[Python-checkins] CVS: python/nondist/sandbox/help htmldoc.py,NONE,1.1 inspect.py,NONE,1.1 pydoc.py,NONE,1.1 textdoc.py,NONE,1.1

Ka-Ping Yee python-dev@python.org
Sat, 13 Jan 2001 18:27:12 -0800


Update of /cvsroot/python/python/nondist/sandbox/help
In directory usw-pr-cvs1:/tmp/cvs-serv2565/help

Added Files:
	htmldoc.py inspect.py pydoc.py textdoc.py 
Log Message:
Added a first pass at an interactive / shell-command / web-based doc system.


--- NEW FILE: htmldoc.py ---
#!/usr/bin/env python
"""Generate HTML documentation from live Python objects."""

__version__ = 'Ka-Ping Yee <ping@lfw.org>, 29 May 2000'

import sys, os, re, inspect
from string import join, replace, expandtabs, rstrip

# ---------------------------------------------------- formatting utilities
def serialize(stuff):
    """Combine a list containing strings and nested lists into a single
    string.  This lets us manipulate lists until the last moment, since
    rearranging lists is faster than rearranging strings."""
    if type(stuff) is type(''): return stuff
    results = []
    for item in stuff:
        if type(item) is type(''): results.append(item)
        else: results.append(serialize(item))
    return join(results, '')

def htmlescape(text):
    return replace(replace(replace(text, '&', '&amp;'),
                                         '<', '&lt;'),
                                         '>', '&gt;')

def htmlrepr(object):
    return htmlescape(repr(object))

def preformat(text):
    text = htmlescape(expandtabs(text))
    return replace(replace(replace(replace(text, '\n\n', '\n \n'),
                                                 '\n\n', '\n \n'),
                                                 ' ', '&nbsp;'),
                                                 '\n', '<br>\n')

def multicolumn(list, format, cols=4):
    results = ['<table width="100%"><tr>']
    rows = (len(list)+cols-1)/cols

    for col in range(cols):
        results.append('<td width="%d%%" valign=top>' % (100/cols))
        for i in range(rows*col, rows*col+rows):
            if i < len(list):
                results.append(format(list[i]) + '<br>')
        results.append('</td>')
    results.append('</tr></table>')
    return results

def heading(title, fgcol, bgcol, extras=''):
    return ["""
<p><table width="100%%" cellspacing=0 cellpadding=0 border=0>
<tr bgcolor="%s"><td colspan=3 valign=bottom><small><small><br></small></small
><font color="%s" face="helvetica, arial">&nbsp;%s</font></td
><td align=right valign=bottom
><font color="%s" face="helvetica, arial">&nbsp;%s</font></td></tr>
""" % (bgcol, fgcol, title, fgcol, extras), '</table>']

def section(title, fgcol, bgcol, contents, width=20,
            prelude='', marginalia=None, gap='&nbsp;&nbsp;&nbsp;'):
    if marginalia is None:
        marginalia = '&nbsp;' * width
    results = []
    results.append("""
<p><table width="100%%" cellspacing=0 cellpadding=0 border=0>
<tr bgcolor="%s"><td colspan=3 valign=bottom><small><small><br></small></small
><font color="%s" face="helvetica, arial">&nbsp;%s</font></td></tr>
""" % (bgcol, fgcol, title))
    if prelude:
        results.append("""
<tr><td bgcolor="%s">%s</td>
<td bgcolor="%s" colspan=2>%s</td></tr>
""" % (bgcol, marginalia, bgcol, prelude))
    results.append("""
<tr><td bgcolor="%s">%s</td><td>%s</td>
""" % (bgcol, marginalia, gap))

    # Alas, this horrible hack seems to be the only way to force Netscape
    # to expand the main cell consistently to the maximum available width.
    results.append('<td><small><small>' + '&nbsp; '*100 + '</small></small\n>')

    results.append(contents)
    results.append('</td></tr></table>')
    return results

def footer():
    return """
<table width="100%"><tr><td align=right>
<font face="helvetica, arial"><small><small>generated with
<strong>htmldoc</strong> by Ka-Ping Yee</a></small></small></font>
</td></tr></table>
"""

# -------------------------------------------------------- automatic markup
def namelink(name, *dicts):
    for dict in dicts:
        if dict.has_key(name):
            return '<a href="%s">%s</a>' % (dict[name], name)
    return name

def classlink(object, modname, *dicts):
    name = object.__name__
    if object.__module__ != modname:
        name = object.__module__ + '.' + name
    for dict in dicts:
        if dict.has_key(object):
            return '<a href="%s">%s</a>' % (dict[object], name)
    return name

def modulelink(object):
    return '<a href="%s.html">%s</a>' % (object.__name__, object.__name__)

def markup(text, functions={}, classes={}, methods={}, escape=htmlescape):
    """Mark up some plain text, given a context of symbols to look for.
    Each context dictionary maps object names to named anchor identifiers."""
    results = []
    here = 0
    pattern = re.compile('(self\.)?(\w+)')
    while 1:
        match = pattern.search(text, here)
        if not match: break
        start, end = match.regs[2]
        found, name = match.group(0), match.group(2)
        results.append(escape(text[here:start]))

        if text[end:end+1] == '(':
            results.append(namelink(name, methods, functions, classes))
        elif match.group(1):
            results.append('<strong>%s</strong>' % name)
        else:
            results.append(namelink(name, classes))
        here = end
    results.append(text[here:])
    return join(results, '')

def getdoc(object):
    result = inspect.getdoc(object)
    if not result:
        try: result = inspect.getcomments(object)
        except: pass
    return result and rstrip(result) + '\n' or ''

