From noreply at sourceforge.net  Sun Apr  3 04:54:12 2005
From: noreply at sourceforge.net (SourceForge.net)
Date: Sun Apr  3 04:54:15 2005
Subject: [Expat-bugs] [ expat-Bugs-1157018 ] not well-formed ( invalid
	token) for Certain XML tags 
Message-ID: <E1DHvFc-0006X9-VT@sc8-sf-web4.sourceforge.net>

Bugs item #1157018, was opened at 2005-03-04 14:56
Message generated for change (Comment added) made by nobody
You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1157018&group_id=10127

Category: XML::Parser (inactive)
Group: None
Status: Open
Resolution: None
Priority: 5
Submitted By: Nobody/Anonymous (nobody)
Assigned to: Nobody/Anonymous (nobody)
Summary:  not well-formed ( invalid token) for Certain XML tags 

Initial Comment:
Hello : 

I have a well formed XML packet  but xmlwf thows out 
error on certain tags 

<entry id="DS000011" version="1">
<timestamp date="2004-11-05" time="22:37:30" 
zone="UNKNOWN"/>
<source mfp="99.99.99.99" service=""/>
<job_info result="success">
<sender email="adad.dadad@adad.com" 
authenticated="false">adad.dadad</sender>
<scan_info page_count="1" size="ltr"/>
<email_info size="888827" method="embedded" 
fileFormat="jpeg" colorSettings="color" 
result="success">
<subject>test</subject>
<email_destination email="adad.dadad@adad.com" 
type="to" result="success"/>
</email_info>
</job_info>
</entry>

 There are lot of other tags before and after these tags ( 
as shown above ). If i remove this particular section the 
xmlwf doesn;t show any error. 

The exact error is 
<LINE NO>:10 : not well-formed (invalid token)

10 is actually the column position. and in the lines 
shown above , "=" is in the column position 10. 

Is there any newer version that handles these kind of 
tags ? or pl. suggest me a work around 

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

Comment By: Nobody/Anonymous (nobody)
Date: 2005-04-02 18:54

Message:
Logged In: NO 

hello,

i am new to using xml parsers in C. i have been playing with 
expat on a windows machine running cygwin and a gcc 
compiler. The version i am using is 1.95.8. i have written a 
code which i think is ok as its parsing the document ok to 
certain extent only.its giving a invalid token error.i am 
attachig the code and the contents of the xml file if any one 
would point me to wher i might be making a mistake i would 
really appreciate it.

the code is below



/*****************************************************************
* This program reads from an xml file and builds a tree that is 
later used to populate the array structure of nics, cabs etc

 */



#include <stdio.h>
#include <stdlib.h>
#include "expat.h"
#define BUFFSIZE  18192
char Buff[BUFFSIZE];
int Depth;

struct node{

                                char *node_name; //name of the node

                                char **attr_name; //string list of 
attribute name

                                char **attr_val; //array of values of the 
attributes

                                char *text; //text that is associated 
with this node

                                struct node **child; //array of children 
that this node can have

                                struct node *parent; //pointer to the 
parent of the current node

                                int child_no;

                };


/*
This handler is called when ever a start tag is encountered in 
the input stream
*/


static void XMLCALL
start(void *userData, const char *el, const char **attr)

{

  struct node **temp_ptr = (struct node**)userData;
  printf("i am in start\n");
  add_node(temp_ptr, el);

}






/*
This handler is called when ever an end tag is encountered in 
the input stream
*/


static void XMLCALL
end(void *userData, const char *el)

{
  printf("i am in end\n");
  struct node **temp_ptr = (struct node**)userData;
  close_node(temp_ptr);


  }





/*
This handler is called when ever a character tag is 
encountered in the input stream
*/


static void XMLCALL
char_handle(void *userData, const XML_Char *s, int len){

        char *data = (char *)s  ; // pointer to the new string that 
we construct
        char *temp_data;
        int i = len;
        struct node **temp_ptr = (struct node**)userData;

       if (len >1) {

        while(i>0){
			        *temp_data = *data;
        			i--;
        			data++;
        			temp_data++;
	    			}
	    *temp_data = '\0';
	    temp_data = temp_data - len;
	    printf("i am in char handle %s and len=%d\n", 
temp_data,len);
	   }


	  add_text(temp_ptr,data);

    }




void add_node(struct node **void_node_ptr, char *el ){

    struct node* next_node_ptr = (struct node*)malloc(sizeof
(struct node*));
    next_node_ptr->child_no = 0;



    struct node *current_node_ptr = (struct node *)
*void_node_ptr;

    // update the previous node with the address of the current 
node
//	current_node_ptr->child[current_node_ptr-
>child_no] = next_node_ptr;
	//current_node_ptr->child_no++;

	next_node_ptr->node_name = el;
	next_node_ptr->parent = current_node_ptr;

	current_node_ptr = next_node_ptr;

}



void add_text(struct node **void_node_ptr,char *data ){

	struct node *current_node_ptr = (struct node *)
*void_node_ptr;
	current_node_ptr->text = data;
	//printf(" in add_text with %s", current_node_ptr-
>text);

}





void close_node(struct node **void_node_ptr ){

	struct node *current_node_ptr = (struct node *)
*void_node_ptr;
	current_node_ptr = current_node_ptr->parent;

}


void
main(int argc, char *argv[]){

printf("i am in main\n");

  XML_Parser p = XML_ParserCreate(NULL);

  if (! p) {

    fprintf(stderr, "Couldn't allocate memory for parser\n");

    exit(-1);

  }


  //char *testdata = "venu\0";
  struct node *node_ptr = (struct node*)malloc(sizeof(struct 
node*));
  node_ptr->child_no = 0;


  //struct node *current_node_ptr = node_ptr;
  void *userData = (void *)node_ptr;

  XML_SetElementHandler(p, start, end);
  XML_SetCharacterDataHandler(p,char_handle);
  XML_SetUserData(p, &userData);



    FILE *fp;
    int len;
    int done=1;
    fp = fopen("/cygdrive/c/master-project/C-
programming/test2.xml", "r");
    len = fread(Buff, 1, BUFFSIZE, fp);
    printf("bytes read are %d and buffer has %d\n", len,sizeof
(Buff));
    fclose(fp);

    //printf("i am here");

    if (XML_Parse(p,Buff,len,done) == XML_STATUS_ERROR) 
{

              fprintf(stderr, "Parse error at line %d:\n%s\n",

                      XML_GetCurrentLineNumber(p),

                      XML_ErrorString(XML_GetErrorCode(p)));

      exit(-1);

     }

}



The contents of the file are 

<a>
<b>
	<c>kkkk</c>
</b>
<d>
	<e>pppp</e>
</d>
</a>

thanks
venu

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

Comment By: Karl Waclawek (kwaclaw)
Date: 2005-03-13 05:56

Message:
Logged In: YES 
user_id=290026

Show us your code - you may have a problem there.

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

Comment By: Nobody/Anonymous (nobody)
Date: 2005-03-04 15:02

Message:
Logged In: NO 

Operating System is HP-UX. 

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

Comment By: Nobody/Anonymous (nobody)
Date: 2005-03-04 15:01

Message:
Logged In: NO 

Operating System is HP-UX. 

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

You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1157018&group_id=10127
From noreply at sourceforge.net  Sun Apr  3 04:59:35 2005
From: noreply at sourceforge.net (SourceForge.net)
Date: Sun Apr  3 04:59:38 2005
Subject: [Expat-bugs] [ expat-Bugs-1175611 ] invalid token parse error
Message-ID: <E1DHvKp-00084f-7M@sc8-sf-web1.sourceforge.net>

Bugs item #1175611, was opened at 2005-04-02 18:59
Message generated for change (Tracker Item Submitted) made by Item Submitter
You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1175611&group_id=10127

Category: None
Group: None
Status: Open
Resolution: None
Priority: 5
Submitted By: Nobody/Anonymous (nobody)
Assigned to: Nobody/Anonymous (nobody)
Summary: invalid token parse error

Initial Comment:
hello,

i am new to using xml parsers in C. i have been playing 
with expat on a windows machine running cygwin and a 
gcc compiler. The version i am using is 1.95.8. i have 
written a code which i think is ok as its parsing the 
document ok but to certain extent only.its giving a 
invalid token error.i am attachig the code and the 
contents of the xml file if any one would point me to 
wher i might be making a mistake, i would really 
appreciate it.

the code is attached, the contents of the file are 

<a>
<b>
	<c>kkkk</c>
</b>
<d>
	<e>pppp</e>
</d>
</a>

i am pasting the contents of the file above as the form 
allows to upload only one file

any help would be really appreciated.

Thanks
venu

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

You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1175611&group_id=10127
From noreply at sourceforge.net  Sun Apr  3 05:46:05 2005
From: noreply at sourceforge.net (SourceForge.net)
Date: Sun Apr  3 05:46:08 2005
Subject: [Expat-bugs] [ expat-Bugs-1157018 ] not well-formed ( invalid
	token) for Certain XML tags 
Message-ID: <E1DHw3p-00053L-Me@sc8-sf-web3.sourceforge.net>

Bugs item #1157018, was opened at 2005-03-04 17:56
Message generated for change (Comment added) made by kwaclaw
You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1157018&group_id=10127

Category: XML::Parser (inactive)
Group: None
Status: Open
Resolution: None
Priority: 5
Submitted By: Nobody/Anonymous (nobody)
Assigned to: Nobody/Anonymous (nobody)
Summary:  not well-formed ( invalid token) for Certain XML tags 

Initial Comment:
Hello : 

I have a well formed XML packet  but xmlwf thows out 
error on certain tags 

<entry id="DS000011" version="1">
<timestamp date="2004-11-05" time="22:37:30" 
zone="UNKNOWN"/>
<source mfp="99.99.99.99" service=""/>
<job_info result="success">
<sender email="adad.dadad@adad.com" 
authenticated="false">adad.dadad</sender>
<scan_info page_count="1" size="ltr"/>
<email_info size="888827" method="embedded" 
fileFormat="jpeg" colorSettings="color" 
result="success">
<subject>test</subject>
<email_destination email="adad.dadad@adad.com" 
type="to" result="success"/>
</email_info>
</job_info>
</entry>

 There are lot of other tags before and after these tags ( 
as shown above ). If i remove this particular section the 
xmlwf doesn;t show any error. 

The exact error is 
<LINE NO>:10 : not well-formed (invalid token)

10 is actually the column position. and in the lines 
shown above , "=" is in the column position 10. 

Is there any newer version that handles these kind of 
tags ? or pl. suggest me a work around 

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

>Comment By: Karl Waclawek (kwaclaw)
Date: 2005-04-02 22:46

Message:
Logged In: YES 
user_id=290026

Your main parsing code looks OK, although normally
one would use a loop, but in your case it seems the whole
file fits into the buffer.

However, in your character data handler you are
copying to temp_data, which is never allocated.
Haven't looked at the other call-backs.

You should also be aware that the character data
between element tags can be reported through more
than one call-back, so you need to buffer them
and wait for the end-element call-back before
null-terminating them.


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

Comment By: Nobody/Anonymous (nobody)
Date: 2005-04-02 21:54

Message:
Logged In: NO 

hello,

i am new to using xml parsers in C. i have been playing with 
expat on a windows machine running cygwin and a gcc 
compiler. The version i am using is 1.95.8. i have written a 
code which i think is ok as its parsing the document ok to 
certain extent only.its giving a invalid token error.i am 
attachig the code and the contents of the xml file if any one 
would point me to wher i might be making a mistake i would 
really appreciate it.

the code is below



/*****************************************************************
* This program reads from an xml file and builds a tree that is 
later used to populate the array structure of nics, cabs etc

 */



#include <stdio.h>
#include <stdlib.h>
#include "expat.h"
#define BUFFSIZE  18192
char Buff[BUFFSIZE];
int Depth;

struct node{

                                char *node_name; //name of the node

                                char **attr_name; //string list of 
attribute name

                                char **attr_val; //array of values of the 
attributes

                                char *text; //text that is associated 
with this node

                                struct node **child; //array of children 
that this node can have

                                struct node *parent; //pointer to the 
parent of the current node

                                int child_no;

                };


/*
This handler is called when ever a start tag is encountered in 
the input stream
*/


static void XMLCALL
start(void *userData, const char *el, const char **attr)

{

  struct node **temp_ptr = (struct node**)userData;
  printf("i am in start\n");
  add_node(temp_ptr, el);

}






/*
This handler is called when ever an end tag is encountered in 
the input stream
*/


static void XMLCALL
end(void *userData, const char *el)

{
  printf("i am in end\n");
  struct node **temp_ptr = (struct node**)userData;
  close_node(temp_ptr);


  }





/*
This handler is called when ever a character tag is 
encountered in the input stream
*/


static void XMLCALL
char_handle(void *userData, const XML_Char *s, int len){

        char *data = (char *)s  ; // pointer to the new string that 
we construct
        char *temp_data;
        int i = len;
        struct node **temp_ptr = (struct node**)userData;

       if (len >1) {

        while(i>0){
			        *temp_data = *data;
        			i--;
        			data++;
        			temp_data++;
	    			}
	    *temp_data = '\0';
	    temp_data = temp_data - len;
	    printf("i am in char handle %s and len=%d\n", 
temp_data,len);
	   }


	  add_text(temp_ptr,data);

    }




void add_node(struct node **void_node_ptr, char *el ){

    struct node* next_node_ptr = (struct node*)malloc(sizeof
(struct node*));
    next_node_ptr->child_no = 0;



    struct node *current_node_ptr = (struct node *)
*void_node_ptr;

    // update the previous node with the address of the current 
node
//	current_node_ptr->child[current_node_ptr-
>child_no] = next_node_ptr;
	//current_node_ptr->child_no++;

	next_node_ptr->node_name = el;
	next_node_ptr->parent = current_node_ptr;

	current_node_ptr = next_node_ptr;

}



void add_text(struct node **void_node_ptr,char *data ){

	struct node *current_node_ptr = (struct node *)
*void_node_ptr;
	current_node_ptr->text = data;
	//printf(" in add_text with %s", current_node_ptr-
>text);

}





void close_node(struct node **void_node_ptr ){

	struct node *current_node_ptr = (struct node *)
*void_node_ptr;
	current_node_ptr = current_node_ptr->parent;

}


void
main(int argc, char *argv[]){

printf("i am in main\n");

  XML_Parser p = XML_ParserCreate(NULL);

  if (! p) {

    fprintf(stderr, "Couldn't allocate memory for parser\n");

    exit(-1);

  }


  //char *testdata = "venu\0";
  struct node *node_ptr = (struct node*)malloc(sizeof(struct 
node*));
  node_ptr->child_no = 0;


  //struct node *current_node_ptr = node_ptr;
  void *userData = (void *)node_ptr;

  XML_SetElementHandler(p, start, end);
  XML_SetCharacterDataHandler(p,char_handle);
  XML_SetUserData(p, &userData);



    FILE *fp;
    int len;
    int done=1;
    fp = fopen("/cygdrive/c/master-project/C-
programming/test2.xml", "r");
    len = fread(Buff, 1, BUFFSIZE, fp);
    printf("bytes read are %d and buffer has %d\n", len,sizeof
(Buff));
    fclose(fp);

    //printf("i am here");

    if (XML_Parse(p,Buff,len,done) == XML_STATUS_ERROR) 
{

              fprintf(stderr, "Parse error at line %d:\n%s\n",

                      XML_GetCurrentLineNumber(p),

                      XML_ErrorString(XML_GetErrorCode(p)));

      exit(-1);

     }

}



The contents of the file are 

<a>
<b>
	<c>kkkk</c>
</b>
<d>
	<e>pppp</e>
</d>
</a>

thanks
venu

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

Comment By: Karl Waclawek (kwaclaw)
Date: 2005-03-13 08:56

Message:
Logged In: YES 
user_id=290026

Show us your code - you may have a problem there.

