cpython/Tools/scripts/texi2html.py

1614 lines
51 KiB
Python
Raw Normal View History

#! /usr/bin/env python
1995-03-15 07:26:05 -04:00
# Convert GNU texinfo files into HTML, one file per node.
# Based on Texinfo 2.14.
1995-08-28 00:01:00 -03:00
# Usage: texi2html [-d] [-d] [-c] inputfile outputdirectory
1995-03-15 07:26:05 -04:00
# 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?)
1995-08-28 00:01:00 -03:00
# More consistent handling of chapters/sections/etc.
# Lots of documentation
# Many more options:
1998-09-14 13:03:02 -03:00
# -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
# ...
1995-08-28 00:01:00 -03:00
# Support the most recent texinfo version and take a good look at HTML 3.0
# More debugging output (customizable) and more fexible error handling
# How about icons ?
1995-03-15 07:26:05 -04:00
import os
import string
import re
1995-03-15 07:26:05 -04:00
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
2001-01-17 04:48:39 -04:00
# running text
#
# menu item (Yuck!)
miprog = re.compile('^\* ([^:]*):(:|[ \t]*([^\t,\n.]+)([^ \t\n]*))[ \t\n]*')
1995-03-15 07:26:05 -04:00
1995-08-28 00:01:00 -03:00
2001-01-17 04:48:39 -04:00
class HTMLNode:
"""Some of the parser's functionality is separated into this class.
1995-08-28 00:01:00 -03:00
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):
1998-09-14 13:03:02 -03:00
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):
1998-09-14 13:03:02 -03:00
map(self.lines.append, lines)
1995-08-28 00:01:00 -03:00
def flush(self):
1998-09-14 13:03:02 -03:00
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):
1998-09-14 13:03:02 -03:00
if nodename:
if string.lower(nodename) == '(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')
1995-08-28 00:01:00 -03:00
def finalize(self):
1998-09-14 13:03:02 -03:00
length = len(self.lines)
self.text = string.joinfields(self.lines, '')
self.lines = []
self.open_links()
self.output_links()
self.close_links()
links = string.joinfields(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):
1998-09-14 13:03:02 -03:00
self.write('<HR>\n')
def close_links(self):
1998-09-14 13:03:02 -03:00
self.write('<HR>\n')
def output_links(self):
1998-09-14 13:03:02 -03:00
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):
1998-09-14 13:03:02 -03:00
self.write('<DIV CLASS=Navigation>\n <HR>\n')
def close_links(self):
1998-09-14 13:03:02 -03:00
self.write(' <HR>\n</DIV>\n')
1995-08-28 00:01:00 -03:00
1995-03-15 07:26:05 -04:00
class TexinfoParser:
COPYRIGHT_SYMBOL = "&copy;"
FN_ID_PATTERN = "(%(id)s)"
FN_SOURCE_PATTERN = '<A NAME=footnoteref%(id)s' \
1998-09-14 13:03:02 -03:00
' HREF="#footnotetext%(id)s">' \
+ FN_ID_PATTERN + '</A>'
FN_TARGET_PATTERN = '<A NAME=footnotetext%(id)s' \
1998-09-14 13:03:02 -03:00
' 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' \
1998-09-14 13:03:02 -03:00
'<STRONG><EM>Footnotes</EM></STRONG>\n<P>'
Node = HTMLNode
# Initialize an instance
def __init__(self):
1998-09-14 13:03:02 -03:00
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.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 (output) directory name
def setdirname(self, dirname):
1998-09-14 13:03:02 -03:00
self.dirname = dirname
# Set include directory name
def setincludedir(self, includedir):
1998-09-14 13:03:02 -03:00
self.includedir = includedir
# Parse the contents of an entire file
def parse(self, fp):
1998-09-14 13:03:02 -03:00
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 '+`MAGIC`
self.parserest(fp, lineno)
# Parse the contents of a file, not expecting a MAGIC header
def parserest(self, fp, initial_lineno):
1998-09-14 13:03:02 -03:00
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)
1998-09-14 13:03:02 -03:00
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):
1998-09-14 13:03:02 -03:00
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):
1998-09-14 13:03:02 -03:00
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):
1998-09-14 13:03:02 -03:00
try:
text = string.joinfields(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):
1998-09-14 13:03:02 -03:00
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):
1998-09-14 13:03:02 -03:00
if self.debugging > 1:
print self.skip, self.stack,
if accu: print accu[0][:30],
if accu[0][30:] or accu[1:]: print '...',
print
if self.stack and self.stack[-1] == 'menu':
# XXX should be done differently
for line in accu:
mo = miprog.match(line)
if not mo:
1998-09-14 13:03:02 -03:00
line = string.strip(line) + '\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)
1998-09-14 13:03:02 -03:00
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.expand(line[end:])
else:
text = string.joinfields(accu, '')
self.expand(text)
1995-03-15 07:26:05 -04:00
# Write a string, expanding embedded @-commands
def expand(self, text):
1998-09-14 13:03:02 -03:00
stack = []
i = 0
n = len(text)
while i < n:
start = i
mo = spprog.search(text, i)
if mo:
i = mo.start()
else:
1998-09-14 13:03:02 -03:00
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('&lt;')
continue
if c == '>':
self.write('&gt;')
continue
if c == '&':
self.write('&amp;')
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 '+`c`
start = i
while i < n and text[i] in string.ascii_letters: i = i+1
1998-09-14 13:03:02 -03:00
if i == start:
# @ plus non-letter: literal next character
i = i+1
c = text[start:i]
if c == ':':
# `@:' means no extra space after
# preceding `.', `?', `!' or `:'
pass
else:
# `@.' means a sentence-ending period;
# `@@', `@{', `@}' quote `@', `{', `}'
self.write(c)
continue
cmd = text[start:i]
if i < n and text[i] == '{':
i = i+1
stack.append(cmd)
try:
method = getattr(self, 'open_' + cmd)
except AttributeError:
self.unknown_open(cmd)
continue
method()
continue
try:
method = getattr(self, 'handle_' + cmd)
except AttributeError:
self.unknown_handle(cmd)
continue
method()
if stack:
print '*** Stack not empty at para:', stack
# --- Handle unknown embedded @-commands ---
def unknown_open(self, cmd):
1998-09-14 13:03:02 -03:00
print '*** No open func for @' + cmd + '{...}'
cmd = cmd + '{'
self.write('@', cmd)
if not self.unknown.has_key(cmd):
self.unknown[cmd] = 1
else:
self.unknown[cmd] = self.unknown[cmd] + 1
def unknown_close(self, cmd):
1998-09-14 13:03:02 -03:00
print '*** No close func for @' + cmd + '{...}'
cmd = '}' + cmd
self.write('}')
if not self.unknown.has_key(cmd):
self.unknown[cmd] = 1
else:
self.unknown[cmd] = self.unknown[cmd] + 1
1995-03-15 07:26:05 -04:00
def unknown_handle(self, cmd):
1998-09-14 13:03:02 -03:00
print '*** No handler for @' + cmd
self.write('@', cmd)
if not self.unknown.has_key(cmd):
self.unknown[cmd] = 1
else:
self.unknown[cmd] = self.unknown[cmd] + 1
# XXX The following sections should be ordered as the texinfo docs
# --- Embedded @-commands without {} argument list --
def handle_noindent(self): pass
def handle_refill(self): pass
# --- Include file handling ---
def do_include(self, args):
1998-09-14 13:03:02 -03:00
file = args
file = os.path.join(self.includedir, file)
try:
fp = open(file, 'r')
except IOError, msg:
print '*** Can\'t open include file', `file`
return
if self.debugging:
print '--> file', `file`
save_done = self.done
save_skip = self.skip
save_stack = self.stack
self.includedepth = self.includedepth + 1
self.parserest(fp, 0)
self.includedepth = self.includedepth - 1
fp.close()
self.done = save_done
self.skip = save_skip
self.stack = save_stack
if self.debugging:
print '<-- file', `file`
# --- Special Insertions ---
def open_dmn(self): pass
def close_dmn(self): pass
def open_dots(self): self.write('...')
def close_dots(self): pass
def open_bullet(self): pass
def close_bullet(self): pass
def open_TeX(self): self.write('TeX')
def close_TeX(self): pass
def handle_copyright(self): self.write(self.COPYRIGHT_SYMBOL)
def open_copyright(self): self.write(self.COPYRIGHT_SYMBOL)
def close_copyright(self): pass
1995-03-15 07:26:05 -04:00
def open_minus(self): self.write('-')
def close_minus(self): pass
1995-03-15 07:26:05 -04:00
# --- Special Glyphs for Examples ---
def open_result(self): self.write('=&gt;')
def close_result(self): pass
def open_expansion(self): self.write('==&gt;')
def close_expansion(self): pass
def open_print(self): self.write('-|')
def close_print(self): pass
def open_error(self): self.write('error--&gt;')
def close_error(self): pass
def open_equiv(self): self.write('==')
def close_equiv(self): pass
def open_point(self): self.write('-!-')
def close_point(self): pass
# --- Cross References ---
def open_pxref(self):
1998-09-14 13:03:02 -03:00
self.write('see ')
self.startsaving()
def close_pxref(self):
1998-09-14 13:03:02 -03:00
self.makeref()
def open_xref(self):
1998-09-14 13:03:02 -03:00
self.write('See ')
self.startsaving()
def close_xref(self):
1998-09-14 13:03:02 -03:00
self.makeref()
def open_ref(self):
1998-09-14 13:03:02 -03:00
self.startsaving()
def close_ref(self):
1998-09-14 13:03:02 -03:00
self.makeref()
def open_inforef(self):
1998-09-14 13:03:02 -03:00
self.write('See info file ')
self.startsaving()
def close_inforef(self):
1998-09-14 13:03:02 -03:00
text = self.collectsavings()
args = string.splitfields(text, ',')
n = len(args)
for i in range(n):
args[i] = string.strip(args[i])
while len(args) < 3: args.append('')
node = args[0]
file = args[2]
self.write('`', file, '\', node `', node, '\'')
def makeref(self):
1998-09-14 13:03:02 -03:00
text = self.collectsavings()
args = string.splitfields(text, ',')
n = len(args)
for i in range(n):
args[i] = string.strip(args[i])
while len(args) < 5: args.append('')
nodename = label = args[0]
if args[2]: label = args[2]
file = args[3]
title = args[4]
href = makefile(nodename)
if file:
href = '../' + file + '/' + href
self.write('<A HREF="', href, '">', label, '</A>')
# --- Marking Words and Phrases ---
# --- Other @xxx{...} commands ---
def open_(self): pass # Used by {text enclosed in braces}
def close_(self): pass
open_asis = open_
close_asis = close_
def open_cite(self): self.write('<CITE>')
def close_cite(self): self.write('</CITE>')
def open_code(self): self.write('<CODE>')
def close_code(self): self.write('</CODE>')
def open_t(self): self.write('<TT>')
def close_t(self): self.write('</TT>')
def open_dfn(self): self.write('<DFN>')
def close_dfn(self): self.write('</DFN>')
def open_emph(self): self.write('<EM>')
def close_emph(self): self.write('</EM>')
def open_i(self): self.write('<I>')
def close_i(self): self.write('</I>')
def open_footnote(self):
1998-09-14 13:03:02 -03:00
# if self.savetext <> None:
# print '*** Recursive footnote -- expect weirdness'
id = len(self.footnotes) + 1
self.write(self.FN_SOURCE_PATTERN % {'id': `id`})
self.startsaving()
def close_footnote(self):
1998-09-14 13:03:02 -03:00
id = len(self.footnotes) + 1
1998-10-08 12:24:48 -03:00
