def createComponents(self, fieldName):
source = StandardTokenizer()
filter1 = LowerCaseFilter(source)
filter1 = PorterStemFilter(filter1)
filter1 = StopFilter(filter1, EnglishAnalyzer.ENGLISH_STOP_WORDS_SET)
return self.TokenStreamComponents(source, filter1)
def createComponents(self, fieldName): source = StandardTokenizer() stream = LowerCaseFilter(source) stream = StopFilter(stream, PortugueseAnalyzer.getDefaultStopSet()) stream = PortugueseLightStemFilter(stream) return self.TokenStreamComponents(source, stream)
def testStopWords(self):
try:
result = StandardTokenizer()
result.setReader(self.reader)
result = StopFilter(result, self.stop_set)
except Exception, e:
self.fail(str(e))
def createComponents(self, fieldName):
source = StandardTokenizer()
result = EnglishPossessiveFilter(source)
result = LowerCaseFilter(result)
result = DiacriticFilter(result)
result = StopFilter(result, self.stopwords)
if self.stemExclusionSet.isEmpty() is False:
result = SetKeywordMarkerFilter(result, self.stemExclusionSet)
result = PorterStemFilter(result)
return Analyzer.TokenStreamComponents(source, result)
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
def setUp(self):
stopWords = ['the', 'and', 's']
self.stop_set = StopFilter.makeStopSet(stopWords)
self.reader = StringReader('foo')
def setUp(self):
stopWords = ['the', 'and', 's']
self.stop_set = StopFilter.makeStopSet(stopWords)
self.reader = StringReader('foo')
def filter_stopwords(stream):
stream = StopFilter(stream, RomanianAnalyzer.getDefaultStopSet())
with open('romanian-stopwords.txt') as f:
additional_stopwords = unicode(f.read(), 'utf-8').split()
additional_stopwords = StopFilter.makeStopSet(additional_stopwords)
return StopFilter(stream, additional_stopwords)