|
"""
PYTHON SOFTWARE FOUNDATION LICENSE VERSION 2
--------------------------------------------
1. This LICENSE AGREEMENT is between the Python Software Foundation
("PSF"), and the Individual or Organization ("Licensee") accessing and
otherwise using this software ("Python") in source or binary form and
its associated documentation.
2. Subject to the terms and conditions of this License Agreement, PSF
hereby grants Licensee a nonexclusive, royalty-free, world-wide
license to reproduce, analyze, test, perform and/or display publicly,
prepare derivative works, distribute, and otherwise use Python
alone or in any derivative version, provided, however, that PSF's
License Agreement and PSF's notice of copyright, i.e., "Copyright (c)
2001, 2002, 2003, 2004 Python Software Foundation; All Rights Reserved"
are retained in Python alone or in any derivative version prepared
by Licensee.
3. In the event Licensee prepares a derivative work that is based on
or incorporates Python or any part thereof, and wants to make
the derivative work available to others as provided herein, then
Licensee hereby agrees to include in any such work a brief summary of
the changes made to Python.
4. PSF is making Python available to Licensee on an "AS IS"
basis. PSF MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR
IMPLIED. BY WAY OF EXAMPLE, BUT NOT LIMITATION, PSF MAKES NO AND
DISCLAIMS ANY REPRESENTATION OR WARRANTY OF MERCHANTABILITY OR FITNESS
FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF PYTHON WILL NOT
INFRINGE ANY THIRD PARTY RIGHTS.
5. PSF SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF PYTHON
FOR ANY INCIDENTAL, SPECIAL, OR CONSEQUENTIAL DAMAGES OR LOSS AS
A RESULT OF MODIFYING, DISTRIBUTING, OR OTHERWISE USING PYTHON,
OR ANY DERIVATIVE THEREOF, EVEN IF ADVISED OF THE POSSIBILITY THEREOF.
6. This License Agreement will automatically terminate upon a material
breach of its terms and conditions.
7. Nothing in this License Agreement shall be deemed to create any
relationship of agency, partnership, or joint venture between PSF and
Licensee. This License Agreement does not grant permission to use PSF
trademarks or trade name in a trademark sense to endorse or promote
products or services of Licensee, or any third party.
8. By copying, installing or otherwise using Python, Licensee
agrees to be bound by the terms and conditions of this License
Agreement.
"""
