#include "normstrngs.h"
#include "icuerrorcode.h"
#include "unichar.h"
#include "unicode/normalizer2.h"
#include "unicode/translit.h"
#include "unicode/unorm2.h"
Go to the source code of this file.
Namespaces | |
tesseract | |
Functions | |
void | tesseract::UTF8ToUTF32 (const char *utf8_str, GenericVector< char32 > *str32) |
void | tesseract::UTF32ToUTF8 (const GenericVector< char32 > &str32, STRING *utf8_str) |
bool | tesseract::is_hyphen_punc (const char32 ch) |
bool | tesseract::is_single_quote (const char32 ch) |
bool | tesseract::is_double_quote (const char32 ch) |
STRING | tesseract::NormalizeUTF8String (const char *str8) |
void | tesseract::NormalizeChar32 (char32 ch, GenericVector< char32 > *str) |
char32 | tesseract::OCRNormalize (char32 ch) |
bool | tesseract::IsOCREquivalent (char32 ch1, char32 ch2) |
bool | tesseract::IsValidCodepoint (const char32 ch) |
bool | tesseract::IsWhitespace (const char32 ch) |
bool | tesseract::IsUTF8Whitespace (const char *text) |
int | tesseract::SpanUTF8Whitespace (const char *text) |
int | tesseract::SpanUTF8NotWhitespace (const char *text) |
bool | tesseract::IsInterchangeValid (const char32 ch) |
bool | tesseract::IsInterchangeValid7BitAscii (const char32 ch) |
char32 | tesseract::FullwidthToHalfwidth (const char32 ch) |