Mercurial > hgrepos > Python2 > PyMuPDF
comparison mupdf-source/thirdparty/tesseract/src/training/unicharset/unicharset_training_utils.h @ 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: unicharset_training_utils.h | |
| 3 // Description: Training utilities for UNICHARSET. | |
| 4 // Author: Ray Smith | |
| 5 // | |
| 6 // (C) Copyright 2014, 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 #ifndef TESSERACT_TRAINING_UNICHARSET_TRAINING_UTILS_H_ | |
| 20 #define TESSERACT_TRAINING_UNICHARSET_TRAINING_UTILS_H_ | |
| 21 | |
| 22 #include "export.h" | |
| 23 | |
| 24 #include <tesseract/export.h> | |
| 25 | |
| 26 #include <string> | |
| 27 | |
| 28 namespace tesseract { | |
| 29 | |
| 30 class UNICHARSET; | |
| 31 | |
| 32 // Helper sets the character attribute properties and sets up the script table. | |
| 33 // Does not set tops and bottoms. | |
| 34 TESS_UNICHARSET_TRAINING_API | |
| 35 void SetupBasicProperties(bool report_errors, bool decompose, UNICHARSET *unicharset); | |
| 36 // Default behavior is to compose, until it is proven that decomposed benefits | |
| 37 // at least one language. | |
| 38 inline void SetupBasicProperties(bool report_errors, UNICHARSET *unicharset) { | |
| 39 SetupBasicProperties(report_errors, false, unicharset); | |
| 40 } | |
| 41 // Helper sets the properties from universal script unicharsets, if found. | |
| 42 TESS_UNICHARSET_TRAINING_API | |
| 43 void SetScriptProperties(const std::string &script_dir, UNICHARSET *unicharset); | |
| 44 // Helper gets the combined x-heights string. | |
| 45 std::string GetXheightString(const std::string &script_dir, const UNICHARSET &unicharset); | |
| 46 | |
| 47 // Helper to set the properties for an input unicharset file, writes to the | |
| 48 // output file. If an appropriate script unicharset can be found in the | |
| 49 // script_dir directory, then the tops and bottoms are expanded using the | |
| 50 // script unicharset. | |
| 51 // If non-empty, xheight data for the fonts are written to the xheights_file. | |
| 52 TESS_UNICHARSET_TRAINING_API | |
| 53 void SetPropertiesForInputFile(const std::string &script_dir, | |
| 54 const std::string &input_unicharset_file, | |
| 55 const std::string &output_unicharset_file, | |
| 56 const std::string &output_xheights_file); | |
| 57 | |
| 58 } // namespace tesseract. | |
| 59 | |
| 60 #endif // TESSERACT_TRAINING_UNICHARSET_TRAINING_UTILS_H_ |