tesseract 3.04.01

tesseract::LTRResultIterator Class Reference

#include <ltrresultiterator.h>

Inheritance diagram for tesseract::LTRResultIterator:
tesseract::PageIterator tesseract::ResultIterator tesseract::MutableIterator

List of all members.

Public Member Functions

 LTRResultIterator (PAGE_RES *page_res, Tesseract *tesseract, int scale, int scaled_yres, int rect_left, int rect_top, int rect_width, int rect_height)
virtual ~LTRResultIterator ()
char * GetUTF8Text (PageIteratorLevel level) const
void SetLineSeparator (const char *new_line)
void SetParagraphSeparator (const char *new_para)
float Confidence (PageIteratorLevel level) const
void RowAttributes (float *row_height, float *descenders, float *ascenders) const
const char * WordFontAttributes (bool *is_bold, bool *is_italic, bool *is_underlined, bool *is_monospace, bool *is_serif, bool *is_smallcaps, int *pointsize, int *font_id) const
const char * WordRecognitionLanguage () const
StrongScriptDirection WordDirection () const
bool WordIsFromDictionary () const
bool WordIsNumeric () const
bool HasBlamerInfo () const
const void * GetParamsTrainingBundle () const
const char * GetBlamerDebug () const
const char * GetBlamerMisadaptionDebug () const
bool HasTruthString () const
bool EquivalentToTruth (const char *str) const
char * WordTruthUTF8Text () const
char * WordNormedUTF8Text () const
const char * WordLattice (int *lattice_size) const
bool SymbolIsSuperscript () const
bool SymbolIsSubscript () const
bool SymbolIsDropcap () const

Protected Attributes

const char * line_separator_
const char * paragraph_separator_

Friends

class ChoiceIterator

Detailed Description

Definition at line 46 of file ltrresultiterator.h.


Constructor & Destructor Documentation

usr src packages BUILD tesseract ccmain ltrresultiterator cpp tesseract::LTRResultIterator::LTRResultIterator ( PAGE_RES page_res,
Tesseract tesseract,
int  scale,
int  scaled_yres,
int  rect_left,
int  rect_top,
int  rect_width,
int  rect_height 
)

Definition at line 31 of file ltrresultiterator.cpp.

  : PageIterator(page_res, tesseract, scale, scaled_yres,
                 rect_left, rect_top, rect_width, rect_height),
    line_separator_("\n"),
    paragraph_separator_("\n") {
}

tesseract::LTRResultIterator::~LTRResultIterator ( ) [virtual]

Definition at line 41 of file ltrresultiterator.cpp.


Member Function Documentation

float tesseract::LTRResultIterator::Confidence ( PageIteratorLevel  level) const

Definition at line 95 of file ltrresultiterator.cpp.

                 {
    case RIL_BLOCK:
      do {
        best_choice = res_it.word()->best_choice;
        ASSERT_HOST(best_choice != NULL);
        mean_certainty += best_choice->certainty();
        ++certainty_count;
        res_it.forward();
      } while (res_it.block() == res_it.prev_block());
      break;
    case RIL_PARA:
      do {
        best_choice = res_it.word()->best_choice;
        ASSERT_HOST(best_choice != NULL);
        mean_certainty += best_choice->certainty();
        ++certainty_count;
        res_it.forward();
      } while (res_it.block() == res_it.prev_block() &&
               res_it.row()->row->para() == res_it.prev_row()->row->para());
      break;
    case RIL_TEXTLINE:
      do {
        best_choice = res_it.word()->best_choice;
        ASSERT_HOST(best_choice != NULL);
        mean_certainty += best_choice->certainty();
        ++certainty_count;
        res_it.forward();
      } while (res_it.row() == res_it.prev_row());
      break;
    case RIL_WORD:
      mean_certainty += best_choice->certainty();
     ++certainty_count;
      break;
    case RIL_SYMBOL:
      mean_certainty += best_choice->certainty(blob_index_);
      ++certainty_count;
  }
  if (certainty_count > 0) {
    mean_certainty /= certainty_count;
    float confidence = 100 + 5 * mean_certainty;
    if (confidence < 0.0f) confidence = 0.0f;
    if (confidence > 100.0f) confidence = 100.0f;
    return confidence;
  }
  return 0.0f;
}

bool tesseract::LTRResultIterator::EquivalentToTruth ( const char *  str) const

Definition at line 269 of file ltrresultiterator.cpp.

const char * tesseract::LTRResultIterator::GetBlamerDebug ( ) const

Definition at line 247 of file ltrresultiterator.cpp.

const char * tesseract::LTRResultIterator::GetBlamerMisadaptionDebug ( ) const

Definition at line 253 of file ltrresultiterator.cpp.

const void * tesseract::LTRResultIterator::GetParamsTrainingBundle ( ) const

Definition at line 240 of file ltrresultiterator.cpp.

                                                              : NULL;
}

char * tesseract::LTRResultIterator::GetUTF8Text ( PageIteratorLevel  level) const

Reimplemented in tesseract::ResultIterator.

Definition at line 46 of file ltrresultiterator.cpp.

