
>>> - configure env according to cmdLN args,
>>> - establish log(s),
>>> - do_some_stuff(),  ** AND **
>>> - instantiate MyClass.
>>>
>>> If these (and do_some_stuff(), like MyClass' methods) were split into
>>> separate functions* might you find it easier to see them as separate
>>> sub-solutions? Each sub-solution would be able to contribute to the
>>> whole - the earlier ones as creating (outputting) a description,
>>> constraint, or basis; which becomes input to a later function/method.
>>
>> So if I want to modify the logging via the command line I might have the
>> following:
>>
>> ---------------------------------------------------------------------
>>
>> #!/usr/bin/env python3
>>
>> import argparse
>> import logging
>>
>>
>> def get_logger(log_level):
>>      """Get global logger"""
>>
>>      logger = logging.getLogger('example')
>>      logger.setLevel(log_level)
>>      ch = logging.StreamHandler()
>>      formatter = logging.Formatter('%(levelname)s - %(message)s')
>>      ch.setFormatter(formatter)
>>      logger.addHandler(ch)
>>
>>      return logger
>>
>>
>> def do_stuff():
>>      """Do some stuff"""
>>
>> #    logger.info("Doing stuff!")
> 
> Looks like I just need
> 
>    logger = logging.getLogger('example)
>    logger.info("Doing stuff!")
> 
>>
>> def main():
>>      """Main"""
>>
>>      parser = argparse.ArgumentParser()
>>      parser.add_argument("--log-level", dest="log_level", type=int)
>>      args = parser.parse_args()
>>
>>      print(f"log level: {args.log_level}")
>>
>>      logger = get_logger(args.log_level)
>>      logger.debug("Logger!")
>>      do_stuff()
>>
>>
>> if __name__ == "__main__":
>>      main()
>>
>> ---------------------------------------------------------------------
>>
>> How can I get logging for 'do_stuff' in this case without explicitly
>> passing 'logger' as an argument or using 'global'?
>>
>> Somehow I am failing to understand how to get 'logger' defined
>> sufficiently high up in the program that all references 'lower down' in
>> the program will be automatically resolved.

At the risk of 'heresy', IMHO the idea of main() is (almost always) 
unnecessary in Python, and largely a habit carried-over from other 
languages (need for an entry-/end-point).

NB be sure of the difference between a "script" and a "module"...


My script template-overview:

''' Script docstring. '''
- author, license, etc docs

global constants such as import-s
set environment

if __name__ == "__main__":
     do_this()
     do_that()
     ie the business of the script


Despite its frequent use, I'm somewhat amused by the apparent 
duplication within:

if __name__ == "__main__":
     main()

ie if this .py file is being executed as a script, call main() - where 
main() is the purpose of the script. Whereas if the file is an import-ed 
module, do not execute any of the contained-code.

Thus, the if-statement achieves the same separation as the main() 
function encapsulation. Also, the word main() conveys considerably less 
meaning than (say) establish_logging().


NB others may care to offer alternate advice for your consideration...


There is a good argument for main(), in that it might enable tests to be 
written which assure the integration of several tasks called by the 
script. Plus, if one excludes non-TDD test-able code, such as user 
interfaces, even 'fancy headings' and printing of conclusions; there's 
little left. Accordingly, I don't mind the apparent duplication involved 
in coding an integration test which checks that do_this() and do_that() 
are playing-nicely together. YMMV!


I'm not sure why, but my 'mainlines' never seem to be very long. Once I 
had been introduced to "Modular Programming" (1970s?), it seemed that 
the purpose of a mainline was merely calling one do-it function after 
another.

To me mainline's seem highly unlikely to be re-usable. Thus, the 
possibility that main() might need to be import-able to some other 
script, is beyond my experience/recollection.

Further, my .py file scripts/mainlines tend to be short and often don't 
contain any of the functions or classes which actually do-the-work - all 
are import-ed (and thus, they are easier to re-use!?)


Returning to 'set environment': the code-examples include argparse and 
logger. Both (in my thinking) are part of creating the environment in 
which the code will execute.

Logging for example, is the only choice when we need to be aware of how 
a web-based system is running (or running into problems) - otherwise, as 
some would argue, we might as well use print(). Similarly, argparse will 
often influence the way a script executes, the data it should use, etc.

Much of such forms the (global) environment in which (this run of) the 
code will execute. Hence locating such setting of priorities and 
constraints, adjacent to the import statements.

These must be established before getting on with 'the business'. That 
said, if someone prefers to put it under if __main__, I won't burst into 
tears. (see earlier comment about the .py file as a script cf module)


You have answered your own question about logging. Well done!

The logging instance can either be explicitly passed into each 
(relevant) function, or it can be treated as a global and thus available 
implicitly. (see also: "Zen of Python")

I prefer your approach of get_logger() - even if that name doesn't quite 
describe the establishment of a logger and its settings. All of that 
part of setting the environment is collected into one place. Which 
in-turn, makes it easy to work on any changes, or work-in any parameters 
which may come from other environment-setting activity.


As well as 'the documentation' there is a HowTo 
(https://docs.python.org/3/howto/logging.html). Other logging-learners 
have found the DigitalOcean tutorial helpful 
(https://www.digitalocean.com/community/tutorials/how-to-use-logging-in-python-3)


>>> * there is some debate amongst developers about whether "one function,
>>>    one purpose" should be a rule, a convention, or tossed in the
>>>   trash. YMMV!
>>>
>>> Personal view: SOLID's "Single" principle applies: there should be
>>> only one reason (hanging over the head of each method/function, like
>>> the Sword of Damocles) for it to change - or one 'user' who could
>>> demand a change to that function. In other words, an updated cmdLN
>>> option shouldn't affect a function which establishes logging, for
>>> example.
>>>
>>>
>>> Web.Refs:
>>> https://people.engr.tamu.edu/choe/choe/courses/20fall/315/lectures/slide23-solid.pdf
>>> https://www.hanselminutes.com/145/solid-principles-with-uncle-bob-robert-c-martin
>>> https://idioms.thefreedictionary.com/sword+of+Damocles
>>> https://en.wikipedia.org/wiki/Damocles
>>
>> I don't really get the "one reason" idea and the Sword of Damocles
>> analogy.  The later to me is more like "there's always a downside",
>> since the perks of being king may mean someone might try to usurp the
>> throne and kill you.  Where is the "single principle" aspect?
>>
>> However, the idea of "one responsibility" in the sense of "do only one
>> thing" seems relatively clear, especially if I think in terms of writing
>> unit tests.

+1

Users are notoriously unable to write clear specifications. Ultimately, 
and not necessarily unkindly, they often do not know what they want - 
and particularly not specified at the level of detail we need. This is 
the downfall of the "waterfall" SDLC development model, and the reason 
why short 'Agile' sprints are (often/in-theory) more successful. The 
sooner a mistake, misunderstanding, or omission is realised, the better!

Not wanting to do more than state the above, things change, life goes 
on, etc, etc. So, when one first demonstrates code to a user, it is rare 
that they won't want to change something. Similarly, over time, it is 
highly unlikely that someone won't dream up some 'improvement' - or 
similar need to amend the code be imposed by an externality, eg 
government legislation or regulation. Such changes may be trivial, eg 
cosmetic; others may be more far-reaching, eg imposition of a tax where 
previously there was none (or v-v).

Accordingly, adding the fourth dimension to one's code, and 
program[me]-design - and the advice about being kind to those who will 
maintain the code after you or your six-months-time-self.

So, the 'sword of Damocles' is knowing that our code should not be 
considered secure (or static). That change is inevitable. We don't need 
to be worrying about danger afflicting us when we least expect it - your 
users are unlikely to actually kill you. However, it is a good idea to 
be aware that change may be required, and that it could come from any 
random direction or "stakeholder".

Perhaps worse, change implies risk. We make a change to suit one aspect, 
and something else 'breaks'. That is the reason many programmers 
actively resist 'change'. That is also one of the promises of TDD - if 
we can quickly run tests which assure (if not "prove") code-correctness, 
then the risks of change decrease. Whereas, if there are no tests to 
ensure 'life goes on' after a change, well, unhappiness reigns!

Hence the allusion.
(apologies if it was too oblique)


Accordingly, the idea that if a function does one job (and does it 
well), should you decide/be required to change that function, then the 
impacts, any side-effects, etc,  of such will only affect that one 
function (and its tests), and whatever is 'downstream' (integrating) 
from there.

Which also reduces the chance that some change 'over here', will have 
some unforeseen impact 'over there'. The structure and the flow work 
together to achieve both a degree of separation and a bringing-together 
or unity. The tension of team-work if you like, cf the dysfunction of 
disorganisation.

NB not that a 'small change' means running only that one test in TDD - 
still run the entire suite of tests (auto-magically) to ensure that 
there are no surprises...


Change is inevitable. Thus, consider that your throne as code-author is 
illusory - the user/client is able/likely to want change.

Then, if the code is organised according to functionality, the logging 
environment (for example) can be changed without any need to re-code 
somewhere else - and/or that tinkering with cmdLN arguments and such 
code-changes can be done quite separately from the establishment of logging.

Ultimately, the smaller the function (think of establishing logging), 
the more likely it will be able to be re-used in the next assignment 
which requires a log! (whereas if it is mixed-in with argparse, re-use 
is unlikely because the cmdLN args will be different)


There's plenty of references about such on the web. Will be happy to 
discuss whichever sub-topics might be of-interest, further...

-- 
Regards,
=dn

From jschwar at sbcglobal.net  Thu Apr  6 15:49:50 2023
From: jschwar at sbcglobal.net (Jim Schwartz)
Date: Thu, 6 Apr 2023 14:49:50 -0500
Subject: Windows installer from python source code without access to
 source code
In-Reply-To: <79F9B803-CE16-418C-B5CA-E88155DD42C5@barrys-emacs.org>
References: <01a501d96709$b3f86f70$1be94e50$@sbcglobal.net>
 <79F9B803-CE16-418C-B5CA-E88155DD42C5@barrys-emacs.org>
Message-ID: <00b201d968c0$f3c1e380$db45aa80$@sbcglobal.net>

I downloaded VS community 2022 and I know how to access the developer command prompt.  I'm using the one called x64 Native Tools Command Prompt for VS 2022

I ran a command to compile my python code that was converted to c with the following command:

H:\Users\LindaJim\Documents\SourceCode\Software\aws_pc_backup\src\c>cl /O2 /I"C:\\Users\\jschw\\AppData\\Local\\Programs\\Python\\Python3112\\include\\" aws_pc_backup.c C:\\Users\\jschw\\AppData\\Local\\Programs\\Python\\Python3112\\libs\\python311.lib
Microsoft (R) C/C++ Optimizing Compiler Version 19.35.32216.1 for x64
Copyright (C) Microsoft Corporation.  All rights reserved.

aws_pc_backup.c
Microsoft (R) Incremental Linker Version 14.35.32216.1
Copyright (C) Microsoft Corporation.  All rights reserved.

/out:aws_pc_backup.exe
aws_pc_backup.obj
C:\\Users\\jschw\\AppData\\Local\\Programs\\Python\\Python3112\\libs\\python311.lib
   Creating library aws_pc_backup.lib and object aws_pc_backup.exp

When I ran the program, I got this, though.  Obviously, it doesn't know about the requests package.  Do I have to link something in with the executable?

H:\Users\LindaJim\Documents\SourceCode\Software\aws_pc_backup\src\c>aws_pc_backup.exe -m:lb
Traceback (most recent call last):
  File "src\\python\\aws_pc_backup_main.py", line 7, in init python.aws_pc_backup_main
ModuleNotFoundError: No module named 'requests'





-----Original Message-----
From: Barry <barry at barrys-emacs.org> 
Sent: Tuesday, April 4, 2023 1:25 PM
To: Jim Schwartz <jschwar at sbcglobal.net>
Cc: Eryk Sun <eryksun at gmail.com>; python-list at python.org
Subject: Re: Windows installer from python source code without access to source code



> On 4 Apr 2023, at 16:28, Jim Schwartz <jschwar at sbcglobal.net> wrote:
> 
> ?Where can I download that cl program?  I've used gcc before, but I hear that cl can use a setup.py program to run the compile and link and create a windows .msi installer.  Is that true?  

It is part of visual studio C++.
Once you have that installed there are bat files that setup environment in the terminal.
Then you can use cl, nmake etc

Barry
> 
> -----Original Message-----
> From: Eryk Sun <eryksun at gmail.com>
> Sent: Friday, March 31, 2023 12:55 PM
> To: Jim Schwartz <jschwar at sbcglobal.net>
> Cc: python-list at python.org
> Subject: Re: Windows installer from python source code without access 
> to source code
> 
>> On 3/31/23, Jim Schwartz <jschwar at sbcglobal.net> wrote:
>> I want a windows installer to install my application that's written 
>> in python, but I don't want the end user to have access to my source code.
> 
> Cython can compile a script to C source code for a module or executable (--embed). The source can be compiled and linked normally.
> For example, the following builds a "hello.exe" executable based on a "hello.py" script.
> 
>> cython -3 --embed hello.py
>> set "PYI=C:\Program Files\Python311\include"
>> set "PYL=C:\Program Files\Python311\libs"
>> cl /I"%PYI%" hello.c /link /libpath:"%PYL%"
>> copy hello.exe embed
>> embed\hello.exe
>    Hello, World!
> 
> I extracted the complete embeddable distribution of Python 3.11 into the "embed" directory. You can reduce the size of the installation, if needed, by minimizing the zipped standard library and removing pyd extensions and DLLs that your application doesn't use.
> 
> The generated "hello.c" is large and not particularly easy to read, but here are some snippets [...]:
> 
>    [...]
>    /* Implementation of 'hello' */
>    static PyObject *__pyx_builtin_print;
>    static const char __pyx_k_main[] = "__main__";
>    static const char __pyx_k_name[] = "__name__";
>    static const char __pyx_k_test[] = "__test__";
>    static const char __pyx_k_print[] = "print";
>    static const char __pyx_k_Hello_World[] = "Hello, World!";
>    [...]
>      /* "hello.py":1
>     * print("Hello, World!")             # <<<<<<<<<<<<<<
>     */
>      __pyx_tuple_ = PyTuple_Pack(1, __pyx_kp_u_Hello_World);
>            if (unlikely(!__pyx_tuple_)) __PYX_ERR(0, 1, __pyx_L1_error)
>    [...]
>      /* "hello.py":1
>     * print("Hello, World!")             # <<<<<<<<<<<<<<
>     */
>      __pyx_t_1 = __Pyx_PyObject_Call(__pyx_builtin_print, __pyx_tuple_,
>                                      NULL);
>            if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 1, __pyx_L1_error)
>    [...]
>    int wmain(int argc, wchar_t **argv) {
>    [...]
>        if (argc && argv)
>            Py_SetProgramName(argv[0]);
>        Py_Initialize();
>        if (argc && argv)
>            PySys_SetArgv(argc, argv);
>    [...]
>              m = PyInit_hello();
>    [...]
>        if (Py_FinalizeEx() < 0)
>            return 2;
>    [...]
>        return 0;
>    [...]
> 
> --
> https://mail.python.org/mailman/listinfo/python-list
> 


From jschwar at sbcglobal.net  Thu Apr  6 18:14:41 2023
From: jschwar at sbcglobal.net (Jim Schwartz)
Date: Thu, 6 Apr 2023 17:14:41 -0500
Subject: Windows installer from python source code without access to
 source code
In-Reply-To: <CAN71zOyiMKNZ-YyDJ0R7zzT0Z1pa_VofnJCkb8nTciwk4JNwPw@mail.gmail.com>
References: <CAN71zOyiMKNZ-YyDJ0R7zzT0Z1pa_VofnJCkb8nTciwk4JNwPw@mail.gmail.com>
Message-ID: <B65CF219-9B1A-4725-9635-AF012FB057F1@sbcglobal.net>

   Could someone please help Carlos? ?I?m not sure how to answer his
   question?

   Sent from my iPhone

     On Apr 6, 2023, at 3:53 PM, Carlos Fulqueris <cafulque at gmail.com> wrote:

     ?
     Hello Jim,
     How can I unsubscribe?to this email list?
     I'm waiting for your response.
     Thanks
     Carlos
     El jue, 6 abr 2023 a las 16:52, Jim Schwartz
     (<[1]jschwar at sbcglobal.net>) escribi?:

       I downloaded VS community 2022 and I know how to access the developer
       command prompt.? I'm using the one called x64 Native Tools Command
       Prompt for VS 2022

       I ran a command to compile my python code that was converted to c with
       the following command:

       H:\Users\LindaJim\Documents\SourceCode\Software\aws_pc_backup\src\c>cl
       /O2
       /I"C:\\Users\\jschw\\AppData\\Local\\Programs\\Python\\Python3112\\include\\"
       aws_pc_backup.c
       C:\\Users\\jschw\\AppData\\Local\\Programs\\Python\\Python3112\\libs\\python311.lib
       Microsoft (R) C/C++ Optimizing Compiler Version 19.35.32216.1 for x64
       Copyright (C) Microsoft Corporation.? All rights reserved.

       aws_pc_backup.c
       Microsoft (R) Incremental Linker Version 14.35.32216.1
       Copyright (C) Microsoft Corporation.? All rights reserved.

       /out:aws_pc_backup.exe
       aws_pc_backup.obj
       C:\\Users\\jschw\\AppData\\Local\\Programs\\Python\\Python3112\\libs\\python311.lib
       ? ?Creating library aws_pc_backup.lib and object aws_pc_backup.exp

       When I ran the program, I got this, though.? Obviously, it doesn't
       know about the requests package.? Do I have to link something in with
       the executable?

       H:\Users\LindaJim\Documents\SourceCode\Software\aws_pc_backup\src\c>aws_pc_backup.exe
       -m:lb
       Traceback (most recent call last):
       ? File "src\\python\\aws_pc_backup_main.py", line 7, in init
       python.aws_pc_backup_main
       ModuleNotFoundError: No module named 'requests'

       -----Original Message-----
       From: Barry <[2]barry at barrys-emacs.org>
       Sent: Tuesday, April 4, 2023 1:25 PM
       To: Jim Schwartz <[3]jschwar at sbcglobal.net>
       Cc: Eryk Sun <[4]eryksun at gmail.com>; [5]python-list at python.org
       Subject: Re: Windows installer from python source code without access
       to source code

       > On 4 Apr 2023, at 16:28, Jim Schwartz <[6]jschwar at sbcglobal.net>
       wrote:
       >
       > ?Where can I download that cl program?? I've used gcc before, but I
       hear that cl can use a setup.py program to run the compile and link
       and create a windows .msi installer.? Is that true??

       It is part of visual studio C++.
       Once you have that installed there are bat files that setup
       environment in the terminal.
       Then you can use cl, nmake etc

       Barry
       >
       > -----Original Message-----
       > From: Eryk Sun <[7]eryksun at gmail.com>
       > Sent: Friday, March 31, 2023 12:55 PM
       > To: Jim Schwartz <[8]jschwar at sbcglobal.net>
       > Cc: [9]python-list at python.org
       > Subject: Re: Windows installer from python source code without
       access
       > to source code
       >
       >> On 3/31/23, Jim Schwartz <[10]jschwar at sbcglobal.net> wrote:
       >> I want a windows installer to install my application that's written
       >> in python, but I don't want the end user to have access to my
       source code.
       >
       > Cython can compile a script to C source code for a module or
       executable (--embed). The source can be compiled and linked normally.
       > For example, the following builds a "hello.exe" executable based on
       a "hello.py" script.
       >
       >> cython -3 --embed hello.py
       >> set "PYI=C:\Program Files\Python311\include"
       >> set "PYL=C:\Program Files\Python311\libs"
       >> cl /I"%PYI%" hello.c /link /libpath:"%PYL%"
       >> copy hello.exe embed
       >> embed\hello.exe
       >? ? Hello, World!
       >
       > I extracted the complete embeddable distribution of Python 3.11 into
       the "embed" directory. You can reduce the size of the installation, if
       needed, by minimizing the zipped standard library and removing pyd
       extensions and DLLs that your application doesn't use.
       >
       > The generated "hello.c" is large and not particularly easy to read,
       but here are some snippets [...]:
       >
       >? ? [...]
       >? ? /* Implementation of 'hello' */
       >? ? static PyObject *__pyx_builtin_print;
       >? ? static const char __pyx_k_main[] = "__main__";
       >? ? static const char __pyx_k_name[] = "__name__";
       >? ? static const char __pyx_k_test[] = "__test__";
       >? ? static const char __pyx_k_print[] = "print";
       >? ? static const char __pyx_k_Hello_World[] = "Hello, World!";
       >? ? [...]
       >? ? ? /* "hello.py":1
       >? ? ?* print("Hello, World!")? ? ? ? ? ? ?# <<<<<<<<<<<<<<
       >? ? ?*/
       >? ? ? __pyx_tuple_ = PyTuple_Pack(1, __pyx_kp_u_Hello_World);
       >? ? ? ? ? ? if (unlikely(!__pyx_tuple_)) __PYX_ERR(0, 1,
       __pyx_L1_error)
       >? ? [...]
       >? ? ? /* "hello.py":1
       >? ? ?* print("Hello, World!")? ? ? ? ? ? ?# <<<<<<<<<<<<<<
       >? ? ?*/
       >? ? ? __pyx_t_1 = __Pyx_PyObject_Call(__pyx_builtin_print,
       __pyx_tuple_,
       >? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? NULL);
       >? ? ? ? ? ? if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 1, __pyx_L1_error)
       >? ? [...]
       >? ? int wmain(int argc, wchar_t **argv) {
       >? ? [...]
       >? ? ? ? if (argc && argv)
       >? ? ? ? ? ? Py_SetProgramName(argv[0]);
       >? ? ? ? Py_Initialize();
       >? ? ? ? if (argc && argv)
       >? ? ? ? ? ? PySys_SetArgv(argc, argv);
       >? ? [...]
       >? ? ? ? ? ? ? m = PyInit_hello();
       >? ? [...]
       >? ? ? ? if (Py_FinalizeEx() < 0)
       >? ? ? ? ? ? return 2;
       >? ? [...]
       >? ? ? ? return 0;
       >? ? [...]
       >
       > --
       > [11]https://mail.python.org/mailman/listinfo/python-list
       >

       --
       [12]https://mail.python.org/mailman/listinfo/python-list

References

   Visible links
   1. mailto:jschwar at sbcglobal.net
   2. mailto:barry at barrys-emacs.org
   3. mailto:jschwar at sbcglobal.net
   4. mailto:eryksun at gmail.com
   5. mailto:python-list at python.org
   6. mailto:jschwar at sbcglobal.net
   7. mailto:eryksun at gmail.com
   8. mailto:jschwar at sbcglobal.net
   9. mailto:python-list at python.org
  10. mailto:jschwar at sbcglobal.net
  11. https://mail.python.org/mailman/listinfo/python-list
  12. https://mail.python.org/mailman/listinfo/python-list

From python at mrabarnett.plus.com  Thu Apr  6 18:49:37 2023
From: python at mrabarnett.plus.com (MRAB)
Date: Thu, 6 Apr 2023 23:49:37 +0100
Subject: Windows installer from python source code without access to
 source code
In-Reply-To: <B65CF219-9B1A-4725-9635-AF012FB057F1@sbcglobal.net>
References: <CAN71zOyiMKNZ-YyDJ0R7zzT0Z1pa_VofnJCkb8nTciwk4JNwPw@mail.gmail.com>
 <B65CF219-9B1A-4725-9635-AF012FB057F1@sbcglobal.net>
Message-ID: <30a87229-e0c7-f326-5e7a-702389b9b8c1@mrabarnett.plus.com>

On 2023-04-06 23:14, Jim Schwartz wrote:
>     Could someone please help Carlos? ?I?m not sure how to answer his
>     question
> 
>     Sent from my iPhone
> 
>       On Apr 6, 2023, at 3:53 PM, Carlos Fulqueris <cafulque at gmail.com> wrote:
> 
>       ?
>       Hello Jim,
>       How can I unsubscribe?to this email list?
>       I'm waiting for your response.
>       Thanks
>       Carlos
[snip]
At the bottom of the post is a link to the page that explains how to 
unsubscribe. It's the link:

>         https://mail.python.org/mailman/listinfo/python-list


From jschwar at sbcglobal.net  Thu Apr  6 19:47:55 2023
From: jschwar at sbcglobal.net (Jim Schwartz)
Date: Thu, 6 Apr 2023 18:47:55 -0500
Subject: Windows installer from python source code without access to
 source code
In-Reply-To: <00b201d968c0$f3c1e380$db45aa80$@sbcglobal.net>
References: <01a501d96709$b3f86f70$1be94e50$@sbcglobal.net>
 <79F9B803-CE16-418C-B5CA-E88155DD42C5@barrys-emacs.org>
 <00b201d968c0$f3c1e380$db45aa80$@sbcglobal.net>
Message-ID: <00cc01d968e2$36b094e0$a411bea0$@sbcglobal.net>

Never mind.  I found it on the web.  I needed to point my PYTHONPATH to sitepackages:  https://stackoverflow.com/questions/56857449/importerror-after-cython-embed


-----Original Message-----
From: Python-list <python-list-bounces+jschwar=sbcglobal.net at python.org> On Behalf Of Jim Schwartz
Sent: Thursday, April 6, 2023 2:50 PM
To: 'Barry' <barry at barrys-emacs.org>
Cc: python-list at python.org
Subject: RE: Windows installer from python source code without access to source code

I downloaded VS community 2022 and I know how to access the developer command prompt.  I'm using the one called x64 Native Tools Command Prompt for VS 2022

I ran a command to compile my python code that was converted to c with the following command:

H:\Users\LindaJim\Documents\SourceCode\Software\aws_pc_backup\src\c>cl /O2 /I"C:\\Users\\jschw\\AppData\\Local\\Programs\\Python\\Python3112\\include\\" aws_pc_backup.c C:\\Users\\jschw\\AppData\\Local\\Programs\\Python\\Python3112\\libs\\python311.lib
Microsoft (R) C/C++ Optimizing Compiler Version 19.35.32216.1 for x64 Copyright (C) Microsoft Corporation.  All rights reserved.

aws_pc_backup.c
Microsoft (R) Incremental Linker Version 14.35.32216.1 Copyright (C) Microsoft Corporation.  All rights reserved.

/out:aws_pc_backup.exe
aws_pc_backup.obj
C:\\Users\\jschw\\AppData\\Local\\Programs\\Python\\Python3112\\libs\\python311.lib
   Creating library aws_pc_backup.lib and object aws_pc_backup.exp

When I ran the program, I got this, though.  Obviously, it doesn't know about the requests package.  Do I have to link something in with the executable?

H:\Users\LindaJim\Documents\SourceCode\Software\aws_pc_backup\src\c>aws_pc_backup.exe -m:lb Traceback (most recent call last):
  File "src\\python\\aws_pc_backup_main.py", line 7, in init python.aws_pc_backup_main
ModuleNotFoundError: No module named 'requests'





-----Original Message-----
From: Barry <barry at barrys-emacs.org>
Sent: Tuesday, April 4, 2023 1:25 PM
To: Jim Schwartz <jschwar at sbcglobal.net>
Cc: Eryk Sun <eryksun at gmail.com>; python-list at python.org
Subject: Re: Windows installer from python source code without access to source code



> On 4 Apr 2023, at 16:28, Jim Schwartz <jschwar at sbcglobal.net> wrote:
> 
> ?Where can I download that cl program?  I've used gcc before, but I hear that cl can use a setup.py program to run the compile and link and create a windows .msi installer.  Is that true?  

It is part of visual studio C++.
Once you have that installed there are bat files that setup environment in the terminal.
Then you can use cl, nmake etc

Barry
> 
> -----Original Message-----
> From: Eryk Sun <eryksun at gmail.com>
> Sent: Friday, March 31, 2023 12:55 PM
> To: Jim Schwartz <jschwar at sbcglobal.net>
> Cc: python-list at python.org
> Subject: Re: Windows installer from python source code without access 
> to source code
> 
>> On 3/31/23, Jim Schwartz <jschwar at sbcglobal.net> wrote:
>> I want a windows installer to install my application that's written 
>> in python, but I don't want the end user to have access to my source code.
> 
> Cython can compile a script to C source code for a module or executable (--embed). The source can be compiled and linked normally.
> For example, the following builds a "hello.exe" executable based on a "hello.py" script.
> 
>> cython -3 --embed hello.py
>> set "PYI=C:\Program Files\Python311\include"
>> set "PYL=C:\Program Files\Python311\libs"
>> cl /I"%PYI%" hello.c /link /libpath:"%PYL%"
>> copy hello.exe embed
>> embed\hello.exe
>    Hello, World!
> 
> I extracted the complete embeddable distribution of Python 3.11 into the "embed" directory. You can reduce the size of the installation, if needed, by minimizing the zipped standard library and removing pyd extensions and DLLs that your application doesn't use.
> 
> The generated "hello.c" is large and not particularly easy to read, but here are some snippets [...]:
> 
>    [...]
>    /* Implementation of 'hello' */
>    static PyObject *__pyx_builtin_print;
>    static const char __pyx_k_main[] = "__main__";
>    static const char __pyx_k_name[] = "__name__";
>    static const char __pyx_k_test[] = "__test__";
>    static const char __pyx_k_print[] = "print";
>    static const char __pyx_k_Hello_World[] = "Hello, World!";
>    [...]
>      /* "hello.py":1
>     * print("Hello, World!")             # <<<<<<<<<<<<<<
>     */
>      __pyx_tuple_ = PyTuple_Pack(1, __pyx_kp_u_Hello_World);
>            if (unlikely(!__pyx_tuple_)) __PYX_ERR(0, 1, __pyx_L1_error)
>    [...]
>      /* "hello.py":1
>     * print("Hello, World!")             # <<<<<<<<<<<<<<
>     */
>      __pyx_t_1 = __Pyx_PyObject_Call(__pyx_builtin_print, __pyx_tuple_,
>                                      NULL);
>            if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 1, __pyx_L1_error)
>    [...]
>    int wmain(int argc, wchar_t **argv) {
>    [...]
>        if (argc && argv)
>            Py_SetProgramName(argv[0]);
>        Py_Initialize();
>        if (argc && argv)
>            PySys_SetArgv(argc, argv);
>    [...]
>              m = PyInit_hello();
>    [...]
>        if (Py_FinalizeEx() < 0)
>            return 2;
>    [...]
>        return 0;
>    [...]
> 
> --
> https://mail.python.org/mailman/listinfo/python-list
> 

-- 
https://mail.python.org/mailman/listinfo/python-list


From eryksun at gmail.com  Thu Apr  6 21:05:40 2023
From: eryksun at gmail.com (Eryk Sun)
Date: Thu, 6 Apr 2023 20:05:40 -0500
Subject: Windows installer from python source code without access to
 source code
In-Reply-To: <00cc01d968e2$36b094e0$a411bea0$@sbcglobal.net>
References: <01a501d96709$b3f86f70$1be94e50$@sbcglobal.net>
 <79F9B803-CE16-418C-B5CA-E88155DD42C5@barrys-emacs.org>
 <00b201d968c0$f3c1e380$db45aa80$@sbcglobal.net>
 <00cc01d968e2$36b094e0$a411bea0$@sbcglobal.net>
Message-ID: <CACL+1au1+E6r2wOhz6LPuo2_rkNtoFKc6bzvCYf_dKCtPUHZKA@mail.gmail.com>

On 4/6/23, Jim Schwartz <jschwar at sbcglobal.net> wrote:
> Never mind.  I found it on the web.  I needed to point my PYTHONPATH to
> sitepackages:

In most cases an application should be isolated from PYTHON*
environment variables. If you're creating a Python application or
embedding Python in an application, use the embeddable distribution,
and add any additional required sys.path directories to the included
"._pth" file (e.g. "python311._pth").

https://docs.python.org/3/library/sys_path_init.html#pth-files

From jschwar at sbcglobal.net  Fri Apr  7 06:33:25 2023
From: jschwar at sbcglobal.net (Jim Schwartz)
Date: Fri, 7 Apr 2023 05:33:25 -0500
Subject: Windows installer from python source code without access to
 source code
In-Reply-To: <CACL+1au1+E6r2wOhz6LPuo2_rkNtoFKc6bzvCYf_dKCtPUHZKA@mail.gmail.com>
References: <01a501d96709$b3f86f70$1be94e50$@sbcglobal.net>
 <79F9B803-CE16-418C-B5CA-E88155DD42C5@barrys-emacs.org>
 <00b201d968c0$f3c1e380$db45aa80$@sbcglobal.net>
 <00cc01d968e2$36b094e0$a411bea0$@sbcglobal.net>
 <CACL+1au1+E6r2wOhz6LPuo2_rkNtoFKc6bzvCYf_dKCtPUHZKA@mail.gmail.com>
Message-ID: <00ea01d9693c$62da53d0$288efb70$@sbcglobal.net>

Yea, thanks a lot.  That makes sense.  I was testing it on my development environment and got it to work that way, but I need to package it and test it on my dual boot "user" environment.  Thanks again for the help.  I've deleted that environment variable.

-----Original Message-----
From: Eryk Sun <eryksun at gmail.com> 
Sent: Thursday, April 6, 2023 8:06 PM
To: Jim Schwartz <jschwar at sbcglobal.net>
Cc: python-list at python.org
Subject: Re: Windows installer from python source code without access to source code

On 4/6/23, Jim Schwartz <jschwar at sbcglobal.net> wrote:
> Never mind.  I found it on the web.  I needed to point my PYTHONPATH 
> to
> sitepackages:

In most cases an application should be isolated from PYTHON* environment variables. If you're creating a Python application or embedding Python in an application, use the embeddable distribution, and add any additional required sys.path directories to the included "._pth" file (e.g. "python311._pth").

https://docs.python.org/3/library/sys_path_init.html#pth-files


From jschwar at sbcglobal.net  Fri Apr  7 08:28:20 2023
From: jschwar at sbcglobal.net (Jim Schwartz)
Date: Fri, 7 Apr 2023 07:28:20 -0500
Subject: Windows installer from python source code without access to
 source code
References: <01a501d96709$b3f86f70$1be94e50$@sbcglobal.net>
 <79F9B803-CE16-418C-B5CA-E88155DD42C5@barrys-emacs.org>
 <00b201d968c0$f3c1e380$db45aa80$@sbcglobal.net>
 <00cc01d968e2$36b094e0$a411bea0$@sbcglobal.net>
 <CACL+1au1+E6r2wOhz6LPuo2_rkNtoFKc6bzvCYf_dKCtPUHZKA@mail.gmail.com> 
Message-ID: <00ef01d9694c$70c6fba0$5254f2e0$@sbcglobal.net>

Is this what you'd recommend doing when distributing a cython-generated code compiled with cl.  I want to distribute this in a windows or other operating system installer.  I'll start with windows first.  I don't think I can use cx_freeze to create the installer, unless I know which files to include in the package and list them.

https://stackoverflow.com/questions/62390978/minimal-set-of-files-required-to-distribute-an-embed-cython-compiled-code-and-ma


-----Original Message-----
From: Jim Schwartz <jschwar at sbcglobal.net> 
Sent: Friday, April 7, 2023 5:33 AM
To: 'Eryk Sun' <eryksun at gmail.com>
Cc: 'python-list at python.org' <python-list at python.org>
Subject: RE: Windows installer from python source code without access to source code

Yea, thanks a lot.  That makes sense.  I was testing it on my development environment and got it to work that way, but I need to package it and test it on my dual boot "user" environment.  Thanks again for the help.  I've deleted that environment variable.

-----Original Message-----
From: Eryk Sun <eryksun at gmail.com>
Sent: Thursday, April 6, 2023 8:06 PM
To: Jim Schwartz <jschwar at sbcglobal.net>
Cc: python-list at python.org
Subject: Re: Windows installer from python source code without access to source code

On 4/6/23, Jim Schwartz <jschwar at sbcglobal.net> wrote:
> Never mind.  I found it on the web.  I needed to point my PYTHONPATH 
> to
> sitepackages:

In most cases an application should be isolated from PYTHON* environment variables. If you're creating a Python application or embedding Python in an application, use the embeddable distribution, and add any additional required sys.path directories to the included "._pth" file (e.g. "python311._pth").

https://docs.python.org/3/library/sys_path_init.html#pth-files


From nntp.mbourne at spamgourmet.com  Fri Apr  7 07:16:07 2023
From: nntp.mbourne at spamgourmet.com (Mark Bourne)
Date: Fri, 7 Apr 2023 12:16:07 +0100
Subject: Windows installer from python source code without access to
 source code
In-Reply-To: <mailman.3.1680821566.20750.python-list@python.org>
References: <CAN71zOyiMKNZ-YyDJ0R7zzT0Z1pa_VofnJCkb8nTciwk4JNwPw@mail.gmail.com>
 <B65CF219-9B1A-4725-9635-AF012FB057F1@sbcglobal.net>
 <30a87229-e0c7-f326-5e7a-702389b9b8c1@mrabarnett.plus.com>
 <mailman.3.1680821566.20750.python-list@python.org>
Message-ID: <u0ou1o$q0oa$1@dont-email.me>

MRAB wrote:
> On 2023-04-06 23:14, Jim Schwartz wrote:
>> ??? Could someone please help Carlos? ?I?m not sure how to answer his
>> ??? question
>>
>> ??? Sent from my iPhone
>>
>> ????? On Apr 6, 2023, at 3:53 PM, Carlos Fulqueris 
>> <cafulque at gmail.com> wrote:
>>
>> ????? ?
>> ????? Hello Jim,
>> ????? How can I unsubscribe?to this email list?
>> ????? I'm waiting for your response.
>> ????? Thanks
>> ????? Carlos
> [snip]
> At the bottom of the post is a link to the page that explains how to 
> unsubscribe. It's the link:
> 
>> ??????? https://mail.python.org/mailman/listinfo/python-list

I read this list via the newsgroup, so don't see those links.  However, 
I've always thought those Mailman pages are confusing for anyone not 
already familiar when it comes to subscribing.  The option to 
unsubscribe is right at the bottom of the page under the "Python-list 
Subscribers" section, which looks like it's only for list 
administrators!  Ignore the admin address and password boxes, just fill 
in your email address in the box below those and click "Unsubscribe or 
edit options".

-- 
Mark.

From jschwar at sbcglobal.net  Thu Apr  6 18:14:41 2023
From: jschwar at sbcglobal.net (Jim Schwartz)
Date: Thu, 6 Apr 2023 17:14:41 -0500
Subject: Windows installer from python source code without access to
 source code
In-Reply-To: <CAN71zOyiMKNZ-YyDJ0R7zzT0Z1pa_VofnJCkb8nTciwk4JNwPw@mail.gmail.com>
References: <CAN71zOyiMKNZ-YyDJ0R7zzT0Z1pa_VofnJCkb8nTciwk4JNwPw@mail.gmail.com>
Message-ID: <B65CF219-9B1A-4725-9635-AF012FB057F1@sbcglobal.net>

   Could someone please help Carlos? ?I?m not sure how to answer his
   question?

   Sent from my iPhone

     On Apr 6, 2023, at 3:53 PM, Carlos Fulqueris <cafulque at gmail.com> wrote:

     ?
     Hello Jim,
     How can I unsubscribe?to this email list?
     I'm waiting for your response.
     Thanks
     Carlos
     El jue, 6 abr 2023 a las 16:52, Jim Schwartz
     (<[1]jschwar at sbcglobal.net>) escribi?:

       I downloaded VS community 2022 and I know how to access the developer
       command prompt.? I'm using the one called x64 Native Tools Command
       Prompt for VS 2022

       I ran a command to compile my python code that was converted to c with
       the following command:

       H:\Users\LindaJim\Documents\SourceCode\Software\aws_pc_backup\src\c>cl
       /O2
       /I"C:\\Users\\jschw\\AppData\\Local\\Programs\\Python\\Python3112\\include\\"
       aws_pc_backup.c
       C:\\Users\\jschw\\AppData\\Local\\Programs\\Python\\Python3112\\libs\\python311.lib
       Microsoft (R) C/C++ Optimizing Compiler Version 19.35.32216.1 for x64
       Copyright (C) Microsoft Corporation.? All rights reserved.

       aws_pc_backup.c
       Microsoft (R) Incremental Linker Version 14.35.32216.1
       Copyright (C) Microsoft Corporation.? All rights reserved.

       /out:aws_pc_backup.exe
       aws_pc_backup.obj
       C:\\Users\\jschw\\AppData\\Local\\Programs\\Python\\Python3112\\libs\\python311.lib
       ? ?Creating library aws_pc_backup.lib and object aws_pc_backup.exp

       When I ran the program, I got this, though.? Obviously, it doesn't
       know about the requests package.? Do I have to link something in with
       the executable?

       H:\Users\LindaJim\Documents\SourceCode\Software\aws_pc_backup\src\c>aws_pc_backup.exe
       -m:lb
       Traceback (most recent call last):
       ? File "src\\python\\aws_pc_backup_main.py", line 7, in init
       python.aws_pc_backup_main
       ModuleNotFoundError: No module named 'requests'

       -----Original Message-----
       From: Barry <[2]barry at barrys-emacs.org>
       Sent: Tuesday, April 4, 2023 1:25 PM
       To: Jim Schwartz <[3]jschwar at sbcglobal.net>
       Cc: Eryk Sun <[4]eryksun at gmail.com>; [5]python-list at python.org
       Subject: Re: Windows installer from python source code without access
       to source code

       > On 4 Apr 2023, at 16:28, Jim Schwartz <[6]jschwar at sbcglobal.net>
       wrote:
       >
       > ?Where can I download that cl program?? I've used gcc before, but I
       hear that cl can use a setup.py program to run the compile and link
       and create a windows .msi installer.? Is that true??

       It is part of visual studio C++.
       Once you have that installed there are bat files that setup
       environment in the terminal.
       Then you can use cl, nmake etc

       Barry
       >
       > -----Original Message-----
       > From: Eryk Sun <[7]eryksun at gmail.com>
       > Sent: Friday, March 31, 2023 12:55 PM
       > To: Jim Schwartz <[8]jschwar at sbcglobal.net>
       > Cc: [9]python-list at python.org
       > Subject: Re: Windows installer from python source code without
       access
       > to source code
       >
       >> On 3/31/23, Jim Schwartz <[10]jschwar at sbcglobal.net> wrote:
       >> I want a windows installer to install my application that's written
       >> in python, but I don't want the end user to have access to my
       source code.
       >
       > Cython can compile a script to C source code for a module or
       executable (--embed). The source can be compiled and linked normally.
       > For example, the following builds a "hello.exe" executable based on
       a "hello.py" script.
       >
       >> cython -3 --embed hello.py
       >> set "PYI=C:\Program Files\Python311\include"
       >> set "PYL=C:\Program Files\Python311\libs"
       >> cl /I"%PYI%" hello.c /link /libpath:"%PYL%"
       >> copy hello.exe embed
       >> embed\hello.exe
       >? ? Hello, World!
       >
       > I extracted the complete embeddable distribution of Python 3.11 into
       the "embed" directory. You can reduce the size of the installation, if
       needed, by minimizing the zipped standard library and removing pyd
       extensions and DLLs that your application doesn't use.
       >
       > The generated "hello.c" is large and not particularly easy to read,
       but here are some snippets [...]:
       >
       >? ? [...]
       >? ? /* Implementation of 'hello' */
       >? ? static PyObject *__pyx_builtin_print;
       >? ? static const char __pyx_k_main[] = "__main__";
       >? ? static const char __pyx_k_name[] = "__name__";
       >? ? static const char __pyx_k_test[] = "__test__";
       >? ? static const char __pyx_k_print[] = "print";
       >? ? static const char __pyx_k_Hello_World[] = "Hello, World!";
       >? ? [...]
       >? ? ? /* "hello.py":1
       >? ? ?* print("Hello, World!")? ? ? ? ? ? ?# <<<<<<<<<<<<<<
       >? ? ?*/
       >? ? ? __pyx_tuple_ = PyTuple_Pack(1, __pyx_kp_u_Hello_World);
       >? ? ? ? ? ? if (unlikely(!__pyx_tuple_)) __PYX_ERR(0, 1,
       __pyx_L1_error)
       >? ? [...]
       >? ? ? /* "hello.py":1
       >? ? ?* print("Hello, World!")? ? ? ? ? ? ?# <<<<<<<<<<<<<<
       >? ? ?*/
       >? ? ? __pyx_t_1 = __Pyx_PyObject_Call(__pyx_builtin_print,
       __pyx_tuple_,
       >? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? NULL);
       >? ? ? ? ? ? if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 1, __pyx_L1_error)
       >? ? [...]
       >? ? int wmain(int argc, wchar_t **argv) {
       >? ? [...]
       >? ? ? ? if (argc && argv)
       >? ? ? ? ? ? Py_SetProgramName(argv[0]);
       >? ? ? ? Py_Initialize();
       >? ? ? ? if (argc && argv)
       >? ? ? ? ? ? PySys_SetArgv(argc, argv);
       >? ? [...]
       >? ? ? ? ? ? ? m = PyInit_hello();
       >? ? [...]
       >? ? ? ? if (Py_FinalizeEx() < 0)
       >? ? ? ? ? ? return 2;
       >? ? [...]
       >? ? ? ? return 0;
       >? ? [...]
       >
       > --
       > [11]https://mail.python.org/mailman/listinfo/python-list
       >

       --
       [12]https://mail.python.org/mailman/listinfo/python-list

References

   Visible links
   1. mailto:jschwar at sbcglobal.net
   2. mailto:barry at barrys-emacs.org
   3. mailto:jschwar at sbcglobal.net
   4. mailto:eryksun at gmail.com
   5. mailto:python-list at python.org
   6. mailto:jschwar at sbcglobal.net
   7. mailto:eryksun at gmail.com
   8. mailto:jschwar at sbcglobal.net
   9. mailto:python-list at python.org
  10. mailto:jschwar at sbcglobal.net
  11. https://mail.python.org/mailman/listinfo/python-list
  12. https://mail.python.org/mailman/listinfo/python-list

From jschwar at sbcglobal.net  Sun Apr  9 07:22:13 2023
From: jschwar at sbcglobal.net (Jim Schwartz)
Date: Sun, 9 Apr 2023 06:22:13 -0500
Subject: Windows installer from python source code without access to
 source code
In-Reply-To: <00ef01d9694c$70c6fba0$5254f2e0$@sbcglobal.net>
References: <01a501d96709$b3f86f70$1be94e50$@sbcglobal.net>
 <79F9B803-CE16-418C-B5CA-E88155DD42C5@barrys-emacs.org>
 <00b201d968c0$f3c1e380$db45aa80$@sbcglobal.net>
 <00cc01d968e2$36b094e0$a411bea0$@sbcglobal.net>
 <CACL+1au1+E6r2wOhz6LPuo2_rkNtoFKc6bzvCYf_dKCtPUHZKA@mail.gmail.com>
 <00ef01d9694c$70c6fba0$5254f2e0$@sbcglobal.net>
Message-ID: <004101d96ad5$89959440$9cc0bcc0$@sbcglobal.net>

Thanks everyone for the help.  I got my app working with using cython to
generate the c code, cl to compile, and visual studio to create the
setup.exe and the msi installer.  I appreciate the help.

-----Original Message-----
From: Python-list <python-list-bounces+jschwar=sbcglobal.net at python.org> On
Behalf Of Jim Schwartz
Sent: Friday, April 7, 2023 7:28 AM
To: 'Eryk Sun' <eryksun at gmail.com>
Cc: python-list at python.org
Subject: RE: Windows installer from python source code without access to
source code

Is this what you'd recommend doing when distributing a cython-generated code
compiled with cl.  I want to distribute this in a windows or other operating
system installer.  I'll start with windows first.  I don't think I can use
cx_freeze to create the installer, unless I know which files to include in
the package and list them.

https://stackoverflow.com/questions/62390978/minimal-set-of-files-required-t
o-distribute-an-embed-cython-compiled-code-and-ma


-----Original Message-----
From: Jim Schwartz <jschwar at sbcglobal.net>
Sent: Friday, April 7, 2023 5:33 AM
To: 'Eryk Sun' <eryksun at gmail.com>
Cc: 'python-list at python.org' <python-list at python.org>
Subject: RE: Windows installer from python source code without access to
source code

Yea, thanks a lot.  That makes sense.  I was testing it on my development
environment and got it to work that way, but I need to package it and test
it on my dual boot "user" environment.  Thanks again for the help.  I've
deleted that environment variable.

-----Original Message-----
From: Eryk Sun <eryksun at gmail.com>
Sent: Thursday, April 6, 2023 8:06 PM
To: Jim Schwartz <jschwar at sbcglobal.net>
Cc: python-list at python.org
Subject: Re: Windows installer from python source code without access to
source code

On 4/6/23, Jim Schwartz <jschwar at sbcglobal.net> wrote:
> Never mind.  I found it on the web.  I needed to point my PYTHONPATH 
> to
> sitepackages:

In most cases an application should be isolated from PYTHON* environment
variables. If you're creating a Python application or embedding Python in an
application, use the embeddable distribution, and add any additional
required sys.path directories to the included "._pth" file (e.g.
"python311._pth").

https://docs.python.org/3/library/sys_path_init.html#pth-files

--
https://mail.python.org/mailman/listinfo/python-list


From yogeshtirthkar-vendor at gic.com.sg  Sun Apr  9 22:14:36 2023
From: yogeshtirthkar-vendor at gic.com.sg (Yogesh Tirthkar)
Date: Mon, 10 Apr 2023 02:14:36 +0000
Subject: [Request for Assistance] To uninstall python installed in other
 user profile (Win 10)
In-Reply-To: <ebf102a0-3d5f-52e7-1967-cdc85a0ae08c@tompassin.net>
References: <OS0PR01MB57649B44D60F20D83009BAC3CF889@OS0PR01MB5764.jpnprd01.prod.outlook.com>
 <ebf102a0-3d5f-52e7-1967-cdc85a0ae08c@tompassin.net>
Message-ID: <OS0PR01MB5764E38E856450591B88F2C0CF959@OS0PR01MB5764.jpnprd01.prod.outlook.com>

Hi,

Is there any way I can uninstall python installed (as user) in someone else' account - without login as that user, but login as local admin ?

Regards,
Yogesh.
_________________________________________________________________________________
Technology Group | GIC Private Limited | 168 Robinson Road, #37-01, Capital Tower, Singapore 068912

-----Original Message-----
From: Python-list <python-list-bounces+yogeshtirthkar-vendor=gic.com.sg at python.org> On Behalf Of Thomas Passin
Sent: Wednesday, March 29, 2023 12:19 AM
To: python-list at python.org
Subject: Re: [Request for Assistance] To uninstall python installed in other user profile (Win 10)

[[External Mail] Do not click on links or attachment from unknown senders.]


On 3/28/2023 12:56 AM, Yogesh Tirthkar wrote:
> Hi Team,
>
> Could you please advise on the scenario in windows 10 machine : Where we need to uninstall/remove python from user profile A (installed by user A in its own profile folder) - via an admin user or system account.
>
> Currently when we try to uninstall it via admin/system account - it displays that the python product is not installed for this user (admin/system).
>
> Appreciate your assistance.

It depends on where the Python installation is located, but I would just delete the entire folder tree at %APPDATA%\Python\Python3xxx.

If Python was installed for all users, its main set of files will probably be in "c:\Program Files" and Window's "Add or Remove" page should remove it.

If it was installed just for User A, then the "Add or Remove" page will find it if run from User A's account.  If for some reason User A will not or cannot cooperate, the admin could change User A's password and then run "Add or Remove".  Of course the admin would not be able to change the pw back, but if User A is not cooperating maybe that wouldn't matter.

--
https://mail.python.org/mailman/listinfo/python-list
This email from GIC may contain confidential information. Unauthorised communication and disclosure of any information in this email is prohibited. If you are not the intended recipient, please notify the sender and delete this email immediately.


From list1 at tompassin.net  Sun Apr  9 23:34:07 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Sun, 9 Apr 2023 23:34:07 -0400
Subject: [Request for Assistance] To uninstall python installed in other
 user profile (Win 10)
In-Reply-To: <OS0PR01MB5764E38E856450591B88F2C0CF959@OS0PR01MB5764.jpnprd01.prod.outlook.com>
References: <OS0PR01MB57649B44D60F20D83009BAC3CF889@OS0PR01MB5764.jpnprd01.prod.outlook.com>
 <ebf102a0-3d5f-52e7-1967-cdc85a0ae08c@tompassin.net>
 <OS0PR01MB5764E38E856450591B88F2C0CF959@OS0PR01MB5764.jpnprd01.prod.outlook.com>
Message-ID: <22a0934f-399d-c6b6-3685-1c5be42906bf@tompassin.net>

On 4/9/2023 10:14 PM, Yogesh Tirthkar wrote:
> Hi,
> 
> Is there any way I can uninstall python installed (as user) in someone else' account - without login as that user, but login as local admin ?

It depends on whether you can use that user's password. With the 
password, it's very feasible.  Without it, some people seem to have 
found ways.  There some discussion of this here -

https://serverfault.com/questions/773038/run-as-a-different-user-without-a-password-from-an-elevated-prompt-in-windows

> Technology Group | GIC Private Limited | 168 Robinson Road, #37-01, Capital Tower, Singapore 068912
> 
> -----Original Message-----
> From: Python-list <python-list-bounces+yogeshtirthkar-vendor=gic.com.sg at python.org> On Behalf Of Thomas Passin
> Sent: Wednesday, March 29, 2023 12:19 AM
> To: python-list at python.org
> Subject: Re: [Request for Assistance] To uninstall python installed in other user profile (Win 10)
> 
> [[External Mail] Do not click on links or attachment from unknown senders.]
> 
> 
> On 3/28/2023 12:56 AM, Yogesh Tirthkar wrote:
>> Hi Team,
>>
>> Could you please advise on the scenario in windows 10 machine : Where we need to uninstall/remove python from user profile A (installed by user A in its own profile folder) - via an admin user or system account.
>>
>> Currently when we try to uninstall it via admin/system account - it displays that the python product is not installed for this user (admin/system).
>>
>> Appreciate your assistance.
> 
> It depends on where the Python installation is located, but I would just delete the entire folder tree at %APPDATA%\Python\Python3xxx.
> 
> If Python was installed for all users, its main set of files will probably be in "c:\Program Files" and Window's "Add or Remove" page should remove it.
> 
> If it was installed just for User A, then the "Add or Remove" page will find it if run from User A's account.  If for some reason User A will not or cannot cooperate, the admin could change User A's password and then run "Add or Remove".  Of course the admin would not be able to change the pw back, but if User A is not cooperating maybe that wouldn't matter.
> 
> --
> https://mail.python.org/mailman/listinfo/python-list
> This email from GIC may contain confidential information. Unauthorised communication and disclosure of any information in this email is prohibited. If you are not the intended recipient, please notify the sender and delete this email immediately.
> 


From yogeshtirthkar-vendor at gic.com.sg  Mon Apr 10 02:19:40 2023
From: yogeshtirthkar-vendor at gic.com.sg (Yogesh Tirthkar)
Date: Mon, 10 Apr 2023 06:19:40 +0000
Subject: [Request for Assistance] To uninstall python installed in other
 user profile (Win 10)
In-Reply-To: <CAFuhuzmbbZr2QJg+NXDbY-ZPjtkEHmCkSPAvJw8JoZVeWKCCcA@mail.gmail.com>
References: <OS0PR01MB57649B44D60F20D83009BAC3CF889@OS0PR01MB5764.jpnprd01.prod.outlook.com>
 <CAFuhuzmbbZr2QJg+NXDbY-ZPjtkEHmCkSPAvJw8JoZVeWKCCcA@mail.gmail.com>
Message-ID: <OS0PR01MB5764FD8BC7B6C6BE130A3983CF959@OS0PR01MB5764.jpnprd01.prod.outlook.com>

Hello,

Thank you for your response.

May I know how to uninstall it from user A profile ? if user A is no longer available.

Is there any means - where I can use local admin account to uninstall the app (installed in User A profile, without user A?s intervention)

Regards,
Yogesh.

From: Sravan Kumar Chitikesi <sravan.chitikesi at iprotechs.com>
Sent: Monday, April 10, 2023 2:17 PM
To: Yogesh Tirthkar <yogeshtirthkar-vendor at gic.com.sg>
Cc: python-list at python.org
Subject: Re: [Request for Assistance] To uninstall python installed in other user profile (Win 10)

[cid:image001.png at 01D96BB7.7B62F3D0]

If Python was installed by user A in their own profile folder, it is likely that it was installed just for that user. In this case, you may need to log in as user A to uninstall Python from their profile. Have you tried logging in as user A and uninstalling Python from there?

Regards,
Sravan Chitikesi
AWS Solutions Architect - Associate


On Tue, Mar 28, 2023 at 11:30?AM Yogesh Tirthkar <yogeshtirthkar-vendor at gic.com.sg<mailto:yogeshtirthkar-vendor at gic.com.sg>> wrote:
Hi Team,

Could you please advise on the scenario in windows 10 machine : Where we need to uninstall/remove python from user profile A (installed by user A in its own profile folder) - via an admin user or system account.

Currently when we try to uninstall it via admin/system account - it displays that the python product is not installed for this user (admin/system).

Appreciate your assistance.


Regards,
Yogesh.
_________________________________________________________________________________
Technology Group | GIC Private Limited | 168 Robinson Road, #37-01, Capital Tower, Singapore 068912


This email from GIC may contain confidential information. Unauthorised communication and disclosure of any information in this email is prohibited. If you are not the intended recipient, please notify the sender and delete this email immediately.
--
https://mail.python.org/mailman/listinfo/python-list

This email from GIC may contain confidential information. Unauthorised communication and disclosure of any information in this email is prohibited. If you are not the intended recipient, please notify the sender and delete this email immediately.

From cl at isbd.net  Sun Apr  9 04:40:51 2023
From: cl at isbd.net (Chris Green)
Date: Sun, 9 Apr 2023 09:40:51 +0100
Subject: Looking for package/library to extract MP4 metadata
Message-ID: <j9aagj-8vfa1.ln1@esprimo.zbmc.eu>

I'm looking for a Python (3) library to access (read only at present)
the metadata in MP4 video files, in particular I want to get at dates
and times.

What's available to do this?  Ideally something available in the
Ubuntu repositories but I can install with PIP if necessary.

-- 
Chris Green
?

From bowman at montana.com  Sun Apr  9 12:31:46 2023
From: bowman at montana.com (rbowman)
Date: 9 Apr 2023 16:31:46 GMT
Subject: Looking for package/library to extract MP4 metadata
References: <j9aagj-8vfa1.ln1@esprimo.zbmc.eu>
Message-ID: <k9g7jiF92uqU1@mid.individual.net>

On Sun, 9 Apr 2023 09:40:51 +0100, Chris Green wrote:

> I'm looking for a Python (3) library to access (read only at present)
> the metadata in MP4 video files, in particular I want to get at dates
> and times.
> 
> What's available to do this?  Ideally something available in the Ubuntu
> repositories but I can install with PIP if necessary.

https://mutagen.readthedocs.io/en/latest/


From cl at isbd.net  Sun Apr  9 13:05:56 2023
From: cl at isbd.net (Chris Green)
Date: Sun, 9 Apr 2023 18:05:56 +0100
Subject: Looking for package/library to extract MP4 metadata
References: <j9aagj-8vfa1.ln1@esprimo.zbmc.eu>
 <k9g7jiF92uqU1@mid.individual.net>
Message-ID: <ks7bgj-nmcc1.ln1@esprimo.zbmc.eu>

rbowman <bowman at montana.com> wrote:
> On Sun, 9 Apr 2023 09:40:51 +0100, Chris Green wrote:
> 
> > I'm looking for a Python (3) library to access (read only at present)
> > the metadata in MP4 video files, in particular I want to get at dates
> > and times.
> > 
> > What's available to do this?  Ideally something available in the Ubuntu
> > repositories but I can install with PIP if necessary.
> 
> https://mutagen.readthedocs.io/en/latest/
> 
Oh, OK, thanks. I already have mutagen installed on my systems
because I use QuodLibet.  I hadn't realised it would let me look at
MP4 video files but I guess it should.

-- 
Chris Green
?

From nospam at please.ty  Sun Apr  9 14:23:52 2023
From: nospam at please.ty (jak)
Date: Sun, 9 Apr 2023 20:23:52 +0200
Subject: Looking for package/library to extract MP4 metadata
In-Reply-To: <k9g7jiF92uqU1@mid.individual.net>
References: <j9aagj-8vfa1.ln1@esprimo.zbmc.eu>
 <k9g7jiF92uqU1@mid.individual.net>
Message-ID: <u0uvro$1qjbq$1@dont-email.me>

rbowman ha scritto:
> On Sun, 9 Apr 2023 09:40:51 +0100, Chris Green wrote:
> 
>> I'm looking for a Python (3) library to access (read only at present)
>> the metadata in MP4 video files, in particular I want to get at dates
>> and times.
>>
>> What's available to do this?  Ideally something available in the Ubuntu
>> repositories but I can install with PIP if necessary.
> 
> https://mutagen.readthedocs.io/en/latest/
> 

I thought it only dealt about audio.

From cl at isbd.net  Sun Apr  9 15:19:37 2023
From: cl at isbd.net (Chris Green)
Date: Sun, 9 Apr 2023 20:19:37 +0100
Subject: Looking for package/library to extract MP4 metadata
References: <j9aagj-8vfa1.ln1@esprimo.zbmc.eu>
 <k9g7jiF92uqU1@mid.individual.net> <u0uvro$1qjbq$1@dont-email.me>
Message-ID: <9nfbgj-90uc1.ln1@esprimo.zbmc.eu>

jak <nospam at please.ty> wrote:
> rbowman ha scritto:
> > On Sun, 9 Apr 2023 09:40:51 +0100, Chris Green wrote:
> > 
> >> I'm looking for a Python (3) library to access (read only at present)
> >> the metadata in MP4 video files, in particular I want to get at dates
> >> and times.
> >>
> >> What's available to do this?  Ideally something available in the Ubuntu
> >> repositories but I can install with PIP if necessary.
> > 
> > https://mutagen.readthedocs.io/en/latest/
> > 
> 
> I thought it only dealt about audio.

That's why I hadn't thought it would help me as I'm after getting
metadata from an MP4 video file but I guess the metadata format may be
the same regardless of whether it's video or audio.

-- 
Chris Green
?

From bowman at montana.com  Sun Apr  9 23:01:00 2023
From: bowman at montana.com (rbowman)
Date: 10 Apr 2023 03:01:00 GMT
Subject: Looking for package/library to extract MP4 metadata
References: <j9aagj-8vfa1.ln1@esprimo.zbmc.eu>
 <k9g7jiF92uqU1@mid.individual.net> <u0uvro$1qjbq$1@dont-email.me>
 <9nfbgj-90uc1.ln1@esprimo.zbmc.eu>
Message-ID: <k9hcfcFeipoU1@mid.individual.net>

On Sun, 9 Apr 2023 20:19:37 +0100, Chris Green wrote:

> That's why I hadn't thought it would help me as I'm after getting
> metadata from an MP4 video file but I guess the metadata format may be
> the same regardless of whether it's video or audio.

If yuo chase back through the various ISOs you tend to wind up at Apple's 
QuickTime container format as the parent. The compression methods for the 
media etc will differ but at least the structure of the file is 
documented.  It's tedious but you can walk through the atoms (chunks, 
blocks, boxes)  and find the metadata.

There is the disclaimer

https://mutagen.readthedocs.io/en/latest/user/mp4.html

so it may not work for your intended purposes, particularly for modifying 
the data. That gets tricky since it may change the size of the chunk. 

https://pypi.org/project/tinytag/

is another one but it's only for reading the metadata.


From nospam at please.ty  Mon Apr 10 06:59:00 2023
From: nospam at please.ty (jak)
Date: Mon, 10 Apr 2023 12:59:00 +0200
Subject: Looking for package/library to extract MP4 metadata
In-Reply-To: <9nfbgj-90uc1.ln1@esprimo.zbmc.eu>
References: <j9aagj-8vfa1.ln1@esprimo.zbmc.eu>
 <k9g7jiF92uqU1@mid.individual.net> <u0uvro$1qjbq$1@dont-email.me>
 <9nfbgj-90uc1.ln1@esprimo.zbmc.eu>
Message-ID: <u10q5l$25d6i$1@dont-email.me>

Chris Green ha scritto:
> jak <nospam at please.ty> wrote:
>> rbowman ha scritto:
>>> On Sun, 9 Apr 2023 09:40:51 +0100, Chris Green wrote:
>>>
>>>> I'm looking for a Python (3) library to access (read only at present)
>>>> the metadata in MP4 video files, in particular I want to get at dates
>>>> and times.
>>>>
>>>> What's available to do this?  Ideally something available in the Ubuntu
>>>> repositories but I can install with PIP if necessary.
>>>
>>> https://mutagen.readthedocs.io/en/latest/
>>>
>>
>> I thought it only dealt about audio.
> 
> That's why I hadn't thought it would help me as I'm after getting
> metadata from an MP4 video file but I guess the metadata format may be
> the same regardless of whether it's video or audio.
> 

Easiest way I found was run ffprobe command via popen. It can output the
information you need in json format which is easily readable with the
json library.

command:
ffprobe -v warning -i "input.mp4" -show_streams -of json
python:
Popen(command, stderr=STDOUT, stdout=PIPE, encoding='utf8')
json:
json.loads(''.join(p.stdout.readlines()))

It's easy to find a version of ffmpeg/ffprobe for every platform.

From cl at isbd.net  Mon Apr 10 08:10:05 2023
From: cl at isbd.net (Chris Green)
Date: Mon, 10 Apr 2023 13:10:05 +0100
Subject: Looking for package/library to extract MP4 metadata
References: <j9aagj-8vfa1.ln1@esprimo.zbmc.eu>
 <k9g7jiF92uqU1@mid.individual.net> <u0uvro$1qjbq$1@dont-email.me>
 <9nfbgj-90uc1.ln1@esprimo.zbmc.eu> <u10q5l$25d6i$1@dont-email.me>
Message-ID: <ttadgj-mdng1.ln1@esprimo.zbmc.eu>

jak <nospam at please.ty> wrote:
> Chris Green ha scritto:
> > jak <nospam at please.ty> wrote:
> >> rbowman ha scritto:
> >>> On Sun, 9 Apr 2023 09:40:51 +0100, Chris Green wrote:
> >>>
> >>>> I'm looking for a Python (3) library to access (read only at present)
> >>>> the metadata in MP4 video files, in particular I want to get at dates
> >>>> and times.
> >>>>
> >>>> What's available to do this?  Ideally something available in the Ubuntu
> >>>> repositories but I can install with PIP if necessary.
> >>>
> >>> https://mutagen.readthedocs.io/en/latest/
> >>>
> >>
> >> I thought it only dealt about audio.
> > 
> > That's why I hadn't thought it would help me as I'm after getting
> > metadata from an MP4 video file but I guess the metadata format may be
> > the same regardless of whether it's video or audio.
> > 
> 
> Easiest way I found was run ffprobe command via popen. It can output the
> information you need in json format which is easily readable with the
> json library.
> 
> command:
> ffprobe -v warning -i "input.mp4" -show_streams -of json
> python:
> Popen(command, stderr=STDOUT, stdout=PIPE, encoding='utf8')
> json:
> json.loads(''.join(p.stdout.readlines()))
> 
> It's easy to find a version of ffmpeg/ffprobe for every platform.

