List of usage examples for org.apache.lucene.codecs PostingsReaderBase init
public abstract void init(IndexInput termsIn, SegmentReadState state) throws IOException;
From source file:com.rocana.lucene.codec.v1.RocanaBlockTreeTermsReader.java
License:Apache License
/** Sole constructor. */ public RocanaBlockTreeTermsReader(PostingsReaderBase postingsReader, SegmentReadState state) throws IOException { boolean success = false; IndexInput indexIn = null;/*from w w w . jav a2 s . co m*/ this.postingsReader = postingsReader; this.segment = state.segmentInfo.name; String termsName = IndexFileNames.segmentFileName(segment, state.segmentSuffix, TERMS_EXTENSION); try { termsIn = state.directory.openInput(termsName, state.context); version = CodecUtil.checkIndexHeader(termsIn, TERMS_CODEC_NAME, VERSION_START, VERSION_CURRENT, state.segmentInfo.getId(), state.segmentSuffix); if (version < VERSION_AUTO_PREFIX_TERMS) { // Old (pre-5.2.0) index, no auto-prefix terms: this.anyAutoPrefixTerms = false; } else if (version == VERSION_AUTO_PREFIX_TERMS) { // 5.2.x index, might have auto-prefix terms: this.anyAutoPrefixTerms = true; } else { // 5.3.x index, we record up front if we may have written any auto-prefix terms: assert version >= VERSION_AUTO_PREFIX_TERMS_COND; byte b = termsIn.readByte(); if (b == 0) { this.anyAutoPrefixTerms = false; } else if (b == 1) { this.anyAutoPrefixTerms = true; } else { throw new CorruptIndexException("invalid anyAutoPrefixTerms: expected 0 or 1 but got " + b, termsIn); } } String indexName = IndexFileNames.segmentFileName(segment, state.segmentSuffix, TERMS_INDEX_EXTENSION); indexIn = state.directory.openInput(indexName, state.context); CodecUtil.checkIndexHeader(indexIn, TERMS_INDEX_CODEC_NAME, version, version, state.segmentInfo.getId(), state.segmentSuffix); // IMPORTANT: comment out this one line to prevent checksumming the entire file. // This is the reason we have a custom Lucene codec and forked Lucene classes. //CodecUtil.checksumEntireFile(indexIn); // Have PostingsReader init itself postingsReader.init(termsIn, state); // NOTE: data file is too costly to verify checksum against all the bytes on open, // but for now we at least verify proper structure of the checksum footer: which looks // for FOOTER_MAGIC + algorithmID. This is cheap and can detect some forms of corruption // such as file truncation. CodecUtil.retrieveChecksum(termsIn); // Read per-field details seekDir(termsIn, dirOffset); seekDir(indexIn, indexDirOffset); final int numFields = termsIn.readVInt(); if (numFields < 0) { throw new CorruptIndexException("invalid numFields: " + numFields, termsIn); } for (int i = 0; i < numFields; ++i) { final int field = termsIn.readVInt(); final long numTerms = termsIn.readVLong(); if (numTerms <= 0) { throw new CorruptIndexException("Illegal numTerms for field number: " + field, termsIn); } final int numBytes = termsIn.readVInt(); if (numBytes < 0) { throw new CorruptIndexException( "invalid rootCode for field number: " + field + ", numBytes=" + numBytes, termsIn); } final BytesRef rootCode = new BytesRef(new byte[numBytes]); termsIn.readBytes(rootCode.bytes, 0, numBytes); rootCode.length = numBytes; final FieldInfo fieldInfo = state.fieldInfos.fieldInfo(field); if (fieldInfo == null) { throw new CorruptIndexException("invalid field number: " + field, termsIn); } final long sumTotalTermFreq = fieldInfo.getIndexOptions() == IndexOptions.DOCS ? -1 : termsIn.readVLong(); final long sumDocFreq = termsIn.readVLong(); final int docCount = termsIn.readVInt(); final int longsSize = termsIn.readVInt(); if (longsSize < 0) { throw new CorruptIndexException( "invalid longsSize for field: " + fieldInfo.name + ", longsSize=" + longsSize, termsIn); } BytesRef minTerm = readBytesRef(termsIn); BytesRef maxTerm = readBytesRef(termsIn); if (docCount < 0 || docCount > state.segmentInfo.maxDoc()) { // #docs with field must be <= #docs throw new CorruptIndexException( "invalid docCount: " + docCount + " maxDoc: " + state.segmentInfo.maxDoc(), termsIn); } if (sumDocFreq < docCount) { // #postings must be >= #docs with field throw new CorruptIndexException("invalid sumDocFreq: " + sumDocFreq + " docCount: " + docCount, termsIn); } if (sumTotalTermFreq != -1 && sumTotalTermFreq < sumDocFreq) { // #positions must be >= #postings throw new CorruptIndexException( "invalid sumTotalTermFreq: " + sumTotalTermFreq + " sumDocFreq: " + sumDocFreq, termsIn); } final long indexStartFP = indexIn.readVLong(); RocanaFieldReader previous = fields.put(fieldInfo.name, new RocanaFieldReader(this, fieldInfo, numTerms, rootCode, sumTotalTermFreq, sumDocFreq, docCount, indexStartFP, longsSize, indexIn, minTerm, maxTerm)); if (previous != null) { throw new CorruptIndexException("duplicate field: " + fieldInfo.name, termsIn); } } indexIn.close(); success = true; } finally { if (!success) { // this.close() will close in: IOUtils.closeWhileHandlingException(indexIn, this); } } }