1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
|
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
using System;
using IndexOutput = Lucene.Net.Store.IndexOutput;
using UnicodeUtil = Lucene.Net.Util.UnicodeUtil;
namespace Lucene.Net.Index
{
/// <summary>Consumes doc and freq, writing them using the current
/// index file format
/// </summary>
sealed class FormatPostingsDocsWriter : FormatPostingsDocsConsumer, IDisposable
{
internal IndexOutput out_Renamed;
internal FormatPostingsTermsWriter parent;
internal FormatPostingsPositionsWriter posWriter;
internal DefaultSkipListWriter skipListWriter;
internal int skipInterval;
internal int totalNumDocs;
internal bool omitTermFreqAndPositions;
internal bool storePayloads;
internal long freqStart;
internal FieldInfo fieldInfo;
internal FormatPostingsDocsWriter(SegmentWriteState state, FormatPostingsTermsWriter parent):base()
{
this.parent = parent;
System.String fileName = IndexFileNames.SegmentFileName(parent.parent.segment, IndexFileNames.FREQ_EXTENSION);
state.flushedFiles.Add(fileName);
out_Renamed = parent.parent.dir.CreateOutput(fileName);
totalNumDocs = parent.parent.totalNumDocs;
// TODO: abstraction violation
skipInterval = parent.parent.termsOut.skipInterval;
skipListWriter = parent.parent.skipListWriter;
skipListWriter.SetFreqOutput(out_Renamed);
posWriter = new FormatPostingsPositionsWriter(state, this);
}
internal void SetField(FieldInfo fieldInfo)
{
this.fieldInfo = fieldInfo;
omitTermFreqAndPositions = fieldInfo.omitTermFreqAndPositions;
storePayloads = fieldInfo.storePayloads;
posWriter.SetField(fieldInfo);
}
internal int lastDocID;
internal int df;
/// <summary>Adds a new doc in this term. If this returns null
/// then we just skip consuming positions/payloads.
/// </summary>
internal override FormatPostingsPositionsConsumer AddDoc(int docID, int termDocFreq)
{
int delta = docID - lastDocID;
if (docID < 0 || (df > 0 && delta <= 0))
throw new CorruptIndexException("docs out of order (" + docID + " <= " + lastDocID + " )");
if ((++df % skipInterval) == 0)
{
// TODO: abstraction violation
skipListWriter.SetSkipData(lastDocID, storePayloads, posWriter.lastPayloadLength);
skipListWriter.BufferSkip(df);
}
System.Diagnostics.Debug.Assert(docID < totalNumDocs, "docID=" + docID + " totalNumDocs=" + totalNumDocs);
lastDocID = docID;
if (omitTermFreqAndPositions)
out_Renamed.WriteVInt(delta);
else if (1 == termDocFreq)
out_Renamed.WriteVInt((delta << 1) | 1);
else
{
out_Renamed.WriteVInt(delta << 1);
out_Renamed.WriteVInt(termDocFreq);
}
return posWriter;
}
private TermInfo termInfo = new TermInfo(); // minimize consing
internal UnicodeUtil.UTF8Result utf8 = new UnicodeUtil.UTF8Result();
/// <summary>Called when we are done adding docs to this term </summary>
internal override void Finish()
{
long skipPointer = skipListWriter.WriteSkip(out_Renamed);
// TODO: this is abstraction violation -- we should not
// peek up into parents terms encoding format
termInfo.Set(df, parent.freqStart, parent.proxStart, (int) (skipPointer - parent.freqStart));
// TODO: we could do this incrementally
UnicodeUtil.UTF16toUTF8(parent.currentTerm, parent.currentTermStart, utf8);
if (df > 0)
{
parent.termsOut.Add(fieldInfo.number, utf8.result, utf8.length, termInfo);
}
lastDocID = 0;
df = 0;
}
public void Dispose()
{
// Move to protected method if class becomes unsealed
out_Renamed.Dispose();
posWriter.Dispose();
}
}
}
|
