|
Lucene example source code file (WikipediaTokenizer.java)
The Lucene WikipediaTokenizer.java source code/** * 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.wikipedia; import org.apache.lucene.analysis.Tokenizer; import org.apache.lucene.analysis.tokenattributes.CharTermAttribute; import org.apache.lucene.analysis.tokenattributes.FlagsAttribute; import org.apache.lucene.analysis.tokenattributes.OffsetAttribute; import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute; import org.apache.lucene.analysis.tokenattributes.TypeAttribute; import org.apache.lucene.util.AttributeSource; import java.io.IOException; import java.io.Reader; import java.util.*; /** * Extension of StandardTokenizer that is aware of Wikipedia syntax. It is based off of the * Wikipedia tutorial available at http://en.wikipedia.org/wiki/Wikipedia:Tutorial, but it may not be complete. * <p/> * <p/> * @lucene.experimental */ public final class WikipediaTokenizer extends Tokenizer { public static final String INTERNAL_LINK = "il"; public static final String EXTERNAL_LINK = "el"; //The URL part of the link, i.e. the first token public static final String EXTERNAL_LINK_URL = "elu"; public static final String CITATION = "ci"; public static final String CATEGORY = "c"; public static final String BOLD = "b"; public static final String ITALICS = "i"; public static final String BOLD_ITALICS = "bi"; public static final String HEADING = "h"; public static final String SUB_HEADING = "sh"; public static final int ALPHANUM_ID = 0; public static final int APOSTROPHE_ID = 1; public static final int ACRONYM_ID = 2; public static final int COMPANY_ID = 3; public static final int EMAIL_ID = 4; public static final int HOST_ID = 5; public static final int NUM_ID = 6; public static final int CJ_ID = 7; public static final int INTERNAL_LINK_ID = 8; public static final int EXTERNAL_LINK_ID = 9; public static final int CITATION_ID = 10; public static final int CATEGORY_ID = 11; public static final int BOLD_ID = 12; public static final int ITALICS_ID = 13; public static final int BOLD_ITALICS_ID = 14; public static final int HEADING_ID = 15; public static final int SUB_HEADING_ID = 16; public static final int EXTERNAL_LINK_URL_ID = 17; /** String token types that correspond to token type int constants */ public static final String [] TOKEN_TYPES = new String [] { "<ALPHANUM>", "<APOSTROPHE>", "<ACRONYM>", "<COMPANY>", "<EMAIL>", "<HOST>", "<NUM>", "<CJ>", INTERNAL_LINK, EXTERNAL_LINK, CITATION, CATEGORY, BOLD, ITALICS, BOLD_ITALICS, HEADING, SUB_HEADING, EXTERNAL_LINK_URL }; /** * Only output tokens */ public static final int TOKENS_ONLY = 0; /** * Only output untokenized tokens, which are tokens that would normally be split into several tokens */ public static final int UNTOKENIZED_ONLY = 1; /** * Output the both the untokenized token and the splits */ public static final int BOTH = 2; /** * This flag is used to indicate that the produced "Token" would, if {@link #TOKENS_ONLY} was used, produce multiple tokens. */ public static final int UNTOKENIZED_TOKEN_FLAG = 1; /** * A private instance of the JFlex-constructed scanner */ private final WikipediaTokenizerImpl scanner; private int tokenOutput = TOKENS_ONLY; private Set<String> untokenizedTypes = Collections.emptySet(); private Iterator<AttributeSource.State> tokens = null; private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class); private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class); private final PositionIncrementAttribute posIncrAtt = addAttribute(PositionIncrementAttribute.class); private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class); private final FlagsAttribute flagsAtt = addAttribute(FlagsAttribute.class); /** * Creates a new instance of the {@link WikipediaTokenizer}. Attaches the * <code>input to a newly created JFlex scanner. * * @param input The Input Reader */ public WikipediaTokenizer(Reader input) { this(input, TOKENS_ONLY, Collections.<String>emptySet()); } /** * Creates a new instance of the {@link org.apache.lucene.analysis.wikipedia.WikipediaTokenizer}. Attaches the * <code>input to a the newly created JFlex scanner. * * @param input The input * @param tokenOutput One of {@link #TOKENS_ONLY}, {@link #UNTOKENIZED_ONLY}, {@link #BOTH} * @param untokenizedTypes */ public WikipediaTokenizer(Reader input, int tokenOutput, Set<String> untokenizedTypes) { super(input); this.scanner = new WikipediaTokenizerImpl(input); init(tokenOutput, untokenizedTypes); } /** * Creates a new instance of the {@link org.apache.lucene.analysis.wikipedia.WikipediaTokenizer}. Attaches the * <code>input to a the newly created JFlex scanner. Uses the given {@link org.apache.lucene.util.AttributeSource.AttributeFactory}. * * @param input The input * @param tokenOutput One of {@link #TOKENS_ONLY}, {@link #UNTOKENIZED_ONLY}, {@link #BOTH} * @param untokenizedTypes */ public WikipediaTokenizer(AttributeFactory factory, Reader input, int tokenOutput, Set<String> untokenizedTypes) { super(factory, input); this.scanner = new WikipediaTokenizerImpl(input); init(tokenOutput, untokenizedTypes); } /** * Creates a new instance of the {@link org.apache.lucene.analysis.wikipedia.WikipediaTokenizer}. Attaches the * <code>input to a the newly created JFlex scanner. Uses the given {@link AttributeSource}. * * @param input The input * @param tokenOutput One of {@link #TOKENS_ONLY}, {@link #UNTOKENIZED_ONLY}, {@link #BOTH} * @param untokenizedTypes */ public WikipediaTokenizer(AttributeSource source, Reader input, int tokenOutput, Set<String> untokenizedTypes) { super(source, input); this.scanner = new WikipediaTokenizerImpl(input); init(tokenOutput, untokenizedTypes); } private void init(int tokenOutput, Set<String> untokenizedTypes) { this.tokenOutput = tokenOutput; this.untokenizedTypes = untokenizedTypes; } /* * (non-Javadoc) * * @see org.apache.lucene.analysis.TokenStream#next() */ @Override public final boolean incrementToken() throws IOException { if (tokens != null && tokens.hasNext()){ AttributeSource.State state = tokens.next(); restoreState(state); return true; } clearAttributes(); int tokenType = scanner.getNextToken(); if (tokenType == WikipediaTokenizerImpl.YYEOF) { return false; } String type = WikipediaTokenizerImpl.TOKEN_TYPES[tokenType]; if (tokenOutput == TOKENS_ONLY || untokenizedTypes.contains(type) == false){ setupToken(); } else if (tokenOutput == UNTOKENIZED_ONLY && untokenizedTypes.contains(type) == true){ collapseTokens(tokenType); } else if (tokenOutput == BOTH){ //collapse into a single token, add it to tokens AND output the individual tokens //output the untokenized Token first collapseAndSaveTokens(tokenType, type); } posIncrAtt.setPositionIncrement(scanner.getPositionIncrement()); typeAtt.setType(type); return true; } private void collapseAndSaveTokens(int tokenType, String type) throws IOException { //collapse StringBuilder buffer = new StringBuilder(32); int numAdded = scanner.setText(buffer); //TODO: how to know how much whitespace to add int theStart = scanner.yychar(); int lastPos = theStart + numAdded; int tmpTokType; int numSeen = 0; List<AttributeSource.State> tmp = new ArrayList Other Lucene examples (source code examples)Here is a short list of links related to this Lucene WikipediaTokenizer.java source code file: |
... this post is sponsored by my books ... | |
#1 New Release! |
FP Best Seller |
Copyright 1998-2021 Alvin Alexander, alvinalexander.com
All Rights Reserved.
A percentage of advertising revenue from
pages under the /java/jwarehouse
URI on this website is
paid back to open source projects.