Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/thirdparty/tesseract/src/ccstruct/blread.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 * File: blread.cpp (Formerly pdread.c)
3 * Description: Friend function of BLOCK to read the uscan pd file.
4 * Author: Ray Smith
5 *
6 * (C) Copyright 1991, 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 #include "blread.h"
20
21 #include "ocrblock.h" // for BLOCK_IT, BLOCK, BLOCK_LIST (ptr only)
22 #include "scanutils.h" // for tfscanf
23
24 #include <cstdio> // for fclose, fopen, FILE
25
26 namespace tesseract {
27
28 #define UNLV_EXT ".uzn" // unlv zone file
29
30 /**********************************************************************
31 * read_unlv_file
32 *
33 * Read a whole unlv zone file to make a list of blocks.
34 **********************************************************************/
35
36 bool read_unlv_file( // print list of sides
37 std::string &name, // basename of file
38 int32_t xsize, // image size
39 int32_t ysize, // image size
40 BLOCK_LIST *blocks // output list
41 ) {
42 FILE *pdfp; // file pointer
43 BLOCK *block; // current block
44 int x; // current top-down coords
45 int y;
46 int width; // of current block
47 int height;
48 BLOCK_IT block_it = blocks; // block iterator
49
50 name += UNLV_EXT; // add extension
51 if ((pdfp = fopen(name.c_str(), "rb")) == nullptr) {
52 return false; // didn't read one
53 } else {
54 while (tfscanf(pdfp, "%d %d %d %d %*s", &x, &y, &width, &height) >= 4) {
55 // make rect block
56 block = new BLOCK(name.c_str(), true, 0, 0, static_cast<int16_t>(x),
57 static_cast<int16_t>(ysize - y - height), static_cast<int16_t>(x + width),
58 static_cast<int16_t>(ysize - y));
59 // on end of list
60 block_it.add_to_end(block);
61 }
62 fclose(pdfp);
63 }
64 tprintf("UZN file %s loaded.\n", name.c_str());
65 return true;
66 }
67
68 void FullPageBlock(int width, int height, BLOCK_LIST *blocks) {
69 BLOCK_IT block_it(blocks);
70 auto *block = new BLOCK("", true, 0, 0, 0, 0, width, height);
71 block_it.add_to_end(block);
72 }
73
74 } // namespace tesseract