Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/thirdparty/tesseract/src/ccstruct/ocrpara.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: ocrpara.cpp
3 // Description: OCR Paragraph Output Type
4 // Author: David Eger
5 //
6 // (C) Copyright 2010, Google Inc.
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 "ocrpara.h"
20
21 #include "host.h" // For NearlyEqual()
22
23 #include <cstdio>
24
25 namespace tesseract {
26
27 using tesseract::JUSTIFICATION_CENTER;
28 using tesseract::JUSTIFICATION_LEFT;
29 using tesseract::JUSTIFICATION_RIGHT;
30 using tesseract::JUSTIFICATION_UNKNOWN;
31
32 static const char *ParagraphJustificationToString(tesseract::ParagraphJustification justification) {
33 switch (justification) {
34 case JUSTIFICATION_LEFT:
35 return "LEFT";
36 case JUSTIFICATION_RIGHT:
37 return "RIGHT";
38 case JUSTIFICATION_CENTER:
39 return "CENTER";
40 default:
41 return "UNKNOWN";
42 }
43 }
44
45 bool ParagraphModel::ValidFirstLine(int lmargin, int lindent, int rindent, int rmargin) const {
46 switch (justification_) {
47 case JUSTIFICATION_LEFT:
48 return NearlyEqual(lmargin + lindent, margin_ + first_indent_, tolerance_);
49 case JUSTIFICATION_RIGHT:
50 return NearlyEqual(rmargin + rindent, margin_ + first_indent_, tolerance_);
51 case JUSTIFICATION_CENTER:
52 return NearlyEqual(lindent, rindent, tolerance_ * 2);
53 default:
54 // shouldn't happen
55 return false;
56 }
57 }
58
59 bool ParagraphModel::ValidBodyLine(int lmargin, int lindent, int rindent, int rmargin) const {
60 switch (justification_) {
61 case JUSTIFICATION_LEFT:
62 return NearlyEqual(lmargin + lindent, margin_ + body_indent_, tolerance_);
63 case JUSTIFICATION_RIGHT:
64 return NearlyEqual(rmargin + rindent, margin_ + body_indent_, tolerance_);
65 case JUSTIFICATION_CENTER:
66 return NearlyEqual(lindent, rindent, tolerance_ * 2);
67 default:
68 // shouldn't happen
69 return false;
70 }
71 }
72
73 bool ParagraphModel::Comparable(const ParagraphModel &other) const {
74 if (justification_ != other.justification_) {
75 return false;
76 }
77 if (justification_ == JUSTIFICATION_CENTER || justification_ == JUSTIFICATION_UNKNOWN) {
78 return true;
79 }
80 int tolerance = (tolerance_ + other.tolerance_) / 4;
81 return NearlyEqual(margin_ + first_indent_, other.margin_ + other.first_indent_, tolerance) &&
82 NearlyEqual(margin_ + body_indent_, other.margin_ + other.body_indent_, tolerance);
83 }
84
85 std::string ParagraphModel::ToString() const {
86 char buffer[200];
87 const char *alignment = ParagraphJustificationToString(justification_);
88 snprintf(buffer, sizeof(buffer), "margin: %d, first_indent: %d, body_indent: %d, alignment: %s",
89 margin_, first_indent_, body_indent_, alignment);
90 return std::string(buffer);
91 }
92
93 } // namespace tesseract