|
1 // Copyright 2013 Google Inc. All Rights Reserved. |
|
2 // |
|
3 // Licensed under the Apache License, Version 2.0 (the "License"); |
|
4 // you may not use this file except in compliance with the License. |
|
5 // You may obtain a copy of the License at |
|
6 // |
|
7 // http://www.apache.org/licenses/LICENSE-2.0 |
|
8 // |
|
9 // Unless required by applicable law or agreed to in writing, software |
|
10 // distributed under the License is distributed on an "AS IS" BASIS, |
|
11 // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
|
12 // See the License for the specific language governing permissions and |
|
13 // limitations under the License. |
|
14 |
|
15 // |
|
16 // Author: dsites@google.com (Dick Sites) |
|
17 // |
|
18 // Stuff used only by online detector, not used offline |
|
19 // |
|
20 |
|
21 #ifndef I18N_ENCODINGS_CLD2_INTERNAL_NEW_CLDUTIL_H__ |
|
22 #define I18N_ENCODINGS_CLD2_INTERNAL_NEW_CLDUTIL_H__ |
|
23 |
|
24 #include "cldutil_shared.h" |
|
25 #include "scoreonescriptspan.h" |
|
26 #include "tote.h" |
|
27 |
|
28 namespace CLD2 { |
|
29 |
|
30 // Score up to 64KB of a single script span in one pass |
|
31 // Make a dummy entry off the end to calc length of last span |
|
32 // Return offset of first unused input byte |
|
33 int GetUniHits(const char* text, |
|
34 int letter_offset, int letter_limit, |
|
35 ScoringContext* scoringcontext, |
|
36 ScoringHitBuffer* hitbuffer); |
|
37 |
|
38 // Score up to 64KB of a single script span, doing both delta-bi and |
|
39 // distinct bis in one pass |
|
40 void GetBiHits(const char* text, |
|
41 int letter_offset, int letter_limit, |
|
42 ScoringContext* scoringcontext, |
|
43 ScoringHitBuffer* hitbuffer); |
|
44 |
|
45 // Score up to 64KB of a single script span in one pass |
|
46 // Make a dummy entry off the end to calc length of last span |
|
47 // Return offset of first unused input byte |
|
48 int GetQuadHits(const char* text, |
|
49 int letter_offset, int letter_limit, |
|
50 ScoringContext* scoringcontext, |
|
51 ScoringHitBuffer* hitbuffer); |
|
52 |
|
53 // Score up to 64KB of a single script span, doing both delta-octa and |
|
54 // distinct words in one pass |
|
55 void GetOctaHits(const char* text, |
|
56 int letter_offset, int letter_limit, |
|
57 ScoringContext* scoringcontext, |
|
58 ScoringHitBuffer* hitbuffer); |
|
59 |
|
60 // Not sure if these belong here or in scoreonescriptspan.cc |
|
61 int ReliabilityDelta(int value1, int value2, int gramcount); |
|
62 int ReliabilityExpected(int actual_score_1kb, int expected_score_1kb); |
|
63 |
|
64 // Create a langprob packed value from its parts. |
|
65 uint32 MakeLangProb(Language lang, int qprob); |
|
66 |
|
67 |
|
68 void ProcessProbV2Tote(uint32 probs, Tote* tote); |
|
69 |
|
70 // Return score for a particular per-script language, or zero |
|
71 int GetLangScore(uint32 probs, uint8 pslang); |
|
72 |
|
73 static inline int minint(int a, int b) {return (a < b) ? a: b;} |
|
74 static inline int maxint(int a, int b) {return (a > b) ? a: b;} |
|
75 |
|
76 } // End namespace CLD2 |
|
77 |
|
78 #endif // I18N_ENCODINGS_CLD2_INTERNAL_NEW_CLDUTIL_H__ |
|
79 |
|
80 |