LUCENE05---Highlighter

In front of the word breaker, but we are in the search is not another effect is highlighted and a piece of text. So here we are to introduce highlighter.

Highlighter:

You can intercept a piece of text and have the keyword highlighted (by specifying a prefix and suffix, because it is displayed in a Web page, specifying <font color= ' Red ' ></font> will appear in red on the page).

FirstLucene03ByHighlighter.java:Java Code   package com.iflytek.lucene;       import java.io.file;       import org.apache.lucene.analysis.analyzer;    import org.apache.lucene.analysis.standard.standardanalyzer;    import org.apache.lucene.document.document;    import org.apache.lucene.index.indexreader;    import org.apache.lucene.index.indexwriter;    import org.apache.lucene.index.indexwriterconfig;    import org.apache.lucene.queryparser.multifieldqueryparser;    import org.apache.lucene.queryparser.queryparser;    import org.apache.lucene.search.filter;    import org.apache.lucene.search.indexsearcher;    import org.apache.lucene.search.query;    import org.apache.lucene.search.scoredoc;    import org.apache.lucene.search.topdocs;    import org.apache.lucene.search.highlight.formatter;    import org.apache.lucene.search.highlight.fragmenter;    import org.apache.lucene.search.highlight.highlighter;    import org.apache.lucene.search.highlight.queryscorer;    import org.apache.lucene.search.highlight.scorer;    import org.apache.lucene.search.highlight.simplefragmenter;    import org.apache.lucene.search.highlight.simplehtmlformatter;    import org.apache.lucene.store.directory;    import org.apache.lucene.store.fsdirectory;    import org.apache.lucene.store.ramdirectory;    import org.apache.lucene.util.version;      /**    *  @author  xudongwang 2012-2-10    *    & nbsp;*         email:xdwangiflytek@gmail.com    */    PUBLIC&NBSP;CLASS&NBSP firstlucene03byhighlighter {          /**         *  source file path        */       private  String filePath01 =  "f:\\workspaces\\workspacese\\blogdemo\\lucenedatasource\\ HelloLucene01.txt ";           /**        *  index path         */       private String indexPath =  " F:\\workspaces\\workspacese\\blogdemo\\luceneindex ";           /**        *  word breaker, here we use the default word breaker , the standard Analyzer (several, but the support for Chinese is not good)        */       private  Analyzer analyzer = new standardanalyzer (version.lucene_35);           private directory ramdir = null;           /**        *  search         *         *  @param  querystr         *             Search Keywords        *  @throws  exception        */       public void search (STRING&NBSP;QUERYSTR)  throws exception {               // 1, parsing the text to be searched into a query object             String[] fields = {  "name",  " Content " };            QueryParser queryParser = new  Multifieldqueryparser (Version.lucene_35, fields, analyzer);            query query = queryparser.parse ( QUERYSTR);               // 2, querying             indexreader indexreader = indexreader.open (RamDir);            indexsearcher indexsearcher = new  indexsearcher (Indexreader);            Filter filter = null;            TopDocs topDocs =  Indexsearcher.search (query, filter, 10000);            system.out.println ("A total of" " +  topdocs.totalhits +  "" matches results ");//  note that the match result here is the number of documents, not the number of search results included in the document               //  Preparing the Highlighter &NBsp;          Formatter formatter = new  Simplehtmlformatter ("<font color= ' Red ' >",  "</font>");            Scorer scorer = new  Queryscorer (query);            Highlighter highlighter = new  Highlighter (formatter, scorer);               fragmenter fragmenter =  new simplefragmenter (x);//  specify 10 characters             highlighter.settextfragmenter (Fragmenter);//  decide whether to generate a summary, and how long the summary                // 3, take out data, and print results             for  (Scoredoc scoredoc : topdocs.scoredocs)  {                int docSn = scoreDoc.doc;//  Document Internal numbering                 document document =  indexsearcher.doc (DOCSN);//  remove the corresponding document according to the document number                    //  Highlight processing                 //  returns the highlighted result, which returns null if no keyword appears in the current property value                 String highlighterStr =  Highlighter.getbestfragment (analyzer,  "Content",  document.get ("content"));                                 if  (highlighterstr == null)  {                    string content = document.get ("content");                     Int endindex = math.min (20, content.length ());                     Highlighterstr=content.substring (0, endindex);//Up to the first 20 characters                 }                 document.getfield ("Content"). SetValue (HIGHLIGHTERSTR);                 File2document.printdocumentinfo (document);//  print out documentation Information             }           }            /**   &Nbsp;    *  optimization creates an index that exists in memory and disk with the use of        *         *  @throws  exception        */       public void createindexbyyouhua ()  throws exception {            file indexfile = new file (IndexPath) ;            directory fsdir = fsdirectory.open ( Indexfile);               // 1, on startup, reads the index from the disk into memory             ramdir = new ramdirectory (FsDir);            indexwriterconfig ramconf = new  indexwriterconfig (Version.lucene_35, analyzer);               //  operating in-memory indexes            indexwriter when running programs  ramindexwriter = new indexwriter (ramdir, ramconf);            Document document =  File2document.file2document (FILEPATH01);            ramindexwriter.adddocument (document);            ramindexwriter.close ();               // 2, saving an in-memory index to disk on exit            IndexWriterConfig fsConf = new  Indexwriterconfig (Version.lucene_35, analyzer);            indexwriter fsindexwriter = new  indexwriter (fsdir, fsconf);            fsindexwriter.addIndexes (ramdir);//  Merge all index data from several other index libraries into the current index library             Fsindexwriter.commit ();            // fsindexwriter.optimize ();//optimize the index file, Thus reducing IO operation            fsindexwriter.forcemerge (1);            fsindexwriter.close ();        }           public static  Void main (String[] args)  throws exception {            firstlucene03byhighlighter lucene = new firstlucene03byhighlighter ();            lucene.createindexbyyouhua ();            lucene.search ("Iteye");        }      }  