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

Comment By: Nobody/Anonymous (nobody)
Date: 2005-03-04 18:02

Message:
Logged In: NO 

Operating System is HP-UX. 

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

Comment By: Nobody/Anonymous (nobody)
Date: 2005-03-04 18:01

Message:
Logged In: NO 

Operating System is HP-UX. 

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

You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1157018&group_id=10127
From noreply at sourceforge.net  Sun Apr  3 05:47:18 2005
From: noreply at sourceforge.net (SourceForge.net)
Date: Sun Apr  3 05:47:21 2005
Subject: [Expat-bugs] [ expat-Bugs-1175611 ] invalid token parse error
Message-ID: <E1DHw50-00053v-IK@sc8-sf-web3.sourceforge.net>

Bugs item #1175611, was opened at 2005-04-02 21:59
Message generated for change (Comment added) made by kwaclaw
You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1175611&group_id=10127

Category: None
Group: None
>Status: Closed
>Resolution: Duplicate
Priority: 5
Submitted By: Nobody/Anonymous (nobody)
Assigned to: Nobody/Anonymous (nobody)
Summary: invalid token parse error

Initial Comment:
hello,

i am new to using xml parsers in C. i have been playing 
with expat on a windows machine running cygwin and a 
gcc compiler. The version i am using is 1.95.8. i have 
written a code which i think is ok as its parsing the 
document ok but to certain extent only.its giving a 
invalid token error.i am attachig the code and the 
contents of the xml file if any one would point me to 
wher i might be making a mistake, i would really 
appreciate it.

the code is attached, the contents of the file are 

<a>
<b>
	<c>kkkk</c>
</b>
<d>
	<e>pppp</e>
</d>
</a>

i am pasting the contents of the file above as the form 
allows to upload only one file

any help would be really appreciated.

Thanks
venu

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

>Comment By: Karl Waclawek (kwaclaw)
Date: 2005-04-02 22:47

Message:
Logged In: YES 
user_id=290026

Duplicate of issue # 1157018.

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

You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1175611&group_id=10127
From noreply at sourceforge.net  Wed Apr  6 19:40:28 2005
From: noreply at sourceforge.net (SourceForge.net)
Date: Wed Apr  6 19:40:32 2005
Subject: [Expat-bugs] [ expat-Bugs-1177957 ] Makefile.in doesn't install
	expat_external.h on SGI
Message-ID: <E1DJEVw-0006s6-W0@sc8-sf-web2.sourceforge.net>

Bugs item #1177957, was opened at 2005-04-06 10:40
Message generated for change (Tracker Item Submitted) made by Item Submitter
You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1177957&group_id=10127

Category: Build control
Group: None
Status: Open
Resolution: None
Priority: 5
Submitted By: Nobody/Anonymous (nobody)
Assigned to: Greg Stein (gstein)
Summary: Makefile.in doesn't install expat_external.h on SGI

Initial Comment:
(Submitted by Mark Zieg, mark@zieg.com)

The conftools/install-sh script provided clearly
specifies that it can only install one file at a time.
 However, there are TWO headers listed in APIHEADER;
ergo, the second one gets dropped.

The following patch fixes Makefile.in:

--- Makefile.in 2004-05-07 16:00:48.000000000 -0400
+++ /home/ziegm/save/Makefile.in        2005-04-06
13:33:57.537788960 -0400
@@ -41,7 +41,8 @@
 mkinstalldirs = $(SHELL)
$(top_srcdir)/conftools/mkinstalldirs

 MANFILE = $(srcdir)/doc/xmlwf.1
-APIHEADER = $(srcdir)/lib/expat.h
$(srcdir)/lib/expat_external.h
+APIHEADER1 = $(srcdir)/lib/expat.h
+APIHEADER2 = $(srcdir)/lib/expat_external.h
 LIBRARY = libexpat.la


@@ -80,7 +81,8 @@
 installlib: $(LIBRARY) $(APIHEADER)
        $(mkinstalldirs) $(libdir) $(includedir)
        $(LIBTOOL) --mode=install $(INSTALL) $(LIBRARY)
$(libdir)/$(LIBRARY)
-       $(INSTALL_DATA) $(APIHEADER) $(includedir)
+       $(INSTALL_DATA) $(APIHEADER1) $(includedir)
+       $(INSTALL_DATA) $(APIHEADER2) $(includedir)

 uninstall: uninstalllib
        $(LIBTOOL) --mode=uninstall rm -f $(bindir)/xmlwf



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

You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1177957&group_id=10127
From noreply at sourceforge.net  Wed Apr  6 19:52:58 2005
From: noreply at sourceforge.net (SourceForge.net)
Date: Wed Apr  6 19:53:01 2005
Subject: [Expat-bugs] [ expat-Bugs-1177957 ] Makefile.in doesn't install
	expat_external.h on SGI
Message-ID: <E1DJEi2-0006EC-K1@sc8-sf-web4.sourceforge.net>

Bugs item #1177957, was opened at 2005-04-06 13:40
Message generated for change (Comment added) made by kwaclaw
You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1177957&group_id=10127

Category: Build control
Group: None
Status: Open
Resolution: None
Priority: 5
Submitted By: Nobody/Anonymous (nobody)
Assigned to: Greg Stein (gstein)
Summary: Makefile.in doesn't install expat_external.h on SGI

Initial Comment:
(Submitted by Mark Zieg, mark@zieg.com)

The conftools/install-sh script provided clearly
specifies that it can only install one file at a time.
 However, there are TWO headers listed in APIHEADER;
ergo, the second one gets dropped.

The following patch fixes Makefile.in:

--- Makefile.in 2004-05-07 16:00:48.000000000 -0400
+++ /home/ziegm/save/Makefile.in        2005-04-06
13:33:57.537788960 -0400
@@ -41,7 +41,8 @@
 mkinstalldirs = $(SHELL)
$(top_srcdir)/conftools/mkinstalldirs

 MANFILE = $(srcdir)/doc/xmlwf.1
-APIHEADER = $(srcdir)/lib/expat.h
$(srcdir)/lib/expat_external.h
+APIHEADER1 = $(srcdir)/lib/expat.h
+APIHEADER2 = $(srcdir)/lib/expat_external.h
 LIBRARY = libexpat.la


@@ -80,7 +81,8 @@
 installlib: $(LIBRARY) $(APIHEADER)
        $(mkinstalldirs) $(libdir) $(includedir)
        $(LIBTOOL) --mode=install $(INSTALL) $(LIBRARY)
$(libdir)/$(LIBRARY)
-       $(INSTALL_DATA) $(APIHEADER) $(includedir)
+       $(INSTALL_DATA) $(APIHEADER1) $(includedir)
+       $(INSTALL_DATA) $(APIHEADER2) $(includedir)

 uninstall: uninstalllib
        $(LIBTOOL) --mode=uninstall rm -f $(bindir)/xmlwf



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

>Comment By: Karl Waclawek (kwaclaw)
Date: 2005-04-06 13:52

Message:
Logged In: YES 
user_id=290026

I think this has been resolved in CVS.
Please check and confirm, so that we can close this issue.

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

You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1177957&group_id=10127
From noreply at sourceforge.net  Mon Apr 18 17:04:57 2005
From: noreply at sourceforge.net (SourceForge.net)
Date: Mon Apr 18 17:05:00 2005
Subject: [Expat-bugs] [ expat-Bugs-1185243 ] Acirc prepended to entity
Message-ID: <E1DNXo1-0008Ss-SN@sc8-sf-web1.sourceforge.net>

Bugs item #1185243, was opened at 2005-04-18 17:04
Message generated for change (Tracker Item Submitted) made by Item Submitter
You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1185243&group_id=10127

Category: None
Group: None
Status: Open
Resolution: None
Priority: 5
Submitted By: Jan Hochstein (janho)
Assigned to: Nobody/Anonymous (nobody)
Summary: Acirc prepended to entity

Initial Comment:
Consider the following xml document:

-----

<?xml version="1.0" encoding="ISO-8859-1"?>

<!DOCTYPE xml [
<!ENTITY deg     "&#176;">
]>

<anything>
Latitude is 42 &deg; 34' north.
</anything>

-----

The character handler is called three times. The data
it receives is this:
1) "Latitude is 42"
2) "??"
3) "34' north."

