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
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
|
/*
* 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.makedict;
import com.android.inputmethod.latin.Constants;
import com.android.inputmethod.latin.makedict.BinaryDictInputOutput.FusionDictionaryBufferInterface;
import com.android.inputmethod.latin.makedict.FormatSpec.FileHeader;
import com.android.inputmethod.latin.makedict.FormatSpec.FormatOptions;
import com.android.inputmethod.latin.makedict.FusionDictionary.CharGroup;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Map;
import java.util.Stack;
public class BinaryDictIOUtils {
private static final boolean DBG = false;
private static class Position {
public static final int NOT_READ_GROUPCOUNT = -1;
public int mAddress;
public int mNumOfCharGroup;
public int mPosition;
public int mLength;
public Position(int address, int length) {
mAddress = address;
mLength = length;
mNumOfCharGroup = NOT_READ_GROUPCOUNT;
}
}
/**
* Tours all node without recursive call.
*/
private static void readUnigramsAndBigramsBinaryInner(
final FusionDictionaryBufferInterface buffer, final int headerSize,
final Map<Integer, String> words, final Map<Integer, Integer> frequencies,
final Map<Integer, ArrayList<PendingAttribute>> bigrams,
final FormatOptions formatOptions) {
int[] pushedChars = new int[FormatSpec.MAX_WORD_LENGTH + 1];
Stack<Position> stack = new Stack<Position>();
int index = 0;
Position initPos = new Position(headerSize, 0);
stack.push(initPos);
while (!stack.empty()) {
Position p = stack.peek();
if (DBG) {
MakedictLog.d("read: address=" + p.mAddress + ", numOfCharGroup=" +
p.mNumOfCharGroup + ", position=" + p.mPosition + ", length=" + p.mLength);
}
if (buffer.position() != p.mAddress) buffer.position(p.mAddress);
if (index != p.mLength) index = p.mLength;
if (p.mNumOfCharGroup == Position.NOT_READ_GROUPCOUNT) {
p.mNumOfCharGroup = BinaryDictInputOutput.readCharGroupCount(buffer);
p.mAddress += BinaryDictInputOutput.getGroupCountSize(p.mNumOfCharGroup);
p.mPosition = 0;
}
CharGroupInfo info = BinaryDictInputOutput.readCharGroup(buffer,
p.mAddress - headerSize, formatOptions);
for (int i = 0; i < info.mCharacters.length; ++i) {
pushedChars[index++] = info.mCharacters[i];
}
p.mPosition++;
if (info.mFrequency != FusionDictionary.CharGroup.NOT_A_TERMINAL) { // found word
words.put(info.mOriginalAddress, new String(pushedChars, 0, index));
frequencies.put(info.mOriginalAddress, info.mFrequency);
if (info.mBigrams != null) bigrams.put(info.mOriginalAddress, info.mBigrams);
}
if (p.mPosition == p.mNumOfCharGroup) {
if (formatOptions.mHasLinkedListNode) {
final int forwardLinkAddress = buffer.readUnsignedInt24();
if (forwardLinkAddress != FormatSpec.NO_FORWARD_LINK_ADDRESS) {
// the node has a forward link.
p.mNumOfCharGroup = Position.NOT_READ_GROUPCOUNT;
p.mAddress = forwardLinkAddress;
} else {
stack.pop();
}
} else {
stack.pop();
}
} else {
// the node has more groups.
p.mAddress = buffer.position();
}
if (BinaryDictInputOutput.hasChildrenAddress(info.mChildrenAddress)) {
Position childrenPos = new Position(info.mChildrenAddress + headerSize, index);
stack.push(childrenPos);
}
}
}
/**
* Reads unigrams and bigrams from the binary file.
* Doesn't make the memory representation of the dictionary.
*
* @param buffer the buffer to read.
* @param words the map to store the address as a key and the word as a value.
* @param frequencies the map to store the address as a key and the frequency as a value.
* @param bigrams the map to store the address as a key and the list of address as a value.
* @throws IOException
* @throws UnsupportedFormatException
*/
public static void readUnigramsAndBigramsBinary(final FusionDictionaryBufferInterface buffer,
final Map<Integer, String> words, final Map<Integer, Integer> frequencies,
final Map<Integer, ArrayList<PendingAttribute>> bigrams) throws IOException,
UnsupportedFormatException {
// Read header
final FileHeader header = BinaryDictInputOutput.readHeader(buffer);
readUnigramsAndBigramsBinaryInner(buffer, header.mHeaderSize, words, frequencies, bigrams,
header.mFormatOptions);
}
/**
* Gets the address of the last CharGroup of the exact matching word in the dictionary.
* If no match is found, returns NOT_VALID_WORD.
*
* @param buffer the buffer to read.
* @param word the word we search for.
* @return the address of the terminal node.
* @throws IOException
* @throws UnsupportedFormatException
*/
public static int getTerminalPosition(final FusionDictionaryBufferInterface buffer,
final String word) throws IOException, UnsupportedFormatException {
if (word == null) return FormatSpec.NOT_VALID_WORD;
if (buffer.position() != 0) buffer.position(0);
final FileHeader header = BinaryDictInputOutput.readHeader(buffer);
int wordPos = 0;
final int wordLen = word.codePointCount(0, word.length());
for (int depth = 0; depth < Constants.Dictionary.MAX_WORD_LENGTH; ++depth) {
if (wordPos >= wordLen) return FormatSpec.NOT_VALID_WORD;
int groupOffset = buffer.position() - header.mHeaderSize;
final int charGroupCount = BinaryDictInputOutput.readCharGroupCount(buffer);
groupOffset += BinaryDictInputOutput.getGroupCountSize(charGroupCount);
for (int i = 0; i < charGroupCount; ++i) {
final int charGroupPos = buffer.position();
final CharGroupInfo currentInfo = BinaryDictInputOutput.readCharGroup(buffer,
buffer.position(), header.mFormatOptions);
boolean same = true;
for (int p = 0, j = word.offsetByCodePoints(0, wordPos);
p < currentInfo.mCharacters.length;
++p, j = word.offsetByCodePoints(j, 1)) {
if (wordPos + p >= wordLen
|| word.codePointAt(j) != currentInfo.mCharacters[p]) {
same = false;
break;
}
}
if (same) {
if (wordPos + currentInfo.mCharacters.length == wordLen) {
if (currentInfo.mFrequency == CharGroup.NOT_A_TERMINAL) {
return FormatSpec.NOT_VALID_WORD;
} else {
return charGroupPos;
}
}
wordPos += currentInfo.mCharacters.length;
if (currentInfo.mChildrenAddress == FormatSpec.NO_CHILDREN_ADDRESS) {
return FormatSpec.NOT_VALID_WORD;
}
buffer.position(currentInfo.mChildrenAddress);
break;
}
groupOffset = currentInfo.mEndAddress;
// not found
if (i >= charGroupCount - 1) {
return FormatSpec.NOT_VALID_WORD;
}
}
}
return FormatSpec.NOT_VALID_WORD;
}
}
|