# -------------------------------------------------- type-specific routines
def document_tree(tree, modname, classes={}, parent=None):
    """Produce HTML for a class tree as returned by inspect.getclasstree()."""
    results = ['<dl>\n']
    for entry in tree:
        if type(entry) is type(()):
            c, bases = entry
            results.append('<dt><font face="helvetica, arial"><small>')
            results.append(classlink(c, modname, classes))
            if bases and bases != (parent,):
                parents = []
                for base in bases:
                    parents.append(classlink(base, modname, classes))
                results.append('(' + join(parents, ', ') + ')')
            results.append('\n</small></font></dt>')
        elif type(entry) is type([]):
            results.append('<dd>\n')
            results.append(document_tree(entry, modname, classes, c))
            results.append('</dd>\n')
    results.append('</dl>\n')
    return results

def document_module(object):
    """Produce HTML documentation for a given module object."""
    name = object.__name__
    results = []
    head = '<br><big><big><strong>&nbsp;%s</strong></big></big>' % name
    try:
        file = inspect.getsourcefile(object)
        filelink = '<a href="file:%s">%s</a>' % (file, file)
    except TypeError:
        filelink = '(built-in)'
    if hasattr(object, '__version__'):
        head = head + ' (version: %s)' % htmlescape(object.__version__)
    results.append(heading(head, '#ffffff', '#7799ee', filelink))

    cadr = lambda list: list[1]
    modules = map(cadr, inspect.getmembers(object, inspect.ismodule))

    classes, cdict = [], {}
    for key, value in inspect.getmembers(object, inspect.isclass):
        if (inspect.getmodule(value) or object) is object:
            classes.append(value)
            cdict[key] = cdict[value] = '#' + key
    functions, fdict = [], {}
    for key, value in inspect.getmembers(object, inspect.isroutine):
        if inspect.isbuiltin(value) or inspect.getmodule(value) is object:
            functions.append(value)
            fdict[key] = '#-' + key
            if inspect.isfunction(value): fdict[value] = fdict[key]

    for c in classes:
        for base in c.__bases__:
            key, modname = base.__name__, base.__module__
            if modname != name and sys.modules.has_key(modname):
                module = sys.modules[modname]
                if hasattr(module, key) and getattr(module, key) is base:
                    if not cdict.has_key(key):
                        cdict[key] = cdict[base] = modname + '.html#' + key

    doc = markup(getdoc(object), fdict, cdict, escape=preformat)
    if doc: doc = '<p><small><tt>' + doc + '</tt></small>\n\n'
    else: doc = '<p><small><em>no doc string</em></small>\n'
    results.append(doc)

    if modules:
        contents = multicolumn(modules, modulelink)
        results.append(section('<big><strong>Modules</strong></big>',
                               '#fffff', '#aa55cc', contents))

    if classes:
        contents = document_tree(inspect.getclasstree(classes, 1), name, cdict)
        for item in classes:
            contents.append(document_class(item, fdict, cdict))
        results.append(section('<big><strong>Classes</strong></big>',
                               '#ffffff', '#ee77aa', contents))
    if functions:
        contents = []
        for item in functions:
            contents.append(document_function(item, fdict, cdict))
        results.append(section('<big><strong>Functions</strong></big>',
                               '#ffffff', '#eeaa77', contents))
    return results

def document_class(object, functions={}, classes={}):
    """Produce HTML documentation for a given class object."""
    name = object.__name__
    bases = object.__bases__
    results = []
    
    methods, mdict = [], {}
    for key, value in inspect.getmembers(object, inspect.ismethod):
        methods.append(value)
        mdict[key] = mdict[value] = '#' + name + '-' + key

    if methods:
        for item in methods:
            results.append(document_method(
                item, functions, classes, mdict, name))

    title = '<a name="%s">class <strong>%s</strong></a>' % (name, name)
    if bases:
        parents = []
        for base in bases:
            parents.append(classlink(base, object.__module__, classes))
        title = title + '(%s)' % join(parents, ', ')
    doc = markup(getdoc(object), functions, classes, mdict, escape=preformat)
    if doc: doc = '<small><tt>' + doc + '<br>&nbsp;</tt></small>'
    else: doc = '<small><em>no doc string</em></small>'
    return section(title, '#000000', '#ffc8d8', results, 10, doc)

def document_method(object, functions={}, classes={}, methods={}, clname=''):
    """Produce HTML documentation for a given method object."""
    return document_function(
        object.im_func, functions, classes, methods, clname)

def defaultformat(object):
    return '<small><font color="#a0a0a0">=' + \
        htmlrepr(object) + '</font></small>'

def document_function(object, functions={}, classes={}, methods={}, clname=''):
    """Produce HTML documentation for a given function object."""
    try:
        args, varargs, varkw, defaults = inspect.getargspec(object)
        argspec = inspect.formatargspec(
            args, varargs, varkw, defaults, defaultformat=defaultformat)
    except TypeError:
        argspec = '(<small>...</em></small>)'
    
    if object.__name__ == '<lambda>':
        decl = ['<em>lambda</em> ', argspec[1:-1]]
    else:
        anchor = clname + '-' + object.__name__
        decl = ['<a name="%s"\n>' % anchor,
                '<strong>%s</strong>' % object.__name__, argspec, '</a>\n']
    doc = markup(getdoc(object), functions, classes, methods, escape=preformat)
    if doc:
        doc = replace(doc, '<br>\n', '</tt></small\n><dd><small><tt>')
        doc = ['<dd><small><tt>', doc, '</tt></small>']
    else:
        doc = '<dd><small><em>no doc string</em></small>'
    return ['<dl><dt>', decl, doc, '</dl>']

def document_builtin(object):
    """Produce HTML documentation for a given built-in function."""
    return ('<strong>%s</strong>' % object.__name__ +
            '(<small>...</small>)')