Thank you, that worked straight away, ffprobe is installed on my
systems already and I can probably just grep for the tag I want as all
I'm looking for is the date of its creation which appears (twice) with
the tag "creation_time". 

This is just to handle the occasional MP4 that a python program which
basically manages JPEGs can't handle.  It throws an exception so I can
just get that to run a simple bash script to get the creation date.

-- 
Chris Green
?

From sravan.chitikesi at iprotechs.com  Mon Apr 10 02:16:57 2023
From: sravan.chitikesi at iprotechs.com (Sravan Kumar Chitikesi)
Date: Mon, 10 Apr 2023 02:16:57 -0400
Subject: [Request for Assistance] To uninstall python installed in other
 user profile (Win 10)
In-Reply-To: <OS0PR01MB57649B44D60F20D83009BAC3CF889@OS0PR01MB5764.jpnprd01.prod.outlook.com>
References: <OS0PR01MB57649B44D60F20D83009BAC3CF889@OS0PR01MB5764.jpnprd01.prod.outlook.com>
Message-ID: <CAFuhuzmbbZr2QJg+NXDbY-ZPjtkEHmCkSPAvJw8JoZVeWKCCcA@mail.gmail.com>

If Python was installed by user A in their own profile folder, it is likely
that it was installed just for that user. In this case, you may need to log
in as user A to uninstall Python from their profile. Have you tried logging
in as user A and uninstalling Python from there?

Regards,
*Sravan Chitikesi*
AWS Solutions Architect - Associate


On Tue, Mar 28, 2023 at 11:30?AM Yogesh Tirthkar <
yogeshtirthkar-vendor at gic.com.sg> wrote:

> Hi Team,
>
> Could you please advise on the scenario in windows 10 machine : Where we
> need to uninstall/remove python from user profile A (installed by user A in
> its own profile folder) - via an admin user or system account.
>
> Currently when we try to uninstall it via admin/system account - it
> displays that the python product is not installed for this user
> (admin/system).
>
> Appreciate your assistance.
>
>
> Regards,
> Yogesh.
>
> _________________________________________________________________________________
> Technology Group | GIC Private Limited | 168 Robinson Road, #37-01,
> Capital Tower, Singapore 068912
>
>
> This email from GIC may contain confidential information. Unauthorised
> communication and disclosure of any information in this email is
> prohibited. If you are not the intended recipient, please notify the sender
> and delete this email immediately.
> --
> https://mail.python.org/mailman/listinfo/python-list
>

From 00jhenryg at gmail.com  Mon Apr 10 09:59:30 2023
From: 00jhenryg at gmail.com (Jack Gilbert)
Date: Mon, 10 Apr 2023 08:59:30 -0500
Subject: Need help please
Message-ID: <CAHPx8a_niOv7suVeCNjhdLs1HBm=dTu07WyX8F0WyAGpnTRSSQ@mail.gmail.com>

I D/L 3.11.3, I can see it in CMD

running W10 64bit

I have IDL on my desktop,

HOW do I get 3.11.3 on my desktop?

Thanks

Jack g

From sravan.chitikesi at iprotechs.com  Mon Apr 10 12:41:46 2023
From: sravan.chitikesi at iprotechs.com (Sravan Kumar Chitikesi)
Date: Mon, 10 Apr 2023 12:41:46 -0400
Subject: Need help please
In-Reply-To: <CAHPx8a_niOv7suVeCNjhdLs1HBm=dTu07WyX8F0WyAGpnTRSSQ@mail.gmail.com>
References: <CAHPx8a_niOv7suVeCNjhdLs1HBm=dTu07WyX8F0WyAGpnTRSSQ@mail.gmail.com>
Message-ID: <CAFuhuz=+Wf0vXA3dSFNz_wPYwM9873=_Ms7nqFiBrcQVZK+9Ag@mail.gmail.com>

use where cmd to find out the path of the binary and create a shortcut to
that file on desktop

Regards,
*Sravan Chitikesi*
AWS Solutions Architect - Associate


On Mon, Apr 10, 2023 at 10:03?AM Jack Gilbert <00jhenryg at gmail.com> wrote:

> I D/L 3.11.3, I can see it in CMD
>
> running W10 64bit
>
> I have IDL on my desktop,
>
> HOW do I get 3.11.3 on my desktop?
>
> Thanks
>
> Jack g
> --
> https://mail.python.org/mailman/listinfo/python-list
>

From list1 at tompassin.net  Mon Apr 10 13:17:41 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Mon, 10 Apr 2023 13:17:41 -0400
Subject: Need help please
In-Reply-To: <CAHPx8a_niOv7suVeCNjhdLs1HBm=dTu07WyX8F0WyAGpnTRSSQ@mail.gmail.com>
References: <CAHPx8a_niOv7suVeCNjhdLs1HBm=dTu07WyX8F0WyAGpnTRSSQ@mail.gmail.com>
Message-ID: <752c8b98-0487-20f9-1bf7-8e7b9375ff78@tompassin.net>

On 4/10/2023 9:59 AM, Jack Gilbert wrote:
> I D/L 3.11.3, I can see it in CMD
> 
> running W10 64bit
> 
> I have IDL on my desktop,
> 
> HOW do I get 3.11.3 on my desktop?

If you mean "How can I create a shortcut to Python 3.11.3 on my desktop 
that opens an interactive Python session", here is one way:

1. Find where your Python 3.11.3 program has been installed.  On the 
command line in a console, type:

py -c "import sys; print(sys.executable)"

You will get a response like this:

C:\Users\tom\AppData\Local\Programs\Python\Python311\python.exe

NOTE:  If the "py" command is not on your computer or does not open 
Python 3.11, then open a python 3.11 session and type the same commands:

import sys
print(sys.executable)

2. Open the Windows file browser ("Windows Explorer") and navigate to 
that directory.  On my computer this is

C:\Users\tom\AppData\Local\Programs\Python\Python311

3. Press and hold both the CTRL and SHIFT keys down at the same time, 
and with the mouse drag the icon for "python.exe" to a blank space on 
the desktop.  This will not drag the program itself but will create a 
shortcut and drag that.

4. Test the new shortcut by double-clicking on it and seeing that a new 
console window opens with the Python interpreter running in it.

If you do not like the size, shape, or font of this new console, change 
them by clicking on the icon in the upper left, then selecting 
"Properties", and making changes in the dialog box that opens.  The new 
choices will be used whenever you use this shortcut again.

5. The new shortcut will probably be named "python.ex".  I suggest that 
you rename it to "Python 3.11".  This way you can create other python 
shortcuts without having their names conflict.

From list1 at tompassin.net  Mon Apr 10 08:29:06 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Mon, 10 Apr 2023 08:29:06 -0400
Subject: [Request for Assistance] To uninstall python installed in other
 user profile (Win 10)
In-Reply-To: <OS0PR01MB5764FD8BC7B6C6BE130A3983CF959@OS0PR01MB5764.jpnprd01.prod.outlook.com>
References: <OS0PR01MB57649B44D60F20D83009BAC3CF889@OS0PR01MB5764.jpnprd01.prod.outlook.com>
 <CAFuhuzmbbZr2QJg+NXDbY-ZPjtkEHmCkSPAvJw8JoZVeWKCCcA@mail.gmail.com>
 <OS0PR01MB5764FD8BC7B6C6BE130A3983CF959@OS0PR01MB5764.jpnprd01.prod.outlook.com>
Message-ID: <188650b9-c470-ffa0-504c-2e29ae4a96df@tompassin.net>

On 4/10/2023 2:19 AM, Yogesh Tirthkar wrote:
> Hello,
> 
> Thank you for your response.
> 
> May I know how to uninstall it from user A profile ? if user A is no longer available.
> 
> Is there any means - where I can use local admin account to uninstall the app (installed in User A profile, without user A?s intervention)

If user A is no longer available, then an administrator can change the 
password for User A and then, logged into the A account, perform the 
un-install.


> From: Sravan Kumar Chitikesi <sravan.chitikesi at iprotechs.com>
> Sent: Monday, April 10, 2023 2:17 PM
> To: Yogesh Tirthkar <yogeshtirthkar-vendor at gic.com.sg>
> Cc: python-list at python.org
> Subject: Re: [Request for Assistance] To uninstall python installed in other user profile (Win 10)
> 
> [cid:image001.png at 01D96BB7.7B62F3D0]
> 
> If Python was installed by user A in their own profile folder, it is likely that it was installed just for that user. In this case, you may need to log in as user A to uninstall Python from their profile. Have you tried logging in as user A and uninstalling Python from there?
> 
> Regards,
> Sravan Chitikesi
> AWS Solutions Architect - Associate
> 
> 
> On Tue, Mar 28, 2023 at 11:30?AM Yogesh Tirthkar <yogeshtirthkar-vendor at gic.com.sg<mailto:yogeshtirthkar-vendor at gic.com.sg>> wrote:
> Hi Team,
> 
> Could you please advise on the scenario in windows 10 machine : Where we need to uninstall/remove python from user profile A (installed by user A in its own profile folder) - via an admin user or system account.
> 
> Currently when we try to uninstall it via admin/system account - it displays that the python product is not installed for this user (admin/system).
> 


From cs at cskk.id.au  Mon Apr 10 20:27:35 2023
From: cs at cskk.id.au (Cameron Simpson)
Date: Tue, 11 Apr 2023 10:27:35 +1000
Subject: Looking for package/library to extract MP4 metadata
In-Reply-To: <ttadgj-mdng1.ln1@esprimo.zbmc.eu>
References: <ttadgj-mdng1.ln1@esprimo.zbmc.eu>
Message-ID: <ZDSpd3o4E6l1+glO@cskk.homeip.net>

On 10Apr2023 13:10, Chris Green <cl at isbd.net> wrote:
>> command:
>> ffprobe -v warning -i "input.mp4" -show_streams -of json
>> python:
>> Popen(command, stderr=STDOUT, stdout=PIPE, encoding='utf8')
>> json:
>> json.loads(''.join(p.stdout.readlines()))
>>
>> It's easy to find a version of ffmpeg/ffprobe for every platform.
>
>Thank you, that worked straight away, ffprobe is installed on my
>systems already and I can probably just grep for the tag I want as all
>I'm looking for is the date of its creation which appears (twice) with
>the tag "creation_time".
>
>This is just to handle the occasional MP4 that a python program which
>basically manages JPEGs can't handle.  It throws an exception so I can
>just get that to run a simple bash script to get the creation date.

Yes, ffprobe is great, particularly the JSON output mode, very parsable.

If you want to get into the knitty gritty you could try my `cs.iso14496` 
package, which has a full MP4/MOV parser and a hook for getting the 
metadata.

Not as convenient as ffprobe, but if you care about the innards...

Cheers,
Cameron Simpson <cs at cskk.id.au>

From miked at dewhirst.com.au  Tue Apr 11 00:12:45 2023
From: miked at dewhirst.com.au (Mike Dewhirst)
Date: Tue, 11 Apr 2023 14:12:45 +1000
Subject: Christoph Gohlke and compiled packages
Message-ID: <f3b7ba9f-adb1-9a44-8c9c-2ee408dbcb52@dewhirst.com.au>

It seems Christoph Gohlke has been cut adrift and his extremely valuable 
web page ...

https://www.lfd.uci.edu/~gohlke/pythonlibs/

... turned into an archive getting staler by the day.

What does the Python Software Foundation and the community think about this?

Cheers

Mike

From rosuav at gmail.com  Tue Apr 11 03:21:14 2023
From: rosuav at gmail.com (Chris Angelico)
Date: Tue, 11 Apr 2023 17:21:14 +1000
Subject: Christoph Gohlke and compiled packages
In-Reply-To: <f3b7ba9f-adb1-9a44-8c9c-2ee408dbcb52@dewhirst.com.au>
References: <f3b7ba9f-adb1-9a44-8c9c-2ee408dbcb52@dewhirst.com.au>
Message-ID: <CAPTjJmpO0x3acr4mKfs9zCtwy6E7KGD_7_8jQqxbQL2z5ep0Wg@mail.gmail.com>

On Tue, 11 Apr 2023 at 14:20, Mike Dewhirst <miked at dewhirst.com.au> wrote:
>
> It seems Christoph Gohlke has been cut adrift and his extremely valuable
> web page ...
>
> https://www.lfd.uci.edu/~gohlke/pythonlibs/
>
> ... turned into an archive getting staler by the day.
>
> What does the Python Software Foundation and the community think about this?

My personal view? Windows is *really really really* hard to support,
and ONE PERSON did a stellar job of supporting the platform for an
incredibly long job.

I don't know if he'll ever read this, but if he does, thank you
Christoph for your amazing contribution to the community.

The fact that we have a problem now is a testament to the length of
time that we *didn't* have a problem, thanks to him.

ChrisA

From miked at dewhirst.com.au  Tue Apr 11 04:22:20 2023
From: miked at dewhirst.com.au (Mike Dewhirst)
Date: Tue, 11 Apr 2023 18:22:20 +1000
Subject: Christoph Gohlke and compiled packages
In-Reply-To: <CAPTjJmpO0x3acr4mKfs9zCtwy6E7KGD_7_8jQqxbQL2z5ep0Wg@mail.gmail.com>
References: <f3b7ba9f-adb1-9a44-8c9c-2ee408dbcb52@dewhirst.com.au>
 <CAPTjJmpO0x3acr4mKfs9zCtwy6E7KGD_7_8jQqxbQL2z5ep0Wg@mail.gmail.com>
Message-ID: <384a4082-9bcf-4e7b-c1dc-466dcec22443@dewhirst.com.au>

On 11/04/2023 5:21 pm, Chris Angelico wrote:
> On Tue, 11 Apr 2023 at 14:20, Mike Dewhirst<miked at dewhirst.com.au>  wrote:
>> It seems Christoph Gohlke has been cut adrift and his extremely valuable
>> web page ...
>>
>> https://www.lfd.uci.edu/~gohlke/pythonlibs/
>>
>> ... turned into an archive getting staler by the day.
>>
>> What does the Python Software Foundation and the community think about this?
> My personal view? Windows is *really really really* hard to support,
> and ONE PERSON did a stellar job of supporting the platform for an
> incredibly long job.

I have to agree - but what you are really saying is that without 
Christoph, Python on Windows is

*really really really*

not viable.

Mike


>
> I don't know if he'll ever read this, but if he does, thank you
> Christoph for your amazing contribution to the community.
>
> The fact that we have a problem now is a testament to the length of
> time that we *didn't* have a problem, thanks to him.
>
> ChrisA


-- 
Signed email is an absolute defence against phishing. This email has
been signed with my private key. If you import my public key you can
automatically decrypt my signature and be sure it came from me. Your
email software can handle signing.

-------------- next part --------------
A non-text attachment was scrubbed...
Name: OpenPGP_signature
Type: application/pgp-signature
Size: 495 bytes
Desc: OpenPGP digital signature
URL: <https://mail.python.org/pipermail/python-list/attachments/20230411/d3b97ae3/attachment.sig>

From rosuav at gmail.com  Tue Apr 11 04:49:30 2023
From: rosuav at gmail.com (Chris Angelico)
Date: Tue, 11 Apr 2023 18:49:30 +1000
Subject: Christoph Gohlke and compiled packages
In-Reply-To: <384a4082-9bcf-4e7b-c1dc-466dcec22443@dewhirst.com.au>
References: <f3b7ba9f-adb1-9a44-8c9c-2ee408dbcb52@dewhirst.com.au>
 <CAPTjJmpO0x3acr4mKfs9zCtwy6E7KGD_7_8jQqxbQL2z5ep0Wg@mail.gmail.com>
 <384a4082-9bcf-4e7b-c1dc-466dcec22443@dewhirst.com.au>
Message-ID: <CAPTjJmq0dEF7_dxOnp7jyTHbEd0eWaC54oHykuWApU8dHbMzRA@mail.gmail.com>

On Tue, 11 Apr 2023 at 18:22, Mike Dewhirst <miked at dewhirst.com.au> wrote:
>
> On 11/04/2023 5:21 pm, Chris Angelico wrote:
>
>> My personal view? Windows is *really really really* hard to support,
>> and ONE PERSON did a stellar job of supporting the platform for an
>> incredibly long job.
>
>
> I have to agree - but what you are really saying is that without Christoph, Python on Windows is
>
> *really really really*
>
> not viable.
>

This may well be true, but before writing Windows off completely [1],
do check out some of the commercial distributions. It may be that it's
possible to do everything through Conda, for instance.

[1] Much as I would like to, this isn't a good idea

From jschwar at sbcglobal.net  Tue Apr 11 06:14:58 2023
From: jschwar at sbcglobal.net (Jim Schwartz)
Date: Tue, 11 Apr 2023 05:14:58 -0500
Subject: Christoph Gohlke and compiled packages
In-Reply-To: <CAPTjJmpO0x3acr4mKfs9zCtwy6E7KGD_7_8jQqxbQL2z5ep0Wg@mail.gmail.com>
References: <CAPTjJmpO0x3acr4mKfs9zCtwy6E7KGD_7_8jQqxbQL2z5ep0Wg@mail.gmail.com>
Message-ID: <DF942C7B-7D3F-4475-A7CB-DE51A7367046@sbcglobal.net>

What?s the problem now?  Is it with python on windows?  I use python on windows so I?d like to know. Thanks

Sent from my iPhone

> On Apr 11, 2023, at 2:24 AM, Chris Angelico <rosuav at gmail.com> wrote:
> 
> ?On Tue, 11 Apr 2023 at 14:20, Mike Dewhirst <miked at dewhirst.com.au> wrote:
>> 
>> It seems Christoph Gohlke has been cut adrift and his extremely valuable
>> web page ...
>> 
>> https://www.lfd.uci.edu/~gohlke/pythonlibs/
>> 
>> ... turned into an archive getting staler by the day.
>> 
>> What does the Python Software Foundation and the community think about this?
> 
> My personal view? Windows is *really really really* hard to support,
> and ONE PERSON did a stellar job of supporting the platform for an
> incredibly long job.
> 
> I don't know if he'll ever read this, but if he does, thank you
> Christoph for your amazing contribution to the community.
> 
> The fact that we have a problem now is a testament to the length of
> time that we *didn't* have a problem, thanks to him.
> 
> ChrisA
> -- 
> https://mail.python.org/mailman/listinfo/python-list


From rosuav at gmail.com  Tue Apr 11 06:58:22 2023
From: rosuav at gmail.com (Chris Angelico)
Date: Tue, 11 Apr 2023 20:58:22 +1000
Subject: Christoph Gohlke and compiled packages
In-Reply-To: <DF942C7B-7D3F-4475-A7CB-DE51A7367046@sbcglobal.net>
References: <CAPTjJmpO0x3acr4mKfs9zCtwy6E7KGD_7_8jQqxbQL2z5ep0Wg@mail.gmail.com>
 <DF942C7B-7D3F-4475-A7CB-DE51A7367046@sbcglobal.net>
Message-ID: <CAPTjJmqykdReJj+dNWbRhHWTPwrWoohDxg3QwnsZh9Z1k6MG8A@mail.gmail.com>

On Tue, 11 Apr 2023 at 20:15, Jim Schwartz <jschwar at sbcglobal.net> wrote:
>
> What?s the problem now?  Is it with python on windows?  I use python on windows so I?d like to know. Thanks
>

Python itself is fine, but a lot of third-party packages are hard to
obtain. So if you need numpy, for instance, or psycopg2, you might
need to find an alternative source.

ChrisA

From oscar.j.benjamin at gmail.com  Tue Apr 11 07:54:05 2023
From: oscar.j.benjamin at gmail.com (Oscar Benjamin)
Date: Tue, 11 Apr 2023 12:54:05 +0100
Subject: Christoph Gohlke and compiled packages
In-Reply-To: <CAPTjJmqykdReJj+dNWbRhHWTPwrWoohDxg3QwnsZh9Z1k6MG8A@mail.gmail.com>
References: <CAPTjJmpO0x3acr4mKfs9zCtwy6E7KGD_7_8jQqxbQL2z5ep0Wg@mail.gmail.com>
 <DF942C7B-7D3F-4475-A7CB-DE51A7367046@sbcglobal.net>
 <CAPTjJmqykdReJj+dNWbRhHWTPwrWoohDxg3QwnsZh9Z1k6MG8A@mail.gmail.com>
Message-ID: <CAHVvXxSUsmRwJ4AiD5jmhBpzfg38MgQ+OUwY_k-v4oa_d5ggjQ@mail.gmail.com>

On Tue, 11 Apr 2023 at 12:01, Chris Angelico <rosuav at gmail.com> wrote:
>
> On Tue, 11 Apr 2023 at 20:15, Jim Schwartz <jschwar at sbcglobal.net> wrote:
> >
> > What?s the problem now?  Is it with python on windows?  I use python on windows so I?d like to know. Thanks
> >
>
> Python itself is fine, but a lot of third-party packages are hard to
> obtain. So if you need numpy, for instance, or psycopg2, you might
> need to find an alternative source.

Both numpy and psycopg2 have binary wheels for Windows that can be pip
installed from PyPI. I haven't used psycopg2 myself and I don't use
Windows so I can't say if there is any difficulty using them but I
presume that they can install and run just fine. Certainly the numpy
wheels have been there for Windows for years and work just fine.
Before numpy provided wheels they also provided MSI installers for
Windows anyway so there was always an alternative to Christoph's
stack.

Christoph's Windows binaries project predated the wheel format and so
the alternative options have improved massively since then. I presume
that there are some projects where Christoph's binaries are still the
only non-conda option (besides build yourself). I would not be
surprised if all of those are installable by conda though and we are
probably talking about projects that would seem obscure to most Python
users.

Certainly for the more widely used libraries like numpy installing
binaries with pip is not a problem these days on Windows or other
popular OS. I notice that psycopg2 *only* provides binaries for
Windows and not e.g. OSX or Linux but the list of binaries provided by
numpy is extensive with the current release listing wheels for all
combinations of CPython 3.8-3.11, win32, win amd64, manylinux amd64,
manylinux aarch64, OSX x64, OSX arm64:
https://pypi.org/project/numpy/1.24.2/#files

The difference now since the days when Cristoph started generating and
hosting binaries is that it is typically expected that a project like
numpy should produce its own binary wheels for popular platforms and
host them on PyPI. Of course that is a burden on the numpy maintainers
but tooling for this is much better than it used to be with things
like cibuildwheel, free CI systems including Windows/OSX runners etc.
It is *much* easier for a project to support generating Windows wheels
now than it used to be and to a certain extent it just forms part of
the normal CI setup that a project like numpy would want to have
anyway.

--
Oscar

From roel at roelschroeven.net  Tue Apr 11 08:03:44 2023
From: roel at roelschroeven.net (Roel Schroeven)
Date: Tue, 11 Apr 2023 14:03:44 +0200
Subject: Christoph Gohlke and compiled packages
In-Reply-To: <CAPTjJmqykdReJj+dNWbRhHWTPwrWoohDxg3QwnsZh9Z1k6MG8A@mail.gmail.com>
References: <CAPTjJmpO0x3acr4mKfs9zCtwy6E7KGD_7_8jQqxbQL2z5ep0Wg@mail.gmail.com>
 <DF942C7B-7D3F-4475-A7CB-DE51A7367046@sbcglobal.net>
 <CAPTjJmqykdReJj+dNWbRhHWTPwrWoohDxg3QwnsZh9Z1k6MG8A@mail.gmail.com>
Message-ID: <16bc870f-c99b-8efd-44c1-b818324eef64@roelschroeven.net>

Op 11/04/2023 om 12:58 schreef Chris Angelico:
> On Tue, 11 Apr 2023 at 20:15, Jim Schwartz <jschwar at sbcglobal.net> wrote:
> >
> > What?s the problem now?  Is it with python on windows?  I use python on windows so I?d like to know. Thanks
> >
>
> Python itself is fine, but a lot of third-party packages are hard to
> obtain. So if you need numpy, for instance, or psycopg2, you might
> need to find an alternative source.
These days I use pip to install packages, and so far for the things I 
need it simply works. "pip install numpy" works, same for psycopg2, 
pillow, pandas, and other packages I use. Conda should work too, for 
those who use the Anaconda Python distribution. I honestly don't even 
know how it's done: are there some kind souls who provide the wheels 
(binary packages) for all those things, or if there is maybe a build 
farm that does the hard work to make things easy for us.

In the past I've used Christoph Gohlke's site and I'm very grateful for 
the service it provided, but these days I don't really need it anymore, 
luckily.

-- 
"Ever since I learned about confirmation bias, I've been seeing
it everywhere."
         -- Jon Ronson


From rosuav at gmail.com  Tue Apr 11 08:55:45 2023
From: rosuav at gmail.com (Chris Angelico)
Date: Tue, 11 Apr 2023 22:55:45 +1000
Subject: Christoph Gohlke and compiled packages
In-Reply-To: <CAHVvXxSUsmRwJ4AiD5jmhBpzfg38MgQ+OUwY_k-v4oa_d5ggjQ@mail.gmail.com>
References: <CAPTjJmpO0x3acr4mKfs9zCtwy6E7KGD_7_8jQqxbQL2z5ep0Wg@mail.gmail.com>
 <DF942C7B-7D3F-4475-A7CB-DE51A7367046@sbcglobal.net>
 <CAPTjJmqykdReJj+dNWbRhHWTPwrWoohDxg3QwnsZh9Z1k6MG8A@mail.gmail.com>
 <CAHVvXxSUsmRwJ4AiD5jmhBpzfg38MgQ+OUwY_k-v4oa_d5ggjQ@mail.gmail.com>
Message-ID: <CAPTjJmow-Y7VP9d75bQsn=vKG58zxk3tLCRJ6Vh4LRjkt8io8Q@mail.gmail.com>

On Tue, 11 Apr 2023 at 21:55, Oscar Benjamin <oscar.j.benjamin at gmail.com> wrote:
>
> Both numpy and psycopg2 have binary wheels for Windows that can be pip
> installed from PyPI.

Ah good. It's been a long time since I've needed to care about
Windows, so I'm a bit out of the loop. That's good news. While not at
all detracting from his amazing contributions over the years, I'm
delighted that it's less necessary now.

ChrisA

From hjp-python at hjp.at  Tue Apr 11 08:52:19 2023
From: hjp-python at hjp.at (Peter J. Holzer)
Date: Tue, 11 Apr 2023 14:52:19 +0200
Subject: Christoph Gohlke and compiled packages
In-Reply-To: <CAHVvXxSUsmRwJ4AiD5jmhBpzfg38MgQ+OUwY_k-v4oa_d5ggjQ@mail.gmail.com>
References: <CAPTjJmpO0x3acr4mKfs9zCtwy6E7KGD_7_8jQqxbQL2z5ep0Wg@mail.gmail.com>
 <DF942C7B-7D3F-4475-A7CB-DE51A7367046@sbcglobal.net>
 <CAPTjJmqykdReJj+dNWbRhHWTPwrWoohDxg3QwnsZh9Z1k6MG8A@mail.gmail.com>
 <CAHVvXxSUsmRwJ4AiD5jmhBpzfg38MgQ+OUwY_k-v4oa_d5ggjQ@mail.gmail.com>
Message-ID: <20230411125219.m3czk3x33bzt4jcn@hjp.at>

On 2023-04-11 12:54:05 +0100, Oscar Benjamin wrote:
> Certainly for the more widely used libraries like numpy installing
> binaries with pip is not a problem these days on Windows or other
> popular OS. I notice that psycopg2 *only* provides binaries for
> Windows and not e.g. OSX or Linux

For Linux there is a separate package psycopg2-binary on PyPI.
That split happened a few years ago and I forgot why it was necessary.
For the distributions I use (Debian and Ubuntu) both packages work (but
for the source package I need to install the necessary development
packages first).

        hp

-- 
   _  | Peter J. Holzer    | Story must make more sense than reality.
|_|_) |                    |
| |   | hjp at hjp.at         |    -- Charles Stross, "Creative writing
__/   | http://www.hjp.at/ |       challenge!"
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 833 bytes
Desc: not available
URL: <https://mail.python.org/pipermail/python-list/attachments/20230411/36abba29/attachment.sig>

From list1 at tompassin.net  Tue Apr 11 09:39:21 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Tue, 11 Apr 2023 09:39:21 -0400
Subject: Christoph Gohlke and compiled packages
In-Reply-To: <CAPTjJmqykdReJj+dNWbRhHWTPwrWoohDxg3QwnsZh9Z1k6MG8A@mail.gmail.com>
References: <CAPTjJmpO0x3acr4mKfs9zCtwy6E7KGD_7_8jQqxbQL2z5ep0Wg@mail.gmail.com>
 <DF942C7B-7D3F-4475-A7CB-DE51A7367046@sbcglobal.net>
 <CAPTjJmqykdReJj+dNWbRhHWTPwrWoohDxg3QwnsZh9Z1k6MG8A@mail.gmail.com>
Message-ID: <82d2b185-c8b9-d1d4-06a7-0d3d1cf8d1da@tompassin.net>

On 4/11/2023 6:58 AM, Chris Angelico wrote:
> On Tue, 11 Apr 2023 at 20:15, Jim Schwartz <jschwar at sbcglobal.net> wrote:
>>
>> What?s the problem now?  Is it with python on windows?  I use python on windows so I?d like to know. Thanks
>>
> 
> Python itself is fine, but a lot of third-party packages are hard to
> obtain. So if you need numpy, for instance, or psycopg2, you might
> need to find an alternative source.

I've noticed a big change in the last few years in that PyPi has many, 
many amd-64 packages than it used to in the heyday of Christoph Gohlke's 
efforts. I haven't needed to go there for some time whereas I used to 
need to all the time.  So if I "need numpy, for instance, or psycopg2" 
for Windows, I get them from PyPi.

Yes, I know that some projects haven't caught up to Python 3.11x yet. 
And I'm glad I haven't needed to create a binary wheel for Windows 
myself.  But the situation is way better than it used to be.  I've had 
more trouble with Python and Python packages on Linux than on Windows.


From mats at wichmann.us  Tue Apr 11 09:53:04 2023
From: mats at wichmann.us (Mats Wichmann)
Date: Tue, 11 Apr 2023 07:53:04 -0600
Subject: Christoph Gohlke and compiled packages
In-Reply-To: <16bc870f-c99b-8efd-44c1-b818324eef64@roelschroeven.net>
References: <CAPTjJmpO0x3acr4mKfs9zCtwy6E7KGD_7_8jQqxbQL2z5ep0Wg@mail.gmail.com>
 <DF942C7B-7D3F-4475-A7CB-DE51A7367046@sbcglobal.net>
 <CAPTjJmqykdReJj+dNWbRhHWTPwrWoohDxg3QwnsZh9Z1k6MG8A@mail.gmail.com>
 <16bc870f-c99b-8efd-44c1-b818324eef64@roelschroeven.net>
Message-ID: <0b9d0f10-4800-0515-bd73-d6e2dce2b89e@wichmann.us>

On 4/11/23 06:03, Roel Schroeven wrote:
> Op 11/04/2023 om 12:58 schreef Chris Angelico:

>> Python itself is fine, but a lot of third-party packages are hard to
>> obtain. So if you need numpy, for instance, or psycopg2, you might
>> need to find an alternative source.
> These days I use pip to install packages, and so far for the things I 
> need it simply works. "pip install numpy" works, same for psycopg2, 
> pillow, pandas, and other packages I use. Conda should work too, for 
> those who use the Anaconda Python distribution. I honestly don't even 
> know how it's done: are there some kind souls who provide the wheels 
> (binary packages) for all those things, or if there is maybe a build 
> farm that does the hard work to make things easy for us.
> 
> In the past I've used Christoph Gohlke's site and I'm very grateful for 
> the service it provided, but these days I don't really need it anymore, 
> luckily.

The deal really is, the instant a new Python version drops (3.11, 3.12, 
etc.) a million people rush to install it, some of whom should know 
better and be more patient.  3rd party packages are their own projects, 
some have binary wheels ready on Python release day, some soon after, 
some months after. That's the main hole this site filled in more recent 
times: for people who feel they must jump forward but their key packages 
were not yet ready, they were probably here. (I should add - it's not 
always impatience, sometimes folks are also being proactive and want to 
test Python betas, etc. so they're prepared, and they'll of course hit 
the same problem of some wheels not being available).

There's even a "readiness" site folks can check (also volunteer-run),

https://pyreadiness.org/

but often the lure of the new shiny thing just wins out.  I predict 
we'll have a flood of anguish again in the fall when 3.12.0 comes out.


From oscar.j.benjamin at gmail.com  Tue Apr 11 13:48:08 2023
From: oscar.j.benjamin at gmail.com (Oscar Benjamin)
Date: Tue, 11 Apr 2023 18:48:08 +0100
Subject: Christoph Gohlke and compiled packages
In-Reply-To: <0b9d0f10-4800-0515-bd73-d6e2dce2b89e@wichmann.us>
References: <CAPTjJmpO0x3acr4mKfs9zCtwy6E7KGD_7_8jQqxbQL2z5ep0Wg@mail.gmail.com>
 <DF942C7B-7D3F-4475-A7CB-DE51A7367046@sbcglobal.net>
 <CAPTjJmqykdReJj+dNWbRhHWTPwrWoohDxg3QwnsZh9Z1k6MG8A@mail.gmail.com>
 <16bc870f-c99b-8efd-44c1-b818324eef64@roelschroeven.net>
 <0b9d0f10-4800-0515-bd73-d6e2dce2b89e@wichmann.us>
Message-ID: <CAHVvXxTqf1HqhV9qa14=fwtsDRJu1O4=csvi-5TB4uzf+6fT8Q@mail.gmail.com>

On Tue, 11 Apr 2023 at 14:55, Mats Wichmann <mats at wichmann.us> wrote:
>
> On 4/11/23 06:03, Roel Schroeven wrote:
> > Op 11/04/2023 om 12:58 schreef Chris Angelico:
>
> >> Python itself is fine, but a lot of third-party packages are hard to
> >> obtain. So if you need numpy, for instance, or psycopg2, you might
> >> need to find an alternative source.
> > These days I use pip to install packages, and so far for the things I
> > need it simply works. "pip install numpy" works, same for psycopg2,
> > pillow, pandas, and other packages I use. Conda should work too, for
> > those who use the Anaconda Python distribution. I honestly don't even
> > know how it's done: are there some kind souls who provide the wheels
> > (binary packages) for all those things, or if there is maybe a build
> > farm that does the hard work to make things easy for us.
> >
> > In the past I've used Christoph Gohlke's site and I'm very grateful for
> > the service it provided, but these days I don't really need it anymore,
> > luckily.
>
> The deal really is, the instant a new Python version drops (3.11, 3.12,
> etc.) a million people rush to install it, some of whom should know
> better and be more patient.  3rd party packages are their own projects,
> some have binary wheels ready on Python release day, some soon after,
> some months after.

You can hardly blame a lot of people for doing this. A seb search for
"download python" gives this as the first hit:
https://www.python.org/downloads/

I am guessing that the release process automatically updates that page
so that the minute 3.12 gets released the big yellow button will
suggest downloading 3.12.0 as the default option.

Perhaps it is really package authors who should be getting a release
out that is compatible with Python 3.12 before 3.12 itself is
released. It's tricky though because as a maintainer it makes more
sense to wait until you see the finished 3.12 product before making a
release that is fully tested with it (even if you are testing the
alphas etc in CI and making incremental fixes before 3.12 is
released).

The other option could be changing the downloads page so that it does
not suggest 3.12.0 as the default option until it is clear that at
least some baseline of widely used packages have uploaded compatible
wheels.

--
Oscar

From loris.bennett at fu-berlin.de  Tue Apr 11 10:29:58 2023
From: loris.bennett at fu-berlin.de (Loris Bennett)
Date: Tue, 11 Apr 2023 16:29:58 +0200
Subject: Initialising a Config class
Message-ID: <87sfd6trtl.fsf@debian-BULLSEYE-live-builder-AMD64>

Hi,

Having solved my problem regarding setting up 'logger' such that it is
accessible throughout my program (thanks to the help on this list), I
now have problem related to a slightly similar issue.

My reading suggests that setting up a module with a Config class which
can be imported by any part of the program might be a reasonable approach:


import configparser

class Config:

    def __init__(self, config_file):

        config = configparser.ConfigParser()
        config.read(config_file)
  

However, in my config file I am using sections, so 'config' is a dict of
dicts.  Is there any cleverer generic way of initialising the class than


        self.config = config


?

This seems a bit clunky, because I'll end up with something like


   import config
   ...
   c = config.Config(config_file)
   uids = get_uids(int(c.config["uids"]["minimum_uid"]))


rather than something like, maybe


   uids = get_uids(int(c.minimum_uid))


or


   uids = get_uids(int(c.uids_minimum_uid))


So the question is: How can I map a dict of dicts onto class attributes
in a generic way such that only code which wants to use a new
configuration parameter needs to be changed and not the Config class
itself?  Or should I be doing this differently?

Note that the values from ConfigParser are all strings, so I am fine
with the attributes being strings - I'll just convert them as needed at
the point of use (but maybe there is also a better way of handling that
within a class).
 
Cheers,

Loris

-- 
This signature is currently under constuction.

From mats at wichmann.us  Tue Apr 11 14:30:01 2023
From: mats at wichmann.us (Mats Wichmann)
Date: Tue, 11 Apr 2023 12:30:01 -0600
Subject: Christoph Gohlke and compiled packages
In-Reply-To: <CAHVvXxTqf1HqhV9qa14=fwtsDRJu1O4=csvi-5TB4uzf+6fT8Q@mail.gmail.com>
References: <CAPTjJmpO0x3acr4mKfs9zCtwy6E7KGD_7_8jQqxbQL2z5ep0Wg@mail.gmail.com>
 <DF942C7B-7D3F-4475-A7CB-DE51A7367046@sbcglobal.net>
 <CAPTjJmqykdReJj+dNWbRhHWTPwrWoohDxg3QwnsZh9Z1k6MG8A@mail.gmail.com>
 <16bc870f-c99b-8efd-44c1-b818324eef64@roelschroeven.net>
 <0b9d0f10-4800-0515-bd73-d6e2dce2b89e@wichmann.us>
 <CAHVvXxTqf1HqhV9qa14=fwtsDRJu1O4=csvi-5TB4uzf+6fT8Q@mail.gmail.com>
Message-ID: <38a3954f-ce5c-d26b-100a-3193b97c9bc7@wichmann.us>

On 4/11/23 11:48, Oscar Benjamin wrote:
> On Tue, 11 Apr 2023 at 14:55, Mats Wichmann <mats at wichmann.us> wrote:
>>
>> On 4/11/23 06:03, Roel Schroeven wrote:
>>> Op 11/04/2023 om 12:58 schreef Chris Angelico:
>>
>>>> Python itself is fine, but a lot of third-party packages are hard to
>>>> obtain. So if you need numpy, for instance, or psycopg2, you might
>>>> need to find an alternative source.
>>> These days I use pip to install packages, and so far for the things I
>>> need it simply works. "pip install numpy" works, same for psycopg2,
>>> pillow, pandas, and other packages I use. Conda should work too, for
>>> those who use the Anaconda Python distribution. I honestly don't even
>>> know how it's done: are there some kind souls who provide the wheels
>>> (binary packages) for all those things, or if there is maybe a build
>>> farm that does the hard work to make things easy for us.
>>>
>>> In the past I've used Christoph Gohlke's site and I'm very grateful for
>>> the service it provided, but these days I don't really need it anymore,
>>> luckily.
>>
>> The deal really is, the instant a new Python version drops (3.11, 3.12,
>> etc.) a million people rush to install it, some of whom should know
>> better and be more patient.  3rd party packages are their own projects,
>> some have binary wheels ready on Python release day, some soon after,
>> some months after.
> 
> You can hardly blame a lot of people for doing this. A seb search for
> "download python" gives this as the first hit:
> https://www.python.org/downloads/
> 
> I am guessing that the release process automatically updates that page
> so that the minute 3.12 gets released the big yellow button will
> suggest downloading 3.12.0 as the default option.

Yes, you're quite right about that.

> Perhaps it is really package authors who should be getting a release
> out that is compatible with Python 3.12 before 3.12 itself is
> released. It's tricky though because as a maintainer it makes more
> sense to wait until you see the finished 3.12 product before making a
> release that is fully tested with it (even if you are testing the
> alphas etc in CI and making incremental fixes before 3.12 is
> released).

If you can find the incantation there are often pending builds for 
packages that need binary wheels, it may be "pip --pre" or it may be 
pointing to test.pypi.org... or there may not be. The projects may not 
tell you.  And for many less experienced users (and yes this is a known 
issue), they have no idea they need to look.

> The other option could be changing the downloads page so that it does
> not suggest 3.12.0 as the default option until it is clear that at
> least some baseline of widely used packages have uploaded compatible
> wheels.

There's been some suggestion of that before. Apparently the choice of 
what goes there is at least a bit political.  Like many projects, I 
believe python prefers to recommend "the latest and best release", while 
user prudence (and especially organizational prudence) tends to say 
"hold off for a while until it's been fully vetted, and the ecosystem 
catches up". I don't think we can cast too much blame on either: I don't 
expect Microsoft will say "Don't download Windows 12 for the first six 
months", even if they know perfectly well that many enterprise customers 
will take an approach like that.

Not sure there's any really good answer, TBH.




From torriem at gmail.com  Tue Apr 11 14:51:08 2023
From: torriem at gmail.com (Michael Torrie)
Date: Tue, 11 Apr 2023 12:51:08 -0600
Subject: Christoph Gohlke and compiled packages
In-Reply-To: <CAHVvXxTqf1HqhV9qa14=fwtsDRJu1O4=csvi-5TB4uzf+6fT8Q@mail.gmail.com>
References: <CAPTjJmpO0x3acr4mKfs9zCtwy6E7KGD_7_8jQqxbQL2z5ep0Wg@mail.gmail.com>
 <DF942C7B-7D3F-4475-A7CB-DE51A7367046@sbcglobal.net>
 <CAPTjJmqykdReJj+dNWbRhHWTPwrWoohDxg3QwnsZh9Z1k6MG8A@mail.gmail.com>
 <16bc870f-c99b-8efd-44c1-b818324eef64@roelschroeven.net>
 <0b9d0f10-4800-0515-bd73-d6e2dce2b89e@wichmann.us>
 <CAHVvXxTqf1HqhV9qa14=fwtsDRJu1O4=csvi-5TB4uzf+6fT8Q@mail.gmail.com>
Message-ID: <d8e2592c-f551-3f79-5e65-d194d10ca373@gmail.com>

On 4/11/23 11:48, Oscar Benjamin wrote:
> You can hardly blame a lot of people for doing this. A seb search for
> "download python" gives this as the first hit:
> https://www.python.org/downloads/

Very true, but it points to the difference between how people install
Python on Windows compared to Linux, which is what Chris was probably
referring to when he said Windows was a nightmare to support.  Usually
when a full version bump of python hits my distros, all the other
packages that need to be rebuilt get rebuilt and install along with the
new python package.  Or often the older version of Python is patched and
continued to be used, not requiring new packages.  So most linux users
never have to go searching for an appropriate version of Numpy, etc.

Whereas Windows only recently has gained a package manager, and as near
as I can tell is not widely used outside of serious developers who use
Visual Studio.  And to make matters worse, MS offers Python in the
Windows Store, which is its own thing and causes much confusion with
users who often end up with more than one version of Python installed.
And nevermind the MingW/MSVC split that affects the distribution of
pre-built binaries, although MS's move to the universal C runtime dll
system might fix this finally (unless C++ is involved).

These are all extremely hard problems to solve, and every solution has
its drawbacks, including the packaging systems used by Linux.
Especially by an open source organization like the PSF.

From David.Raymond at tomtom.com  Tue Apr 11 15:38:31 2023
From: David.Raymond at tomtom.com (David Raymond)
Date: Tue, 11 Apr 2023 19:38:31 +0000
Subject: Initialising a Config class
In-Reply-To: <87sfd6trtl.fsf@debian-BULLSEYE-live-builder-AMD64>
References: <87sfd6trtl.fsf@debian-BULLSEYE-live-builder-AMD64>
Message-ID: <DB7PR07MB3916BD1B40F8076019A59EBD879A9@DB7PR07MB3916.eurprd07.prod.outlook.com>

Not sure if I'm fully understanding the question. But one option instead of making everything class attributes is to just define __getattr__ for when it doesn't find an attribute.

Won't work for every single valid section and option name (because of spaces, name overlaps, etc) but should cover most things.
For example, you could use a dunder to separate section and option. Then something like this?


import configparser

class Config:
    def __init__(self, configFile):
        self._config = configparser.ConfigParser()
        self._config.read(configFile)
    def __getattr__(self, option):
        if "__" in option:
            section, option = option.split("__", 1)
        else:
            section = self._config.default_section
        return self._config[section][option]

c = Config("SomeConfigFile.txt")
print(c.uids__minimum_uid) #Will check for the option "minimum_uid" in the "uids" section
print(c.minimum_uid)       #Will check the default section


Not sure if that works as you said the Config class itself should not need to be changed

> Hi,
> 
> Having solved my problem regarding setting up 'logger' such that it is
> accessible throughout my program (thanks to the help on this list), I
> now have problem related to a slightly similar issue.
> 
> My reading suggests that setting up a module with a Config class which
> can be imported by any part of the program might be a reasonable approach:
> 
> 
> import configparser
> 
> class Config:
> 
>     def __init__(self, config_file):
> 
>         config = configparser.ConfigParser()
>         config.read(config_file)
>   
> 
> However, in my config file I am using sections, so 'config' is a dict of
> dicts.  Is there any cleverer generic way of initialising the class than
> 
> 
>         self.config = config
> 
> 
> ?
> 
> This seems a bit clunky, because I'll end up with something like
> 
> 
>    import config
>    ...
>    c = config.Config(config_file)
>    uids = get_uids(int(c.config["uids"]["minimum_uid"]))
> 
> 
> rather than something like, maybe
> 
> 
>    uids = get_uids(int(c.minimum_uid))
> 
> 
> or
> 
> 
>    uids = get_uids(int(c.uids_minimum_uid))
> 
> 
> So the question is: How can I map a dict of dicts onto class attributes
> in a generic way such that only code which wants to use a new
> configuration parameter needs to be changed and not the Config class
> itself?  Or should I be doing this differently?
> 
> Note that the values from ConfigParser are all strings, so I am fine
> with the attributes being strings - I'll just convert them as needed at
> the point of use (but maybe there is also a better way of handling that
> within a class).
>  
> Cheers,
> 
> Loris
>

From PythonList at DancesWithMice.info  Tue Apr 11 16:26:45 2023
From: PythonList at DancesWithMice.info (dn)
Date: Wed, 12 Apr 2023 08:26:45 +1200
Subject: Initialising a Config class
In-Reply-To: <87sfd6trtl.fsf@debian-BULLSEYE-live-builder-AMD64>
References: <87sfd6trtl.fsf@debian-BULLSEYE-live-builder-AMD64>
Message-ID: <733f4cc0-41a0-c1ce-4f2c-3ff780e31005@DancesWithMice.info>

On 12/04/2023 02.29, Loris Bennett wrote:
> Hi,
> 
> Having solved my problem regarding setting up 'logger' such that it is
...

> My reading suggests that setting up a module with a Config class which
> can be imported by any part of the program might be a reasonable approach:
...

> However, in my config file I am using sections, so 'config' is a dict of
> dicts.  Is there any cleverer generic way of initialising the class than
...

> This seems a bit clunky, because I'll end up with something like
...

> So the question is: How can I map a dict of dicts onto class attributes
> in a generic way such that only code which wants to use a new
> configuration parameter needs to be changed and not the Config class
> itself?  Or should I be doing this differently?
> 
> Note that the values from ConfigParser are all strings, so I am fine
> with the attributes being strings - I'll just convert them as needed at
> the point of use (but maybe there is also a better way of handling that
> within a class).

Good progress!

The first achievement has been related to the (OO) concept of 
"encapsulation" - collecting related data into one place.

The second, has been the making of this, globally-accessible within the 
application.


The balancing-act may now have become: making sub-sets of the data 
available.

Thus, describing which database server and schema/view to use is part of 
the application's environment/config, just as much as the labels, eg 
company name, used in the GUI or reporting. Such data has been collected 
together (into a single 'source of truth'), but will be used in quite 
separate and/or disparate functionality within the application.

The config file has been (sensibly) split into sections - when the code 
is dealing with the DB it does not need to be concerned with 
GUI-settings - or vice-versa.

Accordingly, and like any other class (encapsulation), having been 
collected en-masse (or 'amassed', eg cmdLN options combined with a 
JSON/YAML/.ini file's settings) the data should be delivered 
appropriately. Thus, a 'getter' method (or property) to deliver the name 
of the company (likely a string). The one for the database may deliver a 
dict or key-value pairs which can be immediately 'pasted' into some 
db-open function-call...

Such retrieval-methods will be targeted to the sub-systems of the 
application. They can perform formatting and coercion tasks, as 
necessary, eg construct full-name from two or more separate data-items, 
eg first_name and family_name, or perhaps providing floats where the 
config-collection only receives strings. (best to 'hide' all that within 
the class, than require the application to deal with the 'clunkiness'). 
Plus, they could?should provide whatever combination of data-items is 
appropriate to THAT part of the application's need for config-data or 
constraints. (etc)


Stuff as much as is possible into the config class - how to collect 
environment-data, and satisfying any/all demands for its use. Then, the 
application can be relieved of all detail ("give me what I want"), only 
asking for whatever it requires, when it requires, and in the format it 
requires - tailored and ready for immediate-use...

-- 
Regards,
=dn

From PythonList at DancesWithMice.info  Wed Apr 12 00:58:56 2023
From: PythonList at DancesWithMice.info (dn)
Date: Wed, 12 Apr 2023 16:58:56 +1200
Subject: Dataclasses, immutability(?), and ChatGPT
Message-ID: <f84efb41-daa9-e894-9ca4-9cd889ecf521@DancesWithMice.info>

Are dataclasses (or instances thereof) mutable or immutable?
- and in what sense?


Have been experimenting with ChatGPT. In particular: its possibilities 
as a trainer, good ideas for methods of introducing new topics, its 
capability for drawing-up demonstrations or examples, its interpretation 
of assessment questions (ie evaluating my own work, eg do they test 
desired specifics, is it possible/likely to misinterpret the question, ...)


Conversed with ChatGPT about the differences between (standard) 
custom-classes and dataclasses, and when one might prefer one over the 
other.

We(?) started discussing how dataclasses might be introduced to trainees 
currently only familiar with Python's built-ins: "...how they are 
superior to using built-in data-constructs..."

Amongst the four benefits ChatGPT listed was:
?
Immutable instances: By default, instances of dataclasses are immutable, 
which means that once created, their attributes cannot be modified. This 
can help to prevent unintended modifications to the data.
?

Huh? If we'd been discussing namedtuples over (say) dictionaries, I'd 
perhaps have accepted the reply.


The next step was to write some code to double-check my understanding 
(reproduced below). No change there.
(given that I'm perfect...cough, cough, splutter)


Thus, back to ChatGPT to seek clarification:
?
You said "Immutable instances: By default, instances of dataclasses are 
immutable, which means that once created, their attributes cannot be 
modified. This can help to prevent unintended modifications to the 
data." The attribute-values within a data-class can be changed. In what 
way are Python dataclasses immutable?
?

ChatGPT did indeed clarify that:
?
You're correct that the attribute values within a dataclass can be 
changed, even though the instance itself is considered immutable.
?

That's better. The machine is as smart as I am - or I, as smart as it - 
or something(?)


However, the supporting-explanation then appears to argue against its 
own clarification (and the assertion in the question):
?
So to clarify, when we say that instances of dataclasses are immutable, 
we mean that the attributes of an instance cannot be changed after it is 
created.

In other words, if you create an instance of a dataclass, its attributes 
cannot be modified by any external code. If you want to change the value 
of an attribute, you need to create a new instance of the dataclass with 
the updated attribute value.

... [code excised - see below]

This is because the instance is considered immutable, and its attributes 
cannot be changed directly. Instead, we need to create a new instance of 
the dataclass with the updated attribute value, like this...

Now, new_person is a new instance of the Person dataclass with the 
updated attribute values, while the original person instance remains 
unchanged.

So to summarize, while the attribute values within a dataclass can be 
changed, instances of dataclasses are considered immutable because their 
attributes cannot be modified directly once they are created. Any 
updates to the attributes require the creation of a new instance of the 
dataclass.
?

[Note]
In and amongst the above explanatory-paragraphs it gives example 
code-snippets. Those are condensed into:

 >>> from dataclasses import dataclass
 >>>
 >>> @dataclass
... class Person:
...     name: str
...     age: int
...
 >>> person = Person(name='Alice', age=20)
 >>>
 >>> person.name = 'Bob'  # raises AttributeError: can't set attribute
 >>> person.age = 21      # raises AttributeError: can't set attribute

- note the erroneous comments about exceptions being raised
(they weren't/aren't)!


Here's a home-grown version illustrating all the points made during the 
investigation, by way of proof/disproof:

""" PythonTraining:dataclass.py
     Prove/disprove claim made by Chat-GPT.
"""

__author__ = "dn, IT&T Consultant"
__python__ = "3.11"
__created__ = "PyCharm, 12 Apr 2023"
__copyright__ = "Copyright ? 2023~"
__license__ = "MIT"

# PSL
from dataclasses import dataclass


@dataclass
class Coordinates():
     """Sample dataclass. """
     x:int
     y:int


if __name__ == "__main__":
     print( "\nCommencing execution\n" )

     coordinates = Coordinates( 1, 2, )
     print( coordinates, id( coordinates ), )
     coordinates.x = 3
     print( coordinates, id( coordinates ), )
     coordinates.z = 4
     print( coordinates, id( coordinates ), )
     print( coordinates.x, coordinates.y, coordinates.z, )


### output:
Commencing execution

Coordinates(x=1, y=2) 140436963150928
Coordinates(x=3, y=2) 140436963150928
Coordinates(x=3, y=2) 140436963150928
3 2 4

Terminating
###

Not only are a dataclass instance's attribute-values mutable, but 
further attributes can be dynamically-added to the object-instance!

Yes, if the code included:

coordinates = Coordinates( 5, 6, )

the new "coordinates" identifier would point to a different id() 
'address', ie a fresh immutable-instance.


The 'book of words' (https://docs.python.org/3/library/dataclasses.html) 
does mention immutability (wrt to dataclasses) in that it is possible to 
add a __hash__() method (any object defined with is (technically) 
immutable). However, apart from the default_factory argument, there 
doesn't appear to be other discussion of [im]mutability.


Anything I've 'missed'?
- or a salutary tale of not depending upon ChatGPT etc?

-- 
Regards,
=dn

From roel at roelschroeven.net  Wed Apr 12 04:02:51 2023
From: roel at roelschroeven.net (Roel Schroeven)
Date: Wed, 12 Apr 2023 10:02:51 +0200
Subject: Dataclasses, immutability(?), and ChatGPT
In-Reply-To: <f84efb41-daa9-e894-9ca4-9cd889ecf521@DancesWithMice.info>
References: <f84efb41-daa9-e894-9ca4-9cd889ecf521@DancesWithMice.info>
Message-ID: <35c0528d-2ca3-062a-35ee-20de4b372971@roelschroeven.net>

Op 12/04/2023 om 6:58 schreef dn via Python-list:
> Are dataclasses (or instances thereof) mutable or immutable?
> - and in what sense?
Instances of dataclasses are mutable, just like normal classes. 
Dataclasses *are* normal classes, with some extra special methods. They 
are totally different from namedtuples, even though the use cases 
somewhat overlap. They *can* be immutable, I think, if the programmer 
takes care to make them so. I don't think adding __hash__() is enough: 
as I understand it's an indication that a class is immutable, but 
doesn't actually by itself make it so. "Mutability is a complicated 
property that depends on the programmer?s intent, the existence and 
behavior of |__eq__()|, and the values of the |eq| and |frozen| flags in 
the |dataclass()| 
<https://docs.python.org/3.10/library/dataclasses.html#dataclasses.dataclass> 
decorator.", says the documentation.
> Amongst the four benefits ChatGPT listed was:
> ?
> Immutable instances: By default, instances of dataclasses are 
> immutable, which means that once created, their attributes cannot be 
> modified. This can help to prevent unintended modifications to the data.
> ?
>
> Huh? If we'd been discussing namedtuples over (say) dictionaries, I'd 
> perhaps have accepted the reply.
ChatGPT is wrong.
> Anything I've 'missed'?
> - or a salutary tale of not depending upon ChatGPT etc?
You didn't miss anything, ChatGPT is wrong. The thing to look out for is 
that when ChatGPT is wrong, it sounds just as convincing as when it's 
right; there is no indication in it's tone or style that it's making 
things up. Always double check!

-- 
"A common mistake that people make when trying to design something completely
foolproof is to underestimate the ingenuity of complete fools."
         -- Douglas Adams

From miked at dewhirst.com.au  Wed Apr 12 04:13:42 2023
From: miked at dewhirst.com.au (Mike Dewhirst)
Date: Wed, 12 Apr 2023 18:13:42 +1000
Subject: Christoph Gohlke and compiled packages
In-Reply-To: <82d2b185-c8b9-d1d4-06a7-0d3d1cf8d1da@tompassin.net>
References: <CAPTjJmpO0x3acr4mKfs9zCtwy6E7KGD_7_8jQqxbQL2z5ep0Wg@mail.gmail.com>
 <DF942C7B-7D3F-4475-A7CB-DE51A7367046@sbcglobal.net>
 <CAPTjJmqykdReJj+dNWbRhHWTPwrWoohDxg3QwnsZh9Z1k6MG8A@mail.gmail.com>
 <82d2b185-c8b9-d1d4-06a7-0d3d1cf8d1da@tompassin.net>
Message-ID: <e94288eb-d558-fea8-331f-f5a83bf92b73@dewhirst.com.au>

Well thank you Christoph Gohlke and thank you Ian Bicking and colleagues.

I just used pip to nakedly install psycopg2 and Pillow without a hitch. 
My distrust of Windows has kept me going back to Christoff's well for 
years.

Maybe it is time to assume innocence unless proven guilty ;-)

Thanks to all who showed me the way.

Cheers

Mike

On 11/04/2023 11:39 pm, Thomas Passin wrote:
> On 4/11/2023 6:58 AM, Chris Angelico wrote:
>> On Tue, 11 Apr 2023 at 20:15, Jim Schwartz <jschwar at sbcglobal.net> 
>> wrote:
>>>
>>> What?s the problem now?? Is it with python on windows?? I use python 
>>> on windows so I?d like to know. Thanks
>>>
>>
>> Python itself is fine, but a lot of third-party packages are hard to
>> obtain. So if you need numpy, for instance, or psycopg2, you might
>> need to find an alternative source.
>
> I've noticed a big change in the last few years in that PyPi has many, 
> many amd-64 packages than it used to in the heyday of Christoph 
> Gohlke's efforts. I haven't needed to go there for some time whereas I 
> used to need to all the time.? So if I "need numpy, for instance, or 
> psycopg2" for Windows, I get them from PyPi.
>
> Yes, I know that some projects haven't caught up to Python 3.11x yet. 
> And I'm glad I haven't needed to create a binary wheel for Windows 
> myself.? But the situation is way better than it used to be.? I've had 
> more trouble with Python and Python packages on Linux than on Windows.
>


-- 
Signed email is an absolute defence against phishing. This email has
been signed with my private key. If you import my public key you can
automatically decrypt my signature and be sure it came from me. Your
email software can handle signing.

-------------- next part --------------
A non-text attachment was scrubbed...
Name: OpenPGP_signature
Type: application/pgp-signature
Size: 495 bytes
Desc: OpenPGP digital signature
URL: <https://mail.python.org/pipermail/python-list/attachments/20230412/52978f1d/attachment.sig>

From grant.b.edwards at gmail.com  Wed Apr 12 08:00:36 2023
From: grant.b.edwards at gmail.com (Grant Edwards)
Date: Wed, 12 Apr 2023 05:00:36 -0700 (PDT)
Subject: Dataclasses, immutability(?), and ChatGPT
References: <f84efb41-daa9-e894-9ca4-9cd889ecf521@DancesWithMice.info>
 <35c0528d-2ca3-062a-35ee-20de4b372971@roelschroeven.net>
Message-ID: <64369d64.050a0220.44313.581e@mx.google.com>

On 2023-04-12, Roel Schroeven <roel at roelschroeven.net> wrote:

>> Huh? If we'd been discussing namedtuples over (say) dictionaries, I'd 
>> perhaps have accepted the reply.
>
> ChatGPT is wrong.
>
>> Anything I've 'missed'?
>> - or a salutary tale of not depending upon ChatGPT etc?

> You didn't miss anything, ChatGPT is wrong. The thing to look out for is 
> that when ChatGPT is wrong, it sounds just as convincing as when it's 
> right; there is no indication in it's tone or style that it's making 
> things up.

Yep, that's how ChatGPT works. It's a program to generate output
language that sounds right based on a huge training set of
text. Whether that "right sounding" language agrees with real world
facts or not is irrelevent to the language-generating algorithm.

--
Grant



From list1 at tompassin.net  Wed Apr 12 08:26:47 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Wed, 12 Apr 2023 08:26:47 -0400
Subject: Dataclasses, immutability(?), and ChatGPT
In-Reply-To: <f84efb41-daa9-e894-9ca4-9cd889ecf521@DancesWithMice.info>
References: <f84efb41-daa9-e894-9ca4-9cd889ecf521@DancesWithMice.info>
Message-ID: <1247feb7-17a6-0f95-e4b2-3d8c18fe6be5@tompassin.net>

On 4/12/2023 12:58 AM, dn via Python-list wrote:
> Are dataclasses (or instances thereof) mutable or immutable?
> - and in what sense?
> 
> 
> Have been experimenting with ChatGPT. In particular: its possibilities 
> as a trainer, good ideas for methods of introducing new topics, its 
> capability for drawing-up demonstrations or examples, its interpretation 
> of assessment questions (ie evaluating my own work, eg do they test 
> desired specifics, is it possible/likely to misinterpret the question, ...)
> 
> 
> Conversed with ChatGPT about the differences between (standard) 
> custom-classes and dataclasses, and when one might prefer one over the 
> other.
> 
> We(?) started discussing how dataclasses might be introduced to trainees 
> currently only familiar with Python's built-ins: "...how they are 
> superior to using built-in data-constructs..."
> 
> Amongst the four benefits ChatGPT listed was:
> ?
> Immutable instances: By default, instances of dataclasses are immutable, 
> which means that once created, their attributes cannot be modified. This 
> can help to prevent unintended modifications to the data.
> ?
> 
> Huh? If we'd been discussing namedtuples over (say) dictionaries, I'd 
> perhaps have accepted the reply.
> 
> 
> The next step was to write some code to double-check my understanding 
> (reproduced below). No change there.
> (given that I'm perfect...cough, cough, splutter)
> 
> 
> Thus, back to ChatGPT to seek clarification:
> ?
> You said "Immutable instances: By default, instances of dataclasses are 
> immutable, which means that once created, their attributes cannot be 
> modified. This can help to prevent unintended modifications to the 
> data." The attribute-values within a data-class can be changed. In what 
> way are Python dataclasses immutable?
> ?
> 
> ChatGPT did indeed clarify that:
> ?
> You're correct that the attribute values within a dataclass can be 
> changed, even though the instance itself is considered immutable.
> ?
> 
> That's better. The machine is as smart as I am - or I, as smart as it - 
> or something(?)
> 
> 
> However, the supporting-explanation then appears to argue against its 
> own clarification (and the assertion in the question):
> ?
> So to clarify, when we say that instances of dataclasses are immutable, 
> we mean that the attributes of an instance cannot be changed after it is 
> created.
> 
> In other words, if you create an instance of a dataclass, its attributes 
> cannot be modified by any external code. If you want to change the value 
> of an attribute, you need to create a new instance of the dataclass with 
> the updated attribute value.
> 
> ... [code excised - see below]
> 
> This is because the instance is considered immutable, and its attributes 
> cannot be changed directly. Instead, we need to create a new instance of 
> the dataclass with the updated attribute value, like this...
> 
> Now, new_person is a new instance of the Person dataclass with the 
> updated attribute values, while the original person instance remains 
> unchanged.
> 
> So to summarize, while the attribute values within a dataclass can be 
> changed, instances of dataclasses are considered immutable because their 
> attributes cannot be modified directly once they are created. Any 
> updates to the attributes require the creation of a new instance of the 
> dataclass.
> ?
> 
> [Note]
> In and amongst the above explanatory-paragraphs it gives example 
> code-snippets. Those are condensed into:
> 
>  >>> from dataclasses import dataclass
>  >>>
>  >>> @dataclass
> ... class Person:
> ...???? name: str
> ...???? age: int
> ...
>  >>> person = Person(name='Alice', age=20)
>  >>>
>  >>> person.name = 'Bob'? # raises AttributeError: can't set attribute
>  >>> person.age = 21????? # raises AttributeError: can't set attribute
> 
> - note the erroneous comments about exceptions being raised
> (they weren't/aren't)!
> 
> 
> Here's a home-grown version illustrating all the points made during the 
> investigation, by way of proof/disproof:
> 
> """ PythonTraining:dataclass.py
>  ??? Prove/disprove claim made by Chat-GPT.
> """
> 
> __author__ = "dn, IT&T Consultant"
> __python__ = "3.11"
> __created__ = "PyCharm, 12 Apr 2023"
> __copyright__ = "Copyright ? 2023~"
> __license__ = "MIT"
> 
> # PSL
> from dataclasses import dataclass
> 
> 
> @dataclass
> class Coordinates():
>  ??? """Sample dataclass. """
>  ??? x:int
>  ??? y:int
> 
> 
> if __name__ == "__main__":
>  ??? print( "\nCommencing execution\n" )
> 
>  ??? coordinates = Coordinates( 1, 2, )
>  ??? print( coordinates, id( coordinates ), )
>  ??? coordinates.x = 3
>  ??? print( coordinates, id( coordinates ), )
>  ??? coordinates.z = 4
>  ??? print( coordinates, id( coordinates ), )
>  ??? print( coordinates.x, coordinates.y, coordinates.z, )
> 
> 
> ### output:
> Commencing execution
> 
> Coordinates(x=1, y=2) 140436963150928
> Coordinates(x=3, y=2) 140436963150928
> Coordinates(x=3, y=2) 140436963150928
> 3 2 4
> 
> Terminating
> ###
> 
> Not only are a dataclass instance's attribute-values mutable, but 
> further attributes can be dynamically-added to the object-instance!
> 
> Yes, if the code included:
> 
> coordinates = Coordinates( 5, 6, )
> 
> the new "coordinates" identifier would point to a different id() 
> 'address', ie a fresh immutable-instance.
> 
> 
> The 'book of words' (https://docs.python.org/3/library/dataclasses.html) 
> does mention immutability (wrt to dataclasses) in that it is possible to 
> add a __hash__() method (any object defined with is (technically) 
> immutable). However, apart from the default_factory argument, there 
> doesn't appear to be other discussion of [im]mutability.
> 
> 
> Anything I've 'missed'?
> - or a salutary tale of not depending upon ChatGPT etc?

