org.apache.lucene.index.DefaultIndexingChain Maven / Gradle / Ivy
The newest version!
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.lucene.index;
import java.io.IOException;
import java.util.Arrays;
import java.util.HashMap;
import java.util.Map;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.codecs.DocValuesConsumer;
import org.apache.lucene.codecs.DocValuesFormat;
import org.apache.lucene.codecs.NormsConsumer;
import org.apache.lucene.codecs.NormsFormat;
import org.apache.lucene.codecs.StoredFieldsWriter;
import org.apache.lucene.document.FieldType;
import org.apache.lucene.search.similarities.Similarity;
import org.apache.lucene.store.IOContext;
import org.apache.lucene.util.ArrayUtil;
import org.apache.lucene.util.BytesRef;
import org.apache.lucene.util.BytesRefHash.MaxBytesLengthExceededException;
import org.apache.lucene.util.Counter;
import org.apache.lucene.util.IOUtils;
import org.apache.lucene.util.RamUsageEstimator;
/** Default general purpose indexing chain, which handles
* indexing all types of fields. */
final class DefaultIndexingChain extends DocConsumer {
final Counter bytesUsed;
final DocumentsWriterPerThread.DocState docState;
final DocumentsWriterPerThread docWriter;
final FieldInfos.Builder fieldInfos;
// Writes postings and term vectors:
final TermsHash termsHash;
// lazy init:
private StoredFieldsWriter storedFieldsWriter;
private int lastStoredDocID;
// NOTE: I tried using Hash Map
// but it was ~2% slower on Wiki and Geonames with Java
// 1.7.0_25:
private PerField[] fieldHash = new PerField[2];
private int hashMask = 1;
private int totalFieldCount;
private long nextFieldGen;
// Holds fields seen in each document
private PerField[] fields = new PerField[1];
public DefaultIndexingChain(DocumentsWriterPerThread docWriter) throws IOException {
this.docWriter = docWriter;
this.fieldInfos = docWriter.getFieldInfosBuilder();
this.docState = docWriter.docState;
this.bytesUsed = docWriter.bytesUsed;
TermsHash termVectorsWriter = new TermVectorsConsumer(docWriter);
termsHash = new FreqProxTermsWriter(docWriter, termVectorsWriter);
}
// TODO: can we remove this lazy-init / make cleaner / do it another way...?
private void initStoredFieldsWriter() throws IOException {
if (storedFieldsWriter == null) {
storedFieldsWriter = docWriter.codec.storedFieldsFormat().fieldsWriter(docWriter.directory, docWriter.getSegmentInfo(), IOContext.DEFAULT);
}
}
@Override
public void flush(SegmentWriteState state) throws IOException, AbortingException {
// NOTE: caller (DocumentsWriterPerThread) handles
// aborting on any exception from this method
int maxDoc = state.segmentInfo.maxDoc();
long t0 = System.nanoTime();
writeNorms(state);
if (docState.infoStream.isEnabled("IW")) {
docState.infoStream.message("IW", ((System.nanoTime()-t0)/1000000) + " msec to write norms");
}
t0 = System.nanoTime();
writeDocValues(state);
if (docState.infoStream.isEnabled("IW")) {
docState.infoStream.message("IW", ((System.nanoTime()-t0)/1000000) + " msec to write docValues");
}
// it's possible all docs hit non-aborting exceptions...
t0 = System.nanoTime();
initStoredFieldsWriter();
fillStoredFields(maxDoc);
storedFieldsWriter.finish(state.fieldInfos, maxDoc);
storedFieldsWriter.close();
if (docState.infoStream.isEnabled("IW")) {
docState.infoStream.message("IW", ((System.nanoTime()-t0)/1000000) + " msec to finish stored fields");
}
t0 = System.nanoTime();
Map fieldsToFlush = new HashMap<>();
for (int i=0;i= fieldHash.length/2) {
rehash();
}
if (totalFieldCount > fields.length) {
PerField[] newFields = new PerField[ArrayUtil.oversize(totalFieldCount, RamUsageEstimator.NUM_BYTES_OBJECT_REF)];
System.arraycopy(fields, 0, newFields, 0, fields.length);
fields = newFields;
}
} else if (invert && fp.invertState == null) {
// Messy: must set this here because e.g. FreqProxTermsWriterPerField looks at the initial
// IndexOptions to decide what arrays it must create). Then, we also must set it in
// PerField.invert to allow for later downgrading of the index options:
fp.fieldInfo.setIndexOptions(fieldType.indexOptions());
fp.setInvertState();
}
return fp;
}
/** NOTE: not static: accesses at least docState, termsHash. */
private final class PerField implements Comparable {
final FieldInfo fieldInfo;
final Similarity similarity;
FieldInvertState invertState;
TermsHashPerField termsHashPerField;
// Non-null if this field ever had doc values in this
// segment:
DocValuesWriter docValuesWriter;
/** We use this to know when a PerField is seen for the
* first time in the current document. */
long fieldGen = -1;
// Used by the hash table
PerField next;
// Lazy init'd:
NormValuesWriter norms;
// reused
TokenStream tokenStream;
IndexOptions indexOptions;
public PerField(FieldInfo fieldInfo, boolean invert) {
this.fieldInfo = fieldInfo;
similarity = docState.similarity;
if (invert) {
setInvertState();
}
}
void setInvertState() {
invertState = new FieldInvertState(fieldInfo.name);
termsHashPerField = termsHash.addField(invertState, fieldInfo);
if (fieldInfo.omitsNorms() == false) {
assert norms == null;
// Even if no documents actually succeed in setting a norm, we still write norms for this segment:
norms = new NormValuesWriter(fieldInfo, docState.docWriter.bytesUsed);
}
}
@Override
public int compareTo(PerField other) {
return this.fieldInfo.name.compareTo(other.fieldInfo.name);
}
public void finish() throws IOException {
if (fieldInfo.omitsNorms() == false && invertState.length != 0) {
norms.addValue(docState.docID, similarity.computeNorm(invertState));
}
termsHashPerField.finish();
}
/** Inverts one field for one document; first is true
* if this is the first time we are seeing this field
* name in this document. */
public void invert(IndexableField field, boolean first) throws IOException, AbortingException {
if (first) {
// First time we're seeing this field (indexed) in
// this document:
invertState.reset();
}
IndexableFieldType fieldType = field.fieldType();
IndexOptions indexOptions = fieldType.indexOptions();
fieldInfo.setIndexOptions(indexOptions);
if (fieldType.omitNorms()) {
fieldInfo.setOmitsNorms();
}
final boolean analyzed = fieldType.tokenized() && docState.analyzer != null;
// only bother checking offsets if something will consume them.
