Java Field.setStringValue方法代码示例

import org.apache.lucene.document.Field; //导入方法依赖的package包/类
private IndexReader indexOneDoc(Directory dir, String field, String value, Analyzer analyzer) throws IOException {
    IndexWriterConfig iwc = newIndexWriterConfig(analyzer);
    iwc.setMergePolicy(newLogMergePolicy());
    RandomIndexWriter iw = new RandomIndexWriter(random(), dir, iwc);

    FieldType ft = new FieldType(TextField.TYPE_STORED);
    ft.setIndexOptions(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS);
    Field textField = new Field(field, "", ft);
    Document doc = new Document();
    doc.add(textField);

    textField.setStringValue(value);
    iw.addDocument(doc);
    IndexReader ir = iw.getReader();
    iw.close();
    return ir;
}
 

import org.apache.lucene.document.Field; //导入方法依赖的package包/类
/** Test that core cache key (needed for NRT) is working */
public void testCoreCacheKey() throws Exception {
    Directory dir = newDirectory();
    IndexWriterConfig iwc = new IndexWriterConfig(null);
    iwc.setMaxBufferedDocs(100);
    iwc.setMergePolicy(NoMergePolicy.INSTANCE);
    IndexWriter iw = new IndexWriter(dir, iwc);
    
    // add two docs, id:0 and id:1
    Document doc = new Document();
    Field idField = new StringField("id", "", Field.Store.NO);
    doc.add(idField);
    idField.setStringValue("0");
    iw.addDocument(doc);
    idField.setStringValue("1");
    iw.addDocument(doc);
    
    // open reader
    ShardId shardId = new ShardId("fake", "_na_", 1);
    DirectoryReader ir = ElasticsearchDirectoryReader.wrap(DirectoryReader.open(iw), shardId);
    assertEquals(2, ir.numDocs());
    assertEquals(1, ir.leaves().size());

    // delete id:0 and reopen
    iw.deleteDocuments(new Term("id", "0"));
    DirectoryReader ir2 = DirectoryReader.openIfChanged(ir);
    
    // we should have the same cache key as before
    assertEquals(1, ir2.numDocs());
    assertEquals(1, ir2.leaves().size());
    assertSame(ir.leaves().get(0).reader().getCoreCacheKey(), ir2.leaves().get(0).reader().getCoreCacheKey());
    IOUtils.close(ir, ir2, iw, dir);
}
 

import org.apache.lucene.document.Field; //导入方法依赖的package包/类
public void testCustomPostingsHighlighter() throws Exception {
    Directory dir = newDirectory();
    IndexWriterConfig iwc = newIndexWriterConfig(new MockAnalyzer(random()));
    iwc.setMergePolicy(newLogMergePolicy());
    RandomIndexWriter iw = new RandomIndexWriter(random(), dir, iwc);

    FieldType offsetsType = new FieldType(TextField.TYPE_STORED);
    offsetsType.setIndexOptions(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS);

    //good position but only one match
    final String firstValue = "This is a test. Just a test1 highlighting from postings highlighter.";
    Field body = new Field("body", "", offsetsType);
    Document doc = new Document();
    doc.add(body);
    body.setStringValue(firstValue);

    //two matches, not the best snippet due to its length though
    final String secondValue = "This is the second highlighting value to perform highlighting on a longer text that gets scored lower.";
    Field body2 = new Field("body", "", offsetsType);
    doc.add(body2);
    body2.setStringValue(secondValue);

    //two matches and short, will be scored highest
    final String thirdValue = "This is highlighting the third short highlighting value.";
    Field body3 = new Field("body", "", offsetsType);
    doc.add(body3);
    body3.setStringValue(thirdValue);

    //one match, same as first but at the end, will be scored lower due to its position
    final String fourthValue = "Just a test4 highlighting from postings highlighter.";
    Field body4 = new Field("body", "", offsetsType);
    doc.add(body4);
    body4.setStringValue(fourthValue);

    iw.addDocument(doc);

    IndexReader ir = iw.getReader();
    iw.close();

    String firstHlValue = "Just a test1 <b>highlighting</b> from postings highlighter.";
    String secondHlValue = "This is the second <b>highlighting</b> value to perform <b>highlighting</b> on a longer text that gets scored lower.";
    String thirdHlValue = "This is <b>highlighting</b> the third short <b>highlighting</b> value.";
    String fourthHlValue = "Just a test4 <b>highlighting</b> from postings highlighter.";

    IndexSearcher searcher = newSearcher(ir);
    Query query = new TermQuery(new Term("body", "highlighting"));

