private final void init(Version matchVersion) {
// best effort NPE if you dont call reset
if (matchVersion.onOrAfter(Version.LUCENE_40)) {
this.scanner = new StandardTokenizerImpl(input);
} else if (matchVersion.onOrAfter(Version.LUCENE_34)) {
this.scanner = new StandardTokenizerImpl34(input);
} else if (matchVersion.onOrAfter(Version.LUCENE_31)) {
this.scanner = new StandardTokenizerImpl31(input);
} else {
this.scanner = new ClassicTokenizerImpl(input);
}
}
public RussianAnalyzer(Version matchVersion) {
this(
matchVersion,
matchVersion.onOrAfter(Version.LUCENE_31)
? DefaultSetHolder.DEFAULT_STOP_SET
: DefaultSetHolder.DEFAULT_STOP_SET_30);
}
private void init(Reader input, Version matchVersion) {
if (matchVersion.onOrAfter(Version.LUCENE_24)) {
replaceInvalidAcronym = true;
} else {
replaceInvalidAcronym = false;
}
this.input = input;
termAtt = addAttribute(TermAttribute.class);
offsetAtt = addAttribute(OffsetAttribute.class);
posIncrAtt = addAttribute(PositionIncrementAttribute.class);
typeAtt = addAttribute(TypeAttribute.class);
}
public StoreFileMetaData(
String name, long length, String checksum, Version writtenBy, BytesRef hash) {
// its possible here to have a _na_ checksum or an unsupported writtenBy version, if the
// file is a segments_N file, but that is fine in the case of a segments_N file because
// we handle that case upstream
assert name.startsWith("segments_")
|| (writtenBy != null && writtenBy.onOrAfter(FIRST_LUCENE_CHECKSUM_VERSION))
: "index version less that "
+ FIRST_LUCENE_CHECKSUM_VERSION
+ " are not supported but got: "
+ writtenBy;
this.name = Objects.requireNonNull(name, "name must not be null");
this.length = length;
this.checksum = Objects.requireNonNull(checksum, "checksum must not be null");
this.writtenBy = Objects.requireNonNull(writtenBy, "writtenBy must not be null");
this.hash = hash == null ? new BytesRef() : hash;
}
/**
* Builds an analyzer with the given stop words.
*
* @param matchVersion Lucene version to match See {@link <a href="#version">above</a>}
* @param stopWords stop words
*/
public PhaidraAnalyzer(Version matchVersion, Set<?> stopWords) {
super(matchVersion, stopWords);
replaceInvalidAcronym = matchVersion.onOrAfter(Version.LUCENE_33);
}
private void write(Directory directory) throws IOException {
long nextGeneration = getNextPendingGeneration();
String segmentFileName =
IndexFileNames.fileNameFromGeneration(IndexFileNames.PENDING_SEGMENTS, "", nextGeneration);
// Always advance the generation on write:
generation = nextGeneration;
IndexOutput segnOutput = null;
boolean success = false;
try {
segnOutput = directory.createOutput(segmentFileName, IOContext.DEFAULT);
CodecUtil.writeIndexHeader(
segnOutput,
"segments",
VERSION_CURRENT,
StringHelper.randomId(),
Long.toString(nextGeneration, Character.MAX_RADIX));
segnOutput.writeVInt(Version.LATEST.major);
segnOutput.writeVInt(Version.LATEST.minor);
segnOutput.writeVInt(Version.LATEST.bugfix);
segnOutput.writeLong(version);
segnOutput.writeInt(counter); // write counter
segnOutput.writeInt(size());
if (size() > 0) {
Version minSegmentVersion = null;
// We do a separate loop up front so we can write the minSegmentVersion before
// any SegmentInfo; this makes it cleaner to throw IndexFormatTooOldExc at read time:
for (SegmentCommitInfo siPerCommit : this) {
Version segmentVersion = siPerCommit.info.getVersion();
if (minSegmentVersion == null || segmentVersion.onOrAfter(minSegmentVersion) == false) {
minSegmentVersion = segmentVersion;
}
}
segnOutput.writeVInt(minSegmentVersion.major);
segnOutput.writeVInt(minSegmentVersion.minor);
segnOutput.writeVInt(minSegmentVersion.bugfix);
}
// write infos
for (SegmentCommitInfo siPerCommit : this) {
SegmentInfo si = siPerCommit.info;
segnOutput.writeString(si.name);
byte segmentID[] = si.getId();
// TODO: remove this in lucene 6, we don't need to include 4.x segments in commits anymore
if (segmentID == null) {
segnOutput.writeByte((byte) 0);
} else {
if (segmentID.length != StringHelper.ID_LENGTH) {
throw new IllegalStateException(
"cannot write segment: invalid id segment="
+ si.name
+ "id="
+ StringHelper.idToString(segmentID));
}
segnOutput.writeByte((byte) 1);
segnOutput.writeBytes(segmentID, segmentID.length);
}
segnOutput.writeString(si.getCodec().getName());
segnOutput.writeLong(siPerCommit.getDelGen());
int delCount = siPerCommit.getDelCount();
if (delCount < 0 || delCount > si.maxDoc()) {
throw new IllegalStateException(
"cannot write segment: invalid maxDoc segment="
+ si.name
+ " maxDoc="
+ si.maxDoc()
+ " delCount="
+ delCount);
}
segnOutput.writeInt(delCount);
segnOutput.writeLong(siPerCommit.getFieldInfosGen());
segnOutput.writeLong(siPerCommit.getDocValuesGen());
segnOutput.writeSetOfStrings(siPerCommit.getFieldInfosFiles());
