diff options
| author | Tim Peters <tim.peters@gmail.com> | 2002-04-20 20:26:26 (GMT) |
|---|---|---|
| committer | Tim Peters <tim.peters@gmail.com> | 2002-04-20 20:26:26 (GMT) |
| commit | 454540774618c35374ecd0042ab689692040c425 (patch) | |
| tree | c2851970eff54e1e7ceeb9de2bbf177c4206c2de /Doc | |
| parent | 3d94942000dde4266487969eb75f27fd3d46099f (diff) | |
| download | cpython-454540774618c35374ecd0042ab689692040c425.zip cpython-454540774618c35374ecd0042ab689692040c425.tar.gz cpython-454540774618c35374ecd0042ab689692040c425.tar.bz2 | |
Stopped all warnings from the HTML Help Compiler, by generating proper
HTML (or, at least, proper in its view). The TOC file is now identical
to what the HTML compiler itself generates, except for whitespace and
a glitch identified below. The pretty-printing done by prechm.py is
pretty much destroyed for now; if you need it pretty-printed, just make
the Help Compiler save the files (it's got its own idea of pretty-
printing anyway).
Glitch: The title of Ref Man "2.1.6 Blank lines" shows up as a blank
for now. This is because the relevant entry in ref/index.html contains
nested anchors, and pychm really has no idea what to do with that. I
hacked it for now to avoid any error messages or worse insanity, and
filed a bug report against the docs.
Diffstat (limited to 'Doc')
| -rw-r--r-- | Doc/tools/prechm.py | 55 |
1 files changed, 34 insertions, 21 deletions
diff --git a/Doc/tools/prechm.py b/Doc/tools/prechm.py index 675e400..59a2d21 100644 --- a/Doc/tools/prechm.py +++ b/Doc/tools/prechm.py @@ -19,8 +19,8 @@ import sys import os from formatter import NullWriter, AbstractFormatter from htmllib import HTMLParser -import string import getopt +import cgi usage_mode = ''' Usage: make_chm.py [-c] [-k] [-p] [-v 1.5[.x]] filename @@ -56,31 +56,36 @@ Title=Python %(version)s Documentation [FILES] ''' -contents_header = ''' +contents_header = '''\ +<!DOCTYPE HTML PUBLIC "-//IETF//DTD HTML//EN"> +<HTML> +<HEAD> +<meta name="GENERATOR" content="Microsoft® HTML Help Workshop 4.1"> +<!-- Sitemap 1.0 --> +</HEAD><BODY> <OBJECT type="text/site properties"> <param name="Window Styles" value="0x801227"> <param name="ImageType" value="Folder"> </OBJECT> <UL> -<LI> <OBJECT type="text/sitemap"> - <param name="Name" value="Python %s Docs"> - <param name="Local" value="./index.html"> - </OBJECT> +<LI><OBJECT type="text/sitemap"> + <param name="Name" value="Python %s Docs"> + <param name="Local" value="./index.html"> + </OBJECT> <UL> ''' -contents_footer = ''' -</UL></UL> +contents_footer = '''\ +</UL></UL></BODY></HTML> ''' -object_sitemap = ''' - <LI> <OBJECT type="text/sitemap"> - <param name="Local" value="%s"> - <param name="Name" value="%s"> - </OBJECT> +object_sitemap = '''\ +<OBJECT type="text/sitemap"> + <param name="Name" value="%s"> + <param name="Local" value="%s"> +</OBJECT> ''' - # List of words the full text search facility shouldn't index. This # becomes file ARCH.stp. Note that this list must be pretty small! # Different versions of the MS docs claim the file has a maximum size of @@ -228,6 +233,9 @@ class HelpHtmlParser(HTMLParser): self.indent = 0 # number of tabs for pretty printing of files self.proc = False # True when actively processing, else False # (headers, footers, etc) + # XXX This shouldn't need to be a stack -- anchors shouldn't nest. + # XXX See SF bug <http://www.python.org/sf/546579>. + self.hrefstack = [] # stack of hrefs from anchor begins def begin_group(self): self.indent += 1 @@ -241,14 +249,18 @@ class HelpHtmlParser(HTMLParser): def anchor_bgn(self, href, name, type): if self.proc: self.saved_clear() - self.write('<OBJECT type="text/sitemap">\n') - self.tab('\t<param name="Local" value="%s/%s">\n' % - (self.path, href)) + self.hrefstack.append(href) def anchor_end(self): if self.proc: - self.tab('\t<param name="Name" value="%s">\n' % self.saved_get()) - self.tab('\t</OBJECT>\n') + title = cgi.escape(self.saved_get(), True) + path = self.path + '/' + self.hrefstack.pop() + # XXX See SF bug <http://www.python.org/sf/546579>. + # XXX index.html for the 2.2 language reference manual contains + # XXX nested <a></a> tags in the entry for the section on blank + # XXX lines. We want to ignore the nested part completely. + if len(self.hrefstack) == 0: + self.tab(object_sitemap % (title, path)) def start_dl(self, atr_val): self.begin_group() @@ -332,8 +344,9 @@ def do_content(library, version, output): output.write(contents_header % version) for book in library: print '\t', book.title, '-', book.firstpage - output.write(object_sitemap % (book.directory + "/" + book.firstpage, - book.title)) + path = book.directory + "/" + book.firstpage + output.write('<LI>') + output.write(object_sitemap % (book.title, path)) if book.contentpage: content(book.directory, book.contentpage, output) output.write(contents_footer) |