Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/thirdparty/tesseract/src/training/ambiguous_words.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: ambiguous_words.cpp
3 // Description: A program that takes a text file with a list of words as
4 // input (one per line) and outputs a file with the words
5 // that were found in the dictionary followed by the words
6 // that are ambiguous to them.
7 // Author: Rika Antonova
8 //
9 // (C) Copyright 2011, Google Inc.
10 // Licensed under the Apache License, Version 2.0 (the "License");
11 // you may not use this file except in compliance with the License.
12 // You may obtain a copy of the License at
13 // http://www.apache.org/licenses/LICENSE-2.0
14 // Unless required by applicable law or agreed to in writing, software
15 // distributed under the License is distributed on an "AS IS" BASIS,
16 // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
17 // See the License for the specific language governing permissions and
18 // limitations under the License.
19 //
20 ///////////////////////////////////////////////////////////////////////
21 //
22
23 #include "commontraining.h" // CheckSharedLibraryVersion
24 #include "dict.h"
25 #include "tesseractclass.h"
26
27 #include <tesseract/baseapi.h>
28 #include "helpers.h"
29
30 int main(int argc, char **argv) {
31 tesseract::CheckSharedLibraryVersion();
32
33 // Parse input arguments.
34 if (argc > 1 && (!strcmp(argv[1], "-v") || !strcmp(argv[1], "--version"))) {
35 printf("%s\n", tesseract::TessBaseAPI::Version());
36 return EXIT_SUCCESS;
37 } else if (argc != 4 && (argc != 6 || strcmp(argv[1], "-l") != 0)) {
38 printf(
39 "Usage: %s -v | --version | %s [-l lang] tessdata_dir wordlist_file"
40 " output_ambiguous_wordlist_file\n",
41 argv[0], argv[0]);
42 return EXIT_FAILURE;
43 }
44 int argv_offset = 0;
45 std::string lang;
46 if (argc == 6) {
47 lang = argv[2];
48 argv_offset = 2;
49 } else {
50 lang = "eng";
51 }
52 const char *tessdata_dir = argv[++argv_offset];
53 const char *input_file_str = argv[++argv_offset];
54 const char *output_file_str = argv[++argv_offset];
55
56 // Initialize Tesseract.
57 tesseract::TessBaseAPI api;
58 std::vector<std::string> vars_vec;
59 std::vector<std::string> vars_values;
60 vars_vec.emplace_back("output_ambig_words_file");
61 vars_values.emplace_back(output_file_str);
62 api.Init(tessdata_dir, lang.c_str(), tesseract::OEM_TESSERACT_ONLY, nullptr, 0, &vars_vec,
63 &vars_values, false);
64 tesseract::Dict &dict = api.tesseract()->getDict();
65 FILE *input_file = fopen(input_file_str, "rb");
66 if (input_file == nullptr) {
67 tesseract::tprintf("Failed to open input wordlist file %s\n", input_file_str);
68 return EXIT_FAILURE;
69 }
70 char str[CHARS_PER_LINE];
71
72 // Read word list and call Dict::NoDangerousAmbig() for each word
73 // to record ambiguities in the output file.
74 while (fgets(str, CHARS_PER_LINE, input_file) != nullptr) {
75 tesseract::chomp_string(str); // remove newline
76 tesseract::WERD_CHOICE word(str, dict.getUnicharset());
77 dict.NoDangerousAmbig(&word, nullptr, false, nullptr);
78 }
79 // Clean up.
80 fclose(input_file);
81 return EXIT_SUCCESS;
82 }