{"rsdb":{"rid":"87954","subhead":"","postdate":"0","aid":"65319","fid":"76","uid":"1","topic":"1","content":"
\n \u5206\u8bcd\u7684\u57fa\u672c\u539f\u7406\uff1a \n
\n 1\u3001\u5206\u8bcd\u662f\u7528\u6765\u5bf9\u6587\u672c\u6309\u8bed\u8a00\u7279\u5f81\u6309\u7b97\u6cd5\u8fdb\u884c\u8fc7\u6ee4\u3001\u5206\u7ec4\u5904\u7406\u7684\u4e00\u79cd\u6280\u672f\u3002\n <\/div> \n
\n 2\u3001\u5206\u8bcd\u7684\u5bf9\u8c61\u662f\u6587\u672c\uff0c\u800c\u4e0d\u662f\u56fe\u50cf\u52a8\u753b\u811a\u672c\u7b49\u7b49\u3002\n <\/div> \n
\n 3\u3001\u5206\u8bcd\u7684\u65b9\u5f0f\u5c31\u662f\u8fc7\u6ee4\u548c\u5206\u7ec4\u3002\n <\/div> \n
\n 4\u3001\u8fc7\u6ee4\u4e3b\u8981\u628a\u6587\u672c\u4e2d\u90a3\u4e9b\u6ca1\u6709\u5b9e\u9645\u610f\u4e49\u7684\u5b57\u6216\u8bcd\u8fc7\u6ee4\u6389\u3002\n <\/div> \n
\n 5\u3001\u5206\u7ec4\u5c31\u662f\u6309\u7167\u201d\u5206\u8bcd\n \u6570\u636e\u5e93<\/a>\u201c\u5185\u5df2\u6dfb\u52a0\u597d\u7684\u8bcd\uff0c\u8fdb\u884c\u5339\u914d\u3002\n <\/div> \n
\n \n <\/div> \n
\n \u4e0b\u9762\u6765\u770bLucene\u5206\u8bcd\u5668\u7684\u4f7f\u7528\n <\/div> \n
\n [java<\/a>] \n <\/div> \n
\n package com.qianyan.analyzer; \n <\/div> \n
\n \n <\/div> \n
\n import java<\/a>.io.IOException; \n <\/div> \n
\n import java.io.StringReader; \n <\/div> \n
\n \n <\/div> \n
\n import org.apache.lucene.analysis.Analyzer; \n <\/div> \n
\n import org.apache.lucene.analysis.SimpleAnalyzer; \n <\/div> \n
\n import org.apache.lucene.analysis.Token; \n <\/div> \n
\n import org.apache.lucene.analysis.TokenStream; \n <\/div> \n
\n import org.apache.lucene.analysis.WhitespaceAnalyzer; \n <\/div> \n
\n import org.apache.lucene.analysis.cjk.CJKAnalyzer; \n <\/div> \n
\n import org.apache.lucene.analysis.cn.ChineseAnalyzer; \n <\/div> \n
\n import org.apache.lucene.analysis.standard.StandardAnalyzer; \n <\/div> \n
\n \n <\/div> \n
\n public class TestAnalyzer { \n <\/div> \n
\n \n <\/div> \n
\n public static void main(String[] args) throws IOException { \n <\/div> \n
\n Analyzer analyzer = new StandardAnalyzer(); \/\/\u6807\u51c6 \u8fc7\u6ee4\u505c\u7528\u6b21 \n <\/div> \n
\n \/\/Analyzer analyzer = new SimpleAnalyzer(); \/\/\u7b80\u5355 \u8fc7\u6ee4\u7a7a\u683c\u548c\u7b26\u53f7 \n <\/div> \n
\n \/\/Analyzer analyzer = new WhitespaceAnalyzer(); \/\/\u8fc7\u6ee4\u7a7a\u683c \n <\/div> \n
\n \/\/Analyzer analyzer = new ChineseAnalyzer(); \/\/lucene\u4e0b\u7684\u4e2d\u6587\u5206\u8bcd\u5668 \u62c6\u5206\u6bcf\u4e2a\u5b57\u7b26\uff0c\u8fc7\u6ee4\u7b26\u53f7 \n <\/div> \n
\n \/\/Analyzer analyzer = new CJKAnalyzer(); \/\/\u4e2d\u6587 \u4e24\u5b57\u4e24\u5b57\u62c6\u5206 \u82f1\u6587\u548cstandard\u529f\u80fd\u4e00\u6837 \n <\/div> \n
\n String input = \"this is test lucene analyzer class!\"; \n <\/div> \n
