From 6cfd9d7b79fc5e548a1e684be24e7696e71b48a0 Mon Sep 17 00:00:00 2001 From: Han Jiang Date: Fri, 6 Sep 2013 15:12:24 +0000 Subject: [PATCH] LUCENE-3069: remove impersonate codes, fix typo git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/branches/lucene3069@1520592 13f79535-47bb-0310-9956-ffa450edef68 --- .../codecs/memory/FSTOrdTermsWriter.java | 4 +- .../lucene/codecs/memory/FSTTermsWriter.java | 8 ++-- .../lucene/codecs/BlockTreeTermsReader.java | 4 +- .../lucene41/Lucene41PostingsReader.java | 2 +- .../lucene41/Lucene41PostingsWriter.java | 45 ++----------------- 5 files changed, 13 insertions(+), 50 deletions(-) diff --git a/lucene/codecs/src/java/org/apache/lucene/codecs/memory/FSTOrdTermsWriter.java b/lucene/codecs/src/java/org/apache/lucene/codecs/memory/FSTOrdTermsWriter.java index 81c0dfbcdc6..c11d11e84e9 100644 --- a/lucene/codecs/src/java/org/apache/lucene/codecs/memory/FSTOrdTermsWriter.java +++ b/lucene/codecs/src/java/org/apache/lucene/codecs/memory/FSTOrdTermsWriter.java @@ -94,7 +94,7 @@ import org.apache.lucene.codecs.CodecUtil; * per-field data like number of documents in current field). For each field, there are four blocks: * @@ -126,7 +126,7 @@ import org.apache.lucene.codecs.CodecUtil; *
  • * The format of PostingsHeader and MetaBytes are customized by the specific postings implementation: * they contain arbitrary per-file data (such as parameters or versioning information), and per-term data - * (non-monotonical ones like pulsed postings data). + * (non-monotonic ones like pulsed postings data). *
    • *
  • * During initialization the reader will load all the blocks into memory. SkipBlock will be decoded, so that during seek diff --git a/lucene/codecs/src/java/org/apache/lucene/codecs/memory/FSTTermsWriter.java b/lucene/codecs/src/java/org/apache/lucene/codecs/memory/FSTTermsWriter.java index b48f52c0366..0afa6645fb8 100644 --- a/lucene/codecs/src/java/org/apache/lucene/codecs/memory/FSTTermsWriter.java +++ b/lucene/codecs/src/java/org/apache/lucene/codecs/memory/FSTTermsWriter.java @@ -78,7 +78,7 @@ import org.apache.lucene.codecs.CodecUtil; * with the corresponding term. This part is used by FST to share outputs between arcs. *
    • *
  • - * Generic byte array: Used to store non-monotonical metadata. + * Generic byte array: Used to store non-monotonic metadata. *
    • * *

    @@ -103,14 +103,14 @@ import org.apache.lucene.codecs.CodecUtil; *
  • * The format of PostingsHeader and generic meta bytes are customized by the specific postings implementation: * they contain arbitrary per-file data (such as parameters or versioning information), and per-term data - * (non-monotonical ones like pulsed postings data). + * (non-monotonic ones like pulsed postings data). *
    • *
  • - * The format of TermData is determined by FST, typically monotonical metadata will be dense around shallow arcs, + * The format of TermData is determined by FST, typically monotonic metadata will be dense around shallow arcs, * while in deeper arcs only generic bytes and term statistics exist. *
    • *
  • - * The byte Flag is used to indicate which part of metadata exists on current arc. Specially the monotonical part + * The byte Flag is used to indicate which part of metadata exists on current arc. Specially the monotonic part * is omitted when it is an array of 0s. *
    • *
  • diff --git a/lucene/core/src/java/org/apache/lucene/codecs/BlockTreeTermsReader.java b/lucene/core/src/java/org/apache/lucene/codecs/BlockTreeTermsReader.java index dd8447d447f..5f732a6f128 100644 --- a/lucene/core/src/java/org/apache/lucene/codecs/BlockTreeTermsReader.java +++ b/lucene/core/src/java/org/apache/lucene/codecs/BlockTreeTermsReader.java @@ -616,7 +616,7 @@ public class BlockTreeTermsReader extends FieldsProducer { final BlockTermState termState; - // metadata buffer, holding monotonical values + // metadata buffer, holding monotonic values public long[] longs; // metadata buffer, holding general values public byte[] bytes; @@ -2314,7 +2314,7 @@ public class BlockTreeTermsReader extends FieldsProducer { final BlockTermState state; - // metadata buffer, holding monotonical values + // metadata buffer, holding monotonic values public long[] longs; // metadata buffer, holding general values public byte[] bytes; diff --git a/lucene/core/src/java/org/apache/lucene/codecs/lucene41/Lucene41PostingsReader.java b/lucene/core/src/java/org/apache/lucene/codecs/lucene41/Lucene41PostingsReader.java