People need to remember that ChatGPT-like systems put words together the 
way that many humans usually do.  So what they emit usually sounds 
smooth and human-like.  If it's code they emit, it will tend to seem 
plausible because lines of code are basically sentences, and learning 
how to construct plausible sentences is what these systems are built to 
do. That's **plausible**, not "logical" or "correct".

The vast size of these systems means that they can include a larger 
context in figuring out what words to place next compared with earlier, 
smaller systems.

But consider: what if you wrote code as a stream-of-consciousness 
process?  That code might seem plausible, but why would you have any 
confidence in it?  Or to put it another way, what if most of ChatGPT's 
exposure to code came from StackOverflow archives?

On top of that, ChapGPT-like systems do not know your requirements nor 
the reasons behind your requests.  They only know that when other people 
put words and phrases together like you did, they tended to make 
responses that sound like what the chatbot emits next.  It's basically 
cargo-culting its responses.

Apparently researchers have been learning that the more parameters that 
a system like this has, the more likely it is to learn how to emit 
responses that the questioner likes.  Essentially, it could become the 
ultimate yes-man!

So there is some probability that the system will tell you interesting 
or useful things, some probability that it will try to tell you what it 
thinks you want hear, some probability that it will tell you incorrect 
things that other people have repeated, and some probability that it 
will perseverate - simply make things up.

If I were going to write a novel about an alternate history, I think 
that a chatGPT-like system would be a fantastic writing assistant. 
Code? Not so much.

From miked at dewhirst.com.au  Wed Apr 12 08:59:03 2023
From: miked at dewhirst.com.au (Mike Dewhirst)
Date: Wed, 12 Apr 2023 22:59:03 +1000
Subject: Christoph Gohlke and compiled packages
In-Reply-To: <e94288eb-d558-fea8-331f-f5a83bf92b73@dewhirst.com.au>
References: <CAPTjJmpO0x3acr4mKfs9zCtwy6E7KGD_7_8jQqxbQL2z5ep0Wg@mail.gmail.com>
 <DF942C7B-7D3F-4475-A7CB-DE51A7367046@sbcglobal.net>
 <CAPTjJmqykdReJj+dNWbRhHWTPwrWoohDxg3QwnsZh9Z1k6MG8A@mail.gmail.com>
 <82d2b185-c8b9-d1d4-06a7-0d3d1cf8d1da@tompassin.net>
 <e94288eb-d558-fea8-331f-f5a83bf92b73@dewhirst.com.au>
Message-ID: <0db1af84-212e-566a-2a8f-bed5226987f5@dewhirst.com.au>

Sadly Windows is still in the dock. The jury is still out.

Turns out the "without a hitch" was based on cached wheels.

I'm going to start from scratch with new projects using Pythons 3.8, 
3.10 and 3.11 and report back.

Cheers

Mike

On 12/04/2023 6:13 pm, Mike Dewhirst wrote:
> Well thank you Christoph Gohlke and thank you Ian Bicking and colleagues.
>
> I just used pip to nakedly install psycopg2 and Pillow without a 
> hitch. My distrust of Windows has kept me going back to Christoff's 
> well for years.
>
> Maybe it is time to assume innocence unless proven guilty ;-)
>
> Thanks to all who showed me the way.
>
> Cheers
>
> Mike
>
> On 11/04/2023 11:39 pm, Thomas Passin wrote:
>> On 4/11/2023 6:58 AM, Chris Angelico wrote:
>>> On Tue, 11 Apr 2023 at 20:15, Jim Schwartz <jschwar at sbcglobal.net> 
>>> wrote:
>>>>
>>>> What?s the problem now?? Is it with python on windows?? I use 
>>>> python on windows so I?d like to know. Thanks
>>>>
>>>
>>> Python itself is fine, but a lot of third-party packages are hard to
>>> obtain. So if you need numpy, for instance, or psycopg2, you might
>>> need to find an alternative source.
>>
>> I've noticed a big change in the last few years in that PyPi has 
>> many, many amd-64 packages than it used to in the heyday of Christoph 
>> Gohlke's efforts. I haven't needed to go there for some time whereas 
>> I used to need to all the time.? So if I "need numpy, for instance, 
>> or psycopg2" for Windows, I get them from PyPi.
>>
>> Yes, I know that some projects haven't caught up to Python 3.11x yet. 
>> And I'm glad I haven't needed to create a binary wheel for Windows 
>> myself.? But the situation is way better than it used to be.? I've 
>> had more trouble with Python and Python packages on Linux than on 
>> Windows.
>>
>
>
>


-- 
Signed email is an absolute defence against phishing. This email has
been signed with my private key. If you import my public key you can
automatically decrypt my signature and be sure it came from me. Your
email software can handle signing.

-------------- next part --------------
A non-text attachment was scrubbed...
Name: OpenPGP_signature
Type: application/pgp-signature
Size: 495 bytes
Desc: OpenPGP digital signature
URL: <https://mail.python.org/pipermail/python-list/attachments/20230412/0e123c5e/attachment.sig>

From list1 at tompassin.net  Wed Apr 12 09:19:59 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Wed, 12 Apr 2023 09:19:59 -0400
Subject: Christoph Gohlke and compiled packages
In-Reply-To: <0db1af84-212e-566a-2a8f-bed5226987f5@dewhirst.com.au>
References: <CAPTjJmpO0x3acr4mKfs9zCtwy6E7KGD_7_8jQqxbQL2z5ep0Wg@mail.gmail.com>
 <DF942C7B-7D3F-4475-A7CB-DE51A7367046@sbcglobal.net>
 <CAPTjJmqykdReJj+dNWbRhHWTPwrWoohDxg3QwnsZh9Z1k6MG8A@mail.gmail.com>
 <82d2b185-c8b9-d1d4-06a7-0d3d1cf8d1da@tompassin.net>
 <e94288eb-d558-fea8-331f-f5a83bf92b73@dewhirst.com.au>
 <0db1af84-212e-566a-2a8f-bed5226987f5@dewhirst.com.au>
Message-ID: <3331243b-5d19-1ada-efde-20da781ce287@tompassin.net>

On 4/12/2023 8:59 AM, Mike Dewhirst wrote:
> Sadly Windows is still in the dock. The jury is still out.
> 
> Turns out the "without a hitch" was based on cached wheels.
> 
> I'm going to start from scratch with new projects using Pythons 3.8, 
> 3.10 and 3.11 and report back.

Sorry for the length to come, but here's what I've got so far - on 
Windows, python 3.11 - all pip-installed.  Note especially numpy, scipy, 
statsmodels, mysql-connector-python, scikit-learn -

C:\Users\tom>py -V
Python 3.11.3

C:\Users\tom>py -m pip list
Package                       Version
----------------------------- -------------------
accessible-pygments           0.0.4
alabaster                     0.7.13
argcomplete                   3.0.5
asciidoc                      10.2.0
asciidoc3                     3.2.3
astroid                       2.15.2
asttokens                     2.2.1
async-generator               1.10
attrs                         22.2.0
Babel                         2.12.1
beautifulsoup4                4.12.1
black                         23.3.0
bleach                        6.0.0
bokeh                         2.4.3
build                         0.10.0
certifi                       2022.12.7
cffi                          1.15.1
cftime                        1.6.2
charset-normalizer            3.1.0
click                         8.1.3
colorama                      0.4.6
colorcet                      3.0.1
contourpy                     1.0.7
csaps                         1.1.0
cycler                        0.11.0
datatable                     1.1.0a0+pr3440.2228
defusedxml                    0.7.1
dialite                       0.5.3
dill                          0.3.6
docutils                      0.19
exceptiongroup                1.1.1
fastjsonschema                2.16.3
fire                          0.5.0
flexx                         0.8.4
fonttools                     4.39.3
frechetdist                   0.6
GenDoc                        1.0.1
ghp-import                    2.1.0
h11                           0.14.0
holoviews                     1.15.4
idna                          3.4
imageio                       2.27.0
imagesize                     1.4.1
importlib-metadata            6.1.0
iniconfig                     2.0.0
isort                         5.12.0
jaraco.classes                3.2.3
jill                          0.11.3
Jinja2                        3.1.2
joblib                        1.2.0
jsonschema                    4.17.3
jupyter_client                8.1.0
jupyter_core                  5.3.0
jupyterlab-pygments           0.2.2
karma-sphinx-theme            0.0.8
keyring                       23.13.1
kiwisolver                    1.4.4
lazy_loader                   0.2
lazy-object-proxy             1.9.0
leo                           6.7.2
linkify-it-py                 2.0.0
localreg                      0.5.0
lxml                          4.9.2
lz4                           4.3.2
Markdown                      3.3.7
markdown-it-py                2.2.0
MarkupSafe                    2.1.2
matplotlib                    3.6.3
mccabe                        0.7.0
mdit-py-plugins               0.3.5
mdurl                         0.1.2
mergedeep                     1.3.4
meta                          1.0.2
mistune                       2.0.5
mizani                        0.8.1
mkdocs                        1.4.2
mkdocs-exclude                1.0.2
more-itertools                9.1.0
mpmath                        1.3.0
multidict                     6.0.4
mypy                          1.2.0
mypy-extensions               1.0.0
mysql-connector-python        8.0.32
mysqlclient                   2.1.1
nbclient                      0.7.3
nbconvert                     7.3.0
nbformat                      5.8.0
nest-asyncio                  1.5.6
netCDF4                       1.6.3
networkx                      3.1
nltk                          3.8.1
numpy                         1.24.2
outcome                       1.2.0
packaging                     23.0
palettable                    3.3.1
pandas                        2.0.0
pandoc                        2.3
pandocfilters                 1.5.0
panel                         0.14.4
param                         1.13.0
pathspec                      0.11.1
patsy                         0.5.3
pep517                        0.13.0
Pillow                        9.5.0
pip                           23.0.1
pipx                          1.2.0
pkginfo                       1.9.6
platformdirs                  3.2.0
plotly                        5.14.1
plotnine                      0.10.1
pluggy                        1.0.0
plumbum                       1.8.1
ply                           3.11
progressbar2                  4.2.0
protobuf                      4.22.1
pscript                       0.7.7
pwlf                          2.2.1
pycodestyle                   2.10.0
pycparser                     2.21
pyct                          0.5.0
pydata-sphinx-theme           0.13.3
pyDOE                         0.3.8
pyenchant                     3.2.2
pyflakes                      3.0.1
pygam                         0.9.0
Pygments                      2.14.0
pylint                        2.17.2
pyparsing                     3.0.9
pyperclip                     1.8.2
pyproject_hooks               1.0.0
PyQt5                         5.15.9
PyQt5-Qt5                     5.15.2
PyQt5-sip                     12.11.1
PyQt6                         6.4.2
PyQt6-Qt6                     6.4.3
PyQt6-sip                     13.4.1
PyQt6-WebEngine               6.4.0
PyQt6-WebEngine-Qt6           6.4.3
PyQtWebEngine                 5.15.6
PyQtWebEngine-Qt5             5.15.2
pyrsistent                    0.19.3
pyshortcuts                   1.8.3
PySocks                       1.7.1
pytest                        7.2.2
python-dateutil               2.8.2
python-dotenv                 1.0.0
python-gnupg                  0.5.0
python-utils                  3.5.2
pytz                          2023.3
pyviz-comms                   2.2.1
PyWavelets                    1.4.1
pywin32                       306
pywin32-ctypes                0.2.0
PyYAML                        6.0
pyyaml_env_tag                0.1
pyzmq                         25.0.2
readme-renderer               37.3
regex                         2023.3.23
requests                      2.28.2
requests-futures              1.0.0
requests-toolbelt             0.10.1
rfc3986                       2.0.0
rich                          13.3.3
scaleogram                    0.9.5
scikit-image                  0.20.0
scikit-learn                  1.2.2
scipy                         1.10.1
seaborn                       0.12.2
selenium                      4.8.3
semantic-version              2.10.0
setuptools                    67.6.1
six                           1.16.0
sniffio                       1.3.0
snowballstemmer               2.2.0
sortedcontainers              2.4.0
soupsieve                     2.4
Sphinx                        6.1.3
sphinx-panels                 0.6.0
sphinx-rtd-theme              1.2.0
sphinxcontrib-applehelp       1.0.4
sphinxcontrib-devhelp         1.0.2
sphinxcontrib-htmlhelp        2.0.1
sphinxcontrib-jquery          4.1
sphinxcontrib-jsmath          1.0.1
sphinxcontrib-mermaid         0.8.1
sphinxcontrib-qthelp          1.0.3
sphinxcontrib-serializinghtml 1.1.5
statsmodels                   0.13.5
tabulate                      0.9.0
tenacity                      8.2.2
termcolor                     2.2.0
textblob                      0.17.1
textual                       0.18.0
threadpoolctl                 3.1.0
tifffile                      2023.3.21
tinycss2                      1.2.1
tk                            0.1.0
tomli                         2.0.1
tomlkit                       0.11.7
tornado                       6.2
tqdm                          4.65.0
traitlets                     5.9.0
trio                          0.22.0
trio-websocket                0.10.2
twine                         4.0.2
types-docutils                0.19.1.7
typing_extensions             4.5.0
tzdata                        2023.3
uc-micro-py                   1.0.1
urllib3                       1.26.15
userpath                      1.8.0
watchdog                      3.0.0
webdriver-manager             3.8.5
webencodings                  0.5.1
webruntime                    0.5.8
websockets                    11.0.1
wget                          3.2
wheel                         0.40.0
Whoosh                        2.7.4
windows-curses                2.3.1
wrapt                         1.15.0
wsproto                       1.2.0
xyzservices                   2023.2.0
yapf                          0.32.0
yarl                          1.8.2
zipp                          3.15.0


From garyfallidis at gmail.com  Tue Apr 11 22:50:42 2023
From: garyfallidis at gmail.com (Eleftherios Garyfallidis)
Date: Tue, 11 Apr 2023 22:50:42 -0400
Subject: DIPY Workshop 2023 now to be held online! April 24-28.
Message-ID: <CAN6JmWOD=S5i973uJnqN7J6jbRgR7MdNoMEs0Zv--t9vUd6LsA@mail.gmail.com>

Dear all,

Due to unexpected events we have had to make the decision to
transition our workshop
<https://dipy.org/workshops/dipy-workshop-2023#Why>to a virtual format.
While this change was unexpected, we are well-prepared due to our previous
experience with our own online platform. Rest assured, we are fully
equipped to ensure that the virtual workshop will run smoothly.

It's worth noting that all talks this year will be conducted live, as
opposed to pre-recorded. So now we are offering the following updated and
flexible registration
<https://dipy.org/workshops/dipy-workshop-2023#Registration>options:

Silver : Starts from $200

   1.

   Listen to the talks live. Learn from the experts.
   2.

   3 days workshop, get the basic kit to strive in the diffusion imaging
   world.
   3.

   Ability to upgrade during the workshop.


Gold :  Starts from $500

Everything in Silver plus:

   1.

   Ability to attend study groups and to present your work.
   2.

   Full 5 days workshop.
   3.

   Certificate of attendance (Linkedin verifiable).


Platinum : Starts from $995

Everything in Gold plus:

   1.

   Provides additional preset hourly meetings with the DIPY developers
   beyond the workshop's duration. These will be 1 to 1 meetings to set up or
   improve your pipeline for your needs. Maximum 6 meetings. Each meeting will
   be 1 hour long.
   2.

   Provides access to the talks and all materials after the workshop.
   3.

   Ability to move to yearly long support.


Register now <https://dipy.org/workshops/dipy-workshop-2023#Registration>!

In summary, the workshop offers:


   -

   Hands-on tutorials - Every single day !!!
   -

   Guided practice sessions (bring your data)
   -

   Personalized certificates of attendance
   -

   Effective networking opportunities with one-to-one follow ups
   -

   Comprehensive explanation of theoretical foundations with practical
   examples
   -

   Access to latest and established methods with code and interfaces
   -

   Pointers to move beyond the current challenges and navigate hard to do
   analyses
   -

   Multiple clinical use cases (AZ, Parkinson?s, Stroke, etc.)


This year there is a higher level of focus in AI and ML. These technologies
have been transforming various industries, and now they are revolutionizing
medical imaging. By harnessing the power of advanced algorithms and vast
data sets, we have successfully integrated machine learning into our
imaging solutions, providing unparalleled accuracy and efficiency.


For those of you who are new to this. DIPY is an open source
<https://twitter.com/hashtag/opensource?src=hashtag_click>software project
used for processing structural and diffusion imaging data. Join us for an
exciting in person workshop hosted online April 24-28.
https://dipy.org/workshops/latest

Our team of expert instructors will guide you through the fundamentals of
diffusion theory, data pre-processing, fiber tracking, and much more.
You'll have the opportunity to learn from industry-leading professionals,
ask questions, and network with like-minded peers.

Register today to secure your spot in this highly anticipated event. Now
online!!

https://dipy.org/workshops/dipy-workshop-2023#Registration


Happy to answer any questions you may have.

Thank you!,

DIPY team

From ali.mohseniroodbari at gmail.com  Wed Apr 12 04:03:13 2023
From: ali.mohseniroodbari at gmail.com (Ali Mohseni Roodbari)
Date: Wed, 12 Apr 2023 11:33:13 +0330
Subject: Weak Type Ability for Python
Message-ID: <CAMpB_8R6EMj4nevu2ucjvTR5X=CL2ktYxAoVnxOZG=46koaR=Q@mail.gmail.com>

Hi all,
Please make this command for Python (if possible):

>>> x=1
>>> y='a'
>>> wprint (x+y)
>>> 1a

In fact make a new type of print command which can print and show strings
and integers together.

Sincerely yours,
Ali.

From info at cmcc.it  Wed Apr 12 06:05:39 2023
From: info at cmcc.it (info cmcc)
Date: Wed, 12 Apr 2023 12:05:39 +0200
Subject: Post Degree in Machine Learning | Job position at CMCC Foundation,
 Italy
In-Reply-To: <CA+-poF+vCUJ_Fc+UWhs9NkPyiFH4Jj=co6hK7QuP6mmyN0M1vg@mail.gmail.com>
References: <CA+-poF+LHxdJtXQLsTLe2=Wh-UCEPUtb-wktbc+-PT702Uf=aw@mail.gmail.com>
 <CA+-poF+vCUJ_Fc+UWhs9NkPyiFH4Jj=co6hK7QuP6mmyN0M1vg@mail.gmail.com>
Message-ID: <CA+-poFK0K5iK43SiQn6JAmyoHh9DMROxFxtGtPrU0PbQ4Zx=1g@mail.gmail.com>

*POST-DEGREE IN MACHINE LEARNING*
[Job Opening Code: 12404]
*Lecce (Italy) - Deadline: 15/04/2023*


Our Division of Advanced Scientific Computing (ASC Division) is considering
the possibility to hire a talented and proactive Post Degree candidate to
support CMCC research activities. The contract will be jointly funded by
CMCC and the HPC Training and Research for Earth Sciences (HPC-TRES)
program.



The job location is CMCC Headquarters in Lecce, Italy.



We are looking for a motivated person with the following requirements:

   - M.Sc. degree in Computer Science or Computer Engineering or equivalent
   fields;
   - 2+ years? experience in scientific software development;
   - Excellent knowledge of Python programming language;
   - Good knowledge of Python scientific (numpy, scipy, scikit-learn,
   pandas) and visualization (e.g., matplotlib) libraries;
   - Good theoretical knowledge of Machine Learning algorithms and
   techniques for regression and classification tasks;
   - Good knowledge of at least one Machine/Deep Learning framework (e.g.,
   TensorFlow, Keras, Pytorch);
   - Good capabilities in writing technical reports and scientific papers
   as well as documenting code;
   - Good knowledge of both written and spoken English language.

Additional preferred experience:

   - Experience with HPC systems
   - Experience in training ML models in distributed environments and
   corresponding strategies

Belonging to legally protected categories (ex L. 68/99) will constitute a
preferential condition.


*More details and info about HOW TO APPLY:*
https://cmccfoundation.applytojob.com/apply/c4A2a92Co7/12404-POST-DEGREEMachine-Learning-Skills?source=Our%20Career%20Page%20Widget
--

Fondazione CMCCCentro Euro-Mediterraneo sui Cambiamenti Climatici
Via Marco Biagi, 5 - 73100 Lecce
info at cmcc.it - www.cmcc.it

From nospam at please.ty  Wed Apr 12 06:29:59 2023
From: nospam at please.ty (jak)
Date: Wed, 12 Apr 2023 12:29:59 +0200
Subject: for a 'good python'
Message-ID: <u16177$309hc$1@dont-email.me>

Hi everyone,
some time ago I wrote a class to determine if an ipv4 address belonged
to a subnet. Seldom using python I'm pretty sure it's not written in
'good python' nor too portable. Could you give me some advice to make it
better?

class calcip:
     def __init__(self, psubnet: str):
         ssubnet, scidr = psubnet.replace(' ', '').split('/')
         subnet = int.from_bytes(tuple(
                                   map(lambda n: (int(n)), 
ssubnet.split('.'))),
                                 'big')
         cidr = int(scidr)
         mask = ((2 ** cidr) - 1) << (32 - cidr)
         self.__network = subnet & mask
         self.__wildcard = ~mask & 0xffffffff
         self.__broadcast = (subnet | self.__wildcard) & 0xffffffff
         self.__tsubnet = tuple(subnet.to_bytes(4, 'big'))
         self.__tnetwork = tuple(self.__network.to_bytes(4, 'big'))
         self.__tbroadcast = tuple(self.__broadcast.to_bytes(4, 'big'))
         self.__tmask = tuple(mask.to_bytes(4, 'big'))
         self.__twildcard = tuple(self.__wildcard.to_bytes(4, 'big'))
         self.__host_min = tuple((self.__network + 1).to_bytes(4, 'big'))
         self.__host_max = tuple((self.__broadcast - 1).to_bytes(4, 'big'))

     @staticmethod
     def __to_str(val: tuple):
         return '.'.join(str(v) for v in val)

     @property
     def subnet(self):
         return self.__to_str(self.__tsubnet)

     @property
     def network(self):
         return self.__to_str(self.__tnetwork)

     @property
     def broadcast(self):
         return self.__to_str(self.__tbroadcast)

     @property
     def mask(self):
         return self.__to_str(self.__tmask)

     @property
     def wildcard(self):
         return self.__to_str(self.__twildcard)

     @property
     def host_min(self):
         return self.__to_str(self.__host_min)

     @property
     def host_max(self):
         return self.__to_str(self.__host_max)

     @property
     def hosts_num(self):
         return self.__wildcard - 1

     @property
     def net_class(self):
         tst = (self.__tnetwork[0] & 0xf0) >> 4
         if (tst & 0x8) == 0:
             clx = 'A'
         elif (tst & 0xc) == 0x8:
             clx = 'B'
         elif (tst & 0xe) == 0xc:
             clx = 'C'
         elif (tst & 0xf) == 0xe:
             clx = 'D'
         elif (tst & 0xf) == 0xf:
             clx = 'E'
         return clx

     def __contains__(self, item):
         ret = True
         row_hdr = None
         try:
             row_hdr = int.from_bytes(tuple(map(lambda n: (int(n)), 
item.split('.'))), 'big')
         except:
             ret = False
         if ret:
             if not self.__network < row_hdr < self.__broadcast:
                 ret = False
         return ret


def main():
     sn = calcip('10.0.0.0/26')

     print(f"subnet: {sn.subnet}")
     print(f"network: {sn.network}")
     print(f"broadcast: {sn.broadcast}")
     print(f"mask: {sn.mask}")
     print(f"wildcard: {sn.wildcard}")
     print(f"host_min: {sn.host_min}")
     print(f"host_max: {sn.host_max}")
     print(f"Avaible hosts: {sn.hosts_num}")
     print(f"Class: {sn.net_class}")

     tst_hdr = '10.0.0.31'
     is_not = 'is '
     if not tst_hdr in sn:
         is_not = 'is NOT '
     print("hdr %s %sin range %s - %s" %
           (tst_hdr, is_not, sn.host_min, sn.host_max))

if __name__ == '__main__':
     main()

From nospam at please.ty  Wed Apr 12 08:50:29 2023
From: nospam at please.ty (jak)
Date: Wed, 12 Apr 2023 14:50:29 +0200
Subject: for a 'good python'
In-Reply-To: <good-20230412115228@ram.dialup.fu-berlin.de>
References: <u16177$309hc$1@dont-email.me>
 <good-20230412115228@ram.dialup.fu-berlin.de>
Message-ID: <u169el$31fja$1@dont-email.me>

Stefan Ram ha scritto:
> jak <nospam at please.ty> writes:
>> @property
>> def subnet(self):
>>     return self.__to_str(self.__tsubnet)
> 
>    Maybe each of those attributes should be an object of a
>    special class where your "__to_str" is "__str__"? E.g.,
> 
> # code in "calcip.__init__"
> self.tsubnet = ip_address_class.from_int( subnet )
> 
>    where "ip_address_class" is as in:
> 
> import collections
> import random
> 
> class ip_address_class( collections.UserList ):
>      def __init__( self, bytes_address ):
>          super().__init__( bytes_address )
>      @classmethod
>      def from_int( cls, int_address ):
>          return cls( int_address.to_bytes( 4, 'big' ))
>      def __str__( self ):
>          return '.'.join( str( byte_ )for byte_ in self.data )
> 
> if __name__ == '__main__':
>      ip_address = \
>      ip_address_class.from_int( random.randint( 0, 4294967295 ))
>      print( ip_address[ 0 ])
>      print( ip_address )
> 
>    . Now the client can access each byte individually and also
>    get a "nice" string representation.
> 
>    (You may add more "from_..." methods for all the various
>    formats you create addresses from.)
> 
>    But you should also research the standard library to see
>    if something like this doesn't already exist ready-made
>    specifically for IP addresses in the standard library.
> 
> 
ok. thanks a lot. now i try to do that.



From rosuav at gmail.com  Wed Apr 12 13:11:35 2023
From: rosuav at gmail.com (Chris Angelico)
Date: Thu, 13 Apr 2023 03:11:35 +1000
Subject: Weak Type Ability for Python
In-Reply-To: <CAMpB_8R6EMj4nevu2ucjvTR5X=CL2ktYxAoVnxOZG=46koaR=Q@mail.gmail.com>
References: <CAMpB_8R6EMj4nevu2ucjvTR5X=CL2ktYxAoVnxOZG=46koaR=Q@mail.gmail.com>
Message-ID: <CAPTjJmoQgJ+8Dgu-1TpM=YL4qS+8bOk=J-eLvL0k=uY=vAJ8bQ@mail.gmail.com>

On Thu, 13 Apr 2023 at 03:05, Ali Mohseni Roodbari
<ali.mohseniroodbari at gmail.com> wrote:
>
> Hi all,
> Please make this command for Python (if possible):
>
> >>> x=1
> >>> y='a'
> >>> wprint (x+y)
> >>> 1a
>
> In fact make a new type of print command which can print and show strings
> and integers together.
>

Try:

print(x, y)

ChrisA

From mats at wichmann.us  Wed Apr 12 14:57:39 2023
From: mats at wichmann.us (Mats Wichmann)
Date: Wed, 12 Apr 2023 12:57:39 -0600
Subject: Weak Type Ability for Python
In-Reply-To: <CAPTjJmoQgJ+8Dgu-1TpM=YL4qS+8bOk=J-eLvL0k=uY=vAJ8bQ@mail.gmail.com>
References: <CAMpB_8R6EMj4nevu2ucjvTR5X=CL2ktYxAoVnxOZG=46koaR=Q@mail.gmail.com>
 <CAPTjJmoQgJ+8Dgu-1TpM=YL4qS+8bOk=J-eLvL0k=uY=vAJ8bQ@mail.gmail.com>
Message-ID: <5d7514ec-d6b0-85e8-1c3f-d05c14ff0c24@wichmann.us>

On 4/12/23 11:11, Chris Angelico wrote:
> On Thu, 13 Apr 2023 at 03:05, Ali Mohseni Roodbari
> <ali.mohseniroodbari at gmail.com> wrote:
>>
>> Hi all,
>> Please make this command for Python (if possible):
>>
>>>>> x=1
>>>>> y='a'
>>>>> wprint (x+y)
>>>>> 1a
>>
>> In fact make a new type of print command which can print and show strings
>> and integers together.
>>
> 
> Try:
> 
> print(x, y)
> 
> ChrisA


To continue on, what do you want "addition" of dissimilar types to do - 
since that's what you have asked for above.

You can write yourself an object which is happy with certain 
combinations, so you don't have this scenario:

 >>> x + y
Traceback (most recent call last):
   File "<input>", line 1, in <module>
     x + y
      ~~^~~
TypeError: can only concatenate str (not "int") to str
 >>> y + x
Traceback (most recent call last):
   File "<input>", line 1, in <module>
     y + x
      ~~^~~
TypeError: unsupported operand type(s) for +: 'int' and 'str'
 >>>


Or you can help out the print function by doing some of the fiddling 
yourself:

 >>> print(f"{x}{y}")
1a





From list1 at tompassin.net  Wed Apr 12 14:51:44 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Wed, 12 Apr 2023 14:51:44 -0400
Subject: Weak Type Ability for Python
In-Reply-To: <CAPTjJmoQgJ+8Dgu-1TpM=YL4qS+8bOk=J-eLvL0k=uY=vAJ8bQ@mail.gmail.com>
References: <CAMpB_8R6EMj4nevu2ucjvTR5X=CL2ktYxAoVnxOZG=46koaR=Q@mail.gmail.com>
 <CAPTjJmoQgJ+8Dgu-1TpM=YL4qS+8bOk=J-eLvL0k=uY=vAJ8bQ@mail.gmail.com>
Message-ID: <bab80f52-8ae5-ffd6-d7f2-ccee7cfdbdde@tompassin.net>

On 4/12/2023 1:11 PM, Chris Angelico wrote:
> On Thu, 13 Apr 2023 at 03:05, Ali Mohseni Roodbari
> <ali.mohseniroodbari at gmail.com> wrote:
>>
>> Hi all,
>> Please make this command for Python (if possible):
>>
>>>>> x=1
>>>>> y='a'
>>>>> wprint (x+y)
>>>>> 1a
>>
>> In fact make a new type of print command which can print and show strings
>> and integers together.
>>
> 
> Try:
> 
> print(x, y)
> 
> ChrisA

It puts a space between "1" and "a", whereas the question does not want 
the space.  print(f'{x}{y}') would do it, but only works for variables 
named "x" and "y".

As happens so often, the OP has not specified what he actually wants to 
do so we can only answer the very specific question.


From python at mrabarnett.plus.com  Wed Apr 12 15:11:32 2023
From: python at mrabarnett.plus.com (MRAB)
Date: Wed, 12 Apr 2023 20:11:32 +0100
Subject: Weak Type Ability for Python
In-Reply-To: <5d7514ec-d6b0-85e8-1c3f-d05c14ff0c24@wichmann.us>
References: <CAMpB_8R6EMj4nevu2ucjvTR5X=CL2ktYxAoVnxOZG=46koaR=Q@mail.gmail.com>
 <CAPTjJmoQgJ+8Dgu-1TpM=YL4qS+8bOk=J-eLvL0k=uY=vAJ8bQ@mail.gmail.com>
 <5d7514ec-d6b0-85e8-1c3f-d05c14ff0c24@wichmann.us>
Message-ID: <86423bf1-aa48-5ce4-f144-81024cc3c351@mrabarnett.plus.com>

On 2023-04-12 19:57, Mats Wichmann wrote:
> On 4/12/23 11:11, Chris Angelico wrote:
>> On Thu, 13 Apr 2023 at 03:05, Ali Mohseni Roodbari
>> <ali.mohseniroodbari at gmail.com> wrote:
>>>
>>> Hi all,
>>> Please make this command for Python (if possible):
>>>
>>>>>> x=1
>>>>>> y='a'
>>>>>> wprint (x+y)
>>>>>> 1a
>>>
>>> In fact make a new type of print command which can print and show strings
>>> and integers together.
>>>
>> 
>> Try:
>> 
>> print(x, y)
>> 
>> ChrisA
> 
> 
> To continue on, what do you want "addition" of dissimilar types to do -
> since that's what you have asked for above.
> 
> You can write yourself an object which is happy with certain
> combinations, so you don't have this scenario:
> 
>   >>> x + y
> Traceback (most recent call last):
>     File "<input>", line 1, in <module>
>       x + y
>        ~~^~~
> TypeError: can only concatenate str (not "int") to str
>   >>> y + x
> Traceback (most recent call last):
>     File "<input>", line 1, in <module>
>       y + x
>        ~~^~~
> TypeError: unsupported operand type(s) for +: 'int' and 'str'
>   >>>
> 
> 
> Or you can help out the print function by doing some of the fiddling
> yourself:
> 
>   >>> print(f"{x}{y}")
> 1a
> 
Or:

>>> print(x, y, sep='')
1a

From grant.b.edwards at gmail.com  Wed Apr 12 15:22:44 2023
From: grant.b.edwards at gmail.com (Grant Edwards)
Date: Wed, 12 Apr 2023 12:22:44 -0700 (PDT)
Subject: Weak Type Ability for Python
References: <CAMpB_8R6EMj4nevu2ucjvTR5X=CL2ktYxAoVnxOZG=46koaR=Q@mail.gmail.com>
Message-ID: <64370504.050a0220.fb954.4fef@mx.google.com>

On 2023-04-12, Ali Mohseni Roodbari <ali.mohseniroodbari at gmail.com> wrote:
> Hi all,
> Please make this command for Python (if possible):
>
>>>> x=1
>>>> y='a'
>>>> wprint (x+y)
>>>> 1a

If that's what you want, use PHP or some other language. Don't try to ruin Python.

> In fact make a new type of print command which can print and show strings
> and integers together.



From 2QdxY4RzWzUUiLuE at potatochowder.com  Wed Apr 12 15:17:17 2023
From: 2QdxY4RzWzUUiLuE at potatochowder.com (2QdxY4RzWzUUiLuE at potatochowder.com)
Date: Wed, 12 Apr 2023 15:17:17 -0400
Subject: Weak Type Ability for Python
In-Reply-To: <bab80f52-8ae5-ffd6-d7f2-ccee7cfdbdde@tompassin.net>
References: <CAMpB_8R6EMj4nevu2ucjvTR5X=CL2ktYxAoVnxOZG=46koaR=Q@mail.gmail.com>
 <CAPTjJmoQgJ+8Dgu-1TpM=YL4qS+8bOk=J-eLvL0k=uY=vAJ8bQ@mail.gmail.com>
 <bab80f52-8ae5-ffd6-d7f2-ccee7cfdbdde@tompassin.net>
Message-ID: <ZDcDvUugOChh6n6q@anomaly>

On 2023-04-12 at 14:51:44 -0400,
Thomas Passin <list1 at tompassin.net> wrote:

> On 4/12/2023 1:11 PM, Chris Angelico wrote:
> > On Thu, 13 Apr 2023 at 03:05, Ali Mohseni Roodbari
> > <ali.mohseniroodbari at gmail.com> wrote:
> > > 
> > > Hi all,
> > > Please make this command for Python (if possible):
> > > 
> > > > > > x=1
> > > > > > y='a'
> > > > > > wprint (x+y)
> > > > > > 1a
> > > 
> > > In fact make a new type of print command which can print and show strings
> > > and integers together.
> > > 
> > 
> > Try:
> > 
> > print(x, y)
> > 
> > ChrisA
> 
> It puts a space between "1" and "a", whereas the question does not want the
> space.  print(f'{x}{y}') would do it, but only works for variables named "x"
> and "y".

Or possibly print(x, y, sep='').

> As happens so often, the OP has not specified what he actually wants to do
> so we can only answer the very specific question.

Agreed.

From barry at barrys-emacs.org  Wed Apr 12 17:36:57 2023
From: barry at barrys-emacs.org (Barry)
Date: Wed, 12 Apr 2023 22:36:57 +0100
Subject: for a 'good python'
Message-ID: <B7160289-C80D-455D-A46D-E633C1F41408@barrys-emacs.org>

?


> On 12 Apr 2023, at 18:10, jak <nospam at please.ty> wrote:
> ?Hi everyone,
> some time ago I wrote a class to determine if an ipv4 address belonged
> to a subnet. Seldom using python I'm pretty sure it's not written in
> 'good python' nor too portable. Could you give me some advice to make it
> better?
> 
> class calcip:
>    def __init__(self, psubnet: str):
>        ssubnet, scidr = psubnet.replace(' ', '').split('/')
>        subnet = int.from_bytes(tuple(
>                                  map(lambda n: (int(n)), ssubnet.split('.'))),
>                                'big')
>        cidr = int(scidr)
>        mask = ((2 ** cidr) - 1) << (32 - cidr)
>        self.__network = subnet & mask
>        self.__wildcard = ~mask & 0xffffffff
>        self.__broadcast = (subnet | self.__wildcard) & 0xffffffff
>        self.__tsubnet = tuple(subnet.to_bytes(4, 'big'))
>        self.__tnetwork = tuple(self.__network.to_bytes(4, 'big'))
>        self.__tbroadcast = tuple(self.__broadcast.to_bytes(4, 'big'))
>        self.__tmask = tuple(mask.to_bytes(4, 'big'))
>        self.__twildcard = tuple(self.__wildcard.to_bytes(4, 'big'))
>        self.__host_min = tuple((self.__network + 1).to_bytes(4, 'big'))
>        self.__host_max = tuple((self.__broadcast - 1).to_bytes(4, 'big'))
> 
>    @staticmethod
>    def __to_str(val: tuple):
>        return '.'.join(str(v) for v in val)
> 
>    @property
>    def subnet(self):
>        return self.__to_str(self.__tsubnet)
> 
>    @property
>    def network(self):
>        return self.__to_str(self.__tnetwork)
> 
>    @property
>    def broadcast(self):
>        return self.__to_str(self.__tbroadcast)
> 
>    @property
>    def mask(self):
>        return self.__to_str(self.__tmask)
> 
>    @property
>    def wildcard(self):
>        return self.__to_str(self.__twildcard)
> 
>    @property
>    def host_min(self):
>        return self.__to_str(self.__host_min)
> 
>    @property
>    def host_max(self):
>        return self.__to_str(self.__host_max)
> 
>    @property
>    def hosts_num(self):
>        return self.__wildcard - 1
> 
>    @property
>    def net_class(self):
>        tst = (self.__tnetwork[0] & 0xf0) >> 4
>        if (tst & 0x8) == 0:
>            clx = 'A'
>        elif (tst & 0xc) == 0x8:
>            clx = 'B'
>        elif (tst & 0xe) == 0xc:
>            clx = 'C'
>        elif (tst & 0xf) == 0xe:
>            clx = 'D'
>        elif (tst & 0xf) == 0xf:
>            clx = 'E'
>        return clx
> 
>    def __contains__(self, item):
>        ret = True
>        row_hdr = None
>        try:
>            row_hdr = int.from_bytes(tuple(map(lambda n: (int(n)), item.split('.'))), 'big')
>        except:
>            ret = False
>        if ret:
>            if not self.__network < row_hdr < self.__broadcast:
>                ret = False
>        return ret
> 
> 
> def main():
>    sn = calcip('10.0.0.0/26')
> 
>    print(f"subnet: {sn.subnet}")
>    print(f"network: {sn.network}")
>    print(f"broadcast: {sn.broadcast}")
>    print(f"mask: {sn.mask}")
>    print(f"wildcard: {sn.wildcard}")
>    print(f"host_min: {sn.host_min}")
>    print(f"host_max: {sn.host_max}")
>    print(f"Avaible hosts: {sn.hosts_num}")
>    print(f"Class: {sn.net_class}")
> 
>    tst_hdr = '10.0.0.31'
>    is_not = 'is '
>    if not tst_hdr in sn:
>        is_not = 'is NOT '
>    print("hdr %s %sin range %s - %s" %
>          (tst_hdr, is_not, sn.host_min, sn.host_max))
> 
> if __name__ == '__main__':
>    main()

There is this https://docs.python.org/3/howto/ipaddress.html if you just want a solution.

Or are you after code review feedback?

Barry

> -- 
> https://mail.python.org/mailman/listinfo/python-list

From nospam at please.ty  Wed Apr 12 18:21:58 2023
From: nospam at please.ty (jak)
Date: Thu, 13 Apr 2023 00:21:58 +0200
Subject: for a 'good python'
In-Reply-To: <mailman.52.1681335436.20750.python-list@python.org>
References: <B7160289-C80D-455D-A46D-E633C1F41408@barrys-emacs.org>
 <mailman.52.1681335436.20750.python-list@python.org>
Message-ID: <u17au5$2lss$1@dont-email.me>

Barry ha scritto:
> ?
> 
> 
>> On 12 Apr 2023, at 18:10, jak <nospam at please.ty> wrote:
>> ?Hi everyone,
>> some time ago I wrote a class to determine if an ipv4 address belonged
>> to a subnet. Seldom using python I'm pretty sure it's not written in
>> 'good python' nor too portable. Could you give me some advice to make it
>> better?
>>
>> class calcip:
>>     def __init__(self, psubnet: str):
>>         ssubnet, scidr = psubnet.replace(' ', '').split('/')
>>         subnet = int.from_bytes(tuple(
>>                                   map(lambda n: (int(n)), ssubnet.split('.'))),
>>                                 'big')
>>         cidr = int(scidr)
>>         mask = ((2 ** cidr) - 1) << (32 - cidr)
>>         self.__network = subnet & mask
>>         self.__wildcard = ~mask & 0xffffffff
>>         self.__broadcast = (subnet | self.__wildcard) & 0xffffffff
>>         self.__tsubnet = tuple(subnet.to_bytes(4, 'big'))
>>         self.__tnetwork = tuple(self.__network.to_bytes(4, 'big'))
>>         self.__tbroadcast = tuple(self.__broadcast.to_bytes(4, 'big'))
>>         self.__tmask = tuple(mask.to_bytes(4, 'big'))
>>         self.__twildcard = tuple(self.__wildcard.to_bytes(4, 'big'))
>>         self.__host_min = tuple((self.__network + 1).to_bytes(4, 'big'))
>>         self.__host_max = tuple((self.__broadcast - 1).to_bytes(4, 'big'))
>>
>>     @staticmethod
>>     def __to_str(val: tuple):
>>         return '.'.join(str(v) for v in val)
>>
>>     @property
>>     def subnet(self):
>>         return self.__to_str(self.__tsubnet)
>>
>>     @property
>>     def network(self):
>>         return self.__to_str(self.__tnetwork)
>>
>>     @property
>>     def broadcast(self):
>>         return self.__to_str(self.__tbroadcast)
>>
>>     @property
>>     def mask(self):
>>         return self.__to_str(self.__tmask)
>>
>>     @property
>>     def wildcard(self):
>>         return self.__to_str(self.__twildcard)
>>
>>     @property
>>     def host_min(self):
>>         return self.__to_str(self.__host_min)
>>
>>     @property
>>     def host_max(self):
>>         return self.__to_str(self.__host_max)
>>
>>     @property
>>     def hosts_num(self):
>>         return self.__wildcard - 1
>>
>>     @property
>>     def net_class(self):
>>         tst = (self.__tnetwork[0] & 0xf0) >> 4
>>         if (tst & 0x8) == 0:
>>             clx = 'A'
>>         elif (tst & 0xc) == 0x8:
>>             clx = 'B'
>>         elif (tst & 0xe) == 0xc:
>>             clx = 'C'
>>         elif (tst & 0xf) == 0xe:
>>             clx = 'D'
>>         elif (tst & 0xf) == 0xf:
>>             clx = 'E'
>>         return clx
>>
>>     def __contains__(self, item):
>>         ret = True
>>         row_hdr = None
>>         try:
>>             row_hdr = int.from_bytes(tuple(map(lambda n: (int(n)), item.split('.'))), 'big')
>>         except:
>>             ret = False
>>         if ret:
>>             if not self.__network < row_hdr < self.__broadcast:
>>                 ret = False
>>         return ret
>>
>>
>> def main():
>>     sn = calcip('10.0.0.0/26')
>>
>>     print(f"subnet: {sn.subnet}")
>>     print(f"network: {sn.network}")
>>     print(f"broadcast: {sn.broadcast}")
>>     print(f"mask: {sn.mask}")
>>     print(f"wildcard: {sn.wildcard}")
>>     print(f"host_min: {sn.host_min}")
>>     print(f"host_max: {sn.host_max}")
>>     print(f"Avaible hosts: {sn.hosts_num}")
>>     print(f"Class: {sn.net_class}")
>>
>>     tst_hdr = '10.0.0.31'
>>     is_not = 'is '
>>     if not tst_hdr in sn:
>>         is_not = 'is NOT '
>>     print("hdr %s %sin range %s - %s" %
>>           (tst_hdr, is_not, sn.host_min, sn.host_max))
>>
>> if __name__ == '__main__':
>>     main()
> 
> There is this https://docs.python.org/3/howto/ipaddress.html if you just want a solution.
> 
> Or are you after code review feedback?
> 
> Barry
> 
>> -- 
>> https://mail.python.org/mailman/listinfo/python-list


Thank you too. I had seen this library but I always try not to use
libraries outside the standard ones. Now I don't remember why I was
convinced that this wasn't part of it, perhaps because it was like that
at the time or because I got confused. Only now I realized that it is
not necessary to install it. Now I'm considering whether to use
'ipaddress' or 'socket'. What is certain is that this one you have
suggested is really comfortable. Thanks again for the report.


From miked at dewhirst.com.au  Wed Apr 12 21:27:10 2023
From: miked at dewhirst.com.au (Mike Dewhirst)
Date: Thu, 13 Apr 2023 11:27:10 +1000
Subject: Christoph Gohlke and compiled packages
In-Reply-To: <0db1af84-212e-566a-2a8f-bed5226987f5@dewhirst.com.au>
References: <CAPTjJmpO0x3acr4mKfs9zCtwy6E7KGD_7_8jQqxbQL2z5ep0Wg@mail.gmail.com>
 <DF942C7B-7D3F-4475-A7CB-DE51A7367046@sbcglobal.net>
 <CAPTjJmqykdReJj+dNWbRhHWTPwrWoohDxg3QwnsZh9Z1k6MG8A@mail.gmail.com>
 <82d2b185-c8b9-d1d4-06a7-0d3d1cf8d1da@tompassin.net>
 <e94288eb-d558-fea8-331f-f5a83bf92b73@dewhirst.com.au>
 <0db1af84-212e-566a-2a8f-bed5226987f5@dewhirst.com.au>
Message-ID: <72ff043f-0aa4-1855-fd5f-542b13912dfb@dewhirst.com.au>

On 12/04/2023 10:59 pm, Mike Dewhirst wrote:
> Sadly Windows is still in the dock. The jury is still out.
>
> Turns out the "without a hitch" was based on cached wheels.
>
> I'm going to start from scratch with new projects using Pythons 3.8, 
> 3.10 and 3.11 and report back.

Report summary:

pip install works well with Python 3.8 and 3.10 (and presumably 3.9) but 
3.11 fails.

Report conclusion:

As indicated in this thread, pip cannot find Python 3.11 wheels and 
therefore needs to compile from source. It is looking for Microsoft's 
C++ compiler version 14.

I'll (gulp) attempt to swallow the Koolaid.

See error below ...

Cheers

Mike

(xreq) D:\Users\mike\envs\xreq>pip install -r requirements\dev.txt

...

Collecting psycopg2==2.9.3

 ? Downloading psycopg2-2.9.3.tar.gz (380 kB)

 ???? --------------------------------------- 380.6/380.6 kB 6.0 MB/s eta 0:00:00

 ? Preparing metadata (setup.py) ... done

Collecting Pillow==9.1.1

 ? Downloading Pillow-9.1.1.tar.gz (49.8 MB)

 ???? ---------------------------------------- 49.8/49.8 MB 4.5 MB/s eta 0:00:00

 ? Preparing metadata (setup.py) ... done

...

Installing collected packages: psycopg2, Pillow, ...

 ? DEPRECATION: psycopg2 is being installed using the legacy 'setup.py install' method, because it does not have a 'pyproject.toml' and the 'wheel' package is not installed. pip 23.1 will enforce this behaviour change. A possible replacement is to enable the '--use-pep517' option. Discussion can be found athttps://github.com/pypa/pip/issues/8559

 ? Running setup.py install for psycopg2 ... error

 ? error: subprocess-exited-with-error

 ? ? Running setup.py install for psycopg2 did not run successfully.

 ? ? exit code: 1

 ? ??> [24 lines of output]

 ????? D:\Users\mike\envs\xreq\Lib\site-packages\setuptools\config\setupcfg.py:508: SetuptoolsDeprecationWarning: The license_file parameter is deprecated, use license_files instead.

 ??????? warnings.warn(msg, warning_class)

 ????? running install

 ????? D:\Users\mike\envs\xreq\Lib\site-packages\setuptools\command\install.py:34: SetuptoolsDeprecationWarning: setup.py install is deprecated. Use build and pip and other standards-based tools.

 ??????? warnings.warn(

 ????? running build

 ????? running build_py

 ????? creating build

 ????? creating build\lib.win-amd64-cpython-311

 ????? creating build\lib.win-amd64-cpython-311\psycopg2

 ????? copying lib\errorcodes.py -> build\lib.win-amd64-cpython-311\psycopg2

 ????? copying lib\errors.py -> build\lib.win-amd64-cpython-311\psycopg2

 ????? copying lib\extensions.py -> build\lib.win-amd64-cpython-311\psycopg2

 ????? copying lib\extras.py -> build\lib.win-amd64-cpython-311\psycopg2

 ????? copying lib\pool.py -> build\lib.win-amd64-cpython-311\psycopg2

 ????? copying lib\sql.py -> build\lib.win-amd64-cpython-311\psycopg2

 ????? copying lib\tz.py -> build\lib.win-amd64-cpython-311\psycopg2

 ????? copying lib\_ipaddress.py -> build\lib.win-amd64-cpython-311\psycopg2

 ????? copying lib\_json.py -> build\lib.win-amd64-cpython-311\psycopg2

 ????? copying lib\_range.py -> build\lib.win-amd64-cpython-311\psycopg2

 ????? copying lib\__init__.py -> build\lib.win-amd64-cpython-311\psycopg2

 ????? running build_ext

 ????? building 'psycopg2._psycopg' extension

 ????? error: Microsoft Visual C++ 14.0 or greater is required. Get it with "Microsoft C++ Build Tools":https://visualstudio.microsoft.com/visual-cpp-build-tools/

 ????? [end of output]

 ? note: This error originates from a subprocess, and is likely not a problem with pip.

error: legacy-install-failure

? Encountered error while trying to install package.

??> psycopg2

note: This is an issue with the package mentioned above, not pip.

hint: See above for output from the failure.

(xreq) D:\Users\mike\envs\xreq>




>
> Cheers
>
> Mike
>
> On 12/04/2023 6:13 pm, Mike Dewhirst wrote:
>> Well thank you Christoph Gohlke and thank you Ian Bicking and 
>> colleagues.
>>
>> I just used pip to nakedly install psycopg2 and Pillow without a 
>> hitch. My distrust of Windows has kept me going back to Christoff's 
>> well for years.
>>
>> Maybe it is time to assume innocence unless proven guilty ;-)
>>
>> Thanks to all who showed me the way.
>>
>> Cheers
>>
>> Mike
>>
>> On 11/04/2023 11:39 pm, Thomas Passin wrote:
>>> On 4/11/2023 6:58 AM, Chris Angelico wrote:
>>>> On Tue, 11 Apr 2023 at 20:15, Jim Schwartz <jschwar at sbcglobal.net> 
>>>> wrote:
>>>>>
>>>>> What?s the problem now?? Is it with python on windows?? I use 
>>>>> python on windows so I?d like to know. Thanks
>>>>>
>>>>
>>>> Python itself is fine, but a lot of third-party packages are hard to
>>>> obtain. So if you need numpy, for instance, or psycopg2, you might
>>>> need to find an alternative source.
>>>
>>> I've noticed a big change in the last few years in that PyPi has 
>>> many, many amd-64 packages than it used to in the heyday of 
>>> Christoph Gohlke's efforts. I haven't needed to go there for some 
>>> time whereas I used to need to all the time.? So if I "need numpy, 
>>> for instance, or psycopg2" for Windows, I get them from PyPi.
>>>
>>> Yes, I know that some projects haven't caught up to Python 3.11x 
>>> yet. And I'm glad I haven't needed to create a binary wheel for 
>>> Windows myself.? But the situation is way better than it used to 
>>> be.? I've had more trouble with Python and Python packages on Linux 
>>> than on Windows.
>>>
>>
>>
>>
>
>
>


-- 
Signed email is an absolute defence against phishing. This email has
been signed with my private key. If you import my public key you can
automatically decrypt my signature and be sure it came from me. Your
email software can handle signing.

-------------- next part --------------
A non-text attachment was scrubbed...
Name: OpenPGP_signature
Type: application/pgp-signature
Size: 495 bytes
Desc: OpenPGP digital signature
URL: <https://mail.python.org/pipermail/python-list/attachments/20230413/9b9350d1/attachment.sig>

From python at mrabarnett.plus.com  Wed Apr 12 21:46:47 2023
From: python at mrabarnett.plus.com (MRAB)
Date: Thu, 13 Apr 2023 02:46:47 +0100
Subject: Christoph Gohlke and compiled packages
In-Reply-To: <72ff043f-0aa4-1855-fd5f-542b13912dfb@dewhirst.com.au>
References: <CAPTjJmpO0x3acr4mKfs9zCtwy6E7KGD_7_8jQqxbQL2z5ep0Wg@mail.gmail.com>
 <DF942C7B-7D3F-4475-A7CB-DE51A7367046@sbcglobal.net>
 <CAPTjJmqykdReJj+dNWbRhHWTPwrWoohDxg3QwnsZh9Z1k6MG8A@mail.gmail.com>
 <82d2b185-c8b9-d1d4-06a7-0d3d1cf8d1da@tompassin.net>
 <e94288eb-d558-fea8-331f-f5a83bf92b73@dewhirst.com.au>
 <0db1af84-212e-566a-2a8f-bed5226987f5@dewhirst.com.au>
 <72ff043f-0aa4-1855-fd5f-542b13912dfb@dewhirst.com.au>
Message-ID: <353beaa3-1803-b0c2-06ee-23f63e7ecb2e@mrabarnett.plus.com>

On 2023-04-13 02:27, Mike Dewhirst wrote:
> On 12/04/2023 10:59 pm, Mike Dewhirst wrote:
>> Sadly Windows is still in the dock. The jury is still out.
>>
>> Turns out the "without a hitch" was based on cached wheels.
>>
>> I'm going to start from scratch with new projects using Pythons 3.8, 
>> 3.10 and 3.11 and report back.
> 
> Report summary:
> 
> pip install works well with Python 3.8 and 3.10 (and presumably 3.9) but
> 3.11 fails.
> 
> Report conclusion:
> 
> As indicated in this thread, pip cannot find Python 3.11 wheels and
> therefore needs to compile from source. It is looking for Microsoft's
> C++ compiler version 14.
> 
> I'll (gulp) attempt to swallow the Koolaid.
> 
> See error below ...
> 
> Cheers
> 
> Mike
> 
> (xreq) D:\Users\mike\envs\xreq>pip install -r requirements\dev.txt
> 
> ...
> 
> Collecting psycopg2==2.9.3
> 
>   ? Downloading psycopg2-2.9.3.tar.gz (380 kB)
> 
>   ???? --------------------------------------- 380.6/380.6 kB 6.0 MB/s eta 0:00:00
> 
>   ? Preparing metadata (setup.py) ... done
> 
> Collecting Pillow==9.1.1
> 
>   ? Downloading Pillow-9.1.1.tar.gz (49.8 MB)
> 
>   ???? ---------------------------------------- 49.8/49.8 MB 4.5 MB/s eta 0:00:00
> 
>   ? Preparing metadata (setup.py) ... done
> 
> ...
> 
> Installing collected packages: psycopg2, Pillow, ...
> 
>   ? DEPRECATION: psycopg2 is being installed using the legacy 'setup.py install' method, because it does not have a 'pyproject.toml' and the 'wheel' package is not installed. pip 23.1 will enforce this behaviour change. A possible replacement is to enable the '--use-pep517' option. Discussion can be found athttps://github.com/pypa/pip/issues/8559
> 
>   ? Running setup.py install for psycopg2 ... error
> 
>   ? error: subprocess-exited-with-error
> 
>   ? ? Running setup.py install for psycopg2 did not run successfully.
> 
>   ? ? exit code: 1
> 
>   ? ??> [24 lines of output]
> 
>   ????? D:\Users\mike\envs\xreq\Lib\site-packages\setuptools\config\setupcfg.py:508: SetuptoolsDeprecationWarning: The license_file parameter is deprecated, use license_files instead.
> 
>   ??????? warnings.warn(msg, warning_class)
> 
>   ????? running install
> 
>   ????? D:\Users\mike\envs\xreq\Lib\site-packages\setuptools\command\install.py:34: SetuptoolsDeprecationWarning: setup.py install is deprecated. Use build and pip and other standards-based tools.
> 
>   ??????? warnings.warn(
> 
>   ????? running build
> 
>   ????? running build_py
> 
>   ????? creating build
> 
>   ????? creating build\lib.win-amd64-cpython-311
> 
>   ????? creating build\lib.win-amd64-cpython-311\psycopg2
> 
>   ????? copying lib\errorcodes.py -> build\lib.win-amd64-cpython-311\psycopg2
> 
>   ????? copying lib\errors.py -> build\lib.win-amd64-cpython-311\psycopg2
> 
>   ????? copying lib\extensions.py -> build\lib.win-amd64-cpython-311\psycopg2
> 
>   ????? copying lib\extras.py -> build\lib.win-amd64-cpython-311\psycopg2
> 
>   ????? copying lib\pool.py -> build\lib.win-amd64-cpython-311\psycopg2
> 
>   ????? copying lib\sql.py -> build\lib.win-amd64-cpython-311\psycopg2
> 
>   ????? copying lib\tz.py -> build\lib.win-amd64-cpython-311\psycopg2
> 
>   ????? copying lib\_ipaddress.py -> build\lib.win-amd64-cpython-311\psycopg2
> 
>   ????? copying lib\_json.py -> build\lib.win-amd64-cpython-311\psycopg2
> 
>   ????? copying lib\_range.py -> build\lib.win-amd64-cpython-311\psycopg2
> 
>   ????? copying lib\__init__.py -> build\lib.win-amd64-cpython-311\psycopg2
> 
>   ????? running build_ext
> 
>   ????? building 'psycopg2._psycopg' extension
> 
>   ????? error: Microsoft Visual C++ 14.0 or greater is required. Get it with "Microsoft C++ Build Tools":https://visualstudio.microsoft.com/visual-cpp-build-tools/
> 
>   ????? [end of output]
> 
>   ? note: This error originates from a subprocess, and is likely not a problem with pip.
> 
> error: legacy-install-failure
> 
> ? Encountered error while trying to install package.
> 
> ??> psycopg2
> 
> note: This is an issue with the package mentioned above, not pip.
> 
> hint: See above for output from the failure.
> 
> (xreq) D:\Users\mike\envs\xreq>
> 
[snip]

C:\Users\mrab>py -3.11 -m pip install psycopg2
Collecting psycopg2
   Downloading psycopg2-2.9.6-cp311-cp311-win_amd64.whl (1.2 MB)
      ---------------------------------------- 1.2/1.2 MB 2.4 MB/s eta 
0:00:00
Installing collected packages: psycopg2
Successfully installed psycopg2-2.9.6

C:\Users\mrab>py -3.11 -m pip install Pillow
Requirement already satisfied: Pillow in c:\python311\lib\site-packages 
(9.2.0)


From eryksun at gmail.com  Wed Apr 12 22:00:02 2023
From: eryksun at gmail.com (Eryk Sun)
Date: Wed, 12 Apr 2023 21:00:02 -0500
Subject: Christoph Gohlke and compiled packages
In-Reply-To: <72ff043f-0aa4-1855-fd5f-542b13912dfb@dewhirst.com.au>
References: <CAPTjJmpO0x3acr4mKfs9zCtwy6E7KGD_7_8jQqxbQL2z5ep0Wg@mail.gmail.com>
 <DF942C7B-7D3F-4475-A7CB-DE51A7367046@sbcglobal.net>
 <CAPTjJmqykdReJj+dNWbRhHWTPwrWoohDxg3QwnsZh9Z1k6MG8A@mail.gmail.com>
 <82d2b185-c8b9-d1d4-06a7-0d3d1cf8d1da@tompassin.net>
 <e94288eb-d558-fea8-331f-f5a83bf92b73@dewhirst.com.au>
 <0db1af84-212e-566a-2a8f-bed5226987f5@dewhirst.com.au>
 <72ff043f-0aa4-1855-fd5f-542b13912dfb@dewhirst.com.au>
Message-ID: <CACL+1avcvynzaTL--isBY6DMsmy6UQ3198mUK96PXV5zTikeZg@mail.gmail.com>

On 4/12/23, Mike Dewhirst <miked at dewhirst.com.au> wrote:
>
> Collecting psycopg2==2.9.3

x86 and x64 wheels are available for Python 3.11 if you can use
Psycopg 2 version 2.9.5 or 2.9.6 instead of 2.9.3:

https://pypi.org/project/psycopg2/2.9.5/#files
https://pypi.org/project/psycopg2/2.9.6/#files

From avi.e.gross at gmail.com  Wed Apr 12 22:12:27 2023
From: avi.e.gross at gmail.com (avi.e.gross at gmail.com)
Date: Wed, 12 Apr 2023 22:12:27 -0400
Subject: Weak Type Ability for Python
In-Reply-To: <bab80f52-8ae5-ffd6-d7f2-ccee7cfdbdde@tompassin.net>
References: <CAMpB_8R6EMj4nevu2ucjvTR5X=CL2ktYxAoVnxOZG=46koaR=Q@mail.gmail.com>
 <CAPTjJmoQgJ+8Dgu-1TpM=YL4qS+8bOk=J-eLvL0k=uY=vAJ8bQ@mail.gmail.com>
 <bab80f52-8ae5-ffd6-d7f2-ccee7cfdbdde@tompassin.net>
Message-ID: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>

As originally written, the question posed has way too many possible answers
but the subject line may give a hint. Forget printing.

The Python statement
1 + "a"

SHOULD fail. The first is an integer and the second is  string. These two
are native Python objects that neither define what to do if they are paired
with an object of the other type on the left or the right.

In any case, what should the answer be? Since "a" has no integer value, it
presumably was intended to be the string "1a".

So why NOT use the built-in conversion and instead of:

print(x+y) # where x=1, y='a'

It should be:

print(str(x) + y)

Could this behavior be added to Python? Sure. I wonder how many would not
like it as it often will be an error not caught!

If you defined your own object derived from string and added a __radd__()
method then the method could be made to accept whatever types you wanted
(such as integer or double or probably anything) and simply have code that
converts it to the str() representation and then concatenates them with, or
if you prefer without, any padding between.

I suspect the OP is thinking of languages like PERL or JAVA which guess for
you and make such conversions when it seems to make sense.

Python does not generally choose that as it is quite easy to use one of so
many methods, and lately an f-string is an easy way as others mentioned.


-----Original Message-----
From: Python-list <python-list-bounces+avi.e.gross=gmail.com at python.org> On
Behalf Of Thomas Passin
Sent: Wednesday, April 12, 2023 2:52 PM
To: python-list at python.org
Subject: Re: Weak Type Ability for Python

On 4/12/2023 1:11 PM, Chris Angelico wrote:
> On Thu, 13 Apr 2023 at 03:05, Ali Mohseni Roodbari
> <ali.mohseniroodbari at gmail.com> wrote:
>>
>> Hi all,
>> Please make this command for Python (if possible):
>>
>>>>> x=1
>>>>> y='a'
>>>>> wprint (x+y)
>>>>> 1a
>>
>> In fact make a new type of print command which can print and show strings
>> and integers together.
>>
> 
> Try:
> 
> print(x, y)
> 
> ChrisA

It puts a space between "1" and "a", whereas the question does not want 
the space.  print(f'{x}{y}') would do it, but only works for variables 
named "x" and "y".

As happens so often, the OP has not specified what he actually wants to 
do so we can only answer the very specific question.

-- 
https://mail.python.org/mailman/listinfo/python-list


From miked at dewhirst.com.au  Wed Apr 12 22:18:06 2023
From: miked at dewhirst.com.au (Mike Dewhirst)
Date: Thu, 13 Apr 2023 12:18:06 +1000
Subject: Christoph Gohlke and compiled packages
In-Reply-To: <CACL+1avcvynzaTL--isBY6DMsmy6UQ3198mUK96PXV5zTikeZg@mail.gmail.com>
References: <CAPTjJmpO0x3acr4mKfs9zCtwy6E7KGD_7_8jQqxbQL2z5ep0Wg@mail.gmail.com>
 <DF942C7B-7D3F-4475-A7CB-DE51A7367046@sbcglobal.net>
 <CAPTjJmqykdReJj+dNWbRhHWTPwrWoohDxg3QwnsZh9Z1k6MG8A@mail.gmail.com>
 <82d2b185-c8b9-d1d4-06a7-0d3d1cf8d1da@tompassin.net>
 <e94288eb-d558-fea8-331f-f5a83bf92b73@dewhirst.com.au>
 <0db1af84-212e-566a-2a8f-bed5226987f5@dewhirst.com.au>
 <72ff043f-0aa4-1855-fd5f-542b13912dfb@dewhirst.com.au>
 <CACL+1avcvynzaTL--isBY6DMsmy6UQ3198mUK96PXV5zTikeZg@mail.gmail.com>
Message-ID: <64c39139-33ad-7a9c-b570-44cc23e58b01@dewhirst.com.au>

On 13/04/2023 12:00 pm, Eryk Sun wrote:
> On 4/12/23, Mike Dewhirst<miked at dewhirst.com.au>  wrote:
>> Collecting psycopg2==2.9.3
> x86 and x64 wheels are available for Python 3.11 if you can use
> Psycopg 2 version 2.9.5 or 2.9.6 instead of 2.9.3:
>
> https://pypi.org/project/psycopg2/2.9.5/#files
> https://pypi.org/project/psycopg2/2.9.6/#files

Many thanks to both of you ...