If your encoding is different from mine: the first
character received on the second call is HTML &Acirc;
or ASCII 194.

I have found this example to work with any entity not
just &deg; on expat-1.95.7 and expat-1.95.8 .


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

You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1185243&group_id=10127
From noreply at sourceforge.net  Mon Apr 18 19:33:35 2005
From: noreply at sourceforge.net (SourceForge.net)
Date: Mon Apr 18 19:33:37 2005
Subject: [Expat-bugs] [ expat-Bugs-1185243 ] Acirc prepended to entity
Message-ID: <E1DNa7r-0007wa-AR@sc8-sf-web1.sourceforge.net>

Bugs item #1185243, was opened at 2005-04-18 11:04
Message generated for change (Comment added) made by kwaclaw
You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1185243&group_id=10127

Category: None
Group: None
Status: Open
Resolution: None
Priority: 5
Submitted By: Jan Hochstein (janho)
Assigned to: Nobody/Anonymous (nobody)
Summary: Acirc prepended to entity

Initial Comment:
Consider the following xml document:

-----

<?xml version="1.0" encoding="ISO-8859-1"?>

<!DOCTYPE xml [
<!ENTITY deg     "&#176;">
]>

<anything>
Latitude is 42 &deg; 34' north.
</anything>

-----

The character handler is called three times. The data
it receives is this:
1) "Latitude is 42"
2) "??"
3) "34' north."

If your encoding is different from mine: the first
character received on the second call is HTML &Acirc;
or ASCII 194.

I have found this example to work with any entity not
just &deg; on expat-1.95.7 and expat-1.95.8 .


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

>Comment By: Karl Waclawek (kwaclaw)
Date: 2005-04-18 13:33

Message:
Logged In: YES 
user_id=290026

I cannot reproduce your problem.

Are you aware that Expat reports data in UTF-8 or UTF-16
encoding? Which GUI controls do you use to display
the data from the character handler? Is it the built-in
display of your IDE? It may not handle UTF-8/16.

Why don't you write down the hex values from call-back 2)
and then look up how character 176 (ISO-8859-1) would be
encoded in UTF-8 or UTF-16. Compare this to the call-back
data, and you will know if there is a bug.

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

You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1185243&group_id=10127
From noreply at sourceforge.net  Tue Apr 19 09:35:06 2005
From: noreply at sourceforge.net (SourceForge.net)
Date: Tue Apr 19 09:35:24 2005
Subject: [Expat-bugs] [ expat-Bugs-1185243 ] Acirc prepended to entity
Message-ID: <E1DNnGE-0007Z2-9F@sc8-sf-web2.sourceforge.net>

Bugs item #1185243, was opened at 2005-04-18 17:04
Message generated for change (Comment added) made by janho
You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1185243&group_id=10127

Category: None
Group: None
Status: Open
Resolution: None
Priority: 5
Submitted By: Jan Hochstein (janho)
Assigned to: Nobody/Anonymous (nobody)
Summary: Acirc prepended to entity

Initial Comment:
Consider the following xml document:

-----

<?xml version="1.0" encoding="ISO-8859-1"?>

<!DOCTYPE xml [
<!ENTITY deg     "&#176;">
]>

<anything>
Latitude is 42 &deg; 34' north.
</anything>

-----

The character handler is called three times. The data
it receives is this:
1) "Latitude is 42"
2) "??"
3) "34' north."

If your encoding is different from mine: the first
character received on the second call is HTML &Acirc;
or ASCII 194.

I have found this example to work with any entity not
just &deg; on expat-1.95.7 and expat-1.95.8 .


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

>Comment By: Jan Hochstein (janho)
Date: 2005-04-19 09:35

Message:
Logged In: YES 
user_id=1234078

First of all, the call-back 2) gets two bytes. That would
mean a 16-bit wide encoding. But call-backs 1) and 3) get
only one byte for each character.

The hex codes of the buffers received by the call-backs are
these:
1) 4c 61 74 69 74 75 64 65 20 69 73 20 34 32 20 
2) c2 b0 
3) 20 33 34 27 20 6e 6f 72 74 68 2e 

I attach the C program used to produce them.

If I change the encoding="" in the xml file to UTF-8 the
problem persists.


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

Comment By: Karl Waclawek (kwaclaw)
Date: 2005-04-18 19:33

Message:
Logged In: YES 
user_id=290026

I cannot reproduce your problem.

Are you aware that Expat reports data in UTF-8 or UTF-16
encoding? Which GUI controls do you use to display
the data from the character handler? Is it the built-in
display of your IDE? It may not handle UTF-8/16.

Why don't you write down the hex values from call-back 2)
and then look up how character 176 (ISO-8859-1) would be
encoded in UTF-8 or UTF-16. Compare this to the call-back
data, and you will know if there is a bug.

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

You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1185243&group_id=10127
From noreply at sourceforge.net  Tue Apr 19 15:49:31 2005
From: noreply at sourceforge.net (SourceForge.net)
Date: Tue Apr 19 15:49:34 2005
Subject: [Expat-bugs] [ expat-Bugs-1185243 ] Acirc prepended to entity
Message-ID: <E1DNt6Z-0007nz-K5@sc8-sf-web1.sourceforge.net>

Bugs item #1185243, was opened at 2005-04-18 11:04
Message generated for change (Comment added) made by kwaclaw
You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1185243&group_id=10127

Category: None
Group: None
Status: Open
Resolution: None
Priority: 5
Submitted By: Jan Hochstein (janho)
Assigned to: Nobody/Anonymous (nobody)
Summary: Acirc prepended to entity

Initial Comment:
Consider the following xml document:

-----

<?xml version="1.0" encoding="ISO-8859-1"?>

<!DOCTYPE xml [
<!ENTITY deg     "&#176;">
]>

<anything>
Latitude is 42 &deg; 34' north.
</anything>

-----

The character handler is called three times. The data
it receives is this:
1) "Latitude is 42"
2) "??"
3) "34' north."

If your encoding is different from mine: the first
character received on the second call is HTML &Acirc;
or ASCII 194.

I have found this example to work with any entity not
just &deg; on expat-1.95.7 and expat-1.95.8 .


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

>Comment By: Karl Waclawek (kwaclaw)
Date: 2005-04-19 09:49

Message:
Logged In: YES 
user_id=290026

UTF-8 is a multi-byte encoding.
Please determine the exact UTF-8 encoding for the character
with Unicode code point 176. It might very well be c2 b0.

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

Comment By: Jan Hochstein (janho)
Date: 2005-04-19 03:35

Message:
Logged In: YES 
user_id=1234078

First of all, the call-back 2) gets two bytes. That would
mean a 16-bit wide encoding. But call-backs 1) and 3) get
only one byte for each character.

The hex codes of the buffers received by the call-backs are
these:
1) 4c 61 74 69 74 75 64 65 20 69 73 20 34 32 20 
2) c2 b0 
3) 20 33 34 27 20 6e 6f 72 74 68 2e 

I attach the C program used to produce them.

If I change the encoding="" in the xml file to UTF-8 the
problem persists.


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

Comment By: Karl Waclawek (kwaclaw)
Date: 2005-04-18 13:33

Message:
Logged In: YES 
user_id=290026

I cannot reproduce your problem.

Are you aware that Expat reports data in UTF-8 or UTF-16
encoding? Which GUI controls do you use to display
the data from the character handler? Is it the built-in
display of your IDE? It may not handle UTF-8/16.

Why don't you write down the hex values from call-back 2)
and then look up how character 176 (ISO-8859-1) would be
encoded in UTF-8 or UTF-16. Compare this to the call-back
data, and you will know if there is a bug.

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

You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1185243&group_id=10127
From noreply at sourceforge.net  Tue Apr 19 16:17:56 2005
From: noreply at sourceforge.net (SourceForge.net)
Date: Tue Apr 19 16:17:59 2005
Subject: [Expat-bugs] [ expat-Bugs-1185243 ] Acirc prepended to entity
Message-ID: <E1DNtY4-0001Lf-Fr@sc8-sf-web1.sourceforge.net>

Bugs item #1185243, was opened at 2005-04-18 17:04
Message generated for change (Comment added) made by janho
You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1185243&group_id=10127

Category: None
Group: None
Status: Open
Resolution: None
Priority: 5
Submitted By: Jan Hochstein (janho)
Assigned to: Nobody/Anonymous (nobody)
Summary: Acirc prepended to entity

Initial Comment:
Consider the following xml document:

-----

<?xml version="1.0" encoding="ISO-8859-1"?>

<!DOCTYPE xml [
<!ENTITY deg     "&#176;">
]>

<anything>
Latitude is 42 &deg; 34' north.
</anything>

-----

The character handler is called three times. The data
it receives is this:
1) "Latitude is 42"
2) "??"
3) "34' north."

If your encoding is different from mine: the first
character received on the second call is HTML &Acirc;
or ASCII 194.

I have found this example to work with any entity not
just &deg; on expat-1.95.7 and expat-1.95.8 .


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

>Comment By: Jan Hochstein (janho)
Date: 2005-04-19 16:17

Message:
Logged In: YES 
user_id=1234078

You are right of course. I was not aware that UTF-8 has
characters of different bit lengths.

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

Comment By: Karl Waclawek (kwaclaw)
Date: 2005-04-19 15:49

Message:
Logged In: YES 
user_id=290026

UTF-8 is a multi-byte encoding.
Please determine the exact UTF-8 encoding for the character
with Unicode code point 176. It might very well be c2 b0.

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

Comment By: Jan Hochstein (janho)
Date: 2005-04-19 09:35

Message:
Logged In: YES 
user_id=1234078

First of all, the call-back 2) gets two bytes. That would
mean a 16-bit wide encoding. But call-backs 1) and 3) get
only one byte for each character.

The hex codes of the buffers received by the call-backs are
these:
1) 4c 61 74 69 74 75 64 65 20 69 73 20 34 32 20 
2) c2 b0 
3) 20 33 34 27 20 6e 6f 72 74 68 2e 

I attach the C program used to produce them.

If I change the encoding="" in the xml file to UTF-8 the
problem persists.


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

Comment By: Karl Waclawek (kwaclaw)
Date: 2005-04-18 19:33

Message:
Logged In: YES 
user_id=290026

I cannot reproduce your problem.

Are you aware that Expat reports data in UTF-8 or UTF-16
encoding? Which GUI controls do you use to display
the data from the character handler? Is it the built-in
display of your IDE? It may not handle UTF-8/16.

Why don't you write down the hex values from call-back 2)
and then look up how character 176 (ISO-8859-1) would be
encoded in UTF-8 or UTF-16. Compare this to the call-back
data, and you will know if there is a bug.

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

You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1185243&group_id=10127
From noreply at sourceforge.net  Tue Apr 19 19:50:43 2005
From: noreply at sourceforge.net (SourceForge.net)
Date: Tue Apr 19 19:50:46 2005
Subject: [Expat-bugs] [ expat-Bugs-1185243 ] Acirc prepended to entity
Message-ID: <E1DNwrz-0006V9-IT@sc8-sf-web4.sourceforge.net>

Bugs item #1185243, was opened at 2005-04-18 11:04
Message generated for change (Comment added) made by kwaclaw
You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1185243&group_id=10127

Category: None
Group: None
>Status: Closed
>Resolution: Rejected
Priority: 5
Submitted By: Jan Hochstein (janho)
Assigned to: Nobody/Anonymous (nobody)
Summary: Acirc prepended to entity

Initial Comment:
Consider the following xml document:

-----

<?xml version="1.0" encoding="ISO-8859-1"?>

<!DOCTYPE xml [
<!ENTITY deg     "&#176;">
]>

<anything>
Latitude is 42 &deg; 34' north.
</anything>

-----

The character handler is called three times. The data
it receives is this:
1) "Latitude is 42"
2) "??"
3) "34' north."

If your encoding is different from mine: the first
character received on the second call is HTML &Acirc;
or ASCII 194.

I have found this example to work with any entity not
just &deg; on expat-1.95.7 and expat-1.95.8 .


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

>Comment By: Karl Waclawek (kwaclaw)
Date: 2005-04-19 13:50

Message:
Logged In: YES 
user_id=290026

OK, then let's close the issue.

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

Comment By: Jan Hochstein (janho)
Date: 2005-04-19 10:17

Message:
Logged In: YES 
user_id=1234078

You are right of course. I was not aware that UTF-8 has
characters of different bit lengths.

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

Comment By: Karl Waclawek (kwaclaw)
Date: 2005-04-19 09:49

Message:
Logged In: YES 
user_id=290026

UTF-8 is a multi-byte encoding.
Please determine the exact UTF-8 encoding for the character
with Unicode code point 176. It might very well be c2 b0.

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

Comment By: Jan Hochstein (janho)
Date: 2005-04-19 03:35

Message:
Logged In: YES 
user_id=1234078

First of all, the call-back 2) gets two bytes. That would
mean a 16-bit wide encoding. But call-backs 1) and 3) get
only one byte for each character.

The hex codes of the buffers received by the call-backs are
these:
1) 4c 61 74 69 74 75 64 65 20 69 73 20 34 32 20 
2) c2 b0 
3) 20 33 34 27 20 6e 6f 72 74 68 2e 

I attach the C program used to produce them.

If I change the encoding="" in the xml file to UTF-8 the
problem persists.


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

Comment By: Karl Waclawek (kwaclaw)
Date: 2005-04-18 13:33

Message:
Logged In: YES 
user_id=290026

I cannot reproduce your problem.

Are you aware that Expat reports data in UTF-8 or UTF-16
encoding? Which GUI controls do you use to display
the data from the character handler? Is it the built-in
display of your IDE? It may not handle UTF-8/16.

Why don't you write down the hex values from call-back 2)
and then look up how character 176 (ISO-8859-1) would be
encoded in UTF-8 or UTF-16. Compare this to the call-back
data, and you will know if there is a bug.

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

You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1185243&group_id=10127
From noreply at sourceforge.net  Tue Apr 19 19:52:00 2005
From: noreply at sourceforge.net (SourceForge.net)
Date: Tue Apr 19 19:52:03 2005
Subject: [Expat-bugs] [ expat-Bugs-1162302 ] Fault CharacterDataHandler if
	LF starts data
Message-ID: <E1DNwtE-0006YG-Fn@sc8-sf-web4.sourceforge.net>

Bugs item #1162302, was opened at 2005-03-13 00:26
Message generated for change (Comment added) made by kwaclaw
You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1162302&group_id=10127

Category: None
Group: Not a Bug
>Status: Closed
>Resolution: Rejected
Priority: 5
Submitted By: Nobody/Anonymous (nobody)
Assigned to: Nobody/Anonymous (nobody)
Summary: Fault CharacterDataHandler if LF starts data

Initial Comment:
When a tag's data start with LF (0x0A), I get 
XML_CharacterDataHandler with len=1 and s=0x0A 
instead of the actual data that comes after the LF.

On the attached example I get the following calls to 
XML_CharacterDataHandler :
- len =1, s=0x0A
- len=6, s="closed"
- len =1, s=0x0A
- len =1, s=0x0A
The last two calls for the function are problematic - I 
don't get the actual data that comes after the LF.