// TODO: after we fix analyzers, also check if termVectorOffsets will be indexed.
final boolean checkOffsets = indexOptions == IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS;
/*
* To assist people in tracking down problems in analysis components, we wish to write the field name to the infostream
* when we fail. We expect some caller to eventually deal with the real exception, so we don't want any 'catch' clauses,
* but rather a finally that takes note of the problem.
*/
boolean succeededInProcessingField = false;
try (TokenStream stream = tokenStream = field.tokenStream(docState.analyzer, tokenStream)) {
// reset the TokenStream to the first token
stream.reset();
invertState.setAttributeSource(stream);
termsHashPerField.start(field, first);
while (stream.incrementToken()) {
// If we hit an exception in stream.next below
// (which is fairly common, e.g. if analyzer
// chokes on a given document), then it's
// non-aborting and (above) this one document
// will be marked as deleted, but still
// consume a docID
int posIncr = invertState.posIncrAttribute.getPositionIncrement();
invertState.position += posIncr;
if (invertState.position < invertState.lastPosition) {
if (posIncr == 0) {
throw new IllegalArgumentException("first position increment must be > 0 (got 0) for field '" + field.name() + "'");
} else {
throw new IllegalArgumentException("position increments (and gaps) must be >= 0 (got " + posIncr + ") for field '" + field.name() + "'");
}
} else if (invertState.position > IndexWriter.MAX_POSITION) {
throw new IllegalArgumentException("position " + invertState.position + " is too large for field '" + field.name() + "': max allowed position is " + IndexWriter.MAX_POSITION);
}
invertState.lastPosition = invertState.position;
if (posIncr == 0) {
invertState.numOverlap++;
}
if (checkOffsets) {
int startOffset = invertState.offset + invertState.offsetAttribute.startOffset();
int endOffset = invertState.offset + invertState.offsetAttribute.endOffset();
if (startOffset < invertState.lastStartOffset || endOffset < startOffset) {
throw new IllegalArgumentException("startOffset must be non-negative, and endOffset must be >= startOffset, and offsets must not go backwards "
+ "startOffset=" + startOffset + ",endOffset=" + endOffset + ",lastStartOffset=" + invertState.lastStartOffset + " for field '" + field.name() + "'");
}
invertState.lastStartOffset = startOffset;
}
invertState.length++;
if (invertState.length < 0) {
throw new IllegalArgumentException("too many tokens in field '" + field.name() + "'");
}
//System.out.println(" term=" + invertState.termAttribute);
// If we hit an exception in here, we abort
// all buffered documents since the last
// flush, on the likelihood that the
// internal state of the terms hash is now
// corrupt and should not be flushed to a
// new segment:
try {
termsHashPerField.add();
} catch (MaxBytesLengthExceededException e) {
byte[] prefix = new byte[30];
BytesRef bigTerm = invertState.termAttribute.getBytesRef();
System.arraycopy(bigTerm.bytes, bigTerm.offset, prefix, 0, 30);
String msg = "Document contains at least one immense term in field=\"" + fieldInfo.name + "\" (whose UTF8 encoding is longer than the max length " + DocumentsWriterPerThread.MAX_TERM_LENGTH_UTF8 + "), all of which were skipped. Please correct the analyzer to not produce such terms. The prefix of the first immense term is: '" + Arrays.toString(prefix) + "...', original message: " + e.getMessage();
if (docState.infoStream.isEnabled("IW")) {
docState.infoStream.message("IW", "ERROR: " + msg);
}
// Document will be deleted above:
throw new IllegalArgumentException(msg, e);
} catch (Throwable th) {
throw AbortingException.wrap(th);
}
}
// trigger streams to perform end-of-stream operations
stream.end();
// TODO: maybe add some safety? then again, it's already checked
// when we come back around to the field...
invertState.position += invertState.posIncrAttribute.getPositionIncrement();
invertState.offset += invertState.offsetAttribute.endOffset();
/* if there is an exception coming through, we won't set this to true here:*/
succeededInProcessingField = true;
} finally {
if (!succeededInProcessingField && docState.infoStream.isEnabled("DW")) {
docState.infoStream.message("DW", "An exception was thrown while processing field " + fieldInfo.name);
}
}
if (analyzed) {
invertState.position += docState.analyzer.getPositionIncrementGap(fieldInfo.name);
invertState.offset += docState.analyzer.getOffsetGap(fieldInfo.name);
}
invertState.boost *= field.boost();
}
}
}
© 2015 - 2025 Weber Informatics LLC | Privacy Policy