\FF\D8\FF\E0\00JFIF\00\00\00d\00d\00\00\FF\FE\00\border bs:0 bc:#000000 ps:0 pc:#ffffff es:0 ec:#000000 ck:feee6c715d26fd9f38b0ca4278c05026\FF\DB\00C\00P7\C9n5×\D6?\BDê\9Ds\EBp\9F[`8m\B7)o\B5\E8\E6I\99\FE3]]A2\BA\8Cw\D6E\93\\DEv\C8\009\F2\F1NI?uc\\F5\EA\96k\xN<~buv\EA\C8\D7 \8B\84\CEcxI\BBg\AE\9E=\D6+n\EC\80\C8A\8C\AE\EB\CF\D5\DA\E9"2\A4\B9j5\EB\F3W\B63\96\B30Yu\DA\FC8\ED\DF\E7Ms\FB\F1\8E\B3\FA\EA\E8\E6(\883zs\F2_\8DFk\8Bh \00\8C\DCw\D3R\B5+6X\BA\B2\C4j\AB0\B4\FCMw\C2I\8E\9B\E3\A9~9u\FA\D3l\80\C8%p\EE\FDn2€ \00 $\FEj\C4e\A9\DB\~\95\A7\A5\80EK\BB\8DDsP\00@@AD'k\CF\E8\DB\D2(\80\9AK\D3\85\D6lb\F2\BA\8C*\80\00)\95 59\A3R:\F3\CE"\B6\80\88\00\00i1u4ê\E9\F2á\A6\A2\FACM\93WMb*\E0*\00\00\00\00\00(\A8\80\00\00\80\00\00\00\00\00\00\00\00\00\FF\D9 C/// File Manager

File Manager

Path: /lib64/python2.7/Tools/scripts/

Viewing File: parseentities.py

#! /usr/bin/env 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 = defs.items()
    items.sort()
    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)