MATRIX *Wordrec::word_associator(WERD_RES *word,
STATE *state,
BLOB_CHOICE_LIST_VECTOR *best_char_choices,
DANGERR *fixpt,
STATE *best_state) {
CHUNKS_RECORD chunks_record;
BLOB_WEIGHTS blob_weights;
int x;
int num_chunks;
BLOB_CHOICE_IT blob_choice_it;
num_chunks = array_count(word->seam_array) + 1;
TBLOB* blobs = word->chopped_word->blobs;
chunks_record.chunks = blobs;
chunks_record.splits = word->seam_array;
chunks_record.ratings = record_piece_ratings (blobs);
chunks_record.char_widths = blobs_widths (blobs);
chunks_record.chunk_widths = blobs_widths (blobs);
/* Save chunk weights */
for (x = 0; x < num_chunks; x++) {
BLOB_CHOICE_LIST* choices = get_piece_rating(chunks_record.ratings,
blobs, word->seam_array, x, x);
blob_choice_it.set_to_list(choices);
//This is done by Jetsoft. Divide by zero is possible.
if (blob_choice_it.data()->certainty() == 0) {
blob_weights[x]=0;
} else {
blob_weights[x] =
-(inT16) (10 * blob_choice_it.data()->rating() /
blob_choice_it.data()->certainty());
}
}
chunks_record.weights = blob_weights;
if (chop_debug)
chunks_record.ratings->print(getDict().getUnicharset());
if (enable_new_segsearch) {
SegSearch(&chunks_record, word->best_choice,
best_char_choices, word->raw_choice, state);
} else {
best_first_search(&chunks_record, best_char_choices, word,
state, fixpt, best_state);
}
free_widths (chunks_record.chunk_widths);
free_widths (chunks_record.char_widths);
return chunks_record.ratings;
}
/**
* evaluate_chunks
*
* A particular word level segmentation has been chosen. Evaluation
* this to find the word list that corresponds to it.
*/
BLOB_CHOICE_LIST_VECTOR *Wordrec::evaluate_chunks(CHUNKS_RECORD *chunks_record,
SEARCH_STATE search_state,
BlamerBundle *blamer_bundle) {
BLOB_CHOICE_LIST_VECTOR *char_choices = new BLOB_CHOICE_LIST_VECTOR();
BLOB_CHOICE_LIST *blob_choices;
BLOB_CHOICE_IT blob_choice_it;
int i;
int x = 0;
int y;
// Iterate sub-paths.
for (i = 1; i <= search_state[0] + 1; i++) {
if (i > search_state[0])
y = count_blobs (chunks_record->chunks) - 1;
else
y = x + search_state[i];
// Process one square.
// Classify if needed.
blob_choices = get_piece_rating(chunks_record->ratings,
chunks_record->chunks,
chunks_record->word_res->denorm,
chunks_record->splits,
x, y, blamer_bundle);
if (blob_choices == NULL) {
delete char_choices;
return (NULL);
}
// Add permuted ratings.
blob_choice_it.set_to_list(blob_choices);
last_segmentation[i - 1].certainty = blob_choice_it.data()->certainty();
last_segmentation[i - 1].match = blob_choice_it.data()->rating();
last_segmentation[i - 1].width =
AssociateUtils::GetChunksWidth(chunks_record->chunk_widths, x, y);
last_segmentation[i - 1].gap =
AssociateUtils::GetChunksGap(chunks_record->chunk_widths, y);
*char_choices += blob_choices;
x = y + 1;
}
return (char_choices);
}
/**
* evaluate_chunks
*
* A particular word level segmentation has been chosen. Evaluation
* this to find the word list that corresponds to it.
*/
BLOB_CHOICE_LIST_VECTOR *Wordrec::evaluate_chunks(CHUNKS_RECORD *chunks_record,
SEARCH_STATE search_state) {
BLOB_CHOICE_LIST_VECTOR *char_choices = new BLOB_CHOICE_LIST_VECTOR();
BLOB_CHOICE_LIST *blob_choices;
BLOB_CHOICE_IT blob_choice_it;
int i;
int x = 0;
int y;
/* Iterate sub-paths */
for (i = 1; i <= search_state[0] + 1; i++) {
if (i > search_state[0])
y = count_blobs (chunks_record->chunks) - 1;
else
y = x + search_state[i];
if (tord_blob_skip) {
delete char_choices;
return (NULL);
} /* Process one square */
/* Classify if needed */
blob_choices = get_piece_rating(chunks_record->ratings,
chunks_record->chunks,
chunks_record->splits,
x, y);
if (blob_choices == NULL) {
delete char_choices;
return (NULL);
}
/* Add permuted ratings */
blob_choice_it.set_to_list(blob_choices);
last_segmentation[i - 1].certainty = blob_choice_it.data()->certainty();
last_segmentation[i - 1].match = blob_choice_it.data()->rating();
last_segmentation[i - 1].width =
chunks_width (chunks_record->chunk_widths, x, y);
last_segmentation[i - 1].gap =
chunks_gap (chunks_record->chunk_widths, y);
*char_choices += blob_choices;
x = y + 1;
}
return (char_choices);
}