\n TokenStream tokenStream = analyzer.tokenStream(\"\", new StringReader(input)); \n <\/div> \n
\n Token token = new Token(); \n <\/div> \n
\n while(null != tokenStream.next(token)) \n <\/div> \n
\n System.out.println(token.term()); \n <\/div> \n
\n } \n <\/div> \n
\n } \n <\/div> \n
\n \n <\/div> \n
\n \u5bf9\u4e8e\u521d\u5b66\u8005\uff0c\u6211\u4eec\u53ea\u9700\u8981\u638c\u63e1\u8fd9\u4e9b\u7ecf\u5178\u7684\u5206\u8bcd\u5668\u5c31\u8db3\u591f\u4e86\u3002\n <\/div> \n
\n \u4f46\u5728\u5b9e\u9645\u7684\u5f00\u53d1\u8fc7\u7a0b\u4e2d\uff0c\u6ee1\u8db3\u6211\u4eec\u9700\u8981\u5f97\uff0c\u662f\u4e00\u4e9b\u57fa\u4e8elucene\u5206\u8bcd\u4e4b\u4e0a\u7684\u7b2c\u4e09\u65b9\u4e2d\u6587\u5206\u8bcd\u5305\uff0c\u5728\u8fd9\u91cc\u6211\u4eec\u53ea\u4ecb\u7ecd \u201d\u5e96\u4e01\u5206\u8bcd\u5305\u201c\uff0c\u547d\u4ee4\u501f\u9274\u4e86\u201d\u5e96\u4e01\u89e3\u725b\u201c\u8fd9\u4e2a\u6210\u8bed\u3002\n <\/div> \n
\n \u5e96\u4e01\u89e3\u725b\uff0c\u6211\u56fd\u53e4\u4ee3\u6210\u8bed\uff0c\u51fa\u81ea\u300a\u5e84\u5b50\u300b\uff0c\u6bd4\u55bb\u7ecf\u8fc7\u53cd\u590d\u5b9e\u8df5\uff0c\u638c\u63e1\u4e86\u4e8b\u7269\u7684\u5ba2\u89c2\u89c4\u5f8b\uff0c\u505a\u4e8b\u5f97\u5fc3\u5e94\u624b\uff0c\u8fd0\u7528\u81ea\u5982\u3002\n <\/div> \n
\n \n <\/div> \n
\n \u89e3\u538b\u540e\u6211\u4eec\u9700\u8981\u5bf9\u9879\u76ee\u6dfb\u52a02\u4e2ajar\u5305\uff0c\u89e3\u538b\u76ee\u5f55\u4e0b\u7684paoding-analysis.jar \u548clib\u4e0b\u7684 commons-logging.jar \u3002\u4ee4\u628adic\u6587\u4ef6\u5939\u590d\u5236\u5230\u6211\u4eec\u7684\u9879\u76eesrc\u76ee\u5f55\u4e0b\u3002\n <\/div> \n
\n [java] \n <\/div> \n
\n package com.qianyan.analyzer; \n <\/div> \n
\n \n <\/div> \n
\n import java.io.IOException; \n <\/div> \n
\n import java.io.StringReader; \n <\/div> \n
\n \n <\/div> \n
\n import net.paoding.analysis.analyzer.PaodingAnalyzer; \n <\/div> \n
\n \n <\/div> \n
\n import org.apache.lucene.analysis.Analyzer; \n <\/div> \n
\n import org.apache.lucene.analysis.Token; \n <\/div> \n
\n import org.apache.lucene.analysis.TokenStream; \n <\/div> \n
\n \n <\/div> \n
\n public class TestPaodingAnalyzer { \n <\/div> \n
\n \n <\/div> \n
\n public static void main(String[] args) throws IOException { \n <\/div> \n
\n Analyzer analyzer = new PaodingAnalyzer(); \n <\/div> \n
\n String input = \"\u6211\u7231\u5317\u4eac\u5929\u5b89\u95e8\uff01\"; \n <\/div> \n
\n TokenStream ts = analyzer.tokenStream(\"\", new StringReader(input)); \n <\/div> \n
\n Token token = new Token(); \n <\/div> \n
\n while(null != (token = ts.next(null))) \n <\/div> \n
\n System.out.println(token.term()); \n <\/div> \n
\n } \n <\/div> \n
\n } \n <\/div> \n
\n \n <\/div> \n
