Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/thirdparty/tesseract/src/wordrec/pieces.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 *
3 * File: pieces.cpp
4 * Description:
5 * Author: Mark Seaman, OCR Technology
6 *
7 * (c) Copyright 1987, Hewlett-Packard Company.
8 ** Licensed under the Apache License, Version 2.0 (the "License");
9 ** you may not use this file except in compliance with the License.
10 ** You may obtain a copy of the License at
11 ** http://www.apache.org/licenses/LICENSE-2.0
12 ** Unless required by applicable law or agreed to in writing, software
13 ** distributed under the License is distributed on an "AS IS" BASIS,
14 ** WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15 ** See the License for the specific language governing permissions and
16 ** limitations under the License.
17 *
18 *****************************************************************************/
19 /*----------------------------------------------------------------------
20 I n c l u d e s
21 ----------------------------------------------------------------------*/
22
23 #include "blobs.h"
24 #include "helpers.h"
25 #include "matrix.h"
26 #include "ratngs.h"
27 #include "seam.h"
28 #include "wordrec.h"
29
30 // Include automatically generated configuration file if running autoconf.
31 #ifdef HAVE_CONFIG_H
32 # include "config_auto.h"
33 #endif
34
35 using tesseract::ScoredFont;
36
37 /*----------------------------------------------------------------------
38 F u n c t i o n s
39 ----------------------------------------------------------------------*/
40
41 /**********************************************************************
42 * classify_piece
43 *
44 * Create a larger piece from a collection of smaller ones. Classify
45 * it and return the results. Take the large piece apart to leave
46 * the collection of small pieces un modified.
47 **********************************************************************/
48 namespace tesseract {
49 BLOB_CHOICE_LIST *Wordrec::classify_piece(const std::vector<SEAM *> &seams, int16_t start,
50 int16_t end, const char *description, TWERD *word,
51 BlamerBundle *blamer_bundle) {
52 if (end > start) {
53 SEAM::JoinPieces(seams, word->blobs, start, end);
54 }
55 BLOB_CHOICE_LIST *choices =
56 classify_blob(word->blobs[start], description, ScrollView::WHITE, blamer_bundle);
57 // Set the matrix_cell_ entries in all the BLOB_CHOICES.
58 BLOB_CHOICE_IT bc_it(choices);
59 for (bc_it.mark_cycle_pt(); !bc_it.cycled_list(); bc_it.forward()) {
60 bc_it.data()->set_matrix_cell(start, end);
61 }
62
63 if (end > start) {
64 SEAM::BreakPieces(seams, word->blobs, start, end);
65 }
66
67 return (choices);
68 }
69
70 template <class BLOB_CHOICE>
71 int SortByUnicharID(const void *void1, const void *void2) {
72 const BLOB_CHOICE *p1 = *static_cast<const BLOB_CHOICE *const *>(void1);
73 const BLOB_CHOICE *p2 = *static_cast<const BLOB_CHOICE *const *>(void2);
74
75 return p1->unichar_id() - p2->unichar_id();
76 }
77
78 template <class BLOB_CHOICE>
79 int SortByRating(const void *void1, const void *void2) {
80 const BLOB_CHOICE *p1 = *static_cast<const BLOB_CHOICE *const *>(void1);
81 const BLOB_CHOICE *p2 = *static_cast<const BLOB_CHOICE *const *>(void2);
82
83 if (p1->rating() < p2->rating()) {
84 return 1;
85 }
86 return -1;
87 }
88
89 } // namespace tesseract