java中文分词算法
Posted qq_34844199
tags:
篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了java中文分词算法相关的知识,希望对你有一定的参考价值。
package com.tray.indexData; import java.io.File; import java.io.IOException; import java.io.StringReader; import java.math.BigInteger; import java.util.ArrayList; import java.util.HashMap; import java.util.List; import java.util.Map; import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.analysis.TokenStream; import org.apache.lucene.document.Document; import org.apache.lucene.document.Fieldable; import org.apache.lucene.index.CorruptIndexException; import org.apache.lucene.index.IndexReader; import org.apache.lucene.index.IndexWriter; import org.apache.lucene.index.IndexWriterConfig; import org.apache.lucene.index.IndexWriterConfig.OpenMode; import org.apache.lucene.index.Term; import org.apache.lucene.queryParser.MultiFieldQueryParser; import org.apache.lucene.queryParser.QueryParser; import org.apache.lucene.search.IndexSearcher; import org.apache.lucene.search.PrefixQuery; import org.apache.lucene.search.Query; import org.apache.lucene.search.ScoreDoc; import org.apache.lucene.search.TermQuery; import org.apache.lucene.search.TopDocs; import org.apache.lucene.search.TopScoreDocCollector; import org.apache.lucene.search.WildcardQuery; import org.apache.lucene.search.highlight.Highlighter; import org.apache.lucene.search.highlight.QueryScorer; import org.apache.lucene.search.highlight.SimplehtmlFormatter; import org.apache.lucene.store.Directory; import org.apache.lucene.store.FSDirectory; import org.apache.lucene.util.Version; import org.wltea.analyzer.lucene.IKAnalyzer; import com.tray.bean.SerachResult; import com.tray.common.tools.DateFormater; public class LuceneSearch { private static String DISC_URL = "/home/indexData/data"; static { String os = System.getProperty("os.name"); if(os.toLowerCase().startsWith("win")){ DISC_URL = "E:\\indexData\\data"; } else{ DISC_URL ="/home/indexData/data"; } } //指定分词器 private Analyzer analyzer=new IKAnalyzer(); private static Directory directory; //配置 private static IndexWriterConfig iwConfig; //配置IndexWriter private static IndexWriter writer; private static File indexFile = null; private static Version version = Version.LUCENE_36; private final int PAPGESIZE=10; /** * 全量索引 * @Author haoning */ public void init() throws Exception { try { indexFile = new File(DISC_URL); if (!indexFile.exists()) { indexFile.mkdir(); } directory=FSDirectory.open(indexFile); //配置IndexWriterConfig iwConfig = new IndexWriterConfig(version,analyzer); iwConfig.setOpenMode(OpenMode.CREATE_OR_APPEND); //创建写索引对象 writer = new IndexWriter(directory,iwConfig); } catch (Exception e) { } } public void closeWriter(){ try { writer.close(); } catch (CorruptIndexException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } } public void commit(){ try { writer.commit(); } catch (CorruptIndexException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } } /** * 一个一个索引 * @Author haoning */ public void singleIndex(Document doc) throws Exception { writer.addDocument(doc); } /** * 一个跟新 * @Author haoning */ public void singleUpdate(Document doc) throws Exception { Term term = new Term("url", doc.get("url")); writer.updateDocument(term,doc); } /** * 全量索引 * @Author haoning */ public void fullIndex(Document[] documentes) throws Exception { writer.deleteAll(); for (Document document : documentes) { writer.addDocument(document); } writer.commit(); } /** * 根据id删除索引 * @Author haoning */ public void deleteIndex(Document document)throws Exception{ Term term = new Term("url", document.get("url"));//url才是唯一标志 writer.deleteDocuments(term); writer.commit(); } /** * 根据id增量索引 * @Author haoning */ public void updateIndex(Document[] documentes) throws Exception{ for (Document document : documentes) { Term term = new Term("url", document.get("url")); writer.updateDocument(term, document); } writer.commit(); } /** * 直接查询 * @Author haoning */ public void simpleSearch(String filedStr,String queryStr,int page, int pageSize) throws Exception{ File indexDir = new File(DISC_URL); //索引目录 Directory dir=FSDirectory.open(indexDir); //根据索引目录创建读索引对象 IndexReader reader = IndexReader.open(dir); //搜索对象创建 IndexSearcher searcher = new IndexSearcher(reader); TopScoreDocCollector topCollector = TopScoreDocCollector.create(searcher.maxDoc(), false); Term term = new Term(filedStr, queryStr); Query query = new TermQuery(term); searcher.search(query, topCollector); ScoreDoc[] docs = topCollector.topDocs((page-1)*pageSize, pageSize).scoreDocs; printScoreDoc(docs, searcher); } /** * 高亮查询 * @Author haoning */ public Map<String, Object> highLightSearch(String filed,String keyWord,int curpage, int pageSize) throws Exception{ List<SerachResult> list=new ArrayList<SerachResult>(); Map<String,Object> map = new HashMap<String,Object>(); if (curpage <= 0) { curpage = 1; } if (pageSize <= 0 || pageSize>20) { pageSize = PAPGESIZE; } File indexDir = new File(DISC_URL); //索引目录 Directory dir=FSDirectory.open(indexDir);//根据索引目录创建读索引对象 IndexReader reader = IndexReader.open(dir);//搜索对象创建 IndexSearcher searcher = new IndexSearcher(reader); int start = (curpage - 1) * pageSize; Analyzer analyzer = new IKAnalyzer(true); QueryParser queryParser = new QueryParser(Version.LUCENE_36, filed, analyzer); queryParser.setDefaultOperator(QueryParser.AND_OPERATOR); Query query = queryParser.parse(keyWord); int hm = start + pageSize; TopScoreDocCollector res = TopScoreDocCollector.create(hm, false); searcher.search(query, res); SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("<span style='color:red'>", "</span>"); Highlighter highlighter = new Highlighter(simpleHTMLFormatter, new QueryScorer(query)); long amount = res.getTotalHits(); //long pages = (rowCount - 1) / pageSize + 1; //计算总页数 map.put("amount",amount);//总共多少条记录 TopDocs tds = res.topDocs(start, pageSize); ScoreDoc[] sd = tds.scoreDocs; for (int i = 0; i < sd.length; i++) { Document doc = searcher.doc(sd[i].doc); String temp=doc.get("name"); //做高亮处理 TokenStream ts = analyzer.tokenStream("name", new StringReader(temp)); SerachResult record=new SerachResult(); String name = highlighter.getBestFragment(ts,temp); String skydirverName=doc.get("skydirverName"); String username=doc.get("username"); String shareTime=doc.get("shareTime"); String describ=doc.get("describ"); String typeId=doc.get("typeId"); String id=doc.get("id"); String url=doc.get("url"); record.setName(name); record.setSkydriverName(skydirverName); record.setUsername(username); record.setShareTime(DateFormater.getFormatDate(shareTime,"yyyy-MM-dd HH:mm:ss")); record.setDescrib(describ); record.setTypeId(Integer.parseInt(typeId)); record.setId(new BigInteger(id)); record.setUrl(url); list.add(record); /*System.out.println("name:"+name); System.out.println("skydirverName:"+skydirverName); System.out.println("username:"+username); System.out.println("shareTime:"+shareTime); System.out.println("describ:"+describ); System.out.println("typeId:"+typeId); System.out.println("id:"+id); System.out.println("url:"+url);*/ } map.put("source",list); return map; } /** * 根据前缀查询 * @Author haoning */ public void prefixSearch(String filedStr,String queryStr) throws Exception{ File indexDir = new File(DISC_URL); //索引目录 Directory dir=FSDirectory.open(indexDir); //根据索引目录创建读索引对象 IndexReader reader = IndexReader.open(dir); //搜索对象创建 IndexSearcher searcher = new IndexSearcher(reader); Term term = new Term(filedStr, queryStr); Query query = new PrefixQuery(term); ScoreDoc[] docs = searcher.search(query, 3).scoreDocs; printScoreDoc(docs, searcher); } /** * 通配符查询 * @Author haoning */ public