Examples with Document org.apache.lucene.document.Document used on opensource projects

Example 96 with Document

use of org.apache.lucene.document.Document in project ansj_seg by NLPchina.

the class HeightLightTest method search.

private static void search(Analyzer analyzer, Query query) throws IOException {
    DirectoryReader directoryReader = DirectoryReader.open(directory);
    // 查询索引
    IndexSearcher isearcher = new IndexSearcher(directoryReader);
    System.out.println(query);
    TopDocs hits = isearcher.search(query, 5);
    for (int i = 0; i < hits.scoreDocs.length; i++) {
        int docId = hits.scoreDocs[i].doc;
        Document document = isearcher.doc(docId);
        System.out.println(toHighlighter(analyzer, query, document));
    }
}

Example 97 with Document

use of org.apache.lucene.document.Document in project ansj_seg by NLPchina.

the class HeightLightTest method index.

private static void index(Analyzer analysis, String content) throws CorruptIndexException, IOException {
    Document doc = new Document();
    IndexWriter iwriter = new IndexWriter(directory, new IndexWriterConfig(analysis));
    doc.add(new TextField("text", content, Field.Store.YES));
    iwriter.addDocument(doc);
    iwriter.commit();
    iwriter.close();
}

Example 98 with Document

use of org.apache.lucene.document.Document in project ansj_seg by NLPchina.

the class IndexTest method search.

private void search(Analyzer queryAnalyzer, Directory directory, String queryStr) throws CorruptIndexException, IOException, ParseException {
    IndexSearcher isearcher;
    DirectoryReader directoryReader = DirectoryReader.open(directory);
    // 查询索引
    isearcher = new IndexSearcher(directoryReader);
    QueryParser tq = new QueryParser("text", queryAnalyzer);
    Query query = tq.parse(queryStr);
    System.out.println(query);
    TopDocs hits = isearcher.search(query, 5);
    System.out.println(queryStr + ":共找到" + hits.totalHits + "条记录!");
    for (int i = 0; i < hits.scoreDocs.length; i++) {
        int docId = hits.scoreDocs[i].doc;
        Document document = isearcher.doc(docId);
        System.out.println(toHighlighter(queryAnalyzer, query, document));
    }
}

Example 99 with Document

use of org.apache.lucene.document.Document in project ansj_seg by NLPchina.

the class IndexTest method search.

private void search(Analyzer queryAnalyzer, Directory directory, String queryStr) throws CorruptIndexException, IOException, ParseException {
    IndexSearcher isearcher;
    DirectoryReader directoryReader = DirectoryReader.open(directory);
    // 查询索引
    isearcher = new IndexSearcher(directoryReader);
    QueryParser tq = new QueryParser("text", queryAnalyzer);
    Query query = tq.parse(queryStr);
    System.out.println(query);
    TopDocs hits = isearcher.search(query, 5);
    System.out.println(queryStr + ":共找到" + hits.totalHits + "条记录!");
    for (int i = 0; i < hits.scoreDocs.length; i++) {
        int docId = hits.scoreDocs[i].doc;
        Document document = isearcher.doc(docId);
        System.out.println(toHighlighter(queryAnalyzer, query, document));
    }
}

Example 100 with Document

use of org.apache.lucene.document.Document in project ansj_seg by NLPchina.

the class PhraseTest method main.

public static void main(String[] args) throws IOException, ParseException {
    DicLibrary.insert(DicLibrary.DEFAULT, "上网人");
    DicLibrary.insert(DicLibrary.DEFAULT, "网人");
    AnsjAnalyzer ansjAnalyzer = new AnsjAnalyzer(AnsjAnalyzer.TYPE.index_ansj);
    TokenStream tokenStream = ansjAnalyzer.tokenStream("上网人员测试", "test");
    while (tokenStream.incrementToken()) {
        System.out.println(tokenStream.getAttribute(CharTermAttribute.class));
    }
    IndexWriterConfig config = new IndexWriterConfig(ansjAnalyzer);
    IndexWriter writer = new IndexWriter(new RAMDirectory(), config);
    Document doc = new Document();
    doc.add(new TextField("test", "上网人员测试", Field.Store.YES));
    writer.addDocument(doc);
    writer.commit();
    IndexSearcher searcher = new IndexSearcher(DirectoryReader.open(writer));
    System.out.println(searcher.count(new TermQuery(new Term("test", "网人"))));
    Query q = new QueryParser("test", new AnsjAnalyzer(AnsjAnalyzer.TYPE.index_ansj)).parse("\"上网人\"");
    System.out.println(q);
    System.out.println(searcher.count(q));
}