Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/thirdparty/tesseract/src/dict/stopper.h @ 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 ** Filename: stopper.h
3 ** Purpose: Stopping criteria for word classifier.
4 ** Author: Dan Johnson
5 **
6 ** (c) Copyright Hewlett-Packard Company, 1988.
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 #ifndef STOPPER_H
18 #define STOPPER_H
19
20 #include "params.h"
21 #include "ratngs.h"
22
23 #include <tesseract/unichar.h>
24
25 namespace tesseract {
26
27 class WERD_CHOICE;
28
29 using BLOB_WIDTH = uint8_t;
30
31 struct DANGERR_INFO {
32 DANGERR_INFO()
33 : begin(-1)
34 , end(-1)
35 , dangerous(false)
36 , correct_is_ngram(false)
37 , leftmost(INVALID_UNICHAR_ID) {}
38 DANGERR_INFO(int b, int e, bool d, bool n, UNICHAR_ID l)
39 : begin(b), end(e), dangerous(d), correct_is_ngram(n), leftmost(l) {}
40 int begin;
41 int end;
42 bool dangerous;
43 bool correct_is_ngram;
44 UNICHAR_ID leftmost; // in the replacement, what's the leftmost character?
45 };
46
47 using DANGERR = std::vector<DANGERR_INFO>;
48
49 } // namespace tesseract
50
51 #endif