I'll uninstall Microsoft Build Tools as soon as its finished installing 
(37.3GB and I had to clear space for it)

Cheers

Mike




-- 
Signed email is an absolute defence against phishing. This email has
been signed with my private key. If you import my public key you can
automatically decrypt my signature and be sure it came from me. Your
email software can handle signing.

-------------- next part --------------
A non-text attachment was scrubbed...
Name: OpenPGP_signature
Type: application/pgp-signature
Size: 495 bytes
Desc: OpenPGP digital signature
URL: <https://mail.python.org/pipermail/python-list/attachments/20230413/d9679f74/attachment.sig>

From cs at cskk.id.au  Wed Apr 12 22:21:58 2023
From: cs at cskk.id.au (Cameron Simpson)
Date: Thu, 13 Apr 2023 12:21:58 +1000
Subject: Weak Type Ability for Python
In-Reply-To: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
References: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
Message-ID: <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>

On 12Apr2023 22:12, avi.e.gross at gmail.com <avi.e.gross at gmail.com> wrote:
>I suspect the OP is thinking of languages like PERL or JAVA which guess 
>for
>you and make such conversions when it seems to make sense.

JavaScript guesses. What a nightmare. Java acts like Python and will 
forbid it on type grounds (at compile time with Java, being staticly 
typed).

Cheers,
Cameron Simpson <cs at cskk.id.au>

From python at mrabarnett.plus.com  Wed Apr 12 22:28:37 2023
From: python at mrabarnett.plus.com (MRAB)
Date: Thu, 13 Apr 2023 03:28:37 +0100
Subject: Weak Type Ability for Python
In-Reply-To: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
References: <CAMpB_8R6EMj4nevu2ucjvTR5X=CL2ktYxAoVnxOZG=46koaR=Q@mail.gmail.com>
 <CAPTjJmoQgJ+8Dgu-1TpM=YL4qS+8bOk=J-eLvL0k=uY=vAJ8bQ@mail.gmail.com>
 <bab80f52-8ae5-ffd6-d7f2-ccee7cfdbdde@tompassin.net>
 <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
Message-ID: <e9f694a5-dbe6-926e-085d-346cb374ae64@mrabarnett.plus.com>

On 2023-04-13 03:12, avi.e.gross at gmail.com wrote:
> As originally written, the question posed has way too many possible answers
> but the subject line may give a hint. Forget printing.
> 
> The Python statement
> 1 + "a"
> 
> SHOULD fail. The first is an integer and the second is  string. These two
> are native Python objects that neither define what to do if they are paired
> with an object of the other type on the left or the right.
> 
> In any case, what should the answer be? Since "a" has no integer value, it
> presumably was intended to be the string "1a".
> 
> So why NOT use the built-in conversion and instead of:
> 
> print(x+y) # where x=1, y='a'
> 
> It should be:
> 
> print(str(x) + y)
> 
> Could this behavior be added to Python? Sure. I wonder how many would not
> like it as it often will be an error not caught!
> 
> If you defined your own object derived from string and added a __radd__()
> method then the method could be made to accept whatever types you wanted
> (such as integer or double or probably anything) and simply have code that
> converts it to the str() representation and then concatenates them with, or
> if you prefer without, any padding between.
> 
> I suspect the OP is thinking of languages like PERL or JAVA which guess for
> you and make such conversions when it seems to make sense.
> 
In the case of Perl, there are distinct operators for addition and 
string concatenation, with automatic type conversion (non-numeric 
strings have a numeric value of 0, which can hide bugs).

> Python does not generally choose that as it is quite easy to use one of so
> many methods, and lately an f-string is an easy way as others mentioned.
> 
> 
> -----Original Message-----
> From: Python-list <python-list-bounces+avi.e.gross=gmail.com at python.org> On
> Behalf Of Thomas Passin
> Sent: Wednesday, April 12, 2023 2:52 PM
> To: python-list at python.org
> Subject: Re: Weak Type Ability for Python
> 
> On 4/12/2023 1:11 PM, Chris Angelico wrote:
>> On Thu, 13 Apr 2023 at 03:05, Ali Mohseni Roodbari
>> <ali.mohseniroodbari at gmail.com> wrote:
>>>
>>> Hi all,
>>> Please make this command for Python (if possible):
>>>
>>>>>> x=1
>>>>>> y='a'
>>>>>> wprint (x+y)
>>>>>> 1a
>>>
>>> In fact make a new type of print command which can print and show strings
>>> and integers together.
>>>
>> 
>> Try:
>> 
>> print(x, y)
>> 
>> ChrisA
> 
> It puts a space between "1" and "a", whereas the question does not want
> the space.  print(f'{x}{y}') would do it, but only works for variables
> named "x" and "y".
> 
> As happens so often, the OP has not specified what he actually wants to
> do so we can only answer the very specific question.
> 


From python at mrabarnett.plus.com  Wed Apr 12 22:36:22 2023
From: python at mrabarnett.plus.com (MRAB)
Date: Thu, 13 Apr 2023 03:36:22 +0100
Subject: Weak Type Ability for Python
In-Reply-To: <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>
References: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
 <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>
Message-ID: <e00cf529-1c77-a438-3efa-890d96f141b2@mrabarnett.plus.com>

On 2023-04-13 03:21, Cameron Simpson wrote:
> On 12Apr2023 22:12, avi.e.gross at gmail.com <avi.e.gross at gmail.com> wrote:
>>I suspect the OP is thinking of languages like PERL or JAVA which guess 
>>for
>>you and make such conversions when it seems to make sense.
> 
> JavaScript guesses. What a nightmare. Java acts like Python and will
> forbid it on type grounds (at compile time with Java, being staticly
> typed).
> 
I thought that in Java you can, in fact, concatenate a string and an 
int, so I did a quick search online and it appears that you can.

From avi.e.gross at gmail.com  Wed Apr 12 22:37:36 2023
From: avi.e.gross at gmail.com (avi.e.gross at gmail.com)
Date: Wed, 12 Apr 2023 22:37:36 -0400
Subject: Weak Type Ability for Python
In-Reply-To: <ZDcDvUugOChh6n6q@anomaly>
References: <CAMpB_8R6EMj4nevu2ucjvTR5X=CL2ktYxAoVnxOZG=46koaR=Q@mail.gmail.com>
 <CAPTjJmoQgJ+8Dgu-1TpM=YL4qS+8bOk=J-eLvL0k=uY=vAJ8bQ@mail.gmail.com>
 <bab80f52-8ae5-ffd6-d7f2-ccee7cfdbdde@tompassin.net>
 <ZDcDvUugOChh6n6q@anomaly>
Message-ID: <00ae01d96db0$e8a61350$b9f239f0$@gmail.com>

On closer reading, the OP may be asking how to make a function doing what
they want, albeit without a plus.

Here is a python function as a one-liner that takes exactly two arguments of
any kind (including string and integer) and concatenates them into one
string without anything between and prints them:

def strprint(first, second): print(str(first) + str(second))

>>> strprint(5,1)
51
>>> strprint("a5",1)
a51
>>> strprint(12,"o'clock")
12o'clock
>>> strprint(3.1415926535,complex(3,4))
3.1415926535(3+4j)

Want something similar for any number of arguments? Here is a slightly
longer one-liner:

def strprintall(*many): print(''.join([str(each) for each in many]))

>>>
strprintall(1,"=egy\n",2,"=kett?\n",3,"=h?rom\n",4,"=n?gy\n",5,"=?t\n","in
my childhood language.\n")
1=egy
2=kett?
3=h?rom
4=n?gy
5=?t
in my childhood language.

Note my meager attempt is not using a plus sign as I addressed a sort of way
that could be done using a __radd__ method or other ways like an f-string.

I can not repeat this often enough. The easiest way to do something you want
in a new language is to work within the existing language as-is and not to
ask the language to change to be the way you want. That can take years or
never happen, and especially if the designers did not want the feature you
ask for. 





-----Original Message-----
From: Python-list <python-list-bounces+avi.e.gross=gmail.com at python.org> On
Behalf Of 2QdxY4RzWzUUiLuE at potatochowder.com
Sent: Wednesday, April 12, 2023 3:17 PM
To: python-list at python.org
Subject: Re: Weak Type Ability for Python

On 2023-04-12 at 14:51:44 -0400,
Thomas Passin <list1 at tompassin.net> wrote:

> On 4/12/2023 1:11 PM, Chris Angelico wrote:
> > On Thu, 13 Apr 2023 at 03:05, Ali Mohseni Roodbari
> > <ali.mohseniroodbari at gmail.com> wrote:
> > > 
> > > Hi all,
> > > Please make this command for Python (if possible):
> > > 
> > > > > > x=1
> > > > > > y='a'
> > > > > > wprint (x+y)
> > > > > > 1a
> > > 
> > > In fact make a new type of print command which can print and show
strings
> > > and integers together.
> > > 
> > 
> > Try:
> > 
> > print(x, y)
> > 
> > ChrisA
> 
> It puts a space between "1" and "a", whereas the question does not want
the
> space.  print(f'{x}{y}') would do it, but only works for variables named
"x"
> and "y".

Or possibly print(x, y, sep='').

> As happens so often, the OP has not specified what he actually wants to do
> so we can only answer the very specific question.

Agreed.
-- 
https://mail.python.org/mailman/listinfo/python-list


From cs at cskk.id.au  Wed Apr 12 23:42:38 2023
From: cs at cskk.id.au (Cameron Simpson)
Date: Thu, 13 Apr 2023 13:42:38 +1000
Subject: Weak Type Ability for Python
In-Reply-To: <e00cf529-1c77-a438-3efa-890d96f141b2@mrabarnett.plus.com>
References: <e00cf529-1c77-a438-3efa-890d96f141b2@mrabarnett.plus.com>
Message-ID: <ZDd6LmQOzUXNNUAa@cskk.homeip.net>

On 13Apr2023 03:36, MRAB <python at mrabarnett.plus.com> wrote:
>I thought that in Java you can, in fact, concatenate a string and an 
>int, so I did a quick search online and it appears that you can.

I stand corrected. I could have sworn it didn't, but it has been a long 
time. - Cameron Simpson <cs at cskk.id.au>

From avi.e.gross at gmail.com  Thu Apr 13 01:38:58 2023
From: avi.e.gross at gmail.com (avi.e.gross at gmail.com)
Date: Thu, 13 Apr 2023 01:38:58 -0400
Subject: Weak Type Ability for Python
In-Reply-To: <ZDd6LmQOzUXNNUAa@cskk.homeip.net>
References: <e00cf529-1c77-a438-3efa-890d96f141b2@mrabarnett.plus.com>
 <ZDd6LmQOzUXNNUAa@cskk.homeip.net>
Message-ID: <015501d96dca$3ef2c820$bcd85860$@gmail.com>

Given the significant number of languages other than Python that have some
version of a feature that allows implicit conversion of unlike operands to
concatenate something like a "number" and a string into a string, the
question may not be silly as to how or why Python chose as it chose.

As I see it, python did put in quite a bit of customizability and
flexibility including the ability to create your own object types that alter
the behavior of an operator like plus. I have seen plenty of code that takes
advantage and makes the user of the code assume that different types can
interact seamlessly.

But it is like many other things. Languages that support a wide variety of
integer types such as signed and unsigned versions of integers in 8 bits,
sixteen bits, 32 bits and even 64 bits or perhaps higher, will often look
like they allow you to mix them in various combinations for not just
addition. But underneath it all can be lots of hidden complexity. I have
seen languages that make lots of functions with the same names but different
signatures and then dispatch a call like add(int8, unsignedint32) to the
right function that best matches their signature. The functions internally
can do many things but often convert their arguments to a common format,
perform the operations, then perhaps convert back to whatever result output
was expected.

In the case being discussed we might have to create something that looks
like do_plus(int, int) and then do_plus(int, char) and so on.

The other alternatives can include tables of "generality" and
"convertibility" with rules that govern how to perform a calculation by
changing or upgrading or downgrading things to make a match that can then be
handled. 

The issue here is a sort of operator overloading. In Python, "+" does not
mean plus at all. It means whatever the programmer wanted it to mean. An
infix line of code that includes "obj1 + obj2" is supposed to investigate
how to do it. I am not sure if some built-in objects may be different, but
it does a sequence of operations till it finds what it needs and does it.

I believe it looks a bit like this. The LHS object, obj1, is examined to see
if it has defined a __add__() method. If found, it is called and either
produces a result or signals it cannot handle obj2 for some reason. If that
method is not found, or fails, then it looks to see if the RHS, obj2, has a
__radd__() method defined. That can be given obj1 and return an answer or
signal failure. 

If obj1 is 5 and obj2 is "pm" then we are using the built-in predefined
classes that currently have no interest in concatenating or adding unlike
types like this. If you could add or change these dunder methods (and note
you may also need to deal with __iadd__() to handle the case where x=5 and
you write "x += "pm" albeit that could weirdly change the type of x without
a linter having a clue.

I suggest the latter argument may be a good enough reason that Python did
not implement this. There are many good reasons. Does anyone like a language
that lets you type 2 + "three" and quietly makes that be 5? Sure, it can be
made to work on a subset of number in say English, but will it work in other
languages. It can be hard enough now to write code in UNICODE (I have seen
some) that tries to determine if a code point represents a number in some
language or representation and treats it as a numeral. I have seen the
numeric bullets such as a dark circle containing a white nine be treated as
if the user had put in a nine, for example.

As was mentioned, some languages have different operators for addition
versus concatenation and in that context, it may be intuitive that using the
wrong object type is an implicit call to conversion. Python uses "+" for
both purposes depending on context and potentially for many more purposes
the programmer can devise. 

Consider the asterisk operator as a companion concept. It gladly accepts a
string and a number in either order and does something somewhat intuitive
with them by treating multiplication as a sort of repeated addition:

>>> 5 * "6"
'66666'
>>> "5" * 6
'555555'
>>> 3 * "Hello? "
'Hello? Hello? Hello?

But it will not handle float.

>>> "Hello" * 2.5
TypeError: can't multiply sequence by non-int of type 'float'

If you want to either truncate a float to an into or round it or take a
ceiling, though, it will not guess for you and you must do something
explicit like this:

>>> "Hello" * round(2.5)
'HelloHello'
>>> "Hello" * round(2.6)
'HelloHelloHello'
>>> "Hello" * int(2.6)
'HelloHello'

There is a parallel argument here in arguing it should accept a float and
truncate it. But since you can easily cast a float to an int, in any of many
ways, why have the program choose when it quite likely reflects an error in
the code. And, no, I do not suggest 2.5 be interpreted as putting in an
approximate percentage so that .8 * "Hello" should result in "Hell" ...




-----Original Message-----
From: Python-list <python-list-bounces+avi.e.gross=gmail.com at python.org> On
Behalf Of Cameron Simpson
Sent: Wednesday, April 12, 2023 11:43 PM
To: python-list at python.org
Subject: Re: Weak Type Ability for Python

On 13Apr2023 03:36, MRAB <python at mrabarnett.plus.com> wrote:
>I thought that in Java you can, in fact, concatenate a string and an 
>int, so I did a quick search online and it appears that you can.

I stand corrected. I could have sworn it didn't, but it has been a long 
time. - Cameron Simpson <cs at cskk.id.au>
-- 
https://mail.python.org/mailman/listinfo/python-list


From rosuav at gmail.com  Thu Apr 13 03:01:41 2023
From: rosuav at gmail.com (Chris Angelico)
Date: Thu, 13 Apr 2023 17:01:41 +1000
Subject: Weak Type Ability for Python
In-Reply-To: <015501d96dca$3ef2c820$bcd85860$@gmail.com>
References: <e00cf529-1c77-a438-3efa-890d96f141b2@mrabarnett.plus.com>
 <ZDd6LmQOzUXNNUAa@cskk.homeip.net> <015501d96dca$3ef2c820$bcd85860$@gmail.com>
Message-ID: <CAPTjJmrHgbe46E3z2oe2dZX3B6CyO0K-Ueow3KhW=RbzfsGrfg@mail.gmail.com>

On Thu, 13 Apr 2023 at 15:40, <avi.e.gross at gmail.com> wrote:
> And, no, I do not suggest 2.5 be interpreted as putting in an
> approximate percentage so that .8 * "Hello" should result in "Hell" ...

$ pike
Pike v8.1 release 15 running Hilfe v3.5 (Incremental Pike Frontend)
Ok.
> "Hello, world! " * 2.5;
(1) Result: "Hello, world! Hello, world! Hello, "
> "Hello, world! Hello, world! Hello, " / 10;
(2) Result: ({ /* 3 elements */
                "Hello, wor",
                "ld! Hello,",
                " world! He"
            })
> "Hello, world! Hello, world! Hello, " % 10;
(3) Result: "llo, "
> "Hello, world! Hello, world! Hello, " / 10.0;
(4) Result: ({ /* 4 elements */
                "Hello, wor",
                "ld! Hello,",
                " world! He",
                "llo, "
            })
>

Multiplying and dividing strings by floats makes perfect sense. (The
({ }) notation is Pike's array literal syntax; consider it equivalent
to Python's square brackets for a list.)

ChrisA

From guenther.sohler at gmail.com  Thu Apr 13 03:40:39 2023
From: guenther.sohler at gmail.com (Guenther Sohler)
Date: Thu, 13 Apr 2023 09:40:39 +0200
Subject: Embedded python is not 100% stable
Message-ID: <CAASeUHo-Gq12rgjZKh_dbj1EmY7R-jApL+P0OP0imJ3tMLgTpw@mail.gmail.com>

Hi Python LIst,

I have been working on adding embedded python into OpenSCAD (
www.openscad.org)
for some time already. For that i coded/added an additional Python Type
Object
which means to hold openscad geometric data.

It works quite well but unfortunately its not 100% stable and i have been
heavily checking
all the functions which are referenced in the PyType Object and tried to
match
them with the documentation which i found in the python web site but now i
am stuck
and i cant progress any further
I am specially interested why the program constantly crashes when i
activate the lines 14 and 15
in pyopenscad.cc.
I have attached the two most relevant files and I would be happy if anybody
interested
could tell me, if there is an obvious bug popping into your eyes.
If anybody is interested to see the complete picture, all source code is
available checked in
in github @

https://github.com/gsohler/openscad.git branch "libfive"
Thank you for reading. Any spotted bug found will make me happy

From lal at solute.de  Thu Apr 13 03:42:24 2023
From: lal at solute.de (Lars Liedtke)
Date: Thu, 13 Apr 2023 09:42:24 +0200
Subject: for a 'good python'
In-Reply-To: <u17au5$2lss$1@dont-email.me>
References: <B7160289-C80D-455D-A46D-E633C1F41408@barrys-emacs.org>
 <mailman.52.1681335436.20750.python-list@python.org>
 <u17au5$2lss$1@dont-email.me>
Message-ID: <f488eedc-1afe-acd1-2da4-623d26a210d3@solute.de>




Lars Liedtke
Software Entwickler

[Tel.]  +49 721 98993-
[Fax]   +49 721 98993-
[E-Mail]        lal at solute.de<mailto:lal at solute.de>


solute GmbH
Zeppelinstra?e 15
76185 Karlsruhe
Germany


[Logo Solute]


Marken der solute GmbH | brands of solute GmbH
[Marken]
[Advertising Partner]

Gesch?ftsf?hrer | Managing Director: Dr. Thilo Gans, Bernd Vermaaten
Webseite | www.solute.de <http://www.solute.de/>
Sitz | Registered Office: Karlsruhe
Registergericht | Register Court: Amtsgericht Mannheim
Registernummer | Register No.: HRB 110579
USt-ID | VAT ID: DE234663798



Informationen zum Datenschutz | Information about privacy policy
https://www.solute.de/ger/datenschutz/grundsaetze-der-datenverarbeitung.php




Am 13.04.23 um 00:21 schrieb jak:
Barry ha scritto:
?


On 12 Apr 2023, at 18:10, jak <nospam at please.ty><mailto:nospam at please.ty> wrote:
?Hi everyone,
some time ago I wrote a class to determine if an ipv4 address belonged
to a subnet. Seldom using python I'm pretty sure it's not written in
'good python' nor too portable. Could you give me some advice to make it
better?

class calcip:
    def __init__(self, psubnet: str):
        ssubnet, scidr = psubnet.replace(' ', '').split('/')
        subnet = int.from_bytes(tuple(
                                  map(lambda n: (int(n)), ssubnet.split('.'))),
                                'big')
        cidr = int(scidr)
        mask = ((2 ** cidr) - 1) << (32 - cidr)
        self.__network = subnet & mask
        self.__wildcard = ~mask & 0xffffffff
        self.__broadcast = (subnet | self.__wildcard) & 0xffffffff
        self.__tsubnet = tuple(subnet.to_bytes(4, 'big'))
        self.__tnetwork = tuple(self.__network.to_bytes(4, 'big'))
        self.__tbroadcast = tuple(self.__broadcast.to_bytes(4, 'big'))
        self.__tmask = tuple(mask.to_bytes(4, 'big'))
        self.__twildcard = tuple(self.__wildcard.to_bytes(4, 'big'))
        self.__host_min = tuple((self.__network + 1).to_bytes(4, 'big'))
        self.__host_max = tuple((self.__broadcast - 1).to_bytes(4, 'big'))

    @staticmethod
    def __to_str(val: tuple):
        return '.'.join(str(v) for v in val)

    @property
    def subnet(self):
        return self.__to_str(self.__tsubnet)

    @property
    def network(self):
        return self.__to_str(self.__tnetwork)

    @property
    def broadcast(self):
        return self.__to_str(self.__tbroadcast)

    @property
    def mask(self):
        return self.__to_str(self.__tmask)

    @property
    def wildcard(self):
        return self.__to_str(self.__twildcard)

    @property
    def host_min(self):
        return self.__to_str(self.__host_min)

    @property
    def host_max(self):
        return self.__to_str(self.__host_max)

    @property
    def hosts_num(self):
        return self.__wildcard - 1

    @property
    def net_class(self):
        tst = (self.__tnetwork[0] & 0xf0) >> 4
        if (tst & 0x8) == 0:
            clx = 'A'
        elif (tst & 0xc) == 0x8:
            clx = 'B'
        elif (tst & 0xe) == 0xc:
            clx = 'C'
        elif (tst & 0xf) == 0xe:
            clx = 'D'
        elif (tst & 0xf) == 0xf:
            clx = 'E'
        return clx

    def __contains__(self, item):
        ret = True
        row_hdr = None
        try:
            row_hdr = int.from_bytes(tuple(map(lambda n: (int(n)), item.split('.'))), 'big')
        except:
            ret = False
        if ret:
            if not self.__network < row_hdr < self.__broadcast:
                ret = False
        return ret


def main():
    sn = calcip('10.0.0.0/26')

    print(f"subnet: {sn.subnet}")
    print(f"network: {sn.network}")
    print(f"broadcast: {sn.broadcast}")
    print(f"mask: {sn.mask}")
    print(f"wildcard: {sn.wildcard}")
    print(f"host_min: {sn.host_min}")
    print(f"host_max: {sn.host_max}")
    print(f"Avaible hosts: {sn.hosts_num}")
    print(f"Class: {sn.net_class}")

    tst_hdr = '10.0.0.31'
    is_not = 'is '
    if not tst_hdr in sn:
        is_not = 'is NOT '
    print("hdr %s %sin range %s - %s" %
          (tst_hdr, is_not, sn.host_min, sn.host_max))

if __name__ == '__main__':
    main()

There is this https://docs.python.org/3/howto/ipaddress.html if you just want a solution.

Or are you after code review feedback?

Barry

--
https://mail.python.org/mailman/listinfo/python-list


Thank you too. I had seen this library but I always try not to use
libraries outside the standard ones. Now I don't remember why I was
convinced that this wasn't part of it, perhaps because it was like that
at the time or because I got confused. Only now I realized that it is
not necessary to install it. Now I'm considering whether to use
'ipaddress' or 'socket'. What is certain is that this one you have
suggested is really comfortable. Thanks again for the report.

Unless I am not mistakes, ipadress is "standard" because it is in the standard library

From jpic at yourlabs.org  Thu Apr 13 07:35:16 2023
From: jpic at yourlabs.org (J. Pic)
Date: Thu, 13 Apr 2023 13:35:16 +0200
Subject: Weak Type Ability for Python
In-Reply-To: <CAMpB_8R6EMj4nevu2ucjvTR5X=CL2ktYxAoVnxOZG=46koaR=Q@mail.gmail.com>
References: <CAMpB_8R6EMj4nevu2ucjvTR5X=CL2ktYxAoVnxOZG=46koaR=Q@mail.gmail.com>
Message-ID: <CAC6Op1-2GMZtxpJ2XzCzMQ+T8vWervVnHo3Qs9XnJF6vHO+M4w@mail.gmail.com>

print(f'{x}{y}') ?

On Wed, Apr 12, 2023 at 7:06?PM Ali Mohseni Roodbari <
ali.mohseniroodbari at gmail.com> wrote:

> Hi all,
> Please make this command for Python (if possible):
>
> >>> x=1
> >>> y='a'
> >>> wprint (x+y)
> >>> 1a
>
> In fact make a new type of print command which can print and show strings
> and integers together.
>
> Sincerely yours,
> Ali.
> --
> https://mail.python.org/mailman/listinfo/python-list
>


-- 
Personnel et confidentiel

From list1 at tompassin.net  Thu Apr 13 08:10:30 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Thu, 13 Apr 2023 08:10:30 -0400
Subject: Weak Type Ability for Python
In-Reply-To: <015501d96dca$3ef2c820$bcd85860$@gmail.com>
References: <e00cf529-1c77-a438-3efa-890d96f141b2@mrabarnett.plus.com>
 <ZDd6LmQOzUXNNUAa@cskk.homeip.net>
 <015501d96dca$3ef2c820$bcd85860$@gmail.com>
Message-ID: <ce5a54d6-dcc9-1f2c-59ae-afb671ff696c@tompassin.net>

On 4/13/2023 1:38 AM, avi.e.gross at gmail.com wrote:
> In Python, "+" does not
> mean plus at all. It means whatever the programmer wanted it to mean. An
> infix line of code that includes "obj1 + obj2" is supposed to investigate
> how to do it. I am not sure if some built-in objects may be different, but
> it does a sequence of operations till it finds what it needs and does it.

A really nice example of this is pathlib in the standard library.  You 
can write things like this, overloading the "/" operator:

 >>> from pathlib import PurePath
 >>> pth = PurePath('c:/') / 'temp' / 'python'
 >>> pth
PureWindowsPath('c:/temp/python')
 >>> str(pth)
'c:\\temp\\python'


From dieter at handshake.de  Thu Apr 13 10:21:36 2023
From: dieter at handshake.de (Dieter Maurer)
Date: Thu, 13 Apr 2023 16:21:36 +0200
Subject: Embedded python is not 100% stable
In-Reply-To: <CAASeUHo-Gq12rgjZKh_dbj1EmY7R-jApL+P0OP0imJ3tMLgTpw@mail.gmail.com>
References: <CAASeUHo-Gq12rgjZKh_dbj1EmY7R-jApL+P0OP0imJ3tMLgTpw@mail.gmail.com>
Message-ID: <25656.4080.567997.179911@ixdm.fritz.box>

Guenther Sohler wrote at 2023-4-13 09:40 +0200:
> ...
>I have been working on adding embedded python into OpenSCAD (
>www.openscad.org)
>for some time already. For that i coded/added an additional Python Type
>Object
>which means to hold openscad geometric data.
>
>It works quite well but unfortunately its not 100% stable and i have been
>heavily checking
>all the functions which are referenced in the PyType Object and tried to
>match
>them with the documentation which i found in the python web site

The Python C/C++ interface is complex: it is easy to make
mistakes which may lead to crashes.

Often, `cython` (--> PyPI) can help you to define extension types
in a much safer way. Maybe, you check its documentation?

From barry at barrys-emacs.org  Thu Apr 13 11:00:59 2023
From: barry at barrys-emacs.org (Barry)
Date: Thu, 13 Apr 2023 16:00:59 +0100
Subject: for a 'good python'
Message-ID: <C8DF3182-8172-4FDF-ACBE-1A9FCA3E39D9@barrys-emacs.org>

?

> On 13 Apr 2023, at 00:19, jak <nospam at please.ty> wrote:
> 
> ?Barry ha scritto:
>> ?
>>>> On 12 Apr 2023, at 18:10, jak <nospam at please.ty> wrote:
>>> ?Hi everyone,
>>> some time ago I wrote a class to determine if an ipv4 address belonged
>>> to a subnet. Seldom using python I'm pretty sure it's not written in
>>> 'good python' nor too portable. Could you give me some advice to make it
>>> better?
>>> class calcip:
>>>   def __init__(self, psubnet: str):
>>>       ssubnet, scidr = psubnet.replace(' ', '').split('/')
>>>       subnet = int.from_bytes(tuple(
>>>                                 map(lambda n: (int(n)), ssubnet.split('.'))),
>>>                               'big')
>>>       cidr = int(scidr)
>>>       mask = ((2 ** cidr) - 1) << (32 - cidr)
>>>       self.__network = subnet & mask
>>>       self.__wildcard = ~mask & 0xffffffff
>>>       self.__broadcast = (subnet | self.__wildcard) & 0xffffffff
>>>       self.__tsubnet = tuple(subnet.to_bytes(4, 'big'))
>>>       self.__tnetwork = tuple(self.__network.to_bytes(4, 'big'))
>>>       self.__tbroadcast = tuple(self.__broadcast.to_bytes(4, 'big'))
>>>       self.__tmask = tuple(mask.to_bytes(4, 'big'))
>>>       self.__twildcard = tuple(self.__wildcard.to_bytes(4, 'big'))
>>>       self.__host_min = tuple((self.__network + 1).to_bytes(4, 'big'))
>>>       self.__host_max = tuple((self.__broadcast - 1).to_bytes(4, 'big'))
>>>   @staticmethod
>>>   def __to_str(val: tuple):
>>>       return '.'.join(str(v) for v in val)
>>>   @property
>>>   def subnet(self):
>>>       return self.__to_str(self.__tsubnet)
>>>   @property
>>>   def network(self):
>>>       return self.__to_str(self.__tnetwork)
>>>   @property
>>>   def broadcast(self):
>>>       return self.__to_str(self.__tbroadcast)
>>>   @property
>>>   def mask(self):
>>>       return self.__to_str(self.__tmask)
>>>   @property
>>>   def wildcard(self):
>>>       return self.__to_str(self.__twildcard)
>>>   @property
>>>   def host_min(self):
>>>       return self.__to_str(self.__host_min)
>>>   @property
>>>   def host_max(self):
>>>       return self.__to_str(self.__host_max)
>>>   @property
>>>   def hosts_num(self):
>>>       return self.__wildcard - 1
>>>   @property
>>>   def net_class(self):
>>>       tst = (self.__tnetwork[0] & 0xf0) >> 4
>>>       if (tst & 0x8) == 0:
>>>           clx = 'A'
>>>       elif (tst & 0xc) == 0x8:
>>>           clx = 'B'
>>>       elif (tst & 0xe) == 0xc:
>>>           clx = 'C'
>>>       elif (tst & 0xf) == 0xe:
>>>           clx = 'D'
>>>       elif (tst & 0xf) == 0xf:
>>>           clx = 'E'
>>>       return clx
>>>   def __contains__(self, item):
>>>       ret = True
>>>       row_hdr = None
>>>       try:
>>>           row_hdr = int.from_bytes(tuple(map(lambda n: (int(n)), item.split('.'))), 'big')
>>>       except:
>>>           ret = False
>>>       if ret:
>>>           if not self.__network < row_hdr < self.__broadcast:
>>>               ret = False
>>>       return ret
>>> def main():
>>>   sn = calcip('10.0.0.0/26')
>>>   print(f"subnet: {sn.subnet}")
>>>   print(f"network: {sn.network}")
>>>   print(f"broadcast: {sn.broadcast}")
>>>   print(f"mask: {sn.mask}")
>>>   print(f"wildcard: {sn.wildcard}")
>>>   print(f"host_min: {sn.host_min}")
>>>   print(f"host_max: {sn.host_max}")
>>>   print(f"Avaible hosts: {sn.hosts_num}")
>>>   print(f"Class: {sn.net_class}")
>>>   tst_hdr = '10.0.0.31'
>>>   is_not = 'is '
>>>   if not tst_hdr in sn:
>>>       is_not = 'is NOT '
>>>   print("hdr %s %sin range %s - %s" %
>>>         (tst_hdr, is_not, sn.host_min, sn.host_max))
>>> if __name__ == '__main__':
>>>   main()
>> There is this https://docs.python.org/3/howto/ipaddress.html if you just want a solution.
>> Or are you after code review feedback?
>> Barry
>>> --
>>> https://mail.python.org/mailman/listinfo/python-list
> 
> 
> Thank you too. I had seen this library but I always try not to use
> libraries outside the standard ones. Now I don't remember why I was
> convinced that this wasn't part of it, perhaps because it was like that
> at the time or because I got confused. Only now I realized that it is
> not necessary to install it. Now I'm considering whether to use
> 'ipaddress' or 'socket'. What is certain is that this one you have
> suggested is really comfortable. Thanks again for the report.

Ipaddress was developed outside of the std lib and later added i recall.

Barry
> 
> -- 
> https://mail.python.org/mailman/listinfo/python-list


From grant.b.edwards at gmail.com  Thu Apr 13 11:25:51 2023
From: grant.b.edwards at gmail.com (Grant Edwards)
Date: Thu, 13 Apr 2023 08:25:51 -0700 (PDT)
Subject: Weak Type Ability for Python
References: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
 <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>
Message-ID: <64381eff.920a0220.9f55.07ce@mx.google.com>

On 2023-04-13, Cameron Simpson <cs at cskk.id.au> wrote:
> On 12Apr2023 22:12, avi.e.gross at gmail.com <avi.e.gross at gmail.com> wrote:
>
>>I suspect the OP is thinking of languages like PERL or JAVA which guess 
>>for you and make such conversions when it seems to make sense.
>
> JavaScript guesses. What a nightmare.

So does PHP. What's really impressive is that it never seems to guess
correctly. :)

From avi.e.gross at gmail.com  Thu Apr 13 12:05:53 2023
From: avi.e.gross at gmail.com (avi.e.gross at gmail.com)
Date: Thu, 13 Apr 2023 12:05:53 -0400
Subject: Weak Type Ability for Python
In-Reply-To: <CAPTjJmrHgbe46E3z2oe2dZX3B6CyO0K-Ueow3KhW=RbzfsGrfg@mail.gmail.com>
References: <e00cf529-1c77-a438-3efa-890d96f141b2@mrabarnett.plus.com>
 <ZDd6LmQOzUXNNUAa@cskk.homeip.net>
 <015501d96dca$3ef2c820$bcd85860$@gmail.com>
 <CAPTjJmrHgbe46E3z2oe2dZX3B6CyO0K-Ueow3KhW=RbzfsGrfg@mail.gmail.com>
Message-ID: <002201d96e21$d3995dc0$7acc1940$@gmail.com>

Chris, I was not suggesting it for Python as one of many possible
implementations.

I do see perfectly valid uses in other contexts. For example, if I have a
program that displays my text as pixels in some font and size, I may indeed
want the text clipped at 2 1/2 repetitions. But as always, when there are
choices to be made, you have to very clearly document the choice or offer
ways to do it another way. In a non-fixed-width font, 2.5 may mean knowing
how many pixels and adjusting so that a narrow letter "i" may be shown in
one font and not another, for example. 

If you want completeness, sure, you can define fractional parts of a string
in this context by the percentage of CHARACTERS in it. But as we have often
seen, in other encodings you need to differentiate between varying numbers
of bytes versus the underlying symbols they represent. Your  example from
the Pike language not only supports the multiplication of a string but
division and mod. Python currently does not allow those.

So why not extend it to allow complex numbers? 

>>> "Hello" * complex(5,0)
TypeError: can't multiply sequence by non-int of type 'complex'
>>> "Hello" * complex(0,5)
TypeError: can't multiply sequence by non-int of type 'complex'

The first one above is actually perfectly valid in the sense that the real
part is 5 and there is no imaginary component. With a bit of effort, I can
use the complexity to work:

>>> "Hello" * int(complex(5,0).real)
'HelloHelloHelloHelloHello'

Let me reiterate. There are languages that do all kinds of interesting
things and some of what Python has done is seen by others as interesting.
They regularly borrow from each other or use parts and innovate further. I
have no serious objection to making well-thought-out changes if they are
determined to be not only useful, but of higher priority than a long
shopping list of other requests. I am wary of overly bloating a language by
placing too many things in the core.

It strikes me as doable to create a module that encapsulates a feature like
this in a limited way. What may be needed is just a carefully constructed
class that starts off as similar to str and adds some methods. Any user
wanting to use the new feature would either start using the new class
directly or cast their str to it when they want it to be useable.

But the good news is that I am nowhere in the python hierarchy and have no
ability to make any changes. This is purely academic for me. And, if I want
such features and see tons of existing ways to get what I want or can roll
it for myself, ...


-----Original Message-----
From: Python-list <python-list-bounces+avi.e.gross=gmail.com at python.org> On
Behalf Of Chris Angelico
Sent: Thursday, April 13, 2023 3:02 AM
To: python-list at python.org
Subject: Re: Weak Type Ability for Python

On Thu, 13 Apr 2023 at 15:40, <avi.e.gross at gmail.com> wrote:
> And, no, I do not suggest 2.5 be interpreted as putting in an
> approximate percentage so that .8 * "Hello" should result in "Hell" ...

$ pike
Pike v8.1 release 15 running Hilfe v3.5 (Incremental Pike Frontend)
Ok.
> "Hello, world! " * 2.5;
(1) Result: "Hello, world! Hello, world! Hello, "
> "Hello, world! Hello, world! Hello, " / 10;
(2) Result: ({ /* 3 elements */
                "Hello, wor",
                "ld! Hello,",
                " world! He"
            })
> "Hello, world! Hello, world! Hello, " % 10;
(3) Result: "llo, "
> "Hello, world! Hello, world! Hello, " / 10.0;
(4) Result: ({ /* 4 elements */
                "Hello, wor",
                "ld! Hello,",
                " world! He",
                "llo, "
            })
>

Multiplying and dividing strings by floats makes perfect sense. (The
({ }) notation is Pike's array literal syntax; consider it equivalent
to Python's square brackets for a list.)

ChrisA
-- 
https://mail.python.org/mailman/listinfo/python-list


From rosuav at gmail.com  Thu Apr 13 12:11:45 2023
From: rosuav at gmail.com (Chris Angelico)
Date: Fri, 14 Apr 2023 02:11:45 +1000
Subject: Weak Type Ability for Python
In-Reply-To: <002201d96e21$d3995dc0$7acc1940$@gmail.com>
References: <e00cf529-1c77-a438-3efa-890d96f141b2@mrabarnett.plus.com>
 <ZDd6LmQOzUXNNUAa@cskk.homeip.net> <015501d96dca$3ef2c820$bcd85860$@gmail.com>
 <CAPTjJmrHgbe46E3z2oe2dZX3B6CyO0K-Ueow3KhW=RbzfsGrfg@mail.gmail.com>
 <002201d96e21$d3995dc0$7acc1940$@gmail.com>
Message-ID: <CAPTjJmqRzyPycsbuh8sYSPK0wvT6+kY5-cBqxWZ0FsRRoFpSUg@mail.gmail.com>

On Fri, 14 Apr 2023 at 02:05, <avi.e.gross at gmail.com> wrote:
> So why not extend it to allow complex numbers?
>
> >>> "Hello" * complex(5,0)
> TypeError: can't multiply sequence by non-int of type 'complex'
> >>> "Hello" * complex(0,5)
> TypeError: can't multiply sequence by non-int of type 'complex'
>

Clearly a missed opportunity to rotate the text through a specified angle.

ChrisA

From avi.e.gross at gmail.com  Thu Apr 13 12:55:13 2023
From: avi.e.gross at gmail.com (avi.e.gross at gmail.com)
Date: Thu, 13 Apr 2023 12:55:13 -0400
Subject: Weak Type Ability for Python
In-Reply-To: <CAPTjJmqRzyPycsbuh8sYSPK0wvT6+kY5-cBqxWZ0FsRRoFpSUg@mail.gmail.com>
References: <e00cf529-1c77-a438-3efa-890d96f141b2@mrabarnett.plus.com>
 <ZDd6LmQOzUXNNUAa@cskk.homeip.net>
 <015501d96dca$3ef2c820$bcd85860$@gmail.com>
 <CAPTjJmrHgbe46E3z2oe2dZX3B6CyO0K-Ueow3KhW=RbzfsGrfg@mail.gmail.com>
 <002201d96e21$d3995dc0$7acc1940$@gmail.com>
 <CAPTjJmqRzyPycsbuh8sYSPK0wvT6+kY5-cBqxWZ0FsRRoFpSUg@mail.gmail.com>
Message-ID: <002f01d96e28$b74d1650$25e742f0$@gmail.com>

[THIS CLAIMER: a bit off a bit off a bit off topic, imagine that]

Chris,

You have a gift of taking things I think about but censor myself from
including in my post and then blurting it out! LOL!

The original question in this thread now seems a dim memory but we are now
discussing not how to add a number to a string but how to multiply a string
to make n combined copies and then what it means to have a fractional copy
and finally a way to specify a rotation to the result. Argh!!!!

But since you brought it up as a way of looking at what multiplying by an
imaginary number might mean, as in rotating text, I am now going to throw in
a May Tricks even if it is only April.

So should I now extend a language so a rotation matrix is allowed to
multiply text or even a nested list like:

[ [ cos(theta), -sin(theta) ],
  [ sin(theta), cos(theta) ]

While we are at it, why stop with imaginary numbers when you can imagine
extensions thereof? Unfortunately, it has been proven there are and can only
be two additional such constructs. Quaternions have three distinct imaginary
axes called i,j,k and some see them as interesting to show multidimensional
objects in all kinds of places such as computer vision or orbital mechanics.
Octonions have seven such other imaginary axes and have uses in esoteric
places like String Theory or Quantum Logic.

And, yes, you can use these critters in python. You can add a quaternion
type to numpy for example. Yep, octonions too. See modules like pyoctonion
and pyquaternion and much more.

The immoral moral of this story is that once you start opening some doors,
you may find people clamoring to let in ever more things and features. You
can easily bog down your code to the point where finding the commonly used
parts becomes a chore as you trudge through lots of code that is rarely used
but there for completeness.

Oh, I want to make something clear before I get another message spelling out
what I was thinking but chose to omit.

I slightly misled you above. Yes, it has been proven no number higher than 8
(meaning one real dimension and seven distinct imaginary ones) can exist so
octonions are the final part of that story. Well, not exactly. You lose
commutativity when going from quaternions to octonions and you lose full
associativity if you go higher. But you can make all kinds of mathematical
constructs like sedenions with 16 dimensions.

I cannot imagine ever trying to multiply a string by these critters but who
knows? As I noted above, if you set some parts of each of the above to zero,
they all can look like something with a real part like 3, and no (meaning
zero point zero) imaginary parts. So you could argue you should support all
kinds of things that MAY on examination turn out to be convertible to an
integer or double.

-----Original Message-----
From: Python-list <python-list-bounces+avi.e.gross=gmail.com at python.org> On
Behalf Of Chris Angelico
Sent: Thursday, April 13, 2023 12:12 PM
To: python-list at python.org
Subject: Re: Weak Type Ability for Python

On Fri, 14 Apr 2023 at 02:05, <avi.e.gross at gmail.com> wrote:
> So why not extend it to allow complex numbers?
>
> >>> "Hello" * complex(5,0)
> TypeError: can't multiply sequence by non-int of type 'complex'
> >>> "Hello" * complex(0,5)
> TypeError: can't multiply sequence by non-int of type 'complex'
>

Clearly a missed opportunity to rotate the text through a specified angle.

ChrisA
-- 
https://mail.python.org/mailman/listinfo/python-list


From mkarkera98 at gmail.com  Thu Apr 13 13:10:06 2023
From: mkarkera98 at gmail.com (Meghna Karkera)
Date: Thu, 13 Apr 2023 22:40:06 +0530
Subject: Hide my query about covariance matrix syntax from google
Message-ID: <CA+Vnj_qsVo03H=L46b8K2fqc8vG1x3irTrv8utJ1FSorBv7dVw@mail.gmail.com>

Respected Sir

I kindly request you to hide my query about covariance matrix syntax from
google which was emailed to you a few years back as it appears on google
page.

Hoping that you do the needful.

Dr. Meghna Raviraj Karkera

From wlfraed at ix.netcom.com  Wed Apr 12 22:47:17 2023
From: wlfraed at ix.netcom.com (Dennis Lee Bieber)
Date: Wed, 12 Apr 2023 22:47:17 -0400
Subject: Weak Type Ability for Python
References: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
 <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>
 <mailman.58.1681352533.20750.python-list@python.org>
Message-ID: <0sqe3id664268aqif7sttg1r0c1vikof9k@4ax.com>

On Thu, 13 Apr 2023 12:21:58 +1000, Cameron Simpson <cs at cskk.id.au>
declaimed the following:

>On 12Apr2023 22:12, avi.e.gross at gmail.com <avi.e.gross at gmail.com> wrote:
>>I suspect the OP is thinking of languages like PERL or JAVA which guess 
>>for
>>you and make such conversions when it seems to make sense.
>
>JavaScript guesses. What a nightmare. Java acts like Python and will 
>forbid it on type grounds (at compile time with Java, being staticly 
>typed).
>

	REXX -- where everything is considered a string until it needs to be
something else.

REXX-ooRexx_5.0.0(MT)_64-bit 6.05 23 Dec 2022
  rexxtry.rex lets you interactively try REXX statements.
    Each string is executed when you hit Enter.
    Enter 'call tell' for a description of the features.
  Go on - try a few...            Enter 'exit' to end.
x = 1;
  ........................................... rexxtry.rex on WindowsNT
y = "a";
  ........................................... rexxtry.rex on WindowsNT
say x||y;
1a
  ........................................... rexxtry.rex on WindowsNT

From wlfraed at ix.netcom.com  Wed Apr 12 22:52:29 2023
From: wlfraed at ix.netcom.com (Dennis Lee Bieber)
Date: Wed, 12 Apr 2023 22:52:29 -0400
Subject: for a 'good python'
References: <B7160289-C80D-455D-A46D-E633C1F41408@barrys-emacs.org>
 <mailman.52.1681335436.20750.python-list@python.org>
 <u17au5$2lss$1@dont-email.me>
Message-ID: <dere3i9aksjfqedekbi6fblokdu1tttctb@4ax.com>

On Thu, 13 Apr 2023 00:21:58 +0200, jak <nospam at please.ty> declaimed the
following:


>Thank you too. I had seen this library but I always try not to use
>libraries outside the standard ones. Now I don't remember why I was
>convinced that this wasn't part of it, perhaps because it was like that
>at the time or because I got confused. Only now I realized that it is
>not necessary to install it. Now I'm considering whether to use
>'ipaddress' or 'socket'. What is certain is that this one you have
>suggested is really comfortable. Thanks again for the report.

	It is useful to skim the contents of the standard library documentation
every couple of releases. ipaddress came in with Python 3.3

https://docs.python.org/3.10/library/index.html (I dropped down to 3.10
just as that is the version I have installed; some 3rd party modules
weren't ready when I tried to install on 3.11)

From nospam at please.ty  Thu Apr 13 02:42:39 2023
From: nospam at please.ty (jak)
Date: Thu, 13 Apr 2023 08:42:39 +0200
Subject: for a 'good python'
In-Reply-To: <dere3i9aksjfqedekbi6fblokdu1tttctb@4ax.com>
References: <B7160289-C80D-455D-A46D-E633C1F41408@barrys-emacs.org>
 <mailman.52.1681335436.20750.python-list@python.org>
 <u17au5$2lss$1@dont-email.me> <dere3i9aksjfqedekbi6fblokdu1tttctb@4ax.com>
Message-ID: <u18890$a6d2$1@dont-email.me>

Dennis Lee Bieber ha scritto:
> On Thu, 13 Apr 2023 00:21:58 +0200, jak <nospam at please.ty> declaimed the
> following:
> 
> 
>> Thank you too. I had seen this library but I always try not to use
>> libraries outside the standard ones. Now I don't remember why I was
>> convinced that this wasn't part of it, perhaps because it was like that
>> at the time or because I got confused. Only now I realized that it is
>> not necessary to install it. Now I'm considering whether to use
>> 'ipaddress' or 'socket'. What is certain is that this one you have
>> suggested is really comfortable. Thanks again for the report.
> 
> 	It is useful to skim the contents of the standard library documentation
> every couple of releases. ipaddress came in with Python 3.3
> 
> https://docs.python.org/3.10/library/index.html (I dropped down to 3.10
> just as that is the version I have installed; some 3rd party modules
> weren't ready when I tried to install on 3.11)
> 

Then it was my fault. The version was 3.8.6

From aapost at idontexist.club  Thu Apr 13 12:27:44 2023
From: aapost at idontexist.club (aapost)
Date: Thu, 13 Apr 2023 12:27:44 -0400
Subject: Weak Type Ability for Python
In-Reply-To: <mailman.44.1681319032.20750.python-list@python.org>
References: <CAMpB_8R6EMj4nevu2ucjvTR5X=CL2ktYxAoVnxOZG=46koaR=Q@mail.gmail.com>
 <mailman.44.1681319032.20750.python-list@python.org>
Message-ID: <u19ai0$15o2$1@nnrp.usenet.blueworldhosting.com>

On 4/12/23 04:03, Ali Mohseni Roodbari wrote:
 >
On 4/13/23 07:50, Stefan Ram wrote:
 >    If tomorrow Python would allow "string+int" and "int+string"
 >    in the sense of "string+str(int)" and "str(int)+string",
 >    what harm would be there?
 >
 >    But for now, I think a typical approach would be to just use "str",
 >    i.e., "string+str(int)" and "str(int)+string".


I agree with Py Zen rule 2 in this case:
Explicit is better than implicit.

I hate when things try to guess what I am doing... It is why I can't use 
lxml.

From 2QdxY4RzWzUUiLuE at potatochowder.com  Thu Apr 13 13:47:17 2023
From: 2QdxY4RzWzUUiLuE at potatochowder.com (2QdxY4RzWzUUiLuE at potatochowder.com)
Date: Thu, 13 Apr 2023 13:47:17 -0400
Subject: Weak Type Ability for Python
In-Reply-To: <0sqe3id664268aqif7sttg1r0c1vikof9k@4ax.com>
References: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
 <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>
 <mailman.58.1681352533.20750.python-list@python.org>
 <0sqe3id664268aqif7sttg1r0c1vikof9k@4ax.com>
Message-ID: <ZDhAJXsamhi2p4O5@anomaly>

On 2023-04-12 at 22:47:17 -0400,
Dennis Lee Bieber <wlfraed at ix.netcom.com> wrote:

> 	REXX -- where everything is considered a string until it needs to be
> something else.

I see your REXX, and raise you an awk,? except that awk won't add a
string to a number, or a number to string, but it will concatenate in
both cases:

    $ echo 1 a | awk '{print $1 $2}{print $1 + $2}'
    1a
    1

    $ echo 1 a | awk '{print $2 $1}{print $2 + $1}'
    a1
    1

    $ echo 1 2 | awk '{print $1 $2}{print $2 + $1}'
    12
    3

? GNU Awk 5.2.1, API 3.2, PMA Avon 8-g1, (GNU MPFR 4.2.0, GNU MP 6.2.1)

Dan

From aapost at idontexist.club  Thu Apr 13 13:54:25 2023
From: aapost at idontexist.club (aapost)
Date: Thu, 13 Apr 2023 13:54:25 -0400
Subject: Embedded python is not 100% stable
In-Reply-To: <mailman.65.1681371654.20750.python-list@python.org>
References: <CAASeUHo-Gq12rgjZKh_dbj1EmY7R-jApL+P0OP0imJ3tMLgTpw@mail.gmail.com>
 <mailman.65.1681371654.20750.python-list@python.org>
Message-ID: <u19fkh$m0p$1@nnrp.usenet.blueworldhosting.com>

On 4/13/23 03:40, Guenther Sohler wrote:
> 

Attachments are stripped, so they weren't included.

Glancing at the branch and the 2 lines you mentioned.

You have a comment with a link for python 2.3 documentation.
Yet you have python 3.10 code included elsewhere (and openscad itself 
requires the modern spec C++17, so I assume your aim is at current versions)

https://docs.python.org/3.10/extending/newtypes.html
is the equivalent doc for that.

I am not experienced in defining PyType objects in C, but notice 
syntactical discrepancies, missing "static" on dealloc, use of 
typecasted malloc rather than PyType_GenericAlloc()
https://docs.python.org/3.10/c-api/typeobj.html#c.PyTypeObject.tp_alloc

Without digging in deeper and learning more I can't say for certain 
whether or not those are issues, but intuitively I assume they would be 
and that the implementation needs to more closely mirror the syntactical 
flow implementations of modern working examples..


From avi.e.gross at gmail.com  Thu Apr 13 14:36:47 2023
From: avi.e.gross at gmail.com (avi.e.gross at gmail.com)
Date: Thu, 13 Apr 2023 14:36:47 -0400
Subject: Weak Type Ability for Python
In-Reply-To: <u19ai0$15o2$1@nnrp.usenet.blueworldhosting.com>
References: <CAMpB_8R6EMj4nevu2ucjvTR5X=CL2ktYxAoVnxOZG=46koaR=Q@mail.gmail.com>
 <mailman.44.1681319032.20750.python-list@python.org>
 <u19ai0$15o2$1@nnrp.usenet.blueworldhosting.com>
Message-ID: <006401d96e36$e8003f80$b800be80$@gmail.com>

This reminds me a bit of complaints that the parser does not do what you
want when you do not supply parentheses in an expression like:

5 * 4 + 3

In many and maybe most languages it is seen as (5*4)+3 UNLESS you tell it
you want 5*(4+3). There are precedence and associativity rules.

Of course the computer might guess you meant the latter or could refuse to
do it and offer you a choice before calculating it. Or the language may
insist on parentheses always so you would need to also say ((5*4)+3) with no
default behavior.

The golden rule remains. If there is more than one way something can be
done, then either the programmer must make the choice explicit OR the
documentation must very clearly warn which path was chosen and perhaps point
to ways to do other choices. 

Some people take more complex (but not Complex) arithmetic than the above
and break it up into quite a few simple parts like:

temp1 = 4 + 3
result = 5 + temp1

Of course, the latter can be hard to read and understand for some people,
and some (others?) find fully parenthesized versions hard. But having
precedence rules and also allowing the other methods, should work fine for a
good segment of people except perhaps the ones who like Reverse Polish
Notation and insist on 5 4 3 + * instead.


-----Original Message-----
From: Python-list <python-list-bounces+avi.e.gross=gmail.com at python.org> On
Behalf Of aapost
Sent: Thursday, April 13, 2023 12:28 PM
To: python-list at python.org
Subject: Re: Weak Type Ability for Python

On 4/12/23 04:03, Ali Mohseni Roodbari wrote:
 >
On 4/13/23 07:50, Stefan Ram wrote:
 >    If tomorrow Python would allow "string+int" and "int+string"
 >    in the sense of "string+str(int)" and "str(int)+string",
 >    what harm would be there?
 >
 >    But for now, I think a typical approach would be to just use "str",
 >    i.e., "string+str(int)" and "str(int)+string".


I agree with Py Zen rule 2 in this case:
Explicit is better than implicit.

I hate when things try to guess what I am doing... It is why I can't use 
lxml.
-- 
https://mail.python.org/mailman/listinfo/python-list


From martin.schoon at gmail.com  Thu Apr 13 14:41:19 2023
From: martin.schoon at gmail.com (Martin =?UTF-8?Q?Sch=C3=B6=C3=B6n?=)
Date: 13 Apr 2023 18:41:19 GMT
Subject: Problem with Matplotlib example
Message-ID: <k9r0mfFtcr1U1@mid.individual.net>

Anyone had success running this example?
https://tinyurl.com/yhhyc9r

When I try I get this error:
"TypeError: __init__() got an unexpected keyword argument 'transform'"

This is for the line
"    m = MarkerStyle(SUCESS_SYMBOLS[mood], transform=t)"

Yes, I know, I could dive into the documentation myself but I hope
some kind soul here will help out.

As far as I know I have an up-to-date matplotlib installed. Pip has
nothing more modern to offer me.

TIA

/Martin

From list1 at tompassin.net  Thu Apr 13 15:04:02 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Thu, 13 Apr 2023 15:04:02 -0400
Subject: Weak Type Ability for Python
In-Reply-To: <006401d96e36$e8003f80$b800be80$@gmail.com>
References: <CAMpB_8R6EMj4nevu2ucjvTR5X=CL2ktYxAoVnxOZG=46koaR=Q@mail.gmail.com>
 <mailman.44.1681319032.20750.python-list@python.org>
 <u19ai0$15o2$1@nnrp.usenet.blueworldhosting.com>
 <006401d96e36$e8003f80$b800be80$@gmail.com>
Message-ID: <ed64a52a-64ce-4d7c-1a47-07730ea4822d@tompassin.net>

On 4/13/2023 2:36 PM, avi.e.gross at gmail.com wrote:
> But having
> precedence rules and also allowing the other methods, should work fine for a
> good segment of people except perhaps the ones who like Reverse Polish
> Notation and insist on 5 4 3 + * instead.

For *reading*, I prefer the usual 5 * (4 + 3) form.  But for using a 
calculator, I much prefer RPN.


From rosuav at gmail.com  Thu Apr 13 15:28:06 2023
From: rosuav at gmail.com (Chris Angelico)
Date: Fri, 14 Apr 2023 05:28:06 +1000
Subject: Hide my query about covariance matrix syntax from google
In-Reply-To: <CA+Vnj_qsVo03H=L46b8K2fqc8vG1x3irTrv8utJ1FSorBv7dVw@mail.gmail.com>
References: <CA+Vnj_qsVo03H=L46b8K2fqc8vG1x3irTrv8utJ1FSorBv7dVw@mail.gmail.com>
Message-ID: <CAPTjJmrpi9P2wamk=bzTSBQOtdMhxt_WVy+xA0uvTrMHzfL21w@mail.gmail.com>

On Fri, 14 Apr 2023 at 03:11, Meghna Karkera <mkarkera98 at gmail.com> wrote:
>
> Respected Sir
>
> I kindly request you to hide my query about covariance matrix syntax from
> google which was emailed to you a few years back as it appears on google
> page.
>
> Hoping that you do the needful.

These posts are public. While it's possible to ask for something to be
removed from the official python-list archive, that won't remove it
from Google Groups or any other third-party archive.

Also, there's nothing we can do here to remove your post; you'll have
to contact the list admins.

And just in case it's of interest to you:
https://en.wikipedia.org/wiki/Streisand_effect

ChrisA

From rosuav at gmail.com  Thu Apr 13 15:30:55 2023
From: rosuav at gmail.com (Chris Angelico)
Date: Fri, 14 Apr 2023 05:30:55 +1000
Subject: Weak Type Ability for Python
In-Reply-To: <002f01d96e28$b74d1650$25e742f0$@gmail.com>
References: <e00cf529-1c77-a438-3efa-890d96f141b2@mrabarnett.plus.com>
 <ZDd6LmQOzUXNNUAa@cskk.homeip.net> <015501d96dca$3ef2c820$bcd85860$@gmail.com>
 <CAPTjJmrHgbe46E3z2oe2dZX3B6CyO0K-Ueow3KhW=RbzfsGrfg@mail.gmail.com>
 <002201d96e21$d3995dc0$7acc1940$@gmail.com>
 <CAPTjJmqRzyPycsbuh8sYSPK0wvT6+kY5-cBqxWZ0FsRRoFpSUg@mail.gmail.com>
 <002f01d96e28$b74d1650$25e742f0$@gmail.com>
Message-ID: <CAPTjJmouqCPjCkKZw+JRuRqB3BxhSf77DPtjzHd1_Ovb_+Zv5g@mail.gmail.com>

On Fri, 14 Apr 2023 at 02:55, <avi.e.gross at gmail.com> wrote:
> And, yes, you can use these critters in python. You can add a quaternion
> type to numpy for example. Yep, octonions too.

Hang on hang on hang on. I can multiply a string by an onion? The
possibilities of script-controlled culinary arts just became that much
more awesome...

ChrisA

From list1 at tompassin.net  Thu Apr 13 15:32:38 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Thu, 13 Apr 2023 15:32:38 -0400
Subject: Problem with Matplotlib example
In-Reply-To: <k9r0mfFtcr1U1@mid.individual.net>
References: <k9r0mfFtcr1U1@mid.individual.net>
Message-ID: <8dd48769-7584-9220-7cc2-8e97dcd7df61@tompassin.net>

On 4/13/2023 2:41 PM, Martin Sch??n wrote:
> Anyone had success running this example?
> https://tinyurl.com/yhhyc9r
> 
> When I try I get this error:
> "TypeError: __init__() got an unexpected keyword argument 'transform'"
> 
> This is for the line
> "    m = MarkerStyle(SUCESS_SYMBOLS[mood], transform=t)"
> 
> Yes, I know, I could dive into the documentation myself but I hope
> some kind soul here will help out.
> 
> As far as I know I have an up-to-date matplotlib installed. Pip has
> nothing more modern to offer me.

It works for me, copy-pasted as is.

Python 3.11.3

C:\Users\tom>py -m pip show matplotlib
Name: matplotlib
Version: 3.6.3

C:\Users\tom>py -m pip show numpy
Name: numpy
Version: 1.24.2


From rosuav at gmail.com  Thu Apr 13 15:35:22 2023
From: rosuav at gmail.com (Chris Angelico)
Date: Fri, 14 Apr 2023 05:35:22 +1000
Subject: Weak Type Ability for Python
In-Reply-To: <0sqe3id664268aqif7sttg1r0c1vikof9k@4ax.com>
References: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
 <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>
 <mailman.58.1681352533.20750.python-list@python.org>
 <0sqe3id664268aqif7sttg1r0c1vikof9k@4ax.com>
Message-ID: <CAPTjJmpgrYL=jHWNWUBergoVQ7duvwXP6rua-xtOp_DnE5TEZg@mail.gmail.com>

On Fri, 14 Apr 2023 at 03:29, Dennis Lee Bieber <wlfraed at ix.netcom.com> wrote:
>
> On Thu, 13 Apr 2023 12:21:58 +1000, Cameron Simpson <cs at cskk.id.au>
> declaimed the following:
>
> >On 12Apr2023 22:12, avi.e.gross at gmail.com <avi.e.gross at gmail.com> wrote:
> >>I suspect the OP is thinking of languages like PERL or JAVA which guess
> >>for
> >>you and make such conversions when it seems to make sense.
> >
> >JavaScript guesses. What a nightmare. Java acts like Python and will
> >forbid it on type grounds (at compile time with Java, being staticly
> >typed).
> >
>
>         REXX -- where everything is considered a string until it needs to be
> something else.
>
> REXX-ooRexx_5.0.0(MT)_64-bit 6.05 23 Dec 2022
>   rexxtry.rex lets you interactively try REXX statements.
>     Each string is executed when you hit Enter.
>     Enter 'call tell' for a description of the features.
>   Go on - try a few...            Enter 'exit' to end.
> x = 1;
>   ........................................... rexxtry.rex on WindowsNT
> y = "a";
>   ........................................... rexxtry.rex on WindowsNT
> say x||y;
> 1a
>   ........................................... rexxtry.rex on WindowsNT

REXX - where everything is a string, arithmetic can be done on
strings, and data structures are done in the variable name instead of
the value.

I've seen quite a few strings-only languages, but I can't think of any
other language than REXX where you create arrays and dictionaries by
using computed variable names.

It was quite the experience back in the day (as OS/2's native
scripting language), and one that I'm truly glad to have had, as it
taught me so much about the differences between languages.

(It also taught me to treasure good documentation and value it as
truly precious, because SysSetObjectData was an incredibly powerful
function whose docs just referred to WinSetObjectData, and the window
manager's docs weren't part of what I had available.)

ChrisA

From python at mrabarnett.plus.com  Thu Apr 13 15:34:23 2023
From: python at mrabarnett.plus.com (MRAB)
Date: Thu, 13 Apr 2023 20:34:23 +0100
Subject: Problem with Matplotlib example
In-Reply-To: <k9r0mfFtcr1U1@mid.individual.net>
References: <k9r0mfFtcr1U1@mid.individual.net>
Message-ID: <4cef1b3b-30fd-378e-5fe7-7944bf5aec61@mrabarnett.plus.com>

On 2023-04-13 19:41, Martin Sch??n wrote:
> Anyone had success running this example?
> https://tinyurl.com/yhhyc9r
> 
> When I try I get this error:
> "TypeError: __init__() got an unexpected keyword argument 'transform'"
> 
> This is for the line
> "    m = MarkerStyle(SUCESS_SYMBOLS[mood], transform=t)"
> 
> Yes, I know, I could dive into the documentation myself but I hope
> some kind soul here will help out.
> 
> As far as I know I have an up-to-date matplotlib installed. Pip has
> nothing more modern to offer me.
> 
All I can say is that it works for me!

Python 3.10 and 3.11, matplotlib 3.6.1 and then 3.7.1 after updating it.


