mirror of
https://github.com/tesseract-ocr/tesseract.git
synced 2024-11-27 20:59:36 +08:00
524a61452d
Squashed commit from https://github.com/tesseract-ocr/tesseract/tree/more-doxygen closes #14 Commits:6317305doxygen9f42f69doxygen0fc4d52doxygen37b4b55fix typobded8f1some more doxy020eb00slight tweak524666ddoxygenify2a36a3edoxygenify229d218doxygenify7fd28aedoxygenifya8c64bcdoxygenifyf5d21b6fix5d8ede8doxygenifya58a4e0language_model.cppfa85709lm_pain_points.cpp lm_state.cpp6418da3merge06190baMerge branch 'old_doxygen_merge' into more-doxygen84acf08Merge branch 'master' into more-doxygen50fe1ffpagewalk.cpp cube_reco_context.cpp2982583change to relative192a24aapplybox.cpp, take one8eeb053delete docs for obsolete params52e4c77modernise classify/ocrfeatures.cpp2a1cba6modernise cutil/emalloc.cpp773e006silence doxygen warningaeb1731silence doxygen warningf18387fsilence doxygen; new params are unused?15ad6bddoxygenify cutil/efio.cppc8b5daddoxygenify cutil/danerror.cpp784450fthe globals and exceptions parts are obsolete; remove8bca324doxygen classify/normfeat.cpp9bcbe16doxygen classify/normmatch.cppaa9a971doxygen ccmain/cube_control.cppc083ff2doxygen ccmain/cube_reco_context.cppf842850params changed5c94f12doxygen ccmain/cubeclassifier.cpp15ba750case sensitivef5c71d4case sensitivef85655bdoxygen classify/intproto.cpp4bbc7aapartial doxygen classify/mfx.cppdbb6041partial doxygen classify/intproto.cpp2aa72dbfinish doxygen classify/intproto.cpp0b8de99doxygen training/mftraining.cpp0b5b35cpartial doxygen ccstruct/coutln.cppb81c766partial doxygen ccstruct/coutln.cpp40fc415finished? doxygen ccstruct/coutln.cpp6e4165cdoxygen classify/clusttool.cpp0267decdoxygen classify/cutoffs.cpp7f0c70cdoxygen classify/fpoint.cpp512f3bdignore ~ files5668a52doxygen classify/intmatcher.cpp84788d4doxygen classify/kdtree.cpp29f36cadoxygen classify/mfoutline.cpp40b94b1silence doxygen warnings6c511b9doxygen classify/mfx.cppf9b4080doxygen classify/outfeat.cppaa1df05doxygen classify/picofeat.cppcc5f466doxygen training/cntraining.cppcce044fdoxygen training/commontraining.cpp167e216missing param9498383renamed params37eeac2renamed paramd87b5ddcasec8ee174renamed paramsb858db8typo4c2a838h2 context?81a2c0cfix some param names; add some missing params, no docsbcf8a4cadd some missing params, no docsaf77f86add some missing params, no docs; fix some param names01df24efix some params6161056fix some params68508b6fix some params285aeb6doxygen complains here no matter what529bcfarm some missing params, typoscd21226rm some missing params, add some new ones48a4bc2fix paramsc844628missing param312ce37missing param; rename oneec2fdecmissing param05e15e0missing paramsd515858change "<" to < to make doxygen happyb476a28wrong place
82 lines
3.0 KiB
C++
82 lines
3.0 KiB
C++
///////////////////////////////////////////////////////////////////////
|
|
// File: lm_state.cpp
|
|
// Description: Structures and functionality for capturing the state of
|
|
// segmentation search guided by the language model.
|
|
// Author: Rika Antonova
|
|
// Created: Mon Jun 20 11:26:43 PST 2012
|
|
//
|
|
// (C) Copyright 2012, Google Inc.
|
|
// Licensed under the Apache License, Version 2.0 (the "License");
|
|
// you may not use this file except in compliance with the License.
|
|
// You may obtain a copy of the License at
|
|
// http://www.apache.org/licenses/LICENSE-2.0
|
|
// Unless required by applicable law or agreed to in writing, software
|
|
// distributed under the License is distributed on an "AS IS" BASIS,
|
|
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
// See the License for the specific language governing permissions and
|
|
// limitations under the License.
|
|
//
|
|
///////////////////////////////////////////////////////////////////////
|
|
|
|
#include "lm_state.h"
|
|
|
|
namespace tesseract {
|
|
|
|
ELISTIZE(ViterbiStateEntry);
|
|
|
|
void ViterbiStateEntry::Print(const char *msg) const {
|
|
tprintf("%s ViterbiStateEntry", msg);
|
|
if (updated) tprintf("(NEW)");
|
|
if (this->debug_str != NULL) {
|
|
tprintf(" str=%s", this->debug_str->string());
|
|
}
|
|
tprintf(" with ratings_sum=%.4f length=%d cost=%.6f",
|
|
this->ratings_sum, this->length, this->cost);
|
|
if (this->top_choice_flags) {
|
|
tprintf(" top_choice_flags=0x%x", this->top_choice_flags);
|
|
}
|
|
if (!this->Consistent()) {
|
|
tprintf(" inconsistent=(punc %d case %d chartype %d script %d font %d)",
|
|
this->consistency_info.NumInconsistentPunc(),
|
|
this->consistency_info.NumInconsistentCase(),
|
|
this->consistency_info.NumInconsistentChartype(),
|
|
this->consistency_info.inconsistent_script,
|
|
this->consistency_info.inconsistent_font);
|
|
}
|
|
if (this->dawg_info) tprintf(" permuter=%d", this->dawg_info->permuter);
|
|
if (this->ngram_info) {
|
|
tprintf(" ngram_cl_cost=%g context=%s ngram pruned=%d",
|
|
this->ngram_info->ngram_and_classifier_cost,
|
|
this->ngram_info->context.string(),
|
|
this->ngram_info->pruned);
|
|
}
|
|
if (this->associate_stats.shape_cost > 0.0f) {
|
|
tprintf(" shape_cost=%g", this->associate_stats.shape_cost);
|
|
}
|
|
tprintf(" %s",
|
|
XHeightConsistencyEnumName[this->consistency_info.xht_decision]);
|
|
|
|
tprintf("\n");
|
|
}
|
|
|
|
/// Clears the viterbi search state back to its initial conditions.
|
|
void LanguageModelState::Clear() {
|
|
viterbi_state_entries.clear();
|
|
viterbi_state_entries_prunable_length = 0;
|
|
viterbi_state_entries_prunable_max_cost = MAX_FLOAT32;
|
|
viterbi_state_entries_length = 0;
|
|
}
|
|
|
|
void LanguageModelState::Print(const char *msg) {
|
|
tprintf("%s VSEs (max_cost=%g prn_len=%d tot_len=%d):\n",
|
|
msg, viterbi_state_entries_prunable_max_cost,
|
|
viterbi_state_entries_prunable_length, viterbi_state_entries_length);
|
|
ViterbiStateEntry_IT vit(&viterbi_state_entries);
|
|
for (vit.mark_cycle_pt(); !vit.cycled_list(); vit.forward()) {
|
|
vit.data()->Print("");
|
|
}
|
|
}
|
|
|
|
|
|
} // namespace tesseract
|