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
135
136
137
138
139
140
141
142
143
144
145
146
147
148
|
/*
* Copyright (C) 2013 The Android Open Source Project
*
* Licensed 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.
*/
package com.android.inputmethod.latin.makedict;
import com.android.inputmethod.annotations.UsedForTesting;
import com.android.inputmethod.latin.BinaryDictionary;
import com.android.inputmethod.latin.Dictionary;
import com.android.inputmethod.latin.NgramContext;
import com.android.inputmethod.latin.makedict.FormatSpec.FormatOptions;
import com.android.inputmethod.latin.makedict.FusionDictionary.PtNode;
import com.android.inputmethod.latin.utils.BinaryDictionaryUtils;
import com.android.inputmethod.latin.utils.LocaleUtils;
import java.io.File;
import java.io.IOException;
import java.util.HashMap;
/**
* An implementation of DictEncoder for version 4 binary dictionary.
*/
@UsedForTesting
public class Ver4DictEncoder implements DictEncoder {
private final File mDictPlacedDir;
@UsedForTesting
public Ver4DictEncoder(final File dictPlacedDir) {
mDictPlacedDir = dictPlacedDir;
}
// TODO: This builds a FusionDictionary first and iterates it to add words to the binary
// dictionary. However, it is possible to just add words directly to the binary dictionary
// instead.
// In the long run, when we stop supporting version 2, FusionDictionary will become deprecated
// and we can remove it. Then we'll be able to just call BinaryDictionary directly.
@Override
public void writeDictionary(FusionDictionary dict, FormatOptions formatOptions)
throws IOException, UnsupportedFormatException {
if (formatOptions.mVersion != FormatSpec.VERSION4) {
throw new UnsupportedFormatException("File header has a wrong version number : "
+ formatOptions.mVersion);
}
if (!mDictPlacedDir.isDirectory()) {
throw new UnsupportedFormatException("Given path is not a directory.");
}
if (!BinaryDictionaryUtils.createEmptyDictFile(mDictPlacedDir.getAbsolutePath(),
FormatSpec.VERSION4, LocaleUtils.constructLocaleFromString(
dict.mOptions.mAttributes.get(DictionaryHeader.DICTIONARY_LOCALE_KEY)),
dict.mOptions.mAttributes)) {
throw new IOException("Cannot create dictionary file : "
+ mDictPlacedDir.getAbsolutePath());
}
final BinaryDictionary binaryDict = new BinaryDictionary(mDictPlacedDir.getAbsolutePath(),
0l, mDictPlacedDir.length(), true /* useFullEditDistance */,
LocaleUtils.constructLocaleFromString(dict.mOptions.mAttributes.get(
DictionaryHeader.DICTIONARY_LOCALE_KEY)),
Dictionary.TYPE_USER /* Dictionary type. Does not matter for us */,
true /* isUpdatable */);
if (!binaryDict.isValidDictionary()) {
// Somehow createEmptyDictFile returned true, but the file was not created correctly
throw new IOException("Cannot create dictionary file");
}
for (final WordProperty wordProperty : dict) {
// TODO: switch to addMultipleDictionaryEntries when they support shortcuts
if (null == wordProperty.mShortcutTargets || wordProperty.mShortcutTargets.isEmpty()) {
if (!binaryDict.addUnigramEntry(wordProperty.mWord, wordProperty.getProbability(),
null /* shortcutTarget */, 0 /* shortcutProbability */,
wordProperty.mIsBeginningOfSentence, wordProperty.mIsNotAWord,
wordProperty.mIsBlacklistEntry, 0 /* timestamp */)) {
MakedictLog.e("Cannot add unigram entry for " + wordProperty.mWord);
}
} else {
for (final WeightedString shortcutTarget : wordProperty.mShortcutTargets) {
if (!binaryDict.addUnigramEntry(wordProperty.mWord,
wordProperty.getProbability(),
shortcutTarget.mWord, shortcutTarget.getProbability(),
wordProperty.mIsBeginningOfSentence, wordProperty.mIsNotAWord,
wordProperty.mIsBlacklistEntry, 0 /* timestamp */)) {
MakedictLog.e("Cannot add unigram entry for " + wordProperty.mWord
+ ", shortcutTarget: " + shortcutTarget.mWord);
return;
}
}
}
if (binaryDict.needsToRunGC(true /* mindsBlockByGC */)) {
if (!binaryDict.flushWithGC()) {
MakedictLog.e("Cannot flush dict with GC.");
return;
}
}
}
for (final WordProperty word0Property : dict) {
if (null == word0Property.mBigrams) continue;
for (final WeightedString word1 : word0Property.mBigrams) {
final NgramContext ngramContext =
new NgramContext(new NgramContext.WordInfo(word0Property.mWord));
if (!binaryDict.addNgramEntry(ngramContext, word1.mWord,
word1.getProbability(), 0 /* timestamp */)) {
MakedictLog.e("Cannot add n-gram entry for "
+ ngramContext + " -> " + word1.mWord);
return;
}
if (binaryDict.needsToRunGC(true /* mindsBlockByGC */)) {
if (!binaryDict.flushWithGC()) {
MakedictLog.e("Cannot flush dict with GC.");
return;
}
}
}
}
if (!binaryDict.flushWithGC()) {
MakedictLog.e("Cannot flush dict with GC.");
return;
}
binaryDict.close();
}
@Override
public void setPosition(int position) {
}
@Override
public int getPosition() {
return 0;
}
@Override
public void writePtNodeCount(int ptNodeCount) {
}
@Override
public void writePtNode(PtNode ptNode, FusionDictionary dict,
HashMap<Integer, Integer> codePointToOneByteCodeMap) {
}
}
|
