Examples with CorruptIndexException org.apache.lucene.index.CorruptIndexException used on opensource projects

Example 21 with CorruptIndexException

use of org.apache.lucene.index.CorruptIndexException in project lucene-solr by apache.

the class CodecUtil method validateFooter.

private static void validateFooter(IndexInput in) throws IOException {
    long remaining = in.length() - in.getFilePointer();
    long expected = footerLength();
    if (remaining < expected) {
        throw new CorruptIndexException("misplaced codec footer (file truncated?): remaining=" + remaining + ", expected=" + expected + ", fp=" + in.getFilePointer(), in);
    } else if (remaining > expected) {
        throw new CorruptIndexException("misplaced codec footer (file extended?): remaining=" + remaining + ", expected=" + expected + ", fp=" + in.getFilePointer(), in);
    }
    final int magic = in.readInt();
    if (magic != FOOTER_MAGIC) {
        throw new CorruptIndexException("codec footer mismatch (file truncated?): actual footer=" + magic + " vs expected footer=" + FOOTER_MAGIC, in);
    }
    final int algorithmID = in.readInt();
    if (algorithmID != 0) {
        throw new CorruptIndexException("codec footer mismatch: unknown algorithmID: " + algorithmID, in);
    }
}

Example 22 with CorruptIndexException

use of org.apache.lucene.index.CorruptIndexException in project lucene-solr by apache.

the class SimpleTextPointsReader method checkIntegrity.

@Override
public void checkIntegrity() throws IOException {
    BytesRefBuilder scratch = new BytesRefBuilder();
    IndexInput clone = dataIn.clone();
    clone.seek(0);
    // checksum is fixed-width encoded with 20 bytes, plus 1 byte for newline (the space is included in SimpleTextUtil.CHECKSUM):
    long footerStartPos = dataIn.length() - (SimpleTextUtil.CHECKSUM.length + 21);
    ChecksumIndexInput input = new BufferedChecksumIndexInput(clone);
    while (true) {
        SimpleTextUtil.readLine(input, scratch);
        if (input.getFilePointer() >= 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;
        }
    }
}

Example 23 with CorruptIndexException

use of org.apache.lucene.index.CorruptIndexException in project lucene-solr by apache.

the class SimpleTextUtil method checkFooter.

public static void checkFooter(ChecksumIndexInput input) throws IOException {
    BytesRefBuilder scratch = new BytesRefBuilder();
    String expectedChecksum = String.format(Locale.ROOT, "%020d", input.getChecksum());
    readLine(input, scratch);
    if (StringHelper.startsWith(scratch.get(), CHECKSUM) == false) {
        throw new CorruptIndexException("SimpleText failure: expected checksum line but got " + scratch.get().utf8ToString(), input);
    }
    String actualChecksum = new BytesRef(scratch.bytes(), CHECKSUM.length, scratch.length() - CHECKSUM.length).utf8ToString();
    if (!expectedChecksum.equals(actualChecksum)) {
        throw new CorruptIndexException("SimpleText checksum failure: " + actualChecksum + " != " + expectedChecksum, input);
    }
    if (input.length() != input.getFilePointer()) {
        throw new CorruptIndexException("Unexpected stuff at the end of file, please be careful with your text editor!", input);
    }
}

Example 24 with CorruptIndexException

use of org.apache.lucene.index.CorruptIndexException in project lucene-solr by apache.

the class SimpleTextCompoundFormat method getCompoundReader.

