Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/thirdparty/tesseract/src/wordrec/wordclass.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: wordclass.cpp (Formerly wordclass.c)
4 * Description: Word classifier
5 * Author: Mark Seaman, OCR Technology
6 *
7 * (c) Copyright 1990, 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 "blamer.h" // for blamer_bundle
24 #include "params.h" // for BoolParam
25 #include "render.h" // for display_blob, blob_window, wordrec_blob_pause
26 #include "wordrec.h" // for Wordrec
27
28 struct TBLOB;
29
30 // Include automatically generated configuration file if running autoconf.
31 #ifdef HAVE_CONFIG_H
32 # include "config_auto.h"
33 #endif
34
35 /*----------------------------------------------------------------------
36 F u n c t i o n s
37 ----------------------------------------------------------------------*/
38 namespace tesseract {
39 /**
40 * @name classify_blob
41 *
42 * Classify the this blob if it is not already recorded in the match
43 * table. Attempt to recognize this blob as a character. The recognition
44 * rating for this blob will be stored as a part of the blob. This value
45 * will also be returned to the caller.
46 * @param blob Current blob
47 * @param string The string to display in ScrollView
48 * @param color The colour to use when displayed with ScrollView
49 */
50 BLOB_CHOICE_LIST *Wordrec::classify_blob(TBLOB *blob, const char *string, ScrollView::Color color,
51 BlamerBundle *blamer_bundle) {
52 #ifndef GRAPHICS_DISABLED
53 if (wordrec_display_all_blobs) {
54 display_blob(blob, color);
55 }
56 #endif
57 // TODO(rays) collapse with call_matcher and move all to wordrec.cpp.
58 BLOB_CHOICE_LIST *choices = call_matcher(blob);
59 // If a blob with the same bounding box as one of the truth character
60 // bounding boxes is not classified as the corresponding truth character
61 // blame character classifier for incorrect answer.
62 if (blamer_bundle != nullptr) {
63 blamer_bundle->BlameClassifier(getDict().getUnicharset(), blob->bounding_box(), *choices,
64 wordrec_debug_blamer);
65 }
66 #ifndef GRAPHICS_DISABLED
67 if (classify_debug_level && string) {
68 print_ratings_list(string, choices, getDict().getUnicharset());
69 }
70
71 if (wordrec_blob_pause) {
72 blob_window->Wait();
73 }
74 #endif
75
76 return choices;
77 }
78
79 } // namespace tesseract