Mercurial > hgrepos > Python2 > PyMuPDF
comparison mupdf-source/thirdparty/tesseract/src/dict/hyphen.cpp @ 2:b50eed0cc0ef upstream
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: 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", last_word_on_line_, | |
| 37 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, const DawgPositionVector &active_dawgs) { | |
| 45 if (hyphen_word_ == nullptr) { | |
| 46 hyphen_word_ = new WERD_CHOICE(word.unicharset()); | |
| 47 hyphen_word_->make_bad(); | |
| 48 } | |
| 49 if (hyphen_word_->rating() > word.rating()) { | |
| 50 *hyphen_word_ = word; | |
| 51 // Remove the last unichar id as it is a hyphen, and remove | |
| 52 // any unichar_string/lengths that are present. | |
| 53 hyphen_word_->remove_last_unichar_id(); | |
| 54 hyphen_active_dawgs_ = active_dawgs; | |
| 55 } | |
| 56 if (hyphen_debug_level) { | |
| 57 hyphen_word_->print("set_hyphen_word: "); | |
| 58 } | |
| 59 } | |
| 60 } // namespace tesseract |
