void LMPainPoints::GenerateInitial(WERD_RES *word_res) {
MATRIX *ratings = word_res->ratings;
AssociateStats associate_stats;
for (int col = 0; col < ratings->dimension(); ++col) {
int row_end = MIN(ratings->dimension(), col + ratings->bandwidth() + 1);
for (int row = col + 1; row < row_end; ++row) {
MATRIX_COORD coord(col, row);
if (coord.Valid(*ratings) &&
ratings->get(col, row) != NOT_CLASSIFIED) continue;
// Add an initial pain point if needed.
if (ratings->Classified(col, row - 1, dict_->WildcardID()) ||
(col + 1 < ratings->dimension() &&
ratings->Classified(col + 1, row, dict_->WildcardID()))) {
GeneratePainPoint(col, row, LM_PPTYPE_SHAPE, 0.0,
true, max_char_wh_ratio_, word_res);
}
}
}
}
// Helper recursively prints all paths through the ratings matrix, starting
// at column col.
static void PrintMatrixPaths(int col, int dim,
const MATRIX& ratings,
int length, const BLOB_CHOICE** blob_choices,
const UNICHARSET& unicharset,
const char *label, FILE *output_file) {
for (int row = col; row < dim && row - col < ratings.bandwidth(); ++row) {
if (ratings.get(col, row) != NOT_CLASSIFIED) {
BLOB_CHOICE_IT bc_it(ratings.get(col, row));
for (bc_it.mark_cycle_pt(); !bc_it.cycled_list(); bc_it.forward()) {
blob_choices[length] = bc_it.data();
if (row + 1 < dim) {
PrintMatrixPaths(row + 1, dim, ratings, length + 1, blob_choices,
unicharset, label, output_file);
} else {
PrintPath(length + 1, blob_choices, unicharset, label, output_file);
}
}
}
}
}
void Wordrec::UpdateSegSearchNodes(
float rating_cert_scale,
int starting_col,
GenericVector<SegSearchPending>* pending,
WERD_RES *word_res,
LMPainPoints *pain_points,
BestChoiceBundle *best_choice_bundle,
BlamerBundle *blamer_bundle) {
MATRIX *ratings = word_res->ratings;
ASSERT_HOST(ratings->dimension() == pending->size());
ASSERT_HOST(ratings->dimension() == best_choice_bundle->beam.size());
for (int col = starting_col; col < ratings->dimension(); ++col) {
if (!(*pending)[col].WorkToDo()) continue;
int first_row = col;
int last_row = MIN(ratings->dimension() - 1,
col + ratings->bandwidth() - 1);
if ((*pending)[col].SingleRow() >= 0) {
first_row = last_row = (*pending)[col].SingleRow();
}
if (segsearch_debug_level > 0) {
tprintf("\n\nUpdateSegSearchNodes: col=%d, rows=[%d,%d], alljust=%d\n",
col, first_row, last_row,
(*pending)[col].IsRowJustClassified(INT32_MAX));
}
// Iterate over the pending list for this column.
for (int row = first_row; row <= last_row; ++row) {
// Update language model state of this child+parent pair.
BLOB_CHOICE_LIST *current_node = ratings->get(col, row);
LanguageModelState *parent_node =
col == 0 ? NULL : best_choice_bundle->beam[col - 1];
if (current_node != NULL &&
language_model_->UpdateState((*pending)[col].IsRowJustClassified(row),
col, row, current_node, parent_node,
pain_points, word_res,
best_choice_bundle, blamer_bundle) &&
row + 1 < ratings->dimension()) {
// Since the language model state of this entry changed, process all
// the child column.
(*pending)[row + 1].RevisitWholeColumn();
if (segsearch_debug_level > 0) {
tprintf("Added child col=%d to pending\n", row + 1);
}
} // end if UpdateState.
} // end for row.
} // end for col.
if (best_choice_bundle->best_vse != NULL) {
ASSERT_HOST(word_res->StatesAllValid());
if (best_choice_bundle->best_vse->updated) {
pain_points->GenerateFromPath(rating_cert_scale,
best_choice_bundle->best_vse, word_res);
if (!best_choice_bundle->fixpt.empty()) {
pain_points->GenerateFromAmbigs(best_choice_bundle->fixpt,
best_choice_bundle->best_vse, word_res);
}
}
}
// The segsearch is completed. Reset all updated flags on all VSEs and reset
// all pendings.
for (int col = 0; col < pending->size(); ++col) {
(*pending)[col].Clear();
ViterbiStateEntry_IT
vse_it(&best_choice_bundle->beam[col]->viterbi_state_entries);
for (vse_it.mark_cycle_pt(); !vse_it.cycled_list(); vse_it.forward()) {
vse_it.data()->updated = false;
}
}
}