index 00bb2dfab79..62f6e060b9e 100644 --- a/lucene/core/src/java/org/apache/lucene/codecs/lucene41/Lucene41PostingsReader.java +++ b/lucene/core/src/java/org/apache/lucene/codecs/lucene41/Lucene41PostingsReader.java @@ -195,7 +195,7 @@ public final class Lucene41PostingsReader extends PostingsReaderBase { termState.posStartFP = 0; termState.payStartFP = 0; } - if (version < Lucene41PostingsWriter.VERSION_META_ARRAY) { // impersonation + if (version < Lucene41PostingsWriter.VERSION_META_ARRAY) { // backward compatibility _decodeTerm(in, fieldInfo, termState); return; } diff --git a/lucene/core/src/java/org/apache/lucene/codecs/lucene41/Lucene41PostingsWriter.java b/lucene/core/src/java/org/apache/lucene/codecs/lucene41/Lucene41PostingsWriter.java index 0ca8aa423ca..26421bba401 100644 --- a/lucene/core/src/java/org/apache/lucene/codecs/lucene41/Lucene41PostingsWriter.java +++ b/lucene/core/src/java/org/apache/lucene/codecs/lucene41/Lucene41PostingsWriter.java @@ -67,13 +67,13 @@ public final class Lucene41PostingsWriter extends PostingsWriterBase { // Increment version to change it final static int VERSION_START = 0; final static int VERSION_META_ARRAY = 1; - //final static int VERSION_CURRENT = VERSION_START; final static int VERSION_CURRENT = VERSION_META_ARRAY; final IndexOutput docOut; final IndexOutput posOut; final IndexOutput payOut; + final static IntBlockTermState emptyState = new IntBlockTermState(); IntBlockTermState lastState; // How current field indexes postings: @@ -223,10 +223,7 @@ public final class Lucene41PostingsWriter extends PostingsWriterBase { fieldHasOffsets = indexOptions.compareTo(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS) >= 0; fieldHasPayloads = fieldInfo.hasPayloads(); skipWriter.setField(fieldHasPositions, fieldHasOffsets, fieldHasPayloads); - lastState = newTermState(); - if (VERSION_CURRENT < VERSION_META_ARRAY) { - return 0; - } + lastState = emptyState; if (fieldHasPositions) { if (fieldHasPayloads || fieldHasOffsets) { return 3; // doc + pos + pay FP @@ -519,16 +516,12 @@ public final class Lucene41PostingsWriter extends PostingsWriterBase { // System.out.println(" no skip: docCount=" + docCount); // } } - if (VERSION_CURRENT >= VERSION_META_ARRAY || state.totalTermFreq >= BLOCK_SIZE) { - state.payTermStartFP = payTermStartFP; - } else { - state.payTermStartFP = -1; - } // if (DEBUG) { // System.out.println(" payStartFP=" + payStartFP); // } state.docTermStartFP = docTermStartFP; state.posTermStartFP = posTermStartFP; + state.payTermStartFP = payTermStartFP; state.singletonDocID = singletonDocID; state.skipOffset = skipOffset; state.lastPosBlockOffset = lastPosBlockOffset; @@ -542,11 +535,7 @@ public final class Lucene41PostingsWriter extends PostingsWriterBase { public void encodeTerm(long[] longs, DataOutput out, FieldInfo fieldInfo, BlockTermState _state, boolean absolute) throws IOException { IntBlockTermState state = (IntBlockTermState)_state; if (absolute) { - lastState = newTermState(); - } - if (VERSION_CURRENT < VERSION_META_ARRAY) { // impersonation - _encodeTerm(out, fieldInfo, state); - return; + lastState = emptyState; } longs[0] = state.docTermStartFP - lastState.docTermStartFP; if (fieldHasPositions) { @@ -566,35 +555,9 @@ public final class Lucene41PostingsWriter extends PostingsWriterBase { if (state.skipOffset != -1) { out.writeVLong(state.skipOffset); } - if (state.payTermStartFP == -1) { - state.payTermStartFP = lastState.payTermStartFP; - } lastState = state; } - private void _encodeTerm(DataOutput out, FieldInfo fieldInfo, IntBlockTermState state) throws IOException { - if (state.singletonDocID == -1) { - out.writeVLong(state.docTermStartFP - lastState.docTermStartFP); - lastState.docTermStartFP = state.docTermStartFP; - } else { - out.writeVInt(state.singletonDocID); - } - if (fieldHasPositions) { - out.writeVLong(state.posTermStartFP - lastState.posTermStartFP); - lastState.posTermStartFP = state.posTermStartFP; - if (state.lastPosBlockOffset != -1) { - out.writeVLong(state.lastPosBlockOffset); - } - if ((fieldHasPayloads || fieldHasOffsets) && state.payTermStartFP != -1) { - out.writeVLong(state.payTermStartFP - lastState.payTermStartFP); - lastState.payTermStartFP = state.payTermStartFP; - } - } - if (state.skipOffset != -1) { - out.writeVLong(state.skipOffset); - } - } - @Override public void close() throws IOException { IOUtils.close(docOut, posOut, payOut);