tesseract  3.03
Public Member Functions
tesseract::UnicharAmbigs Class Reference

#include <ambigs.h>

List of all members.

Public Member Functions

 UnicharAmbigs ()
 ~UnicharAmbigs ()
const UnicharAmbigsVector & dang_ambigs () const
const UnicharAmbigsVector & replace_ambigs () const
void InitUnicharAmbigs (const UNICHARSET &unicharset, bool use_ambigs_for_adaption)
void LoadUniversal (const UNICHARSET &encoder_set, UNICHARSET *unicharset)
void LoadUnicharAmbigs (const UNICHARSET &encoder_set, TFile *ambigs_file, int debug_level, bool use_ambigs_for_adaption, UNICHARSET *unicharset)
const UnicharIdVector * OneToOneDefiniteAmbigs (UNICHAR_ID unichar_id) const
const UnicharIdVector * AmbigsForAdaption (UNICHAR_ID unichar_id) const
const UnicharIdVector * ReverseAmbigsForAdaption (UNICHAR_ID unichar_id) const

Detailed Description

Definition at line 144 of file ambigs.h.

Constructor & Destructor Documentation

tesseract::UnicharAmbigs::UnicharAmbigs ( ) [inline]

Definition at line 146 of file ambigs.h.

{}
tesseract::UnicharAmbigs::~UnicharAmbigs ( ) [inline]

Definition at line 147 of file ambigs.h.

                   {
    replace_ambigs_.delete_data_pointers();
    dang_ambigs_.delete_data_pointers();
    one_to_one_definite_ambigs_.delete_data_pointers();
  }

Member Function Documentation

const UnicharIdVector* tesseract::UnicharAmbigs::AmbigsForAdaption ( UNICHAR_ID  unichar_id) const [inline]

Definition at line 191 of file ambigs.h.

                                   {
    if (ambigs_for_adaption_.empty()) return NULL;
    return ambigs_for_adaption_[unichar_id];
  }
const UnicharAmbigsVector& tesseract::UnicharAmbigs::dang_ambigs ( ) const [inline]

Definition at line 153 of file ambigs.h.

{ return dang_ambigs_; }
void tesseract::UnicharAmbigs::InitUnicharAmbigs ( const UNICHARSET &  unicharset,
bool  use_ambigs_for_adaption 
)

Definition at line 53 of file ambigs.cpp.

                                                                    {
  for (int i = 0; i < unicharset.size(); ++i) {
    replace_ambigs_.push_back(NULL);
    dang_ambigs_.push_back(NULL);
    one_to_one_definite_ambigs_.push_back(NULL);
    if (use_ambigs_for_adaption) {
      ambigs_for_adaption_.push_back(NULL);
      reverse_ambigs_for_adaption_.push_back(NULL);
    }
  }
}
void tesseract::UnicharAmbigs::LoadUnicharAmbigs ( const UNICHARSET &  encoder_set,
TFile *  ambigs_file,
int  debug_level,
bool  use_ambigs_for_adaption,
UNICHARSET *  unicharset 
)

Definition at line 74 of file ambigs.cpp.

                                                              {
  int i, j;
  UnicharIdVector *adaption_ambigs_entry;
  if (debug_level) tprintf("Reading ambiguities\n");

  int test_ambig_part_size;
  int replacement_ambig_part_size;
  // The space for buffer is allocated on the heap to avoid
  // GCC frame size warning.
  const int kBufferSize = 10 + 2 * kMaxAmbigStringSize;
  char *buffer = new char[kBufferSize];
  char replacement_string[kMaxAmbigStringSize];
  UNICHAR_ID test_unichar_ids[MAX_AMBIG_SIZE + 1];
  int line_num = 0;
  int type = NOT_AMBIG;

  // Determine the version of the ambigs file.
  int version = 0;
  ASSERT_HOST(ambig_file->FGets(buffer, kBufferSize) != NULL &&
              strlen(buffer) > 0);
  if (*buffer == 'v') {
    version = static_cast<int>(strtol(buffer+1, NULL, 10));
    ++line_num;
  } else {
    ambig_file->Rewind();
  }
  while (ambig_file->FGets(buffer, kBufferSize) != NULL) {
    chomp_string(buffer);
    if (debug_level > 2) tprintf("read line %s\n", buffer);
    ++line_num;
    if (!ParseAmbiguityLine(line_num, version, debug_level, encoder_set,
                            buffer, &test_ambig_part_size, test_unichar_ids,
                            &replacement_ambig_part_size,
                            replacement_string, &type)) continue;
    // Construct AmbigSpec and add it to the appropriate AmbigSpec_LIST.
    AmbigSpec *ambig_spec = new AmbigSpec();
    if (!InsertIntoTable((type == REPLACE_AMBIG) ? replace_ambigs_
                                                 : dang_ambigs_,
                         test_ambig_part_size, test_unichar_ids,
                         replacement_ambig_part_size, replacement_string, type,
                         ambig_spec, unicharset))
      continue;

    // Update one_to_one_definite_ambigs_.
    if (test_ambig_part_size == 1 &&
        replacement_ambig_part_size == 1 && type == DEFINITE_AMBIG) {
      if (one_to_one_definite_ambigs_[test_unichar_ids[0]] == NULL) {
        one_to_one_definite_ambigs_[test_unichar_ids[0]] = new UnicharIdVector();
      }
      one_to_one_definite_ambigs_[test_unichar_ids[0]]->push_back(
          ambig_spec->correct_ngram_id);
    }
    // Update ambigs_for_adaption_.
    if (use_ambigs_for_adaption) {
      GenericVector<UNICHAR_ID> encoding;
      // Silently ignore invalid strings, as before, so it is safe to use a
      // universal ambigs file.
      if (unicharset->encode_string(replacement_string, true, &encoding,
                                    NULL, NULL)) {
        for (i = 0; i < test_ambig_part_size; ++i) {
          if (ambigs_for_adaption_[test_unichar_ids[i]] == NULL) {
            ambigs_for_adaption_[test_unichar_ids[i]] = new UnicharIdVector();
          }
          adaption_ambigs_entry = ambigs_for_adaption_[test_unichar_ids[i]];
          for (int r = 0; r < encoding.size(); ++r) {
            UNICHAR_ID id_to_insert = encoding[r];
            ASSERT_HOST(id_to_insert != INVALID_UNICHAR_ID);
            // Add the new unichar id to adaption_ambigs_entry (only if the
            // vector does not already contain it) keeping it in sorted order.
            for (j = 0; j < adaption_ambigs_entry->size() &&
                 (*adaption_ambigs_entry)[j] > id_to_insert; ++j);
            if (j < adaption_ambigs_entry->size()) {
              if ((*adaption_ambigs_entry)[j] != id_to_insert) {
                adaption_ambigs_entry->insert(id_to_insert, j);
              }
            } else {
              adaption_ambigs_entry->push_back(id_to_insert);
            }
          }
        }
      }
    }
  }
  delete[] buffer;

  // Fill in reverse_ambigs_for_adaption from ambigs_for_adaption vector.
  if (use_ambigs_for_adaption) {
    for (i = 0; i < ambigs_for_adaption_.size(); ++i) {
      adaption_ambigs_entry = ambigs_for_adaption_[i];
      if (adaption_ambigs_entry == NULL) continue;
      for (j = 0; j < adaption_ambigs_entry->size(); ++j) {
        UNICHAR_ID ambig_id = (*adaption_ambigs_entry)[j];
        if (reverse_ambigs_for_adaption_[ambig_id] == NULL) {
          reverse_ambigs_for_adaption_[ambig_id] = new UnicharIdVector();
        }
        reverse_ambigs_for_adaption_[ambig_id]->push_back(i);
      }
    }
  }

  // Print what was read from the input file.
  if (debug_level > 1) {
    for (int tbl = 0; tbl < 2; ++tbl) {
      const UnicharAmbigsVector &print_table =
        (tbl == 0) ? replace_ambigs_ : dang_ambigs_;
      for (i = 0; i < print_table.size(); ++i) {
        AmbigSpec_LIST *lst = print_table[i];
        if (lst == NULL) continue;
        if (!lst->empty()) {
          tprintf("%s Ambiguities for %s:\n",
                  (tbl == 0) ? "Replaceable" : "Dangerous",
                  unicharset->debug_str(i).string());
        }
        AmbigSpec_IT lst_it(lst);
        for (lst_it.mark_cycle_pt(); !lst_it.cycled_list(); lst_it.forward()) {
          AmbigSpec *ambig_spec = lst_it.data();
          tprintf("wrong_ngram:");
          UnicharIdArrayUtils::print(ambig_spec->wrong_ngram, *unicharset);
          tprintf("correct_fragments:");
          UnicharIdArrayUtils::print(ambig_spec->correct_fragments, *unicharset);
        }
      }
    }
    if (use_ambigs_for_adaption) {
      for (int vec_id = 0; vec_id < 2; ++vec_id) {
        const GenericVector<UnicharIdVector *> &vec = (vec_id == 0) ?
          ambigs_for_adaption_ : reverse_ambigs_for_adaption_;
        for (i = 0; i < vec.size(); ++i) {
          adaption_ambigs_entry = vec[i];
          if (adaption_ambigs_entry != NULL) {
            tprintf("%sAmbigs for adaption for %s:\n",
                    (vec_id == 0) ? "" : "Reverse ",
                    unicharset->debug_str(i).string());
            for (j = 0; j < adaption_ambigs_entry->size(); ++j) {
              tprintf("%s ", unicharset->debug_str(
                  (*adaption_ambigs_entry)[j]).string());
            }
            tprintf("\n");
          }
        }
      }
    }
  }
}
void tesseract::UnicharAmbigs::LoadUniversal ( const UNICHARSET &  encoder_set,
UNICHARSET *  unicharset 
)

Definition at line 67 of file ambigs.cpp.

                                                          {
  TFile file;
  if (!file.Open(kUniversalAmbigsFile, ksizeofUniversalAmbigsFile)) return;
  LoadUnicharAmbigs(encoder_set, &file, 0, false, unicharset);
}
const UnicharIdVector* tesseract::UnicharAmbigs::OneToOneDefiniteAmbigs ( UNICHAR_ID  unichar_id) const [inline]

Definition at line 180 of file ambigs.h.

                                   {
    if (one_to_one_definite_ambigs_.empty()) return NULL;
    return one_to_one_definite_ambigs_[unichar_id];
  }
const UnicharAmbigsVector& tesseract::UnicharAmbigs::replace_ambigs ( ) const [inline]

Definition at line 154 of file ambigs.h.

{ return replace_ambigs_; }
const UnicharIdVector* tesseract::UnicharAmbigs::ReverseAmbigsForAdaption ( UNICHAR_ID  unichar_id) const [inline]

Definition at line 200 of file ambigs.h.

                                   {
    if (reverse_ambigs_for_adaption_.empty()) return NULL;
    return reverse_ambigs_for_adaption_[unichar_id];
  }
The documentation for this class was generated from the following files:
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Defines