\n \u5927\u5bb6\u901a\u8fc7\u8fd9\u4e2a\u4f8b\u5b50\u53ef\u4ee5\u770b\u5230\uff0cpaoding\u5206\u8bcd\u5668\u76f8\u5f53\u7684\u5f3a\u5927\uff0c\u5b83\u7684\u8bed\u6cd5\u5728\u6b64\u4e0d\u8fc7\u591a\u4ecb\u7ecd\uff0c\u6709\u5174\u8da3\u7684\u670b\u53cb\u53ef\u4ee5\u770b\u89e3\u538b\u540e\u7684\u4e2d\u6587\u64cd\u4f5c\u624b\u518c\u3002\n <\/div> \n
\n \u4e0b\u9762\u6765\u770b\u4e0b\u5b9e\u9645\u4e2d\u8fd0\u7528\n <\/div> \n
\n \u9996\u5148\u6839\u636epaoding\u5206\u8bcd\u5668\u5efa\u7acb\u7d22\u5f15\uff1a\n <\/div> \n
\n [java] \n <\/div> \n
\n package com.qianyan.index; \n <\/div> \n
\n \n <\/div> \n
\n import java.io.IOException; \n <\/div> \n
\n \n <\/div> \n
\n import net.paoding.analysis.analyzer.PaodingAnalyzer; \n <\/div> \n
\n \n <\/div> \n
\n import org.apache.lucene.analysis.Analyzer; \n <\/div> \n
\n import org.apache.lucene.document.Document; \n <\/div> \n
\n import org.apache.lucene.document.Field; \n <\/div> \n
\n import org.apache.lucene.index.IndexWriter; \n <\/div> \n
\n import org.apache.lucene.store.Directory; \n <\/div> \n
\n import org.apache.lucene.store.FSDirectory; \n <\/div> \n
\n \n <\/div> \n
\n public class TestPaodingIndex { \n <\/div> \n
\n \n <\/div> \n
\n public static void main(String[] args) throws IOException{ \n <\/div> \n
\n \n <\/div> \n
\n String[] ids = {\"1\", \"2\", \"3\", \"4\"}; \n <\/div> \n
\n ","orderid":"0","title":"\u81ea\u5df1\u52a8\u624b\u5199\u641c\u7d22\u5f15\u64ce\uff08\u5e38\u641c\u5427\u5386\u7a0b\u56db#\u5206\u8bcd#\uff09\uff08Java\u3001Lucene\u3001hadoop\uff09(\u4e00)","smalltitle":"","mid":"0","fname":"JAVA","special_id":"0","bak_id":"0","info":"0","hits":"1111","pages":"4","comments":"0","posttime":"2014-11-24 12:04:51","list":"1416801891","username":"admin","author":"","copyfrom":"","copyfromurl":"","titlecolor":"","fonttype":"0","titleicon":"0","picurl":"https:\/\/www.cppentry.com\/upload_files\/","ispic":"0","yz":"1","yzer":"","yztime":"0","levels":"0","levelstime":"0","keywords":"\u81ea\u5df1<\/A> \u624b\u5199<\/A> \u641c\u7d22\u5f15\u64ce<\/A> \u5e38\u641c\u5427<\/A> \u5386\u7a0b<\/A> #\u5206\u8bcd<\/A> Java<\/A> Lucene<\/A> hadoop<\/A>","jumpurl":"","iframeurl":"","style":"","template":"a:3:{s:4:\"head\";s:0:\"\";s:4:\"foot\";s:0:\"\";s:8:\"bencandy\";s:0:\"\";}","target":"0","ip":"114.215.104.12","lastfid":"0","money":"0","buyuser":"","passwd":"","allowdown":"","allowview":"","editer":"","edittime":"0","begintime":"0","endtime":"0","description":"\u81ea\u5df1\u52a8\u624b\u5199\u641c\u7d22\u5f15\u64ce\uff08\u5e38\u641c\u5427\u5386\u7a0b\u56db#\u5206\u8bcd#\uff09\uff08Java\u3001Lucene\u3001hadoop\uff09","lastview":"1703115353","digg_num":"4889","digg_time":"0","forbidcomment":"0","ifvote":"0","heart":"","htmlname":"","city_id":"0"},"page":"1"}