self.footnotes.append((id, self.collectsavings()))
def writefootnotes(self):
1998-09-14 13:03:02 -03:00
self.write(self.FN_HEADER)
for id, text in self.footnotes:
self.write(self.FN_TARGET_PATTERN
% {'id': `id`, 'text': text})
self.footnotes = []
def open_file(self): self.write('<CODE>')
def close_file(self): self.write('</CODE>')
def open_kbd(self): self.write('<KBD>')
def close_kbd(self): self.write('</KBD>')
def open_key(self): self.write('<KEY>')
def close_key(self): self.write('</KEY>')
def open_r(self): self.write('<R>')
def close_r(self): self.write('</R>')
def open_samp(self): self.write('`<SAMP>')
def close_samp(self): self.write('</SAMP>\'')
def open_sc(self): self.write('<SMALLCAPS>')
def close_sc(self): self.write('</SMALLCAPS>')
def open_strong(self): self.write('<STRONG>')
def close_strong(self): self.write('</STRONG>')
def open_b(self): self.write('<B>')
def close_b(self): self.write('</B>')
def open_var(self): self.write('<VAR>')
def close_var(self): self.write('</VAR>')
def open_w(self): self.write('<NOBREAK>')
def close_w(self): self.write('</NOBREAK>')
def open_url(self): self.startsaving()
def close_url(self):
text = self.collectsavings()
self.write('<A HREF="', text, '">', text, '</A>')
def open_email(self): self.startsaving()
def close_email(self):
text = self.collectsavings()
self.write('<A HREF="mailto:', text, '">', text, '</A>')
open_titlefont = open_
close_titlefont = close_
def open_small(self): pass
def close_small(self): pass
def command(self, line, mo):
a, b = mo.span(1)
1998-09-14 13:03:02 -03:00
cmd = line[a:b]
args = string.strip(line[b:])
if self.debugging > 1:
print self.skip, self.stack, '@' + cmd, args
try:
func = getattr(self, 'do_' + cmd)
except AttributeError:
try:
func = getattr(self, 'bgn_' + cmd)
except AttributeError:
# don't complain if we are skipping anyway
if not self.skip:
self.unknown_cmd(cmd, args)
return
self.stack.append(cmd)
func(args)
return
if not self.skip or cmd == 'end':
func(args)
def unknown_cmd(self, cmd, args):
1998-09-14 13:03:02 -03:00
print '*** unknown', '@' + cmd, args
if not self.unknown.has_key(cmd):
self.unknown[cmd] = 1
else:
self.unknown[cmd] = self.unknown[cmd] + 1
1995-03-15 07:26:05 -04:00
def do_end(self, args):
1998-09-14 13:03:02 -03:00
words = string.split(args)
if not words:
print '*** @end w/o args'
else:
cmd = words[0]
if not self.stack or self.stack[-1] <> cmd:
print '*** @end', cmd, 'unexpected'
else:
del self.stack[-1]
try:
func = getattr(self, 'end_' + cmd)
except AttributeError:
self.unknown_end(cmd)
return
func()
def unknown_end(self, cmd):
1998-09-14 13:03:02 -03:00
cmd = 'end ' + cmd
print '*** unknown', '@' + cmd
if not self.unknown.has_key(cmd):
self.unknown[cmd] = 1
else:
self.unknown[cmd] = self.unknown[cmd] + 1
1995-03-15 07:26:05 -04:00
# --- Comments ---
1995-03-15 07:26:05 -04:00
def do_comment(self, args): pass
do_c = do_comment
1995-03-15 07:26:05 -04:00
# --- Conditional processing ---
1995-03-15 07:26:05 -04:00
def bgn_ifinfo(self, args): pass
def end_ifinfo(self): pass
1995-03-15 07:26:05 -04:00
def bgn_iftex(self, args): self.skip = self.skip + 1
def end_iftex(self): self.skip = self.skip - 1
1995-03-15 07:26:05 -04:00
def bgn_ignore(self, args): self.skip = self.skip + 1
def end_ignore(self): self.skip = self.skip - 1
1995-03-15 07:26:05 -04:00
def bgn_tex(self, args): self.skip = self.skip + 1
def end_tex(self): self.skip = self.skip - 1
1995-03-15 07:26:05 -04:00
def do_set(self, args):
1998-09-14 13:03:02 -03:00
fields = string.splitfields(args, ' ')
key = fields[0]
if len(fields) == 1:
value = 1
else:
value = string.joinfields(fields[1:], ' ')
self.values[key] = value
print self.values
def do_clear(self, args):
1998-09-14 13:03:02 -03:00
self.values[args] = None
def bgn_ifset(self, args):
1998-09-14 13:03:02 -03:00
if args not in self.values.keys() \
or self.values[args] is None:
self.skip = self.skip + 1
self.stackinfo[len(self.stack)] = 1
else:
self.stackinfo[len(self.stack)] = 0
def end_ifset(self):
1998-09-14 13:03:02 -03:00
print self.stack
print self.stackinfo
if self.stackinfo[len(self.stack) + 1]:
self.skip = self.skip - 1
del self.stackinfo[len(self.stack) + 1]
def bgn_ifclear(self, args):
1998-09-14 13:03:02 -03:00
if args in self.values.keys() \
and self.values[args] is not None:
self.skip = self.skip + 1
self.stackinfo[len(self.stack)] = 1
else:
self.stackinfo[len(self.stack)] = 0
1995-03-15 07:26:05 -04:00
end_ifclear = end_ifset
1995-03-15 07:26:05 -04:00
def open_value(self):
1998-09-14 13:03:02 -03:00
self.startsaving()
1995-08-28 00:01:00 -03:00
def close_value(self):
1998-09-14 13:03:02 -03:00
key = self.collectsavings()
if key in self.values.keys():
self.write(self.values[key])
else:
print '*** Undefined value: ', key
# --- Beginning a file ---
do_finalout = do_comment
do_setchapternewpage = do_comment
do_setfilename = do_comment
def do_settitle(self, args):
1998-09-14 13:03:02 -03:00
print args
self.startsaving()
self.expand(args)
self.title = self.collectsavings()
print self.title
def do_parskip(self, args): pass
# --- Ending a file ---
def do_bye(self, args):
1998-09-14 13:03:02 -03:00
self.endnode()
self.done = 1
# --- Title page ---
def bgn_titlepage(self, args): self.skip = self.skip + 1
def end_titlepage(self): self.skip = self.skip - 1
def do_shorttitlepage(self, args): pass
def do_center(self, args):
