Example usage for org.apache.lucene.index LeafReader getFieldInfos

Introduction

In this page you can find the example usage for org.apache.lucene.index LeafReader getFieldInfos.

Prototype

public abstract FieldInfos getFieldInfos();

Source Link

Document

Get the FieldInfos describing all fields in this reader.

Usage

From source file:org.elasticsearch.xpack.core.security.authz.accesscontrol.FieldSubsetReader.java

License:Open Source License

/**
 * Wrap a single segment, exposing a subset of its fields.
 *///from  w  w w. ja v  a 2 s  .  co m
FieldSubsetReader(LeafReader in, CharacterRunAutomaton filter) {
    super(in);
    ArrayList<FieldInfo> filteredInfos = new ArrayList<>();
    for (FieldInfo fi : in.getFieldInfos()) {
        if (filter.run(fi.name)) {
            filteredInfos.add(fi);
        }
    }
    fieldInfos = new FieldInfos(filteredInfos.toArray(new FieldInfo[filteredInfos.size()]));
    this.filter = filter;
}

---

From source file:org.elasticsearch.xpack.core.security.authz.accesscontrol.FieldSubsetReaderTests.java

License:Open Source License

/**
 * test filtering two string fields//from   www. j a  va 2s  . c om
 */
public void testIndexed() throws Exception {
    Directory dir = newDirectory();
    IndexWriterConfig iwc = new IndexWriterConfig(null);
    IndexWriter iw = new IndexWriter(dir, iwc);

    // add document with 2 fields
    Document doc = new Document();
    doc.add(new StringField("fieldA", "test", Field.Store.NO));
    doc.add(new StringField("fieldB", "test", Field.Store.NO));
    iw.addDocument(doc);

    // open reader
    DirectoryReader ir = FieldSubsetReader.wrap(DirectoryReader.open(iw),
            new CharacterRunAutomaton(Automata.makeString("fieldA")));

    // see only one field
    LeafReader segmentReader = ir.leaves().get(0).reader();
    Set<String> seenFields = new HashSet<>();
    for (FieldInfo info : segmentReader.getFieldInfos()) {
        seenFields.add(info.name);
    }
    assertEquals(Collections.singleton("fieldA"), seenFields);
    assertNotNull(segmentReader.terms("fieldA"));
    assertNull(segmentReader.terms("fieldB"));

    TestUtil.checkReader(ir);
    IOUtils.close(ir, iw, dir);
}

---

From source file:org.elasticsearch.xpack.core.security.authz.accesscontrol.FieldSubsetReaderTests.java

License:Open Source License

/**
 * test we have correct fieldinfos metadata
 *//*  w  ww .  j  a v a  2s .c o m*/
public void testFieldInfos() throws Exception {
    Directory dir = newDirectory();
    IndexWriterConfig iwc = new IndexWriterConfig(null);
    IndexWriter iw = new IndexWriter(dir, iwc);

    // add document with 2 fields
    Document doc = new Document();
    doc.add(new StringField("fieldA", "test", Field.Store.NO));
    doc.add(new StringField("fieldB", "test", Field.Store.NO));
    iw.addDocument(doc);

    // open reader
    DirectoryReader ir = FieldSubsetReader.wrap(DirectoryReader.open(iw),
            new CharacterRunAutomaton(Automata.makeString("fieldA")));

    // see only one field
    LeafReader segmentReader = ir.leaves().get(0).reader();
    FieldInfos infos = segmentReader.getFieldInfos();
    assertEquals(1, infos.size());
    assertNotNull(infos.fieldInfo("fieldA"));
    assertNull(infos.fieldInfo("fieldB"));

    TestUtil.checkReader(ir);
    IOUtils.close(ir, iw, dir);
}

---

From source file:org.elasticsearch.xpack.core.security.authz.accesscontrol.FieldSubsetReaderTests.java

