summaryrefslogtreecommitdiffstats
path: root/application/basilisk/components/translation/cld2/internal/compact_lang_det.cc
blob: ccc6588fcb538a0828f92261b4c189fed1fa6075 (plain)
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
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
// Copyright 2013 Google Inc. All Rights Reserved.
//
// 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.

//
// Author: dsites@google.com (Dick Sites)
//

#include <stdio.h>
#include <stdlib.h>

#include "../public/compact_lang_det.h"
#include "../public/encodings.h"
#include "compact_lang_det_impl.h"
#include "integral_types.h"
#include "lang_script.h"

namespace CLD2 {

// String is "code_version - data_scrape_date"
//static const char* kDetectLanguageVersion = "V2.0 - 20130715";


// Large-table version for all ~160 languages
// Small-table version for all ~60 languages

// Scan interchange-valid UTF-8 bytes and detect most likely language
Language DetectLanguage(
                          const char* buffer,
                          int buffer_length,
                          bool is_plain_text,
                          bool* is_reliable) {
  bool allow_extended_lang = false;
  Language language3[3];
  int percent3[3];
  double normalized_score3[3];
  int text_bytes;
  int flags = 0;
  Language plus_one = UNKNOWN_LANGUAGE;
  const char* tld_hint = "";
  int encoding_hint = UNKNOWN_ENCODING;
  Language language_hint = UNKNOWN_LANGUAGE;
  CLDHints cldhints = {NULL, tld_hint, encoding_hint, language_hint};

  Language lang = DetectLanguageSummaryV2(
                          buffer,
                          buffer_length,
                          is_plain_text,
                          &cldhints,
                          allow_extended_lang,
                          flags,
                          plus_one,
                          language3,
                          percent3,
                          normalized_score3,
                          NULL,
                          &text_bytes,
                          is_reliable);
  // Default to English
  if (lang == UNKNOWN_LANGUAGE) {
    lang = ENGLISH;
  }
  return lang;
}

// Scan interchange-valid UTF-8 bytes and detect list of top 3 languages.
Language DetectLanguageSummary(
                          const char* buffer,
                          int buffer_length,
                          bool is_plain_text,
                          Language* language3,
                          int* percent3,
                          int* text_bytes,
                          bool* is_reliable) {
  double normalized_score3[3];
  bool allow_extended_lang = false;
  int flags = 0;
  Language plus_one = UNKNOWN_LANGUAGE;
  const char* tld_hint = "";
  int encoding_hint = UNKNOWN_ENCODING;
  Language language_hint = UNKNOWN_LANGUAGE;
  CLDHints cldhints = {NULL, tld_hint, encoding_hint, language_hint};

  Language lang = DetectLanguageSummaryV2(
                          buffer,
                          buffer_length,
                          is_plain_text,
                          &cldhints,
                          allow_extended_lang,
                          flags,
                          plus_one,
                          language3,
                          percent3,
                          normalized_score3,
                          NULL,
                          text_bytes,
                          is_reliable);
  // Default to English
  if (lang == UNKNOWN_LANGUAGE) {
    lang = ENGLISH;
  }
  return lang;
}

// Same as above, with hints supplied
// Scan interchange-valid UTF-8 bytes and detect list of top 3 languages.
Language DetectLanguageSummary(
                          const char* buffer,
                          int buffer_length,
                          bool is_plain_text,
                          const char* tld_hint,       // "id" boosts Indonesian
                          int encoding_hint,          // SJS boosts Japanese
                          Language language_hint,     // ITALIAN boosts it
                          Language* language3,
                          int* percent3,
                          int* text_bytes,
                          bool* is_reliable) {
  double normalized_score3[3];
  bool allow_extended_lang = false;
  int flags = 0;
  Language plus_one = UNKNOWN_LANGUAGE;
  CLDHints cldhints = {NULL, tld_hint, encoding_hint, language_hint};

  Language lang = DetectLanguageSummaryV2(
                          buffer,
                          buffer_length,
                          is_plain_text,
                          &cldhints,
                          allow_extended_lang,
                          flags,
                          plus_one,
                          language3,
                          percent3,
                          normalized_score3,
                          NULL,
                          text_bytes,
                          is_reliable);
  // Default to English
  if (lang == UNKNOWN_LANGUAGE) {
    lang = ENGLISH;
  }
  return lang;
}