1998-09-14 13:03:02 -03:00
# Actually not used outside title page...
self.write('<H1>')
self.expand(args)
self.write('</H1>\n')
do_title = do_center
do_subtitle = do_center
do_author = do_center
do_vskip = do_comment
do_vfill = do_comment
do_smallbook = do_comment
do_paragraphindent = do_comment
do_setchapternewpage = do_comment
do_headings = do_comment
do_footnotestyle = do_comment
do_evenheading = do_comment
do_evenfooting = do_comment
do_oddheading = do_comment
do_oddfooting = do_comment
do_everyheading = do_comment
do_everyfooting = do_comment
# --- Nodes ---
def do_node(self, args):
1998-09-14 13:03:02 -03:00
self.endnode()
self.nodelineno = 0
parts = string.splitfields(args, ',')
while len(parts) < 4: parts.append('')
for i in range(4): parts[i] = string.strip(parts[i])
self.nodelinks = parts
[name, next, prev, up] = parts[:4]
file = self.dirname + '/' + makefile(name)
if self.filenames.has_key(file):
print '*** Filename already in use: ', file
else:
if self.debugging: print '--- writing', file
self.filenames[file] = 1
# self.nodefp = open(file, 'w')
self.nodename = name
if self.cont and self.nodestack:
self.nodestack[-1].cont = self.nodename
if not self.topname: self.topname = name
title = name
if self.title: title = title + ' -- ' + self.title
self.node = self.Node(self.dirname, self.nodename, self.topname,
title, next, prev, up)
1995-08-28 00:01:00 -03:00
def link(self, label, nodename):
1998-09-14 13:03:02 -03:00
if nodename:
if string.lower(nodename) == '(dir)':
addr = '../dir.html'
else:
addr = makefile(nodename)
self.write(label, ': <A HREF="', addr, '" TYPE="',
label, '">', nodename, '</A> \n')
# --- Sectioning commands ---
def popstack(self, type):
1998-09-14 13:03:02 -03:00
if (self.node):
self.node.type = type
while self.nodestack:
if self.nodestack[-1].type > type:
self.nodestack[-1].finalize()
self.nodestack[-1].flush()
del self.nodestack[-1]
elif self.nodestack[-1].type == type:
if not self.nodestack[-1].next:
self.nodestack[-1].next = self.node.name
if not self.node.prev:
self.node.prev = self.nodestack[-1].name
self.nodestack[-1].finalize()
self.nodestack[-1].flush()
del self.nodestack[-1]
else:
if type > 1 and not self.node.up:
self.node.up = self.nodestack[-1].name
break
def do_chapter(self, args):
1998-09-14 13:03:02 -03:00
self.heading('H1', args, 0)
self.popstack(1)
def do_unnumbered(self, args):
1998-09-14 13:03:02 -03:00
self.heading('H1', args, -1)
self.popstack(1)
def do_appendix(self, args):
1998-09-14 13:03:02 -03:00
self.heading('H1', args, -1)
self.popstack(1)
def do_top(self, args):
1998-09-14 13:03:02 -03:00
self.heading('H1', args, -1)
def do_chapheading(self, args):
1998-09-14 13:03:02 -03:00
self.heading('H1', args, -1)
def do_majorheading(self, args):
1998-09-14 13:03:02 -03:00
self.heading('H1', args, -1)
def do_section(self, args):
1998-09-14 13:03:02 -03:00
self.heading('H1', args, 1)
self.popstack(2)
def do_unnumberedsec(self, args):
1998-09-14 13:03:02 -03:00
self.heading('H1', args, -1)
self.popstack(2)
def do_appendixsec(self, args):
1998-09-14 13:03:02 -03:00
self.heading('H1', args, -1)
self.popstack(2)
do_appendixsection = do_appendixsec
def do_heading(self, args):
1998-09-14 13:03:02 -03:00
self.heading('H1', args, -1)
def do_subsection(self, args):
1998-09-14 13:03:02 -03:00
self.heading('H2', args, 2)
self.popstack(3)
def do_unnumberedsubsec(self, args):
1998-09-14 13:03:02 -03:00
self.heading('H2', args, -1)
self.popstack(3)
def do_appendixsubsec(self, args):
1998-09-14 13:03:02 -03:00
self.heading('H2', args, -1)
self.popstack(3)
def do_subheading(self, args):
1998-09-14 13:03:02 -03:00
self.heading('H2', args, -1)
def do_subsubsection(self, args):
1998-09-14 13:03:02 -03:00
self.heading('H3', args, 3)
self.popstack(4)
def do_unnumberedsubsubsec(self, args):
1998-09-14 13:03:02 -03:00
self.heading('H3', args, -1)
self.popstack(4)
def do_appendixsubsubsec(self, args):
1998-09-14 13:03:02 -03:00
self.heading('H3', args, -1)
self.popstack(4)
def do_subsubheading(self, args):
1998-09-14 13:03:02 -03:00
self.heading('H3', args, -1)
def heading(self, type, args, level):
1998-09-14 13:03:02 -03:00
if level >= 0:
while len(self.numbering) <= level:
self.numbering.append(0)
del self.numbering[level+1:]
self.numbering[level] = self.numbering[level] + 1
x = ''
for i in self.numbering:
x = x + `i` + '.'
