| Server IP : 79.136.114.73 / Your IP : 216.73.216.107 Web Server : Apache/2.4.7 (Ubuntu) PHP/5.5.9-1ubuntu4.29 OpenSSL/1.0.1f System : Linux b8009 3.13.0-170-generic #220-Ubuntu SMP Thu May 9 12:40:49 UTC 2019 x86_64 User : www-data ( 33) PHP Version : 5.5.9-1ubuntu4.29 Disable Function : pcntl_alarm,pcntl_fork,pcntl_waitpid,pcntl_wait,pcntl_wifexited,pcntl_wifstopped,pcntl_wifsignaled,pcntl_wexitstatus,pcntl_wtermsig,pcntl_wstopsig,pcntl_signal,pcntl_signal_dispatch,pcntl_get_last_error,pcntl_strerror,pcntl_sigprocmask,pcntl_sigwaitinfo,pcntl_sigtimedwait,pcntl_exec,pcntl_getpriority,pcntl_setpriority, MySQL : ON | cURL : ON | WGET : ON | Perl : ON | Python : ON | Sudo : ON | Pkexec : ON Directory : /proc/self/root/home/b8009/Python-3.6.3/Tools/scripts/ |
Upload File : |
#!/usr/bin/env python3
""" 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
entityRE = re.compile(r'<!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 = r"'\%o'" % code
else:
charcode = repr(charcode)
else:
charcode = repr(charcode)
comment = ' '.join(comment.split())
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)