void wildcardSearch(String filedStr,String queryStr) throws Exception{ File indexDir = new File(DISC_URL); //索引目录 Directory dir=FSDirectory.open(indexDir); //根据索引目录创建读索引对象 IndexReader reader = IndexReader.open(dir); //搜索对象创建 IndexSearcher searcher = new IndexSearcher(reader); Term term = new Term(filedStr, queryStr); Query query = new WildcardQuery(term); ScoreDoc[] docs = searcher.search(query, 3).scoreDocs; printScoreDoc(docs, searcher); } /** * 分词查询 * @Author haoning */ public void analyzerSearch(String filedStr,String queryStr) throws Exception{ File indexDir = new File(DISC_URL); //索引目录 Directory dir=FSDirectory.open(indexDir); //根据索引目录创建读索引对象 IndexReader reader = IndexReader.open(dir); //搜索对象创建 IndexSearcher searcher = new IndexSearcher(reader); QueryParser queryParser = new QueryParser(version, filedStr, analyzer); Query query = queryParser.parse(queryStr); ScoreDoc[] docs = searcher.search(query, 3).scoreDocs; printScoreDoc(docs, searcher); } /** * 多属性分词查询 * @Author haoning */ public void multiAnalyzerSearch(String[] filedStr,String queryStr) throws Exception{ File indexDir = new File(DISC_URL); //索引目录 Directory dir=FSDirectory.open(indexDir); //根据索引目录创建读索引对象 IndexReader reader = IndexReader.open(dir); //搜索对象创建 IndexSearcher searcher = new IndexSearcher(reader); QueryParser queryParser = new MultiFieldQueryParser(version, filedStr, analyzer); Query query = queryParser.parse(queryStr); ScoreDoc[] docs = searcher.search(query, 3).scoreDocs; printScoreDoc(docs, searcher); } public void printScoreDoc(ScoreDoc[] docs,IndexSearcher searcher)throws Exception{ for (int i = 0; i < docs.length; i++) { List<Fieldable> list = searcher.doc(docs[i].doc).getFields(); for (Fieldable fieldable : list) { String fieldName = fieldable.name(); String fieldValue = fieldable.stringValue(); System.out.println(fieldName+" : "+fieldValue); } } } }
package com.tray.indexData; import java.sql.SQLException; import org.apache.lucene.document.Document; import org.apache.lucene.document.Field; import com.mysql.jdbc.Connection; import com.mysql.jdbc.ResultSet; import com.mysql.jdbc.Statement; public class IndexFile { private static Connection conn = null; private static Statement stmt = null; private final int NUM=500000; private LuceneSearch ls; private long count=0; public ResultSet deal6SourceTable(String tableName) throws SQLException{ String sql = "SELECT distinct `NAME`,SKYDRIVER_NAME,USERNAME,SHARE_TIME,DESCRIB,TYPE_ID,ID,URL FROM "+tableName+" where STATUS=1 and TYPE_ID !='-1' and (TYPE_NAME is null or TYPE_NAME!=1) limit "+NUM; //System.out.println(sql); ResultSet rs = (ResultSet) stmt.executeQuery(sql); return rs; } public void update6SourceTable(String tableName) throws SQLException{ Statement st = (Statement) conn.createStatement(); String sql = "update "+tableName+" set TYPE_NAME=1 where STATUS=1 and TYPE_ID !='-1' and (TYPE_NAME is null or TYPE_NAME!=1) limit "+NUM; //System.out.println("update"+sql); try { st.executeUpdate(sql); } catch (SQLException e) { e.printStackTrace(); } } public void indexInit(){//数据库+lcene初始化 conn = (Connection) JdbcUtil.getConnection(); if(conn == null) { try { throw new Exception("数据库连接失败!"); } catch (Exception e) { e.printStackTrace(); } } ls=new LuceneSearch(); try { ls.init(); } catch (Exception e2) { e2.printStackTrace(); } } public void indexEnd(){//数据库+lcene关闭 ls.closeWriter(); try { conn.close();//关闭数据库 } catch (SQLException e) { e.printStackTrace(); } } public void Index6Data() throws SQLException{ try { stmt = (Statement) conn.createStatement(); } catch (SQLException e1) { e1.printStackTrace(); } ResultSet r1=null; ResultSet r2=null; ResultSet r3=null; ResultSet r4=null; ResultSet r5=null; ResultSet r6=null; boolean stop=false; do{ r1=deal6SourceTable("film_and_tv_info"); stop=this.createIndex(r1,ls,"1"); //给数据库创建索引,此处执行一次,不要每次运行都创建索引,以后数据有更新可以后台调用更新索引 if(!stop){ ls.commit();//加个判断条件 } //System.out.println("stop"+stop); }while(!stop); stop=false; do{ r2=deal6SourceTable("music_and_mv_info"); stop=this.createIndex(r2,ls,"2"); //给数据库创建索引,此处执行一次,不要每次运行都创建索引,以后数据有更新可以后台调用更新索引 if(!stop){ ls.commit();//加个判断条件 } }while(!stop); stop=false; do{ r3=deal6SourceTable("e_book_info"); stop=this.createIndex(r3,ls,"3"); //给数据库创建索引,此处执行一次,不要每次运行都创建索引,以后数据有更新可以后台调用更新索引 if(!stop){ ls.commit();//加个判断条件 } }while(!stop); stop=false; do{ r4=deal6SourceTable("bt_file_info"); stop=this.createIndex(r4,ls,"4"); //给数据库创建索引,此处执行一次,不要每次运行都创建索引,以后数据有更新可以后台调用更新索引 if(!stop){ ls.commit();//加个判断条件 } }while(!stop); stop=false; do{ r5=deal6SourceTable("characteristic_software_info"); stop=this.createIndex(r5,ls,"5"); //给数据库创建索引,此处执行一次,不要每次运行都创建索引,以后数据有更新可以后台调用更新索引 if(!stop){ ls.commit();//加个判断条件 } }while(!stop); stop=false; do{ r6=deal6SourceTable("source_code_info"); stop=this.createIndex(r6,ls,"6"); //给数据库创建索引,此处执行一次,不要每次运行都创建索引,以后数据有更新可以后台调用更新索引 if(!stop){ ls.commit();//加个判断条件 } }while(!stop); stop=false; } public ResultSet deal2Share(String tableName) throws SQLException{ String sql = "SELECT distinct NAME,SKYDRIVER_NAME,USERNAME,SHARE_TIME,DESCRIB,TYPE_ID,ID,SHORTURL from "+tableName+" where STATUS=1 and FS_ID ='1' limit "+NUM; //利用FS_ID这个字段,没什么用处 ResultSet rs = (ResultSet) stmt.executeQuery(sql); return rs; } public ResultSet deal3Share(String tableName) throws SQLException{ String sql = "SELECT distinct title,channel,uid,ctime,description,port,id,shorturl from "+tableName+" where name ='1' limit "+NUM; ResultSet rs = (ResultSet) stmt.executeQuery(sql); return rs; } public void Index3Data() throws SQLException{ try { stmt = (Statement) conn.createStatement(); } catch (SQLException e1) { e1.printStackTrace(); } ResultSet r1=null; ResultSet r2=null; ResultSet r3=null; boolean stop=false; do{ r1=deal2Share("share1"); stop=this.createIndex(r1,ls,"7"); //给数据库创建索引,此处执行一次,不要每次运行都创建索引,以后数据有更新可以后台调用更新索引 if(!stop){ ls.commit();//加个判断条件 } //System.out.println("stop"+stop); }while(!stop); stop=false; do{ r2=deal2Share("share2"); stop=this.createIndex(r2,ls,"8"); //给数据库创建索引,此处执行一次,不要每次运行都创建索引,以后数据有更新可以后台调用更新索引 if(!stop){ ls.commit();//加个判断条件 } }while(!stop); stop=false; do{ r3=deal3Share("share3"); stop=this.createIndex(r3,ls,"9"); //给数据库创建索引,此处执行一次,不要每次运行都创建索引,以后数据有更新可以后台调用更新索引 if(!stop){ ls.commit();//加个判断条件 } }while(!stop); stop=false; } public void update2ShareTable(String tableName) throws SQLException{ Statement st = (Statement) conn.createStatement(); String sql = "update "+tableName+" set FS_ID=0 where STATUS=1 and FS_ID ='1' limit "+NUM; //利用FS_ID这个字段,没什么用处 //System.out.println("update"+sql); try { st.executeUpdate(sql); } catch (SQLException e) { e.printStackTrace(); } } public void update3ShareTable(String tableName) throws SQLException{ Statement st = (Statement) conn.createStatement(); String sql = "update "+tableName+" set name=0 where name ='1' limit "+NUM; //System.out.println("update"+sql); try { st.executeUpdate(sql); } catch (SQLException e) { e.printStackTrace(); } } public boolean createIndex(ResultSet rs,LuceneSearch ls,String mark) { try { String tableName=null; if(mark.equals("1")){ tableName="film_and_tv_info"; } if(mark.equals("2")){ tableName="music_and_mv_info"; } if(mark.equals("3")){ tableName="e_book_info"; } if(mark.equals("4")){ tableName="bt_file_info"; } if(mark.equals("5")){ tableName="characteristic_software_info"; } if(mark.equals("6")){ tableName="source_code_info"; } if(mark.equals("7")){ tableName="share1"; } if(mark.equals("8")){ tableName="share2"; } if(mark.equals("9")){ tableName="share3"; } boolean isNull=rs.next(); //System.out.println("hehe"+isNull); if(isNull==false){ return true;//处理完毕 } while(isNull){ if(Integer.parseInt(mark)>=1&&Integer.parseInt(mark)<=8){ Document doc = new Document(); //System.out.println("name"+rs.getString("NAME")); Field name = new Field("name",rs.getString("NAME"),Field.Store.YES,Field.Index.ANALYZED); String skName=rs.getString("SKYDRIVER_NAME"); if(skName==null){ skName="百度"; } Field skydirverName = new Field("skydirverName",skName, Field.Store.YES,Field.Index.NOT_ANALYZED); Field username = new Field("username",rs.getString("USERNAME"),Field.Store.YES, Field.Index.ANALYZED); Field shareTime = new Field("shareTime",rs.getString("SHARE_TIME"), Field.Store.YES,Field.Index.NOT_ANALYZED); String desb=rs.getString("DESCRIB"); if(desb==null){ desb="-1"; } Field describ = new Field("describ",desb,Field.Store.NO,Field.Index.NOT_ANALYZED); Field typeId = new Field("typeId",rs.getString("TYPE_ID"), Field.Store.YES,Field.Index.NOT_ANALYZED); Field id = new Field("id",rs.getString("ID"),Field.Store.YES,Field.Index.NOT_ANALYZED); Field url =null; if(Integer.parseInt(mark)>=7&&Integer.parseInt(mark)<=8){ url = new Field("url",rs.getString("SHORTURL"), Field.Store.YES,Field.Index.ANALYZED); } else{ url = new Field("url",rs.getString("URL"), Field.Store.YES,Field.Index.ANALYZED); } doc.add(name); doc.add(skydirverName); doc.add(username); doc.add(shareTime); doc.add(describ); doc.add(typeId); doc.add(id); doc.add(url); ls.singleUpdate(doc);//用跟新更为合适 isNull=rs.next(); } else{ Document doc = new Document(); //System.out.println("title"+rs.getString("title")); Field name = new Field("name",rs.getString("title"),Field.Store.YES,Field.Index.ANALYZED); String skName=rs.getString("channel"); Field skydirverName = new Field("skydirverName",skName, Field.Store.YES,Field.Index.NOT_ANALYZED); Field username = new Field("username",rs.getString("uid"),Field.Store.YES, Field.Index.ANALYZED); Field shareTime = new Field("shareTime",rs.getString("ctime"), Field.Store.YES,Field.Index.NOT_ANALYZED); String desb=rs.getString("description"); if(desb==null){ desb="-1"; } Field describ = new Field("describ",desb,Field.Store.NO,Field.Index.NOT_ANALYZED); Field typeId = new Field("typeId",rs.getString("port"), Field.Store.YES,Field.Index.NOT_ANALYZED); Field id = new Field("id",rs.getString("id"),Field.Store.YES,Field.Index.NOT_ANALYZED); Field url = new Field("url",rs.getString("shorturl"), Field.Store.YES,Field.Index.ANALYZED); doc.add(name); doc.add(skydirverName); doc.add(username); doc.add(shareTime); doc.add(describ); doc.add(typeId); doc.add(id); doc.add(url); ls.singleUpdate(doc);//用跟新更为合适 isNull=rs.next(); } count=count+1; } if(Integer.parseInt(mark)>=1&&Integer.parseInt(mark)<=6){ update6SourceTable(tableName);//处理完成后做标志 } else if(Integer.parseInt(mark)>=7&&Integer.parseInt(mark)<=8){ update2ShareTable(tableName);//处理完成后做标志 } else{ update3ShareTable(tableName);//处理完成后做标志 } System.out.println("Has index "+count+"条数据,数据来自表"+tableName); } catch (Exception e) { e.printStackTrace(); } return false; } }
package com.tray.indexData; import java.sql.SQLException; public class Application { public static void main(String[] args){ /*IndexFile indexFile=new IndexFile(); indexFile.indexInit(); try { indexFile.Index6Data(); } catch (SQLException e1) { e1.printStackTrace(); } indexFile.indexEnd();*/ IndexFile indexFile1=new IndexFile(); indexFile1.indexInit(); try { indexFile1.Index3Data(); } catch (SQLException e1) { e1.printStackTrace(); } indexFile1.indexEnd(); LuceneSearch lch=new LuceneSearch(); try { long a = System.currentTimeMillis(); lch.highLightSearch("name", "flv", 1,3); long b = System.currentTimeMillis(); long c = b - a; System.out.println("[高级检索花费时间:" + c + "毫秒]"); } catch (Exception e) { e.printStackTrace(); } } }
以上是关于java中文分词算法的主要内容,如果未能解决你的问题,请参考以下文章
片段(Java) | 机试题+算法思路+考点+代码解析 2023
NLP为什么中文分词比英文分词更难?有哪些常用算法?(附代码)