args = x + ' ' + args
1998-10-08 12:24:48 -03:00
self.contents.append((level, args, self.nodename))
1998-09-14 13:03:02 -03:00
self.write('<', type, '>')
self.expand(args)
self.write('</', type, '>\n')
if self.debugging or self.print_headers:
print '---', args
def do_contents(self, args):
1998-09-14 13:03:02 -03:00
# pass
self.listcontents('Table of Contents', 999)
def do_shortcontents(self, args):
1998-09-14 13:03:02 -03:00
pass
# self.listcontents('Short Contents', 0)
do_summarycontents = do_shortcontents
def listcontents(self, title, maxlevel):
1998-09-14 13:03:02 -03:00
self.write('<H1>', title, '</H1>\n<UL COMPACT PLAIN>\n')
prevlevels = [0]
for level, title, node in self.contents:
if level > maxlevel:
continue
if level > prevlevels[-1]:
# can only advance one level at a time
self.write(' '*prevlevels[-1], '<UL PLAIN>\n')
prevlevels.append(level)
elif level < prevlevels[-1]:
# might drop back multiple levels
while level < prevlevels[-1]:
del prevlevels[-1]
self.write(' '*prevlevels[-1],
'</UL>\n')
self.write(' '*level, '<LI> <A HREF="',
makefile(node), '">')
self.expand(title)
self.write('</A>\n')
self.write('</UL>\n' * len(prevlevels))
# --- Page lay-out ---
# These commands are only meaningful in printed text
def do_page(self, args): pass
def do_need(self, args): pass
def bgn_group(self, args): pass
def end_group(self): pass
# --- Line lay-out ---
def do_sp(self, args):
1998-09-14 13:03:02 -03:00
if self.nofill:
self.write('\n')
else:
self.write('<P>\n')
def do_hline(self, args):
1998-09-14 13:03:02 -03:00
self.write('<HR>')
# --- Function and variable definitions ---
def bgn_deffn(self, args):
1998-09-14 13:03:02 -03:00
self.write('<DL>')
self.do_deffnx(args)
def end_deffn(self):
1998-09-14 13:03:02 -03:00
self.write('</DL>\n')
def do_deffnx(self, args):
1998-09-14 13:03:02 -03:00
self.write('<DT>')
words = splitwords(args, 2)
[category, name], rest = words[:2], words[2:]
self.expand('@b{%s}' % name)
for word in rest: self.expand(' ' + makevar(word))
#self.expand(' -- ' + category)
self.write('\n<DD>')
self.index('fn', name)
def bgn_defun(self, args): self.bgn_deffn('Function ' + args)
end_defun = end_deffn
def do_defunx(self, args): self.do_deffnx('Function ' + args)
def bgn_defmac(self, args): self.bgn_deffn('Macro ' + args)
end_defmac = end_deffn
def do_defmacx(self, args): self.do_deffnx('Macro ' + args)
def bgn_defspec(self, args): self.bgn_deffn('{Special Form} ' + args)
end_defspec = end_deffn
def do_defspecx(self, args): self.do_deffnx('{Special Form} ' + args)
def bgn_defvr(self, args):
1998-09-14 13:03:02 -03:00
self.write('<DL>')
self.do_defvrx(args)
end_defvr = end_deffn
def do_defvrx(self, args):
1998-09-14 13:03:02 -03:00
self.write('<DT>')
words = splitwords(args, 2)
[category, name], rest = words[:2], words[2:]
self.expand('@code{%s}' % name)
# If there are too many arguments, show them
for word in rest: self.expand(' ' + word)
#self.expand(' -- ' + category)
self.write('\n<DD>')
self.index('vr', name)
def bgn_defvar(self, args): self.bgn_defvr('Variable ' + args)
end_defvar = end_defvr
def do_defvarx(self, args): self.do_defvrx('Variable ' + args)
def bgn_defopt(self, args): self.bgn_defvr('{User Option} ' + args)
end_defopt = end_defvr
def do_defoptx(self, args): self.do_defvrx('{User Option} ' + args)
# --- Ditto for typed languages ---
def bgn_deftypefn(self, args):
1998-09-14 13:03:02 -03:00
self.write('<DL>')
self.do_deftypefnx(args)
end_deftypefn = end_deffn
def do_deftypefnx(self, args):
1998-09-14 13:03:02 -03:00
self.write('<DT>')
words = splitwords(args, 3)
[category, datatype, name], rest = words[:3], words[3:]
self.expand('@code{%s} @b{%s}' % (datatype, name))
for word in rest: self.expand(' ' + makevar(word))
#self.expand(' -- ' + category)
self.write('\n<DD>')
self.index('fn', name)
def bgn_deftypefun(self, args): self.bgn_deftypefn('Function ' + args)
end_deftypefun = end_deftypefn
def do_deftypefunx(self, args): self.do_deftypefnx('Function ' + args)
def bgn_deftypevr(self, args):
1998-09-14 13:03:02 -03:00
self.write('<DL>')
self.do_deftypevrx(args)
end_deftypevr = end_deftypefn
def do_deftypevrx(self, args):
1998-09-14 13:03:02 -03:00
self.write('<DT>')
words = splitwords(args, 3)
[category, datatype, name], rest = words[:3], words[3:]
self.expand('@code{%s} @b{%s}' % (datatype, name))
# If there are too many arguments, show them
for word in rest: self.expand(' ' + word)
#self.expand(' -- ' + category)
self.write('\n<DD>')
self.index('fn', name)
def bgn_deftypevar(self, args):
1998-09-14 13:03:02 -03:00
