Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/thirdparty/tesseract/src/training/dawg2wordlist.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: dawg2wordlist.cpp
3 // Description: Program to create a word list from a DAWG and unicharset.
4 // Author: David Eger
5 //
6 // (C) Copyright 2011, 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 "commontraining.h" // CheckSharedLibraryVersion
20 #include "dawg.h"
21 #include "trie.h"
22 #include "unicharset.h"
23
24 #include "serialis.h"
25
26 using namespace tesseract;
27
28 static std::unique_ptr<tesseract::Dawg> LoadSquishedDawg(const UNICHARSET &unicharset, const char *filename) {
29 const int kDictDebugLevel = 1;
30 tesseract::TFile dawg_file;
31 if (!dawg_file.Open(filename, nullptr)) {
32 tprintf("Could not open %s for reading.\n", filename);
33 return nullptr;
34 }
35 tprintf("Loading word list from %s\n", filename);
36 auto retval = std::make_unique<tesseract::SquishedDawg>(tesseract::DAWG_TYPE_WORD, "eng",
37 SYSTEM_DAWG_PERM, kDictDebugLevel);
38 if (!retval->Load(&dawg_file)) {
39 tprintf("Could not read %s\n", filename);
40 return nullptr;
41 }
42 tprintf("Word list loaded.\n");
43 return retval;
44 }
45
46 class WordOutputter {
47 public:
48 WordOutputter(FILE *file) : file_(file) {}
49 void output_word(const char *word) {
50 fprintf(file_, "%s\n", word);
51 }
52
53 private:
54 FILE *file_;
55 };
56
57 // returns 0 if successful.
58 static int WriteDawgAsWordlist(const UNICHARSET &unicharset, const tesseract::Dawg *dawg,
59 const char *outfile_name) {
60 FILE *out = fopen(outfile_name, "wb");
61 if (out == nullptr) {
62 tprintf("Could not open %s for writing.\n", outfile_name);
63 return EXIT_FAILURE;
64 }
65 WordOutputter outputter(out);
66 using namespace std::placeholders; // for _1
67 dawg->iterate_words(unicharset, std::bind(&WordOutputter::output_word, &outputter, _1));
68 return fclose(out);
69 }
70
71 int main(int argc, char *argv[]) {
72 tesseract::CheckSharedLibraryVersion();
73
74 if (argc > 1 && (!strcmp(argv[1], "-v") || !strcmp(argv[1], "--version"))) {
75 printf("%s\n", tesseract::TessBaseAPI::Version());
76 return 0;
77 } else if (argc != 4) {
78 tprintf("Print all the words in a given dawg.\n");
79 tprintf(
80 "Usage: %s -v | --version | %s <unicharset> <dawgfile> "
81 "<wordlistfile>\n",
82 argv[0], argv[0]);
83 return EXIT_FAILURE;
84 }
85 const char *unicharset_file = argv[1];
86 const char *dawg_file = argv[2];
87 const char *wordlist_file = argv[3];
88 UNICHARSET unicharset;
89 if (!unicharset.load_from_file(unicharset_file)) {
90 tprintf("Error loading unicharset from %s.\n", unicharset_file);
91 return EXIT_FAILURE;
92 }
93 auto dict = LoadSquishedDawg(unicharset, dawg_file);
94 if (dict == nullptr) {
95 tprintf("Error loading dictionary from %s.\n", dawg_file);
96 return EXIT_FAILURE;
97 }
98 int retval = WriteDawgAsWordlist(unicharset, dict.get(), wordlist_file);
99 return retval;
100 }