#!/usr/bin/python """ $Id: contentformat.py,v 1.9 2007/04/26 08:05:54 dom Exp $ The ContentFormatTestCase implements the validator.testcase.TestCase interface for the tests related to the following BP: * Send content in a format that is known to be supported by the device. License ------- Copyright (c) 2006 World Wide Web Consortium, (Massachusetts Institute of Technology, European Research Consortium for Informatics and Mathematics, Keio University). All Rights Reserved. This work is distributed under the W3C Software License [1] in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. [1] http://www.w3.org/Consortium/Legal/copyright-software """ from validator import testcase # small class to encapsulate data about a DTD class DTD: def __init__(self,name,idtype,id): self.name=name self.idtype=idtype self.id=id # Tests regarding the CONTENT_FORMAT_SUPPORT and CONTENT_FORMAT_PREFERRED BP class ContentFormatTestCase(testcase.LinksBasedTestCase): BpId = ["CONTENT_FORMAT_SUPPORT","CONTENT_FORMAT_PREFERRED"] def _getDoctype(self): import re if not self._content: return None # copied and adapted from # http://dev.w3.org/cvsweb/~checkout~/validator/httpd/cgi-bin/check?rev=1.458&content-type=text/plain doctype_regexp=re.compile("^(?:<\?xml[^\?]*\?>|)\s*]*>",re.UNICODE | re.S | re.M) match = doctype_regexp.search(self._content) if match and len(match.groups())==3: g = match.groups() return DTD(g[0],g[1],g[2]) else: return None def _observeLinks(self): from validator import utils from cgi import parse_header mime = None if self._headers and self._headers.has_key("content-type"): mime = parse_header(self._headers["content-type"])[0] # @@@ this should be loaded from the DDC profile # and passed as param? if not mime in ["application/xhtml+xml"]: if not mime in ["text/html","application/vnd.wap.xhtml+xml"]: self.addObservation(testcase.Observation("CF1",testcase.HeaderLocation(self.uri,"Content-Type"),{"mime":mime})) else: self.addObservation(testcase.Observation("CF7",testcase.HeaderLocation(self.uri,"Content-Type"),{"mime":mime})) # check whether we have an accepted doctype dtd = doctype = self._getDoctype() if dtd: # @@@ this should be loaded from the DDC profile if (dtd.idtype=="PUBLIC" and not dtd.id in ["-//W3C//DTD XHTML Basic 1.0//EN"]) or (dtd.idtype=="SYSTEM" and not dtd.id in ["http://www.w3.org/TR/xhtml-basic/xhtml-basic10.dtd"]): self.addObservation(testcase.Observation("CF4",testcase.Location(self.uri),{"dtd":dtd.id})) else: self.addObservation(testcase.Observation("CF5",testcase.Location(self.uri))) links = self.getLinks() for link in links: if link.nature==utils.LINK_TYPE_EMBED: # @@@ this should be loaded from the DDC profile # and passed as param? if not link.mime in ["image/jpeg","image/gif","text/css"]: self.addObservation(testcase.Observation("CF1",link.location,{"mime":link.mime})) elif link.mime in ["image/jpeg","image/gif"]: import Image, cStringIO headers,content = self._http_request(link.target) try: image = Image.open(cStringIO.StringIO(content)) image.verify() except Exception,msg: self.addObservation(testcase.Observation("CF6",link.location,{"mime":link.mime,"error":str(msg),"image":link.target})) if not "CF1" in self._observations and not "CF4" in self._observations and not "CF5" in self._observations and not "CF6" in self._observations: self.addObservation(testcase.Observation("CF3",Location(self.uri))) # ------------------------- # Unit tests for this module import unittest from validator.testcase import TestResults, Observation, Location, HeaderLocation, LineColumnLocation class Tests(unittest.TestCase): def _test(self,inp,res): a = ContentFormatTestCase() self.assertEqual(a.run(inp),res) def testGoodFormats(self): inp = "http://dev.w3.org/cvsweb/~checkout~/2006/mwbp-validator/tests/contentformat-1.xhtml?content-type=application/xhtml%2Bxml" res = TestResults( [Observation("CF3",Location(inp))] ) self._test(inp,res) def testBadFormats(self): inp = "http://dev.w3.org/cvsweb/~checkout~/2006/mwbp-validator/tests/contentformat-2.xhtml?content-type=text/html" res = TestResults( [Observation('CF7',HeaderLocation(inp,"Content-Type"),{'mime': 'text/html'}), Observation('CF1',LineColumnLocation(inp,'utf-8',11,30),{'mime': 'image/png'}), Observation('CF1',LineColumnLocation(inp,'utf-8',12,25),{'mime': 'image/svg+xml'})] ) self._test(inp,res) def testInvalidImages(self): inp = "http://dev.w3.org/cvsweb/~checkout~/2006/mwbp-validator/tests/contentformat-5.xhtml?content-type=application/xhtml%2Bxml" res = TestResults( [Observation('CF6',LineColumnLocation(inp,'utf-8',11,58),{'image': u'http://dev.w3.org/cvsweb/~checkout~/2006/mwbp-validator/tests/contentformat-5.xhtml?content-type=image%2Fgif', 'mime': 'image/gif', 'error': 'cannot identify image file'}), Observation('CF6',LineColumnLocation(inp,'utf-8',12,73),{'image': u'http://dev.w3.org/cvsweb/~checkout~/2006/mwbp-validator/tests/contentformat-5.xhtml?content-type=image%2Fgif', 'mime': 'image/gif', 'error': '@@@'}), Observation('CF6',LineColumnLocation(inp,'utf-8',13,59),{'image': u'http://dev.w3.org/cvsweb/~checkout~/2006/mwbp-validator/tests/contentformat-5.xhtml?content-type=image%2Fjpeg', 'mime': 'image/jpeg', 'error': 'cannot identify image file'})] ) self._test(inp,res) def testNoDoctype(self): inp = "http://dev.w3.org/cvsweb/~checkout~/2006/mwbp-validator/tests/contentformat-3.xhtml?content-type=application/xhtml%2Bxml" res = TestResults( [Observation('CF5',Location(inp))] ) self._test(inp,res) def testBadDoctype(self): inp = "http://dev.w3.org/cvsweb/~checkout~/2006/mwbp-validator/tests/contentformat-4.xhtml?content-type=application/xhtml%2Bxml" res = TestResults( [Observation('CF4',Location(inp),{'dtd': '-//W3C//DTD XHTML Transitional 1.0//EN'})] ) self._test(inp,res) def _test(): unittest.main() if __name__ == '__main__': _test()