The problem happens when the tag's data start with LF 
but has more characters after the LF.

on Expat-1.95.8 created from 
expat_win32bin_1_95_8.exe


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

>Comment By: Karl Waclawek (kwaclaw)
Date: 2005-04-19 13:52

Message:
Logged In: YES 
user_id=290026

Closing this issue - no follow-up from poster.

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

Comment By: Karl Waclawek (kwaclaw)
Date: 2005-03-14 18:35

Message:
Logged In: YES 
user_id=290026

Just to clarify - in Expat, a contiguous string of characters
does not necessarily have to be reported through exactly one
characterData() call-back. Often, line-breaks determine the
boundary between call-backs. In the attached example, the
character data for the <note> element will likely be reported
through three call-backs, as there are two line-breaks.

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

Comment By: Mike Rosky (mike-rosky)
Date: 2005-03-14 08:20

Message:
Logged In: YES 
user_id=1238831

I think that you (original sender) should examine your code, 
when and for which cases you're calling chardata handler. 
Please note that basically you have to (simplified) reset
chardata buffer at the start element point and accumulate
chardata value every time character data handler is invoked
until parser calls the end element handler for that element.

You can't suppose that chardata handler gets whole value
in one call - actually in your case it's called twice because of 
CRLF, the first call returns CRLF (and eventually preceding 
chars), the second the rest of chardatas. Chardatas can even 
cross two source readings, which leads to same effect.

You can try it when you add a character data handler to
the outline.c example, where chardata handler just prints
out the current part enclosed in brackets or something.

Mike


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

Comment By: Nobody/Anonymous (nobody)
Date: 2005-03-13 23:36

Message:
Logged In: NO 

The attached example has LF (0x0A) in the following cases:
- before the text "sip:pep@example.com"
- before the text "Full state presence document"
In these 2 cases I receive XML_CharacterDataHandler  with 
len=1 and s=0x0A only. The function is not called for the 
data AFTER the LF (In the example to "Full state presence 
document").
Is there a way to overcome this problem?

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

Comment By: Karl Waclawek (kwaclaw)
Date: 2005-03-13 08:54

Message:
Logged In: YES 
user_id=290026

Your attached example does not have any LF directly
before or after the string "closed". Please clarify your problem.

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

You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1162302&group_id=10127
From noreply at sourceforge.net  Tue Apr 19 19:52:58 2005
From: noreply at sourceforge.net (SourceForge.net)
Date: Tue Apr 19 19:53:01 2005
Subject: [Expat-bugs] [ expat-Bugs-1157018 ] not well-formed ( invalid
	token) for Certain XML tags 
Message-ID: <E1DNwuA-0006cQ-PS@sc8-sf-web4.sourceforge.net>

Bugs item #1157018, was opened at 2005-03-04 17:56
Message generated for change (Comment added) made by kwaclaw
You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1157018&group_id=10127

Category: XML::Parser (inactive)
Group: None
>Status: Closed
>Resolution: Rejected
Priority: 5
Submitted By: Nobody/Anonymous (nobody)
Assigned to: Nobody/Anonymous (nobody)
Summary:  not well-formed ( invalid token) for Certain XML tags 

Initial Comment:
Hello : 

I have a well formed XML packet  but xmlwf thows out 
error on certain tags 

<entry id="DS000011" version="1">
<timestamp date="2004-11-05" time="22:37:30" 
zone="UNKNOWN"/>
<source mfp="99.99.99.99" service=""/>
<job_info result="success">
<sender email="adad.dadad@adad.com" 
authenticated="false">adad.dadad</sender>
<scan_info page_count="1" size="ltr"/>
<email_info size="888827" method="embedded" 
fileFormat="jpeg" colorSettings="color" 
result="success">
<subject>test</subject>
<email_destination email="adad.dadad@adad.com" 
type="to" result="success"/>
</email_info>
</job_info>
</entry>

 There are lot of other tags before and after these tags ( 
as shown above ). If i remove this particular section the 
xmlwf doesn;t show any error. 

The exact error is 
<LINE NO>:10 : not well-formed (invalid token)

10 is actually the column position. and in the lines 
shown above , "=" is in the column position 10. 

Is there any newer version that handles these kind of 
tags ? or pl. suggest me a work around 

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

>Comment By: Karl Waclawek (kwaclaw)
Date: 2005-04-19 13:52

Message:
Logged In: YES 
user_id=290026

Closing this issue - no follow-up from poster.

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

Comment By: Karl Waclawek (kwaclaw)
Date: 2005-04-02 22:46

Message:
Logged In: YES 
user_id=290026

Your main parsing code looks OK, although normally
one would use a loop, but in your case it seems the whole
file fits into the buffer.

However, in your character data handler you are
copying to temp_data, which is never allocated.
Haven't looked at the other call-backs.

You should also be aware that the character data
between element tags can be reported through more
than one call-back, so you need to buffer them
and wait for the end-element call-back before
null-terminating them.


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

Comment By: Nobody/Anonymous (nobody)
Date: 2005-04-02 21:54

Message:
Logged In: NO 

hello,

i am new to using xml parsers in C. i have been playing with 
expat on a windows machine running cygwin and a gcc 
compiler. The version i am using is 1.95.8. i have written a 
code which i think is ok as its parsing the document ok to 
certain extent only.its giving a invalid token error.i am 
attachig the code and the contents of the xml file if any one 
would point me to wher i might be making a mistake i would 
really appreciate it.

the code is below



/*****************************************************************
* This program reads from an xml file and builds a tree that is 
later used to populate the array structure of nics, cabs etc

 */



#include <stdio.h>
#include <stdlib.h>
#include "expat.h"
#define BUFFSIZE  18192
char Buff[BUFFSIZE];
int Depth;

struct node{

                                char *node_name; //name of the node

                                char **attr_name; //string list of 
attribute name

                                char **attr_val; //array of values of the 
attributes

                                char *text; //text that is associated 
with this node

                                struct node **child; //array of children 
that this node can have

                                struct node *parent; //pointer to the 
parent of the current node

                                int child_no;

                };


/*
This handler is called when ever a start tag is encountered in 
the input stream
*/


static void XMLCALL
start(void *userData, const char *el, const char **attr)

{

  struct node **temp_ptr = (struct node**)userData;
  printf("i am in start\n");
  add_node(temp_ptr, el);

}






/*
This handler is called when ever an end tag is encountered in 
the input stream
*/


static void XMLCALL
end(void *userData, const char *el)

{
  printf("i am in end\n");
  struct node **temp_ptr = (struct node**)userData;
  close_node(temp_ptr);


  }





/*
This handler is called when ever a character tag is 
encountered in the input stream
*/


static void XMLCALL
char_handle(void *userData, const XML_Char *s, int len){

        char *data = (char *)s  ; // pointer to the new string that 
we construct
        char *temp_data;
        int i = len;
        struct node **temp_ptr = (struct node**)userData;

       if (len >1) {

        while(i>0){
			        *temp_data = *data;
        			i--;
        			data++;
        			temp_data++;
	    			}
	    *temp_data = '\0';
	    temp_data = temp_data - len;
	    printf("i am in char handle %s and len=%d\n", 
temp_data,len);
	   }


	  add_text(temp_ptr,data);

    }




void add_node(struct node **void_node_ptr, char *el ){

    struct node* next_node_ptr = (struct node*)malloc(sizeof
(struct node*));
    next_node_ptr->child_no = 0;



    struct node *current_node_ptr = (struct node *)
*void_node_ptr;

    // update the previous node with the address of the current 
node
//	current_node_ptr->child[current_node_ptr-
>child_no] = next_node_ptr;
	//current_node_ptr->child_no++;

	next_node_ptr->node_name = el;
	next_node_ptr->parent = current_node_ptr;

	current_node_ptr = next_node_ptr;

}



void add_text(struct node **void_node_ptr,char *data ){

	struct node *current_node_ptr = (struct node *)
*void_node_ptr;
	current_node_ptr->text = data;
	//printf(" in add_text with %s", current_node_ptr-
>text);

