Definition at line 296 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 337 of file paragraphs.cpp.
337 {
338 while (pos < wordlen_ && u_->get_isalpha(word_->
unichar_id(pos))) pos++;
339 return pos;
340}
UNICHAR_ID unichar_id(int index) const
◆ SkipDigits()
int tesseract::UnicodeSpanSkipper::SkipDigits |
( |
int |
pos | ) |
|
Definition at line 321 of file paragraphs.cpp.
321 {
323 IsDigitLike(
UnicodeFor(u_, word_, pos)))) pos++;
324 return pos;
325}
int UnicodeFor(const UNICHARSET *u, const WERD_CHOICE *werd, int pos)
bool get_isdigit(UNICHAR_ID unichar_id) const
◆ SkipPunc()
int tesseract::UnicodeSpanSkipper::SkipPunc |
( |
int |
pos | ) |
|
Definition at line 316 of file paragraphs.cpp.
316 {
317 while (pos < wordlen_ && u_->get_ispunctuation(word_->
unichar_id(pos))) pos++;
318 return pos;
319}
◆ SkipRomans()
int tesseract::UnicodeSpanSkipper::SkipRomans |
( |
int |
pos | ) |
|
Definition at line 327 of file paragraphs.cpp.
327 {
328 const char *kRomans = "ivxlmdIVXLMD";
329 while (pos < wordlen_) {
331 if (ch >= 0xF0 || strchr(kRomans, ch) == nullptr) break;
332 pos++;
333 }
334 return pos;
335}
The documentation for this class was generated from the following file: