def testExtractTextInfo(self):
textTags = hrefliterals.extractTextInfo(
self.document, self.exclude_re, '')
self.assertEqual(textTags.keys(), ['f'])
self.assertEqual(len(textTags['f']), 11)
self.assertEqual(textTags['f'][0], hrefliterals.TextTag(
hrefliterals.TextTag.Type.WORD, 29, 34, 'words'))
self.assertEqual(textTags['f'][1], hrefliterals.TextTag(
hrefliterals.TextTag.Type.CHARACTER, 34, 35, ' '))
self.assertEqual(textTags['f'][2], hrefliterals.TextTag(
hrefliterals.TextTag.Type.CHARACTER, 35, 36, '1'))
self.assertEqual(textTags['f'][3], hrefliterals.TextTag(
hrefliterals.TextTag.Type.CHARACTER, 36, 37, ' '))
self.assertEqual(textTags['f'][4], hrefliterals.TextTag(
hrefliterals.TextTag.Type.WORD, 37, 41, 'word'))
self.assertEqual(textTags['f'][5], hrefliterals.TextTag(
hrefliterals.TextTag.Type.CHARACTER, 41, 42, '2'))
self.assertEqual(textTags['f'][6], hrefliterals.TextTag(
hrefliterals.TextTag.Type.CHARACTER, 42, 43, ' '))
self.assertEqual(textTags['f'][7], hrefliterals.TextTag(
hrefliterals.TextTag.Type.WORD, 43, 72, 'word'))
self.assertEqual(textTags['f'][8], hrefliterals.TextTag(
hrefliterals.TextTag.Type.CHARACTER, 72, 73, ' '))
self.assertEqual(textTags['f'][9], hrefliterals.TextTag(
hrefliterals.TextTag.Type.CHARACTER, 123, 124, ' '))
self.assertEqual(textTags['f'][10], hrefliterals.TextTag(
hrefliterals.TextTag.Type.CHARACTER, 150, 151, ' '))
def testFindLiterals(self):
textTags = hrefliterals.extractTextInfo(
self.document, self.exclude_re, '')
literals = {'word':None, 'W.O.R.D.2.':None}
literalTags = hrefliterals.findLiterals(
textTags['f'], literals, {}, self.words, self.stemmer, 0)
self.assertEqual(len(literalTags), 3)
self.assertEqual(literalTags[0], hrefliterals.TextTag(
hrefliterals.TextTag.Type.LITERAL, 29, 34, 'word'))
self.assertEqual(literalTags[1], hrefliterals.TextTag(
hrefliterals.TextTag.Type.LITERAL, 37, 42, 'W.O.R.D.2.'))
self.assertEqual(literalTags[2], hrefliterals.TextTag(
hrefliterals.TextTag.Type.LITERAL, 43, 72, 'word'))
def testExtractTextInfo(self):
textTags = hrefliterals.extractTextInfo(self.document, self.exclude_re,
'')
self.assertEqual(textTags.keys(), ['f'])
self.assertEqual(len(textTags['f']), 11)
self.assertEqual(
textTags['f'][0],
hrefliterals.TextTag(hrefliterals.TextTag.Type.WORD, 29, 34,
'words'))
self.assertEqual(
textTags['f'][1],
hrefliterals.TextTag(hrefliterals.TextTag.Type.CHARACTER, 34, 35,
' '))
self.assertEqual(
textTags['f'][2],
hrefliterals.TextTag(hrefliterals.TextTag.Type.CHARACTER, 35, 36,
'1'))
self.assertEqual(
textTags['f'][3],
hrefliterals.TextTag(hrefliterals.TextTag.Type.CHARACTER, 36, 37,
' '))
self.assertEqual(
textTags['f'][4],
hrefliterals.TextTag(hrefliterals.TextTag.Type.WORD, 37, 41,
'word'))
self.assertEqual(
textTags['f'][5],
hrefliterals.TextTag(hrefliterals.TextTag.Type.CHARACTER, 41, 42,
'2'))
self.assertEqual(
textTags['f'][6],
hrefliterals.TextTag(hrefliterals.TextTag.Type.CHARACTER, 42, 43,
' '))
self.assertEqual(
textTags['f'][7],
hrefliterals.TextTag(hrefliterals.TextTag.Type.WORD, 43, 72,
'word'))
self.assertEqual(
textTags['f'][8],
hrefliterals.TextTag(hrefliterals.TextTag.Type.CHARACTER, 72, 73,
' '))
self.assertEqual(
textTags['f'][9],
hrefliterals.TextTag(hrefliterals.TextTag.Type.CHARACTER, 123, 124,
' '))
self.assertEqual(
textTags['f'][10],
hrefliterals.TextTag(hrefliterals.TextTag.Type.CHARACTER, 150, 151,
' '))
def testReplaceTags(self):
textTags = hrefliterals.extractTextInfo(
self.document, self.exclude_re, '')
literals = {'word':None, 'W.O.R.D.2.':None}
literalTags = hrefliterals.findLiterals(
textTags['f'], literals, {}, self.words, self.stemmer, 0)
literalTags[0].value = '*'
literalTags[1].value = '**'
literalTags[2].value = '***'
replaced = hrefliterals.replaceLiterals(self.source, literalTags)
rsource = r"""
\begin{document}* 1 ** ***
\begin{equation}word\end{equation}
\end{document}
"""
self.assertEqual(replaced, rsource)
def testReplaceTags(self):
textTags = hrefliterals.extractTextInfo(self.document, self.exclude_re,
'')
literals = {'word': None, 'W.O.R.D.2.': None}
literalTags = hrefliterals.findLiterals(textTags['f'], literals, {},
self.words, self.stemmer, 0)
literalTags[0].value = '*'
literalTags[1].value = '**'
literalTags[2].value = '***'
replaced = hrefliterals.replaceLiterals(self.source, literalTags)
rsource = r"""
\begin{document}* 1 ** ***
\begin{equation}word\end{equation}
\end{document}
"""
self.assertEqual(replaced, rsource)
def testFindLiterals(self):
textTags = hrefliterals.extractTextInfo(self.document, self.exclude_re,
'')
literals = {'word': None, 'W.O.R.D.2.': None}
literalTags = hrefliterals.findLiterals(textTags['f'], literals, {},
self.words, self.stemmer, 0)
self.assertEqual(len(literalTags), 3)
self.assertEqual(
literalTags[0],
hrefliterals.TextTag(hrefliterals.TextTag.Type.LITERAL, 29, 34,
'word'))
self.assertEqual(
literalTags[1],
hrefliterals.TextTag(hrefliterals.TextTag.Type.LITERAL, 37, 42,
'W.O.R.D.2.'))
self.assertEqual(
literalTags[2],
hrefliterals.TextTag(hrefliterals.TextTag.Type.LITERAL, 43, 72,
'word'))
def findLiterals(self, source, literals, notLiterals):
document = hrefliterals.parseDocument('f', StringIO.StringIO(source),
os.getcwd())
textTags = hrefliterals.extractTextInfo(document, self.exclude_re, '')
return hrefliterals.findLiterals(textTags['f'], literals, notLiterals,
self.words, self.stemmer, 0)
def findLiterals(self, source, literals, notLiterals):
document = hrefliterals.parseDocument('f', StringIO.StringIO(source),
os.getcwd())
textTags = hrefliterals.extractTextInfo(document, self.exclude_re, '')
return hrefliterals.findLiterals(textTags['f'], literals, notLiterals,
self.words, self.stemmer, 0)
