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
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
|
/*
* Copyright (C) 2012 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.utils;
import android.util.Log;
import com.android.inputmethod.annotations.UsedForTesting;
import com.android.inputmethod.latin.makedict.BinaryDictIOUtils;
import com.android.inputmethod.latin.makedict.DictDecoder;
import com.android.inputmethod.latin.makedict.DictEncoder;
import com.android.inputmethod.latin.makedict.FormatSpec;
import com.android.inputmethod.latin.makedict.FormatSpec.FormatOptions;
import com.android.inputmethod.latin.makedict.FusionDictionary;
import com.android.inputmethod.latin.makedict.FusionDictionary.PtNodeArray;
import com.android.inputmethod.latin.makedict.PendingAttribute;
import com.android.inputmethod.latin.makedict.UnsupportedFormatException;
import com.android.inputmethod.latin.personalization.UserHistoryDictionaryBigramList;
import java.io.IOException;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.Map.Entry;
import java.util.TreeMap;
import java.util.concurrent.TimeUnit;
/**
* Reads and writes Binary files for a UserHistoryDictionary.
*
* All the methods in this class are static.
*/
public final class UserHistoryDictIOUtils {
private static final String TAG = UserHistoryDictIOUtils.class.getSimpleName();
private static final boolean DEBUG = false;
public interface OnAddWordListener {
/**
* Callback to be notified when a word is added to the dictionary.
* @param word The added word.
* @param shortcutTarget A shortcut target for this word, or null if none.
* @param frequency The frequency for this word.
* @param shortcutFreq The frequency of the shortcut (0~15, with 15 = whitelist).
* Unspecified if shortcutTarget is null - do not rely on its value.
*/
public void setUnigram(final String word, final String shortcutTarget, final int frequency,
final int shortcutFreq);
public void setBigram(final String word1, final String word2, final int frequency);
}
@UsedForTesting
public interface BigramDictionaryInterface {
public int getFrequency(final String word1, final String word2);
}
/**
* Writes dictionary to file.
*/
@UsedForTesting
public static void writeDictionary(final DictEncoder dictEncoder,
final BigramDictionaryInterface dict, final UserHistoryDictionaryBigramList bigrams,
final FormatOptions formatOptions, final HashMap<String, String> options) {
final FusionDictionary fusionDict = constructFusionDictionary(dict, bigrams, options);
fusionDict.addOptionAttribute(FormatSpec.FileHeader.USES_FORGETTING_CURVE_KEY,
FormatSpec.FileHeader.ATTRIBUTE_VALUE_TRUE);
fusionDict.addOptionAttribute(FormatSpec.FileHeader.DICTIONARY_DATE_KEY,
String.valueOf(TimeUnit.MILLISECONDS.toSeconds(System.currentTimeMillis())));
try {
dictEncoder.writeDictionary(fusionDict, formatOptions);
Log.d(TAG, "end writing");
} catch (IOException e) {
Log.e(TAG, "IO exception while writing file", e);
} catch (UnsupportedFormatException e) {
Log.e(TAG, "Unsupported format", e);
}
}
/**
* Constructs a new FusionDictionary from BigramDictionaryInterface.
*/
@UsedForTesting
static FusionDictionary constructFusionDictionary(final BigramDictionaryInterface dict,
final UserHistoryDictionaryBigramList bigrams, final HashMap<String, String> options) {
final FusionDictionary fusionDict = new FusionDictionary(new PtNodeArray(),
new FusionDictionary.DictionaryOptions(options));
int profTotal = 0;
for (final String word1 : bigrams.keySet()) {
final HashMap<String, Byte> word1Bigrams = bigrams.getBigrams(word1);
for (final String word2 : word1Bigrams.keySet()) {
final int freq = dict.getFrequency(word1, word2);
if (freq == -1) {
// don't add this bigram.
continue;
}
if (DEBUG) {
if (word1 == null) {
Log.d(TAG, "add unigram: " + word2 + "," + Integer.toString(freq));
} else {
Log.d(TAG, "add bigram: " + word1
+ "," + word2 + "," + Integer.toString(freq));
}
profTotal++;
}
if (word1 == null) { // unigram
fusionDict.add(word2, freq, null, false /* isNotAWord */);
} else { // bigram
if (FusionDictionary.findWordInTree(fusionDict.mRootNodeArray, word1) == null) {
fusionDict.add(word1, 2, null, false /* isNotAWord */);
}
fusionDict.setBigram(word1, word2, freq);
}
bigrams.updateBigram(word1, word2, (byte)freq);
}
}
if (DEBUG) {
Log.d(TAG, "add " + profTotal + "words");
}
return fusionDict;
}
/**
* Reads dictionary from file.
*/
public static void readDictionaryBinary(final DictDecoder dictDecoder,
final OnAddWordListener dict) {
final TreeMap<Integer, String> unigrams = CollectionUtils.newTreeMap();
final TreeMap<Integer, Integer> frequencies = CollectionUtils.newTreeMap();
final TreeMap<Integer, ArrayList<PendingAttribute>> bigrams = CollectionUtils.newTreeMap();
try {
dictDecoder.readUnigramsAndBigramsBinary(unigrams, frequencies, bigrams);
} catch (IOException e) {
Log.e(TAG, "IO exception while reading file", e);
} catch (UnsupportedFormatException e) {
Log.e(TAG, "Unsupported format", e);
} catch (ArrayIndexOutOfBoundsException e) {
Log.e(TAG, "ArrayIndexOutOfBoundsException while reading file", e);
}
addWordsFromWordMap(unigrams, frequencies, bigrams, dict);
}
/**
* Adds all unigrams and bigrams in maps to OnAddWordListener.
*/
@UsedForTesting
static void addWordsFromWordMap(final TreeMap<Integer, String> unigrams,
final TreeMap<Integer, Integer> frequencies,
final TreeMap<Integer, ArrayList<PendingAttribute>> bigrams,
final OnAddWordListener to) {
for (Entry<Integer, String> entry : unigrams.entrySet()) {
final String word1 = entry.getValue();
final int unigramFrequency = frequencies.get(entry.getKey());
to.setUnigram(word1, null /* shortcutTarget */, unigramFrequency, 0 /* shortcutFreq */);
final ArrayList<PendingAttribute> attrList = bigrams.get(entry.getKey());
if (attrList != null) {
for (final PendingAttribute attr : attrList) {
final String word2 = unigrams.get(attr.mAddress);
if (word1 == null || word2 == null) {
Log.e(TAG, "Invalid bigram pair detected: " + word1 + ", " + word2);
continue;
}
to.setBigram(word1, word2,
BinaryDictIOUtils.reconstructBigramFrequency(unigramFrequency,
attr.mFrequency));
}
}
}
}
}
|
