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 = "據路透社報道,印度尼西亞社會事務部一官員星期二(29日)表示," |
|
??????????????? + "日惹市附近當地時間27日晨5時53分發生的里氏6.2級地震已經造成至少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 | 路透社 | 報道 | 印度尼西亞 | 社會 | 事務 | 部 | 官員 | 星期二 | 29日 | 表示 | 日惹 | 市 |
附近 | 當地時間 | 27日 | 晨 | 5時 | 53分 | 發生 | 里氏 | 6.2級 | 地震 | 已經 | 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 = "據路透社報道,印度尼西亞社會事務部一官員星期二(29日)表示," |
|
???????????? + "日惹市附近當地時間27日晨5時53分發生的里氏6.2級地震已經造成至少5427人死亡," |
|
???????????? + "20000余人受傷,近20萬人無家可歸。"; //檢索內容 |
|
?
|
|
???????? //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("內容:" + hitDoc.get(fieldName)); |
|
???????????? } |
|
?
|
|
???????????? isearcher.close(); |
|
???????????? directory.close(); |
|
???????? }? |
|
???????? catch (Exception e)? |
|
???????? { |
|
???????????? e.printStackTrace(); |
|
???????? }??? |
|
???? } |
|
?????
|
|
?} |
|
?
|
|
生成效果: |
|
|
|
命中:1 |
|
內容:據路透社報道,印度尼西亞社會事務部一官員星期二(29日)表示,日惹市附近當地時間27日晨5時53分發生的 里氏6.2級地震已經造成至少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 = "據路透社報道,印度尼西亞社會事務部一官員星期二(29日)表示," |
|
???????????? + "日惹市附近當地時間27日晨5時53分發生的里氏6.2級地震已經造成至少5427人死亡," |
|
???????????? + "20000余人受傷,近20萬人無家可歸。"; //檢索內容 |
|
?
|
|
???????? //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("內容:" + result); |
|
???????????? } |
|
?
|
|
???????????? isearcher.close(); |
|
???????????? directory.close(); |
|
???????? } |
|
???????? catch (Exception e) |
|
???????? { |
|
???????????? e.printStackTrace(); |
|
???????? } |
|
???? } |
|
?
|
|
?} |
|
?
|
|
生成效果: |
|
|
命中:1 |
|
內容:據路透社報道,<B>印度尼西亞</B>社會事務部一官員星期二(29日)表示,日惹市附近當地時間27日晨 5時53分發生的里氏<B>6.2級</B><B>地震</B>已經造成至少5427人死亡,20000余人受傷,近20萬人無家可歸 |