final Map<Integer, Set<String>> dvUpdatesFiles = siPerCommit.getDocValuesUpdatesFiles();
segnOutput.writeInt(dvUpdatesFiles.size());
for (Entry<Integer, Set<String>> e : dvUpdatesFiles.entrySet()) {
segnOutput.writeInt(e.getKey());
segnOutput.writeSetOfStrings(e.getValue());
}
}
segnOutput.writeMapOfStrings(userData);
CodecUtil.writeFooter(segnOutput);
segnOutput.close();
directory.sync(Collections.singleton(segmentFileName));
success = true;
} finally {
if (success) {
pendingCommit = true;
} else {
// We hit an exception above; try to close the file
// but suppress any exception:
IOUtils.closeWhileHandlingException(segnOutput);
// Try not to leave a truncated segments_N file in
// the index:
IOUtils.deleteFilesIgnoringExceptions(directory, segmentFileName);
}
}
}
/**
* Read a particular segmentFileName. Note that this may throw an IOException if a commit is in
* process.
*
* @param directory -- directory containing the segments file
* @param segmentFileName -- segment file to load
* @throws CorruptIndexException if the index is corrupt
* @throws IOException if there is a low-level IO error
*/
public static final SegmentInfos readCommit(Directory directory, String segmentFileName)
throws IOException {
long generation = generationFromSegmentsFileName(segmentFileName);
try (ChecksumIndexInput input = directory.openChecksumInput(segmentFileName, IOContext.READ)) {
// NOTE: as long as we want to throw indexformattooold (vs corruptindexexception), we need
// to read the magic ourselves.
int magic = input.readInt();
if (magic != CodecUtil.CODEC_MAGIC) {
throw new IndexFormatTooOldException(
input, magic, CodecUtil.CODEC_MAGIC, CodecUtil.CODEC_MAGIC);
}
// 4.0+
int format = CodecUtil.checkHeaderNoMagic(input, "segments", VERSION_40, VERSION_CURRENT);
// 5.0+
byte id[] = null;
if (format >= VERSION_50) {
id = new byte[StringHelper.ID_LENGTH];
input.readBytes(id, 0, id.length);
CodecUtil.checkIndexHeaderSuffix(input, Long.toString(generation, Character.MAX_RADIX));
}
SegmentInfos infos = new SegmentInfos();
infos.id = id;
infos.generation = generation;
infos.lastGeneration = generation;
if (format >= VERSION_53) {
// TODO: in the future (7.0? sigh) we can use this to throw IndexFormatTooOldException ...
// or just rely on the
// minSegmentLuceneVersion check instead:
infos.luceneVersion =
Version.fromBits(input.readVInt(), input.readVInt(), input.readVInt());
} else {
// else compute the min version down below in the for loop
}
infos.version = input.readLong();
infos.counter = input.readInt();
int numSegments = input.readInt();
if (numSegments < 0) {
throw new CorruptIndexException("invalid segment count: " + numSegments, input);
}
if (format >= VERSION_53) {
if (numSegments > 0) {
infos.minSegmentLuceneVersion =
Version.fromBits(input.readVInt(), input.readVInt(), input.readVInt());
if (infos.minSegmentLuceneVersion.onOrAfter(Version.LUCENE_4_0_0_ALPHA) == false) {
throw new IndexFormatTooOldException(
input,
"this index contains a too-old segment (version: "
+ infos.minSegmentLuceneVersion
+ ")");
}
} else {
// else leave as null: no segments
}
} else {
// else we recompute it below as we visit segments; it can't be used for throwing
// IndexFormatTooOldExc, but consumers of
// SegmentInfos can maybe still use it for other reasons
}
long totalDocs = 0;
for (int seg = 0; seg < numSegments; seg++) {
String segName = input.readString();
final byte segmentID[];
if (format >= VERSION_50) {
byte hasID = input.readByte();
if (hasID == 1) {
segmentID = new byte[StringHelper.ID_LENGTH];
input.readBytes(segmentID, 0, segmentID.length);
} else if (hasID == 0) {
segmentID = null; // 4.x segment, doesn't have an ID
} else {
throw new CorruptIndexException("invalid hasID byte, got: " + hasID, input);
}
} else {
segmentID = null;
}
Codec codec = readCodec(input, format < VERSION_53);
SegmentInfo info =
codec.segmentInfoFormat().read(directory, segName, segmentID, IOContext.READ);
info.setCodec(codec);
totalDocs += info.maxDoc();
long delGen = input.readLong();
int delCount = input.readInt();
if (delCount < 0 || delCount > info.maxDoc()) {
throw new CorruptIndexException(
"invalid deletion count: " + delCount + " vs maxDoc=" + info.maxDoc(), input);
}
long fieldInfosGen = -1;
if (format >= VERSION_46) {
fieldInfosGen = input.readLong();
}
long dvGen = -1;
if (format >= VERSION_49) {
dvGen = input.readLong();
} else {
dvGen = fieldInfosGen;
}
SegmentCommitInfo siPerCommit =
new SegmentCommitInfo(info, delCount, delGen, fieldInfosGen, dvGen);
if (format >= VERSION_46) {
if (format < VERSION_49) {
// Recorded per-generation files, which were buggy (see
// LUCENE-5636). We need to read and keep them so we continue to
// reference those files. Unfortunately it means that the files will
// be referenced even if the fields are updated again, until the
// segment is merged.
final int numGensUpdatesFiles = input.readInt();
final Map<Long, Set<String>> genUpdatesFiles;
if (numGensUpdatesFiles == 0) {
genUpdatesFiles = Collections.emptyMap();
} else {
genUpdatesFiles = new HashMap<>(numGensUpdatesFiles);
for (int i = 0; i < numGensUpdatesFiles; i++) {
genUpdatesFiles.put(input.readLong(), input.readStringSet());
}
}
siPerCommit.setGenUpdatesFiles(genUpdatesFiles);
} else {
if (format >= VERSION_51) {
siPerCommit.setFieldInfosFiles(input.readSetOfStrings());
} else {
siPerCommit.setFieldInfosFiles(Collections.unmodifiableSet(input.readStringSet()));
}
final Map<Integer, Set<String>> dvUpdateFiles;
final int numDVFields = input.readInt();
if (numDVFields == 0) {
dvUpdateFiles = Collections.emptyMap();
} else {
Map<Integer, Set<String>> map = new HashMap<>(numDVFields);
for (int i = 0; i < numDVFields; i++) {
if (format >= VERSION_51) {
map.put(input.readInt(), input.readSetOfStrings());
} else {
map.put(input.readInt(), Collections.unmodifiableSet(input.readStringSet()));
}
}
dvUpdateFiles = Collections.unmodifiableMap(map);
}
siPerCommit.setDocValuesUpdatesFiles(dvUpdateFiles);
}
}
infos.add(siPerCommit);
Version segmentVersion = info.getVersion();
if (format < VERSION_53) {
if (infos.minSegmentLuceneVersion == null
|| segmentVersion.onOrAfter(infos.minSegmentLuceneVersion) == false) {
infos.minSegmentLuceneVersion = segmentVersion;
}
} else if (segmentVersion.onOrAfter(infos.minSegmentLuceneVersion) == false) {
throw new CorruptIndexException(
"segments file recorded minSegmentLuceneVersion="
+ infos.minSegmentLuceneVersion
+ " but segment="
+ info
+ " has older version="
+ segmentVersion,
input);
}
}
if (format >= VERSION_51) {
infos.userData = input.readMapOfStrings();
} else {
infos.userData = Collections.unmodifiableMap(input.readStringStringMap());
}
if (format >= VERSION_48) {
CodecUtil.checkFooter(input);
} else {
final long checksumNow = input.getChecksum();
final long checksumThen = input.readLong();
if (checksumNow != checksumThen) {
throw new CorruptIndexException(
"checksum failed (hardware problem?) : expected="
+ Long.toHexString(checksumThen)
+ " actual="
+ Long.toHexString(checksumNow),
input);
}
CodecUtil.checkEOF(input);
}
// LUCENE-6299: check we are in bounds
if (totalDocs > IndexWriter.getActualMaxDocs()) {
throw new CorruptIndexException(
"Too many documents: an index cannot exceed "
+ IndexWriter.getActualMaxDocs()
+ " but readers have total maxDoc="
+ totalDocs,
input);
}
return infos;
}
}
/**
* Returns a {@link CharacterUtils} implementation according to the given {@link Version}
* instance.
*
* @param matchVersion a version instance
* @return a {@link CharacterUtils} implementation according to the given {@link Version}
* instance.
*/
public static CharacterUtils getInstance(final Version matchVersion) {
return matchVersion.onOrAfter(Version.LUCENE_31) ? JAVA_5 : JAVA_4;
}