}





void close_node(struct node **void_node_ptr ){

	struct node *current_node_ptr = (struct node *)
*void_node_ptr;
	current_node_ptr = current_node_ptr->parent;

}


void
main(int argc, char *argv[]){

printf("i am in main\n");

  XML_Parser p = XML_ParserCreate(NULL);

  if (! p) {

    fprintf(stderr, "Couldn't allocate memory for parser\n");

    exit(-1);

  }


  //char *testdata = "venu\0";
  struct node *node_ptr = (struct node*)malloc(sizeof(struct 
node*));
  node_ptr->child_no = 0;


  //struct node *current_node_ptr = node_ptr;
  void *userData = (void *)node_ptr;

  XML_SetElementHandler(p, start, end);
  XML_SetCharacterDataHandler(p,char_handle);
  XML_SetUserData(p, &userData);



    FILE *fp;
    int len;
    int done=1;
    fp = fopen("/cygdrive/c/master-project/C-
programming/test2.xml", "r");
    len = fread(Buff, 1, BUFFSIZE, fp);
    printf("bytes read are %d and buffer has %d\n", len,sizeof
(Buff));
    fclose(fp);

    //printf("i am here");

    if (XML_Parse(p,Buff,len,done) == XML_STATUS_ERROR) 
{

              fprintf(stderr, "Parse error at line %d:\n%s\n",

                      XML_GetCurrentLineNumber(p),

                      XML_ErrorString(XML_GetErrorCode(p)));

      exit(-1);

     }

}



The contents of the file are 

<a>
<b>
	<c>kkkk</c>
</b>
<d>
	<e>pppp</e>
</d>
</a>

thanks
venu

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

Comment By: Karl Waclawek (kwaclaw)
Date: 2005-03-13 08:56

Message:
Logged In: YES 
user_id=290026

Show us your code - you may have a problem there.

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

Comment By: Nobody/Anonymous (nobody)
Date: 2005-03-04 18:02

Message:
Logged In: NO 

Operating System is HP-UX. 

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

Comment By: Nobody/Anonymous (nobody)
Date: 2005-03-04 18:01

Message:
Logged In: NO 

Operating System is HP-UX. 

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

You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1157018&group_id=10127
From noreply at sourceforge.net  Tue Apr 19 19:56:26 2005
From: noreply at sourceforge.net (SourceForge.net)
Date: Tue Apr 19 19:56:29 2005
Subject: [Expat-bugs] 
	[ expat-Bugs-1023646 ] Error in codepageMap, codepage.c
Message-ID: <E1DNwxW-0006o6-QM@sc8-sf-web4.sourceforge.net>

Bugs item #1023646, was opened at 2004-09-07 08:39
Message generated for change (Comment added) made by kwaclaw
You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1023646&group_id=10127

Category: None
Group: Platform Specific
Status: Open
Resolution: None
Priority: 5
Submitted By: Nobody/Anonymous (nobody)
Assigned to: Karl Waclawek (kwaclaw)
Summary: Error in codepageMap, codepage.c

Initial Comment:
Applies to expat v.1.95.8

>From MS:

"LeadByte:
Specifies a fixed-length array of lead-byte ranges, 
where the number of lead-byte ranges is variable. If 
there are no lead bytes in this code page, then every 
element of the array is NULL. If there are lead bytes in 
this code page, a starting value and ending value is 
specified for each range. Ranges are inclusive. The 
maximum number of lead-byte ranges for any code page 
is five. The array uses two bytes to describe each 
range, with a double-byte null terminator after the last 
range."

Note that "Ranges are inclusive". Therefore the function 
codepageMap should be changed:

for (i = 0; i < MAX_LEADBYTES; i+=2) 
{
  int j, lim;
  if (info.LeadByte[i] == 0 && info.LeadByte[i + 1] == 0) 
    break;
  lim = info.LeadByte[i + 1];
  for (j = info.LeadByte[i]; j <= lim; j++) map[j] = -2;
}

Regards,
Ole Stauning, spam@uning.dk


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

>Comment By: Karl Waclawek (kwaclaw)
Date: 2005-04-19 13:56

Message:
Logged In: YES 
user_id=290026

To Fred: Has this been committed yet?

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

Comment By: Fred L. Drake, Jr. (fdrake)
Date: 2005-01-27 10:17

Message:
Logged In: YES 
user_id=3066

Then I think this is ok to commit if everything continues to
work for you on Windows.  I'll email the original poster
since it doesn't look like SF will be sending him updates
automatically.

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

Comment By: Karl Waclawek (kwaclaw)
Date: 2005-01-27 09:46

Message:
Logged In: YES 
user_id=290026

FWIW, I agree with the above conclusions as well.

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

Comment By: Fred L. Drake, Jr. (fdrake)
Date: 2005-01-27 00:44

Message:
Logged In: YES 
user_id=3066

I'm inclined to agree, having read the CPINFO 
documentation.  Do you have a test case that breaks using 
the current code, and which your proposed change would 
fix? 

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

You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1023646&group_id=10127
From noreply at sourceforge.net  Tue Apr 19 20:26:30 2005
From: noreply at sourceforge.net (SourceForge.net)
Date: Tue Apr 19 20:26:33 2005
Subject: [Expat-bugs] 
	[ expat-Bugs-1023646 ] Error in codepageMap, codepage.c
Message-ID: <E1DNxQc-0005aM-59@sc8-sf-web1.sourceforge.net>

Bugs item #1023646, was opened at 2004-09-07 08:39
Message generated for change (Comment added) made by kwaclaw
You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1023646&group_id=10127

Category: None
Group: Platform Specific
Status: Open
>Resolution: Fixed
Priority: 5
Submitted By: Nobody/Anonymous (nobody)
>Assigned to: Fred L. Drake, Jr. (fdrake)
Summary: Error in codepageMap, codepage.c

Initial Comment:
Applies to expat v.1.95.8

>From MS:

"LeadByte:
Specifies a fixed-length array of lead-byte ranges, 
where the number of lead-byte ranges is variable. If 
there are no lead bytes in this code page, then every 
element of the array is NULL. If there are lead bytes in 
this code page, a starting value and ending value is 
specified for each range. Ranges are inclusive. The 
maximum number of lead-byte ranges for any code page 
is five. The array uses two bytes to describe each 
range, with a double-byte null terminator after the last 
range."

Note that "Ranges are inclusive". Therefore the function 
codepageMap should be changed:

for (i = 0; i < MAX_LEADBYTES; i+=2) 
{
  int j, lim;
  if (info.LeadByte[i] == 0 && info.LeadByte[i + 1] == 0) 
    break;
  lim = info.LeadByte[i + 1];
  for (j = info.LeadByte[i]; j <= lim; j++) map[j] = -2;
}

Regards,
Ole Stauning, spam@uning.dk


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

>Comment By: Karl Waclawek (kwaclaw)
Date: 2005-04-19 14:26

Message:
Logged In: YES 
user_id=290026

Forget my question, I went ahead and committed it.
See codepage.c rev. 1.12.
Assigned to Fred for testing.

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

Comment By: Karl Waclawek (kwaclaw)
Date: 2005-04-19 13:56

Message:
Logged In: YES 
user_id=290026

To Fred: Has this been committed yet?

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

Comment By: Fred L. Drake, Jr. (fdrake)
Date: 2005-01-27 10:17

Message:
Logged In: YES 
user_id=3066

Then I think this is ok to commit if everything continues to
work for you on Windows.  I'll email the original poster
since it doesn't look like SF will be sending him updates
automatically.

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

Comment By: Karl Waclawek (kwaclaw)
Date: 2005-01-27 09:46

Message:
Logged In: YES 
user_id=290026

FWIW, I agree with the above conclusions as well.