Package Com.iflytek.lucene;import Java.io.file;import Org.apache.lucene.analysis.analyzer;import Org.apache.lucene.analysis.standard.standardanalyzer;import Org.apache.lucene.document.document;import Org.apache.lucene.index.indexreader;import Org.apache.lucene.index.indexwriter;import Org.apache.lucene.index.indexwriterconfig;import Org.apache.lucene.queryparser.multifieldqueryparser;import Org.apache.lucene.queryparser.queryparser;import Org.apache.lucene.search.filter;import Org.apache.lucene.search.indexsearcher;import Org.apache.lucene.search.query;import Org.apache.lucene.search.scoredoc;import Org.apache.lucene.search.topdocs;import Org.apache.lucene.search.highlight.formatter;import Org.apache.lucene.search.highlight.fragmenter;import Org.apache.lucene.search.highlight.highlighter;import Org.apache.lucene.search.highlight.queryscorer;import Org.apache.lucene.search.highlight.scorer;import Org.apache.lucene.search.highlight.simplefragmenter;import Org.apache.lucene.search.highligHt. Simplehtmlformatter;import Org.apache.lucene.store.directory;import Org.apache.lucene.store.fsdirectory;import         Org.apache.lucene.store.ramdirectory;import org.apache.lucene.util.version;/** * @author Xudongwang 2012-2-10 * * Email:xdwangiflytek@gmail.com */public class Firstlucene03byhighlighter {/** * source file path */private String filePath01 = "F	: \\Workspaces\\workspaceSE\\BlogDemo\\luceneDatasource\\HelloLucene01.txt ";	/** * Index Path */private String Indexpath = "F:\\workspaces\\workspacese\\blogdemo\\luceneindex";	/** * Word breaker, here we use the default word breaker, the standard Analyzer (several, but the support for Chinese is not good) */Private Analyzer Analyzer = new StandardAnalyzer (version.lucene_35);	Private Directory ramdir = null; /** * Search * * * @param querystr * Search keywords * @throws Exception * * * public void Search (String querystr) throws		Exception {///1, parse the text to be searched into the query object string[] fields = {"Name", "content"};		Queryparser queryparser = new Multifieldqueryparser (version.lucene_35, fields, analyzer); Query query = Queryparser. Parse (QUERYSTR);		2, the query Indexreader Indexreader = Indexreader.open (Ramdir);		Indexsearcher indexsearcher = new Indexsearcher (Indexreader);		Filter filter = NULL;		Topdocs Topdocs = indexsearcher.search (query, filter, 10000); System.out.println ("A total of" "+ Topdocs.totalhits +" "matches the result");//Note that the matching result here refers to the number of documents, not the number of search results contained in the document//Prepare the highlighter Formatter forma		tter = new Simplehtmlformatter ("<font color= ' Red ' >", "</font>");		Scorer scorer = new Queryscorer (query);		Highlighter highlighter = new Highlighter (formatter, scorer); Fragmenter fragmenter = new Simplefragmenter (10);//Specify 10 characters highlighter.settextfragmenter (fragmenter);//decide whether to generate a summary, As well as the summary how long//3, take out the data and print the result for (Scoredoc scoreDoc:topDocs.scoreDocs) {int DOCSN = scoredoc.doc;//Document Internal number Cument = Indexsearcher.doc (DOCSN);//The corresponding document is taken out according to the document number//to highlight//return the highlighted result, if the current attribute value does not appear in the keyword, will return a null String highlighters						TR = highlighter.getbestfragment (Analyzer, "content", Document.get ("content")); if (Highlighterstr = = NULL) {String content = document.get ("content");				int endIndex = Math.min (+, content.length ());			Highlighterstr=content.substring (0, EndIndex);//Up to the first 20 characters} Document.getfield ("Content"). SetValue (HIGHLIGHTERSTR); File2document.printdocumentinfo (documents);//Print Out Document Information}}/** * Optimize the creation of indexes, the index exists in memory and disk with the use of * * @throws Exception */publi		c void Createindexbyyouhua () throws Exception {file Indexfile = new File (Indexpath);		Directory Fsdir = Fsdirectory.open (indexfile);		1. When starting, read the index in the disk into memory Ramdir = new Ramdirectory (fsdir);		Indexwriterconfig ramconf = new Indexwriterconfig (version.lucene_35, analyzer);		Run the program when the index in memory is indexwriter ramindexwriter = new IndexWriter (Ramdir, ramconf);		Document document = File2document.file2document (FILEPATH01);		Ramindexwriter.adddocument (document);		Ramindexwriter.close ();		2. Save the In-memory index to disk when exiting Indexwriterconfig fsconf = new Indexwriterconfig (version.lucene_35, analyzer);		IndexWriter fsindexwriter = new IndexWriter (Fsdir, fsconf); FsINdexwriter.addindexes (Ramdir);//merge all index data from several other index libraries into the current index library fsindexwriter.commit ();		Fsindexwriter.optimize ();//optimize the index file to reduce the IO operation Fsindexwriter.forcemerge (1);	Fsindexwriter.close (); } public static void Main (string[] args) throws Exception {Firstlucene03byhighlighter Lucene = new Firstlucene03byhighli		Ghter ();		Lucene.createindexbyyouhua ();	Lucene.search ("Iteye"); }}

Operation Result:

There are a total of "1" matching results Name-->hellolucene01.txt Content-in <font color= ' Red ' >iteye</font> blog Path-->f:\workspaces\workspacese\blogdemo\lucenedatasource\hellolucene01.txt Size-->84