    TopDocs topDocs = searcher.search(query, 10, Sort.INDEXORDER);
    assertThat(topDocs.totalHits, equalTo(1));

    int docId = topDocs.scoreDocs[0].doc;

    String fieldValue = firstValue + HighlightUtils.PARAGRAPH_SEPARATOR + secondValue + HighlightUtils.PARAGRAPH_SEPARATOR + thirdValue + HighlightUtils.PARAGRAPH_SEPARATOR + fourthValue;

    CustomPostingsHighlighter highlighter = new CustomPostingsHighlighter(null, new CustomPassageFormatter("<b>", "</b>", new DefaultEncoder()), fieldValue, false);
    Snippet[] snippets = highlighter.highlightField("body", query, searcher, docId, 5);

    assertThat(snippets.length, equalTo(4));

    assertThat(snippets[0].getText(), equalTo(firstHlValue));
    assertThat(snippets[1].getText(), equalTo(secondHlValue));
    assertThat(snippets[2].getText(), equalTo(thirdHlValue));
    assertThat(snippets[3].getText(), equalTo(fourthHlValue));

    ir.close();
    dir.close();
}
 

import org.apache.lucene.document.Field; //导入方法依赖的package包/类
public void testNoMatchSize() throws Exception {
    Directory dir = newDirectory();
    IndexWriterConfig iwc = newIndexWriterConfig(new MockAnalyzer(random()));
    iwc.setMergePolicy(newLogMergePolicy());
    RandomIndexWriter iw = new RandomIndexWriter(random(), dir, iwc);

    FieldType offsetsType = new FieldType(TextField.TYPE_STORED);
    offsetsType.setIndexOptions(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS);
    Field body = new Field("body", "", offsetsType);
    Field none = new Field("none", "", offsetsType);
    Document doc = new Document();
    doc.add(body);
    doc.add(none);

    String firstValue = "This is a test. Just a test highlighting from postings. Feel free to ignore.";
    body.setStringValue(firstValue);
    none.setStringValue(firstValue);
    iw.addDocument(doc);

    IndexReader ir = iw.getReader();
    iw.close();

    Query query = new TermQuery(new Term("none", "highlighting"));

    IndexSearcher searcher = newSearcher(ir);
    TopDocs topDocs = searcher.search(query, 10, Sort.INDEXORDER);
    assertThat(topDocs.totalHits, equalTo(1));
    int docId = topDocs.scoreDocs[0].doc;

    CustomPassageFormatter passageFormatter = new CustomPassageFormatter("<b>", "</b>", new DefaultEncoder());

    CustomPostingsHighlighter highlighter = new CustomPostingsHighlighter(null, passageFormatter, firstValue, false);
    Snippet[] snippets = highlighter.highlightField("body", query, searcher, docId, 5);
    assertThat(snippets.length, equalTo(0));

    highlighter = new CustomPostingsHighlighter(null, passageFormatter, firstValue, true);
    snippets = highlighter.highlightField("body", query, searcher, docId, 5);
    assertThat(snippets.length, equalTo(1));
    assertThat(snippets[0].getText(), equalTo("This is a test."));

    ir.close();
    dir.close();
}
 

import org.apache.lucene.document.Field; //导入方法依赖的package包/类
public void testCustomUnifiedHighlighter() throws Exception {
    Directory dir = newDirectory();
    IndexWriterConfig iwc = newIndexWriterConfig(new MockAnalyzer(random()));
    iwc.setMergePolicy(newLogMergePolicy());
    RandomIndexWriter iw = new RandomIndexWriter(random(), dir, iwc);

    FieldType offsetsType = new FieldType(TextField.TYPE_STORED);
    offsetsType.setIndexOptions(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS);
    offsetsType.setStoreTermVectorOffsets(true);
    offsetsType.setStoreTermVectorPositions(true);
    offsetsType.setStoreTermVectors(true);

    //good position but only one match
    final String firstValue = "This is a test. Just a test1 highlighting from unified highlighter.";
    Field body = new Field("body", "", offsetsType);
    Document doc = new Document();
    doc.add(body);
    body.setStringValue(firstValue);

    //two matches, not the best snippet due to its length though
    final String secondValue = "This is the second highlighting value to perform highlighting on a longer text " +
        "that gets scored lower.";
    Field body2 = new Field("body", "", offsetsType);
    doc.add(body2);
    body2.setStringValue(secondValue);

