// we don't actually write a .fdx-like index, instead we read the
// stored fields file in entirety up-front and save the offsets
// so we can seek to the documents later.
private void readIndex(int size) throws IOException {
ChecksumIndexInput input = new BufferedChecksumIndexInput(in);
offsets = new long[size];
int upto = 0;
while (!scratch.get().equals(END)) {
SimpleTextUtil.readLine(input, scratch);
if (StringHelper.startsWith(scratch.get(), DOC)) {
offsets[upto] = input.getFilePointer();
upto++;
}
}
SimpleTextUtil.checkFooter(input);
assert upto == offsets.length;
}
@Override
public FieldInfos read(
Directory directory, SegmentInfo segmentInfo, String segmentSuffix, IOContext context)
throws IOException {
final String fileName =
IndexFileNames.segmentFileName(
segmentInfo.name, segmentSuffix, Lucene46FieldInfosFormat.EXTENSION);
try (ChecksumIndexInput input = directory.openChecksumInput(fileName, context)) {
int codecVersion =
CodecUtil.checkHeader(
input,
Lucene46FieldInfosFormat.CODEC_NAME,
Lucene46FieldInfosFormat.FORMAT_START,
Lucene46FieldInfosFormat.FORMAT_CURRENT);
final int size = input.readVInt(); // read in the size
FieldInfo infos[] = new FieldInfo[size];
for (int i = 0; i < size; i++) {
String name = input.readString();
final int fieldNumber = input.readVInt();
if (fieldNumber < 0) {
throw new CorruptIndexException(
"invalid field number for field: " + name + ", fieldNumber=" + fieldNumber, input);
}
byte bits = input.readByte();
boolean isIndexed = (bits & Lucene46FieldInfosFormat.IS_INDEXED) != 0;
boolean storeTermVector = (bits & Lucene46FieldInfosFormat.STORE_TERMVECTOR) != 0;
boolean omitNorms = (bits & Lucene46FieldInfosFormat.OMIT_NORMS) != 0;
boolean storePayloads = (bits & Lucene46FieldInfosFormat.STORE_PAYLOADS) != 0;
final IndexOptions indexOptions;
if (!isIndexed) {
indexOptions = IndexOptions.NONE;
} else if ((bits & Lucene46FieldInfosFormat.OMIT_TERM_FREQ_AND_POSITIONS) != 0) {
indexOptions = IndexOptions.DOCS;
} else if ((bits & Lucene46FieldInfosFormat.OMIT_POSITIONS) != 0) {
indexOptions = IndexOptions.DOCS_AND_FREQS;
} else if ((bits & Lucene46FieldInfosFormat.STORE_OFFSETS_IN_POSTINGS) != 0) {
indexOptions = IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS;
} else {
indexOptions = IndexOptions.DOCS_AND_FREQS_AND_POSITIONS;
}
// DV Types are packed in one byte
byte val = input.readByte();
final DocValuesType docValuesType = getDocValuesType(input, (byte) (val & 0x0F));
final DocValuesType normsType = getDocValuesType(input, (byte) ((val >>> 4) & 0x0F));
final long dvGen = input.readLong();
final Map<String, String> attributes = input.readStringStringMap();
if (isIndexed && omitNorms == false && normsType == DocValuesType.NONE) {
// Undead norms! Lucene42NormsProducer will check this and bring norms back from the
// dead:
UndeadNormsProducer.setUndead(attributes);
}
infos[i] =
new FieldInfo(
name,
fieldNumber,
storeTermVector,
omitNorms,
storePayloads,
indexOptions,
docValuesType,
dvGen,
Collections.unmodifiableMap(attributes));
infos[i].checkConsistency();
}
if (codecVersion >= Lucene46FieldInfosFormat.FORMAT_CHECKSUM) {
CodecUtil.checkFooter(input);
} else {
CodecUtil.checkEOF(input);
}
return new FieldInfos(infos);
}
}
@Test
public void testMixedChecksums() throws IOException {
final ShardId shardId = new ShardId(new Index("index"), 1);
DirectoryService directoryService = new LuceneManagedDirectoryService(random());
Store store =
new Store(
shardId,
ImmutableSettings.EMPTY,
directoryService,
randomDistributor(directoryService),
new DummyShardLock(shardId));
// this time random codec....