# --------------------------------------------------- main dispatch routine
def document(object):
    """Generate documentation for a given object."""
    if inspect.ismodule(object): results = document_module(object)
    elif inspect.isclass(object): results = document_class(object)
    elif inspect.ismethod(object): results = document_method(object)
    elif inspect.isfunction(object): results = document_function(object)
    elif inspect.isbuiltin(object): results = document_builtin(object)
    else: raise TypeError, 'don\'t know how to document this kind of object'
    return serialize(results)

def index(dir):
    modules = []
    packages = []
    for file in os.listdir(dir):
        path = dir + '/' + file
        if os.path.isfile(path): 
            if file[-3:] == '.py':
                modules.append(file[:-3])
            elif file[-11:] == 'module.so':
                modules.append(file[:-11])
            elif file[-13:] == 'module.so.1':
                modules.append(file[:-13])
        elif os.path.isdir(path):
            if os.path.exists(path + '/__init__.py'):
                packages.append(file)

    def modulelink(name):
        return '<a href="%s.html">%s</a>' % (name, name)
    modules.sort()
    contents = multicolumn(modules, modulelink)
    results = section('<big><strong>%s</strong></big>' % dir,
                      '#ffffff', '#ee77aa', contents)
    return serialize(results)

if __name__ == '__main__':
    import os
    modnames = []
    for arg in sys.argv[1:]:
        if os.path.isdir(arg):
            for file in os.listdir(arg):
                if file[-3:] == '.py':
                    modnames.append(file[:-3])
                elif file[-9:] == 'module.so':
                    modnames.append(file[:-9])
        else:
            if arg[-3:] == '.py':
                modnames.append(arg[:-3])
            else:
                modnames.append(arg)

    for modname in modnames:
        try:
            module = __import__(modname)
        except:
            print 'failed to import %s' % modname
        else:
            file = open(modname + '.html', 'w')
            file.write(
"""<!doctype html public "-//W3C//DTD HTML 4.0 Transitional//EN">
<html><title>%s</title><body bgcolor="#ffffff">
""" % modname)
            file.write(document(module))
            file.write('</body></html>')
            file.close()
            print 'wrote %s.html' % modname

--- NEW FILE: inspect.py ---
"""Get useful information from live Python objects.

This module encapsulates the interface provided by the internal special
attributes (func_*, co_*, im_*, tb_*, etc.) in a friendlier fashion.
It also provides some help for examining source code and class layout.

Here are some of the useful functions provided by this module:

    getdoc(), getcomments() - get documentation on an object
    getclasstree() - arrange classes so as to represent their hierarchy
    getfile(), getsourcefile(), getsource() - find an object's source code
    getargspec(), getargvalues() - get info about function arguments
    formatargspec(), formatargvalues() - format an argument spec
    stack(), trace() - get info about frames on the stack or in a traceback
"""

# This module is in the public domain.  No warranties.

__version__ = 'Ka-Ping Yee <ping@lfw.org>, 1 Jan 2001'

import sys, types, string, dis, imp

# ----------------------------------------------------------- type-checking
def ismodule(object):
    """Return true if the object is a module.

    Module objects provide these attributes:
        __doc__         documentation string
        __file__        filename (missing for built-in modules)"""
    return type(object) is types.ModuleType

def isclass(object):
    """Return true if the object is a class.

    Class objects provide these attributes:
        __doc__         documentation string
        __module__      name of module in which this class was defined"""
    return type(object) is types.ClassType

def ismethod(object):
    """Return true if the object is an instance method.

    Instance method objects provide these attributes:
        __doc__         documentation string
        __name__        name with which this method was defined
        im_class        class object in which this method belongs
        im_func         function object containing implementation of method
        im_self         instance to which this method is bound, or None"""
    return type(object) is types.MethodType

def isfunction(object):
    """Return true if the object is a user-defined function.

    Function objects provide these attributes:
        __doc__         documentation string
        __name__        name with which this function was defined
        func_code       code object containing compiled function bytecode
        func_defaults   tuple of any default values for arguments
        func_doc        (same as __doc__)
        func_globals    global namespace in which this function was defined
        func_name       (same as __name__)"""
    return type(object) in [types.FunctionType, types.LambdaType]

def istraceback(object):
    """Return true if the object is a traceback.

    Traceback objects provide these attributes:
        tb_frame        frame object at this level
        tb_lasti        index of last attempted instruction in bytecode
        tb_lineno       current line number in Python source code
        tb_next         next inner traceback object (called by this level)"""
    return type(object) is types.TracebackType

def isframe(object):
    """Return true if the object is a frame object.

    Frame objects provide these attributes:
        f_back          next outer frame object (this frame's caller)
        f_builtins      built-in namespace seen by this frame
        f_code          code object being executed in this frame
        f_exc_traceback traceback if raised in this frame, or None
        f_exc_type      exception type if raised in this frame, or None
        f_exc_value     exception value if raised in this frame, or None
        f_globals       global namespace seen by this frame
        f_lasti         index of last attempted instruction in bytecode
        f_lineno        current line number in Python source code
        f_locals        local namespace seen by this frame
        f_restricted    0 or 1 if frame is in restricted execution mode
        f_trace         tracing function for this frame, or None"""
    return type(object) is types.FrameType

def iscode(object):
    """Return true if the object is a code object.

    Code objects provide these attributes:
        co_argcount     number of arguments (not including * or ** args)
        co_code         string of raw compiled bytecode
        co_consts       tuple of constants used in the bytecode
        co_filename     name of file in which this code object was created
        co_firstlineno  number of first line in Python source code
        co_flags        bitmap: 1=optimized | 2=newlocals | 4=*arg | 8=**arg
        co_lnotab       encoded mapping of line numbers to bytecode indices
        co_name         name with which this code object was defined
        co_names        tuple of names of local variables
        co_nlocals      number of local variables
        co_stacksize    virtual machine stack space required
        co_varnames     tuple of names of arguments and local variables"""
    return type(object) is types.CodeType

def isbuiltin(object):
    """Return true if the object is a built-in function or method.

    Built-in functions and methods provide these attributes:
        __doc__         documentation string
        __name__        original name of this function or method
        __self__        instance to which a method is bound, or None"""
    return type(object) in [types.BuiltinFunctionType,
                            types.BuiltinMethodType]

def isroutine(object):
    """Return true if the object is any kind of function or method."""
    return type(object) in [types.FunctionType, types.LambdaType,
                            types.MethodType, types.BuiltinFunctionType,
                            types.BuiltinMethodType]

def getmembers(object, predicate=None):
    """Return all members of an object as (key, value) pairs sorted by key.
    Optionally, only return members that satisfy a given predicate."""
    results = []
    for key in dir(object):
        value = getattr(object, key)
        if not predicate or predicate(value):
            results.append((key, value))
    results.sort()
    return results

# -------------------------------------------------- source code extraction
def indentsize(line):
    """Return the indent size, in spaces, at the start of a line of text."""
    expline = string.expandtabs(line)
    return len(expline) - len(string.lstrip(expline))

def getdoc(object):
    """Get the documentation string for an object.

