Definition at line 294 of file paragraphs.cpp.
| tesseract::UnicodeSpanSkipper::UnicodeSpanSkipper |
( |
const UNICHARSET * |
unicharset, |
|
|
const WERD_CHOICE * |
word |
|
) |
| |
|
inline |
| int tesseract::UnicodeSpanSkipper::SkipAlpha |
( |
int |
pos | ) |
|
Definition at line 335 of file paragraphs.cpp.
336 while (pos < wordlen_ && u_->get_isalpha(word_->
unichar_id(pos))) pos++;
const UNICHAR_ID unichar_id(int index) const
| int tesseract::UnicodeSpanSkipper::SkipDigits |
( |
int |
pos | ) |
|
Definition at line 319 of file paragraphs.cpp.
int UnicodeFor(const UNICHARSET *u, const WERD_CHOICE *werd, int pos)
bool get_isdigit(UNICHAR_ID unichar_id) const
const UNICHAR_ID unichar_id(int index) const
| int tesseract::UnicodeSpanSkipper::SkipPunc |
( |
int |
pos | ) |
|
Definition at line 314 of file paragraphs.cpp.
315 while (pos < wordlen_ && u_->get_ispunctuation(word_->
unichar_id(pos))) pos++;
const UNICHAR_ID unichar_id(int index) const
| int tesseract::UnicodeSpanSkipper::SkipRomans |
( |
int |
pos | ) |
|
Definition at line 325 of file paragraphs.cpp.
326 const char *kRomans =
"ivxlmdIVXLMD";
327 while (pos < wordlen_) {
329 if (ch >= 0xF0 || strchr(kRomans, ch) == 0)
break;
int UnicodeFor(const UNICHARSET *u, const WERD_CHOICE *werd, int pos)
The documentation for this class was generated from the following file:
- /home/abuild/rpmbuild/BUILD/tesseract-ocr-3.02.02/ccmain/paragraphs.cpp