#! /usr/bin/env python
# Convert GNU texinfo files into HTML, one file per node.
# Based on Texinfo 2.14.
# Usage: texi2html [-d] [-d] [-c] inputfile outputdirectory
# The input file must be a complete texinfo file, e.g. emacs.texi.
# This creates many files (one per info node) in the output directory,
# overwriting existing files of the same name. All files created have
# ".html" as their extension.
# XXX To do:
# - handle @comment*** correctly
# - handle @xref {some words} correctly
# - handle @ftable correctly (items aren't indexed?)
# - handle @itemx properly
# - handle @exdent properly
# - add links directly to the proper line from indices
# - check against the definitive list of @-cmds; we still miss (among others):
# - @defindex (hard)
# - @c(omment) in the middle of a line (rarely used)
# - @this* (not really needed, only used in headers anyway)
# - @today{} (ever used outside title page?)
# More consistent handling of chapters/sections/etc.
# Lots of documentation
# Many more options:
# -top designate top node
# -links customize which types of links are included
# -split split at chapters or sections instead of nodes
# -name Allow different types of filename handling. Non unix systems
# will have problems with long node names
# ...
# Support the most recent texinfo version and take a good look at HTML 3.0
# More debugging output (customizable) and more flexible error handling
# How about icons ?
# rpyron 2002-05-07
# Robert Pyron <rpyron@alum.mit.edu>
# 1. BUGFIX: In function makefile(), strip blanks from the nodename.
# This is necesary to match the behavior of parser.makeref() and
# parser.do_node().
# 2. BUGFIX fixed KeyError in end_ifset (well, I may have just made
# it go away, rather than fix it)
# 3. BUGFIX allow @menu and menu items inside @ifset or @ifclear
# 4. Support added for:
# @uref URL reference
# @image image file reference (see note below)
# @multitable output an HTML table
# @vtable
# 5. Partial support for accents, to match MAKEINFO output
# 6. I added a new command-line option, '-H basename', to specify
# HTML Help output. This will cause three files to be created
# in the current directory:
# 'basename'.hhp HTML Help Workshop project file
# 'basename'.hhc Contents file for the project
# 'basename'.hhk Index file for the project
# When fed into HTML Help Workshop, the resulting file will be
# named 'basename'.chm.
# 7. A new class, HTMLHelp, to accomplish item 6.
# 8. Various calls to HTMLHelp functions.
# A NOTE ON IMAGES: Just as 'outputdirectory' must exist before
# running this program, all referenced images must already exist
# in outputdirectory.
import os
import sys
import string
import re
MAGIC = '\\input texinfo'
cmprog = re.compile('^@([a-z]+)([ \t]|$)') # Command (line-oriented)
blprog = re.compile('^[ \t]*$') # Blank line
kwprog = re.compile('@[a-z]+') # Keyword (embedded, usually
# with {} args)
spprog = re.compile('[\n@{}&<>]') # Special characters in
# running text
#
# menu item (Yuck!)
miprog = re.compile('^\* ([^:]*):(:|[ \t]*([^\t,\n.]+)([^ \t\n]*))[ \t\n]*')
# 0 1 1 2 3 34 42 0
# ----- ---------- ---------
# -|-----------------------------
# -----------------------------------------------------
class HTMLNode:
"""Some of the parser's functionality is separated into this class.
A Node accumulates its contents, takes care of links to other Nodes
and saves itself when it is finished and all links are resolved.
"""
DOCTYPE = '<!DOCTYPE HTML PUBLIC "-//IETF//DTD HTML 2.0//EN">'
type = 0
cont = ''
epilogue = '</BODY></HTML>\n'
def __init__(self, dir, name, topname, title, next, prev, up):
self.dirname = dir
self.name = name
if topname:
self.topname = topname
else:
self.topname = name
self.title = title
self.next = next
self.prev = prev
self.up = up
self.lines = []
def write(self, *lines):
map(self.lines.append, lines)
def flush(self):
fp = open(self.dirname + '/' + makefile(self.name), 'w')
fp.write(self.prologue)
fp.write(self.text)
fp.write(self.epilogue)
fp.close()
def link(self, label, nodename, rel=None, rev=None):
if nodename:
if nodename.lower() == '(dir)':
addr = '../dir.html'
title = ''
else:
addr = makefile(nodename)
title = ' TITLE="%s"' % nodename
self.write(label, ': <A HREF="', addr, '"', \
rel and (' REL=' + rel) or "", \
rev and (' REV=' + rev) or "", \
title, '>', nodename, '</A> \n')
def finalize(self):
length = len(self.lines)
self.text = ''.join(self.lines)
self.lines = []
self.open_links()
self.output_links()
self.close_links()
links = ''.join(self.lines)
self.lines = []
self.prologue = (
self.DOCTYPE +
'\n<HTML><HEAD>\n'
' <!-- Converted with texi2html and Python -->\n'
' <TITLE>' + self.title + '</TITLE>\n'
' <LINK REL=Next HREF="'
+ makefile(self.next) + '" TITLE="' + self.next + '">\n'
' <LINK REL=Previous HREF="'
+ makefile(self.prev) + '" TITLE="' + self.prev + '">\n'
' <LINK REL=Up HREF="'
+ makefile(self.up) + '" TITLE="' + self.up + '">\n'
'</HEAD><BODY>\n' +
links)
if length > 20:
self.epilogue = '<P>\n%s</BODY></HTML>\n' % links
def open_links(self):
self.write('<HR>\n')
def close_links(self):
self.write('<HR>\n')
def output_links(self):
if self.cont != self.next:
self.link(' Cont', self.cont)
self.link(' Next', self.next, rel='Next')
self.link(' Prev', self.prev, rel='Previous')
self.link(' Up', self.up, rel='Up')
if self.name <> self.topname:
self.link(' Top', self.topname)
class HTML3Node(HTMLNode):
DOCTYPE = '<!DOCTYPE HTML PUBLIC "-//IETF//DTD HTML Level 3//EN//3.0">'
def open_links(self):
self.write('<DIV CLASS=Navigation>\n <HR>\n')
def close_links(self):
self.write(' <HR>\n</DIV>\n')
class TexinfoParser:
COPYRIGHT_SYMBOL = "©"
FN_ID_PATTERN = "(%(id)s)"
FN_SOURCE_PATTERN = '<A NAME=footnoteref%(id)s' \
' HREF="#footnotetext%(id)s">' \
+ FN_ID_PATTERN + '</A>'
FN_TARGET_PATTERN = '<A NAME=footnotetext%(id)s' \
' HREF="#footnoteref%(id)s">' \
+ FN_ID_PATTERN + '</A>\n%(text)s<P>\n'
FN_HEADER = '\n<P>\n<HR NOSHADE SIZE=1 WIDTH=200>\n' \
'<STRONG><EM>Footnotes</EM></STRONG>\n<P>'
Node = HTMLNode
# Initialize an instance
def __init__(self):
self.unknown = {} # statistics about unknown @-commands
self.filenames = {} # Check for identical filenames
self.debugging = 0 # larger values produce more output
self.print_headers = 0 # always print headers?