From gheskett at shentel.net  Thu Apr 13 19:15:17 2023
From: gheskett at shentel.net (gene heskett)
Date: Thu, 13 Apr 2023 19:15:17 -0400
Subject: Weak Type Ability for Python
In-Reply-To: <0sqe3id664268aqif7sttg1r0c1vikof9k@4ax.com>
References: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
 <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>
 <mailman.58.1681352533.20750.python-list@python.org>
 <0sqe3id664268aqif7sttg1r0c1vikof9k@4ax.com>
Message-ID: <3c90812e-7dbc-89b6-6bc7-6ec4810bfbd9@shentel.net>

On 4/13/23 13:34, Dennis Lee Bieber wrote:
> On Thu, 13 Apr 2023 12:21:58 +1000, Cameron Simpson <cs at cskk.id.au>
> declaimed the following:
> 
>> On 12Apr2023 22:12, avi.e.gross at gmail.com <avi.e.gross at gmail.com> wrote:
>>> I suspect the OP is thinking of languages like PERL or JAVA which guess
>>> for
>>> you and make such conversions when it seems to make sense.
>>
>> JavaScript guesses. What a nightmare. Java acts like Python and will
>> forbid it on type grounds (at compile time with Java, being staticly
>> typed).
>>
> 
> 	REXX -- where everything is considered a string until it needs to be
> something else.
> 
> REXX-ooRexx_5.0.0(MT)_64-bit 6.05 23 Dec 2022
>    rexxtry.rex lets you interactively try REXX statements.
>      Each string is executed when you hit Enter.
>      Enter 'call tell' for a description of the features.
>    Go on - try a few...            Enter 'exit' to end.

You missed the best REXX, Dennis.

ARexx for the amiga's. Bill Hawes wrote in a link to everything amigados 
had and we wrote, in ARexx, stuff that Amigados didn't have starting 
with a cron, a better cron than Paul Vixies. Worst, Bill never got a 
dime from commode-door for the best language it had,  We served our WDTV 
web page with it in the middle 90's. Using ARexx and early php. Now its 
farmed out and 99% commercial junk.

> x = 1;
>    ........................................... rexxtry.rex on WindowsNT
> y = "a";
>    ........................................... rexxtry.rex on WindowsNT
> say x||y;
> 1a
>    ........................................... rexxtry.rex on WindowsNT

Cheers, Gene Heskett.
-- 
"There are four boxes to be used in defense of liberty:
  soap, ballot, jury, and ammo. Please use in that order."
-Ed Howdershelt (Author, 1940)
If we desire respect for the law, we must first make the law respectable.
  - Louis D. Brandeis
Genes Web page <http://geneslinuxbox.net:6309/>


From avi.e.gross at gmail.com  Thu Apr 13 19:25:45 2023
From: avi.e.gross at gmail.com (avi.e.gross at gmail.com)
Date: Thu, 13 Apr 2023 19:25:45 -0400
Subject: Weak Type Ability for Python
In-Reply-To: <CAPTjJmpgrYL=jHWNWUBergoVQ7duvwXP6rua-xtOp_DnE5TEZg@mail.gmail.com>
References: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
 <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>
 <mailman.58.1681352533.20750.python-list@python.org>
 <0sqe3id664268aqif7sttg1r0c1vikof9k@4ax.com>
 <CAPTjJmpgrYL=jHWNWUBergoVQ7duvwXP6rua-xtOp_DnE5TEZg@mail.gmail.com>
Message-ID: <00b801d96e5f$46008d10$d201a730$@gmail.com>

Can I bring a part of this discussion a bit closer to Python?

I stipulate that quite a few languages, including fairly early ones, treated
text often as numbers. Ultimately, much of programming is about taking in
text and often segregating parts into various buckets either explicitly or
by checking if it has a decimal point or looks like scientific notation or
in how it seems to be used.

Is there any concept in Python of storing information in some way, such as
text, and implementing various ideas or interfaces so that you can query if
the contents are willing and able to be viewed in one of many other ways?

As an example, an object may store a fairly large number as a text string in
decimal format. The number is big enough that it cannot be fully represented
in an 8 bit storage as in a byte or in a signed or unsigned 16-bit integer
but can be stored in something larger. It may be possible to store it in a
double precision floating point but not smaller. Yes, I know Python by
default uses indefinite length integers, but you get the idea.

Or it may be storing text in some format but the object is willing to
transform the text into one of several other formats when needed. The text
may also have attributes such as whether it is in English or Hungarian or is
mixed-language.

So for some applications, perhaps leaving the object as a string all the
time may be reasonable. If some operation wishes to use the contents, the
interface can be queried to see what other formats it can be coerced into
and perhaps a specified set of methods need to be included that perform your
transition for you such as object.return_as_int64() 

This can have wider implications. Imagine an object holding text in French
that has been tested by humans using a program like Google Translate and
deemed reasonable for translating into a specific dozen languages such as
Esperanto  and not certified into others like Klingon or High Valyrian or
ASL. The object could contain interfaces for the languages it supports but
does not store the translations, especially when the content is dynamic,
such as a form letter that has been instantiated with a name and address and
perhaps a part detailing what is being billed or shipped. Instead, the
object can present an interface that lets a user determine if it supports
dynamic translation to one or more target, such as the Quebec version of
French or a British versus American version of English.

I am being quite general here and lots of programs out there already
probably have their own way of providing such facilities on a case-by-case
basis. But do some languages have some support within the language itself?

I do note some languages allow objects to oddly belong to multiple classes
at once and have used that feature as a way to check if an object has some
capabilities. Some languages have concepts like a mix-in and Python does
allow thing like multiple inheritance albeit it often is best not to use it
much. It does have ideas about how to test if a class implements some things
by seeing if various dunder methods are in place.

My reason for asking, is based on the discussion. If I want to use plus with
an integer and a string, it may be reasonable for the interpreter to ask one
or the other operand if they are able to be seen another way. If an integer
indicates it can be seen as text, great. If a string indicates it believes
it can deliver a number, great.

Unfortunately, if they BOTH are flexible, how do you decide whether to add
them as numbers or concatenate them as strings?

Sigh!


-----Original Message-----
From: Python-list <python-list-bounces+avi.e.gross=gmail.com at python.org> On
Behalf Of Chris Angelico
Sent: Thursday, April 13, 2023 3:35 PM
To: python-list at python.org
Subject: Re: Weak Type Ability for Python

On Fri, 14 Apr 2023 at 03:29, Dennis Lee Bieber <wlfraed at ix.netcom.com>
wrote:
>
> On Thu, 13 Apr 2023 12:21:58 +1000, Cameron Simpson <cs at cskk.id.au>
> declaimed the following:
>
> >On 12Apr2023 22:12, avi.e.gross at gmail.com <avi.e.gross at gmail.com> wrote:
> >>I suspect the OP is thinking of languages like PERL or JAVA which guess
> >>for
> >>you and make such conversions when it seems to make sense.
> >
> >JavaScript guesses. What a nightmare. Java acts like Python and will
> >forbid it on type grounds (at compile time with Java, being staticly
> >typed).
> >
>
>         REXX -- where everything is considered a string until it needs to
be
> something else.
>
> REXX-ooRexx_5.0.0(MT)_64-bit 6.05 23 Dec 2022
>   rexxtry.rex lets you interactively try REXX statements.
>     Each string is executed when you hit Enter.
>     Enter 'call tell' for a description of the features.
>   Go on - try a few...            Enter 'exit' to end.
> x = 1;
>   ........................................... rexxtry.rex on WindowsNT
> y = "a";
>   ........................................... rexxtry.rex on WindowsNT
> say x||y;
> 1a
>   ........................................... rexxtry.rex on WindowsNT

REXX - where everything is a string, arithmetic can be done on
strings, and data structures are done in the variable name instead of
the value.

I've seen quite a few strings-only languages, but I can't think of any
other language than REXX where you create arrays and dictionaries by
using computed variable names.

It was quite the experience back in the day (as OS/2's native
scripting language), and one that I'm truly glad to have had, as it
taught me so much about the differences between languages.

(It also taught me to treasure good documentation and value it as
truly precious, because SysSetObjectData was an incredibly powerful
function whose docs just referred to WinSetObjectData, and the window
manager's docs weren't part of what I had available.)

ChrisA
-- 
https://mail.python.org/mailman/listinfo/python-list


From learn2program at gmail.com  Thu Apr 13 19:49:45 2023
From: learn2program at gmail.com (Alan Gauld)
Date: Fri, 14 Apr 2023 00:49:45 +0100
Subject: Weak Type Ability for Python
In-Reply-To: <CAPTjJmpgrYL=jHWNWUBergoVQ7duvwXP6rua-xtOp_DnE5TEZg@mail.gmail.com>
References: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
 <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>
 <mailman.58.1681352533.20750.python-list@python.org>
 <0sqe3id664268aqif7sttg1r0c1vikof9k@4ax.com>
 <CAPTjJmpgrYL=jHWNWUBergoVQ7duvwXP6rua-xtOp_DnE5TEZg@mail.gmail.com>
Message-ID: <899fcb5e-016b-1717-de5c-a68ad435cf37@yahoo.co.uk>

On 13/04/2023 20:35, Chris Angelico wrote:

> REXX - where everything is a string,

> It was quite the experience back in the day (as OS/2's native
> scripting language), 

I briefly met REXX on a mainframe, but I did play with OS/2 for
a year or two. Back when it looked like it might be a rival to M$

OS/2 running NeXTstep now that would have been a platform
for the 90s...  both so near yet so far.

-- 
Alan G
Author of the Learn to Program web site
http://www.alan-g.me.uk/
http://www.amazon.com/author/alan_gauld
Follow my photo-blog on Flickr at:
http://www.flickr.com/photos/alangauldphotos



From learn2program at gmail.com  Thu Apr 13 20:13:56 2023
From: learn2program at gmail.com (Alan Gauld)
Date: Fri, 14 Apr 2023 01:13:56 +0100
Subject: Weak Type Ability for Python
In-Reply-To: <00b801d96e5f$46008d10$d201a730$@gmail.com>
References: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
 <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>
 <mailman.58.1681352533.20750.python-list@python.org>
 <0sqe3id664268aqif7sttg1r0c1vikof9k@4ax.com>
 <CAPTjJmpgrYL=jHWNWUBergoVQ7duvwXP6rua-xtOp_DnE5TEZg@mail.gmail.com>
 <00b801d96e5f$46008d10$d201a730$@gmail.com>
Message-ID: <62cbbe2b-be03-75d9-ed27-ed8e93cea36a@yahoo.co.uk>

On 14/04/2023 00:25, avi.e.gross at gmail.com wrote:

> Is there any concept in Python of storing information in some way, such as
> text, and implementing various ideas or interfaces so that you can query if
> the contents are willing and able to be viewed in one of many other ways?

Are you talking about something like a C union type (or a Pascal
variant record)? I'm not aware of any such feature in Python but
have often thought it would be a nice to have for the rare cases
where its useful.

> Or it may be storing text in some format but the object is willing to
> transform the text into one of several other formats when needed. The text
> may also have attributes such as whether it is in English or Hungarian or is
> mixed-language.

Or are you meaning something like an extension to the
struct module that can interpret a bytestring in any way
defined by a format string?

> basis. But do some languages have some support within the language itself?

The closest to what you seem to mean is, I think, the C union
type, at least in my experience. But you have to define all
the ways you can interpret the type up front in the type
definition.

> My reason for asking, is based on the discussion. If I want to use plus with
> an integer and a string, it may be reasonable for the interpreter to ask one
> or the other operand if they are able to be seen another way.

You can achieve that in a slightly different way in Tcl which
allows you to redefine all the operators (commands in Tcl-speak)
in the language so redefining plus is easy. Doing it based on
type is more tricky but doable.

> Unfortunately, if they BOTH are flexible, how do you decide whether to add
> them as numbers or concatenate them as strings?

Yes, that's where it becomes a designer's arbitrary choice.

-- 
Alan G
Author of the Learn to Program web site
http://www.alan-g.me.uk/
http://www.amazon.com/author/alan_gauld
Follow my photo-blog on Flickr at:
http://www.flickr.com/photos/alangauldphotos



From rosuav at gmail.com  Thu Apr 13 20:19:03 2023
From: rosuav at gmail.com (Chris Angelico)
Date: Fri, 14 Apr 2023 10:19:03 +1000
Subject: Weak Type Ability for Python
In-Reply-To: <899fcb5e-016b-1717-de5c-a68ad435cf37@yahoo.co.uk>
References: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
 <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>
 <mailman.58.1681352533.20750.python-list@python.org>
 <0sqe3id664268aqif7sttg1r0c1vikof9k@4ax.com>
 <CAPTjJmpgrYL=jHWNWUBergoVQ7duvwXP6rua-xtOp_DnE5TEZg@mail.gmail.com>
 <899fcb5e-016b-1717-de5c-a68ad435cf37@yahoo.co.uk>
Message-ID: <CAPTjJmr4ATVfixgUCFdhqK8m3fwF2PpajC+0faQD-4TviCaM6Q@mail.gmail.com>

On Fri, 14 Apr 2023 at 09:49, Alan Gauld <learn2program at gmail.com> wrote:
>
> On 13/04/2023 20:35, Chris Angelico wrote:
>
> > REXX - where everything is a string,
>
> > It was quite the experience back in the day (as OS/2's native
> > scripting language),
>
> I briefly met REXX on a mainframe, but I did play with OS/2 for
> a year or two. Back when it looked like it might be a rival to M$
>
> OS/2 running NeXTstep now that would have been a platform
> for the 90s...  both so near yet so far.
>

OS/2 was the primary operating system in our house from about 1992ish
until maybe the early 2000s - possibly 2010 even, depending on how you
count things. After a while we needed to permit the occasional Windows
system due to software that didn't work, and then I started deploying
some Linux systems. Eventually the Linux boxes outnumbered the OS/2,
and finally the last OS/2 system was virtualized under Linux,
completing the transition.

But along the way, I spent many years learning the way that OS/2
works, and that's been so valuable to me ever since. The system was
built from the ground up with threads in mind, so every programmer, as
a matter of course, just learned about threads. It's that simple. Want
to make a GUI app? The rule is, you respond to a window message within
a very few milliseconds; if you can't do your processing in that much
time, you spin off a thread. Easy. VX-REXX actually did that for every
message automatically, running thread zero for the system GUI message
loop, and feeding messages to a REXX message loop; you could, of
course, still spawn your own REXX threads as needed.

The entire Presentation Manager and Workplace Shell (broadly
equivalent to a Linux "desktop manager", I think? Kinda?) were object
oriented; you would have a WPDataFile for every, well, data file, but
some of those might be subclasses of WPDataFile. And it was fairly
straight-forward to write your own subclass of WPDataFile, and there
was an API to say "if you would ever create a WPDataFile, instead
create one of my class instead". This brilliant technique allowed
anyone to enhance the desktop in any way, quite impressive especially
for its time. I've yearned for that ever since, in various systems,
although I'm aware that it would make quite a mess of Python if you
could say "class EnhancedInt(int): ..." and then "any time you would
create an int, create an EnhancedInt instead". A bit tricky to
implement.

Ahh, the memories. Clinging onto several old Realtek RTL8029 cards
long past the days when ten megabit networking was considered
adequate, because I knew that I could ALWAYS rely on them. Seriously,
those things just never gave me issues. Problems with networking? Slap
in an 8029 and see if it's the card or something else. Need to
download the driver before your network card works? Grab an 8029, boot
with that, fetch driver, try again. Good times.

ChrisA

From hjp-python at hjp.at  Thu Apr 13 20:19:27 2023
From: hjp-python at hjp.at (Peter J. Holzer)
Date: Fri, 14 Apr 2023 02:19:27 +0200
Subject: Weak Type Ability for Python
In-Reply-To: <64381eff.920a0220.9f55.07ce@mx.google.com>
References: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
 <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>
 <64381eff.920a0220.9f55.07ce@mx.google.com>
Message-ID: <20230414001927.6slclkq4xenuyop3@hjp.at>

On 2023-04-13 08:25:51 -0700, Grant Edwards wrote:
> On 2023-04-13, Cameron Simpson <cs at cskk.id.au> wrote:
> > On 12Apr2023 22:12, avi.e.gross at gmail.com <avi.e.gross at gmail.com> wrote:
> >
> >>I suspect the OP is thinking of languages like PERL or JAVA which guess 
> >>for you and make such conversions when it seems to make sense.
> >
> > JavaScript guesses. What a nightmare.
> 
> So does PHP.

Not in this case. Like Perl (Not PERL) it has different operators for
concatenation and addition. So $a + $b is always addition, never
concatenation.

Well, at least numbers and strings. For arrays its a (somewhat bizarre)
union.

        hp

-- 
   _  | Peter J. Holzer    | Story must make more sense than reality.
|_|_) |                    |
| |   | hjp at hjp.at         |    -- Charles Stross, "Creative writing
__/   | http://www.hjp.at/ |       challenge!"
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 833 bytes
Desc: not available
URL: <https://mail.python.org/pipermail/python-list/attachments/20230414/48632030/attachment.sig>

From Richard at Damon-Family.org  Thu Apr 13 20:53:21 2023
From: Richard at Damon-Family.org (Richard Damon)
Date: Thu, 13 Apr 2023 20:53:21 -0400
Subject: Weak Type Ability for Python
In-Reply-To: <00b801d96e5f$46008d10$d201a730$@gmail.com>
References: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
 <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>
 <mailman.58.1681352533.20750.python-list@python.org>
 <0sqe3id664268aqif7sttg1r0c1vikof9k@4ax.com>
 <CAPTjJmpgrYL=jHWNWUBergoVQ7duvwXP6rua-xtOp_DnE5TEZg@mail.gmail.com>
 <00b801d96e5f$46008d10$d201a730$@gmail.com>
Message-ID: <8969c20b-5683-73fc-9c6c-5c06ed881c01@Damon-Family.org>

On 4/13/23 7:25 PM, avi.e.gross at gmail.com wrote:
> s there any concept in Python of storing information in some way, such as
> text, and implementing various ideas or interfaces so that you can query if
> the contents are willing and able to be viewed in one of many other ways?

There is nothing that I know of built into Python that does this.

There is no reason you can't write your own class to implement this. 
Something that by "default" looks like a string, but in some contexts 
(operated on by certain types) sees if its string could be treated as a 
value of some other type, and if so, converts its value to that type and 
does the operation.

-- 
Richard Damon


From greg.ewing at canterbury.ac.nz  Thu Apr 13 20:54:45 2023
From: greg.ewing at canterbury.ac.nz (Greg Ewing)
Date: Fri, 14 Apr 2023 12:54:45 +1200
Subject: Weak Type Ability for Python
In-Reply-To: <mailman.74.1681404938.20750.python-list@python.org>
References: <e00cf529-1c77-a438-3efa-890d96f141b2@mrabarnett.plus.com>
 <ZDd6LmQOzUXNNUAa@cskk.homeip.net>
 <015501d96dca$3ef2c820$bcd85860$@gmail.com>
 <CAPTjJmrHgbe46E3z2oe2dZX3B6CyO0K-Ueow3KhW=RbzfsGrfg@mail.gmail.com>
 <002201d96e21$d3995dc0$7acc1940$@gmail.com>
 <CAPTjJmqRzyPycsbuh8sYSPK0wvT6+kY5-cBqxWZ0FsRRoFpSUg@mail.gmail.com>
 <002f01d96e28$b74d1650$25e742f0$@gmail.com>
 <mailman.74.1681404938.20750.python-list@python.org>
Message-ID: <k9rmioF2ggnU1@mid.individual.net>

On 14/04/23 4:55 am, avi.e.gross at gmail.com wrote:
> While we are at it, why stop with imaginary numbers when you can imagine
> extensions thereof? Unfortunately, it has been proven there are and can only
> be two additional such constructs.

You can go beyond that if you broaden your horizons enough.
There are Clifford algebras, Lie algebras, ...

Not sure what any of those should do to strings, though. :-)

-- 
Greg

From avi.e.gross at gmail.com  Thu Apr 13 22:14:25 2023
From: avi.e.gross at gmail.com (avi.e.gross at gmail.com)
Date: Thu, 13 Apr 2023 22:14:25 -0400
Subject: Weak Type Ability for Python
In-Reply-To: <62cbbe2b-be03-75d9-ed27-ed8e93cea36a@yahoo.co.uk>
References: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
 <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>
 <mailman.58.1681352533.20750.python-list@python.org>
 <0sqe3id664268aqif7sttg1r0c1vikof9k@4ax.com>
 <CAPTjJmpgrYL=jHWNWUBergoVQ7duvwXP6rua-xtOp_DnE5TEZg@mail.gmail.com>
 <00b801d96e5f$46008d10$d201a730$@gmail.com>
 <62cbbe2b-be03-75d9-ed27-ed8e93cea36a@yahoo.co.uk>
Message-ID: <00c901d96e76$d6066580$82133080$@gmail.com>

Alan,

Your guess is not quite what I intended.

Something like a C union is just a piece of memory large enough to hold one of several kinds of content and some way to figure out which is currently in place.

I am looking at a data structure that is an object of some class and stores the data in any way that it feels like. But it may be a bit of a chameleon that shows one face or another as needed. I can write code now that simply adds various access methods to the class used and also provides a way to query if it supports some interfaces.

Consider a dumb example. I have an object that holds a temperature and stores it in say degrees Celsius. There are simple formulas that can convert it to Fahrenheit or Kelvin or Rankine. So you can create access methods like get_as_Rankine() but this will only be useful for some programs that know about the interface.

So what if you had a variable in the class such as supported_formats that presented something like a list of scales supported using an official set of names? It may even be possible to get a reference to the function to call to get that functionality, or perhaps you have one access function that accepts any argument on the list and delivers what is wanted.

The temperature would only need to be stored in one format but be available in many. Of course, you could choose to precalculate and store others, or cache them when one request has come in and so forth.

Another example  would be dates stored in some format in a class that can deliver the result in all kinds of formats. Yes, we have functions that do things like that. But can you see advantages to the class hiding lots of details internally?

These are just examples but the point is motivated by some interfaces I have seen.

How do you know if something can be used by a context manner such as in a "with" statement? There may be other ways, but it seems two dunder methods, if present, likely mean it is. They are __enter__() and __exit__().

There are other interfaces like for iterators, that sometimes are more complex as when some things are not present, it uses others. Can you have a general function like is_iterator() or is_context_manager() that pretty much guarantees it is safe for the rest of the code to use the object in the way it wants?

My comments about overloading plus were a sort of extra idea. I think we have discussed the general algorithm for how Python tries to resolve something like "obj1 op obj2" and not just for the plus operator. There are quite a few dunder methods that cover many such operators.

What I was thinking about was a bit of a twist on that algorithm. I did something very vaguely like this years ago when I was working on how to translate documents from one format to another, such as WANG, Multimate, Wordperfect, plain text, etc. The goal was for a sender of an email to add an attachment and send it to many people at once. Each recipient would have a known preference for the type of document format they preferred. I wrote an algorithm in C++ which I got early access to as I was working at Bell Labs that effectively used a registered series of translator software along with info on how well or fast they worked, to do as few translations as possible and send each recipient the format they wanted.

Yes, there were major incompatibilities and you sometimes ended up with some features being dropped or changed. But that is not the point. If format A had do direct translator to format Z, I would find the intersection of formats we had software for to translate to from A, and anther set of languages that could be used to translate from to Z. Sometimes it needed multiple hops. It worked fine but never saw the light of day as, weirdly, the project had been canceled months earlier and they were stalling while planning the next project and thus let me do what I wanted even though I was integrating my C++ code into a project that was otherwise al in C. 

Now back to Python in this regard. If I type alpha + beta then maybe after trying the methods we have described, if still failing, the algorithm could see if alpha and beta registered what types they could output and see if a match could be made. If a number object offered a string version, that would be a match. If the string offered a numeric version, again problem solved. And even if the match was not precise, sometimes the interpreter might know enough to do a bit more and say convert an integer into a double if the sizes of the contents allowed.

The problem with this, and there are many, is that there is a certain nondeterministic aspect that may cause surprises and plenty of cost. 

It was just a academic thought that probably is not needed in the context albeit may  be implemented in some projects to bridge things as described or in other novel ways. 

-----Original Message-----
From: Alan Gauld <learn2program at gmail.com> 
Sent: Thursday, April 13, 2023 8:14 PM
To: avi.e.gross at gmail.com; python-list at python.org
Subject: Re: RE: Weak Type Ability for Python

On 14/04/2023 00:25, avi.e.gross at gmail.com wrote:

> Is there any concept in Python of storing information in some way, such as
> text, and implementing various ideas or interfaces so that you can query if
> the contents are willing and able to be viewed in one of many other ways?

Are you talking about something like a C union type (or a Pascal
variant record)? I'm not aware of any such feature in Python but
have often thought it would be a nice to have for the rare cases
where its useful.

> Or it may be storing text in some format but the object is willing to
> transform the text into one of several other formats when needed. The text
> may also have attributes such as whether it is in English or Hungarian or is
> mixed-language.

Or are you meaning something like an extension to the
struct module that can interpret a bytestring in any way
defined by a format string?

> basis. But do some languages have some support within the language itself?

The closest to what you seem to mean is, I think, the C union
type, at least in my experience. But you have to define all
the ways you can interpret the type up front in the type
definition.

> My reason for asking, is based on the discussion. If I want to use plus with
> an integer and a string, it may be reasonable for the interpreter to ask one
> or the other operand if they are able to be seen another way.

You can achieve that in a slightly different way in Tcl which
allows you to redefine all the operators (commands in Tcl-speak)
in the language so redefining plus is easy. Doing it based on
type is more tricky but doable.

> Unfortunately, if they BOTH are flexible, how do you decide whether to add
> them as numbers or concatenate them as strings?

Yes, that's where it becomes a designer's arbitrary choice.

-- 
Alan G
Author of the Learn to Program web site
http://www.alan-g.me.uk/
http://www.amazon.com/author/alan_gauld
Follow my photo-blog on Flickr at:
http://www.flickr.com/photos/alangauldphotos




From 2QdxY4RzWzUUiLuE at potatochowder.com  Thu Apr 13 22:26:53 2023
From: 2QdxY4RzWzUUiLuE at potatochowder.com (2QdxY4RzWzUUiLuE at potatochowder.com)
Date: Thu, 13 Apr 2023 22:26:53 -0400
Subject: Weak Type Ability for Python
In-Reply-To: <00c901d96e76$d6066580$82133080$@gmail.com>
References: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
 <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>
 <mailman.58.1681352533.20750.python-list@python.org>
 <0sqe3id664268aqif7sttg1r0c1vikof9k@4ax.com>
 <CAPTjJmpgrYL=jHWNWUBergoVQ7duvwXP6rua-xtOp_DnE5TEZg@mail.gmail.com>
 <00b801d96e5f$46008d10$d201a730$@gmail.com>
 <62cbbe2b-be03-75d9-ed27-ed8e93cea36a@yahoo.co.uk>
 <00c901d96e76$d6066580$82133080$@gmail.com>
Message-ID: <ZDi57Wd45jm6Djo9@anomaly>

On 2023-04-13 at 22:14:25 -0400,
avi.e.gross at gmail.com wrote:

> I am looking at a data structure that is an object of some class and
> stores the data in any way that it feels like. But it may be a bit of
> a chameleon that shows one face or another as needed. I can write code
> now that simply adds various access methods to the class used and also
> provides a way to query if it supports some interfaces.

Python dicts act mostly like hash tables.  All by themselves, hash
tables are unordered (and in return for giving up that order, you get
O(1) access to an item if you know its key).

But when you ask a Python dict for the keys, you always get them in the
same order, skipping those that have been deleted since the last time
you asked, and appending the new keys to the end of the list in the
order in which you added them.

There's your chameleon.

From list1 at tompassin.net  Thu Apr 13 23:10:19 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Thu, 13 Apr 2023 23:10:19 -0400
Subject: Weak Type Ability for Python
In-Reply-To: <00c901d96e76$d6066580$82133080$@gmail.com>
References: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
 <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>
 <mailman.58.1681352533.20750.python-list@python.org>
 <0sqe3id664268aqif7sttg1r0c1vikof9k@4ax.com>
 <CAPTjJmpgrYL=jHWNWUBergoVQ7duvwXP6rua-xtOp_DnE5TEZg@mail.gmail.com>
 <00b801d96e5f$46008d10$d201a730$@gmail.com>
 <62cbbe2b-be03-75d9-ed27-ed8e93cea36a@yahoo.co.uk>
 <00c901d96e76$d6066580$82133080$@gmail.com>
Message-ID: <369a53e8-6701-c606-c7b3-2fb974e9f7c9@tompassin.net>

On 4/13/2023 10:14 PM, avi.e.gross at gmail.com wrote:
> Alan,
> 
> Your guess is not quite what I intended.
> 
> Something like a C union is just a piece of memory large enough to hold one of several kinds of content and some way to figure out which is currently in place.
> 
> I am looking at a data structure that is an object of some class and stores the data in any way that it feels like. But it may be a bit of a chameleon that shows one face or another as needed. I can write code now that simply adds various access methods to the class used and also provides a way to query if it supports some interfaces.
> 
> Consider a dumb example. I have an object that holds a temperature and stores it in say degrees Celsius. There are simple formulas that can convert it to Fahrenheit or Kelvin or Rankine. So you can create access methods like get_as_Rankine() but this will only be useful for some programs that know about the interface.
> 
> So what if you had a variable in the class such as supported_formats that presented something like a list of scales supported using an official set of names? It may even be possible to get a reference to the function to call to get that functionality, or perhaps you have one access function that accepts any argument on the list and delivers what is wanted.

Now you are starting to sound like COM.  You ask an object for its 
IUnknown interface, and from that interface you can query what other 
interfaces it has available.  You go on from there.

From avi.e.gross at gmail.com  Thu Apr 13 23:44:56 2023
From: avi.e.gross at gmail.com (avi.e.gross at gmail.com)
Date: Thu, 13 Apr 2023 23:44:56 -0400
Subject: Weak Type Ability for Python
In-Reply-To: <ZDi57Wd45jm6Djo9@anomaly>
References: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
 <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>
 <mailman.58.1681352533.20750.python-list@python.org>
 <0sqe3id664268aqif7sttg1r0c1vikof9k@4ax.com>
 <CAPTjJmpgrYL=jHWNWUBergoVQ7duvwXP6rua-xtOp_DnE5TEZg@mail.gmail.com>
 <00b801d96e5f$46008d10$d201a730$@gmail.com>
 <62cbbe2b-be03-75d9-ed27-ed8e93cea36a@yahoo.co.uk>
 <00c901d96e76$d6066580$82133080$@gmail.com> <ZDi57Wd45jm6Djo9@anomaly>
Message-ID: <00ef01d96e83$7af814b0$70e83e10$@gmail.com>

Yes, Dave, there are many data structures that can be used to maintain a
list of output types the class claims to support. Dictionaries have the
interesting property that you can presumably have a value that holds a
member function to access the way the key specifies.

Ideally, the order is not important for what I am looking for. Generally, I
would think that any class like the ones I have been discussing, would want
to broadcast a fairly short list of output types it would support.

Of course, if you look at my date example, the list could be quite big but
if you simply use something like strftime() for many of the formats, perhaps
you may not need to list all possible ones. Any valid format could be
accepted as an argument and passed to such a utility function. Your
dictionary might simply store some commonly used formats known to work.

But I repeat. This is not a serious request. I know how to build limited
functionality like this if I ever want it, but wonder if anyone has ever
created a proposal for some protocols and perhaps helpers like say an
embedded object that handles aspects of it once you have initialized your
dictionary and also handles requests to show part of what is stored for any
shoppers wondering if you are compatible with their needs.

-----Original Message-----
From: Python-list <python-list-bounces+avi.e.gross=gmail.com at python.org> On
Behalf Of 2QdxY4RzWzUUiLuE at potatochowder.com
Sent: Thursday, April 13, 2023 10:27 PM
To: python-list at python.org
Subject: Re: RE: Weak Type Ability for Python

On 2023-04-13 at 22:14:25 -0400,
avi.e.gross at gmail.com wrote:

> I am looking at a data structure that is an object of some class and
> stores the data in any way that it feels like. But it may be a bit of
> a chameleon that shows one face or another as needed. I can write code
> now that simply adds various access methods to the class used and also
> provides a way to query if it supports some interfaces.

Python dicts act mostly like hash tables.  All by themselves, hash
tables are unordered (and in return for giving up that order, you get
O(1) access to an item if you know its key).

But when you ask a Python dict for the keys, you always get them in the
same order, skipping those that have been deleted since the last time
you asked, and appending the new keys to the end of the list in the
order in which you added them.

There's your chameleon.
-- 
https://mail.python.org/mailman/listinfo/python-list


From wlfraed at ix.netcom.com  Fri Apr 14 00:06:09 2023
From: wlfraed at ix.netcom.com (Dennis Lee Bieber)
Date: Fri, 14 Apr 2023 00:06:09 -0400
Subject: Weak Type Ability for Python
References: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
 <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>
 <mailman.58.1681352533.20750.python-list@python.org>
 <0sqe3id664268aqif7sttg1r0c1vikof9k@4ax.com>
 <CAPTjJmpgrYL=jHWNWUBergoVQ7duvwXP6rua-xtOp_DnE5TEZg@mail.gmail.com>
 <mailman.82.1681414535.20750.python-list@python.org>
Message-ID: <l0kh3i5jkca0ifjapm9ir0k1plkmtdgrs4@4ax.com>

On Fri, 14 Apr 2023 05:35:22 +1000, Chris Angelico <rosuav at gmail.com>
declaimed the following:

>It was quite the experience back in the day (as OS/2's native
>scripting language), and one that I'm truly glad to have had, as it
>taught me so much about the differences between languages.
>

	I still miss the Amiga ARexx implementation which piggy-backed on the
Amiga IPC scheme* such that any application that opened a "RexxPort" could
be the target for "ADDRESS <rexxport>", and hence scripted using ARexx (Did
IBM ever get beyond the two choices of command-line and a line-editor?).


*	Granted, that IPC relied upon the fact that all applications shared one
memory space, so there wasn't the overhead of copying data structures from
sending application to the port's linked list and thence to the receiving
application.

From Keith.S.Thompson+u at gmail.com  Fri Apr 14 00:11:21 2023
From: Keith.S.Thompson+u at gmail.com (Keith Thompson)
Date: Thu, 13 Apr 2023 21:11:21 -0700
Subject: Hide my query about covariance matrix syntax from google
References: <CA+Vnj_qsVo03H=L46b8K2fqc8vG1x3irTrv8utJ1FSorBv7dVw@mail.gmail.com>
 <CAPTjJmrpi9P2wamk=bzTSBQOtdMhxt_WVy+xA0uvTrMHzfL21w@mail.gmail.com>
 <mailman.79.1681414099.20750.python-list@python.org>
Message-ID: <87sfd3drx2.fsf@nosuchdomain.example.com>

Chris Angelico <rosuav at gmail.com> writes:
> On Fri, 14 Apr 2023 at 03:11, Meghna Karkera <mkarkera98 at gmail.com> wrote:
>>
>> Respected Sir
>>
>> I kindly request you to hide my query about covariance matrix syntax from
>> google which was emailed to you a few years back as it appears on google
>> page.
>>
>> Hoping that you do the needful.
>
> These posts are public. While it's possible to ask for something to be
> removed from the official python-list archive, that won't remove it
> from Google Groups or any other third-party archive.
>
> Also, there's nothing we can do here to remove your post; you'll have
> to contact the list admins.
>
> And just in case it's of interest to you:
> https://en.wikipedia.org/wiki/Streisand_effect

It's also mirrored to Usenet (comp.lang.python).  There's basically no
way to delete articles from Usenet.  (The protocol includes a command to
cancel an article, but servers ignore it due to past abuse.)

-- 
Keith Thompson (The_Other_Keith) Keith.S.Thompson+u at gmail.com
Working, but not speaking, for XCOM Labs
void Void(void) { Void(); } /* The recursive call of the void */

From wlfraed at ix.netcom.com  Fri Apr 14 00:22:43 2023
From: wlfraed at ix.netcom.com (Dennis Lee Bieber)
Date: Fri, 14 Apr 2023 00:22:43 -0400
Subject: Weak Type Ability for Python
References: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
 <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>
 <mailman.58.1681352533.20750.python-list@python.org>
 <0sqe3id664268aqif7sttg1r0c1vikof9k@4ax.com>
 <CAPTjJmpgrYL=jHWNWUBergoVQ7duvwXP6rua-xtOp_DnE5TEZg@mail.gmail.com>
 <00b801d96e5f$46008d10$d201a730$@gmail.com>
 <8969c20b-5683-73fc-9c6c-5c06ed881c01@Damon-Family.org>
 <mailman.90.1681433606.20750.python-list@python.org>
Message-ID: <ajkh3id2v8fji782ff78rcqn1tdcipj09o@4ax.com>

On Thu, 13 Apr 2023 20:53:21 -0400, Richard Damon
<Richard at Damon-Family.org> declaimed the following:

>On 4/13/23 7:25 PM, avi.e.gross at gmail.com wrote:
>> s there any concept in Python of storing information in some way, such as
>> text, and implementing various ideas or interfaces so that you can query if
>> the contents are willing and able to be viewed in one of many other ways?
>
>There is nothing that I know of built into Python that does this.
>
>There is no reason you can't write your own class to implement this. 
>Something that by "default" looks like a string, but in some contexts 
>(operated on by certain types) sees if its string could be treated as a 
>value of some other type, and if so, converts its value to that type and 
>does the operation.

	I sure don't want to see the documentation for that...

a = thisType(3)
b = thisType(7)
c = 9	#plain integer

print(a + b + c)

(Since I presume left to right evaluation of equal level operations) Does
this result in

			46 ("3" + "7" => "37", int("37") + 9 => 46)

or

			19 (as int("3") + int("7") => 10, + 9 => 19)

	Worse... changing order of a/b/c would make completely different
results...

			82 (b + a + c)
			127 (int(a) + c returning thisType(12) + b as strings)

and does (c + a) result in returning an integer (a conforming to c); or a
string (a coercing c to thisType).
			

From rosuav at gmail.com  Fri Apr 14 03:22:47 2023
From: rosuav at gmail.com (Chris Angelico)
Date: Fri, 14 Apr 2023 17:22:47 +1000
Subject: Weak Type Ability for Python
In-Reply-To: <l0kh3i5jkca0ifjapm9ir0k1plkmtdgrs4@4ax.com>
References: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
 <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>
 <mailman.58.1681352533.20750.python-list@python.org>
 <0sqe3id664268aqif7sttg1r0c1vikof9k@4ax.com>
 <CAPTjJmpgrYL=jHWNWUBergoVQ7duvwXP6rua-xtOp_DnE5TEZg@mail.gmail.com>
 <mailman.82.1681414535.20750.python-list@python.org>
 <l0kh3i5jkca0ifjapm9ir0k1plkmtdgrs4@4ax.com>
Message-ID: <CAPTjJmrqQ_zC7sWuKzygx4Cqi5k4wcKjoEsL1bf2L1H8P5vv+g@mail.gmail.com>

On Fri, 14 Apr 2023 at 17:17, Dennis Lee Bieber <wlfraed at ix.netcom.com> wrote:
>
> On Fri, 14 Apr 2023 05:35:22 +1000, Chris Angelico <rosuav at gmail.com>
> declaimed the following:
>
> >It was quite the experience back in the day (as OS/2's native
> >scripting language), and one that I'm truly glad to have had, as it
> >taught me so much about the differences between languages.
> >
>
>         I still miss the Amiga ARexx implementation which piggy-backed on the
> Amiga IPC scheme* such that any application that opened a "RexxPort" could
> be the target for "ADDRESS <rexxport>", and hence scripted using ARexx (Did
> IBM ever get beyond the two choices of command-line and a line-editor?).
>
>
> *       Granted, that IPC relied upon the fact that all applications shared one
> memory space, so there wasn't the overhead of copying data structures from
> sending application to the port's linked list and thence to the receiving
> application.

Yeah, the "ADDRESS" command has so much potential. Back in the day, I
built a MUD with REXX scripting, and within those scripts, the default
ADDRESS target was "send message to the invoker of the command", so
you could do something like this:

/* A bare string gets sent to the client */
"Hello!"
/* You can still invoke shell commands, if you actually need to */
address cmd "do_a_thing"

Rabid proponents of OOP say that it's all about sending messages to
things. Well, the ADDRESS command truly lets you send messages, so....
that means REXX is the most object oriented language there is, right?

ChrisA

From wlfraed at ix.netcom.com  Fri Apr 14 10:32:30 2023
From: wlfraed at ix.netcom.com (Dennis Lee Bieber)
Date: Fri, 14 Apr 2023 10:32:30 -0400
Subject: Weak Type Ability for Python
References: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
 <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>
 <mailman.58.1681352533.20750.python-list@python.org>
 <0sqe3id664268aqif7sttg1r0c1vikof9k@4ax.com>
 <CAPTjJmpgrYL=jHWNWUBergoVQ7duvwXP6rua-xtOp_DnE5TEZg@mail.gmail.com>
 <mailman.82.1681414535.20750.python-list@python.org>
 <l0kh3i5jkca0ifjapm9ir0k1plkmtdgrs4@4ax.com>
 <CAPTjJmrqQ_zC7sWuKzygx4Cqi5k4wcKjoEsL1bf2L1H8P5vv+g@mail.gmail.com>
 <mailman.95.1681456981.20750.python-list@python.org>
Message-ID: <ofoi3ihfuds7c622un6jdudmrpj46qhnub@4ax.com>


	{one more entry in the thread drift, and then I think I'll shut up}

On Fri, 14 Apr 2023 17:22:47 +1000, Chris Angelico <rosuav at gmail.com>
declaimed the following:


>Yeah, the "ADDRESS" command has so much potential. Back in the day, I
>built a MUD with REXX scripting, and within those scripts, the default
>ADDRESS target was "send message to the invoker of the command", so
>you could do something like this:

	I used to think (Open)VMS would have been a potential platform for an
effective ADDRESS command. Where ARexx used a shared memory linked-list for
the "port" (as I'd stated, avoiding copying of data), (Open)VMS had
"mailboxes" (they would have to copy data -- or at best remap the virtual
memory from one process to another) which could serve the same purpose;
receiving application creates/owns the named mailbox, sending applications
would provide the data packet including a return mailbox link.

>
>/* A bare string gets sent to the client */
>"Hello!"
>/* You can still invoke shell commands, if you actually need to */
>address cmd "do_a_thing"
>
	Yeah, that was the other feature -- anything that could not be parsed
as a REXX statement was automatically sent to whatever the current ADDRESS
host happened to be.

From martin.schoon at gmail.com  Fri Apr 14 15:47:35 2023
From: martin.schoon at gmail.com (Martin =?UTF-8?Q?Sch=C3=B6=C3=B6n?=)
Date: 14 Apr 2023 19:47:35 GMT
Subject: Problem with Matplotlib example
References: <k9r0mfFtcr1U1@mid.individual.net>
 <4cef1b3b-30fd-378e-5fe7-7944bf5aec61@mrabarnett.plus.com>
 <mailman.83.1681414652.20750.python-list@python.org>
Message-ID: <k9tounFc7f7U1@mid.individual.net>

Den 2023-04-13 skrev MRAB <python at mrabarnett.plus.com>:
> On 2023-04-13 19:41, Martin Sch??n wrote:
>> Anyone had success running this example?
>> https://tinyurl.com/yhhyc9r
>> 
<snip>
>> As far as I know I have an up-to-date matplotlib installed. Pip has
>> nothing more modern to offer me.
>> 
> All I can say is that it works for me!
>
> Python 3.10 and 3.11, matplotlib 3.6.1 and then 3.7.1 after updating it.
>
Thanks are due to both you and Thomas. Your replies put me on the right
scent. I soon learned what I should have know since ages: pip reporting
there is now newer version of a package does not mean there is *no
newer* version. It means there is no newer version for the version of
Python I use. In my case I am on Python 3.7. At work, where I am on
Python 3.8, this matplotlib example works just fine.

/Martin

From avi.e.gross at gmail.com  Fri Apr 14 16:16:00 2023
From: avi.e.gross at gmail.com (avi.e.gross at gmail.com)
Date: Fri, 14 Apr 2023 16:16:00 -0400
Subject: Weak Type Ability for Python
In-Reply-To: <ajkh3id2v8fji782ff78rcqn1tdcipj09o@4ax.com>
References: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
 <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>
 <mailman.58.1681352533.20750.python-list@python.org>
 <0sqe3id664268aqif7sttg1r0c1vikof9k@4ax.com>
 <CAPTjJmpgrYL=jHWNWUBergoVQ7duvwXP6rua-xtOp_DnE5TEZg@mail.gmail.com>
 <00b801d96e5f$46008d10$d201a730$@gmail.com>
 <8969c20b-5683-73fc-9c6c-5c06ed881c01@Damon-Family.org>
 <mailman.90.1681433606.20750.python-list@python.org>
 <ajkh3id2v8fji782ff78rcqn1tdcipj09o@4ax.com>
Message-ID: <001101d96f0d$eea6ff40$cbf4fdc0$@gmail.com>

Dennis,

Before I reply, let me reiterate I am NOT making a concrete suggestion, just having a somewhat abstract discussion.

The general topic is a sort of polymorphism I envisioned where a select group of classes/objects that can be seen as different aspects of an elephant can be handled to provide some functionality in a consistent way. We all agree much of the functionality can be done deliberately by individual programmers. The question was whether anyone had done a more general implementation or even saw any reason to do so.

Fair enough?

So let us assume I have an object, call it obj1, that encapsulates data the old fashioned way. Consider a classical case like an object holding information about a parallelopiped or something like a shoebox. How you store the info can vary, such as recording a height/width/depth, or a series of x,y,z coordinates representing some of the vertices. But no matter how you store the basic info, you can derive many things from them when asked to provide a volume or surface area or whether it will fit within another object of the same kind assuming the sides have no width. Or, you can ask it to return another instance object that has double the width or many other things.

There are several ways to provide the functionality, actually quite a few, but one is to make a method for each thing it does such as obj1.get_surface_area(), obj1.get_volume() and obj1.does_it_fit_in(cl2) and of course you can have methods that change the orientation or ask what angles it is oriented at now and whatever else you want.

Each such method will return something of a usually deterministic type. Volumes will be a double, for example. But what if you design a small language so you can type obj1.get_by_name("volume") and similar requests, or even a comma separated grouping of requests that returns a list of the answers? It now is not so deterministic-looking to a linter. But normal Python allows and often encourages such polymorphism so is this anything new?

What I envisioned is a tad closer to the latter. Not this:

a = thisType(3)
b = thisType(7)
c = 9	#plain integer
print(a + b + c)

Note the above example is standard. My thoughts are a bit more arcane and focused on convertibility of a single value into multiple forms.

Say I have a data type that stores a number representing a temperature. It may have ways to initialize (or change) the temperature so it can be input as degrees centigrade or Fahrenheit or Kelvin or Rankine or even more indirect ways such as 10 degrees Fahrenheit above the freezing point of pure water at a particular atmospheric pressure and so on.

What I want to add is a bit like this. Internally many methods may get created that may not be expected to be used except through a designated interface. Call them f1() and f2() ... fn() for now.

Also in the class initialization or perhaps in the object dunder init, you create something like a dictionary consisting of key words matched by pointers to the aforementioned functions/methods. This structure will have some name designated by the protocol such as _VIEWS and may be visible to anyone looking at the object. The details can be worked out but this is a simplistic explanation.

In this dictionary we may have words like "Celsius", "Fahrenheit" and so on, perhaps even several variants that point to the same functions. If a user wants the temperature in absolute terms, they may call a standard function like "obj1.as_type('Kelvin')" and that function will search the dictionary and get you the results using the appropriate conversion method. You may also support other accessors like 'obj1.supports_type("Fahrenheit451")' that reports as True/False whether the object can handle that output. It merely checks the internal dictionary. You may have another that returns a list of the data types as keys and whatever else is part of the design.

You can, of course, have a second set of such directives that instead of returning a temperature as a double, will return a printable text version that includes ? or ?K or ?R or ?F".

A second example could be something holding a date with plenty of internal abilities to display it in a wide variety of formats or maybe just holds a day of the week that it will display as a string in any language it handles, such as Sunday being shown as:
???? ????????
Diman?o
Vas?rnap
Sonntag
Dimanche
Zondag
???
??????

And so on. Again, it need not store the text for every language but can call translation software as needed and it can be more than the name of a day of the week. It could have a dictionary containing all the languages it handles as described for another example and access methods. Of course, if called on repeatedly and often for the same languages, it could cache results.

My question, again, is not whether this can be done but whether some kind of protocol can be created that is published and suggests the names and so on to use in constructing your own implementation. And, it may be helpful if a module is made available that makes it even simpler to use.

I think it is time for me to drop out of this discussion unless I hear something of interest. It is just an idea I have been pondering. 

-----Original Message-----
From: Python-list <python-list-bounces+avi.e.gross=gmail.com at python.org> On Behalf Of Dennis Lee Bieber
Sent: Friday, April 14, 2023 12:23 AM
To: python-list at python.org
Subject: Re: Weak Type Ability for Python

On Thu, 13 Apr 2023 20:53:21 -0400, Richard Damon
<Richard at Damon-Family.org> declaimed the following:

>On 4/13/23 7:25 PM, avi.e.gross at gmail.com wrote:
>> s there any concept in Python of storing information in some way, such as
>> text, and implementing various ideas or interfaces so that you can query if
>> the contents are willing and able to be viewed in one of many other ways?
>
>There is nothing that I know of built into Python that does this.
>
>There is no reason you can't write your own class to implement this. 
>Something that by "default" looks like a string, but in some contexts 
>(operated on by certain types) sees if its string could be treated as a 
>value of some other type, and if so, converts its value to that type and 
>does the operation.

	I sure don't want to see the documentation for that...

a = thisType(3)
b = thisType(7)
c = 9	#plain integer

print(a + b + c)

(Since I presume left to right evaluation of equal level operations) Does
this result in

			46 ("3" + "7" => "37", int("37") + 9 => 46)

or

			19 (as int("3") + int("7") => 10, + 9 => 19)

	Worse... changing order of a/b/c would make completely different
results...

			82 (b + a + c)
			127 (int(a) + c returning thisType(12) + b as strings)

and does (c + a) result in returning an integer (a conforming to c); or a
string (a coercing c to thisType).
			
-- 
https://mail.python.org/mailman/listinfo/python-list


From hjp-python at hjp.at  Sat Apr 15 07:22:24 2023
From: hjp-python at hjp.at (Peter J. Holzer)
Date: Sat, 15 Apr 2023 13:22:24 +0200
Subject: Weak Type Ability for Python
In-Reply-To: <CAPTjJmr4ATVfixgUCFdhqK8m3fwF2PpajC+0faQD-4TviCaM6Q@mail.gmail.com>
References: <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
 <ZDdnRvB4Rs8vkKqM@cskk.homeip.net>
 <mailman.58.1681352533.20750.python-list@python.org>
 <0sqe3id664268aqif7sttg1r0c1vikof9k@4ax.com>
 <CAPTjJmpgrYL=jHWNWUBergoVQ7duvwXP6rua-xtOp_DnE5TEZg@mail.gmail.com>
 <899fcb5e-016b-1717-de5c-a68ad435cf37@yahoo.co.uk>
 <CAPTjJmr4ATVfixgUCFdhqK8m3fwF2PpajC+0faQD-4TviCaM6Q@mail.gmail.com>
Message-ID: <20230415112224.mpbvmgstbg4ygr2g@hjp.at>

On 2023-04-14 10:19:03 +1000, Chris Angelico wrote:
> The entire Presentation Manager and Workplace Shell (broadly
> equivalent to a Linux "desktop manager", I think? Kinda?) were object
> oriented; you would have a WPDataFile for every, well, data file, but
> some of those might be subclasses of WPDataFile. And it was fairly
> straight-forward to write your own subclass of WPDataFile, and there
> was an API to say "if you would ever create a WPDataFile, instead
> create one of my class instead". This brilliant technique allowed
> anyone to enhance the desktop in any way, quite impressive especially
> for its time. I've yearned for that ever since, in various systems,
> although I'm aware that it would make quite a mess of Python if you
> could say "class EnhancedInt(int): ..." and then "any time you would
> create an int, create an EnhancedInt instead". A bit tricky to
> implement.

Or alternatively you might be able to add or replace methods on the
existing int class. So 5 is still just an int, but now (5 + "x") calls
the modified __add__ method which knows how add a string to an int.

Might make even more of a mess ;-).

        hp

-- 
   _  | Peter J. Holzer    | Story must make more sense than reality.
|_|_) |                    |
| |   | hjp at hjp.at         |    -- Charles Stross, "Creative writing
__/   | http://www.hjp.at/ |       challenge!"
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 833 bytes
Desc: not available
URL: <https://mail.python.org/pipermail/python-list/attachments/20230415/fc257280/attachment.sig>

From hjp-python at hjp.at  Sat Apr 15 07:23:54 2023
From: hjp-python at hjp.at (Peter J. Holzer)
Date: Sat, 15 Apr 2023 13:23:54 +0200
Subject: Weak Type Ability for Python
In-Reply-To: <e9f694a5-dbe6-926e-085d-346cb374ae64@mrabarnett.plus.com>
References: <CAMpB_8R6EMj4nevu2ucjvTR5X=CL2ktYxAoVnxOZG=46koaR=Q@mail.gmail.com>
 <CAPTjJmoQgJ+8Dgu-1TpM=YL4qS+8bOk=J-eLvL0k=uY=vAJ8bQ@mail.gmail.com>
 <bab80f52-8ae5-ffd6-d7f2-ccee7cfdbdde@tompassin.net>
 <00a201d96dad$64ef8990$2ece9cb0$@gmail.com>
 <e9f694a5-dbe6-926e-085d-346cb374ae64@mrabarnett.plus.com>
Message-ID: <20230415112354.phmlnzs37nwu2rpt@hjp.at>

On 2023-04-13 03:28:37 +0100, MRAB wrote:
> On 2023-04-13 03:12, avi.e.gross at gmail.com wrote:
> > I suspect the OP is thinking of languages like PERL or JAVA which guess for
> > you and make such conversions when it seems to make sense.
> > 
> In the case of Perl, there are distinct operators for addition and string
> concatenation, with automatic type conversion (non-numeric strings have a
> numeric value of 0, which can hide bugs).

You get a warning for that, though.

        hp

-- 
   _  | Peter J. Holzer    | Story must make more sense than reality.
|_|_) |                    |
| |   | hjp at hjp.at         |    -- Charles Stross, "Creative writing
__/   | http://www.hjp.at/ |       challenge!"
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 833 bytes
Desc: not available
URL: <https://mail.python.org/pipermail/python-list/attachments/20230415/7cbaf5a0/attachment.sig>

From jiehuan233 at outlook.com  Sun Apr 16 06:57:18 2023
From: jiehuan233 at outlook.com (Jason Wang)
Date: Sun, 16 Apr 2023 18:57:18 +0800
Subject: tksheet - Copy and Paste with headers
In-Reply-To: <f524d6bc-c262-4f17-b627-5a7e91400e36n@googlegroups.com>
References: <f524d6bc-c262-4f17-b627-5a7e91400e36n@googlegroups.com>
Message-ID: <u1gkbd$2h2gq$1@dont-email.me>

? 2023/4/15 2:33, angela vales ??:
> Hello All,
> 
> I found this small group in a google search, so not sure if it is still active but giving it a try nonetheless.
> 
> I have recently created a tkinter app and need the ability to copy and paste data from tksheet table into an Excel file. I do have a button for export, but it will be beneficial to also allow the user to simply copy,paste.
> 
> I have enabled the appropriate bindings but cannot find a solution to also
> copy the header information during the copy and paste.
> 
> My table is generated after a query is run. Here is a small snippet.
> 
>   df = pd.read_sql_query(query, conn)
>      results_table.set_sheet_data(df.values.tolist())
>      results_table.headers(df.columns.tolist())
>      results_table.enable_bindings(
> "drag_select",
> "select_all",
> "column_drag_and_drop",
> "row_drag_and_drop",
> "column_select",
> "row_select",
> "arrowkeys",
> "right_click_popup_menu",
> "copy",
> "paste",
> "undo"
> )
> 
> best
> Angela Vales
I am not sure how to solve your problem. The newsgroup may not be able 
to wait for an answer, so I suggest that you go to Stack Overflow to ask 
questions after conducting a thorough Google search. Of course, you can 
also wait for someone who knows the answer to come and answer:D

From learn2program at gmail.com  Sun Apr 16 09:01:42 2023
From: learn2program at gmail.com (Alan Gauld)
Date: Sun, 16 Apr 2023 14:01:42 +0100
Subject: tksheet - Copy and Paste with headers
In-Reply-To: <u1gkbd$2h2gq$1@dont-email.me>
References: <f524d6bc-c262-4f17-b627-5a7e91400e36n@googlegroups.com>
 <u1gkbd$2h2gq$1@dont-email.me>
Message-ID: <39c79652-b424-abd8-c1fc-2f60b27e2aed@yahoo.co.uk>


> ? 2023/4/15 2:33, angela vales ??:
>> I have recently created a tkinter app and need the ability to copy and 
> paste data from tksheet table into an Excel file. 

First thanks for drawing my attention to tksheet. I've long
been desiring a decent table widget in tkinter and was on the
verge of trying to create one of my own. tksheet looks like
it will do all I need.

As to copy/paste I couldn't see any explicit mention but
it does say the underlying data is in a Tk Canvas so it may
be that copy/paste will just work, did you try it? What
happened if you paste into a text editor in the first
instance? And Excel in the second?

If all else fails you can probably write handlers and bind
to Ctrl-C and Ctrl-V to do something yourself that mimics
cut/paste.


-- 
Alan G
Author of the Learn to Program web site
http://www.alan-g.me.uk/
http://www.amazon.com/author/alan_gauld
Follow my photo-blog on Flickr at:
http://www.flickr.com/photos/alangauldphotos



From list1 at tompassin.net  Sun Apr 16 09:53:03 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Sun, 16 Apr 2023 09:53:03 -0400
Subject: tksheet - Copy and Paste with headers
In-Reply-To: <39c79652-b424-abd8-c1fc-2f60b27e2aed@yahoo.co.uk>
References: <f524d6bc-c262-4f17-b627-5a7e91400e36n@googlegroups.com>
 <u1gkbd$2h2gq$1@dont-email.me>
 <39c79652-b424-abd8-c1fc-2f60b27e2aed@yahoo.co.uk>
Message-ID: <57659803-e20f-ac7a-dd18-9b0ad04208fd@tompassin.net>

On 4/16/2023 9:01 AM, Alan Gauld wrote:
> 
>> ? 2023/4/15 2:33, angela vales ??:
>>> I have recently created a tkinter app and need the ability to copy and
>> paste data from tksheet table into an Excel file.
> 
> First thanks for drawing my attention to tksheet. I've long
> been desiring a decent table widget in tkinter and was on the
> verge of trying to create one of my own. tksheet looks like
> it will do all I need.
> 
> As to copy/paste I couldn't see any explicit mention but
> it does say the underlying data is in a Tk Canvas so it may
> be that copy/paste will just work, did you try it? What
> happened if you paste into a text editor in the first
> instance? And Excel in the second?
> 
> If all else fails you can probably write handlers and bind
> to Ctrl-C and Ctrl-V to do something yourself that mimics
> cut/paste.

I have not used tksheet, but in its documentation at 
https://github.com/ragardner/tksheet/wiki#14-getting-selected-cells, 
there is the method

     get_currently_selected()

     Returns namedtuple of (row, column, type_) e.g. (0, 0, "column")
     type_ can be "row", "column" or "cell"

There are companion methods for rows, columns, etc.  That would be a 
good starting point.

From aapost at idontexist.club  Sun Apr 16 10:24:34 2023
From: aapost at idontexist.club (aapost)
Date: Sun, 16 Apr 2023 10:24:34 -0400
Subject: tksheet - Copy and Paste with headers
In-Reply-To: <f524d6bc-c262-4f17-b627-5a7e91400e36n@googlegroups.com>
References: <f524d6bc-c262-4f17-b627-5a7e91400e36n@googlegroups.com>
Message-ID: <u1h0f2$2alq$1@nnrp.usenet.blueworldhosting.com>

On 4/14/23 14:33, angela vales wrote:
> I have recently created a tkinter app and need the ability to copy and paste data from tksheet table into an Excel file. I do have a button for export, but it will be beneficial to also allow the user to simply copy,paste.
> 
> I have enabled the appropriate bindings but cannot find a solution to also
> copy the header information during the copy and paste.

the csv export code runs through a different path than the ctrl_c code, 
one operating on the sheet level, one on the main table level (I didn't 
dig in to the depths but my assumptions would be that main table doesn't 
mathematically consider the headers in the same way).

def yield_sheet_rows in _tksheet.py vs def ctrl_c in _tksheet_main_table.py

Comparing how the each path functions, without a larger redesign of 
tksheet, you could create a custom button press combo binding to 
something other than ctrl-c utilizing the yield_sheet_rows (or - 
disallow all other ctrl-c functionality in favor of ONLY a csv style 
everything dump when using ctrl-c):

Import these:
import csv as csv_module
import io

This would be your custom binding functionality:
rows = self.sheet.yield_sheet_rows(get_header = True, get_index = False)

s = io.StringIO()
writer = csv_module.writer(s, dialect = csv_module.excel_tab, 
lineterminator = "\n")
for row in rows:
     writer.writerow(row)
self.clipboard_clear()
self.clipboard_append(s.getvalue())

It would need something deeper if you wanted to integrate it to ctrl-c 
and keep the existing ctrl-c functionality



From rshepard at appl-ecosys.com  Sun Apr 16 16:42:10 2023
From: rshepard at appl-ecosys.com (Rich Shepard)
Date: Sun, 16 Apr 2023 13:42:10 -0700 (PDT)
Subject: Cannot install pkg_resources using pip
Message-ID: <702fdd3c-089-f34a-7f-9f971be2d5ba@appl-ecosys.com>

Python3-3.9.10 installed on this Slackware64-14.2 desktop. Trying to run
meson to build an application I'm told it's missing pkg_resources, which is
part of setuptools. The command fails:
# pip install setuptools
bash: /usr/bin/pip: /usr/bin/python3.7: bad interpreter: No such file or directory

There is no python3.7 here:
# ls /usr/bin/python3.7
ls: cannot access '/usr/bin/python3.7': No such file or directory

How do I clean this up?

TIA,

Rich

From list1 at tompassin.net  Sun Apr 16 17:03:43 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Sun, 16 Apr 2023 17:03:43 -0400
Subject: Cannot install pkg_resources using pip
In-Reply-To: <702fdd3c-089-f34a-7f-9f971be2d5ba@appl-ecosys.com>
References: <702fdd3c-089-f34a-7f-9f971be2d5ba@appl-ecosys.com>
Message-ID: <87618b70-ef05-b63f-71a2-738c40b138f9@tompassin.net>

On 4/16/2023 4:42 PM, Rich Shepard wrote:
> Python3-3.9.10 installed on this Slackware64-14.2 desktop. Trying to run
> meson to build an application I'm told it's missing pkg_resources, which is
> part of setuptools. The command fails:
> # pip install setuptools
> bash: /usr/bin/pip: /usr/bin/python3.7: bad interpreter: No such file or 
> directory
> 
> There is no python3.7 here:
> # ls /usr/bin/python3.7
> ls: cannot access '/usr/bin/python3.7': No such file or directory
> 
> How do I clean this up?

What is there to clean up?  If you have Python 3.9 installed, why are 
you fooling around trying to run Python 3.7? It seems you are not 
telling us something ...

It's better to always run pip with the version of Python that you intend 
to use.  If that is launched when you type "python3", then run pip this way:

python3 -m pip

If instead you want to use, say, python3.9, then type this:

python3.9 -m pip


From rshepard at appl-ecosys.com  Sun Apr 16 18:27:56 2023
From: rshepard at appl-ecosys.com (Rich Shepard)
Date: Sun, 16 Apr 2023 15:27:56 -0700 (PDT)
Subject: Cannot install pkg_resources using pip
In-Reply-To: <99b79b42-a19e-51cb-7618-dab8d971abc1@tompassin.net>
References: <702fdd3c-089-f34a-7f-9f971be2d5ba@appl-ecosys.com>
 <87618b70-ef05-b63f-71a2-738c40b138f9@tompassin.net>
 <5d151ae5-3422-198-8164-dec245dfc99e@appl-ecosys.com>
 <99b79b42-a19e-51cb-7618-dab8d971abc1@tompassin.net>
Message-ID: <99628c5c-a034-2076-5d48-2a49b6befec2@appl-ecosys.com>

On Sun, 16 Apr 2023, Thomas Passin wrote:

> It worked then because your path found a pip script. When there are more
> than one Python installations, it can be unclear which one will get run,
> depending on how the path got set up after the last version was installed.

Thomas,

I probably last used pip with a python-3.7 version.

> To check your version of Python, run
> python3 -V

$ python3 -V
Python 3.9.10

> Then try to run pip:
> python3.9 -m pip

$ python3.9 -m pip
/usr/bin/python3.9: No module named pip

> If pip has not been installed (very possible on Linux), then you will need to 
> get it.  If python3.9 is not the system-upgraded version, then do an internet 
> search for "linux python install pip". There's a pip website that has an 
> installer for it. I never remember what it's called, so I always have to 
> search for it myself.

https://www.redhat.com/sysadmin/install-python-pip-linux

I'll download the installer from ther.

> If it appears that python3.9 *is* the version installed by the system, then 
> use the system installer to install the right version of pip - as I said 
> above, the package name can vary across distros.

It should have been installed with the upgrade to 3.9.10

> Your message doesn't seem to have been copied to the mailing list. If you
> don't mind, it could help other people if you copied it and this reply to
> the list.

I always respond to the mail list if that's the 'reply to' address.
Sometimes I don't check the address used in my reply, assuming it's correct.

Thanks,

Rich

From rshepard at appl-ecosys.com  Sun Apr 16 18:34:25 2023
From: rshepard at appl-ecosys.com (Rich Shepard)
Date: Sun, 16 Apr 2023 15:34:25 -0700 (PDT)
Subject: Cannot install pkg_resources using pip
In-Reply-To: <99628c5c-a034-2076-5d48-2a49b6befec2@appl-ecosys.com>
References: <702fdd3c-089-f34a-7f-9f971be2d5ba@appl-ecosys.com>
 <87618b70-ef05-b63f-71a2-738c40b138f9@tompassin.net>
 <5d151ae5-3422-198-8164-dec245dfc99e@appl-ecosys.com>
 <99b79b42-a19e-51cb-7618-dab8d971abc1@tompassin.net>
 <99628c5c-a034-2076-5d48-2a49b6befec2@appl-ecosys.com>
Message-ID: <38c9d095-11fa-dec8-b9dc-8abcf375f06e@appl-ecosys.com>

On Sun, 16 Apr 2023, Rich Shepard wrote:

> I'll download the installer from there.

