Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/thirdparty/tesseract/src/classify/cutoffs.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 ** Filename: cutoffs.c
3 ** Purpose: Routines to manipulate an array of class cutoffs.
4 ** Author: Dan Johnson
5 **
6 ** (c) Copyright Hewlett-Packard Company, 1988.
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 Include Files and Type Defines
19 ----------------------------------------------------------------------------*/
20
21 #include <cstdio>
22 #include <sstream> // for std::istringstream
23 #include <string> // for std::string
24
25 #include <tesseract/unichar.h>
26 #include "classify.h"
27 #include "helpers.h"
28 #include "serialis.h"
29
30 #define MAX_CUTOFF 1000
31
32 namespace tesseract {
33 /**
34 * Open file, read in all of the class-id/cutoff pairs
35 * and insert them into the Cutoffs array. Cutoffs are
36 * indexed in the array by class id. Unused entries in the
37 * array are set to an arbitrarily high cutoff value.
38 * @param fp file containing cutoff definitions
39 * @param Cutoffs array to put cutoffs into
40 */
41 void Classify::ReadNewCutoffs(TFile *fp, uint16_t *Cutoffs) {
42 int Cutoff;
43
44 if (shape_table_ != nullptr) {
45 if (!fp->DeSerialize(shapetable_cutoffs_)) {
46 tprintf("Error during read of shapetable pffmtable!\n");
47 }
48 }
49 for (int i = 0; i < MAX_NUM_CLASSES; i++) {
50 Cutoffs[i] = MAX_CUTOFF;
51 }
52
53 const int kMaxLineSize = 100;
54 char line[kMaxLineSize];
55 while (fp->FGets(line, kMaxLineSize) != nullptr) {
56 std::string Class;
57 CLASS_ID ClassId;
58 std::istringstream stream(line);
59 stream.imbue(std::locale::classic());
60 stream >> Class >> Cutoff;
61 if (stream.fail()) {
62 break;
63 }
64 if (Class.compare("NULL") == 0) {
65 ClassId = unicharset.unichar_to_id(" ");
66 } else {
67 ClassId = unicharset.unichar_to_id(Class.c_str());
68 }
69 ASSERT_HOST(ClassId >= 0 && ClassId < MAX_NUM_CLASSES);
70 Cutoffs[ClassId] = Cutoff;
71 }
72 }
73
74 } // namespace tesseract