org.apache.lucene.codecs.simpletext.SimpleTextPointsReader Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of lucene-codecs Show documentation
Show all versions of lucene-codecs Show documentation
Apache Lucene (module: codecs)
/*
* 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.codecs.simpletext;
import java.io.IOException;
import java.nio.charset.StandardCharsets;
import java.util.HashMap;
import java.util.Map;
import org.apache.lucene.codecs.PointsReader;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.FieldInfo;
import org.apache.lucene.index.IndexFileNames;
import org.apache.lucene.index.PointValues;
import org.apache.lucene.index.SegmentReadState;
import org.apache.lucene.store.BufferedChecksumIndexInput;
import org.apache.lucene.store.ChecksumIndexInput;
import org.apache.lucene.store.IOContext;
import org.apache.lucene.store.IndexInput;
import org.apache.lucene.util.BytesRef;
import org.apache.lucene.util.BytesRefBuilder;
import org.apache.lucene.util.IOUtils;
import org.apache.lucene.util.StringHelper;
import static org.apache.lucene.codecs.simpletext.SimpleTextPointsWriter.BLOCK_FP;
import static org.apache.lucene.codecs.simpletext.SimpleTextPointsWriter.BYTES_PER_DIM;
import static org.apache.lucene.codecs.simpletext.SimpleTextPointsWriter.DOC_COUNT;
import static org.apache.lucene.codecs.simpletext.SimpleTextPointsWriter.FIELD_COUNT;
import static org.apache.lucene.codecs.simpletext.SimpleTextPointsWriter.FIELD_FP;
import static org.apache.lucene.codecs.simpletext.SimpleTextPointsWriter.FIELD_FP_NAME;
import static org.apache.lucene.codecs.simpletext.SimpleTextPointsWriter.INDEX_COUNT;
import static org.apache.lucene.codecs.simpletext.SimpleTextPointsWriter.MAX_LEAF_POINTS;
import static org.apache.lucene.codecs.simpletext.SimpleTextPointsWriter.MAX_VALUE;
import static org.apache.lucene.codecs.simpletext.SimpleTextPointsWriter.MIN_VALUE;
import static org.apache.lucene.codecs.simpletext.SimpleTextPointsWriter.NUM_DIMS;
import static org.apache.lucene.codecs.simpletext.SimpleTextPointsWriter.POINT_COUNT;
import static org.apache.lucene.codecs.simpletext.SimpleTextPointsWriter.SPLIT_COUNT;
import static org.apache.lucene.codecs.simpletext.SimpleTextPointsWriter.SPLIT_DIM;
import static org.apache.lucene.codecs.simpletext.SimpleTextPointsWriter.SPLIT_VALUE;
class SimpleTextPointsReader extends PointsReader {
private final IndexInput dataIn;
final SegmentReadState readState;
final Map readers = new HashMap<>();
final BytesRefBuilder scratch = new BytesRefBuilder();
public SimpleTextPointsReader(SegmentReadState readState) throws IOException {
// Initialize readers now:
// Read index:
Map fieldToFileOffset = new HashMap<>();
String indexFileName = IndexFileNames.segmentFileName(readState.segmentInfo.name, readState.segmentSuffix, SimpleTextPointsFormat.POINT_INDEX_EXTENSION);
try (ChecksumIndexInput in = readState.directory.openChecksumInput(indexFileName, IOContext.DEFAULT)) {
readLine(in);
int count = parseInt(FIELD_COUNT);
for(int i=0;i ent : fieldToFileOffset.entrySet()) {
readers.put(ent.getKey(), initReader(ent.getValue()));
}
success = true;
} finally {
if (success == false) {
IOUtils.closeWhileHandlingException(this);
}
}
this.readState = readState;
}
private SimpleTextBKDReader initReader(long fp) throws IOException {
// NOTE: matches what writeIndex does in SimpleTextPointsWriter
dataIn.seek(fp);
readLine(dataIn);
int numDims = parseInt(NUM_DIMS);
readLine(dataIn);
int bytesPerDim = parseInt(BYTES_PER_DIM);
readLine(dataIn);
int maxPointsInLeafNode = parseInt(MAX_LEAF_POINTS);
readLine(dataIn);
int count = parseInt(INDEX_COUNT);
readLine(dataIn);
assert startsWith(MIN_VALUE);
BytesRef minValue = SimpleTextUtil.fromBytesRefString(stripPrefix(MIN_VALUE));
assert minValue.length == numDims*bytesPerDim;
readLine(dataIn);
assert startsWith(MAX_VALUE);
BytesRef maxValue = SimpleTextUtil.fromBytesRefString(stripPrefix(MAX_VALUE));
assert maxValue.length == numDims*bytesPerDim;
readLine(dataIn);
assert startsWith(POINT_COUNT);
long pointCount = parseLong(POINT_COUNT);
readLine(dataIn);
assert startsWith(DOC_COUNT);
int docCount = parseInt(DOC_COUNT);
long[] leafBlockFPs = new long[count];
for(int i=0;i= footerStartPos) {
// Make sure we landed at precisely the right location:
if (input.getFilePointer() != footerStartPos) {
throw new CorruptIndexException("SimpleText failure: footer does not start at expected position current=" + input.getFilePointer() + " vs expected=" + footerStartPos, input);
}
SimpleTextUtil.checkFooter(input);
break;
}
}
}
@Override
public long ramBytesUsed() {
return 0L;
}
@Override
public void close() throws IOException {
dataIn.close();
}
@Override
public String toString() {
return "SimpleTextPointsReader(segment=" + readState.segmentInfo.name + " maxDoc=" + readState.segmentInfo.maxDoc() + ")";
}
}