tesseract v5.3.3.20231005
tesseract::TestableValidator Class Reference
Inheritance diagram for tesseract::TestableValidator:
tesseract::Validator

Static Public Member Functions

static ViramaScript TestableMostFrequentViramaScript (const std::vector< char32 > &utf32)
 
- Static Public Member Functions inherited from tesseract::Validator
static bool ValidateCleanAndSegment (GraphemeNormMode g_mode, bool report_errors, const std::vector< char32 > &src, std::vector< std::vector< char32 > > *dest)
 
static bool IsZeroWidthMark (char32 ch)
 

Additional Inherited Members

- Public Member Functions inherited from tesseract::Validator
virtual ~Validator ()
 
- Static Public Attributes inherited from tesseract::Validator
static const char32 kZeroWidthSpace = 0x200B
 
static const char32 kZeroWidthNonJoiner = 0x200C
 
static const char32 kZeroWidthJoiner = 0x200D
 
static const char32 kLeftToRightMark = 0x200E
 
static const char32 kRightToLeftMark = 0x200F
 
static const char32 kInvalid = 0xfffd
 
- Protected Types inherited from tesseract::Validator
enum class  CharClass {
  kConsonant = 'C' , kVowel = 'V' , kVirama = 'H' , kMatra = 'M' ,
  kMatraPiece = 'P' , kVowelModifier = 'D' , kZeroWidthNonJoiner = 'z' , kZeroWidthJoiner = 'Z' ,
  kVedicMark = 'v' , kNukta = 'N' , kRobat = 'R' , kOther = 'O' ,
  kWhitespace = ' ' , kCombiner = 'c'
}
 
using IndicPair = std::pair< CharClass, char32 >
 
- Protected Member Functions inherited from tesseract::Validator
 Validator (ViramaScript script, bool report_errors)
 
bool ValidateCleanAndSegmentInternal (GraphemeNormMode g_mode, const std::vector< char32 > &src, std::vector< std::vector< char32 > > *dest)
 
void MoveResultsToDest (GraphemeNormMode g_mode, std::vector< std::vector< char32 > > *dest)
 
bool IsSubscriptScript () const
 
bool CodeOnlyToOutput ()
 
void MultiCodePart (unsigned length)
 
bool UseMultiCode (unsigned length)
 
virtual bool ConsumeGraphemeIfValid ()=0
 
void ComputeClassCodes (const std::vector< char32 > &text)
 
virtual CharClass UnicodeToCharClass (char32 ch) const =0
 
void Clear ()
 
- Static Protected Member Functions inherited from tesseract::Validator
static std::unique_ptr< ValidatorScriptValidator (ViramaScript script, bool report_errors)
 
static ViramaScript MostFrequentViramaScript (const std::vector< char32 > &utf32)
 
static bool IsVirama (char32 unicode)
 
static bool IsVedicAccent (char32 unicode)
 
- Protected Attributes inherited from tesseract::Validator
ViramaScript script_
 
std::vector< IndicPaircodes_
 
std::vector< std::vector< char32 > > parts_
 
std::vector< char32output_
 
unsigned codes_used_
 
unsigned output_used_
 
bool report_errors_
 
- Static Protected Attributes inherited from tesseract::Validator
static const int kIndicCodePageSize = 128
 
static const char32 kMinIndicUnicode = 0x900
 
static const char32 kMaxSinhalaUnicode = 0xdff
 
static const char32 kMaxViramaScriptUnicode = 0x17ff
 
static const char32 kSinhalaVirama = 0xdca
 
static const char32 kMyanmarVirama = 0x1039
 
static const char32 kKhmerVirama = 0x17d2
 
static const char32 kJavaneseVirama = 0xa9c0
 
static const char32 kMaxJavaneseUnicode = 0xa9df
 

Detailed Description

Definition at line 19 of file validator_test.cc.

Member Function Documentation

◆ TestableMostFrequentViramaScript()

static ViramaScript tesseract::TestableValidator::TestableMostFrequentViramaScript ( const std::vector< char32 > &  utf32)
inlinestatic

Definition at line 21 of file validator_test.cc.

21 {
22 return MostFrequentViramaScript(utf32);
23 }
static ViramaScript MostFrequentViramaScript(const std::vector< char32 > &utf32)
Definition: validator.cpp:135

The documentation for this class was generated from the following file: