def getDescription(xmlfile):
"""Extract test data
Each test case is an XML file which contains not only a test feed
but also the description of the test, i.e. the condition that we
would expect the parser to create when it parses the feed. Example:
<!--
Description: feed title
Expect: feed['title'] == u'Example feed'
-->
"""
data = open(xmlfile, 'rb').read()
if data[:4] == _l2bytes([0x4c, 0x6f, 0xa7, 0x94]):
data = feedparser._ebcdic_to_ascii(data)
elif data[:4] == _l2bytes([0x00, 0x00, 0xfe, 0xff]):
if not _utf32_available: return None, None, None, '0'
data = unicode(data, 'utf-32be').encode('utf-8')
elif data[:4] == _l2bytes([0xff, 0xfe, 0x00, 0x00]):
if not _utf32_available: return None, None, None, '0'
data = unicode(data, 'utf-32le').encode('utf-8')
elif data[:4] == _l2bytes([0x00, 0x00, 0x00, 0x3c]):
if not _utf32_available: return None, None, None, '0'
data = unicode(data, 'utf-32be').encode('utf-8')
elif data[:4] == _l2bytes([0x3c, 0x00, 0x00, 0x00]):
if not _utf32_available: return None, None, None, '0'
data = unicode(data, 'utf-32le').encode('utf-8')
elif data[:4] == _l2bytes([0x00, 0x3c, 0x00, 0x3f]):
data = unicode(data, 'utf-16be').encode('utf-8')
elif data[:4] == _l2bytes([0x3c, 0x00, 0x3f, 0x00]):
data = unicode(data, 'utf-16le').encode('utf-8')
elif (data[:2] == _l2bytes([0xfe, 0xff
])) and (data[2:4] != _l2bytes([0x00, 0x00])):
data = unicode(data[2:], 'utf-16be').encode('utf-8')
elif (data[:2] == _l2bytes([0xff, 0xfe
])) and (data[2:4] != _l2bytes([0x00, 0x00])):
data = unicode(data[2:], 'utf-16le').encode('utf-8')
elif data[:3] == _l2bytes([0xef, 0xbb, 0xbf]):
data = data[3:]
skip_results = skip_re.search(data)
if skip_results:
skipUnless = skip_results.group(1).strip()
else:
skipUnless = '1'
search_results = desc_re.search(data)
if not search_results:
raise RuntimeError, "can't parse %s" % xmlfile
description, evalString = map(string.strip, list(search_results.groups()))
description = xmlfile + ": " + unicode(description, 'utf8')
return TestCase.failUnlessEval, description, evalString, skipUnless
def getDescription(xmlfile):
"""Extract test data
Each test case is an XML file which contains not only a test feed
but also the description of the test, i.e. the condition that we
would expect the parser to create when it parses the feed. Example:
<!--
Description: feed title
Expect: feed['title'] == u'Example feed'
-->
"""
data = open(xmlfile, 'rb').read()
if data[:4] == _l2bytes([0x4c, 0x6f, 0xa7, 0x94]):
data = feedparser._ebcdic_to_ascii(data)
elif data[:4] == _l2bytes([0x00, 0x00, 0xfe, 0xff]):
if not _utf32_available: return None, None, None, '0'
data = str(data, 'utf-32be').encode('utf-8')
elif data[:4] == _l2bytes([0xff, 0xfe, 0x00, 0x00]):
if not _utf32_available: return None, None, None, '0'
data = str(data, 'utf-32le').encode('utf-8')
elif data[:4] == _l2bytes([0x00, 0x00, 0x00, 0x3c]):
if not _utf32_available: return None, None, None, '0'
data = str(data, 'utf-32be').encode('utf-8')
elif data[:4] == _l2bytes([0x3c, 0x00, 0x00, 0x00]):
if not _utf32_available: return None, None, None, '0'
data = str(data, 'utf-32le').encode('utf-8')
elif data[:4] == _l2bytes([0x00, 0x3c, 0x00, 0x3f]):
data = str(data, 'utf-16be').encode('utf-8')
elif data[:4] == _l2bytes([0x3c, 0x00, 0x3f, 0x00]):
data = str(data, 'utf-16le').encode('utf-8')
elif (data[:2] == _l2bytes([0xfe, 0xff])) and (data[2:4] != _l2bytes([0x00, 0x00])):
data = str(data[2:], 'utf-16be').encode('utf-8')
elif (data[:2] == _l2bytes([0xff, 0xfe])) and (data[2:4] != _l2bytes([0x00, 0x00])):
data = str(data[2:], 'utf-16le').encode('utf-8')
elif data[:3] == _l2bytes([0xef, 0xbb, 0xbf]):
data = data[3:]
skip_results = skip_re.search(data)
if skip_results:
skipUnless = skip_results.group(1).strip()
else:
skipUnless = '1'
search_results = desc_re.search(data)
if not search_results:
raise RuntimeError("can't parse %s" % xmlfile)
description, evalString = list(map(string.strip, list(search_results.groups())))
description = xmlfile + ": " + str(description, 'utf8')
return TestCase.failUnlessEval, description, evalString, skipUnless
def getDescription(xmlfile):
"""Extract test data
Each test case is an XML file which contains not only a test feed
but also the description of the test, i.e. the condition that we
would expect the parser to create when it parses the feed. Example:
<!--
Description: feed title
Expect: feed['title'] == u'Example feed'
-->
"""
data = open(xmlfile).read()
if data[:4] == '\x4c\x6f\xa7\x94':
data = feedparser._ebcdic_to_ascii(data)
elif data[:4] == '\x00\x00\xfe\xff':
if not _utf32_available: return None, None, None, '0'
data = unicode(data, 'utf-32be').encode('utf-8')
elif data[:4] == '\xff\xfe\x00\x00':
if not _utf32_available: return None, None, None, '0'
data = unicode(data, 'utf-32le').encode('utf-8')
elif data[:4] == '\x00\x00\x00\x3c':
if not _utf32_available: return None, None, None, '0'
data = unicode(data, 'utf-32be').encode('utf-8')
elif data[:4] == '\x3c\x00\x00\x00':
if not _utf32_available: return None, None, None, '0'
data = unicode(data, 'utf-32le').encode('utf-8')
elif data[:4] == '\x00\x3c\x00\x3f':
data = unicode(data, 'utf-16be').encode('utf-8')
elif data[:4] == '\x3c\x00\x3f\x00':
data = unicode(data, 'utf-16le').encode('utf-8')
elif (data[:2] == '\xfe\xff') and (data[2:4] != '\x00\x00'):
data = unicode(data[2:], 'utf-16be').encode('utf-8')
elif (data[:2] == '\xff\xfe') and (data[2:4] != '\x00\x00'):
data = unicode(data[2:], 'utf-16le').encode('utf-8')
elif data[:3] == '\xef\xbb\xbf':
data = data[3:]
skip_results = skip_re.search(data)
if skip_results:
skipUnless = skip_results.group(1).strip()
else:
skipUnless = '1'
search_results = desc_re.search(data)
if not search_results:
raise RuntimeError, "can't parse %s" % xmlfile
description, evalString = map(string.strip, list(search_results.groups()))
description = xmlfile + ": " + description
return TestCase.failUnlessEval, description, evalString, skipUnless