/**
* 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 final void read(Directory directory, String segmentFileName)
throws CorruptIndexException, IOException {
boolean success = false;
// Clear any previous segments:
this.clear();
ChecksumIndexInput input = new ChecksumIndexInput(directory.openInput(segmentFileName));
generation = generationFromSegmentsFileName(segmentFileName);
lastGeneration = generation;
try {
int format = input.readInt();
if (format < 0) { // file contains explicit format info
// check that it is a format we can understand
if (format < CURRENT_FORMAT)
throw new CorruptIndexException("Unknown format version: " + format);
version = input.readLong(); // read version
counter = input.readInt(); // read counter
} else { // file is in old format without explicit format info
counter = format;
}
for (int i = input.readInt(); i > 0; i--) { // read segmentInfos
SegmentInfo si = new SegmentInfo(directory, format, input);
if (si.getVersion() == null) {
// It's a pre-3.1 segment, upgrade its version to either 3.0 or 2.x
Directory dir = directory;
if (si.getDocStoreOffset() != -1) {
if (si.getDocStoreIsCompoundFile()) {
dir =
new CompoundFileReader(
dir,
IndexFileNames.segmentFileName(
si.getDocStoreSegment(), IndexFileNames.COMPOUND_FILE_STORE_EXTENSION),
1024);
}
} else if (si.getUseCompoundFile()) {
dir =
new CompoundFileReader(
dir,
IndexFileNames.segmentFileName(si.name, IndexFileNames.COMPOUND_FILE_EXTENSION),
1024);
}
try {
String store = si.getDocStoreOffset() != -1 ? si.getDocStoreSegment() : si.name;
si.setVersion(FieldsReader.detectCodeVersion(dir, store));
} finally {
// If we opened the directory, close it
if (dir != directory) dir.close();
}
}
add(si);
}
if (format >= 0) { // in old format the version number may be at the end of the file
if (input.getFilePointer() >= input.length())
version = System.currentTimeMillis(); // old file format without version number
else version = input.readLong(); // read version
}
if (format <= FORMAT_USER_DATA) {
if (format <= FORMAT_DIAGNOSTICS) {
userData = input.readStringStringMap();
} else if (0 != input.readByte()) {
userData = Collections.singletonMap("userData", input.readString());
} else {
userData = Collections.<String, String>emptyMap();
}
} else {
userData = Collections.<String, String>emptyMap();
}
if (format <= FORMAT_CHECKSUM) {
final long checksumNow = input.getChecksum();
final long checksumThen = input.readLong();
if (checksumNow != checksumThen)
throw new CorruptIndexException("checksum mismatch in segments file");
}
success = true;
} finally {
input.close();
if (!success) {
// Clear any segment infos we had loaded so we
// have a clean slate on retry:
this.clear();
}
}
}
/**
* 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;
}
}