<rt id="bn8ez"></rt>
<label id="bn8ez"></label>

  • <span id="bn8ez"></span>

    <label id="bn8ez"><meter id="bn8ez"></meter></label>

    隨筆-295  評論-26  文章-1  trackbacks-0
    字符串切分
    ?package demo.analysis;
    ?
    ?import java.io.IOException;
    ?
    ?import jeasy.analysis.MMAnalyzer;
    ?
    ?public class Segment?
    ?{
    ????????
    ???? public static void main(String[] args)?
    ???? {
    ???????? String text = "據(jù)路透社報道,印度尼西亞社會事務(wù)部一官員星期二(29日)表示,"
    ??????????????? + "日惹市附近當(dāng)?shù)貢r間27日晨5時53分發(fā)生的里氏6.2級地震已經(jīng)造成至少5427人死亡,"
    ??????????????? + "20000余人受傷,近20萬人無家可歸。";?
    ?????????
    ???????? MMAnalyzer analyzer = new MMAnalyzer();
    ???????? try?
    ???????? {
    ???????????????? System.out.println(analyzer.segment(text, " | "));
    ???????? }?
    ???????? catch (IOException e)?
    ???????? {
    ???????????????? e.printStackTrace();
    ???????? }
    ???? }
    ?}
    ?
    生成效果:
    據(jù) | 路透社 | 報道 | 印度尼西亞 | 社會 | 事務(wù) | 部 | 官員 | 星期二 | 29日 | 表示 | 日惹 | 市 |
    附近 | 當(dāng)?shù)貢r間 | 27日 | 晨 | 5時 | 53分 | 發(fā)生 | 里氏 | 6.2級 | 地震 | 已經(jīng) | 造成 | 至少 |
    5427人 | 死亡 | 20000 | 余人 | 受傷 | 近 | 20萬人 | 無家可歸 |
    ?
    Lucene搜索
    ?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 = "據(jù)路透社報道,印度尼西亞社會事務(wù)部一官員星期二(29日)表示,"
    ???????????? + "日惹市附近當(dāng)?shù)貢r間27日晨5時53分發(fā)生的里氏6.2級地震已經(jīng)造成至少5427人死亡,"
    ???????????? + "20000余人受傷,近20萬人無家可歸。"; //檢索內(nèi)容
    ?
    ???????? //采用正向最大匹配的中文分詞算法
    ???????? 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("印度尼西亞 6.2級地震");//檢索詞
    ???????????? 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("內(nèi)容:" + hitDoc.get(fieldName));
    ???????????? }
    ?
    ???????????? isearcher.close();
    ???????????? directory.close();
    ???????? }?
    ???????? catch (Exception e)?
    ???????? {
    ???????????? e.printStackTrace();
    ???????? }???
    ???? }
    ?????
    ?}
    ?
    生成效果:
    命中:1
    內(nèi)容:據(jù)路透社報道,印度尼西亞社會事務(wù)部一官員星期二(29日)表示,日惹市附近當(dāng)?shù)貢r間27日晨5時53分發(fā)生的
    里氏6.2級地震已經(jīng)造成至少5427人死亡,20000余人受傷,近20萬人無家可歸。
    搜索詞加亮
    ?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 = "據(jù)路透社報道,印度尼西亞社會事務(wù)部一官員星期二(29日)表示,"
    ???????????? + "日惹市附近當(dāng)?shù)貢r間27日晨5時53分發(fā)生的里氏6.2級地震已經(jīng)造成至少5427人死亡,"
    ???????????? + "20000余人受傷,近20萬人無家可歸。"; //檢索內(nèi)容
    ?
    ???????? //采用正向最大匹配的中文分詞算法
    ???????? 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("印度尼西亞 6.2級地震");//檢索詞
    ???????????? 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("內(nèi)容:" + result);
    ???????????? }
    ?
    ???????????? isearcher.close();
    ???????????? directory.close();
    ???????? }
    ???????? catch (Exception e)
    ???????? {
    ???????????? e.printStackTrace();
    ???????? }
    ???? }
    ?
    ?}
    ?
    生成效果:
    命中:1
    內(nèi)容:據(jù)路透社報道,<B>印度尼西亞</B>社會事務(wù)部一官員星期二(29日)表示,日惹市附近當(dāng)?shù)貢r間27日晨
    5時53分發(fā)生的里氏<B>6.2級</B><B>地震</B>已經(jīng)造成至少5427人死亡,20000余人受傷,近20萬人無家可歸


    大盤預(yù)測 國富論
    posted on 2008-10-29 10:21 華夢行 閱讀(906) 評論(0)  編輯  收藏

    只有注冊用戶登錄后才能發(fā)表評論。


    網(wǎng)站導(dǎo)航:
     
    主站蜘蛛池模板: 五月天国产成人AV免费观看| 老湿机一区午夜精品免费福利 | 77777亚洲午夜久久多喷| 特级毛片爽www免费版| 亚洲国产成人五月综合网| 特级毛片aaaa级毛片免费| 亚洲国产成人乱码精品女人久久久不卡| 自拍偷自拍亚洲精品播放| 免费人成视频x8x8入口| 特级毛片A级毛片100免费播放| 免费在线不卡视频| 一个人晚上在线观看的免费视频 | 亚洲成AV人片天堂网无码| 久久成人免费大片| 亚洲精彩视频在线观看| 亚洲人成网站免费播放| 亚洲精品成a人在线观看夫| 国产在线观看免费不卡 | 99免费在线观看视频| 亚洲最大中文字幕| 免费无码一区二区三区蜜桃大| 蜜芽亚洲av无码一区二区三区| 亚洲国产成人久久综合野外| 99久久免费国产特黄| 亚洲熟妇av一区二区三区下载| 成人a免费α片在线视频网站| 色妞www精品视频免费看| 国产国拍亚洲精品mv在线观看 | 国产男女猛烈无遮挡免费视频| 七次郎成人免费线路视频| 亚洲阿v天堂在线| 欧美三级在线电影免费| 男女猛烈激情xx00免费视频| 久久久亚洲欧洲日产国码农村| 57PAO成人国产永久免费视频 | 亚洲AV无码乱码在线观看代蜜桃 | 亚洲精品无码中文久久字幕| 四虎永久免费影院在线| 99久久成人国产精品免费| 亚洲国产综合在线| 亚洲成A人片77777国产|