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
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
|
/* Copyright 2010 Google Inc. All Rights Reserved.
Distributed under MIT license.
See file LICENSE for detail or copy at https://opensource.org/licenses/MIT
*/
// Transformations on dictionary words.
#ifndef BROTLI_ENC_TRANSFORM_H_
#define BROTLI_ENC_TRANSFORM_H_
#include <string>
#include "./dictionary.h"
namespace brotli {
enum WordTransformType {
kIdentity = 0,
kOmitLast1 = 1,
kOmitLast2 = 2,
kOmitLast3 = 3,
kOmitLast4 = 4,
kOmitLast5 = 5,
kOmitLast6 = 6,
kOmitLast7 = 7,
kOmitLast8 = 8,
kOmitLast9 = 9,
kUppercaseFirst = 10,
kUppercaseAll = 11,
kOmitFirst1 = 12,
kOmitFirst2 = 13,
kOmitFirst3 = 14,
kOmitFirst4 = 15,
kOmitFirst5 = 16,
kOmitFirst6 = 17,
kOmitFirst7 = 18,
kOmitFirst8 = 19,
kOmitFirst9 = 20
};
struct Transform {
const char* prefix;
WordTransformType word_transform;
const char* suffix;
};
static const Transform kTransforms[] = {
{ "", kIdentity, "" },
{ "", kIdentity, " " },
{ " ", kIdentity, " " },
{ "", kOmitFirst1, "" },
{ "", kUppercaseFirst, " " },
{ "", kIdentity, " the " },
{ " ", kIdentity, "" },
{ "s ", kIdentity, " " },
{ "", kIdentity, " of " },
{ "", kUppercaseFirst, "" },
{ "", kIdentity, " and " },
{ "", kOmitFirst2, "" },
{ "", kOmitLast1, "" },
{ ", ", kIdentity, " " },
{ "", kIdentity, ", " },
{ " ", kUppercaseFirst, " " },
{ "", kIdentity, " in " },
{ "", kIdentity, " to " },
{ "e ", kIdentity, " " },
{ "", kIdentity, "\"" },
{ "", kIdentity, "." },
{ "", kIdentity, "\">" },
{ "", kIdentity, "\n" },
{ "", kOmitLast3, "" },
{ "", kIdentity, "]" },
{ "", kIdentity, " for " },
{ "", kOmitFirst3, "" },
{ "", kOmitLast2, "" },
{ "", kIdentity, " a " },
{ "", kIdentity, " that " },
{ " ", kUppercaseFirst, "" },
{ "", kIdentity, ". " },
{ ".", kIdentity, "" },
{ " ", kIdentity, ", " },
{ "", kOmitFirst4, "" },
{ "", kIdentity, " with " },
{ "", kIdentity, "'" },
{ "", kIdentity, " from " },
{ "", kIdentity, " by " },
{ "", kOmitFirst5, "" },
{ "", kOmitFirst6, "" },
{ " the ", kIdentity, "" },
{ "", kOmitLast4, "" },
{ "", kIdentity, ". The " },
{ "", kUppercaseAll, "" },
{ "", kIdentity, " on " },
{ "", kIdentity, " as " },
{ "", kIdentity, " is " },
{ "", kOmitLast7, "" },
{ "", kOmitLast1, "ing " },
{ "", kIdentity, "\n\t" },
{ "", kIdentity, ":" },
{ " ", kIdentity, ". " },
{ "", kIdentity, "ed " },
{ "", kOmitFirst9, "" },
{ "", kOmitFirst7, "" },
{ "", kOmitLast6, "" },
{ "", kIdentity, "(" },
{ "", kUppercaseFirst, ", " },
{ "", kOmitLast8, "" },
{ "", kIdentity, " at " },
{ "", kIdentity, "ly " },
{ " the ", kIdentity, " of " },
{ "", kOmitLast5, "" },
{ "", kOmitLast9, "" },
{ " ", kUppercaseFirst, ", " },
{ "", kUppercaseFirst, "\"" },
{ ".", kIdentity, "(" },
{ "", kUppercaseAll, " " },
{ "", kUppercaseFirst, "\">" },
{ "", kIdentity, "=\"" },
{ " ", kIdentity, "." },
{ ".com/", kIdentity, "" },
{ " the ", kIdentity, " of the " },
{ "", kUppercaseFirst, "'" },
{ "", kIdentity, ". This " },
{ "", kIdentity, "," },
{ ".", kIdentity, " " },
{ "", kUppercaseFirst, "(" },
{ "", kUppercaseFirst, "." },