But, I still cannot install the pkg_resources module that meson wants to
start the build of pulseaudio-equalizer:
# pip install pkg_resources
ERROR: Could not find a version that satisfies the requirement pkg_resources (from versions: none)
ERROR: No matching distribution found for pkg_resources

Rich


From khoinguyenn343 at gmail.com  Sun Apr 16 16:54:59 2023
From: khoinguyenn343 at gmail.com (Khoinguyen Nguyen)
Date: Sun, 16 Apr 2023 16:54:59 -0400
Subject: Fwd: pip is not installed
In-Reply-To: <CAEDgu=cbfkrZ2+pK4RXv+E_0J_kM6rCsSYc6iQoEsgFenMNw0Q@mail.gmail.com>
References: <CAEDgu=cbfkrZ2+pK4RXv+E_0J_kM6rCsSYc6iQoEsgFenMNw0Q@mail.gmail.com>
Message-ID: <CAEDgu=etuBOg26AprQ=SHiSPiQhyWTyNticiTLu-KDPpGLA2Bg@mail.gmail.com>

To whom it may concern,
I have tried to reinstall, repair, and run in command prompt, but it seems
as though pip won't install. I am using Windows 10 and Python 3.11.3. Are
there any other suggestions for troubleshooting?
Thank you.

From python at mrabarnett.plus.com  Sun Apr 16 22:09:36 2023
From: python at mrabarnett.plus.com (MRAB)
Date: Mon, 17 Apr 2023 03:09:36 +0100
Subject: Fwd: pip is not installed
In-Reply-To: <CAEDgu=etuBOg26AprQ=SHiSPiQhyWTyNticiTLu-KDPpGLA2Bg@mail.gmail.com>
References: <CAEDgu=cbfkrZ2+pK4RXv+E_0J_kM6rCsSYc6iQoEsgFenMNw0Q@mail.gmail.com>
 <CAEDgu=etuBOg26AprQ=SHiSPiQhyWTyNticiTLu-KDPpGLA2Bg@mail.gmail.com>
Message-ID: <e98435b4-c8b6-1e2e-bcd7-7a733500a733@mrabarnett.plus.com>

On 2023-04-16 21:54, Khoinguyen Nguyen wrote:
> To whom it may concern,
> I have tried to reinstall, repair, and run in command prompt, but it seems
> as though pip won't install. I am using Windows 10 and Python 3.11.3. Are
> there any other suggestions for troubleshooting?
> Thank you.

Have you tried using pip via the Python Launcher?

py -m pip

That's installed by default by the installer from python.org.


From cs at cskk.id.au  Sun Apr 16 22:11:06 2023
From: cs at cskk.id.au (Cameron Simpson)
Date: Mon, 17 Apr 2023 12:11:06 +1000
Subject: Fwd: pip is not installed
In-Reply-To: <CAEDgu=etuBOg26AprQ=SHiSPiQhyWTyNticiTLu-KDPpGLA2Bg@mail.gmail.com>
References: <CAEDgu=etuBOg26AprQ=SHiSPiQhyWTyNticiTLu-KDPpGLA2Bg@mail.gmail.com>
Message-ID: <ZDyquu6pBBpWxNMo@cskk.homeip.net>

On 16Apr2023 16:54, Khoinguyen Nguyen <khoinguyenn343 at gmail.com> wrote:
>I have tried to reinstall, repair, and run in command prompt, but it 
>seems
>as though pip won't install. I am using Windows 10 and Python 3.11.3. Are
>there any other suggestions for troubleshooting?

Have you tried invoking pip _via_ Python? This is actually the 
recommended approach because it uses the pip for that specific Python.  
Example:

     py -m pip install foo

This invokes the "pip" module for thePython invoked by "py" (which I 
believe is how Python is normally invoked from a Windows command line), 
to install some package "foo".

Cheers,
Cameron Simpson <cs at cskk.id.au>

From list1 at tompassin.net  Sun Apr 16 22:59:16 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Sun, 16 Apr 2023 22:59:16 -0400
Subject: Cannot install pkg_resources using pip
In-Reply-To: <99628c5c-a034-2076-5d48-2a49b6befec2@appl-ecosys.com>
References: <702fdd3c-089-f34a-7f-9f971be2d5ba@appl-ecosys.com>
 <87618b70-ef05-b63f-71a2-738c40b138f9@tompassin.net>
 <5d151ae5-3422-198-8164-dec245dfc99e@appl-ecosys.com>
 <99b79b42-a19e-51cb-7618-dab8d971abc1@tompassin.net>
 <99628c5c-a034-2076-5d48-2a49b6befec2@appl-ecosys.com>
Message-ID: <2a81722b-40ac-620d-b186-4f17e47e71b2@tompassin.net>

On 4/16/2023 6:27 PM, Rich Shepard wrote:
> On Sun, 16 Apr 2023, Thomas Passin wrote:
[snip]


> It should have been installed with the upgrade to 3.9.10

In my experience, on Windows pip is always included but on Linux hardly 
ever.  I have always needed to install the system installer pip package 
or get it from the pip site, depending, as I wrote earlier, on whether 
your version of Python was installed by the system or not.

[I'm no great Linux expert but I've had to go through this for probably 
a dozen VMs over the last few years].

From list1 at tompassin.net  Sun Apr 16 23:08:56 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Sun, 16 Apr 2023 23:08:56 -0400
Subject: Cannot install pkg_resources using pip
In-Reply-To: <38c9d095-11fa-dec8-b9dc-8abcf375f06e@appl-ecosys.com>
References: <702fdd3c-089-f34a-7f-9f971be2d5ba@appl-ecosys.com>
 <87618b70-ef05-b63f-71a2-738c40b138f9@tompassin.net>
 <5d151ae5-3422-198-8164-dec245dfc99e@appl-ecosys.com>
 <99b79b42-a19e-51cb-7618-dab8d971abc1@tompassin.net>
 <99628c5c-a034-2076-5d48-2a49b6befec2@appl-ecosys.com>
 <38c9d095-11fa-dec8-b9dc-8abcf375f06e@appl-ecosys.com>
Message-ID: <ee8217fa-f3f0-f3cb-b5ef-e0196a6bd3fa@tompassin.net>

On 4/16/2023 6:34 PM, Rich Shepard wrote:
> On Sun, 16 Apr 2023, Rich Shepard wrote:
> 
>> I'll download the installer from there.
> 
> But, I still cannot install the pkg_resources module that meson wants to
> start the build of pulseaudio-equalizer:
> # pip install pkg_resources
> ERROR: Could not find a version that satisfies the requirement 
> pkg_resources (from versions: none)
> ERROR: No matching distribution found for pkg_resources
> 
> Rich


Sorry, Rich, I've never dealt with this so someone else will have to 
give suggestions.

I would try to see if there are any versions available.  It could be 
that meson says it needs version x but only version y > x is available. 
Pip will quit but meson may very well work with the available version 
anyway.  So I would try to install pkg_resources on its own, and then 
see if the meson build can succeed.  No guarantees, but I've seen this 
work before.  So

python3.9 -m pip install --user pkg_resources

Or, to see what versions if any are available:

python3.9 -m pip install --user pkg_resources==
# NO spaces allowed before the "==".

There is a pip option to ignore the version specification and just leave 
the existing package installed as is, and this could help if the full 
installation wants to downgrade the pgk_resources that you just installed.

You can also use the --dry-run option to see what would happen without 
actually changing anything.

From list1 at tompassin.net  Mon Apr 17 00:07:13 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Mon, 17 Apr 2023 00:07:13 -0400
Subject: Cannot install pkg_resources using pip
In-Reply-To: <99628c5c-a034-2076-5d48-2a49b6befec2@appl-ecosys.com>
References: <702fdd3c-089-f34a-7f-9f971be2d5ba@appl-ecosys.com>
 <87618b70-ef05-b63f-71a2-738c40b138f9@tompassin.net>
 <5d151ae5-3422-198-8164-dec245dfc99e@appl-ecosys.com>
 <99b79b42-a19e-51cb-7618-dab8d971abc1@tompassin.net>
 <99628c5c-a034-2076-5d48-2a49b6befec2@appl-ecosys.com>
Message-ID: <91e91f6a-7520-b636-ab3a-de9f72be262b@tompassin.net>

On 4/16/2023 6:27 PM, Rich Shepard wrote:
>> If pip has not been installed (very possible on Linux), then you will 
>> need to get it.? If python3.9 is not the system-upgraded version, then 
>> do an internet search for "linux python install pip". There's a pip 
>> website that has an installer for it. I never remember what it's 
>> called, so I always have to search for it myself.
> 
> https://www.redhat.com/sysadmin/install-python-pip-linux
> 
> I'll download the installer from ther.

The page I was thinking of is

https://pip.pypa.io/en/stable/installation/

I found it by an internet search for "pip installer".  It covers several 
ways to install pip on Linux, MacOS, and Windows. On Linux, use it for 
Python installations that were *not* installed by the system.  Use the 
package manager if the Python installation or upgrade *was* installed by 
the system.

That Redhat link basically uses the pypa.io instructions.

From list1 at tompassin.net  Sun Apr 16 23:16:10 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Sun, 16 Apr 2023 23:16:10 -0400
Subject: Fwd: pip is not installed
In-Reply-To: <e98435b4-c8b6-1e2e-bcd7-7a733500a733@mrabarnett.plus.com>
References: <CAEDgu=cbfkrZ2+pK4RXv+E_0J_kM6rCsSYc6iQoEsgFenMNw0Q@mail.gmail.com>
 <CAEDgu=etuBOg26AprQ=SHiSPiQhyWTyNticiTLu-KDPpGLA2Bg@mail.gmail.com>
 <e98435b4-c8b6-1e2e-bcd7-7a733500a733@mrabarnett.plus.com>
Message-ID: <c4675b64-1adc-f88d-e193-c602d05a2dac@tompassin.net>

On 4/16/2023 10:09 PM, MRAB wrote:
> On 2023-04-16 21:54, Khoinguyen Nguyen wrote:
>> To whom it may concern,
>> I have tried to reinstall, repair, and run in command prompt, but it 
>> seems
>> as though pip won't install. I am using Windows 10 and Python 3.11.3. Are
>> there any other suggestions for troubleshooting?
>> Thank you.
> 
> Have you tried using pip via the Python Launcher?
> 
> py -m pip
> 
> That's installed by default by the installer from python.org.

To elaborate, Python might have been installed using an installer from 
python.org, from the Windows store, or in some other way.  "py" may only 
be available for a python.org installer.

In general, you would do best to always launch pip with the command

pythonx -m pip

where "pythonx" means the command that launches the version of python 
you want to work with.  This might be "py", "python3.11", "py -3.11", or 
something else, so use what you will be using on your system.


From rshepard at appl-ecosys.com  Mon Apr 17 08:45:51 2023
From: rshepard at appl-ecosys.com (Rich Shepard)
Date: Mon, 17 Apr 2023 05:45:51 -0700 (PDT)
Subject: Cannot install pkg_resources using pip
In-Reply-To: <ee8217fa-f3f0-f3cb-b5ef-e0196a6bd3fa@tompassin.net>
References: <702fdd3c-089-f34a-7f-9f971be2d5ba@appl-ecosys.com>
 <87618b70-ef05-b63f-71a2-738c40b138f9@tompassin.net>
 <5d151ae5-3422-198-8164-dec245dfc99e@appl-ecosys.com>
 <99b79b42-a19e-51cb-7618-dab8d971abc1@tompassin.net>
 <99628c5c-a034-2076-5d48-2a49b6befec2@appl-ecosys.com>
 <38c9d095-11fa-dec8-b9dc-8abcf375f06e@appl-ecosys.com>
 <ee8217fa-f3f0-f3cb-b5ef-e0196a6bd3fa@tompassin.net>
Message-ID: <9f7bd325-8436-29ac-2896-ea35bdd918f6@appl-ecosys.com>

On Sun, 16 Apr 2023, Thomas Passin wrote:

> Sorry, Rich, I've never dealt with this so someone else will have to give
> suggestions.

Thomas,

This is all new to me, too.

> I would try to see if there are any versions available. It could be that
> meson says it needs version x but only version y > x is available. Pip
> will quit but meson may very well work with the available version anyway.
> So I would try to install pkg_resources on its own, and then see if the
> meson build can succeed. No guarantees, but I've seen this work before. So
> python3.9 -m pip install --user pkg_resources
>
> Or, to see what versions if any are available:
> python3.9 -m pip install --user pkg_resources==
> # NO spaces allowed before the "==".

Thank you. I'll give this a try.

Regards,

Rich

From FJ100111 at hotmail.com  Mon Apr 17 03:36:43 2023
From: FJ100111 at hotmail.com (=?iso-2022-jp?B?GyRCTWUbKEIgGyRCQ2ZNJhsoQg==?=)
Date: Mon, 17 Apr 2023 07:36:43 +0000
Subject: pip upgrade error
Message-ID: <OSZP286MB1450A27CB797B11529629466C39C9@OSZP286MB1450.JPNP286.PROD.OUTLOOK.COM>


When I using pip list, it tells me there is a new release of pip is available, but I got these error messages when I upgrading pip. I don?t know what happened it is.
PS C:\Users\USER> pip --version pip
pip 23.0.1 from C:\Users\USER\AppData\Roaming\Python\Python310\site-packages\pip (python 3.10)
PS C:\Users\USER> python.exe -m pip install --upgrade pip
Requirement already satisfied: pip in c:\users\user\appdata\roaming\python\python310\site-packages (23.0.1)
Collecting pip
  Using cached pip-23.1-py3-none-any.whl (2.1 MB)
Installing collected packages: pip
  Attempting uninstall: pip
    Found existing installation: pip 23.0.1
    Uninstalling pip-23.0.1:
      Successfully uninstalled pip-23.0.1
  Rolling back uninstall of pip
  Moving to c:\users\user\appdata\roaming\python\python310\scripts\pip.exe
   from C:\Users\USER\AppData\Local\Temp\pip-uninstall-byh29tpt\pip.exe
  Moving to c:\users\user\appdata\roaming\python\python310\scripts\pip3.10.exe
   from C:\Users\USER\AppData\Local\Temp\pip-uninstall-byh29tpt\pip3.10.exe
  Moving to c:\users\user\appdata\roaming\python\python310\scripts\pip3.exe
   from C:\Users\USER\AppData\Local\Temp\pip-uninstall-byh29tpt\pip3.exe
  Moving to c:\users\user\appdata\roaming\python\python310\site-packages\pip-23.0.1.dist-info\
   from C:\Users\USER\AppData\Roaming\Python\Python310\site-packages\~ip-23.0.1.dist-info
  Moving to c:\users\user\appdata\roaming\python\python310\site-packages\pip\
   from C:\Users\USER\AppData\Roaming\Python\Python310\site-packages\~ip
ERROR: Exception:
Traceback (most recent call last):
  File "C:\Users\USER\AppData\Roaming\Python\Python310\site-packages\pip\_internal\cli\base_command.py", line 160, in exc_logging_wrapper
    status = run_func(*args)
  File "C:\Users\USER\AppData\Roaming\Python\Python310\site-packages\pip\_internal\cli\req_command.py", line 247, in wrapper
    return func(self, options, args)
  File "C:\Users\USER\AppData\Roaming\Python\Python310\site-packages\pip\_internal\commands\install.py", line 507, in run
    installed = install_given_reqs(
  File "C:\Users\USER\AppData\Roaming\Python\Python310\site-packages\pip\_internal\req\__init__.py", line 73, in install_given_reqs
    requirement.install(
  File "C:\Users\USER\AppData\Roaming\Python\Python310\site-packages\pip\_internal\req\req_install.py", line 796, in install
    install_wheel(
  File "C:\Users\USER\AppData\Roaming\Python\Python310\site-packages\pip\_internal\operations\install\wheel.py", line 729, in install_wheel
    _install_wheel(
  File "C:\Users\USER\AppData\Roaming\Python\Python310\site-packages\pip\_internal\operations\install\wheel.py", line 646, in _install_wheel
    generated_console_scripts = maker.make_multiple(scripts_to_generate)
  File "C:\Users\USER\AppData\Roaming\Python\Python310\site-packages\pip\_vendor\distlib\scripts.py", line 436, in make_multiple
    filenames.extend(self.make(specification, options))
  File "C:\Users\USER\AppData\Roaming\Python\Python310\site-packages\pip\_internal\operations\install\wheel.py", line 427, in make
    return super().make(specification, options)
  File "C:\Users\USER\AppData\Roaming\Python\Python310\site-packages\pip\_vendor\distlib\scripts.py", line 425, in make
    self._make_script(entry, filenames, options=options)
  File "C:\Users\USER\AppData\Roaming\Python\Python310\site-packages\pip\_vendor\distlib\scripts.py", line 325, in _make_script
    self._write_script(scriptnames, shebang, script, filenames, ext)
  File "C:\Users\USER\AppData\Roaming\Python\Python310\site-packages\pip\_vendor\distlib\scripts.py", line 249, in _write_script
    launcher = self._get_launcher('t')
  File "C:\Users\USER\AppData\Roaming\Python\Python310\site-packages\pip\_vendor\distlib\scripts.py", line 404, in _get_launcher
    raise ValueError(msg)
ValueError: Unable to find resource t64.exe in package pip._vendor.distlib

[notice] A new release of pip is available: 23.0.1 -> 23.1
[notice] To update, run: python.exe -m pip install --upgrade pip

From aapost at idontexist.club  Mon Apr 17 11:00:20 2023
From: aapost at idontexist.club (aapost)
Date: Mon, 17 Apr 2023 11:00:20 -0400
Subject: Cannot install pkg_resources using pip
In-Reply-To: <mailman.112.1681735555.20750.python-list@python.org>
References: <702fdd3c-089-f34a-7f-9f971be2d5ba@appl-ecosys.com>
 <87618b70-ef05-b63f-71a2-738c40b138f9@tompassin.net>
 <5d151ae5-3422-198-8164-dec245dfc99e@appl-ecosys.com>
 <99b79b42-a19e-51cb-7618-dab8d971abc1@tompassin.net>
 <99628c5c-a034-2076-5d48-2a49b6befec2@appl-ecosys.com>
 <38c9d095-11fa-dec8-b9dc-8abcf375f06e@appl-ecosys.com>
 <ee8217fa-f3f0-f3cb-b5ef-e0196a6bd3fa@tompassin.net>
 <9f7bd325-8436-29ac-2896-ea35bdd918f6@appl-ecosys.com>
 <mailman.112.1681735555.20750.python-list@python.org>
Message-ID: <u1jmu4$1a2m$1@nnrp.usenet.blueworldhosting.com>

On 4/17/23 08:45, Rich Shepard wrote:
> On Sun, 16 Apr 2023, Thomas Passin wrote:

Slackware isn't as straight forward in it's management as other distros 
(not standardized anyway). If this is someone elses install I would be 
cautious in using any advice I am providing, as it would be better for 
someone with familiarity with how they want the device set up to address 
the issues (such as if they prefer using some sort of package scheme or 
if doing everything from source is ok).

That being said, if you start from python source (as in overwriting what 
is currently there and doing a fresh reinstall), you can download 
Python3.9, then run
./configure
make
make install

after doing that, verify (python may still link to something old, that 
may be ok in this case, but good to note)
python --version
python3 --version
python3.9 --version

pkg_resources is inside of setuptools

so you would run
python3.9 -m pip install setuptools
(might already be there with the reinstall)

after that run
python3.9

then run
import pkg_resources
import setuptools
to see if you get errors or successful imports

if they import successfully, attempt to reinstall meson and ninja 
against your fresh python install
python3.9 -m pip install meson
python3.9 -m pip install ninja

verify versions with
meson -v
ninja --version

Then follow the instructions of the meson package from there (you 
mentioned some sort of pulseaudio-equalizer, depending on your desktop 
environment, you may run in to additional issues depending on how your 
slackware is setup).


From rshepard at appl-ecosys.com  Mon Apr 17 13:33:50 2023
From: rshepard at appl-ecosys.com (Rich Shepard)
Date: Mon, 17 Apr 2023 10:33:50 -0700 (PDT)
Subject: Cannot install pkg_resources using pip [RESOLVED]
In-Reply-To: <702fdd3c-089-f34a-7f-9f971be2d5ba@appl-ecosys.com>
References: <702fdd3c-089-f34a-7f-9f971be2d5ba@appl-ecosys.com>
Message-ID: <511ec947-de7c-c7a-be66-5e179e5ed857@appl-ecosys.com>

On Sun, 16 Apr 2023, Rich Shepard wrote:

> How do I clean this up?

My thanks for the suggestions and ideas you sent me on this issue. I've
resolved it by not trying to build pulseaudio-equalizer. I don't need it
because I learned this morning that my Yamaha CM500 headset clearly heard
the Zoom audio test tones and voices on a YouTube video.

I'm testing the headset on a Zoom call this afternoon with a friend.
Assuming it works with the meeting as it did on the Zoom test I'll use it
for Zoom and Jitsi meetings and use the Marantz Pro mic and Panasonic
headphones for recording web tutorials and podcasts.

Regards,

Rich

From rshepard at appl-ecosys.com  Mon Apr 17 14:13:15 2023
From: rshepard at appl-ecosys.com (Rich Shepard)
Date: Mon, 17 Apr 2023 11:13:15 -0700 (PDT)
Subject: Cannot install pkg_resources using pip
In-Reply-To: <u1jmu4$1a2m$1@nnrp.usenet.blueworldhosting.com>
References: <702fdd3c-089-f34a-7f-9f971be2d5ba@appl-ecosys.com>
 <87618b70-ef05-b63f-71a2-738c40b138f9@tompassin.net>
 <5d151ae5-3422-198-8164-dec245dfc99e@appl-ecosys.com>
 <99b79b42-a19e-51cb-7618-dab8d971abc1@tompassin.net>
 <99628c5c-a034-2076-5d48-2a49b6befec2@appl-ecosys.com>
 <38c9d095-11fa-dec8-b9dc-8abcf375f06e@appl-ecosys.com>
 <ee8217fa-f3f0-f3cb-b5ef-e0196a6bd3fa@tompassin.net>
 <9f7bd325-8436-29ac-2896-ea35bdd918f6@appl-ecosys.com>
 <mailman.112.1681735555.20750.python-list@python.org>
 <u1jmu4$1a2m$1@nnrp.usenet.blueworldhosting.com>
Message-ID: <9aed49f2-e95e-d332-bedb-274160e7bba4@appl-ecosys.com>

On Mon, 17 Apr 2023, aapost wrote:

> Slackware isn't as straight forward in it's management as other distros
> (not standardized anyway).

I've used Slackware for 20 years; it's completely rationale and comfortable
for me. :-)

> That being said, if you start from python source ...

If worse came to worse, I'd reinstall the distro package.

Thanks,

Rich

From hjp-python at hjp.at  Mon Apr 17 15:24:03 2023
From: hjp-python at hjp.at (Peter J. Holzer)
Date: Mon, 17 Apr 2023 21:24:03 +0200
Subject: Cannot install pkg_resources using pip
In-Reply-To: <87618b70-ef05-b63f-71a2-738c40b138f9@tompassin.net>
References: <702fdd3c-089-f34a-7f-9f971be2d5ba@appl-ecosys.com>
 <87618b70-ef05-b63f-71a2-738c40b138f9@tompassin.net>
Message-ID: <20230417192403.tjstbhqvqsdvdurm@hjp.at>

On 2023-04-16 17:03:43 -0400, Thomas Passin wrote:
> On 4/16/2023 4:42 PM, Rich Shepard wrote:
> > Python3-3.9.10 installed on this Slackware64-14.2 desktop.
[...]
> > # pip install setuptools
> > bash: /usr/bin/pip: /usr/bin/python3.7: bad interpreter: No such file or
> > directory
> > 
> > There is no python3.7 here:
> > # ls /usr/bin/python3.7
> > ls: cannot access '/usr/bin/python3.7': No such file or directory
> > 
> > How do I clean this up?
> 
> What is there to clean up?

There is a version of pip installed for a version of python which isn't
installed. That's definitely not useful, so it should be cleaned up.

As to how to do that:

Find out which package /usr/bin/pip belongs to and deinstall or upgrade
this package. How to find that package is a Slackware question, not a
Python question. And since Rich wrote that he's been comfortably using
Slackware for 20 years, I'll trust that he knows how to do that and just
needed a little nudge into the right direction.

        hp

-- 
   _  | Peter J. Holzer    | Story must make more sense than reality.
|_|_) |                    |
| |   | hjp at hjp.at         |    -- Charles Stross, "Creative writing
__/   | http://www.hjp.at/ |       challenge!"
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 833 bytes
Desc: not available
URL: <https://mail.python.org/pipermail/python-list/attachments/20230417/ccd296bb/attachment.sig>

From info at cmcc.it  Tue Apr 18 10:51:39 2023
From: info at cmcc.it (info cmcc)
Date: Tue, 18 Apr 2023 16:51:39 +0200
Subject: Scientific Software Developer for the Digital Twin of the Ocean | Job
 position at CMCC Foundation, Italy
In-Reply-To: <CA+-poFK0K5iK43SiQn6JAmyoHh9DMROxFxtGtPrU0PbQ4Zx=1g@mail.gmail.com>
References: <CA+-poF+LHxdJtXQLsTLe2=Wh-UCEPUtb-wktbc+-PT702Uf=aw@mail.gmail.com>
 <CA+-poF+vCUJ_Fc+UWhs9NkPyiFH4Jj=co6hK7QuP6mmyN0M1vg@mail.gmail.com>
 <CA+-poFK0K5iK43SiQn6JAmyoHh9DMROxFxtGtPrU0PbQ4Zx=1g@mail.gmail.com>
Message-ID: <CA+-poFJ8wZ4N3KApGHPtjUSOvX9vqi+ivs6TazSy0g=amziSig@mail.gmail.com>

*SCIENTIFIC SOFTWARE DEVELOPER FOR THE DIGITAL TWIN OF THE OCEAN*
[Job Opening Code: 12443]
*Lecce (Italy) - Deadline: 30/04/2023*


Our Division of Advanced Scientific Computing (ASC Division) is considering
the possibility to hire a talented and proactive Post Degree candidate to
support CMCC research activities. The contract will be jointly funded by
CMCC and the HPC Training and Research for Earth Sciences (HPC-TRES)
program.

The job location is CMCC Headquarters in Lecce, Italy.

We are looking for a motivated person with the following requirements:

   - M.Sc. degree in Computer Science or Computer Engineering or equivalent
   fields;
   - 2+ years? experience in scientific software development;
   - Excellent knowledge of Python programming language;
   - Good knowledge of Python scientific (numpy, scipy, scikit-learn,
   pandas) and visualization (e.g., matplotlib) libraries;
   - Good theoretical knowledge of Machine Learning algorithms and
   techniques for regression and classification tasks;
   - Good knowledge of at least one Machine/Deep Learning framework (e.g.,
   TensorFlow, Keras, Pytorch);
   - Good capabilities in writing technical reports and scientific papers
   as well as documenting code;
   - Good knowledge of both written and spoken English language.

Additional preferred experience:

   - Experience with HPC systems
   - Experience in training ML models in distributed environments and
   corresponding strategies

Belonging to legally protected categories (ex L. 68/99) will constitute a
preferential condition.


*More details and info about HOW TO APPLY:*
https://cmccfoundation.applytojob.com/apply/vmml1qbN4W/12443-Scientific-Software-Developer-For-The-Digital-Twin-Of-The-Ocean?source=Our%20Career%20Page%20Widget


-- 

Fondazione CMCCCentro Euro-Mediterraneo sui Cambiamenti Climatici
Via Marco Biagi, 5 - 73100 Lecce
info at cmcc.it - www.cmcc.it

From kevinmwilson1956 at yahoo.com  Tue Apr 18 19:18:57 2023
From: kevinmwilson1956 at yahoo.com (Kevin M. Wilson)
Date: Tue, 18 Apr 2023 23:18:57 +0000 (UTC)
Subject: Pycharm IDE
References: <127255282.580618.1681859937764.ref@mail.yahoo.com>
Message-ID: <127255282.580618.1681859937764@mail.yahoo.com>

Greetings... Kevin here:I need help, as you have guessed!I have this line: The Print Statement... Why complain about a 'comma', or a ')'???def play_game():
    number = random.randint(1, LIMIT)
    print (f'"I am thinking of a number between 1 to {LIMIT}\n")Or is this a setting in the IDE, I need to reassign?

Regards, Perplexed
"When you pass through the waters, I will be with you: and when you?pass through the rivers, they will not sweep over?you. When?you walk?through the fire, you will not be burned: the flames will not set you ablaze."? ? ? 
Isaiah 43:2

|  | Virus-free.www.avg.com |


From PythonList at DancesWithMice.info  Tue Apr 18 20:02:33 2023
From: PythonList at DancesWithMice.info (dn)
Date: Wed, 19 Apr 2023 12:02:33 +1200
Subject: Pycharm IDE
In-Reply-To: <127255282.580618.1681859937764@mail.yahoo.com>
References: <127255282.580618.1681859937764.ref@mail.yahoo.com>
 <127255282.580618.1681859937764@mail.yahoo.com>
Message-ID: <61cbbdd9-0b3c-bf38-95ea-f4d521d78e5a@DancesWithMice.info>

On 19/04/2023 11.18, Kevin M. Wilson via Python-list wrote:
> Greetings... Kevin here:I need help, as you have guessed!I have this line: The Print Statement... Why complain about a 'comma', or a ')'???def play_game():
>      number = random.randint(1, LIMIT)
>      print (f'"I am thinking of a number between 1 to {LIMIT}\n")Or is this a setting in the IDE, I need to reassign?

The code is a bit difficult to read (wrapping), but the error message 
may be an assumption (on Python's part).

Should the line be:

     print( F"I am thinking...
             ^
no extraneous/unbalanced apostrophe here?

-- 
Regards,
=dn

From list1 at tompassin.net  Tue Apr 18 19:48:12 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Tue, 18 Apr 2023 19:48:12 -0400
Subject: Pycharm IDE
In-Reply-To: <127255282.580618.1681859937764@mail.yahoo.com>
References: <127255282.580618.1681859937764.ref@mail.yahoo.com>
 <127255282.580618.1681859937764@mail.yahoo.com>
Message-ID: <60c5a5c1-5434-1d8e-8322-a4022d906075@tompassin.net>

On 4/18/2023 7:18 PM, Kevin M. Wilson via Python-list wrote:
> Greetings... Kevin here:I need help, as you have guessed!I have this line: The Print Statement... Why complain about a 'comma', or a ')'???def play_game():
>      number = random.randint(1, LIMIT)
>      print (f'"I am thinking of a number between 1 to {LIMIT}\n")Or is this a setting in the IDE, I need to reassign?

I'm not sure what error you are talking about, but the f-string isn't 
closed (and doesn't appear to need the double quotes, either, though 
that is not an error).  So -

print (f'I am thinking of a number between 1 to {LIMIT}')

(print() will add its own newline at the end so you don't need the \n 
unless you actually want another newline).

Next time, please include the actual error message and make sure you 
include line breaks so things don't run together.

> 
> Regards, Perplexed
> "When you pass through the waters, I will be with you: and when you?pass through the rivers, they will not sweep over?you. When?you walk?through the fire, you will not be burned: the flames will not set you ablaze."
> Isaiah 43:2
> 
> |  | Virus-free.www.avg.com |
> 


From aapost at idontexist.club  Tue Apr 18 20:02:49 2023
From: aapost at idontexist.club (aapost)
Date: Tue, 18 Apr 2023 20:02:49 -0400
Subject: Pycharm IDE
In-Reply-To: <mailman.118.1681859944.20750.python-list@python.org>
References: <127255282.580618.1681859937764.ref@mail.yahoo.com>
 <127255282.580618.1681859937764@mail.yahoo.com>
 <mailman.118.1681859944.20750.python-list@python.org>
Message-ID: <u1nb39$2m5i$1@nnrp.usenet.blueworldhosting.com>

On 4/18/23 19:18, Kevin M. Wilson wrote:
>Why complain about a 'comma', or a ')'???
>      print (f'"I am thinking of a number between 1 to {LIMIT}\n")

my version says it expects ' first (to close the fstring)
then on a new line below it, it mentions the comma and )
I believe that is just showing you after ' it expects you to end the 
print with ) as you have
or , to add additional arguments to print

From kevinmwilson1956 at yahoo.com  Wed Apr 19 01:16:00 2023
From: kevinmwilson1956 at yahoo.com (Kevin M. Wilson)
Date: Wed, 19 Apr 2023 05:16:00 +0000 (UTC)
Subject: Pycharm IDE
In-Reply-To: <u1nb39$2m5i$1@nnrp.usenet.blueworldhosting.com>
References: <127255282.580618.1681859937764.ref@mail.yahoo.com>
 <127255282.580618.1681859937764@mail.yahoo.com>
 <mailman.118.1681859944.20750.python-list@python.org>
 <u1nb39$2m5i$1@nnrp.usenet.blueworldhosting.com>
Message-ID: <1155066518.688499.1681881360098@mail.yahoo.com>

print (f'"I am thinking of a number between 1 to {LIMIT}\n")I had the impression that the format specifier 'f' was necessary for the print function, but the double quotes are for the string printed to the user, as a prompt!The Pycharm IDE is showing that it expects a single quotation mark or ')'! No error message is displayed.
Perplexed
"When you pass through the waters, I will be with you: and when you?pass through the rivers, they will not sweep over?you. When?you walk?through the fire, you will not be burned: the flames will not set you ablaze."? ? ? 
Isaiah 43:2 

    On Tuesday, April 18, 2023 at 06:44:37 PM MDT, aapost <aapost at idontexist.club> wrote:  
 
 On 4/18/23 19:18, Kevin M. Wilson wrote:
>Why complain about a 'comma', or a ')'???
>? ? ? print (f'"I am thinking of a number between 1 to {LIMIT}\n")

my version says it expects ' first (to close the fstring)
then on a new line below it, it mentions the comma and )
I believe that is just showing you after ' it expects you to end the 
print with ) as you have
or , to add additional arguments to print
-- 
https://mail.python.org/mailman/listinfo/python-list
  

|  | Virus-free.www.avg.com |


From kevinmwilson1956 at yahoo.com  Wed Apr 19 01:27:56 2023
From: kevinmwilson1956 at yahoo.com (Kevin M. Wilson)
Date: Wed, 19 Apr 2023 05:27:56 +0000 (UTC)
Subject: Pycharm IDE
In-Reply-To: <1155066518.688499.1681881360098@mail.yahoo.com>
References: <127255282.580618.1681859937764.ref@mail.yahoo.com>
 <127255282.580618.1681859937764@mail.yahoo.com>
 <mailman.118.1681859944.20750.python-list@python.org>
 <u1nb39$2m5i$1@nnrp.usenet.blueworldhosting.com>
 <1155066518.688499.1681881360098@mail.yahoo.com>
Message-ID: <1242860619.686995.1681882076134@mail.yahoo.com>

Ok, I got rid of the "print (f'"I am thinking of a number between 1 to {LIMIT}\n")"print ("I am thinking of a number between 1 to {LIMIT}\n"),
and Pycharm stopped complaining about it... WHY??
Perplexed
"When you pass through the waters, I will be with you: and when you?pass through the rivers, they will not sweep over?you. When?you walk?through the fire, you will not be burned: the flames will not set you ablaze."? ? ? 
Isaiah 43:2 

    On Tuesday, April 18, 2023 at 11:17:52 PM MDT, Kevin M. Wilson via Python-list <python-list at python.org> wrote:  
 
 print (f'"I am thinking of a number between 1 to {LIMIT}\n")I had the impression that the format specifier 'f' was necessary for the print function, but the double quotes are for the string printed to the user, as a prompt!The Pycharm IDE is showing that it expects a single quotation mark or ')'! No error message is displayed.
Perplexed
"When you pass through the waters, I will be with you: and when you?pass through the rivers, they will not sweep over?you. When?you walk?through the fire, you will not be burned: the flames will not set you ablaze."? ? ? 
Isaiah 43:2 

? ? On Tuesday, April 18, 2023 at 06:44:37 PM MDT, aapost <aapost at idontexist.club> wrote:? 
 
 On 4/18/23 19:18, Kevin M. Wilson wrote:
>Why complain about a 'comma', or a ')'???
>? ? ? print (f'"I am thinking of a number between 1 to {LIMIT}\n")

my version says it expects ' first (to close the fstring)
then on a new line below it, it mentions the comma and )
I believe that is just showing you after ' it expects you to end the 
print with ) as you have
or , to add additional arguments to print
-- 
https://mail.python.org/mailman/listinfo/python-list
? 

|? | Virus-free.www.avg.com |

-- 
https://mail.python.org/mailman/listinfo/python-list
  

|  | Virus-free.www.avg.com |


From PythonList at DancesWithMice.info  Wed Apr 19 03:17:03 2023
From: PythonList at DancesWithMice.info (dn)
Date: Wed, 19 Apr 2023 19:17:03 +1200
Subject: Pycharm IDE
In-Reply-To: <1242860619.686995.1681882076134@mail.yahoo.com>
References: <127255282.580618.1681859937764.ref@mail.yahoo.com>
 <127255282.580618.1681859937764@mail.yahoo.com>
 <mailman.118.1681859944.20750.python-list@python.org>
 <u1nb39$2m5i$1@nnrp.usenet.blueworldhosting.com>
 <1155066518.688499.1681881360098@mail.yahoo.com>
 <1242860619.686995.1681882076134@mail.yahoo.com>
Message-ID: <0e119db8-996d-d545-5435-566ade5433f1@DancesWithMice.info>

Kevin,

As mentioned in another response, the format of these messages seems 
very confused.

Please copy-paste all of (the pertinent part of) the code, and ensure 
that the line-endings are in the correct places, tab/indentation looks 
correct, etc?
(this will allow us to copy the same code into our PyCharm software and 
see what is happening!)

There still appears to be both an apostrophe (') and quotation-marks 
("). Do you want the user to see one/both?

There was mention of this being an input prompt - hence the 
question-mark. Are you aware that this could be done as part of the 
input() function?

How about creating a string and then printing that, eg

prompt = f'"I am thinking of a number between 1 to {LIMIT}"
print( prompt )

NB because of the question asked earlier, the above code is NOT 
syntactically-correct Python!
NBB am assuming there's previous code which defines LIMIT



On 19/04/2023 17.27, Kevin M. Wilson via Python-list wrote:
> Ok, I got rid of the "print (f'"I am thinking of a number between 1 to {LIMIT}\n")"print ("I am thinking of a number between 1 to {LIMIT}\n"),
> and Pycharm stopped complaining about it... WHY??
> Perplexed
> "When you pass through the waters, I will be with you: and when you?pass through the rivers, they will not sweep over?you. When?you walk?through the fire, you will not be burned: the flames will not set you ablaze."
> Isaiah 43:2
> 
>      On Tuesday, April 18, 2023 at 11:17:52 PM MDT, Kevin M. Wilson via Python-list <python-list at python.org> wrote:
>   
>   print (f'"I am thinking of a number between 1 to {LIMIT}\n")I had the impression that the format specifier 'f' was necessary for the print function, but the double quotes are for the string printed to the user, as a prompt!The Pycharm IDE is showing that it expects a single quotation mark or ')'! No error message is displayed.
> Perplexed
> "When you pass through the waters, I will be with you: and when you?pass through the rivers, they will not sweep over?you. When?you walk?through the fire, you will not be burned: the flames will not set you ablaze."
> Isaiah 43:2
> 
>  ? ? On Tuesday, April 18, 2023 at 06:44:37 PM MDT, aapost <aapost at idontexist.club> wrote:
>   
>   On 4/18/23 19:18, Kevin M. Wilson wrote:
>> Why complain about a 'comma', or a ')'???
>>  ? ? ? print (f'"I am thinking of a number between 1 to {LIMIT}\n")
> 
> my version says it expects ' first (to close the fstring)
> then on a new line below it, it mentions the comma and )
> I believe that is just showing you after ' it expects you to end the
> print with ) as you have
> or , to add additional arguments to print

-- 
Regards,
=dn

From PythonList at DancesWithMice.info  Wed Apr 19 05:33:19 2023
From: PythonList at DancesWithMice.info (dn)
Date: Wed, 19 Apr 2023 21:33:19 +1200
Subject: Pycharm IDE
In-Reply-To: <1057815704.182764.1681895608091@mail.yahoo.com>
References: <127255282.580618.1681859937764.ref@mail.yahoo.com>
 <127255282.580618.1681859937764@mail.yahoo.com>
 <mailman.118.1681859944.20750.python-list@python.org>
 <u1nb39$2m5i$1@nnrp.usenet.blueworldhosting.com>
 <1155066518.688499.1681881360098@mail.yahoo.com>
 <1242860619.686995.1681882076134@mail.yahoo.com>
 <0e119db8-996d-d545-5435-566ade5433f1@DancesWithMice.info>
 <1057815704.182764.1681895608091@mail.yahoo.com>
Message-ID: <dab31304-5c08-2b9a-1d64-40e202ba3d2e@DancesWithMice.info>

On 19/04/2023 21.13, Kevin M. Wilson wrote:
> Sorry the code snippet I sent was what is written in PyCharm. LIMIT is 
> defined and is not causing an error!
> PyCharm is flagging the Parentheses at the end. It is not seeing the 
> Parentheses as the end of the print function.
> 
> def play_game():
> number= random.randint(1, LIMIT)
>      print (f'"I am thinking of a number between 1 to {LIMIT}\n")
> 
> Observe... Look at the color of the parenthesis, it's green!!!
> !!! = WTH


Same question!

Please explain: why is there a (single) apostrophe?

NB some email clients don't notice list communications and ReplyList - 
you may need to do that manually...

-- 
Regards,
=dn


From list1 at tompassin.net  Wed Apr 19 08:33:21 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Wed, 19 Apr 2023 08:33:21 -0400
Subject: Pycharm IDE
In-Reply-To: <1242860619.686995.1681882076134@mail.yahoo.com>
References: <127255282.580618.1681859937764.ref@mail.yahoo.com>
 <127255282.580618.1681859937764@mail.yahoo.com>
 <mailman.118.1681859944.20750.python-list@python.org>
 <u1nb39$2m5i$1@nnrp.usenet.blueworldhosting.com>
 <1155066518.688499.1681881360098@mail.yahoo.com>
 <1242860619.686995.1681882076134@mail.yahoo.com>
Message-ID: <152fb9fa-ce51-ad2f-c18c-a2052130e00b@tompassin.net>

On 4/19/2023 1:27 AM, Kevin M. Wilson via Python-list wrote:
> Ok, I got rid of the "print (f'"I am thinking of a number between 1 to {LIMIT}\n")"print ("I am thinking of a number between 1 to {LIMIT}\n"),

I think you misunderstand several things at the same time here.

1. These errors originate from syntax errors.  They are basically Python 
errors.  It's possible that behind the scenes, PyCharm is running one or 
another Python program to detect them, but they are errors in your 
Python code.

2. print() doesn't care whether you give it an f-string or not, because 
a f-string is a string too.

3. All strings need to be closed with the same kind of quote they 
started with.  If one is not closed, then Python thinks the string is 
supposed to continue, and - say- the final parenthesis of the print() 
function looks like it is part of the string. So Python (or PyCharm) 
notices that the closing parenthesis of the print() expression is missing.

4. in an f-string, the expression in braces is evaluated and replaced by 
its string value.  So if you try to do this

print('{LIMIT}')

then that will be printed as is with no  substitution - because it is 
not an f-string.  So you will see "{LIMIT}" But you thought you were 
going to see "42" (if LIMIT == 42, that is). OTOH,

print(f'{LIMIT})

will substitute the string value of LIMIT before printing the string. 
Both are legitimate but the first is not what you seem to want.

5. As I posted earlier, you almost certainly do not need to add the "\n".

So, some suggestions:

- If you are having a problem with some piece of code, try to simplify 
it down to the smallest bit that shows the problem.

- If you are having trouble with f-strings, then think about what you 
want to achieve and look up information about f-strings with that in mind.

- If you are having trouble with the print statement, think what you 
want it to display and look up information about the print function with 
that in mind.

- If your tool - PyCharm in this case - is producing messages but you 
don't understand why they are being produced, try to look up information 
about how and when PyCharm produces error messages

Do you see a pattern here?

Also note that just because you don't see an error message does not mean 
that the code is correct.  It may be correct from the point of view of 
Python syntax but that doesn't mean that it will perform correctly nor 
how you expect.

> and Pycharm stopped complaining about it... WHY??
> Perplexed
> "When you pass through the waters, I will be with you: and when you?pass through the rivers, they will not sweep over?you. When?you walk?through the fire, you will not be burned: the flames will not set you ablaze."
> Isaiah 43:2
> 
>      On Tuesday, April 18, 2023 at 11:17:52 PM MDT, Kevin M. Wilson via Python-list <python-list at python.org> wrote:
>   
>   print (f'"I am thinking of a number between 1 to {LIMIT}\n")I had the impression that the format specifier 'f' was necessary for the print function, but the double quotes are for the string printed to the user, as a prompt!The Pycharm IDE is showing that it expects a single quotation mark or ')'! No error message is displayed.
> Perplexed
> "When you pass through the waters, I will be with you: and when you?pass through the rivers, they will not sweep over?you. When?you walk?through the fire, you will not be burned: the flames will not set you ablaze."
> Isaiah 43:2
> 
>  ? ? On Tuesday, April 18, 2023 at 06:44:37 PM MDT, aapost <aapost at idontexist.club> wrote:
>   
>   On 4/18/23 19:18, Kevin M. Wilson wrote:
>> Why complain about a 'comma', or a ')'???
>>  ? ? ? print (f'"I am thinking of a number between 1 to {LIMIT}\n")
> 
> my version says it expects ' first (to close the fstring)
> then on a new line below it, it mentions the comma and )
> I believe that is just showing you after ' it expects you to end the
> print with ) as you have
> or , to add additional arguments to print


From kevinmwilson1956 at yahoo.com  Wed Apr 19 05:51:24 2023
From: kevinmwilson1956 at yahoo.com (Kevin M. Wilson)
Date: Wed, 19 Apr 2023 09:51:24 +0000 (UTC)
Subject: PyCharm's strict PEP and not so strict?
References: <2110321349.5908606.1681897884162.ref@mail.yahoo.com>
Message-ID: <2110321349.5908606.1681897884162@mail.yahoo.com>

Greetings,????? ? ?I'm in a bit of a quandary, I want some strict syntax errors to be flagged, but the use of single quotes vs double quotes! NOT what I need from the 'checker', you dig? As I've recently returned to the IDE, and no longer have the
"stones" for bull, how do I set up the kind of "checking" I want?
Thank you, Kevin
"When you pass through the waters, I will be with you: and when you?pass through the rivers, they will not sweep over?you. When?you walk?through the fire, you will not be burned: the flames will not set you ablaze."? ? ? 
Isaiah 43:2

|  | Virus-free.www.avg.com |


From learn2program at gmail.com  Wed Apr 19 12:25:37 2023
From: learn2program at gmail.com (Alan Gauld)
Date: Wed, 19 Apr 2023 17:25:37 +0100
Subject: PyCharm's strict PEP and not so strict?
In-Reply-To: <2110321349.5908606.1681897884162@mail.yahoo.com>
References: <2110321349.5908606.1681897884162.ref@mail.yahoo.com>
 <2110321349.5908606.1681897884162@mail.yahoo.com>
Message-ID: <b36efc8f-7fcf-e646-57e1-1f008d8f719a@yahoo.co.uk>

On 19/04/2023 10:51, Kevin M. Wilson via Python-list wrote:
> ?I'm in a bit of a quandary, I want some strict syntax errors to be flagged,

OK, You might want to use a "linter" in that case because most
tools use the interpreter itself to flag syntax errors.


>  but the use of single quotes vs double quotes! 
> NOT what I need from the 'checker', you dig? 

Not really. What is the problem. Use of single versus double quotes
is straightforward - use one or the other and make sure they
match(opening and closing) You can nest one type inside the
other if you need literal quotes. And of course the same applies
to triple quotes except you can include newlines inside those.

What kind of problems are you experiencing with quotes?
If we have some specific examples we can give specific answers.

> "stones" for bull, how do I set up the kind of "checking" I want?

That's not a phrase with which I'm familiar but my guess
is you need to install a linter tool and then, possibly
configure it to flag or hide particular error/warning types
to your personal taste. Each tool is different so you
will need to read the docs on how to configure it
(and how to plumb it into your IDE).

Personally I've never felt the need for any stricter error
checking than the interpreter provides so I can't offer
anything beyond the generic suggestion to use a linter.

-- 
Alan G
Author of the Learn to Program web site
http://www.alan-g.me.uk/
http://www.amazon.com/author/alan_gauld
Follow my photo-blog on Flickr at:
http://www.flickr.com/photos/alangauldphotos



From PythonList at DancesWithMice.info  Wed Apr 19 13:37:33 2023
From: PythonList at DancesWithMice.info (dn)
Date: Thu, 20 Apr 2023 05:37:33 +1200
Subject: PyCharm's strict PEP and not so strict?
In-Reply-To: <b36efc8f-7fcf-e646-57e1-1f008d8f719a@yahoo.co.uk>
References: <2110321349.5908606.1681897884162.ref@mail.yahoo.com>
 <2110321349.5908606.1681897884162@mail.yahoo.com>
 <b36efc8f-7fcf-e646-57e1-1f008d8f719a@yahoo.co.uk>
Message-ID: <06af8d39-a128-27e6-eeb8-f9e3f8fde7b6@DancesWithMice.info>

On 20/04/2023 04.25, Alan Gauld wrote:
> On 19/04/2023 10:51, Kevin M. Wilson via Python-list wrote:
>>  ?I'm in a bit of a quandary, I want some strict syntax errors to be flagged,
> 
> OK, You might want to use a "linter" in that case because most
> tools use the interpreter itself to flag syntax errors.
> 
> 
>>   but the use of single quotes vs double quotes!
>> NOT what I need from the 'checker', you dig?
> 
> Not really. What is the problem. Use of single versus double quotes
> is straightforward - use one or the other and make sure they
> match(opening and closing) You can nest one type inside the
> other if you need literal quotes. And of course the same applies
> to triple quotes except you can include newlines inside those.
> 
> What kind of problems are you experiencing with quotes?
> If we have some specific examples we can give specific answers.
> 
>> "stones" for bull, how do I set up the kind of "checking" I want?
> 
> That's not a phrase with which I'm familiar but my guess
> is you need to install a linter tool and then, possibly
> configure it to flag or hide particular error/warning types
> to your personal taste. Each tool is different so you
> will need to read the docs on how to configure it
> (and how to plumb it into your IDE).
> 
> Personally I've never felt the need for any stricter error
> checking than the interpreter provides so I can't offer
> anything beyond the generic suggestion to use a linter.

+1

PyCharm enables a range of Python-linters. Some by add-in. Some by 
"External tools" 
(https://www.jetbrains.com/help/pycharm/configuring-third-party-tools.html).

Once a linter is made-available, some allow one to tune the application 
or relaxation of certain 'rules', eg whether commas in a comma-separated 
list are to be followed by a space.

Whether any enable the restriction of quotes use is another matter - 
probably for the reasons @Alan has already covered.

PyCharm auto-magically enters both an opening-quote and a closing-quote 
whenever start typing a string. The 'trick' is not to delete the close 
whilst editing.

After gaining experience, I have a convention of when to use apostrophes 
and when double-quotes. These old eyes dislike mixing both in a single 
expression - but sometimes it is the best course to follow.

YMMV!

-- 
Regards,
=dn

From bob1.250211 at outlook.com  Wed Apr 19 12:14:25 2023
From: bob1.250211 at outlook.com (charles wiewiora)
Date: Wed, 19 Apr 2023 16:14:25 +0000
Subject: Python-pickle error
Message-ID: <PAWPR03MB994760978DE511870B829299A9629@PAWPR03MB9947.eurprd03.prod.outlook.com>

Hello,
I am experincing problems with the pickle moducle
the folowing code was working before,

import pickle
number=2
my_pickeld_object=pickle.dumps(number)
print("this is my pickled object",{my_pickeld_object},)
with open('file.pkl', 'rb') as file:
    number=pickle.load(file)
my_unpickeled_object=pickle.loads(my_pickeld_object)
print("this is my unpickeled object",{my_unpickeled_object},)

but now i get error

Traceback (most recent call last):
  File "C:\Users\lukwi\Desktop\python\tester2.py", line 5, in <module>
    with open('file.pkl', 'rb') as file:
FileNotFoundError: [Errno 2] No such file or directory: 'file.pkl'

im get this problem after this,
a .pkl came into my Python script files
i though this could be a spare file made from python becauce i was doing this first,

import pickle
number=2
my_pickeld_object=pickle.dumps(number)
print("this is my pickled object",{my_pickeld_object},)
with open('file.pkl', 'rb') as file:
    number=pickle.load(file)

so i stupidly deleted the file

do you know how to fix this?
i reinstalled it but it didn't work
this is on widnows and on version 3.11.3 on python

thank you

From nntp.mbourne at spamgourmet.com  Wed Apr 19 16:06:18 2023
From: nntp.mbourne at spamgourmet.com (Mark Bourne)
Date: Wed, 19 Apr 2023 21:06:18 +0100
Subject: Pycharm IDE
In-Reply-To: <mailman.125.1681907634.20750.python-list@python.org>
References: <127255282.580618.1681859937764.ref@mail.yahoo.com>
 <127255282.580618.1681859937764@mail.yahoo.com>
 <mailman.118.1681859944.20750.python-list@python.org>
 <u1nb39$2m5i$1@nnrp.usenet.blueworldhosting.com>
 <1155066518.688499.1681881360098@mail.yahoo.com>
 <1242860619.686995.1681882076134@mail.yahoo.com>
 <152fb9fa-ce51-ad2f-c18c-a2052130e00b@tompassin.net>
 <mailman.125.1681907634.20750.python-list@python.org>
Message-ID: <u1phjq$5tni$2@dont-email.me>

Thomas Passin wrote:
> On 4/19/2023 1:27 AM, Kevin M. Wilson via Python-list wrote:
>> Ok, I got rid of the "print (f'"I am thinking of a number between 1 to 
>> {LIMIT}\n")"print ("I am thinking of a number between 1 to {LIMIT}\n"),
> 
> I think you misunderstand several things at the same time here.
> 
> 1. These errors originate from syntax errors.? They are basically Python 
> errors.? It's possible that behind the scenes, PyCharm is running one or 
> another Python program to detect them, but they are errors in your 
> Python code.
> 
> 2. print() doesn't care whether you give it an f-string or not, because 
> a f-string is a string too.
> 
> 3. All strings need to be closed with the same kind of quote they 
> started with.? If one is not closed, then Python thinks the string is 
> supposed to continue, and - say- the final parenthesis of the print() 
> function looks like it is part of the string. So Python (or PyCharm) 
> notices that the closing parenthesis of the print() expression is missing.
> 
> 4. in an f-string, the expression in braces is evaluated and replaced by 
> its string value.? So if you try to do this
> 
> print('{LIMIT}')
> 
> then that will be printed as is with no? substitution - because it is 
> not an f-string.? So you will see "{LIMIT}" But you thought you were 
> going to see "42" (if LIMIT == 42, that is). OTOH,
> 
> print(f'{LIMIT})

^ I think this one should be:

print(f'{LIMIT}')

with the closing quote ;o)

> will substitute the string value of LIMIT before printing the string. 
> Both are legitimate but the first is not what you seem to want.
> 
> 5. As I posted earlier, you almost certainly do not need to add the "\n".
> 
> So, some suggestions:
> 
> - If you are having a problem with some piece of code, try to simplify 
> it down to the smallest bit that shows the problem.
> 
> - If you are having trouble with f-strings, then think about what you 
> want to achieve and look up information about f-strings with that in mind.
> 
> - If you are having trouble with the print statement, think what you 
> want it to display and look up information about the print function with 
> that in mind.
> 
> - If your tool - PyCharm in this case - is producing messages but you 
> don't understand why they are being produced, try to look up information 
> about how and when PyCharm produces error messages
> 
> Do you see a pattern here?
> 
> Also note that just because you don't see an error message does not mean 
> that the code is correct.? It may be correct from the point of view of 
> Python syntax but that doesn't mean that it will perform correctly nor 
> how you expect.
> 
>> and Pycharm stopped complaining about it... WHY??
>> Perplexed
>> "When you pass through the waters, I will be with you: and when 
>> you?pass through the rivers, they will not sweep over?you. When?you 
>> walk?through the fire, you will not be burned: the flames will not set 
>> you ablaze."
>> Isaiah 43:2
>>
>> ???? On Tuesday, April 18, 2023 at 11:17:52 PM MDT, Kevin M. Wilson 
>> via Python-list <python-list at python.org> wrote:
>> ? print (f'"I am thinking of a number between 1 to {LIMIT}\n")I had 
>> the impression that the format specifier 'f' was necessary for the 
>> print function, but the double quotes are for the string printed to 
>> the user, as a prompt!The Pycharm IDE is showing that it expects a 
>> single quotation mark or ')'! No error message is displayed.
>> Perplexed
>> "When you pass through the waters, I will be with you: and when 
>> you?pass through the rivers, they will not sweep over?you. When?you 
>> walk?through the fire, you will not be burned: the flames will not set 
>> you ablaze."
>> Isaiah 43:2
>>
>> ?? ? On Tuesday, April 18, 2023 at 06:44:37 PM MDT, aapost 
>> <aapost at idontexist.club> wrote:
>> ? On 4/18/23 19:18, Kevin M. Wilson wrote:
>>> Why complain about a 'comma', or a ')'???
>>> ?? ? ? print (f'"I am thinking of a number between 1 to {LIMIT}\n")
>>
>> my version says it expects ' first (to close the fstring)
>> then on a new line below it, it mentions the comma and )
>> I believe that is just showing you after ' it expects you to end the
>> print with ) as you have
>> or , to add additional arguments to print
> 

From list1 at tompassin.net  Wed Apr 19 16:59:51 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Wed, 19 Apr 2023 16:59:51 -0400
Subject: Pycharm IDE
In-Reply-To: <u1phjq$5tni$2@dont-email.me>
References: <127255282.580618.1681859937764.ref@mail.yahoo.com>
 <127255282.580618.1681859937764@mail.yahoo.com>
 <mailman.118.1681859944.20750.python-list@python.org>
 <u1nb39$2m5i$1@nnrp.usenet.blueworldhosting.com>
 <1155066518.688499.1681881360098@mail.yahoo.com>
 <1242860619.686995.1681882076134@mail.yahoo.com>
 <152fb9fa-ce51-ad2f-c18c-a2052130e00b@tompassin.net>
 <mailman.125.1681907634.20750.python-list@python.org>
 <u1phjq$5tni$2@dont-email.me>
Message-ID: <7c7354d4-58fd-38e1-1c34-9587be89de83@tompassin.net>

On 4/19/2023 4:06 PM, Mark Bourne wrote:
>>
>> print(f'{LIMIT})
> 
> ^ I think this one should be:
> 
> print(f'{LIMIT}')
> 
> with the closing quote ;o)

Yup a typo!  Where's pylint when I need it?


From list1 at tompassin.net  Wed Apr 19 17:12:04 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Wed, 19 Apr 2023 17:12:04 -0400
Subject: Python-pickle error
In-Reply-To: <PAWPR03MB994760978DE511870B829299A9629@PAWPR03MB9947.eurprd03.prod.outlook.com>
References: <PAWPR03MB994760978DE511870B829299A9629@PAWPR03MB9947.eurprd03.prod.outlook.com>
Message-ID: <eae761f1-5a3b-ddaa-e344-ce9493f942e3@tompassin.net>

On 4/19/2023 12:14 PM, charles wiewiora wrote:
> Hello,
> I am experincing problems with the pickle moducle
> the folowing code was working before,
> 
> import pickle
> number=2
> my_pickeld_object=pickle.dumps(number)
> print("this is my pickled object",{my_pickeld_object},)
> with open('file.pkl', 'rb') as file:
>      number=pickle.load(file)
> my_unpickeled_object=pickle.loads(my_pickeld_object)
> print("this is my unpickeled object",{my_unpickeled_object},)
> 
> but now i get error
> 
> Traceback (most recent call last):
>    File "C:\Users\lukwi\Desktop\python\tester2.py", line 5, in <module>
>      with open('file.pkl', 'rb') as file:
> FileNotFoundError: [Errno 2] No such file or directory: 'file.pkl'

That's because you haven't saved anything to a file named "file.pkl". If 
this code seemed to work in the past, it may have been because there was 
a file named "file.pkl" left over from some previous experiment.  But 
it's not there now, and even if it were it would not contain your 
current pickled object.

Take a look at .load() and .dump() (instead of .loads() and .dumps(). 
Maybe they will do what you want a little easier.

> im get this problem after this,
> a .pkl came into my Python script files
> i though this could be a spare file made from python becauce i was doing this first,
> 
> import pickle
> number=2
> my_pickeld_object=pickle.dumps(number)
> print("this is my pickled object",{my_pickeld_object},)
> with open('file.pkl', 'rb') as file:
>      number=pickle.load(file)
> 
> so i stupidly deleted the file
> 
> do you know how to fix this?
> i reinstalled it but it didn't work
> this is on widnows and on version 3.11.3 on python
> 
> thank you


From PythonList at DancesWithMice.info  Wed Apr 19 19:19:43 2023
From: PythonList at DancesWithMice.info (dn)
Date: Thu, 20 Apr 2023 11:19:43 +1200
Subject: PyCharm's strict PEP and not so strict?
In-Reply-To: <692943468.6227351.1681935070220@mail.yahoo.com>
References: <2110321349.5908606.1681897884162.ref@mail.yahoo.com>
 <2110321349.5908606.1681897884162@mail.yahoo.com>
 <b36efc8f-7fcf-e646-57e1-1f008d8f719a@yahoo.co.uk>
 <06af8d39-a128-27e6-eeb8-f9e3f8fde7b6@DancesWithMice.info>
 <692943468.6227351.1681935070220@mail.yahoo.com>
Message-ID: <949d6719-a06b-6dcf-9aa5-6d6497c38060@DancesWithMice.info>

NB this reply came only to me (so @Alan will have missed your response 
to his posting). Have replied on-list (only) - please see earlier 
comment about email-client behaviors...


On 20/04/2023 08.11, Kevin M. Wilson wrote:
> *What kind of problems are you experiencing with quotes?*
> If we have some specific examples we can give specific answers.
> 
> /I have an issue with the 'Light Blub', if I wanted suggestions I'd turn 
> on that option... Assuming it's an option!/

The "light bulb" has little to do with "quotes"! This is one of the 
advantages of utilising a Python-native IDE (cf a more general-purpose 
alternative, perhaps with some Python add-on). PyCharm attempts to 
understand the code it is editing, and apply various lessons or 
experiences to offer intelligent assistance.

Thus, the "light bulb" is an icon indicating that PyCharm had spotted 
one or more "intention actions". These may be faults in the code, or may 
be anticipating what you're about to do and offering to do it for you. A 
red light-bulb indicates that there is an error in the Python code. 
Whereas, the yellow color indicates opportunity, aka "a light-bulb 
moment". Hah!

Yes, there are times when the icon overlays and obstructs the code, and 
thus irritates. I believe it can be turned-off (but don't recommend such 
to coders at your level of skill). Please read the manual, specifically 
that page 
(https://www.jetbrains.com/help/pycharm/intention-actions.html) - 
there's even an F-string code-example!

In this case, PyCharm undoubtedly was picking-up that the string was 
opened by a single-quote but never closed. One of the useful options 
PyCharm suggests in this case, is to presume that the string is longer 
than will fit on one line, and it will 'break' the string for you/us and 
ensure that the correct punctuation is placed at the beginning and end 
of each fragment of the string - something many of us find either 
slightly confusing or a nuisance of 'boiler-plate'.

To see what it has noticed, the alternative actions are to mouse-click 
on the light-bulb, or to type Alt+Enter. Interestingly, the latter is 
called "Show Context Actions" (but is still talking about "Intentions". 
The description reads "Quick-fixes for highlighted errors and warnings, 
intention actions for improving and optimizing your code." 
(https://www.jetbrains.com/help/pycharm/mastering-keyboard-shortcuts.html)

You may have noticed some indicators/statistics at the top-right of the 
editing panel. Green ticks/check-marks, and amber/yellow or red 
caution-triangles. These similarly indicate problems PyCharm has 
noticed, or wisdom from which you may choose to benefit. These come from 
a feature called "inspection". There are some controls enabling 
adjustment of "inspection severity" 
(https://www.jetbrains.com/help/pycharm/configuring-inspection-severities.html) 
which may be worth the reading-time. However, and once again, changing 
any cannot be recommended to someone at an early stage of Python-experience.


> *Not really. What is the problem. Use of single versus double quotes?is 
> straightforward - use one or the other and make sure they?match(opening 
> and closing) You can nest one type inside the
> other if you need literal quotes. And of course the same applies?to 
> triple quotes except you can include newlines inside those.*
> *
> *
> Not stupid typing... Thanks! I use Double quotes, the light blub 
> suggestions aren't, in many cases, relevant to my
> style of coding, nor of 'english'... I'd like to set my options!

Sadly this wouldn't help!

If you (can) turn-off such warnings in PyCharm, it will simply delay the 
inevitable - when the code is executed Python will object to the opening 
of a single-quote and not finding its matching close.
ie the issue is NOT with PyCharm (nor with Python) but ...


> *PyCharm enables a range of Python-linters. Some by add-in. Some by
> "External tools"*
> 
> I was not 'up' on "linters", Thanks for the heads up! Attempted finding 
> a "linter" on jetbrains... I take it that finding a 'linter' for Build 
> #PC-222.4554.11, built on March 15, 2023
> Is a matter of hit and miss... Any suggestions?

Try a web-search for "Python linters". Linters, I've know a few... (hum 
along with the music...) have long been a part of the Python eco-system. 
They have usually been designed to run from Python or 'the 
command-line'. Accordingly, many can be added into PyCharm from 'the 
outside'.

The original purpose was possibly to guide/nudge coders into the 
practices recommended by PEP-008 (https://peps.python.org/pep-0008/). 
This, as you will read, is not about syntax, but more about coding "style".

There are many to choose from. Some are more strict than others. 
Recommendation: (for the good of your blood-pressure) stay away from 
"highly opinionated" alternatives, such as Black. Try the ones which 
offer options to turn-on/-off particular situations (as described earlier).


> "stones" for bull, how do I set up the kind of "checking" I want?
> 
> That's not a phrase with which I'm familiar but my guess?is you need to 
> install a linter tool and then, possibly?configure it to flag or hide 
> particular error/warning types?to your personal taste. Each tool is 
> different so you?will need to read the docs on how to configure it?(and 
> how to plumb it into your IDE).
> 
> Sorry, at 67 I use the idioms of many eras! "Stones", 'balls'...