    All tabs are expanded to spaces.  To clean up docstrings that are
    indented to line up with blocks of code, any whitespace than can be
    uniformly removed from the second line onwards is removed."""
    if hasattr(object, '__doc__') and object.__doc__:
        lines = string.split(string.expandtabs(object.__doc__), '\n')
        margin = None
        for line in lines[1:]:
            content = len(string.lstrip(line))
            if not content: continue
            indent = len(line) - content
            if margin is None: margin = indent
            else: margin = min(margin, indent)
        if margin is not None:
            for i in range(1, len(lines)): lines[i] = lines[i][margin:]
        return string.join(lines, '\n')

def getfile(object):
    """Try to guess which (text or binary) file an object was defined in."""
    if ismodule(object):
        if hasattr(object, '__file__'):
            return object.__file__
        raise TypeError, 'arg is a built-in module'
    if isclass(object):
        object = sys.modules[object.__module__]
        if hasattr(object, '__file__'):
            return object.__file__
        raise TypeError, 'arg is a built-in class'
    if ismethod(object):
        object = object.im_func
    if isfunction(object):
        object = object.func_code
    if istraceback(object):
        object = object.tb_frame
    if isframe(object):
        object = object.f_code
    if iscode(object):
        return object.co_filename
    raise TypeError, 'arg is not a module, class, method, ' \
                     'function, traceback, frame, or code object'

modulesbyfile = {}

def getmodule(object):
    """Try to guess which module an object was defined in."""
    try:
        file = getsourcefile(object)
    except TypeError:
        return None
    if modulesbyfile.has_key(file):
        return sys.modules[modulesbyfile[file]]
    for module in sys.modules.values():
        if hasattr(module, '__file__'):
            modulesbyfile[getsourcefile(module)] = module.__name__
    if modulesbyfile.has_key(file):
        return sys.modules[modulesbyfile[file]]
    main = sys.modules['__main__']
    try:
        mainobject = getattr(main, object.__name__)
        if mainobject is object: return main
    except AttributeError: pass
    builtin = sys.modules['__builtin__']
    try:
        builtinobject = getattr(builtin, object.__name__)
        if builtinobject is object: return builtin
    except AttributeError: pass

def getsourcefile(object):
    """Try to guess which Python source file an object was defined in."""
    filename = getfile(object)
    if filename[-4:] == '.pyc':
        filename = filename[:-4] + '.py'
    return filename

def findsource(object):
    """Find the first line of code corresponding to a given module, class,
    method, function, traceback, frame, or code object; return the entire
    contents of the source file and the starting line number.  An IOError
    exception is raised if the source code cannot be retrieved."""
    try:
        file = open(getsourcefile(object))
        lines = file.readlines()
        file.close()
    except (TypeError, IOError):
        raise IOError, 'could not get source code'

    if ismodule(object):
        return lines, 0

    if isclass(object):
        name = object.__name__
        matches = (['class', name], ['class', name + ':'])
        for i in range(len(lines)):
            if string.split(lines[i])[:2] in matches:
                return lines, i
        else: raise IOError, 'could not find class definition'

    if ismethod(object):
        object = object.im_func
    if isfunction(object):
        object = object.func_code
    if istraceback(object):
        object = object.tb_frame
    if isframe(object):
        object = object.f_code
    if iscode(object):
        try:
            lnum = object.co_firstlineno - 1
        except AttributeError:
            raise IOError, 'could not find function definition'
        else:
            while lnum > 0:
                if string.split(lines[lnum])[:1] == ['def']: break
                lnum = lnum - 1
            return lines, lnum

def getcomments(object):
    """Get lines of comments immediately preceding an object's source code."""
    try: lines, lnum = findsource(object)
    except: return None

    if ismodule(object):
        # Look for a comment block at the top of the file.
        start = 0
        if lines[0][:2] == '#!': start = 1
        while start < len(lines) and string.strip(lines[start]) in ['', '#']:
            start = start + 1
        if lines[start][:1] == '#':
            comments = []
            end = start
            while end < len(lines) and lines[end][:1] == '#':
                comments.append(string.expandtabs(lines[end]))
                end = end + 1
            return string.join(comments, '')

    # Look for a preceding block of comments at the same indentation.
    elif lnum > 0:
        indent = indentsize(lines[lnum])
        end = lnum - 1
        if string.strip(lines[end]) == '':
            while end >= 0 and string.strip(lines[end]) == '':
                end = end - 1
        else:
            while string.lstrip(lines[end])[:1] != '#' and \
                indentsize(lines[end]) == indent:
                end = end - 1
        if end >= 0 and string.lstrip(lines[end])[:1] == '#' and \
            indentsize(lines[end]) == indent:
            comments = [string.lstrip(string.expandtabs(lines[end]))]
            if end > 0:
                end = end - 1
                comment = string.lstrip(string.expandtabs(lines[end]))
                while comment[:1] == '#' and indentsize(lines[end]) == indent:
                    comments[:0] = [comment]
                    end = end - 1
                    if end < 0: break
                    comment = string.lstrip(string.expandtabs(lines[end]))
            return string.join(comments, '')

import tokenize

class ListReader:
    """Provide a readline() method to return lines from a list of strings."""
    def __init__(self, lines):
        self.lines = lines
        self.index = 0

    def readline(self):
        i = self.index
        if i < len(self.lines):
            self.index = i + 1
            return self.lines[i]
        else: return ''

class EndOfBlock(Exception): pass

class BlockFinder:
    """Provide a tokeneater() method to detect the end of a code block."""
    def __init__(self):
        self.indent = 0
        self.started = 0
        self.last = 0

    def tokeneater(self, type, token, (srow, scol), (erow, ecol), line):
        if not self.started:
            if type == tokenize.NAME: self.started = 1
        elif type == tokenize.NEWLINE:
            self.last = srow
        elif type == tokenize.INDENT:
            self.indent = self.indent + 1
        elif type == tokenize.DEDENT:
            self.indent = self.indent - 1
            if self.indent == 0: raise EndOfBlock, self.last

def getblock(lines):
    """Extract the block of code at the top of the given list of lines."""
    try:
        tokenize.tokenize(ListReader(lines).readline, BlockFinder().tokeneater)
    except EndOfBlock, eob:
        return lines[:eob.args[0]]

def getsourcelines(object):
    """Try to get the source code corresponding to a module, class, method,
    function, traceback, frame, or code object.  Return a list of lines and
    the line number of the first line, or raise an IOError exception if the
    source code cannot be retrieved."""
    lines, lnum = findsource(object)

    if ismodule(object): return lines, 0
    else: return getblock(lines[lnum:]), lnum

def getsource(object):
    """Try to get the source code corresponding to a module, class, method,
    function, traceback, frame, or code object.  Return a string, or raise
    an IOError exception if the source code cannot be retrieved."""
    lines, lnum = getsourcelines(object)
    return string.join(lines, '')