{ "", kIdentity, " not " },
{ " ", kIdentity, "=\"" },
{ "", kIdentity, "er " },
{ " ", kUppercaseAll, " " },
{ "", kIdentity, "al " },
{ " ", kUppercaseAll, "" },
{ "", kIdentity, "='" },
{ "", kUppercaseAll, "\"" },
{ "", kUppercaseFirst, ". " },
{ " ", kIdentity, "(" },
{ "", kIdentity, "ful " },
{ " ", kUppercaseFirst, ". " },
{ "", kIdentity, "ive " },
{ "", kIdentity, "less " },
{ "", kUppercaseAll, "'" },
{ "", kIdentity, "est " },
{ " ", kUppercaseFirst, "." },
{ "", kUppercaseAll, "\">" },
{ " ", kIdentity, "='" },
{ "", kUppercaseFirst, "," },
{ "", kIdentity, "ize " },
{ "", kUppercaseAll, "." },
{ "\xc2\xa0", kIdentity, "" },
{ " ", kIdentity, "," },
{ "", kUppercaseFirst, "=\"" },
{ "", kUppercaseAll, "=\"" },
{ "", kIdentity, "ous " },
{ "", kUppercaseAll, ", " },
{ "", kUppercaseFirst, "='" },
{ " ", kUppercaseFirst, "," },
{ " ", kUppercaseAll, "=\"" },
{ " ", kUppercaseAll, ", " },
{ "", kUppercaseAll, "," },
{ "", kUppercaseAll, "(" },
{ "", kUppercaseAll, ". " },
{ " ", kUppercaseAll, "." },
{ "", kUppercaseAll, "='" },
{ " ", kUppercaseAll, ". " },
{ " ", kUppercaseFirst, "=\"" },
{ " ", kUppercaseAll, "='" },
{ " ", kUppercaseFirst, "='" },
};
static const size_t kNumTransforms =
sizeof(kTransforms) / sizeof(kTransforms[0]);
static const size_t kOmitLastNTransforms[10] = {
0, 12, 27, 23, 42, 63, 56, 48, 59, 64,
};
static size_t ToUpperCase(uint8_t *p, size_t len) {
if (len == 1 || p[0] < 0xc0) {
if (p[0] >= 'a' && p[0] <= 'z') {
p[0] ^= 32;
}
return 1;
}
if (p[0] < 0xe0) {
p[1] ^= 32;
return 2;
}
if (len == 2) {
return 2;
}
p[2] ^= 5;
return 3;
}
inline std::string TransformWord(
WordTransformType transform_type, const uint8_t* word, size_t len) {
if (transform_type <= kOmitLast9) {
if (len <= transform_type) {
return std::string();
}
return std::string(word, word + len - transform_type);
}
if (transform_type >= kOmitFirst1) {
const size_t skip = transform_type - (kOmitFirst1 - 1);
if (len <= skip) {
return std::string();
}
return std::string(word + skip, word + len);
}
std::string ret = std::string(word, word + len);
uint8_t *uppercase = reinterpret_cast<uint8_t*>(&ret[0]);
if (transform_type == kUppercaseFirst) {
ToUpperCase(uppercase, len);
} else if (transform_type == kUppercaseAll) {
size_t position = 0;
while (position < len) {
size_t step = ToUpperCase(uppercase, len - position);
uppercase += step;
position += step;
}
}
return ret;
}
inline std::string ApplyTransform(
const Transform& t, const uint8_t* word, size_t len) {
return std::string(t.prefix) +
TransformWord(t.word_transform, word, len) + std::string(t.suffix);
}
inline std::string GetTransformedDictionaryWord(size_t len_code,
size_t word_id) {
size_t num_words = 1u << kBrotliDictionarySizeBitsByLength[len_code];
size_t offset = kBrotliDictionaryOffsetsByLength[len_code];
size_t t = word_id / num_words;
size_t word_idx = word_id % num_words;
offset += len_code * word_idx;
const uint8_t* word = &kBrotliDictionary[offset];
return ApplyTransform(kTransforms[t], word, len_code);
}
} // namespace brotli
#endif // BROTLI_ENC_TRANSFORM_H_
|
