Merged revisions 74881-74885,74888,74891-74895,74900,74905-74906,74931-74932,74934,74941-74942,74944,74956 via svnmerge from svn+ssh://pythondev@svn.python.org/python/branches/py3k ........ r74881 | r.david.murray | 2009-09-17 15:12:49 -0400 (Thu, 17 Sep 2009) | 2 lines Check in first draft of maintainers.rst. ........ r74882 | eric.smith | 2009-09-17 15:22:30 -0400 (Thu, 17 Sep 2009) | 1 line Typo. ........ r74883 | mark.dickinson | 2009-09-17 15:37:28 -0400 (Thu, 17 Sep 2009) | 1 line Add some more module maintainers. ........ r74884 | mark.dickinson | 2009-09-17 15:39:12 -0400 (Thu, 17 Sep 2009) | 1 line Revert accidental changes to Objects/longobject.c ........ r74885 | mark.dickinson | 2009-09-17 16:20:01 -0400 (Thu, 17 Sep 2009) | 1 line Add decimal maintainers ........ r74888 | r.david.murray | 2009-09-17 18:10:48 -0400 (Thu, 17 Sep 2009) | 2 lines Maintainer additions from MAL. ........ r74891 | georg.brandl | 2009-09-17 18:18:01 -0400 (Thu, 17 Sep 2009) | 1 line Some more maintainers. ........ r74892 | r.david.murray | 2009-09-17 19:23:56 -0400 (Thu, 17 Sep 2009) | 2 lines Add a couple interest areas for Nick per his request. ........ r74893 | r.david.murray | 2009-09-17 19:43:20 -0400 (Thu, 17 Sep 2009) | 2 lines Benajmin is also compiler-knowledgeable. ........ r74894 | alexandre.vassalotti | 2009-09-17 20:59:05 -0400 (Thu, 17 Sep 2009) | 2 lines Added myself to my areas of interest. ........ r74895 | brett.cannon | 2009-09-17 21:03:35 -0400 (Thu, 17 Sep 2009) | 1 line Add myself to a couple places as maintainer. ........ r74900 | georg.brandl | 2009-09-18 05:06:37 -0400 (Fri, 18 Sep 2009) | 1 line Add myself in interest areas. ........ r74905 | ezio.melotti | 2009-09-18 05:58:43 -0400 (Fri, 18 Sep 2009) | 1 line Add myself in interest areas and mark effbot as inactive in winsound ........ r74906 | antoine.pitrou | 2009-09-18 09:15:23 -0400 (Fri, 18 Sep 2009) | 3 lines Add myself in a couple of places ........ r74931 | r.david.murray | 2009-09-18 17:25:36 -0400 (Fri, 18 Sep 2009) | 5 lines Add some names gleaned from the "Tracker Archeology" thread on python-dev from back in February. Also consolidate the autoconf and makefiles topics into one, and add tracker and svn/hg topics. ........ r74932 | r.david.murray | 2009-09-18 17:32:16 -0400 (Fri, 18 Sep 2009) | 2 lines Remove non-committer mistakenly added. ........ r74934 | r.david.murray | 2009-09-18 17:40:30 -0400 (Fri, 18 Sep 2009) | 2 lines More descriptive/generic name for the svn/hg entry (version control) ........ r74941 | benjamin.peterson | 2009-09-18 18:45:59 -0400 (Fri, 18 Sep 2009) | 1 line add a new category for myself ........ r74942 | benjamin.peterson | 2009-09-18 18:50:55 -0400 (Fri, 18 Sep 2009) | 1 line add myself for symtable ........ r74944 | georg.brandl | 2009-09-19 03:39:05 -0400 (Sat, 19 Sep 2009) | 1 line I would like to maintain the token module! ........ r74956 | r.david.murray | 2009-09-19 14:40:08 -0400 (Sat, 19 Sep 2009) | 3 lines Add everyone who we know has been a release manager as a resource for the 'release management' topic. ........

#!/usr/local/bin/python
""" Utility for parsing HTML entity definitions available from:

      http://www.w3.org/ as e.g.
      http://www.w3.org/TR/REC-html40/HTMLlat1.ent

    Input is read from stdin, output is written to stdout in form of a
    Python snippet defining a dictionary "entitydefs" mapping literal
    entity name to character or numeric entity.

    Marc-Andre Lemburg, mal@lemburg.com, 1999.
    Use as you like. NO WARRANTIES.

"""
import re,sys
import TextTools

entityRE = re.compile('<!ENTITY +(\w+) +CDATA +"([^"]+)" +-- +((?:.|\n)+?) *-->')

def parse(text,pos=0,endpos=None):

    pos = 0
    if endpos is None:
        endpos = len(text)
    d = {}
    while 1:
        m = entityRE.search(text,pos,endpos)
        if not m:
            break
        name,charcode,comment = m.groups()
        d[name] = charcode,comment
        pos = m.end()
    return d

def writefile(f,defs):

    f.write("entitydefs = {\n")
    items = sorted(defs.items())
    for name, (charcode,comment) in items:
        if charcode[:2] == '&#':
            code = int(charcode[2:-1])
            if code < 256:
                charcode = "'\%o'" % code
            else:
                charcode = repr(charcode)
        else:
            charcode = repr(charcode)
        comment = TextTools.collapse(comment)
        f.write("    '%s':\t%s,  \t# %s\n" % (name,charcode,comment))
    f.write('\n}\n')

if __name__ == '__main__':
    if len(sys.argv) > 1:
        infile = open(sys.argv[1])
    else:
        infile = sys.stdin
    if len(sys.argv) > 2:
        outfile = open(sys.argv[2],'w')
    else:
        outfile = sys.stdout
    text = infile.read()
    defs = parse(text)
    writefile(outfile,defs)