Definition at line 297 of file paragraphs.cpp.
◆ UnicodeSpanSkipper()
tesseract::UnicodeSpanSkipper::UnicodeSpanSkipper |
( |
const UNICHARSET * |
unicharset, |
|
|
const WERD_CHOICE * |
word |
|
) |
| |
|
inline |
◆ SkipAlpha()
int tesseract::UnicodeSpanSkipper::SkipAlpha |
( |
int |
pos | ) |
|
Definition at line 338 of file paragraphs.cpp.
339 while (pos < wordlen_ && u_->get_isalpha(word_->
unichar_id(pos))) pos++;
UNICHAR_ID unichar_id(int index) const
◆ SkipDigits()
int tesseract::UnicodeSpanSkipper::SkipDigits |
( |
int |
pos | ) |
|
Definition at line 322 of file paragraphs.cpp.
324 IsDigitLike(
UnicodeFor(u_, word_, pos)))) pos++;
int UnicodeFor(const UNICHARSET *u, const WERD_CHOICE *werd, int pos)
bool get_isdigit(UNICHAR_ID unichar_id) const
UNICHAR_ID unichar_id(int index) const
◆ SkipPunc()
int tesseract::UnicodeSpanSkipper::SkipPunc |
( |
int |
pos | ) |
|
Definition at line 317 of file paragraphs.cpp.
318 while (pos < wordlen_ && u_->get_ispunctuation(word_->
unichar_id(pos))) pos++;
UNICHAR_ID unichar_id(int index) const
◆ SkipRomans()
int tesseract::UnicodeSpanSkipper::SkipRomans |
( |
int |
pos | ) |
|
Definition at line 328 of file paragraphs.cpp.
329 const char *kRomans =
"ivxlmdIVXLMD";
330 while (pos < wordlen_) {
332 if (ch >= 0xF0 || strchr(kRomans, ch) ==
nullptr)
break;
int UnicodeFor(const UNICHARSET *u, const WERD_CHOICE *werd, int pos)
The documentation for this class was generated from the following file: