1 # Copyright (C) 2011 Google Inc. All rights reserved.
3 # Redistribution and use in source and binary forms, with or without
4 # modification, are permitted provided that the following conditions are
7 # * Redistributions of source code must retain the above copyright
8 # notice, this list of conditions and the following disclaimer.
9 # * Redistributions in binary form must reproduce the above
10 # copyright notice, this list of conditions and the following disclaimer
11 # in the documentation and/or other materials provided with the
14 # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
15 # "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
16 # LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
17 # A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
18 # OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
19 # SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
20 # LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
21 # DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
22 # THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
23 # (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
24 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26 """Utility module for reftests."""
29 from HTMLParser import HTMLParser
32 class ExtractReferenceLinkParser(HTMLParser):
35 HTMLParser.__init__(self)
39 def handle_starttag(self, tag, attrs):
43 if not "rel" in attrs:
45 if not "href" in attrs:
47 if attrs["rel"] == "match":
48 self.matches.append(attrs["href"])
49 if attrs["rel"] == "mismatch":
50 self.mismatches.append(attrs["href"])
53 def get_reference_link(html_string):
54 """Returns reference links in the given html_string.
57 a tuple of two URL lists, (matches, mismatches).
59 parser = ExtractReferenceLinkParser()
60 parser.feed(html_string)
63 return parser.matches, parser.mismatches