self.bgn_deftypevr('Variable ' + args)
end_deftypevar = end_deftypevr
def do_deftypevarx(self, args):
1998-09-14 13:03:02 -03:00
self.do_deftypevrx('Variable ' + args)
# --- Ditto for object-oriented languages ---
def bgn_defcv(self, args):
1998-09-14 13:03:02 -03:00
self.write('<DL>')
self.do_defcvx(args)
end_defcv = end_deftypevr
def do_defcvx(self, args):
1998-09-14 13:03:02 -03:00
self.write('<DT>')
words = splitwords(args, 3)
[category, classname, name], rest = words[:3], words[3:]
self.expand('@b{%s}' % name)
# If there are too many arguments, show them
for word in rest: self.expand(' ' + word)
#self.expand(' -- %s of @code{%s}' % (category, classname))
self.write('\n<DD>')
self.index('vr', '%s @r{on %s}' % (name, classname))
def bgn_defivar(self, args):
1998-09-14 13:03:02 -03:00
self.bgn_defcv('{Instance Variable} ' + args)
end_defivar = end_defcv
def do_defivarx(self, args):
1998-09-14 13:03:02 -03:00
self.do_defcvx('{Instance Variable} ' + args)
def bgn_defop(self, args):
1998-09-14 13:03:02 -03:00
self.write('<DL>')
self.do_defopx(args)
end_defop = end_defcv
def do_defopx(self, args):
1998-09-14 13:03:02 -03:00
self.write('<DT>')
words = splitwords(args, 3)
[category, classname, name], rest = words[:3], words[3:]
self.expand('@b{%s}' % name)
for word in rest: self.expand(' ' + makevar(word))
#self.expand(' -- %s of @code{%s}' % (category, classname))
self.write('\n<DD>')
self.index('fn', '%s @r{on %s}' % (name, classname))
def bgn_defmethod(self, args):
1998-09-14 13:03:02 -03:00
self.bgn_defop('Method ' + args)
end_defmethod = end_defop
def do_defmethodx(self, args):
1998-09-14 13:03:02 -03:00
self.do_defopx('Method ' + args)
# --- Ditto for data types ---
def bgn_deftp(self, args):
1998-09-14 13:03:02 -03:00
self.write('<DL>')
self.do_deftpx(args)
end_deftp = end_defcv
def do_deftpx(self, args):
1998-09-14 13:03:02 -03:00
self.write('<DT>')
words = splitwords(args, 2)
[category, name], rest = words[:2], words[2:]
self.expand('@b{%s}' % name)
for word in rest: self.expand(' ' + word)
#self.expand(' -- ' + category)
self.write('\n<DD>')
self.index('tp', name)
# --- Making Lists and Tables
def bgn_enumerate(self, args):
1998-09-14 13:03:02 -03:00
if not args:
self.write('<OL>\n')
self.stackinfo[len(self.stack)] = '</OL>\n'
else:
self.itemnumber = args
self.write('<UL>\n')
self.stackinfo[len(self.stack)] = '</UL>\n'
def end_enumerate(self):
1998-09-14 13:03:02 -03:00
self.itemnumber = None
self.write(self.stackinfo[len(self.stack) + 1])
del self.stackinfo[len(self.stack) + 1]
def bgn_itemize(self, args):
1998-09-14 13:03:02 -03:00
self.itemarg = args
self.write('<UL>\n')
def end_itemize(self):
1998-09-14 13:03:02 -03:00
self.itemarg = None
self.write('</UL>\n')
def bgn_table(self, args):
1998-09-14 13:03:02 -03:00
self.itemarg = args
self.write('<DL>\n')
def end_table(self):
1998-09-14 13:03:02 -03:00
self.itemarg = None
self.write('</DL>\n')
def bgn_ftable(self, args):
1998-09-14 13:03:02 -03:00
self.itemindex = 'fn'
self.bgn_table(args)
def end_ftable(self):
1998-09-14 13:03:02 -03:00
self.itemindex = None
self.end_table()
def do_item(self, args):
1998-09-14 13:03:02 -03:00
if self.itemindex: self.index(self.itemindex, args)
if self.itemarg:
if self.itemarg[0] == '@' and self.itemarg[1:2] and \
self.itemarg[1] in string.ascii_letters:
1998-09-14 13:03:02 -03:00
args = self.itemarg + '{' + args + '}'
else:
# some other character, e.g. '-'
args = self.itemarg + ' ' + args
if self.itemnumber <> None:
args = self.itemnumber + '. ' + args
self.itemnumber = increment(self.itemnumber)
if self.stack and self.stack[-1] == 'table':
self.write('<DT>')
self.expand(args)
self.write('\n<DD>')
else:
self.write('<LI>')
self.expand(args)
self.write(' ')
do_itemx = do_item # XXX Should suppress leading blank line
# --- Enumerations, displays, quotations ---
# XXX Most of these should increase the indentation somehow
def bgn_quotation(self, args): self.write('<BLOCKQUOTE>')
def end_quotation(self): self.write('</BLOCKQUOTE>\n')
def bgn_example(self, args):
1998-09-14 13:03:02 -03:00
self.nofill = self.nofill + 1
self.write('<PRE>')
def end_example(self):
1998-09-14 13:03:02 -03:00
self.write('</PRE>\n')
self.nofill = self.nofill - 1
bgn_lisp = bgn_example # Synonym when contents are executable lisp code
end_lisp = end_example
bgn_smallexample = bgn_example # XXX Should use smaller font
end_smallexample = end_example
bgn_smalllisp = bgn_lisp # Ditto
end_smalllisp = end_lisp
bgn_display = bgn_example
end_display = end_example
bgn_format = bgn_display
end_format = end_display
