tesseract  4.1.1
tesseract::UnicodeSpanSkipper Class Reference

Public Member Functions

 UnicodeSpanSkipper (const UNICHARSET *unicharset, const WERD_CHOICE *word)
 
int SkipPunc (int pos)
 
int SkipDigits (int pos)
 
int SkipRomans (int pos)
 
int SkipAlpha (int pos)
 

Detailed Description

Definition at line 296 of file paragraphs.cpp.

Constructor & Destructor Documentation

◆ UnicodeSpanSkipper()

tesseract::UnicodeSpanSkipper::UnicodeSpanSkipper ( const UNICHARSET unicharset,
const WERD_CHOICE word 
)
inline

Definition at line 298 of file paragraphs.cpp.

299  : u_(unicharset), word_(word) { wordlen_ = word->length(); }
int length() const
Definition: ratngs.h:293

Member Function Documentation

◆ 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
Definition: ratngs.h:305

◆ SkipDigits()

int tesseract::UnicodeSpanSkipper::SkipDigits ( int  pos)

Definition at line 321 of file paragraphs.cpp.

321  {
322  while (pos < wordlen_ && (u_->get_isdigit(word_->unichar_id(pos)) ||
323  IsDigitLike(UnicodeFor(u_, word_, pos)))) pos++;
324  return pos;
325 }
int UnicodeFor(const UNICHARSET *u, const WERD_CHOICE *werd, int pos)
Definition: paragraphs.cpp:288
bool get_isdigit(UNICHAR_ID unichar_id) const
Definition: unicharset.h:512

◆ 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_) {
330  int ch = UnicodeFor(u_, word_, pos);
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: