原文地址:http://xiarilian12.iteye.com/blog/855245
- 支持英文、数字、中文(简体)混合分词
- 常用的数量和人名的匹配
- 超过22万词的词库整理
- 实现正向最大匹配算法
- //采用正向最大匹配的中文分词算法,相当于分词粒度等于0
- MMAnalyzer analyzer = new MMAnalyzer();
- //参数为分词粒度:当字数等于或超过该参数,且能成词,该词就被切分出来
- MMAnalyzer analyzer = new MMAnalyzer(2);
- //增加一个新词典,采用每行一个词的读取方式
- MMAnalyzer.addDictionary(reader);
- //增加一个新词
- MMAnalyzer.addWord(newWord);
- //删除词库中的全部词语(注意:非常危险的操作,在没有加载新的词库前所有的分词都将失效)
- MMAnalyzer.clear();
- //词库中是否包含该词
- MMAnalyzer.contains(String word);
- //从词库中移除该词
- MMAnalyzer.removeWord(String word);
- //当前词库中包含的词语总数
- MMAnalyzer.size();
- view plaincopy to clipboardprint?
- package demo.analysis;
- import java.io.IOException;
- import jeasy.analysis.MMAnalyzer;
- public class Segment
- {
- public static void main(String[] args)
- {
- String text = "据路透社报道,印度尼西亚社会事务部一官员星期二(29日)表示,"
- + "日惹市附近当地时间27日晨5时53分发生的里氏6.2级地震已经造成至少5427人死亡,"
- + "20000余人受伤,近20万人无家可归。";
- MMAnalyzer analyzer = new MMAnalyzer();
- try
- {
- System.out.println(analyzer.segment(text, " | "));
- }
- catch (IOException e)
- {
- e.printStackTrace();
- }
- }
- }
- package demo.analysis;
- import java.io.IOException;
- import jeasy.analysis.MMAnalyzer;
- public class Segment
- {
- public static void main(String[] args)
- {
- String text = "据路透社报道,印度尼西亚社会事务部一官员星期二(29日)表示,"
- + "日惹市附近当地时间27日晨5时53分发生的里氏6.2级地震已经造成至少5427人死亡,"
- + "20000余人受伤,近20万人无家可归。";
- MMAnalyzer analyzer = new MMAnalyzer();
- try
- {
- System.out.println(analyzer.segment(text, " | "));
- }
- catch (IOException e)
- {
- e.printStackTrace();
- }
- }
- }
- 生成效果:
- 据 | 路透社 | 报道 | 印度尼西亚 | 社会 | 事务 | 部 | 官员 | 星期二 | 29日 | 表示 | 日惹 | 市 | 附近 | 当地时间 | 27日
- | 晨 | 5时 | 53分 | 发生 | 里氏 | 6.2级 | 地震 | 已经 | 造成 | 至少 | 5427人 | 死亡 | 20000 | 余人 | 受伤 | 近 | 20万人 | 无家可归 |
- view plaincopy to clipboardprint?
- package demo.analysis;
- import jeasy.analysis.MMAnalyzer;
- import org.apache.lucene.analysis.Analyzer;
- import org.apache.lucene.document.Document;
- import org.apache.lucene.document.Field;
- import org.apache.lucene.index.IndexWriter;
- import org.apache.lucene.queryParser.QueryParser;
- import org.apache.lucene.search.Hits;
- import org.apache.lucene.search.IndexSearcher;
- import org.apache.lucene.search.Query;
- import org.apache.lucene.store.Directory;
- import org.apache.lucene.store.RAMDirectory;
- public class Segment
- {
- public static void main(String[] args)
- {
- String fieldName = "text";
- String text = "据路透社报道,印度尼西亚社会事务部一官员星期二(29日)表示,"
- + "日惹市附近当地时间27日晨5时53分发生的里氏6.2级地震已经造成至少5427人死亡,"
- + "20000余人受伤,近20万人无家可归。"; //检索内容
- //采用正向最大匹配的中文分词算法
- Analyzer analyzer = new MMAnalyzer();
- Directory directory = new RAMDirectory();
- //Directory directory = FSDirectory.getDirectory("/tmp/testindex", true);
- try
- {
- IndexWriter iwriter = new IndexWriter(directory, analyzer, true);
- iwriter.setMaxFieldLength(25000);
- Document doc = new Document();
- doc.add(new Field(fieldName, text, Field.Store.YES, Field.Index.TOKENIZED));
- iwriter.addDocument(doc);
- iwriter.close();
- IndexSearcher isearcher = new IndexSearcher(directory);
- QueryParser parser = new QueryParser(fieldName, analyzer);
- Query query = parser.parse("印度尼西亚 6.2级地震");//检索词
- Hits hits = isearcher.search(query);
- System.out.println("命中:" + hits.length());
- for (int i = 0; i < hits.length(); i++)
- {
- Document hitDoc = hits.doc(i);
- System.out.println("内容:" + hitDoc.get(fieldName));
- }
- isearcher.close();
- directory.close();
- }
- catch (Exception e)
- {