License:Open Source License

/**
 * test filtering an index with no fields
 *//*from  www.  j a v a2  s  .c  o m*/
public void testEmpty() throws Exception {
    Directory dir = newDirectory();
    IndexWriterConfig iwc = new IndexWriterConfig(null);
    IndexWriter iw = new IndexWriter(dir, iwc);
    iw.addDocument(new Document());

    // open reader
    DirectoryReader ir = FieldSubsetReader.wrap(DirectoryReader.open(iw),
            new CharacterRunAutomaton(Automata.makeString("fieldA")));

    // see no fields
    LeafReader segmentReader = ir.leaves().get(0).reader();
    Set<String> seenFields = new HashSet<>();
    for (FieldInfo info : segmentReader.getFieldInfos()) {
        seenFields.add(info.name);
    }
    assertEquals(0, seenFields.size());
    assertNull(segmentReader.terms("foo"));

    // see no vectors
    assertNull(segmentReader.getTermVectors(0));

    // see no stored fields
    Document document = segmentReader.document(0);
    assertEquals(0, document.getFields().size());

    TestUtil.checkReader(ir);
    IOUtils.close(ir, iw, dir);
}

---

From source file:org.tallison.gramreaper.terms.DumpTerms.java

License:Apache License

private void dumpTopN(LeafReader leafReader) throws IOException {
    if (config.field == null) {
        FieldInfos fieldInfos = leafReader.getFieldInfos();
        for (FieldInfo fieldInfo : fieldInfos) {
            dumpTopNField(leafReader, fieldInfo.name);
        }//from  www. j  a v a  2  s .  co m
    } else {
        dumpTopNField(leafReader, config.field);
    }
}

---

From source file:org.tallison.gramreaper.terms.DumpTerms.java

License:Apache License

private void dumpTopNField(LeafReader leafReader, String field) throws IOException {
    AbstractTokenTFDFPriorityQueue queue = config.sort.equals(DumpTermsConfig.SORT.DF)
            ? new TokenDFPriorityQueue(config.topN)
            : new TokenTFPriorityQueue(config.topN);
    Terms terms = leafReader.terms(field);
    if (terms == null) {
        StringBuilder sb = new StringBuilder();
        int i = 0;
        for (FieldInfo fieldInfo : leafReader.getFieldInfos()) {
            if (i++ > 0) {
                sb.append("\n");
            }/* ww w .j  a  v a  2s  .  co  m*/
            sb.append(fieldInfo.name);

        }
        throw new RuntimeException("I can't find field \"" + field + "\".\n" + "I only see:\n" + sb.toString());
    }
    TermsEnum termsEnum = terms.iterator();
    BytesRef bytesRef = termsEnum.next();
    int docsWThisField = leafReader.getDocCount(field);
    while (bytesRef != null) {
        int df = termsEnum.docFreq();
        long tf = termsEnum.totalTermFreq();
        if (config.minDocFreq > -1 && df < config.minDocFreq) {
            bytesRef = termsEnum.next();
            continue;
        }
        if (config.minDocPercentage > -1.0d
                && (double) df / (double) docsWThisField < config.minDocPercentage) {
            bytesRef = termsEnum.next();
            continue;
        }

        if (queue.top() == null || queue.size() < config.topN
                || (config.sort.equals(DumpTermsConfig.SORT.DF) ? df >= queue.top().df : tf > queue.top().tf)) {
            String t = bytesRef.utf8ToString();
            if (!config.stopWords.contains(t) && !config.startWords.contains(t)) {

                queue.insertWithOverflow(new TokenDFTF(t, df, tf));
            }
        }
        bytesRef = termsEnum.next();
    }
    if (config.outputFile == null) {
        StringBuilder sb = new StringBuilder();
        for (TokenDFTF tp : queue.getArray()) {
            System.out.println(getRow(sb, tp));
        }
    } else if (Files.isDirectory(config.outputFile)) {
        writeTopN(config.outputFile.resolve(field), queue);
    } else {
        writeTopN(config.outputFile, queue);
    }
}

---

• «
• 1
• 2
• 3
• »