# --------------------------------------------------- class tree extraction
def walktree(classes, children, parent):
    """Recursive helper function for getclasstree()."""
    results = []
    classes.sort(lambda a, b: cmp(a.__name__, b.__name__))
    for c in classes:
        results.append((c, c.__bases__))
        if children.has_key(c):
            results.append(walktree(children[c], children, c))
    return results

def getclasstree(classes, unique=0):
    """Arrange the given list of classes into a hierarchy of nested lists.
    Where a nested list appears, it contains classes derived from the class
    whose entry immediately precedes the list.  Each entry is a 2-tuple
    containing a class and a tuple of its base classes.  If the 'unique'
    argument is true, exactly one entry appears in the returned structure
    for each class in the given list.  Otherwise, classes that multiply
    inherit, and their descendants, will appear multiple times."""
    children = {}
    roots = []
    for c in classes:
        if c.__bases__:
            for parent in c.__bases__:
                if not children.has_key(parent):
                    children[parent] = []
                children[parent].append(c)
                if unique and parent in classes: break
        elif c not in roots:
            roots.append(c)
    for parent in children.keys():
        if parent not in classes:
            roots.append(parent)
    return walktree(roots, children, None)

# ------------------------------------------------ argument list extraction
# These constants are from Python's compile.h.
CO_OPTIMIZED, CO_NEWLOCALS, CO_VARARGS, CO_VARKEYWORDS = 1, 2, 4, 8

def getargs(co):
    """Get information about the arguments accepted by a code object.
    Three things are returned: (args, varargs, varkw), where 'args' is
    a list of argument names (possibly containing nested lists), and
    'varargs' and 'varkw' are the names of the * and ** arguments or None."""
    if not iscode(co): raise TypeError, 'arg is not a code object'

    code = co.co_code
    nargs = co.co_argcount
    names = co.co_varnames
    args = list(names[:nargs])
    step = 0

    # The following acrobatics are for anonymous (tuple) arguments.
    for i in range(nargs):
        if args[i][:1] in ['', '.']:
            stack, remain, count = [], [], []
            while step < len(code):
                op = ord(code[step])
                step = step + 1
                if op >= dis.HAVE_ARGUMENT:
                    opname = dis.opname[op]
                    value = ord(code[step]) + ord(code[step+1])*256
                    step = step + 2
                    if opname == 'UNPACK_TUPLE':
                        remain.append(value)
                        count.append(value)
                    elif opname == 'STORE_FAST':
                        stack.append(names[value])
                        remain[-1] = remain[-1] - 1
                        while remain[-1] == 0:
                            remain.pop()
                            size = count.pop()
                            stack[-size:] = [stack[-size:]]
                            if not remain: break
                            remain[-1] = remain[-1] - 1
                        if not remain: break
            args[i] = stack[0]

    varargs = None
    if co.co_flags & CO_VARARGS:
        varargs = co.co_varnames[nargs]
        nargs = nargs + 1
    varkw = None
    if co.co_flags & CO_VARKEYWORDS:
        varkw = co.co_varnames[nargs]
    return args, varargs, varkw

def getargspec(func):
    """Get the names and default values of a function's arguments.
    A tuple of four things is returned: (args, varargs, varkw, defaults).
    'args' is a list of the argument names (it may contain nested lists).
    'varargs' and 'varkw' are the names of the * and ** arguments or None.
    'defaults' is an n-tuple of the default values of the last n arguments."""
    if not isfunction(func): raise TypeError, 'arg is not a Python function'
    args, varargs, varkw = getargs(func.func_code)
    return args, varargs, varkw, func.func_defaults

def getargvalues(frame):
    """Get information about arguments passed into a particular frame.
    A tuple of four things is returned: (args, varargs, varkw, locals).
    'args' is a list of the argument names (it may contain nested lists).
    'varargs' and 'varkw' are the names of the * and ** arguments or None.
    'locals' is the locals dictionary of the given frame."""
    args, varargs, varkw = getargs(frame.f_code)
    return args, varargs, varkw, frame.f_locals

def strseq(object, convert=str):
    """Recursively walk a sequence, stringifying each element."""
    if type(object) in [types.ListType, types.TupleType]:
        results = map(lambda o, c=convert: strseq(o, c), object)
        if len(results) == 1:
            return '(' + results[0] + ',)'
        else:
            return '(' + string.join(results, ', ') + ')'
    else:
        return convert(object)

def formatargspec(args, varargs=None, varkw=None, defaults=None,
                  argformat=str, defaultformat=lambda x: '=' + repr(x),
                  varargsformat=lambda name: '*' + name,
                  varkwformat=lambda name: '**' + name):
    """Format a pretty argument spec from the 4-tuple returned by getargspec.
    The arguments are (args, varargs, varkw, defaults)."""
    specs = []
    if defaults:
        firstdefault = len(args) - len(defaults)
    for i in range(len(args)):
        spec = strseq(args[i], argformat)
        if defaults and i >= firstdefault:
            spec = spec + defaultformat(defaults[i - firstdefault])
        specs.append(spec)
    if varargs:
        specs.append(varargsformat(varargs))
    if varkw:
        specs.append(varkwformat(varkw))
    return '(' + string.join(specs, ', ') + ')'

def formatargvalues(args, varargs, varkw, locals,
                    argformat=str, valueformat=repr,
                    varargsformat=lambda name: '*' + name,
                    varkwformat=lambda name: '**' + name):
    """Format a pretty argument spec from the 4-tuple returned by getargvalues.
    The arguments are (args, varargs, varkw, locals)."""
    def convert(name, locals=locals,
                argformat=argformat, valueformat=valueformat):
        return argformat(name) + '=' + valueformat(locals[name])
    specs = []
    for i in range(len(args)):
        specs.append(strseq(args[i], convert))
    if varargs:
        specs.append(varargsformat(varargs) + '=' +
                     valueformat(locals[varargs]))
    if varkw:   
        specs.append(varkwformat(varkw) + '=' + valueformat(locals[varkw]))
    return '(' + string.join(specs, ', ') + ')'