- e.printStackTrace();
- }
- }
- }
- package demo.analysis;
- import jeasy.analysis.MMAnalyzer;
- import org.apache.lucene.analysis.Analyzer;
- import org.apache.lucene.document.Document;
- import org.apache.lucene.document.Field;
- import org.apache.lucene.index.IndexWriter;
- import org.apache.lucene.queryParser.QueryParser;
- import org.apache.lucene.search.Hits;
- import org.apache.lucene.search.IndexSearcher;
- import org.apache.lucene.search.Query;
- import org.apache.lucene.store.Directory;
- import org.apache.lucene.store.RAMDirectory;
- public class Segment
- {
- public static void main(String[] args)
- {
- String fieldName = "text";
- String text = "据路透社报道,印度尼西亚社会事务部一官员星期二(29日)表示,"
- + "日惹市附近当地时间27日晨5时53分发生的里氏6.2级地震已经造成至少5427人死亡,"
- + "20000余人受伤,近20万人无家可归。"; //检索内容
- //采用正向最大匹配的中文分词算法
- Analyzer analyzer = new MMAnalyzer();
- Directory directory = new RAMDirectory();
- //Directory directory = FSDirectory.getDirectory("/tmp/testindex", true);
- try
- {
- IndexWriter iwriter = new IndexWriter(directory, analyzer, true);
- iwriter.setMaxFieldLength(25000);
- Document doc = new Document();
- doc.add(new Field(fieldName, text, Field.Store.YES, Field.Index.TOKENIZED));
- iwriter.addDocument(doc);
- iwriter.close();
- IndexSearcher isearcher = new IndexSearcher(directory);
- QueryParser parser = new QueryParser(fieldName, analyzer);
- Query query = parser.parse("印度尼西亚 6.2级地震");//检索词
- Hits hits = isearcher.search(query);
- System.out.println("命中:" + hits.length());
- for (int i = 0; i < hits.length(); i++)
- {
- Document hitDoc = hits.doc(i);
- System.out.println("内容:" + hitDoc.get(fieldName));
- }
- isearcher.close();
- directory.close();
- }
- catch (Exception e)
- {
- e.printStackTrace();
- }
- }
- }
- 生成效果:
- 命中:1
- 内容:据路透社报道,印度尼西亚社会事务部一官员星期二(29日)表示,日惹市附近当地时间27日晨5时53分发生
- 的里氏6.2级地震已经造成至少5427人死亡,20000余人受伤,近20万人无家可归。
- view plaincopy to clipboardprint?
- package demo.analysis;
- import jeasy.analysis.MMAnalyzer;
- import org.apache.lucene.analysis.Analyzer;
- import org.apache.lucene.analysis.TokenStream;
- import org.apache.lucene.document.Document;
- import org.apache.lucene.document.Field;
- import org.apache.lucene.index.IndexReader;
- import org.apache.lucene.index.IndexWriter;
- import org.apache.lucene.index.TermPositionVector;
- import org.apache.lucene.queryParser.QueryParser;
- import org.apache.lucene.search.Hits;
- import org.apache.lucene.search.IndexSearcher;
- import org.apache.lucene.search.Query;
- import org.apache.lucene.search.highlight.Highlighter;
- import org.apache.lucene.search.highlight.QueryScorer;
- import org.apache.lucene.search.highlight.TokenSources;
- import org.apache.lucene.store.Directory;
- import org.apache.lucene.store.RAMDirectory;
- public class Segment
- {
- public static void main(String[] args)
- {
- String fieldName = "text";
- String text = "据路透社报道,印度尼西亚社会事务部一官员星期二(29日)表示,"
- + "日惹市附近当地时间27日晨5时53分发生的里氏6.2级地震已经造成至少5427人死亡,"
- + "20000余人受伤,近20万人无家可归。"; //检索内容
- //采用正向最大匹配的中文分词算法
- Analyzer analyzer = new MMAnalyzer();
- Directory directory = new RAMDirectory();
- //Directory directory = FSDirectory.getDirectory("/tmp/testindex", true);
- try
- {
- IndexWriter iwriter = new IndexWriter(directory, analyzer, true);
- iwriter.setMaxFieldLength(25000);
- Document doc = new Document();
- doc.add(new Field(fieldName, text, Field.Store.YES,
- Field.Index.TOKENIZED,
- Field.TermVector.WITH_POSITIONS_OFFSETS));
- iwriter.addDocument(doc);
- iwriter.close();
- IndexSearcher isearcher = new IndexSearcher(directory);
- QueryParser parser = new QueryParser(fieldName, analyzer);
- Query query = parser.parse("印度尼西亚 6.2级地震");//检索词
- Hits hits = isearcher.search(query);
- System.out.println("命中:" + hits.length());
- Highlighter highlighter = new Highlighter(new QueryScorer(query));
- for (int i = 0; i < hits.length(); i++)
- {
- text = hits.doc(i).get(fieldName);
- TermPositionVector tpv = (TermPositionVector) IndexReader.open(
- directory).getTermFreqVector(hits.id(i), fieldName);
- TokenStream tokenStream = TokenSources.getTokenStream(tpv);
- String result = highlighter.getBestFragments(tokenStream, text, 3, "...");
- System.out.println("内容:" + result);
- }
- isearcher.close();
- directory.close();
- }
- catch (Exception e)
- {
- e.printStackTrace();
- }
- }
- }
- package demo.analysis;
- import jeasy.analysis.MMAnalyzer;
- import org.apache.lucene.analysis.Analyzer;
- import org.apache.lucene.analysis.TokenStream;
- import org.apache.lucene.document.Document;
- import org.apache.lucene.document.Field;
- import org.apache.lucene.index.IndexReader;
- import org.apache.lucene.index.IndexWriter;
- import org.apache.lucene.index.TermPositionVector;
- import org.apache.lucene.queryParser.QueryParser;
- import org.apache.lucene.search.Hits;
- import org.apache.lucene.search.IndexSearcher;
- import org.apache.lucene.search.Query;
- import org.apache.lucene.search.highlight.Highlighter;
- import org.apache.lucene.search.highlight.QueryScorer;
- import org.apache.lucene.search.highlight.TokenSources;
- import org.apache.lucene.store.Directory;
- import org.apache.lucene.store.RAMDirectory;
- public class Segment
- {
- public static void main(String[] args)
- {
- String fieldName = "text";
- String text = "据路透社报道,印度尼西亚社会事务部一官员星期二(29日)表示,"
- + "日惹市附近当地时间27日晨5时53分发生的里氏6.2级地震已经造成至少5427人死亡,"
- + "20000余人受伤,近20万人无家可归。"; //检索内容
- //采用正向最大匹配的中文分词算法
- Analyzer analyzer = new MMAnalyzer();
- Directory directory = new RAMDirectory();
- //Directory directory = FSDirectory.getDirectory("/tmp/testindex", true);
- try
- {
- IndexWriter iwriter = new IndexWriter(directory, analyzer, true);
- iwriter.setMaxFieldLength(25000);
- Document doc = new Document();
- doc.add(new Field(fieldName, text, Field.Store.YES,
- Field.Index.TOKENIZED,
- Field.TermVector.WITH_POSITIONS_OFFSETS));
- iwriter.addDocument(doc);
- iwriter.close();
- IndexSearcher isearcher = new IndexSearcher(directory);
- QueryParser parser = new QueryParser(fieldName, analyzer);
- Query query = parser.parse("印度尼西亚 6.2级地震");//检索词
- Hits hits = isearcher.search(query);
- System.out.println("命中:" + hits.length());
- Highlighter highlighter = new Highlighter(new QueryScorer(query));
- for (int i = 0; i < hits.length(); i++)
- {
- text = hits.doc(i).get(fieldName);
- TermPositionVector tpv = (TermPositionVector) IndexReader.open(
- directory).getTermFreqVector(hits.id(i), fieldName);
- TokenStream tokenStream = TokenSources.getTokenStream(tpv);
- String result = highlighter.getBestFragments(tokenStream, text, 3, "...");
- System.out.println("内容:" + result);
- }
- isearcher.close();
- directory.close();
- }
- catch (Exception e)
- {
- e.printStackTrace();
- }
- }
- }
- 生成效果:
- 命中:1
- 内容:据路透社报道,<B>印度尼西亚</B>社会事务部一官员星期二(29日)表示,日惹市附近当地时间27日晨5时53分发生的
- 里氏<B>6.2级</B><B>地震</B>已经造成至少5427人死亡,20000余人受伤,近20万人无家可归
- 本文来自CSDN博客,转载请标明出处:http://blog.csdn.net/xiaoping8411/archive/2010/03/30/5435134.aspx