def testStopList(self):
stopWords = ["good", "test", "analyzer"]
stopWordsSet = StopFilter.makeStopSet(stopWords)
newStop = StopAnalyzer(stopWordsSet)
reader = StringReader("This is a good test of the english stop analyzer")
stream = newStop.tokenStream("test", reader)
self.assert_(stream is not None)
stream.reset()
termAtt = stream.getAttribute(CharTermAttribute.class_)
while stream.incrementToken():
text = termAtt.toString()
self.assert_(text not in stopWordsSet)
def testStopListPositions(self):
stopWords = ["good", "test", "analyzer"]
stopWordsSet = StopFilter.makeStopSet(stopWords)
newStop = StopAnalyzer(stopWordsSet)
reader = StringReader("This is a good test of the english stop analyzer with positions")
expectedIncr = [ 1, 1, 1, 3, 1, 1, 1, 2, 1]
stream = newStop.tokenStream("test", reader)
self.assert_(stream is not None)
stream.reset()
i = 0
termAtt = stream.getAttribute(CharTermAttribute.class_)
posIncrAtt = stream.addAttribute(PositionIncrementAttribute.class_)
while stream.incrementToken():
text = termAtt.toString()
self.assert_(text not in stopWordsSet)
self.assertEqual(expectedIncr[i],
posIncrAtt.getPositionIncrement())
i += 1
class StopAnalyzerTestCase(unittest.TestCase):
"""
Unit tests ported from Java Lucene
"""
def setUp(self):
self.stop = StopAnalyzer()
self.invalidTokens = StopAnalyzer.ENGLISH_STOP_WORDS_SET
def testDefaults(self):
self.assert_(self.stop is not None)
reader = StringReader("This is a test of the english stop analyzer")
stream = self.stop.tokenStream("test", reader)
self.assert_(stream is not None)
stream.reset()
termAtt = stream.getAttribute(CharTermAttribute.class_)
while stream.incrementToken():
self.assert_(termAtt.toString() not in self.invalidTokens)
def testStopList(self):
stopWords = ["good", "test", "analyzer"]
stopWordsSet = StopFilter.makeStopSet(stopWords)
newStop = StopAnalyzer(stopWordsSet)
reader = StringReader("This is a good test of the english stop analyzer")
stream = newStop.tokenStream("test", reader)
self.assert_(stream is not None)
stream.reset()
termAtt = stream.getAttribute(CharTermAttribute.class_)
while stream.incrementToken():
text = termAtt.toString()
self.assert_(text not in stopWordsSet)
def testStopListPositions(self):
stopWords = ["good", "test", "analyzer"]
stopWordsSet = StopFilter.makeStopSet(stopWords)
newStop = StopAnalyzer(stopWordsSet)
reader = StringReader("This is a good test of the english stop analyzer with positions")
expectedIncr = [ 1, 1, 1, 3, 1, 1, 1, 2, 1]
stream = newStop.tokenStream("test", reader)
self.assert_(stream is not None)
stream.reset()
i = 0
termAtt = stream.getAttribute(CharTermAttribute.class_)
posIncrAtt = stream.addAttribute(PositionIncrementAttribute.class_)
while stream.incrementToken():
text = termAtt.toString()
self.assert_(text not in stopWordsSet)
self.assertEqual(expectedIncr[i],
posIncrAtt.getPositionIncrement())
i += 1