Search in sources :

Example 51 with QueryParser

use of org.apache.lucene.queryparser.classic.QueryParser in project elasticsearch by elastic.

the class TopHitsAggregatorTests method testInsideTerms.

/**
     * Tests {@code top_hits} inside of {@code terms}. While not strictly a unit test this is a fairly common way to run {@code top_hits}
     * and serves as a good example of running {@code top_hits} inside of another aggregation.
     */
public void testInsideTerms() throws Exception {
    Aggregation result;
    if (randomBoolean()) {
        result = testCase(new MatchAllDocsQuery(), terms("term").field("string").subAggregation(topHits("top").sort("string", SortOrder.DESC)));
    } else {
        Query query = new QueryParser("string", new KeywordAnalyzer()).parse("d^1000 c^100 b^10 a^1");
        result = testCase(query, terms("term").field("string").subAggregation(topHits("top")));
    }
    Terms terms = (Terms) result;
    // The "a" bucket
    TopHits hits = (TopHits) terms.getBucketByKey("a").getAggregations().get("top");
    SearchHits searchHits = (hits).getHits();
    assertEquals(2L, searchHits.getTotalHits());
    assertEquals("2", searchHits.getAt(0).getId());
    assertEquals("1", searchHits.getAt(1).getId());
    // The "b" bucket
    searchHits = ((TopHits) terms.getBucketByKey("b").getAggregations().get("top")).getHits();
    assertEquals(2L, searchHits.getTotalHits());
    assertEquals("3", searchHits.getAt(0).getId());
    assertEquals("1", searchHits.getAt(1).getId());
    // The "c" bucket
    searchHits = ((TopHits) terms.getBucketByKey("c").getAggregations().get("top")).getHits();
    assertEquals(1L, searchHits.getTotalHits());
    assertEquals("2", searchHits.getAt(0).getId());
    // The "d" bucket
    searchHits = ((TopHits) terms.getBucketByKey("d").getAggregations().get("top")).getHits();
    assertEquals(1L, searchHits.getTotalHits());
    assertEquals("3", searchHits.getAt(0).getId());
}
Also used : Aggregation(org.elasticsearch.search.aggregations.Aggregation) KeywordAnalyzer(org.apache.lucene.analysis.core.KeywordAnalyzer) QueryParser(org.apache.lucene.queryparser.classic.QueryParser) Query(org.apache.lucene.search.Query) MatchNoDocsQuery(org.apache.lucene.search.MatchNoDocsQuery) MatchAllDocsQuery(org.apache.lucene.search.MatchAllDocsQuery) Terms(org.elasticsearch.search.aggregations.bucket.terms.Terms) SearchHits(org.elasticsearch.search.SearchHits) MatchAllDocsQuery(org.apache.lucene.search.MatchAllDocsQuery)

Example 52 with QueryParser

use of org.apache.lucene.queryparser.classic.QueryParser in project ansj_seg by NLPchina.

the class IndexAndTest 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));
    }
}
Also used : IndexSearcher(org.apache.lucene.search.IndexSearcher) TopDocs(org.apache.lucene.search.TopDocs) QueryParser(org.apache.lucene.queryparser.classic.QueryParser) Query(org.apache.lucene.search.Query) DirectoryReader(org.apache.lucene.index.DirectoryReader) Document(org.apache.lucene.document.Document)

Example 53 with QueryParser

use of org.apache.lucene.queryparser.classic.QueryParser 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));
}
Also used : IndexSearcher(org.apache.lucene.search.IndexSearcher) TermQuery(org.apache.lucene.search.TermQuery) TokenStream(org.apache.lucene.analysis.TokenStream) Query(org.apache.lucene.search.Query) TermQuery(org.apache.lucene.search.TermQuery) Term(org.apache.lucene.index.Term) Document(org.apache.lucene.document.Document) RAMDirectory(org.apache.lucene.store.RAMDirectory) QueryParser(org.apache.lucene.queryparser.classic.QueryParser) CharTermAttribute(org.apache.lucene.analysis.tokenattributes.CharTermAttribute) AnsjAnalyzer(org.ansj.lucene5.AnsjAnalyzer) IndexWriter(org.apache.lucene.index.IndexWriter) TextField(org.apache.lucene.document.TextField) IndexWriterConfig(org.apache.lucene.index.IndexWriterConfig)

Example 54 with QueryParser

use of org.apache.lucene.queryparser.classic.QueryParser in project ansj_seg by NLPchina.

