Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/thirdparty/tesseract/src/wordrec/wordrec.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: wordrec.cpp
3 // Description: wordrec class.
4 // Author: Samuel Charron
5 //
6 // (C) Copyright 2006, 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 "wordrec.h"
20
21 #include <memory>
22
23 #ifdef DISABLED_LEGACY_ENGINE
24
25 # include "params.h"
26
27 namespace tesseract {
28 Wordrec::Wordrec()
29 : // control parameters
30
31 BOOL_MEMBER(wordrec_debug_blamer, false, "Print blamer debug messages", params())
32 ,
33
34 BOOL_MEMBER(wordrec_run_blamer, false, "Try to set the blame for errors", params()) {
35 prev_word_best_choice_ = nullptr;
36 }
37
38 } // namespace tesseract
39
40 #else // DISABLED_LEGACY_ENGINE not defined
41
42 # include "language_model.h"
43 # include "params.h"
44
45 namespace tesseract {
46 Wordrec::Wordrec()
47 : // control parameters
48 BOOL_MEMBER(merge_fragments_in_matrix, true,
49 "Merge the fragments in the ratings matrix and delete them"
50 " after merging",
51 params())
52 , BOOL_MEMBER(wordrec_enable_assoc, true, "Associator Enable", params())
53 , BOOL_MEMBER(force_word_assoc, false,
54 "force associator to run regardless of what enable_assoc is."
55 " This is used for CJK where component grouping is necessary.",
56 CCUtil::params())
57 , INT_MEMBER(repair_unchopped_blobs, 1, "Fix blobs that aren't chopped", params())
58 , double_MEMBER(tessedit_certainty_threshold, -2.25, "Good blob limit", params())
59 , INT_MEMBER(chop_debug, 0, "Chop debug", params())
60 , BOOL_MEMBER(chop_enable, 1, "Chop enable", params())
61 , BOOL_MEMBER(chop_vertical_creep, 0, "Vertical creep", params())
62 , INT_MEMBER(chop_split_length, 10000, "Split Length", params())
63 , INT_MEMBER(chop_same_distance, 2, "Same distance", params())
64 , INT_MEMBER(chop_min_outline_points, 6, "Min Number of Points on Outline", params())
65 , INT_MEMBER(chop_seam_pile_size, 150, "Max number of seams in seam_pile", params())
66 , BOOL_MEMBER(chop_new_seam_pile, 1, "Use new seam_pile", params())
67 , INT_MEMBER(chop_inside_angle, -50, "Min Inside Angle Bend", params())
68 , INT_MEMBER(chop_min_outline_area, 2000, "Min Outline Area", params())
69 , double_MEMBER(chop_split_dist_knob, 0.5, "Split length adjustment", params())
70 , double_MEMBER(chop_overlap_knob, 0.9, "Split overlap adjustment", params())
71 , double_MEMBER(chop_center_knob, 0.15, "Split center adjustment", params())
72 , INT_MEMBER(chop_centered_maxwidth, 90,
73 "Width of (smaller) chopped blobs "
74 "above which we don't care that a chop is not near the center.",
75 params())
76 , double_MEMBER(chop_sharpness_knob, 0.06, "Split sharpness adjustment", params())
77 , double_MEMBER(chop_width_change_knob, 5.0, "Width change adjustment", params())
78 , double_MEMBER(chop_ok_split, 100.0, "OK split limit", params())
79 , double_MEMBER(chop_good_split, 50.0, "Good split limit", params())
80 , INT_MEMBER(chop_x_y_weight, 3, "X / Y length weight", params())
81 , BOOL_MEMBER(assume_fixed_pitch_char_segment, false,
82 "include fixed-pitch heuristics in char segmentation", params())
83 , INT_MEMBER(wordrec_debug_level, 0, "Debug level for wordrec", params())
84 , INT_MEMBER(wordrec_max_join_chunks, 4, "Max number of broken pieces to associate", params())
85 , BOOL_MEMBER(wordrec_skip_no_truth_words, false,
86 "Only run OCR for words that had truth recorded in BlamerBundle", params())
87 , BOOL_MEMBER(wordrec_debug_blamer, false, "Print blamer debug messages", params())
88 , BOOL_MEMBER(wordrec_run_blamer, false, "Try to set the blame for errors", params())
89 , INT_MEMBER(segsearch_debug_level, 0, "SegSearch debug level", params())
90 , INT_MEMBER(segsearch_max_pain_points, 2000,
91 "Maximum number of pain points stored in the queue", params())
92 , INT_MEMBER(segsearch_max_futile_classifications, 20,
93 "Maximum number of pain point classifications per chunk that"
94 " did not result in finding a better word choice.",
95 params())
96 , double_MEMBER(segsearch_max_char_wh_ratio, 2.0, "Maximum character width-to-height ratio",
97 params())
98 , BOOL_MEMBER(save_alt_choices, true,
99 "Save alternative paths found during chopping"
100 " and segmentation search",
101 params())
102 , language_model_(std::make_unique<LanguageModel>(&get_fontinfo_table(), &(getDict())))
103 , pass2_ok_split(0.0f)
104 , prev_word_best_choice_(nullptr)
105 , fill_lattice_(nullptr) {
106 }
107
108 } // namespace tesseract
109
110 #endif // DISABLED_LEGACY_ENGINE