Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/thirdparty/tesseract/src/textord/wordseg.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 * File: wordseg.h (Formerly wspace.h)
3 * Description: Code to segment the blobs into words.
4 * Author: Ray Smith
5 *
6 * (C) Copyright 1992, Hewlett-Packard Ltd.
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 **********************************************************************/
18
19 #ifndef WORDSEG_H
20 #define WORDSEG_H
21
22 #include "blobbox.h"
23 #include "params.h"
24 #include "textord.h"
25
26 namespace tesseract {
27 class Tesseract;
28
29 extern BOOL_VAR_H(textord_force_make_prop_words);
30 extern BOOL_VAR_H(textord_chopper_test);
31
32 void make_single_word(bool one_blob, TO_ROW_LIST *rows, ROW_LIST *real_rows);
33 void make_words(tesseract::Textord *textord,
34 ICOORD page_tr, // top right
35 float gradient, // page skew
36 BLOCK_LIST *blocks, // block list
37 TO_BLOCK_LIST *port_blocks); // output list
38 void set_row_spaces( // find space sizes
39 TO_BLOCK *block, // block to do
40 FCOORD rotation, // for drawing
41 bool testing_on // correct orientation
42 );
43 int32_t row_words( // compute space size
44 TO_BLOCK *block, // block it came from
45 TO_ROW *row, // row to operate on
46 int32_t maxwidth, // max expected space size
47 FCOORD rotation, // for drawing
48 bool testing_on // for debug
49 );
50 int32_t row_words2( // compute space size
51 TO_BLOCK *block, // block it came from
52 TO_ROW *row, // row to operate on
53 int32_t maxwidth, // max expected space size
54 FCOORD rotation, // for drawing
55 bool testing_on // for debug
56 );
57 void make_real_words(tesseract::Textord *textord,
58 TO_BLOCK *block, // block to do
59 FCOORD rotation // for drawing
60 );
61 ROW *make_rep_words( // make a row
62 TO_ROW *row, // row to convert
63 TO_BLOCK *block // block it lives in
64 );
65 WERD *make_real_word( // make a WERD
66 BLOBNBOX_IT *box_it, // iterator
67 int32_t blobcount, // no of blobs to use
68 bool bol, // start of line
69 uint8_t blanks // no of blanks
70 );
71
72 } // namespace tesseract
73
74 #endif