Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/thirdparty/tesseract/src/dict/dawg_cache.cpp @ 2:b50eed0cc0ef upstream

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
ADD: MuPDF v1.26.7: the MuPDF source as downloaded by a default build of PyMuPDF 1.26.4. The directory name has changed: no version number in the expanded directory now.
author Franz Glasner <fzglas.hg@dom66.de>
date Mon, 15 Sep 2025 11:43:07 +0200
parents
children
comparison
equal deleted inserted replaced
1:1d09e1dec1d9 2:b50eed0cc0ef
1 ///////////////////////////////////////////////////////////////////////
2 // File: dawg_cache.cpp
3 // Description: A class that knows about loading and caching dawgs.
4 // Author: David Eger
5 //
6 // (C) Copyright 2012, Google Inc.
7 // Licensed under the Apache License, Version 2.0 (the "License");
8 // you may not use this file except in compliance with the License.
9 // You may obtain a copy of the License at
10 // http://www.apache.org/licenses/LICENSE-2.0
11 // Unless required by applicable law or agreed to in writing, software
12 // distributed under the License is distributed on an "AS IS" BASIS,
13 // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 // See the License for the specific language governing permissions and
15 // limitations under the License.
16 //
17 ///////////////////////////////////////////////////////////////////////
18
19 #include "dawg_cache.h"
20
21 #include "dawg.h"
22 #include "object_cache.h"
23 #include "tessdatamanager.h"
24
25 namespace tesseract {
26
27 struct DawgLoader {
28 DawgLoader(const std::string &lang, TessdataType tessdata_dawg_type, int dawg_debug_level,
29 TessdataManager *data_file)
30 : lang_(lang)
31 , data_file_(data_file)
32 , tessdata_dawg_type_(tessdata_dawg_type)
33 , dawg_debug_level_(dawg_debug_level) {}
34
35 Dawg *Load();
36
37 std::string lang_;
38 TessdataManager *data_file_;
39 TessdataType tessdata_dawg_type_;
40 int dawg_debug_level_;
41 };
42
43 Dawg *DawgCache::GetSquishedDawg(const std::string &lang, TessdataType tessdata_dawg_type,
44 int debug_level, TessdataManager *data_file) {
45 std::string data_id = data_file->GetDataFileName();
46 data_id += kTessdataFileSuffixes[tessdata_dawg_type];
47 DawgLoader loader(lang, tessdata_dawg_type, debug_level, data_file);
48 return dawgs_.Get(data_id, std::bind(&DawgLoader::Load, &loader));
49 }
50
51 Dawg *DawgLoader::Load() {
52 TFile fp;
53 if (!data_file_->GetComponent(tessdata_dawg_type_, &fp)) {
54 return nullptr;
55 }
56 DawgType dawg_type;
57 PermuterType perm_type;
58 switch (tessdata_dawg_type_) {
59 case TESSDATA_PUNC_DAWG:
60 case TESSDATA_LSTM_PUNC_DAWG:
61 dawg_type = DAWG_TYPE_PUNCTUATION;
62 perm_type = PUNC_PERM;
63 break;
64 case TESSDATA_SYSTEM_DAWG:
65 case TESSDATA_LSTM_SYSTEM_DAWG:
66 dawg_type = DAWG_TYPE_WORD;
67 perm_type = SYSTEM_DAWG_PERM;
68 break;
69 case TESSDATA_NUMBER_DAWG:
70 case TESSDATA_LSTM_NUMBER_DAWG:
71 dawg_type = DAWG_TYPE_NUMBER;
72 perm_type = NUMBER_PERM;
73 break;
74 case TESSDATA_BIGRAM_DAWG:
75 dawg_type = DAWG_TYPE_WORD; // doesn't actually matter
76 perm_type = COMPOUND_PERM; // doesn't actually matter
77 break;
78 case TESSDATA_UNAMBIG_DAWG:
79 dawg_type = DAWG_TYPE_WORD;
80 perm_type = SYSTEM_DAWG_PERM;
81 break;
82 case TESSDATA_FREQ_DAWG:
83 dawg_type = DAWG_TYPE_WORD;
84 perm_type = FREQ_DAWG_PERM;
85 break;
86 default:
87 return nullptr;
88 }
89 auto *retval = new SquishedDawg(dawg_type, lang_, perm_type, dawg_debug_level_);
90 if (retval->Load(&fp)) {
91 return retval;
92 }
93 delete retval;
94 return nullptr;
95 }
96
97 } // namespace tesseract