Mercurial > hgrepos > Python2 > PyMuPDF
diff mupdf-source/thirdparty/tesseract/src/training/unicharset/validate_khmer.h @ 3:2c135c81b16c
MERGE: upstream PyMuPDF 1.26.4 with MuPDF 1.26.7
| author | Franz Glasner <fzglas.hg@dom66.de> |
|---|---|
| date | Mon, 15 Sep 2025 11:44:09 +0200 |
| parents | b50eed0cc0ef |
| children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mupdf-source/thirdparty/tesseract/src/training/unicharset/validate_khmer.h Mon Sep 15 11:44:09 2025 +0200 @@ -0,0 +1,26 @@ +#ifndef TESSERACT_TRAINING_VALIDATE_KHMER_H_ +#define TESSERACT_TRAINING_VALIDATE_KHMER_H_ + +#include "validator.h" + +namespace tesseract { + +// Subclass of Validator that validates and segments Khmer. +class ValidateKhmer : public Validator { +public: + ValidateKhmer(ViramaScript script, bool report_errors) : Validator(script, report_errors) {} + ~ValidateKhmer() override = default; + +protected: + // Returns whether codes matches the pattern for an Khmer Grapheme. + // Consumes the next Grapheme in codes_[codes_used_++...] and copies it to + // parts_ and output_. Returns true if a valid Grapheme was consumed, + // otherwise does not increment codes_used_. + bool ConsumeGraphemeIfValid() override; + // Returns the CharClass corresponding to the given Unicode ch. + CharClass UnicodeToCharClass(char32 ch) const override; +}; + +} // namespace tesseract + +#endif // TESSERACT_TRAINING_VALIDATE_KHMER_H_
