All Downloads are FREE. Search and download functionalities are using the official Maven repository.

org.apache.lucene.analysis.pattern.SimplePatternSplitTokenizerFactory Maven / Gradle / Ivy

There is a newer version: 8.11.4
Show newest version
/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package org.apache.lucene.analysis.pattern;

import java.util.Map;

import org.apache.lucene.analysis.util.TokenizerFactory;
import org.apache.lucene.util.AttributeFactory;
import org.apache.lucene.util.automaton.Automaton;
import org.apache.lucene.util.automaton.Operations;
import org.apache.lucene.util.automaton.RegExp;

/**
 * Factory for {@link SimplePatternSplitTokenizer}, for producing tokens by splitting according to the provided regexp.
 *
 * 

This tokenizer uses Lucene {@link RegExp} pattern matching to construct distinct tokens * for the input stream. The syntax is more limited than {@link PatternTokenizer}, but the * tokenization is quite a bit faster. It takes two arguments: *
*

    *
  • "pattern" (required) is the regular expression, according to the syntax described at {@link RegExp}
  • *
  • "maxDeterminizedStates" (optional, default 10000) the limit on total state count for the determined automaton computed from the regexp
  • *
*

* The pattern matches the characters that should split tokens, like {@code String.split}, and the * matching is greedy such that the longest token separator matching at a given point is matched. Empty * tokens are never created. * *

For example, to match tokens delimited by simple whitespace characters: * *

 * <fieldType name="text_ptn" class="solr.TextField" positionIncrementGap="100">
 *   <analyzer>
 *     <tokenizer class="solr.SimplePatternSplitTokenizerFactory" pattern="[ \t\r\n]+"/>
 *   </analyzer>
 * </fieldType>
* * @lucene.experimental * * @see SimplePatternSplitTokenizer * * @since 6.5.0 * @lucene.spi {@value #NAME} */ public class SimplePatternSplitTokenizerFactory extends TokenizerFactory { /** SPI name */ public static final String NAME = "simplePatternSplit"; public static final String PATTERN = "pattern"; private final Automaton dfa; private final int maxDeterminizedStates; /** Creates a new SimpleSplitPatternTokenizerFactory */ public SimplePatternSplitTokenizerFactory(Map args) { super(args); maxDeterminizedStates = getInt(args, "maxDeterminizedStates", Operations.DEFAULT_MAX_DETERMINIZED_STATES); dfa = Operations.determinize(new RegExp(require(args, PATTERN)).toAutomaton(), maxDeterminizedStates); if (args.isEmpty() == false) { throw new IllegalArgumentException("Unknown parameters: " + args); } } @Override public SimplePatternSplitTokenizer create(final AttributeFactory factory) { return new SimplePatternSplitTokenizer(factory, dfa); } }




© 2015 - 2024 Weber Informatics LLC | Privacy Policy