tesseract  5.0.0-alpha-619-ge9db
hyphen.cpp
Go to the documentation of this file.
1 /******************************************************************************
2  * File: hyphen.cpp (Formerly hyphen.c)
3  * Description: Functions for maintaining information about hyphenated words.
4  * Author: Mark Seaman, OCR Technology
5  * Status: Reusable Software Component
6  *
7  * (c) Copyright 1987, Hewlett-Packard Company.
8  ** Licensed under the Apache License, Version 2.0 (the "License");
9  ** you may not use this file except in compliance with the License.
10  ** You may obtain a copy of the License at
11  ** http://www.apache.org/licenses/LICENSE-2.0
12  ** Unless required by applicable law or agreed to in writing, software
13  ** distributed under the License is distributed on an "AS IS" BASIS,
14  ** WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15  ** See the License for the specific language governing permissions and
16  ** limitations under the License.
17  *
18  *****************************************************************************/
19 
20 #include "dict.h"
21 
22 namespace tesseract {
23 
24 // Unless the previous word was the last one on the line, and the current
25 // one is not (thus it is the first one on the line), erase hyphen_word_,
26 // clear hyphen_active_dawgs_, hyphen_constraints_ update last_word_on_line_.
27 void Dict::reset_hyphen_vars(bool last_word_on_line) {
28  if (!(last_word_on_line_ == true && last_word_on_line == false)) {
29  if (hyphen_word_ != nullptr) {
30  delete hyphen_word_;
31  hyphen_word_ = nullptr;
32  hyphen_active_dawgs_.clear();
33  }
34  }
35  if (hyphen_debug_level) {
36  tprintf("reset_hyphen_vars: last_word_on_line %d -> %d\n",
37  last_word_on_line_, last_word_on_line);
38  }
39  last_word_on_line_ = last_word_on_line;
40 }
41 
42 // Update hyphen_word_, and copy the given DawgPositionVectors into
43 // hyphen_active_dawgs_.
44 void Dict::set_hyphen_word(const WERD_CHOICE &word,
45  const DawgPositionVector &active_dawgs) {
46  if (hyphen_word_ == nullptr) {
47  hyphen_word_ = new WERD_CHOICE(word.unicharset());
48  hyphen_word_->make_bad();
49  }
50  if (hyphen_word_->rating() > word.rating()) {
51  *hyphen_word_ = word;
52  // Remove the last unichar id as it is a hyphen, and remove
53  // any unichar_string/lengths that are present.
54  hyphen_word_->remove_last_unichar_id();
55  hyphen_active_dawgs_ = active_dawgs;
56  }
57  if (hyphen_debug_level) {
58  hyphen_word_->print("set_hyphen_word: ");
59  }
60 }
61 } // namespace tesseract
tesseract::DawgPositionVector::clear
void clear()
Definition: dawg.h:377
dict.h
WERD_CHOICE
Definition: ratngs.h:261
WERD_CHOICE::make_bad
void make_bad()
Set the fields in this choice to be default (bad) values.
Definition: ratngs.h:431
WERD_CHOICE::unicharset
const UNICHARSET * unicharset() const
Definition: ratngs.h:288
tesseract::Dict::set_hyphen_word
void set_hyphen_word(const WERD_CHOICE &word, const DawgPositionVector &active_dawgs)
Definition: hyphen.cpp:59
tesseract
Definition: baseapi.h:65
tesseract::DawgPositionVector
Definition: dawg.h:373
WERD_CHOICE::remove_last_unichar_id
void remove_last_unichar_id()
Definition: ratngs.h:471
WERD_CHOICE::print
void print() const
Definition: ratngs.h:568
tesseract::Dict::reset_hyphen_vars
void reset_hyphen_vars(bool last_word_on_line)
Definition: hyphen.cpp:42
tprintf
DLLSYM void tprintf(const char *format,...)
Definition: tprintf.cpp:34
WERD_CHOICE::rating
float rating() const
Definition: ratngs.h:315
tesseract::Dict::hyphen_debug_level
int hyphen_debug_level
Definition: dict.h:623