# -------------------------------------------------- stack frame extraction
def getframe(frame, context=1):
    """For a given frame or traceback object, return the filename, line
    number, function name, a given number of lines of context from the
    source code, and the index of the line within the lines of context."""
    if istraceback(frame):
        frame = frame.tb_frame
    if not isframe(frame):
        raise TypeError, 'arg is not a frame or traceback object'

    filename = getsourcefile(frame)
    if context > 0:
        start = frame.f_lineno - 1 - context/2
        try:
            lines, lnum = findsource(frame)
            start = max(start, 1)
            start = min(start, len(lines) - context)
            lines = lines[start:start+context]
            index = frame.f_lineno - 1 - start
        except:
            lines = index = None
    else:
        lines = index = None

    return (filename, frame.f_lineno, frame.f_code.co_name, lines, index)

def getouterframes(frame, context=1):
    """Get a list of records for a frame and all higher (calling) frames.
    Each record contains a frame object, filename, line number, function
    name, the requested amount of context, and index within the context."""
    framelist = []
    while frame:
        framelist.append((frame,) + getframe(frame, context))
        frame = frame.f_back
    return framelist

def getinnerframes(traceback, context=1):
    """Get a list of records for a traceback's frame and all lower frames.
    Each record contains a frame object, filename, line number, function
    name, the requested amount of context, and index within the context."""
    traceback = traceback.tb_next
    framelist = []
    while traceback:
        framelist.append((traceback.tb_frame,) + getframe(traceback, context))
        traceback = traceback.tb_next
    return framelist

def currentframe():
    """Return the frame object for the caller's stack frame."""
    try:
        raise 'catch me'
    except:
        return sys.exc_traceback.tb_frame.f_back

if hasattr(sys, '_getframe'): currentframe = sys._getframe

def stack(context=1):
    """Return a list of records for the stack above the caller's frame."""
    return getouterframes(currentframe().f_back, context)

def trace(context=1):
    """Return a list of records for the stack below the current exception.""" 
    return getinnerframes(sys.exc_traceback, context)

--- NEW FILE: pydoc.py ---
#!/usr/bin/env python

"""Format Python documentation for interactive use.

At the shell command line outside of Python, run "pydoc <name>" to show
documentation on something.  <name> may be the name of a Python function,
module, package, or a dotted reference to a class or function within a
module or module in a package.

Or, at the shell prompt, run "pydoc -k <keyword>" to search for a keyword
in the one-line descriptions of modules.

Or, at the shell prompt, run "pydoc -p <port>" to start an HTTP server
on a given port on the local machine to generate documentation web pages.

In the Python interpreter, do "from pydoc import help" to provide online
help.  Calling help(thing) on a Python object documents the object."""

__author__ = "Ka-Ping Yee <ping@lfw.org>"
__version__ = "10 January 2001"

import sys, os, string, types, getopt
import inspect, htmldoc, textdoc

def precis(filename):
    """Get the one-line summary out of a module file."""
    file = open(filename)
    line = file.readline()
    while line[:1] in ['#', '\n']:
        line = file.readline()
    if line[-2:] == '\\\n': line = line[:-2] + file.readline()
    file.close()
    line = string.strip(line)
    if line[:3] == '"""':
        i = string.find(line, '"""', 3)
        if i >= 0: return line[3:i]
        return line[3:]

identchars = string.letters + string.digits + '_'

def index(dir):
    """Return a list of (module-name, precis) pairs for a given directory."""
    results = []
    for entry in os.listdir(dir):
        path = os.path.join(dir, entry)
        init = os.path.join(path, '__init__.py')
        if os.path.isdir(path) and os.path.exists(init):
            results.extend(map(
                lambda (m, s), pkg=entry: (pkg + '.' + m, s), index(path)))
        elif os.path.isfile(path) and entry[-3:] == '.py':
            results.append((entry[:-3], precis(path)))
    return results

def pager(text):
    """The first time this is called, determine what kind of pager to use."""
    global pager
    pager = getpager()
    pager(text)

def getpager():
    """Decide what method to use for paging through text."""
    if not sys.stdin.isatty() or type(sys.stdout) is not types.FileType:
        return plainpager
    if os.environ.has_key('PAGER'):
        return lambda text: pipepager(text, os.environ['PAGER'])
    if hasattr(sys, 'winver'):
        return lambda text: tempfilepager(text, 'more')
    if hasattr(os, 'system') and os.system('less 2>/dev/null') == 0:
        return lambda text: pipepager(text, 'less')

    import tempfile
    filename = tempfile.mktemp()
    open(filename, 'w').close()
    try:
        if hasattr(os, 'system') and os.system('more %s' % filename) == 0:
            return lambda text: pipepager(text, 'more')
        else:
            return ttypager
    finally:
        os.unlink(filename)

def pipepager(text, cmd):
    """Page through text by feeding it to another program."""
    pipe = os.popen(cmd, 'w')
    try:
        pipe.write(text)
    except IOError:
        # Ignore broken pipes caused by quitting the pager program.
        pass
    pipe.close()

def tempfilepager(text, cmd):
    """Page through text by invoking a program on a temporary file."""
    import tempfile
    filename = tempfile.mktemp()
    file = open(filename, 'w')
    file.write(text)
    file.close()
    try:
        os.system(cmd + ' ' + filename)
    finally:
        os.unlink(filename)

def plain(text):
    """Remove boldface formatting from text."""
    import re
    return re.sub('.\b', '', text)

def ttypager(text):
    """Page through text on a text terminal."""
    lines = string.split(plain(text), '\n')
    try:
        import tty
    except ImportError:
        tty = None

    try:
        if tty:
            fd = sys.stdin.fileno()
            old = tty.tcgetattr(fd)
            tty.setcbreak(fd)
            getchar = lambda: sys.stdin.read(1)
        else:
            getchar = lambda: sys.stdin.readline()[:-1][:1]

        r = inc = 24
        sys.stdout.write(string.join(lines[:inc], '\n') + '\n')
        while lines[r:]:
            sys.stdout.write('-- more --')
            sys.stdout.flush()
            c = getchar()

            if c in ['q', 'Q']:
                sys.stdout.write('\r          \r')
                break
            elif c in ['\r', '\n']:
                sys.stdout.write('\r          \r' + lines[r] + '\n')
                r = r + 1
                continue

            if c in ['b', 'B', '\x1b']:
                r = r - inc - inc
                if r < 0: r = 0
            sys.stdout.write('\n' + string.join(lines[r:r+inc], '\n') + '\n')
            r = r + inc

    finally:
        if tty:
            tty.tcsetattr(fd, tty.TCSAFLUSH, old)

def plainpager(text):
    sys.stdout.write(plain(text))

def describe(thing):
    """Produce a short description of the given kind of thing."""
    if inspect.ismodule(thing):
        if thing.__name__ in sys.builtin_module_names:
            return 'built-in module ' + thing.__name__
        if hasattr(thing, '__path__'):
            return 'package ' + thing.__name__
        else:
            return 'module ' + thing.__name__
    if inspect.isbuiltin(thing):
        return 'built-in function ' + thing.__name__
    if inspect.isclass(thing):
        return 'class ' + thing.__name__
    if inspect.isfunction(thing):
        return 'function ' + thing.__name__
    if inspect.ismethod(thing):
        return 'method ' + thing.__name__
    return repr(thing)

def find(name):
    """Locate an object by name (or dotted path), importing as necessary."""
    if hasattr(__builtins__, name):
        return None, getattr(__builtins__, name)
    parts = string.split(name, '.')
    n = 1
    while n <= len(parts):
        name = string.join(parts[:n], '.')
        try:
            mod = __import__(name)
        except ImportError:
            break
        try:
            mod = reload(mod)
        except ImportError:
            pass
        try:
            x = mod
            for p in parts[1:]:
                x = getattr(x, p)
            return string.join(parts[:-1], '.'), x
        except AttributeError:
            n = n + 1
            continue
    return None, None

# ------------------------------------------------------ external interface
def doc(thing):
    """Display documentation on an object (for interactive use)."""
    if type(thing) is type(""):
        path, x = find(thing)
        if x:
            thing = x
        else:
            print 'could not import or find %s' % thing
            return

    desc = describe(thing)
    module = inspect.getmodule(thing)
    if module and module is not thing:
        desc = desc + ' in module ' + module.__name__
    pager('Help on %s:\n\n' % desc + textdoc.document(thing))

class Helper:
    def __repr__(self):
        return """To get help on a Python object, call help(object).
To get help on a module or package, either import it before calling
help(module) or call help('modulename')."""

    def __call__(self, object):
        doc(object)

help = Helper()

def man(key):
    """Display documentation on an object in a form similar to man(1)."""
    path, x = find(key)
    if x:
        title = 'Python Library Documentation: ' + describe(x)
        if path: title = title + ' in ' + path
        pager('\n' + title + '\n\n' + textdoc.document(x))
        found = 1
    else:
        print 'no Python documentation found for %s' % key

def apropos(key):
    for module in sys.builtin_module_names:
        desc = __import__(module).__doc__
        if desc:
            desc = string.split(desc, '\n')[0]
        if (string.find(string.lower(module), key) >= 0 or 
            desc and string.find(string.lower(desc), key) >= 0):
            print module, '-', desc
    seen = {}
    for dir in sys.path:
        for module, desc in index(dir or '.'):
            desc = desc or '(no description)'
            if not seen.has_key(module):
                seen[module] = 1
                if (string.find(string.lower(module), key) >= 0 or 
                    desc and string.find(string.lower(desc), key) >= 0):
                    if module[-9:] == '.__init__':
                        print module[:-9], '(package) -', desc
                    else:
                        print module, '-', desc

def server(port):
    print 'starting server on port', port
    import BaseHTTPServer

    class DocReqHandler(BaseHTTPServer.BaseHTTPRequestHandler):
        def send_document(self, title, contents):
            self.send_response(200)
            self.send_header('Content-Type', 'text/html')
            self.end_headers()
            self.wfile.write(
'''<!doctype html public "-//W3C//DTD HTML 4.0 Transitional//EN">
<html><title>Python: %s</title><body bgcolor="#ffffff">''' % title)
            self.wfile.write(contents)
            self.wfile.write('</body></html>')

        def do_GET(self):
            path = self.path
            if path[-5:] == '.html': path = path[:-5]
            if path[:1] == '/': path = path[1:]
            if path:
                p, x = find(path)
                if x:
                    self.send_document(describe(x), htmldoc.document(x))
                else:
                    self.send_document(path,
'There is no Python module or object named "%s".' % path)
            else:
                contents = htmldoc.heading(
                    '<br><big><big><strong>&nbsp;'
                    'Python: Index of Modules'
                    '</strong></big></big>',
                    '#ffffff', '#7799ee')
                builtins = []
                for name in sys.builtin_module_names:
                    builtins.append('<a href="%s.html">%s</a>' % (name, name))
                contents.append('<p>Built-in modules: ')
                contents.append(string.join(builtins, ', '))
                contents.extend(map(htmldoc.index, sys.path))
                contents = htmldoc.serialize(contents)
                self.send_document('Index of Modules', contents)

        def log_message(self, *args): pass

    BaseHTTPServer.HTTPServer(('', port), DocReqHandler).serve_forever()

def usage():
    print """%s <name> ...
    Show documentation on something.
    <name> may be the name of a Python function, module,
    package, or a dotted reference to a class or function
    within a module or module in a package.

%s -k <keyword>
    Search for a keyword in the short descriptions of modules.