Let's try to dispute another old saw - the one about "old dogs"...
Then there's "slowly, slowly, catchee..."
(but all of these are probably regarded as 'politically incorrect', and 
anything disrespectful of others transgresses the Python Code of 
Conduct, so let's park 'the attitude' right there)

@Alan is an accomplished author - even if more familiar with British 
slang, rather than Spanish 'translations'. This list is blessed by 
contributions from people from all around the globe. Accordingly, 
there'll be many who are unable to understand your/my aphorisms and 
allusions. Hence trying to stay with a more 'international English'.


> "When you pass through the waters, I will be with you: and when you?pass 
> through the rivers, they will not sweep over?you. When?you walk?through 
> the fire, you will not be burned: the flames will not set you ablaze."
> *Isaiah 43:2*
> 
> 
> On Wednesday, April 19, 2023 at 11:39:36 AM MDT, dn via Python-list 
> <python-list at python.org> wrote:
> 
> 
> On 20/04/2023 04.25, Alan Gauld wrote:
>  > On 19/04/2023 10:51, Kevin M. Wilson via Python-list wrote:
>  >>? ?I'm in a bit of a quandary, I want some strict syntax errors to be 
> flagged,
>  >
>  > OK, You might want to use a "linter" in that case because most
>  > tools use the interpreter itself to flag syntax errors.
>  >
>  >
>  >>? but the use of single quotes vs double quotes!
>  >> NOT what I need from the 'checker', you dig?
>  >
>  > Not really. What is the problem. Use of single versus double quotes
>  > is straightforward - use one or the other and make sure they
>  > match(opening and closing) You can nest one type inside the
>  > other if you need literal quotes. And of course the same applies
>  > to triple quotes except you can include newlines inside those.
>  >
>  > What kind of problems are you experiencing with quotes?
>  > If we have some specific examples we can give specific answers.
>  >
>  >> "stones" for bull, how do I set up the kind of "checking" I want?
>  >
>  > That's not a phrase with which I'm familiar but my guess
>  > is you need to install a linter tool and then, possibly
>  > configure it to flag or hide particular error/warning types
>  > to your personal taste. Each tool is different so you
>  > will need to read the docs on how to configure it
>  > (and how to plumb it into your IDE).
>  >
>  > Personally I've never felt the need for any stricter error
>  > checking than the interpreter provides so I can't offer
>  > anything beyond the generic suggestion to use a linter.
> 
> 
> +1
> 
> 
> PyCharm enables a range of Python-linters. Some by add-in. Some by
> "External tools"
> (https://www.jetbrains.com/help/pycharm/configuring-third-party-tools.html).
> 
> Once a linter is made-available, some allow one to tune the application
> or relaxation of certain 'rules', eg whether commas in a comma-separated
> list are to be followed by a space.
> 
> Whether any enable the restriction of quotes use is another matter -
> probably for the reasons @Alan has already covered.
> 
> PyCharm auto-magically enters both an opening-quote and a closing-quote
> whenever start typing a string. The 'trick' is not to delete the close
> whilst editing.
> 
> After gaining experience, I have a convention of when to use apostrophes
> and when double-quotes. These old eyes dislike mixing both in a single
> expression - but sometimes it is the best course to follow.
> 
> YMMV!
> 
> -- 
> Regards,
> =dn
> -- 
> https://mail.python.org/mailman/listinfo/python-list 
> <https://mail.python.org/mailman/listinfo/python-list>
> 
> 
> <http://www.avg.com/email-signature?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=webmail>	Virus-free.www.avg.com <http://www.avg.com/email-signature?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=webmail>
> 
> <#DAB4FAD8-2DD7-40BB-A1B8-4E2AA1F9FDF2>

-- 
Regards,
=dn


From PythonList at DancesWithMice.info  Wed Apr 19 19:48:30 2023
From: PythonList at DancesWithMice.info (dn)
Date: Thu, 20 Apr 2023 11:48:30 +1200
Subject: Pycharm IDE
In-Reply-To: <7c7354d4-58fd-38e1-1c34-9587be89de83@tompassin.net>
References: <127255282.580618.1681859937764.ref@mail.yahoo.com>
 <127255282.580618.1681859937764@mail.yahoo.com>
 <mailman.118.1681859944.20750.python-list@python.org>
 <u1nb39$2m5i$1@nnrp.usenet.blueworldhosting.com>
 <1155066518.688499.1681881360098@mail.yahoo.com>
 <1242860619.686995.1681882076134@mail.yahoo.com>
 <152fb9fa-ce51-ad2f-c18c-a2052130e00b@tompassin.net>
 <mailman.125.1681907634.20750.python-list@python.org>
 <u1phjq$5tni$2@dont-email.me>
 <7c7354d4-58fd-38e1-1c34-9587be89de83@tompassin.net>
Message-ID: <55435ecb-8e89-bef5-519b-85e27cc4ddf8@DancesWithMice.info>

On 20/04/2023 08.59, Thomas Passin wrote:
> On 4/19/2023 4:06 PM, Mark Bourne wrote:
>>>
>>> print(f'{LIMIT})
>>
>> ^ I think this one should be:
>>
>> print(f'{LIMIT}')
>>
>> with the closing quote ;o)
> 
> Yup a typo!? Where's pylint when I need it?

but (and you designed it this way - right?) an excellent object-lesson 
for the OP

AND

great rationale for why linters are so handy!


I am bullish on F-strings, but they can stretch the typing fingers and 
strain the eyes. Remember the days when pythonista used to make 
deprecating remarks about the superiority of Python's syntax because we 
didn't have 'all those braces' (and other punctuation-characters) 
cluttering-up the code???

-- 
Regards,
=dn

From list1 at tompassin.net  Thu Apr 20 08:52:59 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Thu, 20 Apr 2023 08:52:59 -0400
Subject: Pycharm IDE
In-Reply-To: <55435ecb-8e89-bef5-519b-85e27cc4ddf8@DancesWithMice.info>
References: <127255282.580618.1681859937764.ref@mail.yahoo.com>
 <127255282.580618.1681859937764@mail.yahoo.com>
 <mailman.118.1681859944.20750.python-list@python.org>
 <u1nb39$2m5i$1@nnrp.usenet.blueworldhosting.com>
 <1155066518.688499.1681881360098@mail.yahoo.com>
 <1242860619.686995.1681882076134@mail.yahoo.com>
 <152fb9fa-ce51-ad2f-c18c-a2052130e00b@tompassin.net>
 <mailman.125.1681907634.20750.python-list@python.org>
 <u1phjq$5tni$2@dont-email.me>
 <7c7354d4-58fd-38e1-1c34-9587be89de83@tompassin.net>
 <55435ecb-8e89-bef5-519b-85e27cc4ddf8@DancesWithMice.info>
Message-ID: <f5c41cba-0870-89fb-2d36-495d83b03884@tompassin.net>

On 4/19/2023 7:48 PM, dn via Python-list wrote:
> On 20/04/2023 08.59, Thomas Passin wrote:
>> On 4/19/2023 4:06 PM, Mark Bourne wrote:
>>>>
>>>> print(f'{LIMIT})
>>>
>>> ^ I think this one should be:
>>>
>>> print(f'{LIMIT}')
>>>
>>> with the closing quote ;o)
>>
>> Yup a typo!? Where's pylint when I need it?
> 
> but (and you designed it this way - right?) an excellent object-lesson 
> for the OP
> 
> AND
> 
> great rationale for why linters are so handy!

The Leo editor, which I use, checks the file you are working on for 
syntax errors and also for undefined variables, missing imports, and the 
like, when you save it.  It gives you a clickable link to the line in 
question.  This is a good compromise because it stays out of your way 
until you take a break by saving.

> I am bullish on F-strings, but they can stretch the typing fingers and 
> strain the eyes. Remember the days when pythonista used to make 
> deprecating remarks about the superiority of Python's syntax because we 
> didn't have 'all those braces' (and other punctuation-characters) 
> cluttering-up the code???

When you get right down for it, there isn't much difference between

'Here is the result: %s, %s' %(a.b, c)

and

'Here is the result: {}, {}'.format(a.b, c)

Readability and typeability aren't much different.  It's only when we 
get to f-strings that there's a real change, and the second form started 
to prepare us for it (yes, I know that the .format() form lets you use 
your own formatter - probably a real advantage though I never had 
occasion to use it)


From list1 at tompassin.net  Thu Apr 20 09:04:36 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Thu, 20 Apr 2023 09:04:36 -0400
Subject: PyCharm's strict PEP and not so strict?
In-Reply-To: <949d6719-a06b-6dcf-9aa5-6d6497c38060@DancesWithMice.info>
References: <2110321349.5908606.1681897884162.ref@mail.yahoo.com>
 <2110321349.5908606.1681897884162@mail.yahoo.com>
 <b36efc8f-7fcf-e646-57e1-1f008d8f719a@yahoo.co.uk>
 <06af8d39-a128-27e6-eeb8-f9e3f8fde7b6@DancesWithMice.info>
 <692943468.6227351.1681935070220@mail.yahoo.com>
 <949d6719-a06b-6dcf-9aa5-6d6497c38060@DancesWithMice.info>
Message-ID: <2568a5a1-44a8-e817-1218-5b17628ed994@tompassin.net>

On 4/19/2023 7:19 PM, dn via Python-list wrote:
> 
>> *PyCharm enables a range of Python-linters. Some by add-in. Some by
>> "External tools"*
>>
>> I was not 'up' on "linters", Thanks for the heads up! Attempted 
>> finding a "linter" on jetbrains... I take it that finding a 'linter' 
>> for Build #PC-222.4554.11, built on March 15, 2023
>> Is a matter of hit and miss... Any suggestions?
> 
> Try a web-search for "Python linters". Linters, I've know a few... (hum 
> along with the music...) have long been a part of the Python eco-system. 
> They have usually been designed to run from Python or 'the 
> command-line'. Accordingly, many can be added into PyCharm from 'the 
> outside'.
> 
> The original purpose was possibly to guide/nudge coders into the 
> practices recommended by PEP-008 (https://peps.python.org/pep-0008/). 
> This, as you will read, is not about syntax, but more about coding "style".
> 
> There are many to choose from. Some are more strict than others. 
> Recommendation: (for the good of your blood-pressure) stay away from 
> "highly opinionated" alternatives, such as Black. Try the ones which 
> offer options to turn-on/-off particular situations (as described earlier).

Be aware that most of these tools can be configured to be more or less 
fussy, but it's not going to be so easy for the uninitiated. 
Unconfigured, you will likely see a stream of messages that aren't 
helpful but may seem overwhelming. Once you have finally gotten one 
configured to your satisfaction, you probably will not need to change 
the configuration again for a long time.

You can generally disable specific warnings at a point in the code with 
special comments.  Using pylint, for example, perhaps appropriate in 
view of the OP's original post:

# pylint: disable = consider-using-f-string


From mats at wichmann.us  Thu Apr 20 12:23:49 2023
From: mats at wichmann.us (Mats Wichmann)
Date: Thu, 20 Apr 2023 10:23:49 -0600
Subject: PyCharm's strict PEP and not so strict?
In-Reply-To: <949d6719-a06b-6dcf-9aa5-6d6497c38060@DancesWithMice.info>
References: <2110321349.5908606.1681897884162.ref@mail.yahoo.com>
 <2110321349.5908606.1681897884162@mail.yahoo.com>
 <b36efc8f-7fcf-e646-57e1-1f008d8f719a@yahoo.co.uk>
 <06af8d39-a128-27e6-eeb8-f9e3f8fde7b6@DancesWithMice.info>
 <692943468.6227351.1681935070220@mail.yahoo.com>
 <949d6719-a06b-6dcf-9aa5-6d6497c38060@DancesWithMice.info>
Message-ID: <07e77bf8-4de8-b2a2-907a-3deaa480bdd8@wichmann.us>

On 4/19/23 17:19, dn via Python-list wrote:

> The "light bulb" has little to do with "quotes"! This is one of the 
> advantages of utilising a Python-native IDE (cf a more general-purpose 
> alternative, perhaps with some Python add-on). PyCharm attempts to 
> understand the code it is editing, and apply various lessons or 
> experiences to offer intelligent assistance.

To nitpick a little bit, PyCharm isn't *exactly* Python-native, it's a 
derivative of the IntelliJ generic IDE platform (written in, sigh, Java) 
with a *very* evolved Python add-on and packaged in such a way as to 
make it look as if it weren't an addon at all (but if you lift the 
covers up you can see the roots)


Builtin bits are very configurable, usually, but I haven't found that 
the Python code inspection (this is the stuff that by default gives you 
the PEP8-type warnings) is particularly so - be happy to stand corrected 
on that. However, you can configure an external tool - say, pylint - and 
if you do, you configure that in the normal way (a .pylintrc rcfile, or 
a toml config file). If you do this, you can turn off those style checks 
from the builtin checker.   If you want.


From l.catoni.99 at gmail.com  Thu Apr 20 18:44:38 2023
From: l.catoni.99 at gmail.com (Lorenzo Catoni)
Date: Fri, 21 Apr 2023 00:44:38 +0200
Subject: Question regarding unexpected behavior in using __enter__ method
Message-ID: <CAEGro7UrWuNKwBV8HuW8geMk+NM4T=4_DRfztT1p0Md1EcTW3A@mail.gmail.com>

Dear Python Mailing List members,

I am writing to seek your assistance in understanding an unexpected
behavior that I encountered while using the __enter__ method. I have
provided a code snippet below to illustrate the problem:

```
>>> class X:
...     __enter__ = int
...     __exit__ = lambda *_: None
...
>>> with X() as x:
...     pass
...
>>> x
0
```
As you can see, the __enter__ method does not throw any exceptions and
returns the output of "int()" correctly. However, one would normally expect
the input parameter "self" to be passed to the function.

On the other hand, when I implemented a custom function in place of the
__enter__ method, I encountered the following TypeError:

```
>>> def myint(*a, **kw):
...     return int(*a, **kw)
...
>>> class X:
...     __enter__ = myint
...     __exit__ = lambda *_: None
...
>>> with X() as x:
...     pass
...
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "<stdin>", line 2, in myint
TypeError: int() argument must be a string, a bytes-like object or a real
number, not 'X'
```
Here, the TypeError occurred because "self" was passed as an input
parameter to "myint". Can someone explain why this unexpected behavior
occurs only in the latter case?

I tested this issue on the following Python versions, and the problem
persists on all of them:
- Python 3.8.10 (default, Nov 14 2022, 12:59:47) [GCC 9.4.0] on linux
- Python 3.10.10 (main, Feb  8 2023, 14:50:01) [GCC 9.4.0] on linux
- Python 3.10.7 (tags/v3.10.7:6cc6b13, Sep  5 2022, 14:08:36) [MSC v.1933
64 bit (AMD64)] on win32

I appreciate any input or insights that you might have on this matter.

Thank you for your help in advance!

Best regards,
Lorenzo Catoni

From PythonList at DancesWithMice.info  Thu Apr 20 22:49:49 2023
From: PythonList at DancesWithMice.info (dn)
Date: Fri, 21 Apr 2023 14:49:49 +1200
Subject: Question regarding unexpected behavior in using __enter__ method
In-Reply-To: <CAEGro7UrWuNKwBV8HuW8geMk+NM4T=4_DRfztT1p0Md1EcTW3A@mail.gmail.com>
References: <CAEGro7UrWuNKwBV8HuW8geMk+NM4T=4_DRfztT1p0Md1EcTW3A@mail.gmail.com>
Message-ID: <0cf986cc-2bc5-8e70-0ecf-bb32b2aadfb9@DancesWithMice.info>

On 21/04/2023 10.44, Lorenzo Catoni wrote:
> I am writing to seek your assistance in understanding an unexpected
> behavior that I encountered while using the __enter__ method. I have
> provided a code snippet below to illustrate the problem:

It is expected behavior - just not what WE might have expected!


>>>> class X:
> ...     __enter__ = int
> ...     __exit__ = lambda *_: None
> ...
>>>> with X() as x:
> ...     pass
> ...
>>>> x
> 0

Note that what is happening is the creation of an alias for the int 
built-in function.

The docs say:
?
class int(x=0)
class int(x, base=10)

     Return an integer object constructed from a number or string x, or 
return 0 if no arguments are given. If x defines __int__(), int(x) 
returns x.__int__(). If x defines __index__(), it returns x.__index__(). 
If x defines __trunc__(), it returns x.__trunc__(). For floating point 
numbers, this truncates towards zero.
...
?

(https://docs.python.org/3/library/functions.html#int)

No argument is given. int() delivers as-promised. Hence, the x == 0 
result obtained.



> As you can see, the __enter__ method does not throw any exceptions and
> returns the output of "int()" correctly. However, one would normally expect
> the input parameter "self" to be passed to the function.
> 
> On the other hand, when I implemented a custom function in place of the
> __enter__ method, I encountered the following TypeError:
> 
> ```
>>>> def myint(*a, **kw):
> ...     return int(*a, **kw)
> ...
>>>> class X:
> ...     __enter__ = myint
> ...     __exit__ = lambda *_: None
> ...
>>>> with X() as x:
> ...     pass
> ...
> Traceback (most recent call last):
>    File "<stdin>", line 1, in <module>
>    File "<stdin>", line 2, in myint
> TypeError: int() argument must be a string, a bytes-like object or a real
> number, not 'X'
> ```
> Here, the TypeError occurred because "self" was passed as an input
> parameter to "myint". Can someone explain why this unexpected behavior
> occurs only in the latter case?
> 
> I tested this issue on the following Python versions, and the problem
> persists on all of them:
> - Python 3.8.10 (default, Nov 14 2022, 12:59:47) [GCC 9.4.0] on linux
> - Python 3.10.10 (main, Feb  8 2023, 14:50:01) [GCC 9.4.0] on linux
> - Python 3.10.7 (tags/v3.10.7:6cc6b13, Sep  5 2022, 14:08:36) [MSC v.1933
> 64 bit (AMD64)] on win32
> 
> I appreciate any input or insights that you might have on this matter.


(you know this next part!)

However, if int() is fed an X-object, which in no way represents a 
numeric or numeric-able value, then it crashes. After the class 
definition, try:

int( X )

=> int 0


Right-y-ho: the evidence.

Firstly, what happens when int() is called with no argument?

print( "int", int(), )


Note that whereas int and myint are both called with no argument(s), and 
therefore int() defaults to 0, myint is attempting to use the arguments 
as part of its return-value - "pass-through".

As identified, the first argument (the a-tuple's zero-th element) is 
going to be x's self - which is NOT numeric, stored in a tuple - which 
is NOT numeric...


Thus, if we "shadow" the built-in int() with a user-function, we can see 
what is being passed-in

def int( *a, **kw, ):
     print( locals(), )
     print( "a", a, type( a ), id( a ), )
     print( len( a ), a[ 0 ], type( a[ 0 ], ) )
     print( "kw", kw, type( kw ), id( kw ), )
     return 42

class X:
     __enter__ = int
     __exit__ = lambda *_: None

with X() as x:
     pass

print( "After first CM", x, "\n\n")

del( int )


def myint(*a, **kw):
     print( locals(), )
     print( "a", a, type( a ), id( a ), )
     print( len( a ), a[ 0 ], type( a[ 0 ], ) )
     print( "kw", kw, type( kw ), id( kw ), )
     return int(*a, **kw)

class Y:
     __enter__ = myint
     __exit__ = lambda *_: None


print( Y, type( Y ), id( Y ), )

with Y() as y:
     print( y, type( y ), id( y ), )
     pass

print( y )


=>
{'a': (<__main__.X object at 0x7f9b6bf13b90>,), 'kw': {}}
a (<__main__.X object at 0x7f9b6bf13b90>,) <class 'tuple'> 140305733882528
1 <__main__.X object at 0x7f9b6bf13b90> <class '__main__.X'>
kw {} <class 'dict'> 140305734120576
After first CM 42


<class '__main__.Y'> <class 'type'> 93904023389520
{'a': (<__main__.Y object at 0x7f9b6bf2c0d0>,), 'kw': {}}
a (<__main__.Y object at 0x7f9b6bf2c0d0>,) <class 'tuple'> 140305507712640
1 <__main__.Y object at 0x7f9b6bf2c0d0> <class '__main__.Y'>
kw {} <class 'dict'> 140305507621376
Traceback (most recent call last):
   File "/home/dn/Projects/analyzer/lorenzo.py", line 53, in <module>
     with Y() as y:
   File "/home/dn/Projects/analyzer/lorenzo.py", line 44, in myint
     return int(*a, **kw)
            ^^^^^^^^^^^^^
TypeError: int() argument must be a string, a bytes-like object or a 
real number, not 'Y'


If you remover the del() and leave my play-version of int(), Python can 
make it work...

(the second half of the output)

<class '__main__.Y'> <class 'type'> 94557671306576
{'a': (<__main__.Y object at 0x7f950ee2c0d0>,), 'kw': {}}
a (<__main__.Y object at 0x7f950ee2c0d0>,) <class 'tuple'> 140278176579200
1 <__main__.Y object at 0x7f950ee2c0d0> <class '__main__.Y'>
kw {} <class 'dict'> 140278176487936
{'a': (<__main__.Y object at 0x7f950ee2c0d0>,), 'kw': {}}
a (<__main__.Y object at 0x7f950ee2c0d0>,) <class 'tuple'> 140278176579152
1 <__main__.Y object at 0x7f950ee2c0d0> <class '__main__.Y'>
kw {} <class 'dict'> 140278176482368
42 <class 'int'> 140278410201800
42


So, it rather depends upon what you want returned from the actual 
myint() function.


Web.Refs:
https://docs.python.org/3/reference/datamodel.html?highlight=context%20manager#with-statement-context-managers
https://docs.python.org/3/reference/compound_stmts.html?highlight=context%20manager#the-with-statement



I'm curious though, why not:

class X:
     def __enter__( etc
     def __exit__( etc

with the actual code from myint9) as the suite/body of the __enter__()?
(in which case, the r?le of self is 'standard operating procedure' and 
may be more obvious)

-- 
Regards,
=dn

From cs at cskk.id.au  Thu Apr 20 20:25:46 2023
From: cs at cskk.id.au (Cameron Simpson)
Date: Fri, 21 Apr 2023 10:25:46 +1000
Subject: Question regarding unexpected behavior in using __enter__ method
In-Reply-To: <CAEGro7UrWuNKwBV8HuW8geMk+NM4T=4_DRfztT1p0Md1EcTW3A@mail.gmail.com>
References: <CAEGro7UrWuNKwBV8HuW8geMk+NM4T=4_DRfztT1p0Md1EcTW3A@mail.gmail.com>
Message-ID: <ZEHYCjlZyl0Eeelq@cskk.homeip.net>

On 21Apr2023 00:44, Lorenzo Catoni <l.catoni.99 at gmail.com> wrote:
>I am writing to seek your assistance in understanding an unexpected
>behavior that I encountered while using the __enter__ method. I have
>provided a code snippet below to illustrate the problem:
>
>```
>>>> class X:
>...     __enter__ = int
>...     __exit__ = lambda *_: None
>...
>>>> with X() as x:
>...     pass
>...
>>>> x
>0
>```
>As you can see, the __enter__ method does not throw any exceptions and
>returns the output of "int()" correctly. However, one would normally expect
>the input parameter "self" to be passed to the function.

My descriptor fu is weak, but I believe this is because `int` is not a 
plain function but a type.

Consider this class definition:

     class X:
        x = 1
        def y(self):
            return "y"

When you define a class, the body of the class is run in a namespace, 
and on completion, the namespace is _used_ to construct the class.  
During that process, the various names are considered. Here we've got 2 
names: "x" and "y".

"x" refers to an int and is just stored as a class attribute, unchanged.

"y" refers to a function, and is promoted to a descriptor of an unbound 
method.

So later: X.x return 1 but X.y returns a unbound method. If we make an 
instance:

     objx = X()

then obj.x returns 1 (by not fining an "x" on "obj", but finding one on 
"type(obj)" i.e. the class attribute.

By contrast, obj.y returns a bound method, a function already curried 
with a leading parameter "obj" (which will be "self"). There's no "y" 
attribute directly on "obj" but there's an unbound method on 
"type(obj).y", which gets bound by saying "obj.y".

The means that what happens to a name when you define the class depends 
on the typeof the value bound to the name.

A plain function gets turned into an unbound instance method, but other 
things are left alone.

When you went:

     __enter__ = int

That's not a plain function and so "obj.__enter__" doesn't turn into a 
bound method - it it just `int`.

Cheers,
Cameron Simpson <cs at cskk.id.au>

From __peter__ at web.de  Fri Apr 21 03:41:07 2023
From: __peter__ at web.de (Peter Otten)
Date: Fri, 21 Apr 2023 09:41:07 +0200
Subject: Question regarding unexpected behavior in using __enter__ method
In-Reply-To: <CAEGro7UrWuNKwBV8HuW8geMk+NM4T=4_DRfztT1p0Md1EcTW3A@mail.gmail.com>
References: <CAEGro7UrWuNKwBV8HuW8geMk+NM4T=4_DRfztT1p0Md1EcTW3A@mail.gmail.com>
Message-ID: <46d0c9cd-cf53-0535-b42e-3ef063f7b9a6@web.de>

On 21/04/2023 00:44, Lorenzo Catoni wrote:
> Dear Python Mailing List members,
>
> I am writing to seek your assistance in understanding an unexpected
> behavior that I encountered while using the __enter__ method. I have
> provided a code snippet below to illustrate the problem:
>
> ```
>>>> class X:
> ...     __enter__ = int
> ...     __exit__ = lambda *_: None
> ...
>>>> with X() as x:
> ...     pass
> ...
>>>> x
> 0
> ```
> As you can see, the __enter__ method does not throw any exceptions and
> returns the output of "int()" correctly. However, one would normally expect
> the input parameter "self" to be passed to the function.
>
> On the other hand, when I implemented a custom function in place of the
> __enter__ method, I encountered the following TypeError:
>
> ```
>>>> def myint(*a, **kw):
> ...     return int(*a, **kw)
> ...
>>>> class X:
> ...     __enter__ = myint
> ...     __exit__ = lambda *_: None
> ...
>>>> with X() as x:
> ...     pass
> ...
> Traceback (most recent call last):
>    File "<stdin>", line 1, in <module>
>    File "<stdin>", line 2, in myint
> TypeError: int() argument must be a string, a bytes-like object or a real
> number, not 'X'
> ```
> Here, the TypeError occurred because "self" was passed as an input
> parameter to "myint". Can someone explain why this unexpected behavior
> occurs only in the latter case?

Cameron is right, it's the descriptor protocol. Technically

inst.attr

invokes attr.__get__(...) if it exists:

 >>> class A:
	def __get__(self, *args): return args


 >>> class B: pass

 >>> class X:
	a = A()
	b = B()


 >>> x = X()
 >>> x.b
<__main__.B object at 0x02C2E388>
 >>> x.a
(<__main__.X object at 0x02C2E280>, <class '__main__.X'>)

Python functions support the descriptor protocol

 >>> hasattr(lambda: None, "__get__")
True

while builtin functions don't:

 >>> hasattr(ord, "__get__")
False


I'm unsure whether to regard int as a class or or function, but as there
is no __get__

 >>> hasattr(int, "__get__")
False

it behaves like builtin functions in this case.


From l.catoni.99 at gmail.com  Fri Apr 21 03:46:00 2023
From: l.catoni.99 at gmail.com (Lorenzo Catoni)
Date: Fri, 21 Apr 2023 09:46:00 +0200
Subject: Question regarding unexpected behavior in using __enter__ method
In-Reply-To: <ZEHYCjlZyl0Eeelq@cskk.homeip.net>
References: <CAEGro7UrWuNKwBV8HuW8geMk+NM4T=4_DRfztT1p0Md1EcTW3A@mail.gmail.com>
 <ZEHYCjlZyl0Eeelq@cskk.homeip.net>
Message-ID: <CAEGro7X9n346zkQNnXTP6WUOO0_qWj4CTFAzm3aBidemESwsVg@mail.gmail.com>

Thankyou for your answer,
i think i found the reason for this behavior, is has to do with the
function being user defined or not, rather than being a plain function or
type, as stated here
https://docs.python.org/3/reference/datamodel.html#:~:text=Also%20notice%20that%20this%20transformation%20only%20happens%20for%20user%2Ddefined%20functions%3B%20other%20callable%20objects%20(and%20all%20non%2Dcallable%20objects)%20are%20retrieved%20without%20transformation

Regards,
Lorenzo Catoni

On Fri, 21 Apr 2023 at 07:21, Cameron Simpson <cs at cskk.id.au> wrote:

> On 21Apr2023 00:44, Lorenzo Catoni <l.catoni.99 at gmail.com> wrote:
> >I am writing to seek your assistance in understanding an unexpected
> >behavior that I encountered while using the __enter__ method. I have
> >provided a code snippet below to illustrate the problem:
> >
> >```
> >>>> class X:
> >...     __enter__ = int
> >...     __exit__ = lambda *_: None
> >...
> >>>> with X() as x:
> >...     pass
> >...
> >>>> x
> >0
> >```
> >As you can see, the __enter__ method does not throw any exceptions and
> >returns the output of "int()" correctly. However, one would normally
> expect
> >the input parameter "self" to be passed to the function.
>
> My descriptor fu is weak, but I believe this is because `int` is not a
> plain function but a type.
>
> Consider this class definition:
>
>      class X:
>         x = 1
>         def y(self):
>             return "y"
>
> When you define a class, the body of the class is run in a namespace,
> and on completion, the namespace is _used_ to construct the class.
> During that process, the various names are considered. Here we've got 2
> names: "x" and "y".
>
> "x" refers to an int and is just stored as a class attribute, unchanged.
>
> "y" refers to a function, and is promoted to a descriptor of an unbound
> method.
>
> So later: X.x return 1 but X.y returns a unbound method. If we make an
> instance:
>
>      objx = X()
>
> then obj.x returns 1 (by not fining an "x" on "obj", but finding one on
> "type(obj)" i.e. the class attribute.
>
> By contrast, obj.y returns a bound method, a function already curried
> with a leading parameter "obj" (which will be "self"). There's no "y"
> attribute directly on "obj" but there's an unbound method on
> "type(obj).y", which gets bound by saying "obj.y".
>
> The means that what happens to a name when you define the class depends
> on the typeof the value bound to the name.
>
> A plain function gets turned into an unbound instance method, but other
> things are left alone.
>
> When you went:
>
>      __enter__ = int
>
> That's not a plain function and so "obj.__enter__" doesn't turn into a
> bound method - it it just `int`.
>
> Cheers,
> Cameron Simpson <cs at cskk.id.au>
> --
> https://mail.python.org/mailman/listinfo/python-list
>

From simon+python at bleah.co.uk  Fri Apr 21 09:19:28 2023
From: simon+python at bleah.co.uk (Simon Ward)
Date: Fri, 21 Apr 2023 14:19:28 +0100
Subject: ipaddress (was: Re: for a 'good python')
In-Reply-To: <C8DF3182-8172-4FDF-ACBE-1A9FCA3E39D9@barrys-emacs.org>
References: <C8DF3182-8172-4FDF-ACBE-1A9FCA3E39D9@barrys-emacs.org>
Message-ID: <20230421131928.GA16196@bleah.co.uk>

On Thu, Apr 13, 2023 at 04:00:59PM +0100, Barry wrote:
>Ipaddress was developed outside of the std lib and later added i 
>recall.

I used it prior to it being in the standard library:
https://pypi.org/project/ipaddr/

Simon

-- 
A complex system that works is invariably found to have evolved from a
simple system that works.?John Gall

From Ralf_M at t-online.de  Thu Apr 20 17:47:01 2023
From: Ralf_M at t-online.de (Ralf M.)
Date: Thu, 20 Apr 2023 23:47:01 +0200
Subject: Incomplete sys.path with embeddable python (Windows)!?
Message-ID: <a90b360e-054a-d8c7-2275-6d197aec7040@t-online.de>

Hello,

when I run a script with a "normally" installed python, the directory 
the script resides in is automatically added as first element to 
sys.path, so that "import my_local_module" finds my_local_module.py in 
the directory of the script.

However, when I run the same script with embeddable python ("Windows 
embeddable package (64-bit)", download link
https://www.python.org/ftp/python/3.11.3/python-3.11.3-embed-amd64.zip) 
the script directory is *not* prepended to the path, thus "import 
my_local_module" gives an ImportError.

I couldn't find an option to get the "normal" behaviour. Any ideas how 
to do that?

What I tried so far:

* The start-up value for sys.path seems to be defined in python311._pth. 
It looks that I can add further static paths to it, but I don't know how 
to make it add the script path (which can be different for different 
scripts).

* Uncommenting "import site" in python311._pth doesn't help.

* It seems that I could import something else in python311._pth, but I 
don't know how something imported from there could find out the path of 
the script that is about to be started.

* I read the (rather short) documentation of the embeddable package and 
of the site module several times but couldn't recognize a hint as to how 
to solve the issue.

* I can add the following lines to every script:
     import sys
     script_path = __file__.rsplit("\\", 1)[0]
     if script_path not in sys.path:
         sys.path[0:0] = [script_path]
     import my_local_modul
That works, but it's ugly, executing code between imports is frowned 
upon, and it needs to be added to every script.

Does anybody have a better idea?
Any help is appreciated.

Ralf M.

From mats at wichmann.us  Fri Apr 21 11:31:40 2023
From: mats at wichmann.us (Mats Wichmann)
Date: Fri, 21 Apr 2023 09:31:40 -0600
Subject: Incomplete sys.path with embeddable python (Windows)!?
In-Reply-To: <a90b360e-054a-d8c7-2275-6d197aec7040@t-online.de>
References: <a90b360e-054a-d8c7-2275-6d197aec7040@t-online.de>
Message-ID: <5d93e6e2-9c5c-88d8-8616-f778f79fc4ec@wichmann.us>

On 4/20/23 15:47, Ralf M. wrote:
> Hello,
> 
> when I run a script with a "normally" installed python, the directory 
> the script resides in is automatically added as first element to 
> sys.path, so that "import my_local_module" finds my_local_module.py in 
> the directory of the script.
> 
> However, when I run the same script with embeddable python ("Windows 
> embeddable package (64-bit)", download link
> https://www.python.org/ftp/python/3.11.3/python-3.11.3-embed-amd64.zip) 
> the script directory is *not* prepended to the path, thus "import 
> my_local_module" gives an ImportError.

This is intended behavior - the question comes up from time to time. The 
embeddable distribution is intended to be part of an application, not a 
general-purpose Python you can call for just anything.

There are a bunch of details here, for example:

https://github.com/python/cpython/issues/79022



From list1 at tompassin.net  Fri Apr 21 12:07:57 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Fri, 21 Apr 2023 12:07:57 -0400
Subject: Incomplete sys.path with embeddable python (Windows)!?
In-Reply-To: <a90b360e-054a-d8c7-2275-6d197aec7040@t-online.de>
References: <a90b360e-054a-d8c7-2275-6d197aec7040@t-online.de>
Message-ID: <ed2d59e2-20fc-deb8-8a55-a4aa39146d41@tompassin.net>

On 4/20/2023 5:47 PM, Ralf M. wrote:
> Hello,
> 
> when I run a script with a "normally" installed python, the directory 
> the script resides in is automatically added as first element to 
> sys.path, so that "import my_local_module" finds my_local_module.py in 
> the directory of the script.
> 
> However, when I run the same script with embeddable python ("Windows 
> embeddable package (64-bit)", download link
> https://www.python.org/ftp/python/3.11.3/python-3.11.3-embed-amd64.zip) 
> the script directory is *not* prepended to the path, thus "import 
> my_local_module" gives an ImportError.
> 
> I couldn't find an option to get the "normal" behaviour. Any ideas how 
> to do that?
> 
> What I tried so far:
> 
> * The start-up value for sys.path seems to be defined in python311._pth. 
> It looks that I can add further static paths to it, but I don't know how 
> to make it add the script path (which can be different for different 
> scripts).
> 
> * Uncommenting "import site" in python311._pth doesn't help.
> 
> * It seems that I could import something else in python311._pth, but I 
> don't know how something imported from there could find out the path of 
> the script that is about to be started.
> 
> * I read the (rather short) documentation of the embeddable package and 
> of the site module several times but couldn't recognize a hint as to how 
> to solve the issue.
> 
> * I can add the following lines to every script:
>  ??? import sys
>  ??? script_path = __file__.rsplit("\\", 1)[0]
>  ??? if script_path not in sys.path:
>  ??????? sys.path[0:0] = [script_path]
>  ??? import my_local_modul
> That works, but it's ugly, executing code between imports is frowned 
> upon, and it needs to be added to every script.
> 
> Does anybody have a better idea?
> Any help is appreciated.

I haven't worked with embeddable python, but here are some possibilities 
that came to mind, depending on how your system works -

1. If your script is started from the command line, sys.argv[0] gives 
the path to the script; You could use os.path.dirname() to get its 
directory.  This will end up the same place as your code fragment, but 
looks nicer and handles different path separators (e.g., Linux vs Windows);

2. You could write a little module that figures out the script's path 
and import that first in all your scripts.

3. If you know all the directories that your scripts will be in, you 
could add them all to a xx.pth file (do a search to make sure where to 
put .pth files for an embeddable case).

Not executing code between imports is a guideline, but guidelines are 
not laws and you can certainly deviate from them if there is a good reason.

My preference would be for 1) if at all possible.  Something like this 
(untested) -

import sys
import os.path

script_dir = os.path.dirname(sys.argv[0])
sys.path.insert(0, script_dir)  # Use built-in method to insert

Inserting the path entry again in case it's already there is not harmful 
so there's no need to check.  If for some reason sys.argv is not 
available, just substitute __file__.  That still won't be too clunky.

From grant.b.edwards at gmail.com  Fri Apr 21 16:57:45 2023
From: grant.b.edwards at gmail.com (Grant Edwards)
Date: Fri, 21 Apr 2023 13:57:45 -0700 (PDT)
Subject: Is npyscreen still alive?
Message-ID: <6442f8c9.050a0220.3ed35.17c6@mx.google.com>

I recently googled across the ncurses application framework npyscreen,
and was thinking about giving it a try for a small but real project
(something that would be distributed to customers), but I'm a bit
concerned that npyscreen no longer "alive".

The pypi page says the homepage is http://www.npcole.com/npyscreen/,
which then points to a Google Code page at https://code.google.com/archive/p/npyscreen/.

That page says the official repo is at https://bitbucket.org/npcole/npyscreen
which returns a 404.

There seems to be a copy in Github at https://github.com/npcole/npyscreen/commits/master,
but the last commit was almost 4 years ago.

Maybe it "just works" and is suitable for production?





From barry at barrys-emacs.org  Fri Apr 21 17:57:33 2023
From: barry at barrys-emacs.org (Barry)
Date: Fri, 21 Apr 2023 22:57:33 +0100
Subject: Is npyscreen still alive?
In-Reply-To: <6442f8c9.050a0220.3ed35.17c6@mx.google.com>
References: <6442f8c9.050a0220.3ed35.17c6@mx.google.com>
Message-ID: <FF7D8DCA-73CB-461E-A885-23CC6D11965B@barrys-emacs.org>



> On 21 Apr 2023, at 22:00, Grant Edwards <grant.b.edwards at gmail.com> wrote:
> 
> ?I recently googled across the ncurses application framework npyscreen,
> and was thinking about giving it a try for a small but real project
> (something that would be distributed to customers), but I'm a bit
> concerned that npyscreen no longer "alive".
> 
> The pypi page says the homepage is http://www.npcole.com/npyscreen/,
> which then points to a Google Code page at https://code.google.com/archive/p/npyscreen/.
> 
> That page says the official repo is at https://bitbucket.org/npcole/npyscreen
> which returns a 404.
> 
> There seems to be a copy in Github at https://github.com/npcole/npyscreen/commits/master,
> but the last commit was almost 4 years ago.
> 
> Maybe it "just works" and is suitable for production?

Maybe this, recently lwn.net article, https://textual.textualize.io/
I was planning to check it out.

Barry
> 
> 
> 
> 
> -- 
> https://mail.python.org/mailman/listinfo/python-list
> 

From list1 at tompassin.net  Fri Apr 21 18:51:14 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Fri, 21 Apr 2023 18:51:14 -0400
Subject: Is npyscreen still alive?
In-Reply-To: <FF7D8DCA-73CB-461E-A885-23CC6D11965B@barrys-emacs.org>
References: <6442f8c9.050a0220.3ed35.17c6@mx.google.com>
 <FF7D8DCA-73CB-461E-A885-23CC6D11965B@barrys-emacs.org>
Message-ID: <0a6c2a83-e44b-45e6-fe5b-e78df8b69828@tompassin.net>

On 4/21/2023 5:57 PM, Barry wrote:
> 
> 
>> On 21 Apr 2023, at 22:00, Grant Edwards <grant.b.edwards at gmail.com> wrote:
>>
>> ?I recently googled across the ncurses application framework npyscreen,
>> and was thinking about giving it a try for a small but real project
>> (something that would be distributed to customers), but I'm a bit
>> concerned that npyscreen no longer "alive".
>>
>> The pypi page says the homepage is http://www.npcole.com/npyscreen/,
>> which then points to a Google Code page at https://code.google.com/archive/p/npyscreen/.
>>
>> That page says the official repo is at https://bitbucket.org/npcole/npyscreen
>> which returns a 404.
>>
>> There seems to be a copy in Github at https://github.com/npcole/npyscreen/commits/master,
>> but the last commit was almost 4 years ago.
>>
>> Maybe it "just works" and is suitable for production?
> 
> Maybe this, recently lwn.net article, https://textual.textualize.io/
> I was planning to check it out.

It's still pip-installable from PyPi.


From aapost at idontexist.club  Thu Apr 20 21:36:18 2023
From: aapost at idontexist.club (aapost)
Date: Thu, 20 Apr 2023 21:36:18 -0400
Subject: Question regarding unexpected behavior in using __enter__ method
In-Reply-To: <mailman.137.1682030890.20750.python-list@python.org>
References: <CAEGro7UrWuNKwBV8HuW8geMk+NM4T=4_DRfztT1p0Md1EcTW3A@mail.gmail.com>
 <mailman.137.1682030890.20750.python-list@python.org>
Message-ID: <u1spai$2hsq$1@nnrp.usenet.blueworldhosting.com>

On 4/20/23 18:44, Lorenzo Catoni wrote:
> Here, the TypeError occurred because "self" was passed as an input

Instantiate X and observe it there

x2 = X()

 >>> X.__enter__
<class 'int'>
 >>> X.__exit__
<function X.<lambda> at 0x...>
 >>> x2.__enter__
<class 'int'>
 >>> x2.__exit__
<bound method X.<lambda> of <__main__.X object at 0x...>>


To receive self the method must be bound. __enter__ = int doesn't bind 
the int type/class on instantiation, so it never gets self. Your custom 
function binds and receives self.

I am not sure if there is documentation to explain better specifically 
what makes makes type different and not bindable.


From info at cmcc.it  Fri Apr 21 05:33:16 2023
From: info at cmcc.it (info cmcc)
Date: Fri, 21 Apr 2023 11:33:16 +0200
Subject: Deadline Reminder: April 30, 2023 - Software Developer | Job position
 at CMCC Foundation, Italy
In-Reply-To: <CA+-poF+vbbFyX9DKW=_3Pum7SFq82V=w6n3Ap-ujpo0s7=xzyg@mail.gmail.com>
References: <CA+-poF+vbbFyX9DKW=_3Pum7SFq82V=w6n3Ap-ujpo0s7=xzyg@mail.gmail.com>
Message-ID: <CA+-poFK9o7Wp2K9GSY_sj5kfK2s8fyvjAQ9hnLkef7r9eObEow@mail.gmail.com>

*Software Developer (Research Associate) code 12428*
(Deadline: April 30, 2023)

The CMCC Foundation is a scientific research center on climate change and
its interactions with the environment, the society, the world of business
and policy makers.

Our work aims to stimulate sustainable growth, protect the environment, and
develop strategies for the adaptation and mitigation of climate change.

Our Division of Ocean Predictions and Applications (OPA) is looking for new
positions of Software Developers, responsible for (i) supporting modelling
developments, implementation, and validation, (ii)
porting/recoding/re-engineering/developing numerical procedures in the
frame of ocean models, and (iii) deployment of applications and services
with virtualization software such as Virtual Machines and Dockers.

The job location is CMCC Headquarters in Lecce, Italy.

We are looking for motivated persons with the following requirements:

   - M.Sc. degree (or equivalent working experience) in Computer Science,
   Engineering, or other scientific disciplines (i.e., physics, mathematics);
   fluency in English;
   - knowledge of UNIX/Linux operating systems and script languages (i.e.,
   *nix shell);
   - good knowledge and skills in programming (i.e., Python and bash
   scripting);
   - knowledge of version control systems (i.e., git).

Furthermore, it is welcome that you have as much as possible of the
following experience:

   - knowledge of workflow management platforms;
   - knowledge of Fortran;
   - HPC architectures and job schedulers (i.e., IBM Spectrum LSF);
   - experience in managing/manipulating NetCDF data.




*More details and info about HOW TO APPLY:
https://cmccfoundation.applytojob.com/apply/WkA5Dhltc9/12428-Software-Developer-Research-Associate
<https://cmccfoundation.applytojob.com/apply/WkA5Dhltc9/12428-Software-Developer-Research-Associate>*


-- 

Fondazione CMCCCentro Euro-Mediterraneo sui Cambiamenti Climatici
Via Marco Biagi, 5 - 73100 Lecce
info at cmcc.it - www.cmcc.it

From info at cmcc.it  Fri Apr 21 05:49:36 2023
From: info at cmcc.it (info cmcc)
Date: Fri, 21 Apr 2023 11:49:36 +0200
Subject: Junior Research Associate in HPC | Job position at CMCC Foundation,
 Italy
In-Reply-To: <CA+-poFLKm6cyOhX3kx+nhSBxB3X6qD+c2RcY=A9Vdz7qAO+rZg@mail.gmail.com>
References: <CA+-poFL+RvZtmb=Soq_2qZH3UjN80V93LnOkEs8ukFjvjBni+A@mail.gmail.com>
 <CA+-poFLbPw+mjef_ceePx=Q2Xg=33c-_dfXUoBd=H3L7qMjz4g@mail.gmail.com>
 <CA+-poF+0uMLS1obZOyMn3hbCK5cUdu-0YEohXbGBRi=3Qo6Qbw@mail.gmail.com>
 <CA+-poFJfipKH5wEAyTbqUbz4Ug4PZqMNt1r6ymQYf4hit+v9iQ@mail.gmail.com>
 <CA+-poFJBzTfz+21yxkXJeeMXC8Ee2AtZpZ14Rj9EGox6V9NG0g@mail.gmail.com>
 <CA+-poFJ6somvVgDZhcFEDiu9Pwip-W3R_=861NW0sEPCReD7NA@mail.gmail.com>
 <CA+-poF+ziybYZXNfRpduYrV=KHmO5TTmw8cB716cY4cV368VFQ@mail.gmail.com>
 <CA+-poF+Fwve161CUECAn=X0fQMgfkwdSrqzRsUG8Avwvmc-tBg@mail.gmail.com>
 <CA+-poFJbqaT69v46WaL9sVXzxEN2XUc98BivyogJb0vKyV72nQ@mail.gmail.com>
 <CA+-poFKEU_yUO5Ax6xBjr6ucaFykKQ562x934GCPryMgQWv_KA@mail.gmail.com>
 <CA+-poFJ=L8g3ZzByHdODF2GnjdmRRSAOaL5zqTUb+k0pYWhuiQ@mail.gmail.com>
 <CA+-poFLKm6cyOhX3kx+nhSBxB3X6qD+c2RcY=A9Vdz7qAO+rZg@mail.gmail.com>
Message-ID: <CA+-poFKDNR7atryWRWqSNEEcF4CdqiwtzEFG2ZuiowAPDZ5CNA@mail.gmail.com>

*Junior Research Associate in HPC*

*Deadline: May 15, 2023*
*The job location is CMCC Headquarters of Lecce*

The CMCC Foundation is a scientific research center on climate change and
its interactions with the environment, society, the world of business, and
policymakers.

Our work aims to stimulate sustainable growth, protect the environment and
develop strategies for adapting and mitigating climate change.

Our Division of Advanced Scientific Computing (ASC) is looking for a new
position of Junior Research Associate in HPC, responsible for *supporting
research activities in HPC*.

The position has been opened within the project *PNRR HPC SPOKE, CUP Number
C83C22000560007.*

The job location is CMCC Headquarters in *Lecce, Italy. *

We are looking for a motivated person with the following requirements:

   - *M.Sc. degree in Computer Science or Computer Engineering or
   equivalent fields;*
   - *3+ years? experience in scientific software development and parallel
   programming;*
   - *Excellent knowledge of C and Fortran programming language;*
   - Parallel programming with MPI of scientific codes for heterogenous HPC
   architectures;
   - OpenACC/OpenMP and GPU programming;
   - Performance analysis of parallel codes;
   - *Expert with HPC systems;*
   - Fluent handling of scripting languages like Bash and Python;
   - Experience in complex software development and software version
   control systems (e.g. Git);
   - Knowledge in numerical methods and numerical schemes;
   - Knowledge in the application of computational fluid dynamics or
   weather and climate modelling is an asset;
   - *Good knowledge of both written and spoken English language.*

The project promotes female and youth employment and the reduction of
territorial gaps according to art.  47 ?promotion of generational and
gender equal opportunities for the awarding of public contracts for the
implementation of the National Recovery and Resilience Plan (PNRR)?, of the
Italian Law Decree no. 77/2021 converted into law no. 108 of 29 July 2021.


*More details and info about HOW TO APPLY:
<https://cmccfoundation.applytojob.com/apply/ScbvrZiu29/12434-Climate-Weather-Model-Developer?source=Our%20Career%20Page%20Widget>*
https://cmccfoundation.applytojob.com/apply/qCBuoQihlI/12447-Junior-Research-Associate-In-HPC
*-- *
Fondazione CMCC
Centro Euro-Mediterraneo sui Cambiamenti Climatici
Via Augusto Imperatore, 16 - 73100 Lecce
info at cmcc.it - www.cmcc.it

From greg.ewing at canterbury.ac.nz  Fri Apr 21 21:27:49 2023
From: greg.ewing at canterbury.ac.nz (Greg Ewing)
Date: Sat, 22 Apr 2023 13:27:49 +1200
Subject: Incomplete sys.path with embeddable python (Windows)!?
In-Reply-To: <mailman.144.1682091286.20750.python-list@python.org>
References: <a90b360e-054a-d8c7-2275-6d197aec7040@t-online.de>
 <5d93e6e2-9c5c-88d8-8616-f778f79fc4ec@wichmann.us>
 <mailman.144.1682091286.20750.python-list@python.org>
Message-ID: <kagrgoFcbb3U1@mid.individual.net>

How are you invoking your script? Presumably you have some code
in your embedding application that takes a script path and runs
it. Instead of putting the code to update sys.path into every
script, the embedding application could do it before running
the script.

-- 
Greg

From Ralf_M at t-online.de  Sat Apr 22 17:35:37 2023
From: Ralf_M at t-online.de (Ralf M.)
Date: Sat, 22 Apr 2023 23:35:37 +0200
Subject: Incomplete sys.path with embeddable python (Windows)!?
In-Reply-To: <5d93e6e2-9c5c-88d8-8616-f778f79fc4ec@wichmann.us>
References: <a90b360e-054a-d8c7-2275-6d197aec7040@t-online.de>
 <5d93e6e2-9c5c-88d8-8616-f778f79fc4ec@wichmann.us>
Message-ID: <a27f2479-792f-ef4b-33ec-ae1406474470@t-online.de>

Am 21.04.2023 um 17:31 schrieb Mats Wichmann:
> On 4/20/23 15:47, Ralf M. wrote:
>> Hello,
>>
>> when I run a script with a "normally" installed python, the directory 
>> the script resides in is automatically added as first element to 
>> sys.path, so that "import my_local_module" finds my_local_module.py in 
>> the directory of the script.
>>
>> However, when I run the same script with embeddable python ("Windows 
>> embeddable package (64-bit)", download link
>> https://www.python.org/ftp/python/3.11.3/python-3.11.3-embed-amd64.zip) the script directory is *not* prepended to the path, thus "import my_local_module" gives an ImportError.
> 
> This is intended behavior - the question comes up from time to time. The 
> embeddable distribution is intended to be part of an application, not a 
> general-purpose Python you can call for just anything.
> 
> There are a bunch of details here, for example:
> 
> https://github.com/python/cpython/issues/79022
> 
Thank you for the pointer to the issue. I'll try to remove the ._pth 
completely (and see whether that breaks anything) and may have a look at 
the nuget.org package.

I can see that for many cases the behaviour is appropriate, but I had 
hoped that there is a configuration option for the cases where it is not.

About my use case:
There is a complex application package, consisting of some commercial 
and some freeware software, tied together with scripts in at least four 
different scripting languages. Now I intend to add further functionality 
in a fifth language, Python. The idea is to make the embeddedable 
package part of the application package and have scripts for the new 
functions. Several independent functions are to be added, each 
consisting of a script plus some local modules, and all of them should 
use the same python embedded into the application package.

From Ralf_M at t-online.de  Sat Apr 22 17:45:11 2023
From: Ralf_M at t-online.de (Ralf M.)
Date: Sat, 22 Apr 2023 23:45:11 +0200
Subject: Incomplete sys.path with embeddable python (Windows)!?
In-Reply-To: <kagrgoFcbb3U1@mid.individual.net>
References: <a90b360e-054a-d8c7-2275-6d197aec7040@t-online.de>
 <5d93e6e2-9c5c-88d8-8616-f778f79fc4ec@wichmann.us>
 <mailman.144.1682091286.20750.python-list@python.org>
 <kagrgoFcbb3U1@mid.individual.net>
Message-ID: <d638f08d-32c7-fdeb-f97d-8731f26b1550@t-online.de>

Am 22.04.2023 um 03:27 schrieb Greg Ewing via Python-list:
> How are you invoking your script? Presumably you have some code
> in your embedding application that takes a script path and runs
> it. Instead of putting the code to update sys.path into every
> script, the embedding application could do it before running
> the script.
> 
In principle a good idea, but I don't know how to do that:
The script is currently invoked by a .cmd file, but that may change to a 
shortcut (.lnk). This is what the embeddable package documentation calls 
"Python Application - simple approach".
To update sys.path on start up I would need to do something like
   C:\path\to\python.exe --add-path C:\s-path C:\s-path\script.py
but I couldn't find an option like --add-path.

From Ralf_M at t-online.de  Sat Apr 22 18:04:16 2023
From: Ralf_M at t-online.de (Ralf M.)
Date: Sun, 23 Apr 2023 00:04:16 +0200
Subject: Incomplete sys.path with embeddable python (Windows)!?
In-Reply-To: <ed2d59e2-20fc-deb8-8a55-a4aa39146d41@tompassin.net>
References: <a90b360e-054a-d8c7-2275-6d197aec7040@t-online.de>
 <ed2d59e2-20fc-deb8-8a55-a4aa39146d41@tompassin.net>
Message-ID: <3979254c-95fa-935f-e6a4-4756526f1171@t-online.de>

Am 21.04.2023 um 18:07 schrieb Thomas Passin:
> On 4/20/2023 5:47 PM, Ralf M. wrote:
>> Hello,
>>
>> when I run a script with a "normally" installed python, the directory 
>> the script resides in is automatically added as first element to 
>> sys.path, so that "import my_local_module" finds my_local_module.py in 
>> the directory of the script.
>>
>> However, when I run the same script with embeddable python ("Windows 
>> embeddable package (64-bit)", download link
>> https://www.python.org/ftp/python/3.11.3/python-3.11.3-embed-amd64.zip) the script directory is *not* prepended to the path, thus "import my_local_module" gives an ImportError.
>>
>> I couldn't find an option to get the "normal" behaviour. Any ideas how 
>> to do that?
>>
>> What I tried so far:
>> [...]
>> * I can add the following lines to every script:
>> ???? import sys
>> ???? script_path = __file__.rsplit("\\", 1)[0]
>> ???? if script_path not in sys.path:
>> ???????? sys.path[0:0] = [script_path]
>> ???? import my_local_modul
>> [...] 

Thank your for your hints.

> I haven't worked with embeddable python, but here are some possibilities 
> that came to mind, depending on how your system works -
> 
> 1. If your script is started from the command line, sys.argv[0] gives 
> the path to the script; 
I didn't think of sys.argv[0] to get at the path; this might be quite 
useful, I'll try it out next week.

> You could use os.path.dirname() to get its 
> directory.? This will end up the same place as your code fragment, but 
> looks nicer and handles different path separators (e.g., Linux vs Windows);
Yes, but it requires another import and the embedded package is only 
available for windows anyway, I think. I'll consider the idea, though.

> 2. You could write a little module that figures out the script's path 
> and import that first in all your scripts.
> 
> 3. If you know all the directories that your scripts will be in, you 
> could add them all to a xx.pth file (do a search to make sure where to 
> put .pth files for an embeddable case).
I thought about that, but for that to work all local modules across all 
script locations must have unique names, otherwise import might get hold 
of a module from the wrong directory. Certainly doable for a few 
scripts, but might become a source of hard to track errors when the 
number of scripts increases and later maintainers are not aware of the 
naming restriction.

> [...}


From list1 at tompassin.net  Sat Apr 22 18:17:59 2023
From: list1 at tompassin.net (Thomas Passin)
Date: Sat, 22 Apr 2023 18:17:59 -0400
Subject: Incomplete sys.path with embeddable python (Windows)!?
In-Reply-To: <d638f08d-32c7-fdeb-f97d-8731f26b1550@t-online.de>
References: <a90b360e-054a-d8c7-2275-6d197aec7040@t-online.de>
 <5d93e6e2-9c5c-88d8-8616-f778f79fc4ec@wichmann.us>
 <mailman.144.1682091286.20750.python-list@python.org>
 <kagrgoFcbb3U1@mid.individual.net>
 <d638f08d-32c7-fdeb-f97d-8731f26b1550@t-online.de>
Message-ID: <9bc10f4c-890a-4c89-2cd2-e505a715c92e@tompassin.net>

On 4/22/2023 5:45 PM, Ralf M. wrote:
> Am 22.04.2023 um 03:27 schrieb Greg Ewing via Python-list:
>> How are you invoking your script? Presumably you have some code
>> in your embedding application that takes a script path and runs
>> it. Instead of putting the code to update sys.path into every
>> script, the embedding application could do it before running
>> the script.
>>
> In principle a good idea, but I don't know how to do that:
> The script is currently invoked by a .cmd file, but that may change to a 
> shortcut (.lnk). This is what the embeddable package documentation calls 
> "Python Application - simple approach".
> To update sys.path on start up I would need to do something like
>  ? C:\path\to\python.exe --add-path C:\s-path C:\s-path\script.py
> but I couldn't find an option like --add-path.

You can get the .cmd file's path and put it into an environmental 
variable (or as a command line argument).  If you haven't encountered 
that trick of Windows batch file procesing, here it is:

%~dp0 (returns the directory a batch file is running from)


From greg.ewing at canterbury.ac.nz  Sat Apr 22 19:49:03 2023
From: greg.ewing at canterbury.ac.nz (Greg Ewing)
Date: Sun, 23 Apr 2023 11:49:03 +1200
Subject: Incomplete sys.path with embeddable python (Windows)!?
In-Reply-To: <mailman.153.1682201576.20750.python-list@python.org>
References: <a90b360e-054a-d8c7-2275-6d197aec7040@t-online.de>
 <ed2d59e2-20fc-deb8-8a55-a4aa39146d41@tompassin.net>
 <3979254c-95fa-935f-e6a4-4756526f1171@t-online.de>
 <mailman.153.1682201576.20750.python-list@python.org>
Message-ID: <kaja3hFns33U1@mid.individual.net>

On 23/04/23 10:04 am, Ralf M. wrote:
> I thought about that, but for that to work all local modules across all 
> script locations must have unique names, otherwise import might get hold 
> of a module from the wrong directory.

You could put all the local modules belonging to a particular
script into a package named after the script, e.g. put the local
modules used by foo.py into a package called foolib.

-- 
Greg

From mats at wichmann.us  Sun Apr 23 12:17:26 2023
From: mats at wichmann.us (Mats Wichmann)
Date: Sun, 23 Apr 2023 10:17:26 -0600
Subject: Incomplete sys.path with embeddable python (Windows)!?
In-Reply-To: <3979254c-95fa-935f-e6a4-4756526f1171@t-online.de>
References: <a90b360e-054a-d8c7-2275-6d197aec7040@t-online.de>
 <ed2d59e2-20fc-deb8-8a55-a4aa39146d41@tompassin.net>
 <3979254c-95fa-935f-e6a4-4756526f1171@t-online.de>
Message-ID: <2e9b9b87-0707-79c8-bb10-47adb35daf32@wichmann.us>

On 4/22/23 16:04, Ralf M. wrote:
> Am 21.04.2023 um 18:07 schrieb Thomas Passin:
>> On 4/20/2023 5:47 PM, Ralf M. wrote:
>>> Hello,
>>>
>>> when I run a script with a "normally" installed python, the directory 
>>> the script resides in is automatically added as first element to 
>>> sys.path, so that "import my_local_module" finds my_local_module.py 
>>> in the directory of the script.
>>>
>>> However, when I run the same script with embeddable python ("Windows 
>>> embeddable package (64-bit)", download link
>>> https://www.python.org/ftp/python/3.11.3/python-3.11.3-embed-amd64.zip) the script directory is *not* prepended to the path, thus "import my_local_module" gives an ImportError.
>>>
>>> I couldn't find an option to get the "normal" behaviour. Any ideas 
>>> how to do that?
>>>
>>> What I tried so far:
>>> [...]
>>> * I can add the following lines to every script:
>>> ???? import sys
>>> ???? script_path = __file__.rsplit("\\", 1)[0]
>>> ???? if script_path not in sys.path:
>>> ???????? sys.path[0:0] = [script_path]
>>> ???? import my_local_modul
>>> [...] 

Have used this stanza (actually, for the inverse purpose, to remove that 
script's dir from sys.path, but whatever...):

script_dir = os.path.dirname(os.path.realpath(__file__))

you can then insert it:

sys.path.insert(0, script_dir)

or just add:

sys.path = [script_dir] + sys.path

assuming you want it at the front...

but it doesn't really solve your problem of needing it *everywhere*...


From torriem at gmail.com  Mon Apr 24 09:37:21 2023
From: torriem at gmail.com (Michael Torrie)
Date: Mon, 24 Apr 2023 07:37:21 -0600
Subject: Is npyscreen still alive?
In-Reply-To: <FF7D8DCA-73CB-461E-A885-23CC6D11965B@barrys-emacs.org>
References: <6442f8c9.050a0220.3ed35.17c6@mx.google.com>
 <FF7D8DCA-73CB-461E-A885-23CC6D11965B@barrys-emacs.org>
Message-ID: <5ad249e5-5c11-a30d-106a-e4a5a21abbf4@gmail.com>

On 4/21/23 15:57, Barry wrote:
> Maybe this, recently lwn.net article, https://textual.textualize.io/
> I was planning to check it out.

Textual definitely looks slick and modern.  And with a modern terminal
emulator it works quite well and is responsive.  I'd definitely consider
it for a TUI.

But on the Linux console, or on an older terminal, not so much.
Textual's really designed for smallish unicode fonts in a windowed
environment, not any kind of real, old-school text mode.  Just something
to keep in mind.  99% of terminal users are using a modern terminal
emulator these days, with full color and unicode, which is the target of
textual.

Curses-based programs don't look great on anything, but they do look
consistent on more primitive terminals.

From grant.b.edwards at gmail.com  Mon Apr 24 10:04:22 2023
From: grant.b.edwards at gmail.com (Grant Edwards)
Date: Mon, 24 Apr 2023 07:04:22 -0700 (PDT)
Subject: Is npyscreen still alive?
References: <6442f8c9.050a0220.3ed35.17c6@mx.google.com>
 <FF7D8DCA-73CB-461E-A885-23CC6D11965B@barrys-emacs.org>
 <5ad249e5-5c11-a30d-106a-e4a5a21abbf4@gmail.com>
Message-ID: <64468c66.050a0220.c3e8f.372e@mx.google.com>

On 2023-04-24, Michael Torrie <torriem at gmail.com> wrote:
> On 4/21/23 15:57, Barry wrote:
>
>> Maybe this, recently lwn.net article,
>> https://textual.textualize.io/ I was planning to check it out.
>
> Textual definitely looks slick and modern.  And with a modern
> terminal emulator it works quite well and is responsive.  I'd
> definitely consider it for a TUI.
>
> But on the Linux console, or on an older terminal, not so much.
> Textual's really designed for smallish unicode fonts in a windowed
> environment, not any kind of real, old-school text mode.  Just
> something to keep in mind.  99% of terminal users are using a modern
> terminal emulator these days, with full color and unicode, which is
> the target of textual.

Is putty running on Windows a "modern terminal emulator" in this
context?  After observing some of the local IT types work, I suspect
that will be a common use-case for the app I'm working on.

> Curses-based programs don't look great on anything, but they do look
> consistent on more primitive terminals.

The other big advantage of an ncurses program is that since curses
support is in the std library, a curses app is simpler to distribute.
Right now, the application is a single .py file you just copy to the
destination machine and run.  It supports command-line use and a Tk
GUI. I can add an ncurses "CUI" without having to either adopt a more
complex bundling mechanism that requires it to be "installed" or
require that users install dependencies via pip/apt/yum/whatever.