@Override
public Directory getCompoundReader(Directory dir, SegmentInfo si, IOContext context) throws IOException {
    String dataFile = IndexFileNames.segmentFileName(si.name, "", DATA_EXTENSION);
    final IndexInput in = dir.openInput(dataFile, context);
    BytesRefBuilder scratch = new BytesRefBuilder();
    // first get to TOC:
    DecimalFormat df = new DecimalFormat(OFFSETPATTERN, DecimalFormatSymbols.getInstance(Locale.ROOT));
    long pos = in.length() - TABLEPOS.length - OFFSETPATTERN.length() - 1;
    in.seek(pos);
    SimpleTextUtil.readLine(in, scratch);
    assert StringHelper.startsWith(scratch.get(), TABLEPOS);
    long tablePos = -1;
    try {
        tablePos = df.parse(stripPrefix(scratch, TABLEPOS)).longValue();
    } catch (ParseException e) {
        throw new CorruptIndexException("can't parse CFS trailer, got: " + scratch.get().utf8ToString(), in);
    }
    // seek to TOC and read it
    in.seek(tablePos);
    SimpleTextUtil.readLine(in, scratch);
    assert StringHelper.startsWith(scratch.get(), TABLE);
    int numEntries = Integer.parseInt(stripPrefix(scratch, TABLE));
    final String[] fileNames = new String[numEntries];
    final long[] startOffsets = new long[numEntries];
    final long[] endOffsets = new long[numEntries];
    for (int i = 0; i < numEntries; i++) {
        SimpleTextUtil.readLine(in, scratch);
        assert StringHelper.startsWith(scratch.get(), TABLENAME);
        fileNames[i] = si.name + IndexFileNames.stripSegmentName(stripPrefix(scratch, TABLENAME));
        if (i > 0) {
            // files must be unique and in sorted order
            assert fileNames[i].compareTo(fileNames[i - 1]) > 0;
        }
        SimpleTextUtil.readLine(in, scratch);
        assert StringHelper.startsWith(scratch.get(), TABLESTART);
        startOffsets[i] = Long.parseLong(stripPrefix(scratch, TABLESTART));
        SimpleTextUtil.readLine(in, scratch);
        assert StringHelper.startsWith(scratch.get(), TABLEEND);
        endOffsets[i] = Long.parseLong(stripPrefix(scratch, TABLEEND));
    }
    return new Directory() {

        private int getIndex(String name) throws IOException {
            int index = Arrays.binarySearch(fileNames, name);
            if (index < 0) {
                throw new FileNotFoundException("No sub-file found (fileName=" + name + " files: " + Arrays.toString(fileNames) + ")");
            }
            return index;
        }

        @Override
        public String[] listAll() throws IOException {
            ensureOpen();
            return fileNames.clone();
        }

        @Override
        public long fileLength(String name) throws IOException {
            ensureOpen();
            int index = getIndex(name);
            return endOffsets[index] - startOffsets[index];
        }

        @Override
        public IndexInput openInput(String name, IOContext context) throws IOException {
            ensureOpen();
            int index = getIndex(name);
            return in.slice(name, startOffsets[index], endOffsets[index] - startOffsets[index]);
        }

        @Override
        public void close() throws IOException {
            in.close();
        }

        // write methods: disabled
        @Override
        public IndexOutput createOutput(String name, IOContext context) {
            throw new UnsupportedOperationException();
        }

        @Override
        public IndexOutput createTempOutput(String prefix, String suffix, IOContext context) {
            throw new UnsupportedOperationException();
        }

        @Override
        public void sync(Collection<String> names) {
            throw new UnsupportedOperationException();
        }

        @Override
        public void deleteFile(String name) {
            throw new UnsupportedOperationException();
        }

        @Override
        public void rename(String source, String dest) {
            throw new UnsupportedOperationException();
        }

        @Override
        public void syncMetaData() {
            throw new UnsupportedOperationException();
        }

        @Override
        public Lock obtainLock(String name) {
            throw new UnsupportedOperationException();
        }
    };
}

Example 25 with CorruptIndexException

use of org.apache.lucene.index.CorruptIndexException in project lucene-solr by apache.

the class Lucene50SegmentInfoFormat method read.

@Override
public SegmentInfo read(Directory dir, String segment, byte[] segmentID, IOContext context) throws IOException {
    final String fileName = IndexFileNames.segmentFileName(segment, "", Lucene50SegmentInfoFormat.SI_EXTENSION);
    try (ChecksumIndexInput input = dir.openChecksumInput(fileName, context)) {
        Throwable priorE = null;
        SegmentInfo si = null;
        try {
            CodecUtil.checkIndexHeader(input, Lucene50SegmentInfoFormat.CODEC_NAME, Lucene50SegmentInfoFormat.VERSION_START, Lucene50SegmentInfoFormat.VERSION_CURRENT, segmentID, "");
            final Version version = Version.fromBits(input.readInt(), input.readInt(), input.readInt());
            final int docCount = input.readInt();
            if (docCount < 0) {
                throw new CorruptIndexException("invalid docCount: " + docCount, input);
            }
            final boolean isCompoundFile = input.readByte() == SegmentInfo.YES;
            final Map<String, String> diagnostics = input.readMapOfStrings();
            final Set<String> files = input.readSetOfStrings();
            final Map<String, String> attributes = input.readMapOfStrings();
            si = new SegmentInfo(dir, version, null, segment, docCount, isCompoundFile, null, diagnostics, segmentID, attributes, null);
            si.setFiles(files);
        } catch (Throwable exception) {
            priorE = exception;
        } finally {
            CodecUtil.checkFooter(input, priorE);
        }
        return si;
    }
}