def extract(self, analyzer, str):
tokenStream = analyzer.tokenStream('content', StringReader(str))
termAttr = tokenStream.addAttribute(lucene.findClass('org/apache/lucene/analysis/tokenattributes/CharTermAttribute'))
keywords = []
tokenStream.reset()
while tokenStream.incrementToken():
keywords.append(termAttr.toString())
return keywords
def debug(cls, analyzer, str):
tokenStream = analyzer.tokenStream('debug', StringReader(str))
termAttr = tokenStream.addAttribute(lucene.findClass('org/apache/lucene/analysis/tokenattributes/CharTermAttribute'))
str = ''
tokenStream.reset()
while tokenStream.incrementToken():
str = str + ('[%s] ' % termAttr.toString())
return str
def search_interactive_history(self):
doc = None
while True:
print()
print('Hit enter with no input to quit.')
command = raw_input('Query:')
if command == '':
return doc
print()
print('Searching for:'.format(command))
query = TermQuery(Term('history', command))
hits = self._searcher_ngram.search(query, 1000).scoreDocs
print('{} total matching documents.'.format(len(hits)))
for i, hit in enumerate(hits):
doc = self._searcher_ngram.doc(hit.doc)
print('doc {}:'.format(i))
for f in doc:
print(type(f))
print('\t{}'.format(f.toString().encode('utf-8')))
# print 'text:', doc.get("text")
if i >= 30:
break
if __name__ == '__main__':
try:
lucene.findClass('org/apache/lucene/document/Document')
except:
lucene.initVM(vmargs=['-Djava.awt.headless=true'])
print('lucene {}'.format(lucene.VERSION))