--
Grant

From nospam at please.ty  Sun Apr 23 02:38:36 2023
From: nospam at please.ty (jak)
Date: Sun, 23 Apr 2023 08:38:36 +0200
Subject: Incomplete sys.path with embeddable python (Windows)!?
In-Reply-To: <mailman.152.1682200502.20750.python-list@python.org>
References: <a90b360e-054a-d8c7-2275-6d197aec7040@t-online.de>
 <5d93e6e2-9c5c-88d8-8616-f778f79fc4ec@wichmann.us>
 <mailman.144.1682091286.20750.python-list@python.org>
 <kagrgoFcbb3U1@mid.individual.net>
 <d638f08d-32c7-fdeb-f97d-8731f26b1550@t-online.de>
 <mailman.152.1682200502.20750.python-list@python.org>
Message-ID: <u22jpd$3n2f7$1@dont-email.me>

Ralf M. ha scritto:
> Am 22.04.2023 um 03:27 schrieb Greg Ewing via Python-list:
>> How are you invoking your script? Presumably you have some code
>> in your embedding application that takes a script path and runs
>> it. Instead of putting the code to update sys.path into every
>> script, the embedding application could do it before running
>> the script.
>>
> In principle a good idea, but I don't know how to do that:
> The script is currently invoked by a .cmd file, but that may change to a 
> shortcut (.lnk). This is what the embeddable package documentation calls 
> "Python Application - simple approach".
> To update sys.path on start up I would need to do something like
>  ? C:\path\to\python.exe --add-path C:\s-path C:\s-path\script.py
> but I couldn't find an option like --add-path.


what about:

foo.py:
from sys import path
print('path:', path)
#end foo.py

from prompt:

$ python -c "import sys;sys.path=['/user/foopath']+sys.path;import foo;foo"

output:

path: ['/user/foopath', '', '/usr/lib/python39.zip', 
'/usr/lib/python3.9', '/usr/lib/python3.9/lib-dynload', 
'/usr/lib/python3.9/site-packages']

From jamesbtobin at gmail.com  Mon Apr 24 05:02:58 2023
From: jamesbtobin at gmail.com (James Tobin)
Date: Mon, 24 Apr 2023 10:02:58 +0100
Subject: JOB | Linux Platform Engineer (India and Singapore)
Message-ID: <CAMyPCTTGf_8AodEe7s1PAZPH2U3drhgaKdO0f2GP4fso6V7Z2g@mail.gmail.com>

Hello, i'm working with an employer that is looking to hire a Linux
platform engineer for their office in India and Singapore that has
experience in automation and management of platform configuration from
both an onprem and cloud perspective.  Consequently, I had hoped that
some members may like to discuss further; off-list.  I can be reached
using "JamesBTobin (at) Gmail (dot) Com".  Kind regards, James

From grant.b.edwards at gmail.com  Mon Apr 24 12:26:29 2023
From: grant.b.edwards at gmail.com (Grant Edwards)
Date: Mon, 24 Apr 2023 09:26:29 -0700 (PDT)
Subject: Python curses missing form library?
Message-ID: <6446adb5.5e0a0220.6fef5.3633@mx.google.com>

Does the Python curses support in the standard library not include
support for the curses form library? It seems to include support for
the panel library, but I can't find any mention of the form library.

I see in the docs that menu support is still missing. :/

--
Grant


From grant.b.edwards at gmail.com  Mon Apr 24 12:32:37 2023
From: grant.b.edwards at gmail.com (Grant Edwards)
Date: Mon, 24 Apr 2023 09:32:37 -0700 (PDT)
Subject: Is npyscreen still alive?
References: <6442f8c9.050a0220.3ed35.17c6@mx.google.com>
 <FF7D8DCA-73CB-461E-A885-23CC6D11965B@barrys-emacs.org>
 <5ad249e5-5c11-a30d-106a-e4a5a21abbf4@gmail.com>
 <64468c66.050a0220.c3e8f.372e@mx.google.com>
Message-ID: <6446af25.050a0220.ed912.397a@mx.google.com>

On 2023-04-24, Grant Edwards <grant.b.edwards at gmail.com> wrote:

> The other big advantage of an ncurses program is that since curses
> support is in the std library, a curses app is simpler to
> distribute.  Right now, the application is a single .py file you
> just copy to the destination machine and run.  It supports
> command-line use and a Tk GUI. I can add an ncurses "CUI" without
> having to either adopt a more complex bundling mechanism that
> requires it to be "installed" or require that users install
> dependencies via pip/apt/yum/whatever.

However... I just realized that Python's curses support is missing two
huge chunks: both menu and form support are not there.  I guess that
explains why people feel the need to write high-level UI wrappers for
Python curses: the high level stuff that curses does support is
missing from the Python bindings.

Adding a curses UI for my app might not be feasible after all...

--
Grant


From learn2program at gmail.com  Mon Apr 24 14:36:51 2023
From: learn2program at gmail.com (Alan Gauld)
Date: Mon, 24 Apr 2023 19:36:51 +0100
Subject: Python curses missing form library?
In-Reply-To: <6446adb5.5e0a0220.6fef5.3633@mx.google.com>
References: <6446adb5.5e0a0220.6fef5.3633@mx.google.com>
Message-ID: <97e5f793-7348-7c62-f928-61b54fd3886f@yahoo.co.uk>

On 24/04/2023 17:26, Grant Edwards wrote:
> Does the Python curses support in the standard library not include
> support for the curses form library? It seems to include support for
> the panel library, but I can't find any mention of the form library.

I don't believe so. If you are building terminal based form-type
apps the best bet seems to be urwid. I haven't used it in anger
but the beginner docs I saw looked promising.

-- 
Alan G
Author of the Learn to Program web site
http://www.alan-g.me.uk/
http://www.amazon.com/author/alan_gauld
Follow my photo-blog on Flickr at:
http://www.flickr.com/photos/alangauldphotos



From mats at wichmann.us  Mon Apr 24 14:39:49 2023
From: mats at wichmann.us (Mats Wichmann)
Date: Mon, 24 Apr 2023 12:39:49 -0600
Subject: Is npyscreen still alive?
In-Reply-To: <6446af25.050a0220.ed912.397a@mx.google.com>
References: <6442f8c9.050a0220.3ed35.17c6@mx.google.com>
 <FF7D8DCA-73CB-461E-A885-23CC6D11965B@barrys-emacs.org>
 <5ad249e5-5c11-a30d-106a-e4a5a21abbf4@gmail.com>
 <64468c66.050a0220.c3e8f.372e@mx.google.com>
 <6446af25.050a0220.ed912.397a@mx.google.com>
Message-ID: <b33773e8-c7ba-b4ef-ec20-10cb213c5a58@wichmann.us>

On 4/24/23 10:32, Grant Edwards wrote:
> On 2023-04-24, Grant Edwards <grant.b.edwards at gmail.com> wrote:
> 
>> The other big advantage of an ncurses program is that since curses
>> support is in the std library, a curses app is simpler to
>> distribute.  Right now, the application is a single .py file you
>> just copy to the destination machine and run.  It supports
>> command-line use and a Tk GUI. I can add an ncurses "CUI" without
>> having to either adopt a more complex bundling mechanism that
>> requires it to be "installed" or require that users install
>> dependencies via pip/apt/yum/whatever.
> 
> However... I just realized that Python's curses support is missing two
> huge chunks: both menu and form support are not there.  I guess that
> explains why people feel the need to write high-level UI wrappers for
> Python curses: the high level stuff that curses does support is
> missing from the Python bindings.
> 
> Adding a curses UI for my app might not be feasible after all...
> 
> --
> Grant
> 

I guess it's also worth mentioning that Python curses doesn't work out 
of the box on Windows - because the actual curses library isn't commonly 
present on Windows. It's not hard to get hold of builds (check PyPI) but 
that means it's no longer "standard".





From grant.b.edwards at gmail.com  Mon Apr 24 14:55:34 2023
From: grant.b.edwards at gmail.com (Grant Edwards)
Date: Mon, 24 Apr 2023 11:55:34 -0700 (PDT)
Subject: Python curses missing form library?
References: <6446adb5.5e0a0220.6fef5.3633@mx.google.com>
 <97e5f793-7348-7c62-f928-61b54fd3886f@yahoo.co.uk>
Message-ID: <6446d0a6.050a0220.f74f6.3aeb@mx.google.com>

On 2023-04-24, Alan Gauld <learn2program at gmail.com> wrote:
> On 24/04/2023 17:26, Grant Edwards wrote:
>> Does the Python curses support in the standard library not include
>> support for the curses form library? It seems to include support for
>> the panel library, but I can't find any mention of the form library.
>
> I don't believe so. If you are building terminal based form-type
> apps the best bet seems to be urwid. I haven't used it in anger
> but the beginner docs I saw looked promising.

urwid does indeed look nice, but it would require doing the whole
bundling and installing thing. I was hoping to avoid that by sticking
with stdlib and curses.

--
Grant



From grant.b.edwards at gmail.com  Mon Apr 24 14:59:54 2023
From: grant.b.edwards at gmail.com (Grant Edwards)
Date: Mon, 24 Apr 2023 11:59:54 -0700 (PDT)
Subject: Is npyscreen still alive?
References: <6442f8c9.050a0220.3ed35.17c6@mx.google.com>
 <FF7D8DCA-73CB-461E-A885-23CC6D11965B@barrys-emacs.org>
 <5ad249e5-5c11-a30d-106a-e4a5a21abbf4@gmail.com>
 <64468c66.050a0220.c3e8f.372e@mx.google.com>
 <6446af25.050a0220.ed912.397a@mx.google.com>
 <b33773e8-c7ba-b4ef-ec20-10cb213c5a58@wichmann.us>
Message-ID: <6446d1aa.920a0220.3a115.3c0d@mx.google.com>

On 2023-04-24, Mats Wichmann <mats at wichmann.us> wrote:
> On 4/24/23 10:32, Grant Edwards wrote:
>
>> However... I just realized that Python's curses support is missing two
>> huge chunks: both menu and form support are not there.  I guess that
>> explains why people feel the need to write high-level UI wrappers for
>> Python curses: the high level stuff that curses does support is
>> missing from the Python bindings.
>> 
>> Adding a curses UI for my app might not be feasible after all...
>
> I guess it's also worth mentioning that Python curses doesn't work out 
> of the box on Windows - because the actual curses library isn't commonly 
> present on Windows. It's not hard to get hold of builds (check PyPI) but 
> that means it's no longer "standard".

That's a good point. I neglected to mention that the use case for
curses UI app is to run on headless Linux servers. It needs to work
when run on a Linux by a user logged in via Putty on Windows, but I
have no need to execute the application in curses-mode on Windows.

--
Grant




From torriem at gmail.com  Mon Apr 24 15:17:03 2023
From: torriem at gmail.com (Michael Torrie)
Date: Mon, 24 Apr 2023 13:17:03 -0600
Subject: Is npyscreen still alive?
In-Reply-To: <64468c66.050a0220.c3e8f.372e@mx.google.com>
References: <6442f8c9.050a0220.3ed35.17c6@mx.google.com>
 <FF7D8DCA-73CB-461E-A885-23CC6D11965B@barrys-emacs.org>
 <5ad249e5-5c11-a30d-106a-e4a5a21abbf4@gmail.com>
 <64468c66.050a0220.c3e8f.372e@mx.google.com>
Message-ID: <678d716f-557d-2f05-c5e7-451797a9a35a@gmail.com>

On 4/24/23 08:04, Grant Edwards wrote:
> Is putty running on Windows a "modern terminal emulator" in this
> context?  After observing some of the local IT types work, I suspect
> that will be a common use-case for the app I'm working on.

Yes, Putty qualifies as a "modern terminal emulator."  It supports UTF-8
and unicode fonts.  And the mouse events work as well.  The only catch
is the default font is courier new which seems to not have some of the
line drawing characters in it. But if I change to something like
Cascadia Code it looks very good.


From info at tundraware.com  Mon Apr 24 19:10:56 2023
From: info at tundraware.com (Tim Daneliuk)
Date: Mon, 24 Apr 2023 18:10:56 -0500
Subject: Is npyscreen still alive?
In-Reply-To: <curses-20230424151328@ram.dialup.fu-berlin.de>
References: <6442f8c9.050a0220.3ed35.17c6@mx.google.com>
 <FF7D8DCA-73CB-461E-A885-23CC6D11965B@barrys-emacs.org>
 <5ad249e5-5c11-a30d-106a-e4a5a21abbf4@gmail.com>
 <64468c66.050a0220.c3e8f.372e@mx.google.com>
 <mailman.157.1682345066.20750.python-list@python.org>
 <curses-20230424151328@ram.dialup.fu-berlin.de>
Message-ID: <0tejhj-9uq2.ln1@oceanview.tundraware.com>

On 4/24/23 09:14, Stefan Ram wrote:
> Grant Edwards <grant.b.edwards at gmail.com> writes:
>> The other big advantage of an ncurses program is that since curses
>> support is in the std library, a curses app is simpler to distribute.
> 
>    IIRC curses is not in the standard library /on Windows/. I miss
>    a platform independent (well, at least for Linux, Mac, and
>    Windows) package with curses features in the standard library.
> 
> 


That's correct (or was, last time I looked).  For this reason, I
resorted to using tkinter for the twander file browser.  While
it works, the code needs a complete rethink and to be written
to be Python3 compatible.  Perhaps when/if that happens, something
like Textual need serious consideration.

tkinter works, but is showing its age.  So a fresher look without
all the burden of X and or requiring a browser, while also giving
you that option is appealing.

From info at tundraware.com  Mon Apr 24 19:13:08 2023
From: info at tundraware.com (Tim Daneliuk)
Date: Mon, 24 Apr 2023 18:13:08 -0500
Subject: Is npyscreen still alive?
In-Reply-To: <mailman.160.1682353961.20750.python-list@python.org>
References: <6442f8c9.050a0220.3ed35.17c6@mx.google.com>
 <FF7D8DCA-73CB-461E-A885-23CC6D11965B@barrys-emacs.org>
 <5ad249e5-5c11-a30d-106a-e4a5a21abbf4@gmail.com>
 <64468c66.050a0220.c3e8f.372e@mx.google.com>
 <6446af25.050a0220.ed912.397a@mx.google.com>
 <mailman.160.1682353961.20750.python-list@python.org>
Message-ID: <8f7af4f4-6843-8449-cd6a-fd1c0d294646@tundraware.com>

On 4/24/23 11:32, Grant Edwards wrote:
> On 2023-04-24, Grant Edwards <grant.b.edwards at gmail.com> wrote:
> 
>> The other big advantage of an ncurses program is that since curses
>> support is in the std library, a curses app is simpler to
>> distribute.  Right now, the application is a single .py file you
>> just copy to the destination machine and run.  It supports
>> command-line use and a Tk GUI. I can add an ncurses "CUI" without
>> having to either adopt a more complex bundling mechanism that
>> requires it to be "installed" or require that users install
>> dependencies via pip/apt/yum/whatever.
> 
> However... I just realized that Python's curses support is missing two
> huge chunks: both menu and form support are not there.  I guess that
> explains why people feel the need to write high-level UI wrappers for
> Python curses: the high level stuff that curses does support is
> missing from the Python bindings.
> 
> Adding a curses UI for my app might not be feasible after all...
> 
> --
> Grant
> 


That's because the Gods Of Ancient Internets knew that all you
ever really need is VT220 escape sequences ... unless you
are one of the heathens that still program in HLLAPI on 327x
machinery ....   (I kid, I kid, NO one needs that pain ...)


From rob.cliffe at btinternet.com  Sat Apr 22 09:56:02 2023
From: rob.cliffe at btinternet.com (Rob Cliffe)
Date: Sat, 22 Apr 2023 14:56:02 +0100
Subject: Question regarding unexpected behavior in using __enter__ method
In-Reply-To: <CAEGro7UrWuNKwBV8HuW8geMk+NM4T=4_DRfztT1p0Md1EcTW3A@mail.gmail.com>
References: <CAEGro7UrWuNKwBV8HuW8geMk+NM4T=4_DRfztT1p0Md1EcTW3A@mail.gmail.com>
Message-ID: <70c4ee88-a9c5-a7d9-7404-aae558ccbda7@btinternet.com>

This puzzled me at first, but I think others have nailed it.? It is not 
to do with the 'with' statement, but with the way functions are defined.
When a class is instantiated, as in x=X():
 ??? the instance object gets (at least in effect), as attributes, 
copies of functions defined *in the class* (using def or lambda) but 
they become "bound methods", i.e. bound to the instance.? Whenever they 
are called, they will be called with the instance as the first argument, 
aka self:
 ??? class X(object):
 ??? ??? def func(*args, **kargs): pass
 ??? x = X()
 ??? y = ()
x.func and y.func are two *different" functions.? When x.func is called, 
x is added as the first argument.? When y.func is called. y is added as 
the first argument.
 ???? boundFunc = y.func
 ??? boundFunc() # Adds y as first argument.
Indeed, these functions have an attribute called __self__ whose value is 
... you guessed it ... the object they are bound to
When a function is defined outside of a class, it remains a simple 
function, not bound to any object.? It does not have a __self__ 
attribute.? Neither does a built-in type such as 'int'.
Nor for that matter does the class function X.func:
 ??? X.func() # Called with no arguments

Best wishes
Rob Cliffe

On 20/04/2023 23:44, Lorenzo Catoni wrote:
> Dear Python Mailing List members,
>
> I am writing to seek your assistance in understanding an unexpected
> behavior that I encountered while using the __enter__ method. I have
> provided a code snippet below to illustrate the problem:
>
> ```
>>>> class X:
> ...     __enter__ = int
> ...     __exit__ = lambda *_: None
> ...
>>>> with X() as x:
> ...     pass
> ...
>>>> x
> 0
> ```
> As you can see, the __enter__ method does not throw any exceptions and
> returns the output of "int()" correctly. However, one would normally expect
> the input parameter "self" to be passed to the function.
>
> On the other hand, when I implemented a custom function in place of the
> __enter__ method, I encountered the following TypeError:
>
> ```
>>>> def myint(*a, **kw):
> ...     return int(*a, **kw)
> ...
>>>> class X:
> ...     __enter__ = myint
> ...     __exit__ = lambda *_: None
> ...
>>>> with X() as x:
> ...     pass
> ...
> Traceback (most recent call last):
>    File "<stdin>", line 1, in <module>
>    File "<stdin>", line 2, in myint
> TypeError: int() argument must be a string, a bytes-like object or a real
> number, not 'X'
> ```
> Here, the TypeError occurred because "self" was passed as an input
> parameter to "myint". Can someone explain why this unexpected behavior
> occurs only in the latter case?
>
> I tested this issue on the following Python versions, and the problem
> persists on all of them:
> - Python 3.8.10 (default, Nov 14 2022, 12:59:47) [GCC 9.4.0] on linux
> - Python 3.10.10 (main, Feb  8 2023, 14:50:01) [GCC 9.4.0] on linux
> - Python 3.10.7 (tags/v3.10.7:6cc6b13, Sep  5 2022, 14:08:36) [MSC v.1933
> 64 bit (AMD64)] on win32
>
> I appreciate any input or insights that you might have on this matter.
>
> Thank you for your help in advance!
>
> Best regards,
> Lorenzo Catoni


From avi.e.gross at gmail.com  Tue Apr 25 23:47:06 2023
From: avi.e.gross at gmail.com (avi.e.gross at gmail.com)
Date: Tue, 25 Apr 2023 23:47:06 -0400
Subject: Question regarding unexpected behavior in using __enter__ method
In-Reply-To: <70c4ee88-a9c5-a7d9-7404-aae558ccbda7@btinternet.com>
References: <CAEGro7UrWuNKwBV8HuW8geMk+NM4T=4_DRfztT1p0Md1EcTW3A@mail.gmail.com>
 <70c4ee88-a9c5-a7d9-7404-aae558ccbda7@btinternet.com>
Message-ID: <008f01d977f1$c56eb1d0$504c1570$@gmail.com>


I think you got that right, Rob. A method created in a class is normally expected to care about the class in the sense that it often wants to access internal aspects and is given a "this" or "self" or whatever name you choose as a first argument. As noted, it is sometimes possible to create a function attached not to an object but to the class itself  as in, I think, the math class that is not normally instantiated as an object but lets you use things like math.pi and math.cos() and so on.

A comment on dunder methods in python is that they have a sort of purpose albeit you can hijack some to do other things. The protocol for WITH is a bit slippery as __enter__() and __exit__ are expected to do some abstract things that loosely are intended to set up something at the start in a way that will be (guaranteed) to be done if the exit routine is called when done. This can be about opening a file, or network connection and later closing it, or setting up some data structure and freeing the memory at the end, but it could be ANYTHING you feel like. For example, it can turn logging of some kind on and off and also compress the log file at the end. Or it could set up changes to the object that are there for the duration of the WITH and then reset the changes back at the end. 

An imaginary example might be to start caching what some methods are doing or replace a method by another, then empty the cache at the end or put back the redirected one.

And if what you want done at the beginning or end is outside the object being worked on, fine. Consider wrapping your function call in a simple function that calls the one you want after ignoring or removing the first argument. There are decorators that can do things like that.

So if you want int() or some existing plain non-member function, define an f() whose body calls int() with all arguments passed along other than the first. 

I just wrote and tested a trivial example where for some reason you just want to call sum() either with an iterable argument or with a second unnamed or named argument that specified a start you can add to. If this is written as a class method, it would have a first argument of "self" to ignore so I simulate that here:

def plusone(first, *rest, **named):
  return(sum(*rest, **named))

If you call this as below with valid arguments, it sort of swallows the first argument and passes the rest along:

>>> plusone("ignore", [])
0
>>> plusone("ignore", [1,2,3])
6
>>> plusone("ignore", [1,2,3], 100)
106
>>> plusone("ignore", range(7), start=100)
121

Yes, anything like this adds overhead. It does add flexibility and allows you to hijack the WITH protocol to do other things perhaps never anticipated but that may make sense, such as changing a companion object rather than the current one. But you need to live within some rules to do things and that means knowing there will be a first argument.

Avi
-----Original Message-----
From: Python-list <python-list-bounces+avi.e.gross=gmail.com at python.org> On Behalf Of Rob Cliffe via Python-list
Sent: Saturday, April 22, 2023 9:56 AM
To: Lorenzo Catoni <l.catoni.99 at gmail.com>; python-list at python.org
Subject: Re: Question regarding unexpected behavior in using __enter__ method

This puzzled me at first, but I think others have nailed it.  It is not 
to do with the 'with' statement, but with the way functions are defined.
When a class is instantiated, as in x=X():
     the instance object gets (at least in effect), as attributes, 
copies of functions defined *in the class* (using def or lambda) but 
they become "bound methods", i.e. bound to the instance.  Whenever they 
are called, they will be called with the instance as the first argument, 
aka self:
     class X(object):
         def func(*args, **kargs): pass
     x = X()
     y = ()
x.func and y.func are two *different" functions.  When x.func is called, 
x is added as the first argument.  When y.func is called. y is added as 
the first argument.
      boundFunc = y.func
     boundFunc() # Adds y as first argument.
Indeed, these functions have an attribute called __self__ whose value is 
... you guessed it ... the object they are bound to
When a function is defined outside of a class, it remains a simple 
function, not bound to any object.  It does not have a __self__ 
attribute.  Neither does a built-in type such as 'int'.
Nor for that matter does the class function X.func:
     X.func() # Called with no arguments

Best wishes
Rob Cliffe

On 20/04/2023 23:44, Lorenzo Catoni wrote:
> Dear Python Mailing List members,
>
> I am writing to seek your assistance in understanding an unexpected
> behavior that I encountered while using the __enter__ method. I have
> provided a code snippet below to illustrate the problem:
>
> ```
>>>> class X:
> ...     __enter__ = int
> ...     __exit__ = lambda *_: None
> ...
>>>> with X() as x:
> ...     pass
> ...
>>>> x
> 0
> ```
> As you can see, the __enter__ method does not throw any exceptions and
> returns the output of "int()" correctly. However, one would normally expect
> the input parameter "self" to be passed to the function.
>
> On the other hand, when I implemented a custom function in place of the
> __enter__ method, I encountered the following TypeError:
>
> ```
>>>> def myint(*a, **kw):
> ...     return int(*a, **kw)
> ...
>>>> class X:
> ...     __enter__ = myint
> ...     __exit__ = lambda *_: None
> ...
>>>> with X() as x:
> ...     pass
> ...
> Traceback (most recent call last):
>    File "<stdin>", line 1, in <module>
>    File "<stdin>", line 2, in myint
> TypeError: int() argument must be a string, a bytes-like object or a real
> number, not 'X'
> ```
> Here, the TypeError occurred because "self" was passed as an input
> parameter to "myint". Can someone explain why this unexpected behavior
> occurs only in the latter case?
>
> I tested this issue on the following Python versions, and the problem
> persists on all of them:
> - Python 3.8.10 (default, Nov 14 2022, 12:59:47) [GCC 9.4.0] on linux
> - Python 3.10.10 (main, Feb  8 2023, 14:50:01) [GCC 9.4.0] on linux
> - Python 3.10.7 (tags/v3.10.7:6cc6b13, Sep  5 2022, 14:08:36) [MSC v.1933
> 64 bit (AMD64)] on win32
>
> I appreciate any input or insights that you might have on this matter.
>
> Thank you for your help in advance!
>
> Best regards,
> Lorenzo Catoni

-- 
https://mail.python.org/mailman/listinfo/python-list


From nntp.mbourne at spamgourmet.com  Wed Apr 26 15:41:50 2023
From: nntp.mbourne at spamgourmet.com (Mark Bourne)
Date: Wed, 26 Apr 2023 20:41:50 +0100
Subject: Question regarding unexpected behavior in using __enter__ method
In-Reply-To: <mailman.137.1682030890.20750.python-list@python.org>
References: <CAEGro7UrWuNKwBV8HuW8geMk+NM4T=4_DRfztT1p0Md1EcTW3A@mail.gmail.com>
 <mailman.137.1682030890.20750.python-list@python.org>
Message-ID: <u2bupv$1gvcc$1@dont-email.me>

Lorenzo Catoni wrote:
> Dear Python Mailing List members,
> 
> I am writing to seek your assistance in understanding an unexpected
> behavior that I encountered while using the __enter__ method. I have
> provided a code snippet below to illustrate the problem:
> 
> ```
>>>> class X:
> ...     __enter__ = int
> ...     __exit__ = lambda *_: None
> ...
>>>> with X() as x:
> ...     pass
> ...
>>>> x
> 0
> ```
> As you can see, the __enter__ method does not throw any exceptions and
> returns the output of "int()" correctly. However, one would normally expect
> the input parameter "self" to be passed to the function.
> 
> On the other hand, when I implemented a custom function in place of the
> __enter__ method, I encountered the following TypeError:
> 
> ```
>>>> def myint(*a, **kw):
> ...     return int(*a, **kw)
> ...
>>>> class X:
> ...     __enter__ = myint
> ...     __exit__ = lambda *_: None
> ...
>>>> with X() as x:
> ...     pass
> ...
> Traceback (most recent call last):
>    File "<stdin>", line 1, in <module>
>    File "<stdin>", line 2, in myint
> TypeError: int() argument must be a string, a bytes-like object or a real
> number, not 'X'
> ```
> Here, the TypeError occurred because "self" was passed as an input
> parameter to "myint". Can someone explain why this unexpected behavior
> occurs only in the latter case?
> 
> I tested this issue on the following Python versions, and the problem
> persists on all of them:
> - Python 3.8.10 (default, Nov 14 2022, 12:59:47) [GCC 9.4.0] on linux
> - Python 3.10.10 (main, Feb  8 2023, 14:50:01) [GCC 9.4.0] on linux
> - Python 3.10.7 (tags/v3.10.7:6cc6b13, Sep  5 2022, 14:08:36) [MSC v.1933
> 64 bit (AMD64)] on win32
> 
> I appreciate any input or insights that you might have on this matter.
> 
> Thank you for your help in advance!

Aside from other explanations and suggestions, the following definition 
of X also works:

class X:
     __enter__ = staticmethod(myint)
     __exit__ = lambda *_: None

Wrapping `myint` in a call to `staticmethod` is the same as using 
`@staticmethod` as a decorator on a method within the class, so the 
`self` parameter doesn't get passed.  Equivalent to:

class X:
     @staticmethod
     def __enter__(*a, **kw):
         return int(*a, **kw)
     __exit__ = lambda *_: None

Which in turn is just a neater way of doing:

class X:
     def __enter__(*a, **kw):
         return int(*a, **kw)
     __enter__ = staticmethod(__enter__)
     __exit__ = lambda *_: None

Those equivalents are a bit pointless, since no arguments will be passed 
into `__enter__` anyway in normal usage, but perhaps make it a bit 
clearer that the second example behaves as would be expected for a 
method of X (where the instance is passed as the first argument), and 
that it's the first example (with `__enter__ = int`) that should be a 
bit more surprising.  (I'm not sure there's much practical use for the 
original `__enter__ = int` either, but presumably that's just used as a 
cut-down demonstration).

-- 
Mark.

From fungus at amongus.com  Wed Apr 26 20:31:10 2023
From: fungus at amongus.com (Retrograde)
Date: Wed, 26 Apr 2023 20:31:10 -0400
Subject: replacement for nntplib on Python3
Message-ID: <20230426203110.fb1a0de75df0296488b16381@amongus.com>

I used to use a script that relied on nntplib, which is currently still
available in Python3 but scheduled for deprecation in the near future.
What would be a suitable replacement?

-- 
Retrograde <fungus at amongus.com.invalid>

From skip.montanaro at gmail.com  Wed Apr 26 21:56:09 2023
From: skip.montanaro at gmail.com (Skip Montanaro)
Date: Wed, 26 Apr 2023 20:56:09 -0500
Subject: replacement for nntplib on Python3
In-Reply-To: <20230426203110.fb1a0de75df0296488b16381@amongus.com>
References: <20230426203110.fb1a0de75df0296488b16381@amongus.com>
Message-ID: <CANc-5UzGNfC+AQD5iTkW7vUURPQqWh2sGYGh59S3sOfk21ZfHg@mail.gmail.com>

You could create a git repo with just nntplib and generate a package on
PyPI, then use that when running a version of Python which lacks nntplib.

Skip

On Wed, Apr 26, 2023, 8:42 PM Retrograde <fungus at amongus.com> wrote:

> I used to use a script that relied on nntplib, which is currently still
> available in Python3 but scheduled for deprecation in the near future.
> What would be a suitable replacement?
>
> --
> Retrograde <fungus at amongus.com.invalid>
> --
> https://mail.python.org/mailman/listinfo/python-list
>

From pozzugno at gmail.com  Fri Apr 28 06:31:36 2023
From: pozzugno at gmail.com (pozz)
Date: Fri, 28 Apr 2023 12:31:36 +0200
Subject: Multithreading? How?
Message-ID: <u2g7a7$2bet6$1@dont-email.me>

I need to develop a Python application that is a sort of gateway between 
to networks: a "serial bus" network (think of a serial port or a USB 
connection) and a MQTT connection (in my case, it's AWS IoT service).

On the bus, a proprietary protocol is implemented. From the bus, the app 
knows the status of the system (think of a simple ON/OFF status).
The user can retrieve the status of the system through MQTT: it sends a 
message to read/status MQTT topic and receive back a message with the 
current status on read/status/reply MQTT topic. Of course, they are just 
examples.

On the contrary, when the app detects a status change reported from the 
serial bus (think of a transition from ON to OFF), it sends a MQTT message.

I'm thinking to split the application in three classes: Bus, App and 
IoT. Bus and IoT are also threads.
The thread of Bus manages the serial protocol, while the thread of IoT 
manages MQTT connection with the broker (the server).

However I don't know if it could be a good architecture. Suppone Bus 
thread receives a new status from the system. In the context of 
ThreadBus, the object Bus could call a method of App object:

   app.set_status(new_status_from_the_bus)

In the App I have:

   class App():
     ..
     def set_status(new_status):  # Could be called from ThreadBus
       if new_status != self.new_status:
         self.new_status = new_status
         # Do some actions on status change

     def get_status():            # Could be called from ThreadIoT
       return self.status

Of course, IoT object needs to know the current status of the system 
when a message is received from MQTT. So ThreadIoT could call 
app.get_status().

I think this architecture has some problems with race conditions or 
threads synchronization. What happens if IoT calls get_status() exactly 
when set_status() called by ThreadBus is executing? If status is a big 
data structure, set_status() could be interrupted by get_status() that 
could get a completely corrupted status, because it was only partly 
updated by set_status().

I know I can use locks or semaphores in get_status() and set_status(), 
but I don't know if this is a good approach. Consider that the system is 
complex, it isn't composed by a simple single status. It has many many 
parameters that are collected from the serial bus. Should I use a lock 
for every [get|set]_status(), [get|set]_dimensions(), 
[get|set]_battery_level(), [get|set]_mains_present(), and so on?


Another possibility is to use a Queue for Bus and a Queue for IoT. So 
the set_status(new_status) called from Bus object will be transformed in 
a put in the queue:

   app_queue.put({"type": "new_status", "data": ...})

However how could be transformed the get_status() from IoT? How the 
return value (the current status) is real retrieved?

   class IoT():
     ..
     def status_request_from_MQTT():
       app_queue.put({"type": "get_status"})
       # How to get the status to return?
       return current_status

Should the app put the status on the same queue and should IoT waits for 
a new message in the Queue?

     def status_request_from_MQTT():
       app_queue.put({"type": "get_status"})
       try:
         current_status = app_queue.get(timeout=10)
       except Empty:
         # What to do?
       return current_status


Again another approach is to avoid multi-threading at all and create a 
single "main loop" function that waits at the same time for incoming 
events on the serial bus and MQTT (how?). I don't know if this could be 
done in my case, because I'm using awscrt Python module and it works 
through callbacks that I think is called from another thread.


Any suggestions on this architecture?

From cl at isbd.net  Fri Apr 28 11:55:41 2023
From: cl at isbd.net (Chris Green)
Date: Fri, 28 Apr 2023 16:55:41 +0100
Subject: How to 'ignore' an error in Python?
Message-ID: <ts6thj-fc3k.ln1@esprimo.zbmc.eu>

I'm sure I'm missing something obvious here but I can't see an elegant
way to do this.  I want to create a directory, but if it exists it's
not an error and the code should just continue.

So, I have:-

    for dirname in listofdirs:
        try:
            os.mkdir(dirname)
        except FileExistsError:
            # so what can I do here that says 'carry on regardless'
        except:
            # handle any other error, which is really an error

        # I want code here to execute whether or not dirname exists


Do I really have to use a finally: block?  It feels rather clumsy.

I suppose I could test if the directory exists before the os.mkdir()
but again that feels a bit clumsy somehow.

I suppose also I could use os.mkdirs() with exist_ok=True but again
that feels vaguely wrong somehow.


-- 
Chris Green
?

From mats at wichmann.us  Fri Apr 28 12:39:36 2023
From: mats at wichmann.us (Mats Wichmann)
Date: Fri, 28 Apr 2023 10:39:36 -0600
Subject: How to 'ignore' an error in Python?
In-Reply-To: <ts6thj-fc3k.ln1@esprimo.zbmc.eu>
References: <ts6thj-fc3k.ln1@esprimo.zbmc.eu>
Message-ID: <606727f8-70a5-e8a6-c664-f539d9f82567@wichmann.us>

On 4/28/23 09:55, Chris Green wrote:
> I'm sure I'm missing something obvious here but I can't see an elegant
> way to do this.  I want to create a directory, but if it exists it's
> not an error and the code should just continue.
> 
> So, I have:-
> 
>      for dirname in listofdirs:
>          try:
>              os.mkdir(dirname)
>          except FileExistsError:
>              # so what can I do here that says 'carry on regardless'
>          except:
>              # handle any other error, which is really an error
> 
>          # I want code here to execute whether or not dirname exists
> 
> 
> Do I really have to use a finally: block?  It feels rather clumsy.

For this specific case, you can use os.makedirs:

os.makedirs(dirname, exist_ok=True)

The mkdir in pathlib also takes the exist_ok flag


As to the way you asked the question, you can use "pass" or the ellipses 
for the "# so what can I do here"



From python at mrabarnett.plus.com  Fri Apr 28 13:05:23 2023
From: python at mrabarnett.plus.com (MRAB)
Date: Fri, 28 Apr 2023 18:05:23 +0100
Subject: How to 'ignore' an error in Python?
In-Reply-To: <ts6thj-fc3k.ln1@esprimo.zbmc.eu>
References: <ts6thj-fc3k.ln1@esprimo.zbmc.eu>
Message-ID: <02181fec-dcd3-abdf-d1dd-648e6c74c78e@mrabarnett.plus.com>

On 2023-04-28 16:55, Chris Green wrote:
> I'm sure I'm missing something obvious here but I can't see an elegant
> way to do this.  I want to create a directory, but if it exists it's
> not an error and the code should just continue.
> 
> So, I have:-
> 
>      for dirname in listofdirs:
>          try:
>              os.mkdir(dirname)
>          except FileExistsError:
>              # so what can I do here that says 'carry on regardless'
>          except:
>              # handle any other error, which is really an error
> 
>          # I want code here to execute whether or not dirname exists
> 
> 
> Do I really have to use a finally: block?  It feels rather clumsy.
> 
> I suppose I could test if the directory exists before the os.mkdir()
> but again that feels a bit clumsy somehow.
> 
> I suppose also I could use os.mkdirs() with exist_ok=True but again
> that feels vaguely wrong somehow.
> 
I'd do this:

     from contextlib import suppress

     for dirname in listofdirs:
         with suppress(FileExistsError):
             os.mkdir(dirname)


From mats at wichmann.us  Fri Apr 28 13:40:53 2023
From: mats at wichmann.us (Mats Wichmann)
Date: Fri, 28 Apr 2023 11:40:53 -0600
Subject: How to 'ignore' an error in Python?
In-Reply-To: <02181fec-dcd3-abdf-d1dd-648e6c74c78e@mrabarnett.plus.com>
References: <ts6thj-fc3k.ln1@esprimo.zbmc.eu>
 <02181fec-dcd3-abdf-d1dd-648e6c74c78e@mrabarnett.plus.com>
Message-ID: <a3f85cdd-c4d2-5083-5868-92b380d55203@wichmann.us>

On 4/28/23 11:05, MRAB wrote:
> On 2023-04-28 16:55, Chris Green wrote:
>> I'm sure I'm missing something obvious here but I can't see an elegant
>> way to do this.? I want to create a directory, but if it exists it's
>> not an error and the code should just continue.
>>
>> So, I have:-
>>
>> ???? for dirname in listofdirs:
>> ???????? try:
>> ???????????? os.mkdir(dirname)
>> ???????? except FileExistsError:
>> ???????????? # so what can I do here that says 'carry on regardless'
>> ???????? except:
>> ???????????? # handle any other error, which is really an error

> I'd do this:
> 
>  ??? from contextlib import suppress
> 
>  ??? for dirname in listofdirs:
>  ??????? with suppress(FileExistsError):
>  ??????????? os.mkdir(dirname)

I'm fond of that approach too, though you can't use if it you really 
wanted to do the

           except:
               # handle any other error, which is really an error

If you're okay letting Python just raise whatever other error it found, 
then great!



From cs at cskk.id.au  Fri Apr 28 21:36:07 2023
From: cs at cskk.id.au (Cameron Simpson)
Date: Sat, 29 Apr 2023 11:36:07 +1000
Subject: How to 'ignore' an error in Python?
In-Reply-To: <ts6thj-fc3k.ln1@esprimo.zbmc.eu>
References: <ts6thj-fc3k.ln1@esprimo.zbmc.eu>
Message-ID: <ZEx0h1fEX+Qe3+vp@cskk.homeip.net>

On 28Apr2023 16:55, Chris Green <cl at isbd.net> wrote:
>    for dirname in listofdirs:
>        try:
>            os.mkdir(dirname)
>        except FileExistsError:
>            # so what can I do here that says 'carry on regardless'
>        except:
>            # handle any other error, which is really an error
>
>        # I want code here to execute whether or not dirname exists
>
>Do I really have to use a finally: block?  It feels rather clumsy.

You don't. Provided the "handle any other error" part reraises or does a 
break/continue, so as to skip the bottom of the loop body.

     ok = true
     for dirname in listofdirs:
         try:
             os.mkdir(dirname)
         except FileExistsError:
             pass
         except Exception as e:
             warning("mkdir(%r): %s", dirname, e)
             ok = False
             continue
         rest of the loop body ...
     if not ok:
         ... not all directories made ...

2 notes on the above:
- catching Exception, not a bare except (which catches a rather broader 
   suit of things)
- reporting the other exception

Cheers,
Cameron Simpson <cs at cskk.id.au>

From cs at cskk.id.au  Fri Apr 28 21:32:52 2023
From: cs at cskk.id.au (Cameron Simpson)
Date: Sat, 29 Apr 2023 11:32:52 +1000
Subject: How to 'ignore' an error in Python?
In-Reply-To: <606727f8-70a5-e8a6-c664-f539d9f82567@wichmann.us>
References: <606727f8-70a5-e8a6-c664-f539d9f82567@wichmann.us>
Message-ID: <ZExzxIZh3GVjDyrs@cskk.homeip.net>

On 28Apr2023 10:39, Mats Wichmann <mats at wichmann.us> wrote:
>For this specific case, you can use os.makedirs:
>os.makedirs(dirname, exist_ok=True)

I'm not a great fan of makedirs because it will make all the missing 
components, not just the final one. So as an example, if you've got a 
NAS mounted backup area at eg:

     /mnt/nas/backups/the-thing/backups-subdir

and your config file has this mistyped as:

     /mn/nas/backups/the-thing/backups-subdir

and makedirs is used, then it will make the backup area on eg the root 
drive where there's no room. (I'm looking at you, Docker, grr). There 
are plenty of similar situations.

Because of this I usually am prepared to make a missing final component 
with mkdir(), but not a potentially deep path with makedirs().

Cheers,
Cameron Simpson <cs at cskk.id.au>

From kushal at locationd.net  Sat Apr 29 00:18:45 2023
From: kushal at locationd.net (Kushal Kumaran)
Date: Fri, 28 Apr 2023 21:18:45 -0700
Subject: How to 'ignore' an error in Python?
In-Reply-To: <ts6thj-fc3k.ln1@esprimo.zbmc.eu> (Chris Green's message of "Fri, 
 28 Apr 2023 16:55:41 +0100")
References: <ts6thj-fc3k.ln1@esprimo.zbmc.eu>
Message-ID: <874joznwwq.fsf@copper.locationd.net>

On Fri, Apr 28 2023 at 04:55:41 PM, Chris Green <cl at isbd.net> wrote:
> I'm sure I'm missing something obvious here but I can't see an elegant
> way to do this.  I want to create a directory, but if it exists it's
> not an error and the code should just continue.
>
> So, I have:-
>
>     for dirname in listofdirs:
>         try:
>             os.mkdir(dirname)
>         except FileExistsError:
>             # so what can I do here that says 'carry on regardless'
>         except:
>             # handle any other error, which is really an error
>
>         # I want code here to execute whether or not dirname exists
>
>
> Do I really have to use a finally: block?  It feels rather clumsy.
>
> I suppose I could test if the directory exists before the os.mkdir()
> but again that feels a bit clumsy somehow.
>
> I suppose also I could use os.mkdirs() with exist_ok=True but again
> that feels vaguely wrong somehow.
>

Why does exist_ok=True feel wrong to you?  This is exactly what it is
there for.

-- 
regards,
kushal

From rosuav at gmail.com  Sat Apr 29 00:33:48 2023
From: rosuav at gmail.com (Chris Angelico)
Date: Sat, 29 Apr 2023 14:33:48 +1000
Subject: How to 'ignore' an error in Python?
In-Reply-To: <874joznwwq.fsf@copper.locationd.net>
References: <ts6thj-fc3k.ln1@esprimo.zbmc.eu>
 <874joznwwq.fsf@copper.locationd.net>
Message-ID: <CAPTjJmop-tX2QPxZLD9hq_nCn08nuEEAK7DM4xVA25v5-q096Q@mail.gmail.com>

On Sat, 29 Apr 2023 at 14:27, Kushal Kumaran <kushal at locationd.net> wrote:
>
> On Fri, Apr 28 2023 at 04:55:41 PM, Chris Green <cl at isbd.net> wrote:
> > I'm sure I'm missing something obvious here but I can't see an elegant
> > way to do this.  I want to create a directory, but if it exists it's
> > not an error and the code should just continue.
> >
> > So, I have:-
> >
> >     for dirname in listofdirs:
> >         try:
> >             os.mkdir(dirname)
> >         except FileExistsError:
> >             # so what can I do here that says 'carry on regardless'
> >         except:
> >             # handle any other error, which is really an error
> >
> >         # I want code here to execute whether or not dirname exists
> >
> >
> > Do I really have to use a finally: block?  It feels rather clumsy.
> >
> > I suppose I could test if the directory exists before the os.mkdir()
> > but again that feels a bit clumsy somehow.
> >
> > I suppose also I could use os.mkdirs() with exist_ok=True but again
> > that feels vaguely wrong somehow.
> >
>
> Why does exist_ok=True feel wrong to you?  This is exactly what it is
> there for.
>

Using mkdirs when you only want to make one is inviting problems of
being subtly wrong, where it creates too many levels of directory.
Personally, I would just do:

try: os.mkdir(dirname)
except FileExistsError: pass

and not try to handle anything else at all.

ChrisA

From avi.e.gross at gmail.com  Sat Apr 29 13:41:41 2023
From: avi.e.gross at gmail.com (avi.e.gross at gmail.com)
Date: Sat, 29 Apr 2023 13:41:41 -0400
Subject: How to 'ignore' an error in Python?
In-Reply-To: <874joznwwq.fsf@copper.locationd.net>
References: <ts6thj-fc3k.ln1@esprimo.zbmc.eu>
 <874joznwwq.fsf@copper.locationd.net>
Message-ID: <006301d97ac1$dbc30c10$93492430$@gmail.com>

I get a tad suspicious when someone keeps telling us every offered solution
does not feel right. Perhaps they are not using the right programming
language as clearly they are not willing to work with it as it is not as it
should be.

 After all the back and forth, there are several choices including accepting
whatever method is least annoying to them, or rolling their own.

Create a function with a name like do_it_my_way_or_the_highway() that uses
any acceptable method but completely hides the implementation details from
your code. One way might be to get the source code and copy it under your
own name and modify it so the default is to do what you want. It can even be
as simple as a small wrapper that forwards to the original function with a
keyword set by default.

After all, this does seem to be a bit like what you are asking for. A way to
call your functionality that does it the way you insist it should have been
designed, never mind that many others are happy with it as it is and use the
techniques mentioned at other times.

But I do have sympathy. I have seen lots of simple-minded code that seems to
cleanly and elegantly solve a problem as long as all the ducks are just-so.
Then someone points out that the code may break if it is called with some
other type than expected or if it tries to divide by zero or if something
else changes a variable between the time you looked at it and the time you
update it and so on. Next thing you know, your code grows (even
exponentially) to try to handle all these conditions and includes lots of
nested IF statements and all kinds of TRY statements and slows down and is
hard to read or even think about. And to make it worse, people ask for your
formerly simple function to become a Swiss army knife that accepts oodles of
keyword arguments that alter various aspects of the behavior!

So, yes, it can feel wrong. But so what? Sometimes you can find ways to
reduce the complexity and sometimes you simply create a few accessory
functions you can use that tame the complexity a bit. But almost any complex
program in any language can require a loss of simplicity.


-----Original Message-----
From: Python-list <python-list-bounces+avi.e.gross=gmail.com at python.org> On
Behalf Of Kushal Kumaran
Sent: Saturday, April 29, 2023 12:19 AM
To: python-list at python.org
Subject: Re: How to 'ignore' an error in Python?

On Fri, Apr 28 2023 at 04:55:41 PM, Chris Green <cl at isbd.net> wrote:
> I'm sure I'm missing something obvious here but I can't see an elegant
> way to do this.  I want to create a directory, but if it exists it's
> not an error and the code should just continue.
>
> So, I have:-
>
>     for dirname in listofdirs:
>         try:
>             os.mkdir(dirname)
>         except FileExistsError:
>             # so what can I do here that says 'carry on regardless'
>         except:
>             # handle any other error, which is really an error
>
>         # I want code here to execute whether or not dirname exists
>
>
> Do I really have to use a finally: block?  It feels rather clumsy.
>
> I suppose I could test if the directory exists before the os.mkdir()
> but again that feels a bit clumsy somehow.
>
> I suppose also I could use os.mkdirs() with exist_ok=True but again
> that feels vaguely wrong somehow.
>

Why does exist_ok=True feel wrong to you?  This is exactly what it is
there for.

-- 
regards,
kushal
-- 
https://mail.python.org/mailman/listinfo/python-list


From greg.ewing at canterbury.ac.nz  Sat Apr 29 21:04:54 2023
From: greg.ewing at canterbury.ac.nz (Greg Ewing)
Date: Sun, 30 Apr 2023 13:04:54 +1200
Subject: How to 'ignore' an error in Python?
In-Reply-To: <u2jaep$2vu8n$1@dont-email.me>
References: <ts6thj-fc3k.ln1@esprimo.zbmc.eu>
 <874joznwwq.fsf@copper.locationd.net>
 <CAPTjJmop-tX2QPxZLD9hq_nCn08nuEEAK7DM4xVA25v5-q096Q@mail.gmail.com>
 <mailman.7.1682742840.13552.python-list@python.org>
 <u2j5qq$2v80c$1@dont-email.me> <name-20230429151834@ram.dialup.fu-berlin.de>
 <u2jaep$2vu8n$1@dont-email.me>
Message-ID: <kb5t5mFk6s4U1@mid.individual.net>

On 30/04/23 2:43 am, jak wrote:
> Maybe I expressed myself badly but I didn't mean to propose alternatives
> to the EAFP way but just to evaluate the possibility that it is not a
> folder.

If it's not a folder, you'll find out when the next thing you
try to do to it fails.

You could check for it earlier, but there's still the possibility
of a race condition -- someone could delete the folder and replace
it with a file in the meantime. Or just delete it and not replace
it with anything. So you need to be prepared to deal with failures
at any point.

-- 
Greg

From cl at isbd.net  Sat Apr 29 03:32:25 2023
From: cl at isbd.net (Chris Green)
Date: Sat, 29 Apr 2023 08:32:25 +0100
Subject: How to 'ignore' an error in Python?
References: <ts6thj-fc3k.ln1@esprimo.zbmc.eu>
 <874joznwwq.fsf@copper.locationd.net>
 <mailman.6.1682742349.13552.python-list@python.org>
Message-ID: <9ptuhj-nnhn.ln1@esprimo.zbmc.eu>

Kushal Kumaran <kushal at locationd.net> wrote:
> On Fri, Apr 28 2023 at 04:55:41 PM, Chris Green <cl at isbd.net> wrote:
> > I'm sure I'm missing something obvious here but I can't see an elegant
> > way to do this.  I want to create a directory, but if it exists it's
> > not an error and the code should just continue.
> >
> > So, I have:-
> >
> >     for dirname in listofdirs:
> >         try:
> >             os.mkdir(dirname)
> >         except FileExistsError:
> >             # so what can I do here that says 'carry on regardless'
> >         except:
> >             # handle any other error, which is really an error
> >
> >         # I want code here to execute whether or not dirname exists
> >
> >
> > Do I really have to use a finally: block?  It feels rather clumsy.
> >
> > I suppose I could test if the directory exists before the os.mkdir()
> > but again that feels a bit clumsy somehow.
> >
> > I suppose also I could use os.mkdirs() with exist_ok=True but again
> > that feels vaguely wrong somehow.
> >
> 
> Why does exist_ok=True feel wrong to you?  This is exactly what it is
> there for.
> 
It was rather using os.mekedirs() to create a single directory that
seemed wrong.  If os.mkdir() had exist_ok=True than that would have
been the obvious way to do it.

-- 
Chris Green
?

From cl at isbd.net  Sat Apr 29 03:34:41 2023
From: cl at isbd.net (Chris Green)
Date: Sat, 29 Apr 2023 08:34:41 +0100
Subject: How to 'ignore' an error in Python?
References: <ts6thj-fc3k.ln1@esprimo.zbmc.eu>
 <874joznwwq.fsf@copper.locationd.net>
 <CAPTjJmop-tX2QPxZLD9hq_nCn08nuEEAK7DM4xVA25v5-q096Q@mail.gmail.com>
 <mailman.7.1682742840.13552.python-list@python.org>
Message-ID: <httuhj-nnhn.ln1@esprimo.zbmc.eu>

Chris Angelico <rosuav at gmail.com> wrote:
> On Sat, 29 Apr 2023 at 14:27, Kushal Kumaran <kushal at locationd.net> wrote:
> >
> > On Fri, Apr 28 2023 at 04:55:41 PM, Chris Green <cl at isbd.net> wrote:
> > > I'm sure I'm missing something obvious here but I can't see an elegant
> > > way to do this.  I want to create a directory, but if it exists it's
> > > not an error and the code should just continue.
> > >
> > > So, I have:-
> > >
> > >     for dirname in listofdirs:
> > >         try:
> > >             os.mkdir(dirname)
> > >         except FileExistsError:
> > >             # so what can I do here that says 'carry on regardless'
> > >         except:
> > >             # handle any other error, which is really an error
> > >
> > >         # I want code here to execute whether or not dirname exists
> > >
> > >
> > > Do I really have to use a finally: block?  It feels rather clumsy.
> > >
> > > I suppose I could test if the directory exists before the os.mkdir()
> > > but again that feels a bit clumsy somehow.
> > >
> > > I suppose also I could use os.mkdirs() with exist_ok=True but again
> > > that feels vaguely wrong somehow.
> > >
> >
> > Why does exist_ok=True feel wrong to you?  This is exactly what it is
> > there for.
> >
> 
> Using mkdirs when you only want to make one is inviting problems of
> being subtly wrong, where it creates too many levels of directory.
> Personally, I would just do:
> 
> try: os.mkdir(dirname)
> except FileExistsError: pass
> 
> and not try to handle anything else at all.
> 
Yes, OP here, that seems to me to be the 'right' way to do it.
Basically I hadn't realised the effect of pass in a try block and
that's why I asked the question originally.

-- 
Chris Green
?

From nospam at please.ty  Sat Apr 29 09:24:42 2023
From: nospam at please.ty (jak)
Date: Sat, 29 Apr 2023 15:24:42 +0200
Subject: How to 'ignore' an error in Python?
In-Reply-To: <mailman.7.1682742840.13552.python-list@python.org>
References: <ts6thj-fc3k.ln1@esprimo.zbmc.eu>
 <874joznwwq.fsf@copper.locationd.net>
 <CAPTjJmop-tX2QPxZLD9hq_nCn08nuEEAK7DM4xVA25v5-q096Q@mail.gmail.com>
 <mailman.7.1682742840.13552.python-list@python.org>
Message-ID: <u2j5qq$2v80c$1@dont-email.me>

Chris Angelico ha scritto:
> Using mkdirs when you only want to make one is inviting problems of
> being subtly wrong, where it creates too many levels of directory.
> Personally, I would just do:


Maybe I only say this because it has happened to me too many times but
before ignoring the error in the 'except' branch, I would make sure that
if the name exists it is a folder and not a file.


From nospam at please.ty  Sat Apr 29 10:43:38 2023
From: nospam at please.ty (jak)
Date: Sat, 29 Apr 2023 16:43:38 +0200
Subject: How to 'ignore' an error in Python?
In-Reply-To: <name-20230429151834@ram.dialup.fu-berlin.de>
References: <ts6thj-fc3k.ln1@esprimo.zbmc.eu>
 <874joznwwq.fsf@copper.locationd.net>
 <CAPTjJmop-tX2QPxZLD9hq_nCn08nuEEAK7DM4xVA25v5-q096Q@mail.gmail.com>
 <mailman.7.1682742840.13552.python-list@python.org>
 <u2j5qq$2v80c$1@dont-email.me> <name-20230429151834@ram.dialup.fu-berlin.de>
Message-ID: <u2jaep$2vu8n$1@dont-email.me>

Stefan Ram ha scritto:
> jak <nospam at please.ty> writes:
>> Maybe I only say this because it has happened to me too many times but
>> before ignoring the error in the 'except' branch, I would make sure that
>> if the name exists it is a folder and not a file.
> 
>    If the name exists and it is a file's name, this will be detected
>    by "mkdir( exist_ok=True )", and an object will be raised. Such
>    an object, indeed, usually should /not/ be ignored by the caller.
>    But there is no reason to deviate from the EAFP path.
> 
> 


Maybe I expressed myself badly but I didn't mean to propose alternatives
to the EAFP way but just to evaluate the possibility that it is not a
folder.

From rosuav at gmail.com  Sat Apr 29 22:04:30 2023
From: rosuav at gmail.com (Chris Angelico)
Date: Sun, 30 Apr 2023 12:04:30 +1000
Subject: How to 'ignore' an error in Python?
In-Reply-To: <httuhj-nnhn.ln1@esprimo.zbmc.eu>
References: <ts6thj-fc3k.ln1@esprimo.zbmc.eu>
 <874joznwwq.fsf@copper.locationd.net>
 <CAPTjJmop-tX2QPxZLD9hq_nCn08nuEEAK7DM4xVA25v5-q096Q@mail.gmail.com>
 <mailman.7.1682742840.13552.python-list@python.org>
 <httuhj-nnhn.ln1@esprimo.zbmc.eu>
Message-ID: <CAPTjJmq8=ppiJLaq2=AJxyTn2xUzxZn_AXt1A_pAJLf+dLD8zA@mail.gmail.com>

On Sun, 30 Apr 2023 at 11:58, Chris Green <cl at isbd.net> wrote:
>
> Chris Angelico <rosuav at gmail.com> wrote:
> > On Sat, 29 Apr 2023 at 14:27, Kushal Kumaran <kushal at locationd.net> wrote:
> > >
> > > On Fri, Apr 28 2023 at 04:55:41 PM, Chris Green <cl at isbd.net> wrote:
> > > > I'm sure I'm missing something obvious here but I can't see an elegant
> > > > way to do this.  I want to create a directory, but if it exists it's
> > > > not an error and the code should just continue.
> > > >
> > > > So, I have:-
> > > >
> > > >     for dirname in listofdirs:
> > > >         try:
> > > >             os.mkdir(dirname)
> > > >         except FileExistsError:
> > > >             # so what can I do here that says 'carry on regardless'
> > > >         except:
> > > >             # handle any other error, which is really an error
> > > >
> > > >         # I want code here to execute whether or not dirname exists
> > > >
> > > >
> > > > Do I really have to use a finally: block?  It feels rather clumsy.
> > > >
> > > > I suppose I could test if the directory exists before the os.mkdir()
> > > > but again that feels a bit clumsy somehow.
> > > >
> > > > I suppose also I could use os.mkdirs() with exist_ok=True but again
> > > > that feels vaguely wrong somehow.
> > > >
> > >
> > > Why does exist_ok=True feel wrong to you?  This is exactly what it is
> > > there for.
> > >
> >
> > Using mkdirs when you only want to make one is inviting problems of
> > being subtly wrong, where it creates too many levels of directory.
> > Personally, I would just do:
> >
> > try: os.mkdir(dirname)
> > except FileExistsError: pass
> >
> > and not try to handle anything else at all.
> >
> Yes, OP here, that seems to me to be the 'right' way to do it.
> Basically I hadn't realised the effect of pass in a try block and
> that's why I asked the question originally.
>

There's two points to note here. "pass" doesn't do anything
whatsoever; it's only there to prevent the syntactic problem of having
nothing in that block. This will also suppress the error:

try:
    os.mkdir(dirname)
except FileExistsError:
    dummy = "ignore"

The second thing is that, as soon as you have an "except" clause that
matches the error, that's it - it stops there. The error is considered
handled at that point. If that's NOT what you want, you have a few
options. Firstly, you can simply not have a matching except clause.
That's why we like to be as precise as possible with our catching;
every other type of problem will be left uncaught. Secondly, you can
use "try/finally" to add code that happens as the exception flies by,
but doesn't catch it (it also happens at the end of the block for
other reasons). And thirdly, you can reraise the exception:

try:
    os.mkdir(dirname)
except FileExistsError:
    print("Hey, that one already exists!")
    raise

That's going to keep the exception going just as if it hadn't been
caught, but with the additional handling.

But if you don't do any of those things, the exception is deemed to be
handled, and it goes no further.

ChrisA

From rosuav at gmail.com  Sat Apr 29 22:05:49 2023
From: rosuav at gmail.com (Chris Angelico)
Date: Sun, 30 Apr 2023 12:05:49 +1000
Subject: How to 'ignore' an error in Python?
In-Reply-To: <u2j5qq$2v80c$1@dont-email.me>
References: <ts6thj-fc3k.ln1@esprimo.zbmc.eu>
 <874joznwwq.fsf@copper.locationd.net>
 <CAPTjJmop-tX2QPxZLD9hq_nCn08nuEEAK7DM4xVA25v5-q096Q@mail.gmail.com>
 <mailman.7.1682742840.13552.python-list@python.org>
 <u2j5qq$2v80c$1@dont-email.me>
Message-ID: <CAPTjJmqs4_VOeZjFURoicy8onPyUusGMC034=zASJ5rDD+GfuQ@mail.gmail.com>

On Sun, 30 Apr 2023 at 12:02, jak <nospam at please.ty> wrote:
>
> Chris Angelico ha scritto:
> > Using mkdirs when you only want to make one is inviting problems of
> > being subtly wrong, where it creates too many levels of directory.
> > Personally, I would just do:
>
>
> Maybe I only say this because it has happened to me too many times but
> before ignoring the error in the 'except' branch, I would make sure that
> if the name exists it is a folder and not a file.
>

That's a fair consideration, although the other way to handle that is
to allow other operations to fail later (if someone creates a file
called "logs" and then you try to create "logs/2023-04-30.txt", you
get an error at that point). I have also known situations where this
is a deliberate way to suppress something (like a cache or log
directory).

ChrisA

From psam1304 at gmail.com  Sat Apr 29 23:28:59 2023
From: psam1304 at gmail.com (Phu Sam)
Date: Sat, 29 Apr 2023 20:28:59 -0700
Subject: How to 'ignore' an error in Python?
In-Reply-To: <CAPTjJmq8=ppiJLaq2=AJxyTn2xUzxZn_AXt1A_pAJLf+dLD8zA@mail.gmail.com>
References: <ts6thj-fc3k.ln1@esprimo.zbmc.eu>
 <874joznwwq.fsf@copper.locationd.net>
 <CAPTjJmop-tX2QPxZLD9hq_nCn08nuEEAK7DM4xVA25v5-q096Q@mail.gmail.com>
 <mailman.7.1682742840.13552.python-list@python.org>
 <httuhj-nnhn.ln1@esprimo.zbmc.eu>
 <CAPTjJmq8=ppiJLaq2=AJxyTn2xUzxZn_AXt1A_pAJLf+dLD8zA@mail.gmail.com>
Message-ID: <CANjxQ6wo9Mcbqu-jP0zLjsp05x+tU-EqkRzNMP3U=qdX6gombQ@mail.gmail.com>

Unsubscribe

On Sat, Apr 29, 2023 at 7:05 PM Chris Angelico <rosuav at gmail.com> wrote:

> On Sun, 30 Apr 2023 at 11:58, Chris Green <cl at isbd.net> wrote:
> >
> > Chris Angelico <rosuav at gmail.com> wrote:
> > > On Sat, 29 Apr 2023 at 14:27, Kushal Kumaran <kushal at locationd.net>
> wrote:
> > > >
> > > > On Fri, Apr 28 2023 at 04:55:41 PM, Chris Green <cl at isbd.net> wrote:
> > > > > I'm sure I'm missing something obvious here but I can't see an
> elegant
> > > > > way to do this.  I want to create a directory, but if it exists
> it's
> > > > > not an error and the code should just continue.
> > > > >
> > > > > So, I have:-
> > > > >
> > > > >     for dirname in listofdirs:
> > > > >         try:
> > > > >             os.mkdir(dirname)
> > > > >         except FileExistsError:
> > > > >             # so what can I do here that says 'carry on regardless'
> > > > >         except:
> > > > >             # handle any other error, which is really an error
> > > > >
> > > > >         # I want code here to execute whether or not dirname exists
> > > > >
> > > > >
> > > > > Do I really have to use a finally: block?  It feels rather clumsy.
> > > > >
> > > > > I suppose I could test if the directory exists before the
> os.mkdir()
> > > > > but again that feels a bit clumsy somehow.
> > > > >
> > > > > I suppose also I could use os.mkdirs() with exist_ok=True but again
> > > > > that feels vaguely wrong somehow.
> > > > >
> > > >
> > > > Why does exist_ok=True feel wrong to you?  This is exactly what it is
> > > > there for.
> > > >
> > >
> > > Using mkdirs when you only want to make one is inviting problems of
> > > being subtly wrong, where it creates too many levels of directory.
> > > Personally, I would just do:
> > >
> > > try: os.mkdir(dirname)
> > > except FileExistsError: pass
> > >
> > > and not try to handle anything else at all.
> > >
> > Yes, OP here, that seems to me to be the 'right' way to do it.
> > Basically I hadn't realised the effect of pass in a try block and
> > that's why I asked the question originally.
> >
>
> There's two points to note here. "pass" doesn't do anything
> whatsoever; it's only there to prevent the syntactic problem of having
> nothing in that block. This will also suppress the error:
>
> try:
>     os.mkdir(dirname)
> except FileExistsError:
>     dummy = "ignore"
>
> The second thing is that, as soon as you have an "except" clause that
> matches the error, that's it - it stops there. The error is considered
> handled at that point. If that's NOT what you want, you have a few
> options. Firstly, you can simply not have a matching except clause.
> That's why we like to be as precise as possible with our catching;
> every other type of problem will be left uncaught. Secondly, you can
> use "try/finally" to add code that happens as the exception flies by,
> but doesn't catch it (it also happens at the end of the block for
> other reasons). And thirdly, you can reraise the exception:
>
> try:
>     os.mkdir(dirname)
> except FileExistsError:
>     print("Hey, that one already exists!")
>     raise
>
> That's going to keep the exception going just as if it hadn't been
> caught, but with the additional handling.
>
> But if you don't do any of those things, the exception is deemed to be
> handled, and it goes no further.
>
> ChrisA
> --
> https://mail.python.org/mailman/listinfo/python-list
>

From specially at processed.almost.meat  Sun Apr 30 11:40:21 2023
From: specially at processed.almost.meat (Roy Hann)
Date: Sun, 30 Apr 2023 15:40:21 -0000 (UTC)
Subject: Using loguru in a library
Message-ID: <u2m254$3irjb$1@dont-email.me>

Is there anyone using loguru (loguru 0.5.3 in my case) successfully in a
library?


In my __init__.py in mylib I do

  logger.disable('mylib')

which definitely works. I don't get any more logging. 

I "pip install ." the library, then in mytest.py I do

  import mylib
  logger.enable('mylib')

expecting that it would report any log messages above level DEBUG, just
as it does when I don't disable logging. Unfortunately it doesn't
have any effect; it doesn't report any logging from mylib.

I have verified that __name__ is visible in the library and is 'mylib'.

I would also have expected that logger.enable(None) would turn all the
logging on everywhere but it seems not.

I have probably misunderstood how logger.enable() is supposed to be
used. Can anyone share a brief example?

Roy