%s -p <port>
    Start an HTTP server on the given port on the local machine.
""" % ((sys.argv[0],) * 3)

if __name__ == '__main__':
    try:
        opts, args = getopt.getopt(sys.argv[1:], 'k:p:')
    except getopt.error:
        usage()
    else:
        for opt, val in opts:
            if opt == '-k':
                apropos(string.lower(val))
                break
            if opt == '-p':
                try:
                    port = int(val)
                except ValueError:
                    usage()
                else:
                    server(port)
                break
        else:
            if args:
                for arg in args:
                    man(arg)
            else:
                usage()

--- NEW FILE: textdoc.py ---
"""Generate text documentation from live Python objects."""

__version__ = 'Ka-Ping Yee <ping@lfw.org>, 10 Jan 2001'

import sys, inspect
from string import join, split, strip, rstrip

# ---------------------------------------------------- formatting utilities
def serialize(stuff):
    """Combine a list containing strings and nested lists into a single
    string.  This lets us manipulate lists until the last moment, since
    rearranging lists is faster than rearranging strings."""
    if type(stuff) is type(''): return stuff
    results = []
    for item in stuff:
        if type(item) is type(''): results.append(item)
        else: results.append(serialize(item))
    return join(results, '')

def bold(text):
    result = ''
    for char in text:
        result = result + char + '\b' + char
    return result

def section(title, contents):
    return bold(title) + '\n' + rstrip(indent(contents)) + '\n\n'

def indent(text, spaces=4):
    """Indent text a given number of spaces."""
    if type(text) is type([]): text = serialize(text)
    lines = split(text, '\n')
    lines = map(lambda line, prefix=' ' * spaces: prefix + line, lines)
    if lines: lines[-1] = rstrip(lines[-1])
    return join(lines, '\n')

def classname(object, modname):
    name = object.__name__
    if object.__module__ != modname:
        name = object.__module__ + '.' + name
    return name

def getdoc(object):
    result = inspect.getdoc(object)
    if not result:
        try: result = inspect.getcomments(object)
        except: pass
    return result and rstrip(result) + '\n' or ''

# -------------------------------------------------- type-specific routines
def document_tree(tree, modname, parent=None, prefix=''):
    """Render in text a class tree as returned by inspect.getclasstree()."""
    results = []
    for entry in tree:
        if type(entry) is type(()):
            c, bases = entry
            results.append(prefix + classname(c, modname))
            if bases and bases != (parent,):
                parents = map(lambda c, m=modname: classname(c, m), bases)
                results.append('(%s)' % join(parents, ', '))
            results.append('\n')
        elif type(entry) is type([]):
            results.append(document_tree(entry, modname, c, prefix + '    '))
    return results

def document_module(object):
    """Produce text documentation for a given module object."""
    results = []

    name = object.__name__
    lines = split(strip(getdoc(object)), '\n')
    if len(lines) == 1:
        name = name + ' - ' + lines[0]
        lines = []
    elif len(lines) >= 2 and not rstrip(lines[1]):
        name = name + ' - ' + lines[0]
        lines = lines[2:]
    results.append(section('NAME', name))
    try: file = inspect.getsourcefile(object)
    except TypeError: file = None
    results.append(section('FILE', file or '(built-in)'))
    if lines:
        results.append(section('DESCRIPTION', join(lines, '\n')))

    classes = []
    for key, value in inspect.getmembers(object, inspect.isclass):
        if (inspect.getmodule(value) or object) is object:
            classes.append(value)
    functions = []
    for key, value in inspect.getmembers(object, inspect.isroutine):
        if inspect.isbuiltin(value) or inspect.getmodule(value) is object:
            functions.append(value)

    if classes:
        contents = document_tree(
            inspect.getclasstree(classes, 1), object.__name__)
        contents.append('\n')
        for item in classes:
            contents.append([document_class(item), '\n'])
        results.append(section('CLASSES', contents))

    if functions:
        contents = []
        for item in functions:
            contents.append([document_function(item), '\n'])
        results.append(section('FUNCTIONS', contents))

    if hasattr(object, '__version__'):
        version = object.__version__
        if hasattr(object, '__date__'):
            version = version + ', ' + object.__date__
        results.append(section('VERSION', version))

    if hasattr(object, '__author__'):
        author = object.__author__
        if hasattr(object, '__email__'):
            author = author + ' <' + object.__email__ + '>'
        results.append(section('AUTHOR', author))

    return results

def document_class(object):
    """Produce text documentation for a given class object."""
    name = object.__name__
    bases = object.__bases__
    doc = getdoc(object)
    if doc:
        results = [doc, '\n']
    else:
        results = [doc]

    methods = map(lambda (key, value): value,
                  inspect.getmembers(object, inspect.ismethod))
    for item in methods:
        results.append([document_method(item), '\n'])

    title = 'class ' + bold(name)
    if bases:
        parents = map(lambda c, m=object.__module__: classname(c, m), bases)
        title = title + '(%s)' % join(parents, ', ')

    return title + '\n' + rstrip(indent(results)) + '\n'

def document_method(object):
    return document_function(object.im_func)

def document_function(object):
    """Produce text documentation for a given function object."""
    try:
        args, varargs, varkw, defaults = inspect.getargspec(object)
        argspec = inspect.formatargspec(args, varargs, varkw, defaults)
    except TypeError:
        argspec = '(...)'

    if object.__name__ == '<lambda>':
        decl = ['<lambda> ', argspec[1:-1]]
    else:
        decl = bold(object.__name__) + argspec
    doc = getdoc(object)
    if doc:
        return decl + '\n' + rstrip(indent(doc)) + '\n'
    else:
        return decl + '\n'

def document_builtin(object):
    return [bold(object.__name__) + '(...)\n',
            rstrip(indent(object.__doc__)) + '\n']

# --------------------------------------------------- main dispatch routine
def document(object):
    """Generate documentation for a given object."""
    if inspect.ismodule(object): results = document_module(object)
    elif inspect.isclass(object): results = document_class(object)
    elif inspect.ismethod(object): results = document_method(object)
    elif inspect.isfunction(object): results = document_function(object)
    elif inspect.isbuiltin(object): results = document_builtin(object)
    else: raise TypeError, 'don\'t know how to document this kind of object'
    return serialize(results)