self.nodefp = None # open file we're writing to
self.nodelineno = 0 # Linenumber relative to node
self.links = None # Links from current node
self.savetext = None # If not None, save text head instead
self.savestack = [] # If not None, save text head instead
self.htmlhelp = None # html help data
self.dirname = 'tmp' # directory where files are created
self.includedir = '.' # directory to search @include files
self.nodename = '' # name of current node
self.topname = '' # name of top node (first node seen)
self.title = '' # title of this whole Texinfo tree
self.resetindex() # Reset all indices
self.contents = [] # Reset table of contents
self.numbering = [] # Reset section numbering counters
self.nofill = 0 # Normal operation: fill paragraphs
self.values={'html': 1} # Names that should be parsed in ifset
self.stackinfo={} # Keep track of state in the stack
# XXX The following should be reset per node?!
self.footnotes = [] # Reset list of footnotes
self.itemarg = None # Reset command used by @item
self.itemnumber = None # Reset number for @item in @enumerate
self.itemindex = None # Reset item index name
self.node = None
self.nodestack = []
self.cont = 0
self.includedepth = 0
# Set htmlhelp helper class
def sethtmlhelp(self, htmlhelp):
self.htmlhelp = htmlhelp
# Set (output) directory name
def setdirname(self, dirname):
self.dirname = dirname
# Set include directory name
def setincludedir(self, includedir):
self.includedir = includedir
# Parse the contents of an entire file
def parse(self, fp):
line = fp.readline()
lineno = 1
while line and (line[0] == '%' or blprog.match(line)):
line = fp.readline()
lineno = lineno + 1
if line[:len(MAGIC)] <> MAGIC:
raise SyntaxError, 'file does not begin with %r' % (MAGIC,)
self.parserest(fp, lineno)
# Parse the contents of a file, not expecting a MAGIC header
def parserest(self, fp, initial_lineno):
lineno = initial_lineno
self.done = 0
self.skip = 0
self.stack = []
accu = []
while not self.done:
line = fp.readline()
self.nodelineno = self.nodelineno + 1
if not line:
if accu:
if not self.skip: self.process(accu)
accu = []
if initial_lineno > 0:
print '*** EOF before @bye'
break
lineno = lineno + 1
mo = cmprog.match(line)
if mo:
a, b = mo.span(1)
cmd = line[a:b]
if cmd in ('noindent', 'refill'):
accu.append(line)
else:
if accu:
if not self.skip:
self.process(accu)
accu = []
self.command(line, mo)
elif blprog.match(line) and \
'format' not in self.stack and \
'example' not in self.stack:
if accu:
if not self.skip:
self.process(accu)
if self.nofill:
self.write('\n')
else:
self.write('<P>\n')
accu = []
else:
