Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/thirdparty/tesseract/src/training/unicharset/validate_javanese.h @ 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: validate_javanese.h
3 * Description: Text validator for Javanese Script - aksara jawa.
4 * Author: Shree Devi Kumar
5 * Created: August 03, 2018
6 *
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 #ifndef TESSERACT_TRAINING_VALIDATE_JAVANESE_H_
20 #define TESSERACT_TRAINING_VALIDATE_JAVANESE_H_
21
22 #include "validator.h"
23
24 namespace tesseract {
25
26 // Subclass of Validator that validates and segments Javanese scripts
27
28 class ValidateJavanese : public Validator {
29 public:
30 ValidateJavanese(ViramaScript script, bool report_errors) : Validator(script, report_errors) {}
31 ~ValidateJavanese() override = default;
32
33 protected:
34 // Returns whether codes matches the pattern for an Javanese Grapheme.
35 // Consumes the next Grapheme in codes_[codes_used_++...] and copies it to
36 // parts_ and output_. Returns true if a valid Grapheme was consumed,
37 // otherwise does not increment codes_used_.
38 bool ConsumeGraphemeIfValid() override;
39 // Returns the CharClass corresponding to the given Unicode ch.
40 Validator::CharClass UnicodeToCharClass(char32 ch) const override;
41
42 private:
43 // Helper consumes/copies a virama and any associated post-virama joiners.
44 bool ConsumeViramaIfValid(IndicPair joiner, bool post_matra);
45 // Helper consumes/copies a series of consonants separated by viramas while
46 // valid, but not any vowel or other modifiers.
47 bool ConsumeConsonantHeadIfValid();
48 // Helper consumes/copies a tail part of a consonant, comprising optional
49 // matra/piece, vowel modifier, vedic mark, terminating virama.
50 bool ConsumeConsonantTailIfValid();
51 // Helper consumes/copies a vowel and optional modifiers.
52 bool ConsumeVowelIfValid();
53
54 // Some special unicodes used only for Javanese processing.
55 static const char32 kPengkal = 0xa9be; // Javanese Ya
56 static const char32 kCakra = 0xa9bf; // Javanese Ra
57 };
58
59 } // namespace tesseract
60
61 #endif // TESSERACT_TRAINING_VALIDATE_JAVANESE_H_