def do_exdent(self, args): self.expand(args + '\n')
# XXX Should really mess with indentation
def bgn_flushleft(self, args):
1998-09-14 13:03:02 -03:00
self.nofill = self.nofill + 1
self.write('<PRE>\n')
def end_flushleft(self):
1998-09-14 13:03:02 -03:00
self.write('</PRE>\n')
self.nofill = self.nofill - 1
def bgn_flushright(self, args):
1998-09-14 13:03:02 -03:00
self.nofill = self.nofill + 1
self.write('<ADDRESS COMPACT>\n')
def end_flushright(self):
1998-09-14 13:03:02 -03:00
self.write('</ADDRESS>\n')
self.nofill = self.nofill - 1
def bgn_menu(self, args):
1998-09-14 13:03:02 -03:00
self.write('<DIR>\n')
self.write(' <STRONG><EM>Menu</EM></STRONG><P>\n')
def end_menu(self):
1998-09-14 13:03:02 -03:00
self.write('</DIR>\n')
def bgn_cartouche(self, args): pass
def end_cartouche(self): pass
# --- Indices ---
def resetindex(self):
1998-09-14 13:03:02 -03:00
self.noncodeindices = ['cp']
self.indextitle = {}
self.indextitle['cp'] = 'Concept'
self.indextitle['fn'] = 'Function'
self.indextitle['ky'] = 'Keyword'
self.indextitle['pg'] = 'Program'
self.indextitle['tp'] = 'Type'
self.indextitle['vr'] = 'Variable'
#
self.whichindex = {}
for name in self.indextitle.keys():
self.whichindex[name] = []
def user_index(self, name, args):
1998-09-14 13:03:02 -03:00
if self.whichindex.has_key(name):
self.index(name, args)
else:
print '*** No index named', `name`
def do_cindex(self, args): self.index('cp', args)
def do_findex(self, args): self.index('fn', args)
def do_kindex(self, args): self.index('ky', args)
def do_pindex(self, args): self.index('pg', args)
def do_tindex(self, args): self.index('tp', args)
def do_vindex(self, args): self.index('vr', args)
def index(self, name, args):
1998-10-08 12:24:48 -03:00
self.whichindex[name].append((args, self.nodename))
def do_synindex(self, args):
1998-09-14 13:03:02 -03:00
words = string.split(args)
if len(words) <> 2:
print '*** bad @synindex', args
return
[old, new] = words
if not self.whichindex.has_key(old) or \
not self.whichindex.has_key(new):
print '*** bad key(s) in @synindex', args
return
if old <> new and \
self.whichindex[old] is not self.whichindex[new]:
inew = self.whichindex[new]
inew[len(inew):] = self.whichindex[old]
self.whichindex[old] = inew
do_syncodeindex = do_synindex # XXX Should use code font
def do_printindex(self, args):
1998-09-14 13:03:02 -03:00
words = string.split(args)
for name in words:
if self.whichindex.has_key(name):
self.prindex(name)
else:
print '*** No index named', `name`
def prindex(self, name):
1998-09-14 13:03:02 -03:00
iscodeindex = (name not in self.noncodeindices)
index = self.whichindex[name]
if not index: return
if self.debugging:
print '--- Generating', self.indextitle[name], 'index'
# The node already provides a title
index1 = []
junkprog = re.compile('^(@[a-z]+)?{')
1998-09-14 13:03:02 -03:00
for key, node in index:
sortkey = string.lower(key)
# Remove leading `@cmd{' from sort key
# -- don't bother about the matching `}'
oldsortkey = sortkey
while 1:
mo = junkprog.match(sortkey)
if not mo:
break
i = mo.end()
1998-09-14 13:03:02 -03:00
sortkey = sortkey[i:]
1998-10-08 12:24:48 -03:00
index1.append((sortkey, key, node))
1998-09-14 13:03:02 -03:00
del index[:]
index1.sort()
self.write('<DL COMPACT>\n')
prevkey = prevnode = None
for sortkey, key, node in index1:
if (key, node) == (prevkey, prevnode):
continue
if self.debugging > 1: print key, ':', node
self.write('<DT>')
if iscodeindex: key = '@code{' + key + '}'
if key != prevkey:
self.expand(key)
self.write('\n<DD><A HREF="%s">%s</A>\n' % (makefile(node), node))
prevkey, prevnode = key, node
self.write('</DL>\n')
# --- Final error reports ---
def report(self):
1998-09-14 13:03:02 -03:00
if self.unknown:
print '--- Unrecognized commands ---'
cmds = self.unknown.keys()
cmds.sort()
for cmd in cmds:
print string.ljust(cmd, 20), self.unknown[cmd]
1995-03-15 07:26:05 -04:00
class TexinfoParserHTML3(TexinfoParser):
COPYRIGHT_SYMBOL = "&copy;"
FN_ID_PATTERN = "[%(id)s]"
FN_SOURCE_PATTERN = '<A ID=footnoteref%(id)s ' \
1998-09-14 13:03:02 -03:00
'HREF="#footnotetext%(id)s">' + FN_ID_PATTERN + '</A>'
FN_TARGET_PATTERN = '<FN ID=footnotetext%(id)s>\n' \
1998-09-14 13:03:02 -03:00
'<P><A HREF="#footnoteref%(id)s">' + FN_ID_PATTERN \
+ '</A>\n%(text)s</P></FN>\n'
FN_HEADER = '<DIV CLASS=footnotes>\n <HR NOSHADE WIDTH=200>\n' \
1998-09-14 13:03:02 -03:00
' <STRONG><EM>Footnotes</EM></STRONG>\n <P>\n'
Node = HTML3Node
def bgn_quotation(self, args): self.write('<BQ>')
def end_quotation(self): self.write('</BQ>\n')
def bgn_example(self, args):