# Append the line including trailing \n!
accu.append(line)
#
if self.skip:
print '*** Still skipping at the end'
if self.stack:
print '*** Stack not empty at the end'
print '***', self.stack
if self.includedepth == 0:
while self.nodestack:
self.nodestack[-1].finalize()
self.nodestack[-1].flush()
del self.nodestack[-1]
# Start saving text in a buffer instead of writing it to a file
def startsaving(self):
if self.savetext <> None:
self.savestack.append(self.savetext)
# print '*** Recursively saving text, expect trouble'
self.savetext = ''
# Return the text saved so far and start writing to file again
def collectsavings(self):
savetext = self.savetext
if len(self.savestack) > 0:
self.savetext = self.savestack[-1]
del self.savestack[-1]
else:
self.savetext = None
return savetext or ''
# Write text to file, or save it in a buffer, or ignore it
def write(self, *args):
try:
text = ''.join(args)
except:
print args
raise TypeError
if self.savetext <> None:
self.savetext = self.savetext + text
elif self.nodefp:
self.nodefp.write(text)
elif self.node:
self.node.write(text)
# Complete the current node -- write footnotes and close file
def endnode(self):
if self.savetext <> None:
print '*** Still saving text at end of node'
dummy = self.collectsavings()
if self.footnotes:
self.writefootnotes()
if self.nodefp:
if self.nodelineno > 20:
self.write('<HR>\n')
[name, next, prev, up] = self.nodelinks[:4]
self.link('Next', next)
self.link('Prev', prev)
self.link('Up', up)
if self.nodename <> self.topname:
self.link('Top', self.topname)
self.write('<HR>\n')
self.write('</BODY>\n')
self.nodefp.close()
self.nodefp = None
elif self.node:
if not self.cont and \
(not self.node.type or \
(self.node.next and self.node.prev and self.node.up)):
self.node.finalize()
self.node.flush()
else:
self.nodestack.append(self.node)
self.node = None
self.nodename = ''
# Process a list of lines, expanding embedded @-commands
# This mostly distinguishes between menus and normal text
def process(self, accu):
if self.debugging > 1:
print '!'*self.debugging, 'process:', self.skip, self.stack,
if accu: print accu[0][:30],
if accu[0][30:] or accu[1:]: print '...',
print
if self.inmenu():
# XXX should be done differently
for line in accu:
mo = miprog.match(line)
if not mo:
line = line.strip() + '\n'
self.expand(line)
continue
bgn, end = mo.span(0)
a, b = mo.span(1)
c, d = mo.span(2)
e, f = mo.span(3)
g, h = mo.span(4)
label = line[a:b]
nodename = line[c:d]
if nodename[0] == ':': nodename = label
else: nodename = line[e:f]
punct = line[g:h]
self.write(' <LI><A HREF="',
makefile(nodename),
'">', nodename,
'</A>', punct, '\n')
self.htmlhelp.menuitem(nodename)
self.expand(line[end:])
else:
text = ''.join(accu)
self.expand(text)
# find 'menu' (we might be inside 'ifset' or 'ifclear')
def inmenu(self):
#if 'menu' in self.stack:
# print 'inmenu :', self.skip, self.stack, self.stackinfo
stack = self.stack
while stack and stack[-1] in ('ifset','ifclear'):
try:
if self.stackinfo[len(stack)]:
return 0
except KeyError:
pass
stack = stack[:-1]
return (stack and stack[-1] == 'menu')
# Write a string, expanding embedded @-commands
def expand(self, text):
stack = []
i = 0
n = len(text)
while i < n:
start = i
mo = spprog.search(text, i)
if mo:
i = mo.start()
else:
self.write(text[start:])
break
self.write(text[start:i])
c = text[i]
i = i+1
if c == '\n':
self.write('\n')
continue
if c == '<':
self.write('<')
continue
if c == '>':
self.write('>')
continue
if c == '&':
self.write('&')
continue
if c == '{':
stack.append('')
continue
if c == '}':
if not stack:
print '*** Unmatched }'
self.write('}')
continue
cmd = stack[-1]
del stack[-1]
try:
method = getattr(self, 'close_' + cmd)
except AttributeError:
self.unknown_close(cmd)
continue
method()
continue
if c <> '@':
# Cannot happen unless spprog is changed
raise RuntimeError, 'unexpected funny %r' % c
start = i
while i < n and text[i] in string.ascii_letters: i = i+1
if i == start:
# @ plus non-letter: literal next character
i = i+1
c = text[start:i]
&
|
