Go to the documentation of this file.
19 #ifndef TESSERACT_CCUTIL_UNICHAR_H_
20 #define TESSERACT_CCUTIL_UNICHAR_H_
30 #define UNICHAR_LEN 30
37 static const int INVALID_UNICHAR_ID = -1;
39 static const char INVALID_UNICHAR[] =
"__INVALID_UNICHAR__";
141 return lhs.it_ == rhs.it_;
144 return !(lhs == rhs);
157 static const_iterator
begin(
const char*
utf8_str,
int byte_length);
158 static const_iterator
end(
const char*
utf8_str,
int byte_length);
165 static std::string
UTF32ToUTF8(
const std::vector<char32>& str32);
176 #endif // TESSERACT_CCUTIL_UNICHAR_H_
friend bool operator!=(const CI &lhs, const CI &rhs)
int get_utf8(char *buf) const
static std::vector< char32 > UTF8ToUTF32(const char *utf8_str)
const char * utf8() const
const char * utf8_data() const
static const_iterator begin(const char *utf8_str, int byte_length)
static std::string UTF32ToUTF8(const std::vector< char32 > &str32)
const_iterator & operator++()
static const_iterator end(const char *utf8_str, int byte_length)
static int utf8_step(const char *utf8_str)
friend bool operator==(const CI &lhs, const CI &rhs)