                           {
    text = res_it.word()->BestUTF8(blob_index_, false);
  } else if (level == RIL_WORD) {
    text = best_choice->unichar_string();
  } else {
    bool eol = false;  // end of line?
    bool eop = false;  // end of paragraph?
    do {  // for each paragraph in a block
      do {  // for each text line in a paragraph
        do {  // for each word in a text line
          best_choice = res_it.word()->best_choice;
          ASSERT_HOST(best_choice != NULL);
          text += best_choice->unichar_string();
          text += " ";
          res_it.forward();
          eol = res_it.row() != res_it.prev_row();
        } while (!eol);
        text.truncate_at(text.length() - 1);
        text += line_separator_;
        eop = res_it.block() != res_it.prev_block() ||
            res_it.row()->row->para() != res_it.prev_row()->row->para();
      } while (level != RIL_TEXTLINE && !eop);
      if (eop) text += paragraph_separator_;
    } while (level == RIL_BLOCK && res_it.block() == res_it.prev_block());
  }
  int length = text.length() + 1;
  char* result = new char[length];
  strncpy(result, text.string(), length);
  return result;
}

bool tesseract::LTRResultIterator::HasBlamerInfo ( ) const

Definition at line 233 of file ltrresultiterator.cpp.

bool tesseract::LTRResultIterator::HasTruthString ( ) const

Definition at line 258 of file ltrresultiterator.cpp.

                                             {
    return false;  // no truth information for this word
  }
  return true;
}

void tesseract::LTRResultIterator::RowAttributes ( float *  row_height,
float *  descenders,
float *  ascenders 
) const

Definition at line 149 of file ltrresultiterator.cpp.

                                                              {
    *row_height = it_->row()->row->x_height() + it_->row()-> row->ascenders()
                  - it_->row()->row->descenders();
    *descenders = it_->row()->row->descenders();
    *ascenders = it_->row()->row->ascenders();
}

void tesseract::LTRResultIterator::SetLineSeparator ( const char *  new_line)

Definition at line 84 of file ltrresultiterator.cpp.

void tesseract::LTRResultIterator::SetParagraphSeparator ( const char *  new_para)

Definition at line 89 of file ltrresultiterator.cpp.

bool tesseract::LTRResultIterator::SymbolIsDropcap ( ) const

Definition at line 335 of file ltrresultiterator.cpp.

bool tesseract::LTRResultIterator::SymbolIsSubscript ( ) const

Definition at line 326 of file ltrresultiterator.cpp.

bool tesseract::LTRResultIterator::SymbolIsSuperscript ( ) const

Definition at line 316 of file ltrresultiterator.cpp.

StrongScriptDirection tesseract::LTRResultIterator::WordDirection ( ) const

Definition at line 204 of file ltrresultiterator.cpp.

const char * tesseract::LTRResultIterator::WordFontAttributes ( bool *  is_bold,
bool *  is_italic,
bool *  is_underlined,
bool *  is_monospace,
bool *  is_serif,
bool *  is_smallcaps,
int *  pointsize,
int *  font_id 
) const

Definition at line 166 of file ltrresultiterator.cpp.

                                                                      {
  if (it_->word() == NULL) return NULL;  // Already at the end!
  if (it_->word()->fontinfo == NULL) {
    *font_id = -1;
    return NULL;  // No font information.
  }
  const FontInfo& font_info = *it_->word()->fontinfo;
  *font_id = font_info.universal_id;
  *is_bold = font_info.is_bold();
  *is_italic = font_info.is_italic();
  *is_underlined = false;  // TODO(rays) fix this!
  *is_monospace = font_info.is_fixed_pitch();
  *is_serif = font_info.is_serif();
  *is_smallcaps = it_->word()->small_caps;
  float row_height = it_->row()->row->x_height() +
      it_->row()->row->ascenders() - it_->row()->row->descenders();
  // Convert from pixels to printers points.
  *pointsize = scaled_yres_ > 0
      ? static_cast<int>(row_height * kPointsPerInch / scaled_yres_ + 0.5)
      : 0;

  return font_info.name;
}

bool tesseract::LTRResultIterator::WordIsFromDictionary ( ) const

Definition at line 218 of file ltrresultiterator.cpp.

bool tesseract::LTRResultIterator::WordIsNumeric ( ) const

Definition at line 226 of file ltrresultiterator.cpp.

const char * tesseract::LTRResultIterator::WordLattice ( int *  lattice_size) const

Definition at line 306 of file ltrresultiterator.cpp.

char * tesseract::LTRResultIterator::WordNormedUTF8Text ( ) const

Definition at line 289 of file ltrresultiterator.cpp.

                                                  {
    ocr_text += unicharset->get_normed_unichar(best_choice->unichar_id(i));
  }
  int length = ocr_text.length() + 1;
  char* result = new char[length];
  strncpy(result, ocr_text.string(), length);
  return result;
}

const char * tesseract::LTRResultIterator::WordRecognitionLanguage ( ) const

Definition at line 198 of file ltrresultiterator.cpp.

char * tesseract::LTRResultIterator::WordTruthUTF8Text ( ) const

Definition at line 278 of file ltrresultiterator.cpp.


Friends And Related Function Documentation

friend class ChoiceIterator [friend]

Definition at line 47 of file ltrresultiterator.h.


Member Data Documentation

Definition at line 181 of file ltrresultiterator.h.

Definition at line 182 of file ltrresultiterator.h.


The documentation for this class was generated from the following files:
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Defines