def testMinimalExample(self):
file_ = os.path.abspath(os.path.join('..','testFiles','minimalExample.tex'))
sArgs = sortArgs([])
repRE, extRE, puncRE, delRE = compileRegex(sArgs[0], sArgs[1], sArgs[3],
sArgs[4], sArgs[2])
text = extractText(file_, repRE, extRE, puncRE, delRE)
self.assertEqual(text, "")
def testSampleOneReplaceClass(self):
file_ = os.path.abspath(os.path.join('..','testFiles','example1.tex'))
sArgs = sortArgs(["--replace-class","hword","Header"])
repRE, extRE, puncRE, delRE = compileRegex(sArgs[0], sArgs[1], sArgs[3],
sArgs[4], sArgs[2])
text = extractText(file_, repRE, extRE, puncRE, delRE)
self.assertEqual(text, "Header Header Header This is a sample document to test expected extraction."+\
" Header Header Header This is section one. Header Header This is section two.")
def testSampleOneIgnoreDefault(self):
file_ = os.path.abspath(os.path.join('..','testFiles','example1.tex'))
sArgs = sortArgs(["--ignore-default-extraction","--extract-class","word"])
repRE, extRE, puncRE, delRE = compileRegex(sArgs[0], sArgs[1], sArgs[3],
sArgs[4], sArgs[2])
text = extractText(file_, repRE, extRE, puncRE, delRE)
self.assertEqual(text, "This is a sample document to test expected extraction."+\
" This is section one. This is section two.")
def testSampleOneNoPunc(self):
file_ = os.path.abspath(os.path.join('..','testFiles','example1.tex'))
sArgs = sortArgs(["--no-punctuation"])
repRE, extRE, puncRE, delRE = compileRegex(sArgs[0], sArgs[1], sArgs[3],
sArgs[4], sArgs[2])
text = extractText(file_, repRE, extRE, puncRE, delRE)
self.assertEqual(text, "Sample Article One This is a sample document to test expected extraction"+\
" Section One Title This is section one Section Two This is section two")
def testMinimalExample(self):
file_ = os.path.abspath(
os.path.join('..', 'testFiles', 'minimalExample.tex'))
sArgs = sortArgs([])
repRE, extRE, puncRE, delRE = compileRegex(sArgs[0], sArgs[1],
sArgs[3], sArgs[4],
sArgs[2])
text = extractText(file_, repRE, extRE, puncRE, delRE)
self.assertEqual(text, "")
def testSample2ReplaceInlineMath(self):
file_ = os.path.abspath(os.path.join('..','testFiles','example2.tex'))
sArgs = sortArgs(["--replace-inline-math","inline_math"])
repRE, extRE, puncRE, delRE = compileRegex(sArgs[0], sArgs[1], sArgs[3],
sArgs[4], sArgs[2])
text = extractText(file_, repRE, extRE, puncRE, delRE)
self.assertEqual(text, "Sample Article Two This is a sample document to test expected extraction."+\
" Section One Title This is section one. This is an inline equation inline_math with text surrounding it."+\
" This is a normal equation This is a figure")
def testSampleOneReplaceClass(self):
file_ = os.path.abspath(os.path.join('..', 'testFiles',
'example1.tex'))
sArgs = sortArgs(["--replace-class", "hword", "Header"])
repRE, extRE, puncRE, delRE = compileRegex(sArgs[0], sArgs[1],
sArgs[3], sArgs[4],
sArgs[2])
text = extractText(file_, repRE, extRE, puncRE, delRE)
self.assertEqual(text, "Header Header Header This is a sample document to test expected extraction."+\
" Header Header Header This is section one. Header Header This is section two.")
def testSampleOneNoPunc(self):
file_ = os.path.abspath(os.path.join('..', 'testFiles',
'example1.tex'))
sArgs = sortArgs(["--no-punctuation"])
repRE, extRE, puncRE, delRE = compileRegex(sArgs[0], sArgs[1],
sArgs[3], sArgs[4],
sArgs[2])
text = extractText(file_, repRE, extRE, puncRE, delRE)
self.assertEqual(text, "Sample Article One This is a sample document to test expected extraction"+\
" Section One Title This is section one Section Two This is section two")
def testSample2PuncFile(self):
file_ = os.path.abspath(os.path.join('..','testFiles','example2.tex'))
pFile = os.path.abspath(os.path.join('..','testFiles','samplePuncFile.txt'))
sArgs = sortArgs(["--punctuation-file",pFile])
repRE, extRE, puncRE, delRE = compileRegex(sArgs[0], sArgs[1], sArgs[3],
sArgs[4], sArgs[2])
text = extractText(file_, repRE, extRE, puncRE, delRE)
self.assertEqual(text, "Sample Article Two This is a sample document to test expected extraction."+\
" Section One Title This is section one. This is an inline equation with text surrounding it."+\
" This is a normal equation This is a figure:")
def testSample2ReplaceInlineMath(self):
file_ = os.path.abspath(os.path.join('..', 'testFiles',
'example2.tex'))
sArgs = sortArgs(["--replace-inline-math", "inline_math"])
repRE, extRE, puncRE, delRE = compileRegex(sArgs[0], sArgs[1],
sArgs[3], sArgs[4],
sArgs[2])
text = extractText(file_, repRE, extRE, puncRE, delRE)
self.assertEqual(text, "Sample Article Two This is a sample document to test expected extraction."+\
" Section One Title This is section one. This is an inline equation inline_math with text surrounding it."+\
" This is a normal equation This is a figure")
def testSampleOneIgnoreDefault(self):
file_ = os.path.abspath(os.path.join('..', 'testFiles',
'example1.tex'))
sArgs = sortArgs(
["--ignore-default-extraction", "--extract-class", "word"])
repRE, extRE, puncRE, delRE = compileRegex(sArgs[0], sArgs[1],
sArgs[3], sArgs[4],
sArgs[2])
text = extractText(file_, repRE, extRE, puncRE, delRE)
self.assertEqual(text, "This is a sample document to test expected extraction."+\
" This is section one. This is section two.")
def testSample2PuncFile(self):
file_ = os.path.abspath(os.path.join('..', 'testFiles',
'example2.tex'))
pFile = os.path.abspath(
os.path.join('..', 'testFiles', 'samplePuncFile.txt'))
sArgs = sortArgs(["--punctuation-file", pFile])
repRE, extRE, puncRE, delRE = compileRegex(sArgs[0], sArgs[1],
sArgs[3], sArgs[4],
sArgs[2])
text = extractText(file_, repRE, extRE, puncRE, delRE)
self.assertEqual(text, "Sample Article Two This is a sample document to test expected extraction."+\
" Section One Title This is section one. This is an inline equation with text surrounding it."+\
" This is a normal equation This is a figure:")