    //two matches and short, will be scored highest
    final String thirdValue = "This is highlighting the third short highlighting value.";
    Field body3 = new Field("body", "", offsetsType);
    doc.add(body3);
    body3.setStringValue(thirdValue);

    //one match, same as first but at the end, will be scored lower due to its position
    final String fourthValue = "Just a test4 highlighting from unified highlighter.";
    Field body4 = new Field("body", "", offsetsType);
    doc.add(body4);
    body4.setStringValue(fourthValue);

    iw.addDocument(doc);

    IndexReader ir = iw.getReader();
    iw.close();

    String firstHlValue = "Just a test1 <b>highlighting</b> from unified highlighter.";
    String secondHlValue = "This is the second <b>highlighting</b> value to perform <b>highlighting</b> on a" +
        " longer text that gets scored lower.";
    String thirdHlValue = "This is <b>highlighting</b> the third short <b>highlighting</b> value.";
    String fourthHlValue = "Just a test4 <b>highlighting</b> from unified highlighter.";

    IndexSearcher searcher = newSearcher(ir);
    Query query = new TermQuery(new Term("body", "highlighting"));

    TopDocs topDocs = searcher.search(query, 10, Sort.INDEXORDER);
    assertThat(topDocs.totalHits, equalTo(1));

    int docId = topDocs.scoreDocs[0].doc;

    String fieldValue = firstValue + HighlightUtils.PARAGRAPH_SEPARATOR + secondValue +
        HighlightUtils.PARAGRAPH_SEPARATOR + thirdValue + HighlightUtils.PARAGRAPH_SEPARATOR + fourthValue;

    CustomUnifiedHighlighter highlighter = new CustomUnifiedHighlighter(searcher, iwc.getAnalyzer(),
        new CustomPassageFormatter("<b>", "</b>", new DefaultEncoder()), null, fieldValue, true);
    Snippet[] snippets = highlighter.highlightField("body", query, docId, 5);

    assertThat(snippets.length, equalTo(4));

    assertThat(snippets[0].getText(), equalTo(firstHlValue));
    assertThat(snippets[1].getText(), equalTo(secondHlValue));
    assertThat(snippets[2].getText(), equalTo(thirdHlValue));
    assertThat(snippets[3].getText(), equalTo(fourthHlValue));
    ir.close();
    dir.close();
}
 

import org.apache.lucene.document.Field; //导入方法依赖的package包/类
public void testNoMatchSize() throws Exception {
    Directory dir = newDirectory();
    Analyzer analyzer = new StandardAnalyzer();
    IndexWriterConfig iwc = newIndexWriterConfig(analyzer);
    iwc.setMergePolicy(newLogMergePolicy());
    RandomIndexWriter iw = new RandomIndexWriter(random(), dir, iwc);

    FieldType offsetsType = new FieldType(TextField.TYPE_STORED);
    offsetsType.setIndexOptions(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS);
    offsetsType.setStoreTermVectorOffsets(true);
    offsetsType.setStoreTermVectorPositions(true);
    offsetsType.setStoreTermVectors(true);
    Field body = new Field("body", "", offsetsType);
    Field none = new Field("none", "", offsetsType);
    Document doc = new Document();
    doc.add(body);
    doc.add(none);

    String firstValue = "This is a test. Just a test highlighting from unified. Feel free to ignore.";
    body.setStringValue(firstValue);
    none.setStringValue(firstValue);
    iw.addDocument(doc);

    IndexReader ir = iw.getReader();
    iw.close();

    Query query = new TermQuery(new Term("none", "highlighting"));

    IndexSearcher searcher = newSearcher(ir);
    TopDocs topDocs = searcher.search(query, 10, Sort.INDEXORDER);
    assertThat(topDocs.totalHits, equalTo(1));
    int docId = topDocs.scoreDocs[0].doc;

    CustomPassageFormatter passageFormatter = new CustomPassageFormatter("<b>", "</b>", new DefaultEncoder());
    CustomUnifiedHighlighter highlighter = new CustomUnifiedHighlighter(searcher, analyzer, passageFormatter,
        null, firstValue, false);
    Snippet[] snippets = highlighter.highlightField("body", query, docId, 5);
    assertThat(snippets.length, equalTo(0));

    highlighter = new CustomUnifiedHighlighter(searcher, analyzer, passageFormatter, null, firstValue, true);
    snippets = highlighter.highlightField("body", query, docId, 5);
    assertThat(snippets.length, equalTo(1));
    assertThat(snippets[0].getText(), equalTo("This is a test."));
    ir.close();
    dir.close();
}