// Scan interchange-valid UTF-8 bytes and detect list of top 3 extended
// languages.
// Extended languages are additional Google interface languages and Unicode
// single-language scripts, from ext_lang_enc.h
Language ExtDetectLanguageSummary(
                          const char* buffer,
                          int buffer_length,
                          bool is_plain_text,
                          Language* language3,
                          int* percent3,
                          int* text_bytes,
                          bool* is_reliable) {
  double normalized_score3[3];
  bool allow_extended_lang = true;
  int flags = 0;
  Language plus_one = UNKNOWN_LANGUAGE;
  const char* tld_hint = "";
  int encoding_hint = UNKNOWN_ENCODING;
  Language language_hint = UNKNOWN_LANGUAGE;
  CLDHints cldhints = {NULL, tld_hint, encoding_hint, language_hint};

  Language lang = DetectLanguageSummaryV2(
                          buffer,
                          buffer_length,
                          is_plain_text,
                          &cldhints,
                          allow_extended_lang,
                          flags,
                          plus_one,
                          language3,
                          percent3,
                          normalized_score3,
                          NULL,
                          text_bytes,
                          is_reliable);
  // Do not default to English
  return lang;
}

// Same as above, with hints supplied
// Scan interchange-valid UTF-8 bytes and detect list of top 3 extended
// languages.
// Extended languages are additional Google interface languages and Unicode
// single-language scripts, from ext_lang_enc.h
Language ExtDetectLanguageSummary(
                          const char* buffer,
                          int buffer_length,
                          bool is_plain_text,
                          const char* tld_hint,       // "id" boosts Indonesian
                          int encoding_hint,          // SJS boosts Japanese
                          Language language_hint,     // ITALIAN boosts it
                          Language* language3,
                          int* percent3,
                          int* text_bytes,
                          bool* is_reliable) {
  double normalized_score3[3];
  bool allow_extended_lang = true;
  int flags = 0;
  Language plus_one = UNKNOWN_LANGUAGE;
  CLDHints cldhints = {NULL, tld_hint, encoding_hint, language_hint};

  Language lang = DetectLanguageSummaryV2(
                          buffer,
                          buffer_length,
                          is_plain_text,
                          &cldhints,
                          allow_extended_lang,
                          flags,
                          plus_one,
                          language3,
                          percent3,
                          normalized_score3,
                          NULL,
                          text_bytes,
                          is_reliable);
  // Do not default to English
  return lang;
}

// Same as above, and also returns internal language scores as a ratio to
// normal score for real text in that language. Scores close to 1.0 indicate
// normal text, while scores far away from 1.0 indicate badly-skewed text or
// gibberish
//
Language ExtDetectLanguageSummary(
                        const char* buffer,
                        int buffer_length,
                        bool is_plain_text,
                        const char* tld_hint,       // "id" boosts Indonesian
                        int encoding_hint,          // SJS boosts Japanese
                        Language language_hint,     // ITALIAN boosts it
                        Language* language3,
                        int* percent3,
                        double* normalized_score3,
                        int* text_bytes,
                        bool* is_reliable) {
  bool allow_extended_lang = true;
  int flags = 0;
  Language plus_one = UNKNOWN_LANGUAGE;
  CLDHints cldhints = {NULL, tld_hint, encoding_hint, language_hint};

  Language lang = DetectLanguageSummaryV2(
                          buffer,
                          buffer_length,
                          is_plain_text,
                          &cldhints,
                          allow_extended_lang,
                          flags,
                          plus_one,
                          language3,
                          percent3,
                          normalized_score3,
                          NULL,
                          text_bytes,
                          is_reliable);
  // Do not default to English
  return lang;
}

// Use this one.
// Hints are collected into a struct.
// Flags are passed in (normally zero).
//
// Also returns 3 internal language scores as a ratio to
// normal score for real text in that language. Scores close to 1.0 indicate
// normal text, while scores far away from 1.0 indicate badly-skewed text or
// gibberish
//
// Returns a vector of chunks in different languages, so that caller may
// spell-check, translate, or otherwaise process different parts of the input
// buffer in language-dependant ways.
//
Language ExtDetectLanguageSummary(
                        const char* buffer,
                        int buffer_length,
                        bool is_plain_text,
                        const CLDHints* cld_hints,
                        int flags,
                        Language* language3,
                        int* percent3,
                        double* normalized_score3,
                        ResultChunkVector* resultchunkvector,
                        int* text_bytes,
                        bool* is_reliable) {
  bool allow_extended_lang = true;
  Language plus_one = UNKNOWN_LANGUAGE;

  Language lang = DetectLanguageSummaryV2(
                          buffer,
                          buffer_length,
                          is_plain_text,
                          cld_hints,
                          allow_extended_lang,
                          flags,
                          plus_one,
                          language3,
                          percent3,
                          normalized_score3,
                          resultchunkvector,
                          text_bytes,
                          is_reliable);
  // Do not default to English
  return lang;
}

}       // End namespace CLD2