EdgeNGram フィルターをラップするアナライザーの例を次に示します。
import lucene
class EdgeNGramAnalyzer(lucene.PythonAnalyzer):
'''
This is an example of a custom Analyzer (in this case an edge-n-gram analyzer)
EdgeNGram Analyzers are good for type-ahead
'''
def __init__(self, side, minlength, maxlength):
'''
Args:
side[enum] Can be one of lucene.EdgeNGramTokenFilter.Side.FRONT or lucene.EdgeNGramTokenFilter.Side.BACK
minlength[int]
maxlength[int]
'''
lucene.PythonAnalyzer.__init__(self)
self.side = side
self.minlength = minlength
self.maxlength = maxlength
def tokenStream(self, fieldName, reader):
result = lucene.LowerCaseTokenizer(Version.LUCENE_CURRENT, reader)
result = lucene.StandardFilter(result)
result = lucene.StopFilter(True, result, StopAnalyzer.ENGLISH_STOP_WORDS_SET)
result = lucene.ASCIIFoldingFilter(result)
result = lucene.EdgeNGramTokenFilter(result, self.side, self.minlength, self.maxlength)
return result
PorterStemmer を再実装する別の例を次に示します。
# This sample illustrates how to write an Analyzer 'extension' in Python.
#
# What is happening behind the scenes ?
#
# The PorterStemmerAnalyzer python class does not in fact extend Analyzer,
# it merely provides an implementation for Analyzer's abstract tokenStream()
# method. When an instance of PorterStemmerAnalyzer is passed to PyLucene,
# with a call to IndexWriter(store, PorterStemmerAnalyzer(), True) for
# example, the PyLucene SWIG-based glue code wraps it into an instance of
# PythonAnalyzer, a proper java extension of Analyzer which implements a
# native tokenStream() method whose job is to call the tokenStream() method
# on the python instance it wraps. The PythonAnalyzer instance is the
# Analyzer extension bridge to PorterStemmerAnalyzer.
'''
More explanation...
Analyzers split up a chunk of text into tokens...
Analyzers are applied to an index globally (unless you use perFieldAnalyzer)
Analyzers implement Tokenizers and TokenFilters.
Tokenizers break up string into tokens. TokenFilters break of Tokens into more Tokens or filter out
Tokens
'''
import sys, os
from datetime import datetime
from lucene import *
from IndexFiles import IndexFiles
class PorterStemmerAnalyzer(PythonAnalyzer):
def tokenStream(self, fieldName, reader):
#There can only be 1 tokenizer in each Analyzer
result = StandardTokenizer(Version.LUCENE_CURRENT, reader)
result = StandardFilter(result)
result = LowerCaseFilter(result)
result = PorterStemFilter(result)
result = StopFilter(True, result, StopAnalyzer.ENGLISH_STOP_WORDS_SET)
return result
if __name__ == '__main__':
if len(sys.argv) < 2:
sys.exit("requires at least one argument: lucene-index-path")
initVM()
start = datetime.now()
try:
IndexFiles(sys.argv[1], "index", PorterStemmerAnalyzer())
end = datetime.now()
print end - start
except Exception, e:
print "Failed: ", e
perFieldAnalyzerWrapper.java
もチェックアウト
KeywordAnalyzerTest.py
analyzer = PerFieldAnalyzerWrapper(SimpleAnalyzer())
analyzer.addAnalyzer("partnum", KeywordAnalyzer())
query = QueryParser(Version.LUCENE_CURRENT, "description",
analyzer).parse("partnum:Q36 AND SPACE")
scoreDocs = self.searcher.search(query, 50).scoreDocs