1998-09-14 13:03:02 -03:00
# this use of <CODE> would not be legal in HTML 2.0,
# but is in more recent DTDs.
self.nofill = self.nofill + 1
self.write('<PRE CLASS=example><CODE>')
def end_example(self):
1998-09-14 13:03:02 -03:00
self.write("</CODE></PRE>\n")
self.nofill = self.nofill - 1
def bgn_flushleft(self, args):
1998-09-14 13:03:02 -03:00
self.nofill = self.nofill + 1
self.write('<PRE CLASS=flushleft>\n')
def bgn_flushright(self, args):
1998-09-14 13:03:02 -03:00
self.nofill = self.nofill + 1
self.write('<DIV ALIGN=right CLASS=flushright><ADDRESS COMPACT>\n')
def end_flushright(self):
1998-09-14 13:03:02 -03:00
self.write('</ADDRESS></DIV>\n')
self.nofill = self.nofill - 1
def bgn_menu(self, args):
1998-09-14 13:03:02 -03:00
self.write('<UL PLAIN CLASS=menu>\n')
self.write(' <LH>Menu</LH>\n')
def end_menu(self):
1998-09-14 13:03:02 -03:00
self.write('</UL>\n')
1995-03-15 07:26:05 -04:00
# Put @var{} around alphabetic substrings
def makevar(str):
return '@var{'+str+'}'
1995-03-15 07:26:05 -04:00
# Split a string in "words" according to findwordend
def splitwords(str, minlength):
words = []
i = 0
n = len(str)
while i < n:
1998-09-14 13:03:02 -03:00
while i < n and str[i] in ' \t\n': i = i+1
if i >= n: break
start = i
i = findwordend(str, i, n)
words.append(str[start:i])
while len(words) < minlength: words.append('')
return words
1995-03-15 07:26:05 -04:00
# Find the end of a "word", matching braces and interpreting @@ @{ @}
fwprog = re.compile('[@{} ]')
1995-03-15 07:26:05 -04:00
def findwordend(str, i, n):
level = 0
while i < n:
mo = fwprog.search(str, i)
if not mo:
break
i = mo.start()
1998-09-14 13:03:02 -03:00
c = str[i]; i = i+1
if c == '@': i = i+1 # Next character is not special
elif c == '{': level = level+1
elif c == '}': level = level-1
elif c == ' ' and level <= 0: return i-1
return n
1995-03-15 07:26:05 -04:00
# Convert a node name into a file name
def makefile(nodename):
return fixfunnychars(nodename) + '.html'
1995-03-15 07:26:05 -04:00
# Characters that are perfectly safe in filenames and hyperlinks
goodchars = string.ascii_letters + string.digits + '!@-=+.'
1995-03-15 07:26:05 -04:00
1995-08-28 00:01:00 -03:00
# Replace characters that aren't perfectly safe by dashes
# Underscores are bad since Cern HTTPD treats them as delimiters for
# encoding times, so you get mismatches if you compress your files:
# a.html.gz will map to a_b.html.gz
1995-03-15 07:26:05 -04:00
def fixfunnychars(addr):
i = 0
while i < len(addr):
1998-09-14 13:03:02 -03:00
c = addr[i]
if c not in goodchars:
c = '-'
addr = addr[:i] + c + addr[i+1:]
i = i + len(c)
return addr
1995-03-15 07:26:05 -04:00
# Increment a string used as an enumeration
def increment(s):
if not s:
1998-09-14 13:03:02 -03:00
return '1'
for sequence in string.digits, string.lowercase, string.uppercase:
1998-09-14 13:03:02 -03:00
lastc = s[-1]
if lastc in sequence:
i = string.index(sequence, lastc) + 1
if i >= len(sequence):
if len(s) == 1:
s = sequence[0]*2
if s == '00':
s = '10'
else:
s = increment(s[:-1]) + sequence[0]
else:
s = s[:-1] + sequence[i]
return s
return s # Don't increment
1995-03-15 07:26:05 -04:00
def test():
import sys
debugging = 0
print_headers = 0
cont = 0
html3 = 0
2001-01-17 04:48:39 -04:00
while sys.argv[1:2] == ['-d']:
1998-09-14 13:03:02 -03:00
debugging = debugging + 1
del sys.argv[1:2]
if sys.argv[1] == '-p':
1998-09-14 13:03:02 -03:00
print_headers = 1
del sys.argv[1]
if sys.argv[1] == '-c':
1998-09-14 13:03:02 -03:00
cont = 1
del sys.argv[1]
if sys.argv[1] == '-3':
1998-09-14 13:03:02 -03:00
html3 = 1
del sys.argv[1]
if len(sys.argv) <> 3:
1998-09-14 13:03:02 -03:00
print 'usage: texi2html [-d [-d]] [-p] [-c] inputfile outputdirectory'
sys.exit(2)
if html3:
1998-09-14 13:03:02 -03:00
parser = TexinfoParserHTML3()
else:
1998-09-14 13:03:02 -03:00
parser = TexinfoParser()
parser.cont = cont
parser.debugging = debugging
parser.print_headers = print_headers
file = sys.argv[1]
parser.setdirname(sys.argv[2])
if file == '-':
1998-09-14 13:03:02 -03:00
fp = sys.stdin
else:
1998-09-14 13:03:02 -03:00
parser.setincludedir(os.path.dirname(file))
try:
fp = open(file, 'r')
except IOError, msg:
print file, ':', msg
sys.exit(1)
parser.parse(fp)
fp.close()
parser.report()
if __name__ == "__main__":
test()