the class IndexAndTest 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));
    }
}
Also used : IndexSearcher(org.apache.lucene.search.IndexSearcher) TopDocs(org.apache.lucene.search.TopDocs) QueryParser(org.apache.lucene.queryparser.classic.QueryParser) Query(org.apache.lucene.search.Query) DirectoryReader(org.apache.lucene.index.DirectoryReader) Document(org.apache.lucene.document.Document)

Example 55 with QueryParser

use of org.apache.lucene.queryparser.classic.QueryParser in project graylog2-server by Graylog2.

the class SearchResource method createRequestExceptionForParseFailure.

protected WebApplicationException createRequestExceptionForParseFailure(String query, SearchPhaseExecutionException e) {
    LOG.warn("Unable to execute search: {}", e.getMessage());
    QueryParseError errorMessage = QueryParseError.create(query, "Unable to execute search", e.getClass().getCanonicalName());
    // We're so going to hell for this…
    if (e.toString().contains("nested: QueryParsingException")) {
        final QueryParser queryParser = new QueryParser("", new StandardAnalyzer());
        try {
            queryParser.parse(query);
        } catch (ParseException parseException) {
            Token currentToken = null;
            try {
                // FIXME I have no idea why this is necessary but without that call currentToken will be null.
                final ParseException exception = queryParser.generateParseException();
                currentToken = exception.currentToken;
            } catch (NullPointerException npe) {
                // "Normal" exception and no need to spam the logs with it.
                LOG.debug("Exception thrown while generating parse exception.", npe);
            }
            if (currentToken == null) {
                LOG.warn("No position/token available for ParseException.", parseException);
                errorMessage = QueryParseError.create(query, parseException.getMessage(), parseException.getClass().getCanonicalName());
            } else {
                // scan for first usable token with position information
                int beginColumn = 0;
                int beginLine = 0;
                int endColumn = 0;
                int endLine = 0;
                while (currentToken != null && beginLine == 0) {
                    beginColumn = currentToken.beginColumn;
                    beginLine = currentToken.beginLine;
                    endColumn = currentToken.endColumn;
                    endLine = currentToken.endLine;
                    currentToken = currentToken.next;
                }
                errorMessage = QueryParseError.create(query, beginColumn, beginLine, endColumn, endLine, parseException.getMessage(), parseException.getClass().getCanonicalName());
            }
        }
        return new BadRequestException(Response.status(Response.Status.BAD_REQUEST).entity(errorMessage).build());
    } else {
        return new InternalServerErrorException("Unable to fulfill search request", e);
    }
}
Also used : QueryParser(org.apache.lucene.queryparser.classic.QueryParser) QueryParseError(org.graylog2.rest.resources.search.responses.QueryParseError) StandardAnalyzer(org.apache.lucene.analysis.standard.StandardAnalyzer) BadRequestException(javax.ws.rs.BadRequestException) InternalServerErrorException(javax.ws.rs.InternalServerErrorException) Token(org.apache.lucene.queryparser.classic.Token) ParseException(org.apache.lucene.queryparser.classic.ParseException)

Aggregations

QueryParser (org.apache.lucene.queryparser.classic.QueryParser)73 Query (org.apache.lucene.search.Query)50 IndexSearcher (org.apache.lucene.search.IndexSearcher)32 Document (org.apache.lucene.document.Document)26 IOException (java.io.IOException)24 Analyzer (org.apache.lucene.analysis.Analyzer)21 TopDocs (org.apache.lucene.search.TopDocs)21 IndexReader (org.apache.lucene.index.IndexReader)18 ScoreDoc (org.apache.lucene.search.ScoreDoc)18 ArrayList (java.util.ArrayList)16 ParseException (org.apache.lucene.queryparser.classic.ParseException)16 StandardAnalyzer (org.apache.lucene.analysis.standard.StandardAnalyzer)14 BooleanQuery (org.apache.lucene.search.BooleanQuery)14 TermQuery (org.apache.lucene.search.TermQuery)13 ScoredDocuments (io.anserini.rerank.ScoredDocuments)6 Term (org.apache.lucene.index.Term)6 MatchAllDocsQuery (org.apache.lucene.search.MatchAllDocsQuery)6 WildcardQuery (org.apache.lucene.search.WildcardQuery)6 EnglishAnalyzer (org.apache.lucene.analysis.en.EnglishAnalyzer)5 IndexWriter (org.apache.lucene.index.IndexWriter)5