class TextParserTC(unittest.TestCase):
def setUp(self):
self.parser = TextParser()
def testTitleGuess(
self
): #XXX: complete this with PDF/PS files before commit time !!!
"""Make sure the title is the filename when we treat a text file
or no title could be found
"""
title, text, links, offset = self.parser.parseFile(
join(DATADIR, 'latin1.txt'), 'latin1.txt', 'ISO-8859-1')
self.assertEquals(title, 'latin1.txt')
self.assertEquals(normalizeText(text), "c'est l'ete")
self.assertEquals(links, [])
# Now, PS file
title, text, links, offset = self.parser.parseFile(
join(DATADIR, 'utf8.ps'), 'utf8.ps', 'UTF-8')
self.assertEquals(title, 'utf8.ps')
self.assertEquals(links, [])
# The PDF (yes, it's important to test this too)
title, text, links, offset = self.parser.parseFile(
join(DATADIR, 'utf8.pdf'), 'utf8.pdf', 'UTF-8')
self.assertEquals(title, 'utf8.pdf')
self.assertEquals(links, [])
class TextParserTC(unittest.TestCase):
def setUp(self):
self.parser = TextParser()
def testTitleGuess(self): #XXX: complete this with PDF/PS files before commit time !!!
"""Make sure the title is the filename when we treat a text file
or no title could be found
"""
title, text, links, offset = self.parser.parseFile(join(DATADIR, 'latin1.txt'), 'latin1.txt', 'ISO-8859-1')
self.assertEquals(title, 'latin1.txt')
self.assertEquals(normalizeText(text), "c'est l'ete")
self.assertEquals(links, [])
# Now, PS file
title, text, links, offset = self.parser.parseFile(join(DATADIR, 'utf8.ps'), 'utf8.ps', 'UTF-8')
self.assertEquals(title, 'utf8.ps')
self.assertEquals(links, [])
# The PDF (yes, it's important to test this too)
title, text, links, offset = self.parser.parseFile(join(DATADIR, 'utf8.pdf'), 'utf8.pdf', 'UTF-8')
self.assertEquals(title, 'utf8.pdf')
self.assertEquals(links, [])
def setUp(self):
self.parser = TextParser()
def setUp(self):
self.parser = TextParser()
def getParser(self):
if self.OUTPUT_TYPE == 'html':
return HTMLParser()
else:
return TextParser()
def getParser(self):
return TextParser()
