Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/thirdparty/tesseract/src/textord/blkocc.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: blkocc.cpp (Formerly blockocc.c)
4 * Description: Block Occupancy routines
5 * Author: Chris Newton
6 *
7 * (c) Copyright 1991, 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 #include "blkocc.h"
21
22 #include "drawtord.h"
23 #include "errcode.h"
24
25 #include <cctype>
26 #include <cmath>
27
28 #include "helpers.h"
29
30 namespace tesseract {
31
32 double_VAR(textord_underline_threshold, 0.5, "Fraction of width occupied");
33
34 // Forward declarations of static functions
35 static void horizontal_cblob_projection(C_BLOB *blob, // blob to project
36 STATS *stats); // output
37 static void horizontal_coutline_projection(C_OUTLINE *outline,
38 STATS *stats); // output
39
40 /**
41 * test_underline
42 *
43 * Check to see if the blob is an underline.
44 * Return true if it is.
45 */
46
47 bool test_underline( // look for underlines
48 bool testing_on, ///< drawing blob
49 C_BLOB *blob, ///< blob to test
50 int16_t baseline, ///< coords of baseline
51 int16_t xheight ///< height of line
52 ) {
53 TDimension occ;
54 STATS projection;
55
56 auto blob_box = blob->bounding_box();
57 auto blob_width = blob->bounding_box().width();
58 projection.set_range(blob_box.bottom(), blob_box.top());
59 if (testing_on) {
60 // blob->plot(to_win,GOLDENROD,GOLDENROD);
61 // line_color_index(to_win,GOLDENROD);
62 // move2d(to_win,blob_box.left(),baseline);
63 // draw2d(to_win,blob_box.right(),baseline);
64 // move2d(to_win,blob_box.left(),baseline+xheight);
65 // draw2d(to_win,blob_box.right(),baseline+xheight);
66 tprintf("Testing underline on blob at (%d,%d)->(%d,%d), base=%d\nOccs:",
67 blob->bounding_box().left(), blob->bounding_box().bottom(),
68 blob->bounding_box().right(), blob->bounding_box().top(), baseline);
69 }
70 horizontal_cblob_projection(blob, &projection);
71 int32_t desc_occ = 0;
72 for (occ = blob_box.bottom(); occ < baseline; occ++) {
73 if (occ <= blob_box.top() && projection.pile_count(occ) > desc_occ) {
74 // max in region
75 desc_occ = projection.pile_count(occ);
76 }
77 }
78 int32_t x_occ = 0;
79 for (occ = baseline; occ <= baseline + xheight; occ++) {
80 if (occ >= blob_box.bottom() && occ <= blob_box.top() && projection.pile_count(occ) > x_occ) {
81 // max in region
82 x_occ = projection.pile_count(occ);
83 }
84 }
85 int32_t asc_occ = 0;
86 for (occ = baseline + xheight + 1; occ <= blob_box.top(); occ++) {
87 if (occ >= blob_box.bottom() && projection.pile_count(occ) > asc_occ) {
88 asc_occ = projection.pile_count(occ);
89 }
90 }
91 if (testing_on) {
92 tprintf("%d %d %d\n", desc_occ, x_occ, asc_occ);
93 }
94 if (desc_occ == 0 && x_occ == 0 && asc_occ == 0) {
95 tprintf("Bottom=%d, top=%d, base=%d, x=%d\n", blob_box.bottom(), blob_box.top(), baseline,
96 xheight);
97 projection.print();
98 }
99 if (desc_occ > x_occ + x_occ && desc_occ > blob_width * textord_underline_threshold) {
100 return true; // real underline
101 }
102 return asc_occ > x_occ + x_occ && asc_occ > blob_width * textord_underline_threshold; // overline
103 // neither
104 }
105
106 /**
107 * horizontal_cblob_projection
108 *
109 * Compute the horizontal projection of a cblob from its outlines
110 * and add to the given STATS.
111 */
112
113 static void horizontal_cblob_projection( // project outlines
114 C_BLOB *blob, ///< blob to project
115 STATS *stats ///< output
116 ) {
117 // outlines of blob
118 C_OUTLINE_IT out_it = blob->out_list();
119
120 for (out_it.mark_cycle_pt(); !out_it.cycled_list(); out_it.forward()) {
121 horizontal_coutline_projection(out_it.data(), stats);
122 }
123 }
124
125 /**
126 * horizontal_coutline_projection
127 *
128 * Compute the horizontal projection of an outline from its outlines
129 * and add to the given STATS.
130 */
131
132 static void horizontal_coutline_projection( // project outlines
133 C_OUTLINE *outline, ///< outline to project
134 STATS *stats ///< output
135 ) {
136 ICOORD pos; // current point
137 ICOORD step; // edge step
138 int32_t length; // of outline
139 int16_t stepindex; // current step
140 C_OUTLINE_IT out_it = outline->child();
141
142 pos = outline->start_pos();
143 length = outline->pathlength();
144 for (stepindex = 0; stepindex < length; stepindex++) {
145 step = outline->step(stepindex);
146 if (step.y() > 0) {
147 stats->add(pos.y(), pos.x());
148 } else if (step.y() < 0) {
149 stats->add(pos.y() - 1, -pos.x());
150 }
151 pos += step;
152 }
153
154 for (out_it.mark_cycle_pt(); !out_it.cycled_list(); out_it.forward()) {
155 horizontal_coutline_projection(out_it.data(), stats);
156 }
157 }
158
159 } // namespace tesseract