IndexWriter writer =
new IndexWriter(
store.directory(),
newIndexWriterConfig(random(), new MockAnalyzer(random()))
.setCodec(actualDefaultCodec()));
int docs = 1 + random().nextInt(100);
for (int i = 0; i < docs; i++) {
Document doc = new Document();
doc.add(
new TextField("id", "" + i, random().nextBoolean() ? Field.Store.YES : Field.Store.NO));
doc.add(
new TextField(
"body",
TestUtil.randomRealisticUnicodeString(random()),
random().nextBoolean() ? Field.Store.YES : Field.Store.NO));
doc.add(
new SortedDocValuesField(
"dv", new BytesRef(TestUtil.randomRealisticUnicodeString(random()))));
writer.addDocument(doc);
}
if (random().nextBoolean()) {
for (int i = 0; i < docs; i++) {
if (random().nextBoolean()) {
Document doc = new Document();
doc.add(
new TextField(
"id", "" + i, random().nextBoolean() ? Field.Store.YES : Field.Store.NO));
doc.add(
new TextField(
"body",
TestUtil.randomRealisticUnicodeString(random()),
random().nextBoolean() ? Field.Store.YES : Field.Store.NO));
writer.updateDocument(new Term("id", "" + i), doc);
}
}
}
if (random().nextBoolean()) {
DirectoryReader.open(writer, random().nextBoolean()).close(); // flush
}
Store.MetadataSnapshot metadata;
// check before we committed
try {
store.getMetadata();
fail("no index present - expected exception");
} catch (IndexNotFoundException ex) {
// expected
}
assertThat(store.getMetadataOrEmpty(), is(Store.MetadataSnapshot.EMPTY)); // nothing committed
writer.commit();
writer.close();
Store.LegacyChecksums checksums = new Store.LegacyChecksums();
metadata = store.getMetadata();
assertThat(metadata.asMap().isEmpty(), is(false));
for (StoreFileMetaData meta : metadata) {
try (IndexInput input = store.directory().openInput(meta.name(), IOContext.DEFAULT)) {
if (meta.checksum() == null) {
String checksum = null;
try {
CodecUtil.retrieveChecksum(input);
fail("expected a corrupt index - posting format has not checksums");
} catch (CorruptIndexException
| IndexFormatTooOldException
| IndexFormatTooNewException ex) {
try (ChecksumIndexInput checksumIndexInput =
store.directory().openChecksumInput(meta.name(), IOContext.DEFAULT)) {
checksumIndexInput.seek(meta.length());
checksum = Store.digestToString(checksumIndexInput.getChecksum());
}
// fine - it's a postings format without checksums
checksums.add(new StoreFileMetaData(meta.name(), meta.length(), checksum, null));
}
} else {
String checksum = Store.digestToString(CodecUtil.retrieveChecksum(input));
assertThat(
"File: " + meta.name() + " has a different checksum",
meta.checksum(),
equalTo(checksum));
assertThat(meta.hasLegacyChecksum(), equalTo(false));
assertThat(meta.writtenBy(), equalTo(Version.LATEST));
}
}
}
assertConsistent(store, metadata);
checksums.write(store);
metadata = store.getMetadata();
assertThat(metadata.asMap().isEmpty(), is(false));
for (StoreFileMetaData meta : metadata) {
assertThat(
"file: " + meta.name() + " has a null checksum", meta.checksum(), not(nullValue()));
if (meta.hasLegacyChecksum()) {
try (ChecksumIndexInput checksumIndexInput =
store.directory().openChecksumInput(meta.name(), IOContext.DEFAULT)) {
checksumIndexInput.seek(meta.length());
assertThat(
meta.checksum(), equalTo(Store.digestToString(checksumIndexInput.getChecksum())));
}
} else {
try (IndexInput input = store.directory().openInput(meta.name(), IOContext.DEFAULT)) {
String checksum = Store.digestToString(CodecUtil.retrieveChecksum(input));
assertThat(
"File: " + meta.name() + " has a different checksum",
meta.checksum(),
equalTo(checksum));
assertThat(meta.hasLegacyChecksum(), equalTo(false));
assertThat(meta.writtenBy(), equalTo(Version.LATEST));
}
}
}
assertConsistent(store, metadata);
TestUtil.checkIndex(store.directory());
assertDeleteContent(store, directoryService);
IOUtils.close(store);
}
/**
* 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;
}
}