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

Comment By: Fred L. Drake, Jr. (fdrake)
Date: 2005-01-27 00:44

Message:
Logged In: YES 
user_id=3066

I'm inclined to agree, having read the CPINFO 
documentation.  Do you have a test case that breaks using 
the current code, and which your proposed change would 
fix? 

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

You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1023646&group_id=10127
From noreply at sourceforge.net  Wed Apr 27 02:25:27 2005
From: noreply at sourceforge.net (SourceForge.net)
Date: Wed Apr 27 02:25:30 2005
Subject: [Expat-bugs] [ expat-Bugs-1190650 ] Incorrectly parses property
	whose value is the property name
Message-ID: <E1DQaMp-000088-S6@sc8-sf-web4.sourceforge.net>

Bugs item #1190650, was opened at 2005-04-26 17:25
Message generated for change (Tracker Item Submitted) made by Item Submitter
You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1190650&group_id=10127

Category: None
Group: None
Status: Open
Resolution: None
Priority: 5
Submitted By: Nobody/Anonymous (nobody)
Assigned to: Nobody/Anonymous (nobody)
Summary: Incorrectly parses property whose value is the property name

Initial Comment:
   I'm using Expat 1.95.8. When I parse an XML doc
which has a property whose value is the same as that
property's name, and there is another XML property
after it in the same XML element, then Expat
misinterprets the first property's value to be the
second property's name. An example that demonstrates
this (more tersely, too!) is that Expat parses the input:

<message hello="hello" world="world">

...as if it were:

<message hello="world" world="world">

Another example would be:

<tag firstProperty="firstProperty"
secondProperty="secondProperty"
thirdProperty="thirdProperty">

...becomes:

<tag firstProperty="secondProperty"
secondProperty="thirdProperty"
thirdProperty="thirdProperty">

   It's a pretty rare case, obviously.

Thanks,

Daniel Brewer
dbrewer( at-no spam )extensis.com

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

You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1190650&group_id=10127
From noreply at sourceforge.net  Wed Apr 27 04:40:06 2005
From: noreply at sourceforge.net (SourceForge.net)
Date: Wed Apr 27 04:40:18 2005
Subject: [Expat-bugs] [ expat-Bugs-1190650 ] Incorrectly parses property
	whose value is the property name
Message-ID: <E1DQcT8-0000kN-NY@sc8-sf-web2.sourceforge.net>

Bugs item #1190650, was opened at 2005-04-26 20:25
Message generated for change (Comment added) made by kwaclaw
You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1190650&group_id=10127

Category: None
Group: None
Status: Open
Resolution: None
Priority: 5
Submitted By: Nobody/Anonymous (nobody)
>Assigned to: Karl Waclawek (kwaclaw)
Summary: Incorrectly parses property whose value is the property name

Initial Comment:
   I'm using Expat 1.95.8. When I parse an XML doc
which has a property whose value is the same as that
property's name, and there is another XML property
after it in the same XML element, then Expat
misinterprets the first property's value to be the
second property's name. An example that demonstrates
this (more tersely, too!) is that Expat parses the input:

<message hello="hello" world="world">

...as if it were:

<message hello="world" world="world">

Another example would be:

<tag firstProperty="firstProperty"
secondProperty="secondProperty"
thirdProperty="thirdProperty">

...becomes:

<tag firstProperty="secondProperty"
secondProperty="thirdProperty"
thirdProperty="thirdProperty">

   It's a pretty rare case, obviously.

Thanks,

Daniel Brewer
dbrewer( at-no spam )extensis.com

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

>Comment By: Karl Waclawek (kwaclaw)
Date: 2005-04-26 22:40

Message:
Logged In: YES 
user_id=290026

This works fine for me with current CVS.
Are you sure the problem is not in your code?

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

You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1190650&group_id=10127
From li.xu at ge.com  Wed Apr 27 04:30:12 2005
From: li.xu at ge.com (Xu, Li (Research))
Date: Wed Apr 27 08:31:30 2005
Subject: [Expat-bugs] expat compile error
Message-ID: <D02325A0F0177A468FD385A98178C53E0D48993F@SHAMLVEM01.e2k.ad.ge.com>

Hello all,

I encountered an compile error when build expat-1.95.8 under cygwin2.29

error message:
/usr/lib/libcygwin.a(libcmain.o)(.text+0x6a):libcmain.c: undefined =
reference to
`WinMain@16'

Does anyone met the same error before? Should i need a more recent =
Cygwin
version to build the expat?

Thanks and Regards

Li

> g GE Global Research Center
_________________________________________________
Xu Li

Real-time / Power Controls Lab (EPST)
GE Global Research Center - Shanghai

1800 Cailun Rd. Zhangjiang High-tech Park, Shanghai, 201203, China
D: 388-1291
T: (86-21)50504666-1291
F: (86-21)50807277
E: li.xu@ge.com


From noreply at sourceforge.net  Wed Apr 27 11:57:33 2005
From: noreply at sourceforge.net (SourceForge.net)
Date: Wed Apr 27 11:57:35 2005
Subject: [Expat-bugs] [ expat-Bugs-1190887 ] bad charset mangement in DTD
Message-ID: <E1DQjIT-0007cw-GU@sc8-sf-web2.sourceforge.net>

Bugs item #1190887, was opened at 2005-04-27 02:57
Message generated for change (Tracker Item Submitted) made by Item Submitter
You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1190887&group_id=10127

Category: None
Group: None
Status: Open
Resolution: None
Priority: 5
Submitted By: Nobody/Anonymous (nobody)
Assigned to: Nobody/Anonymous (nobody)
Summary: bad charset mangement in DTD

Initial Comment:
Run the example hereafter you will have this message :
not well-formed (invalid token) (line 1, offset 17)

The char "?" is in ISO-8859-1but expat doesn't like it.

e-mail : lemathias@gmail.com



#include <stdio.h>
#include "expat.h"


#include <assert.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>


static int XMLCALL test(XML_Parser parser,
                       const XML_Char *context,
                       const XML_Char *base,
                       const XML_Char *systemId,
                       const XML_Char *publicId)
{
    char *text = (char *)XML_GetUserData(parser);
    XML_Parser extparser;

    extparser = XML_ExternalEntityParserCreate(parser,
context, NULL);
    if (extparser == NULL)
    {
      fprintf(stderr, "fine\n");
      return 0;
    }
    if (  XML_Parse(extparser, text, strlen(text),
XML_TRUE)
          == XML_STATUS_ERROR) {
      fprintf(stderr,"%s (line %d, offset %d)\n",
            XML_ErrorString(XML_GetErrorCode(extparser)),
            XML_GetCurrentLineNumber(extparser),
            XML_GetCurrentColumnNumber(extparser));
        return XML_STATUS_ERROR;
    }
    return XML_STATUS_OK;
}

int main(int argc, char *argv[])
{
    char *text =
        "<?xml version='1.0' encoding='ISO-8859-1'
standalone='yes'?>\n"
        "<!DOCTYPE doc SYSTEM 'foo'>\n"
        "<doc>&entity;</doc>";
    char *foo_text =
        "<!ELEMENT Employ?s (#PCDATA)*>"; /* "?" is in
the ISO-8859-1 charset */

    XML_Parser  parser = XML_ParserCreate(NULL);
    if (parser == NULL)
    {
      return 0;
    }

    XML_SetParamEntityParsing(parser,
XML_PARAM_ENTITY_PARSING_ALWAYS);
    XML_SetUserData(parser, foo_text);
    XML_SetExternalEntityRefHandler(parser, test);

    if (XML_Parse(parser, text, strlen(text), XML_TRUE)
== XML_STATUS_OK)
    {
      fprintf(stderr, "fine\n");
      return 0;
    }
 
    if (XML_GetErrorCode(parser) !=
XML_ERROR_UNDEFINED_ENTITY)
    {
      fprintf(stderr, "fine\n");
      return 0;
    }

  return 1;
}

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

You can respond by visiting: 
https://sourceforge.net/tracker/?func=detail&atid=110127&aid=1190887&group_id=10127