#!/usr/bin/env python
import md5
import sgmllib
def escape(data, escape_quote = False):
data = data.replace("&", "&")
data = data.replace("<", "<")
if escape_quote:
data = data.replace('"', """)
return data
class Parser(sgmllib.SGMLParser):
from htmlentitydefs import entitydefs
def __init__(self, fp, verbose = False):
sgmllib.SGMLParser.__init__(self, verbose)
self.fp = fp
def reset(self):
sgmllib.SGMLParser.reset(self)
self.hashes = md5.new(), md5.new()
self.passthrough = False
self.row = None
def feed(self, data):
sgmllib.SGMLParser.feed(self, data)
self.hashes[0].update(data)
def write(self, data):
self.fp.write(data)
self.hashes[1].update(data)
def digests(self):
return [hash.hexdigest() for hash in self.hashes]
# handle passthrough in generic overrides
def handle_starttag(self, tag, method, attrs):
sgmllib.SGMLParser.handle_starttag(self, tag, method, attrs)
if self.passthrough:
self.__write_tag(tag, attrs)
def unknown_starttag(self, tag, attrs):
sgmllib.SGMLParser.unknown_starttag(self, tag, attrs)
if self.passthrough:
self.__write_tag(tag, attrs)
def handle_endtag(self, tag, method):
if self.passthrough:
self.__write_tag("/" + tag)
sgmllib.SGMLParser.handle_endtag(self, tag, method)
def unknown_endtag(self, tag):
if self.passthrough:
self.__write_tag("/" + tag)
sgmllib.SGMLParser.unknown_endtag(self, tag)
def handle_data(self, data):
if self.passthrough:
self.write(data)
def __write_tag(self, tag, attrs = ()):
self.write("<%s%s>" % (tag, "".join(
[' %s="%s"' % (name, escape(value, True))
for name, value in attrs])))
# handle everything else in tag-specific overrides
def start_table(self, attrs):
for name, value in attrs:
if name == "summary":
if value == "methods and the premissions they require":
self.passthrough = True
self.row = 0
break
if self.passthrough:
self.write("\n \n ")
def end_table(self):
if self.passthrough:
self.write("\n \n\n")
self.passthrough = False
def start_tr(self, attrs):
if self.passthrough:
if self.row == 29:
self.passthrough = False
self.row_tagged = False
elif self.row == 29:
self.passthrough = True
def end_tr(self):
if self.passthrough:
self.row += 1
def start_th(self, attrs):
if self.passthrough:
if not self.row_tagged:
self.write("| ID | \n ")
self.row_tagged = True
def start_td(self, attrs):
if self.passthrough:
if not self.row_tagged:
self.write("se%03d | \n " % self.row)
self.row_tagged = True
if __name__ == "__main__":
import os
import sys
import urllib
version = "1.4.2"
src = "http://java.sun.com/j2se/" + version \
+ "/docs/guide/security/permissions.html"
dst = "throwpoints-%s.html" % version
if os.path.exists(dst):
print "%s: file exists" % dst
sys.exit(1)
parser = Parser(open(dst, "w"))
parser.feed(urllib.urlopen(src).read())
parser.close()
digests = parser.digests()
if digests[1] == "3c40052647c417dead97068a32f51911":
status = "PASS"
elif digests[0] == "c4b9248859682e65ad71788acfc03b78":
status = "FAIL (processing)"
else:
status = "FAIL (input = %s)" % digests[0]
print "status:", status