2007-07-18 09:15:07 +08:00
|
|
|
///////////////////////////////////////////////////////////////////////
|
|
|
|
// File: wordlist2dawg.cpp
|
|
|
|
// Description: Program to generate a DAWG from a word list file
|
|
|
|
// Author: Thomas Kielbus
|
|
|
|
//
|
|
|
|
// (C) Copyright 2006, 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.
|
|
|
|
//
|
|
|
|
///////////////////////////////////////////////////////////////////////
|
|
|
|
|
|
|
|
// Given a file that contains a list of words (one word per line) this program
|
|
|
|
// generates the corresponding squished DAWG file.
|
|
|
|
|
2009-07-11 10:44:07 +08:00
|
|
|
#include "classify.h"
|
2018-04-15 16:33:46 +08:00
|
|
|
#include "commontraining.h" // CheckSharedLibraryVersion
|
2007-07-18 09:15:07 +08:00
|
|
|
#include "dawg.h"
|
2010-11-24 02:34:14 +08:00
|
|
|
#include "dict.h"
|
|
|
|
#include "helpers.h"
|
|
|
|
#include "serialis.h"
|
2009-07-11 10:44:07 +08:00
|
|
|
#include "trie.h"
|
|
|
|
#include "unicharset.h"
|
2007-07-18 09:15:07 +08:00
|
|
|
|
2009-07-11 10:44:07 +08:00
|
|
|
int main(int argc, char** argv) {
|
2018-04-15 16:33:46 +08:00
|
|
|
tesseract::CheckSharedLibraryVersion();
|
|
|
|
|
2018-04-21 04:15:04 +08:00
|
|
|
if (argc > 1 && (!strcmp(argv[1], "-v") || !strcmp(argv[1], "--version"))) {
|
2018-04-16 13:56:29 +08:00
|
|
|
printf("%s\n", tesseract::TessBaseAPI::Version());
|
|
|
|
return 0;
|
|
|
|
} else if (!(argc == 4 || (argc == 5 && strcmp(argv[1], "-t") == 0) ||
|
|
|
|
(argc == 6 && strcmp(argv[1], "-r") == 0))) {
|
2018-04-21 04:15:04 +08:00
|
|
|
printf("Usage: %s -v | --version |\n"
|
2018-04-16 13:56:29 +08:00
|
|
|
" %s [-t | -r [reverse policy] ] word_list_file"
|
|
|
|
" dawg_file unicharset_file\n", argv[0], argv[0]);
|
2009-07-11 10:44:07 +08:00
|
|
|
return 1;
|
|
|
|
}
|
2010-11-24 02:34:14 +08:00
|
|
|
tesseract::Classify *classify = new tesseract::Classify();
|
2009-07-11 10:44:07 +08:00
|
|
|
int argv_index = 0;
|
|
|
|
if (argc == 5) ++argv_index;
|
2012-02-02 11:02:16 +08:00
|
|
|
tesseract::Trie::RTLReversePolicy reverse_policy =
|
|
|
|
tesseract::Trie::RRP_DO_NO_REVERSE;
|
|
|
|
if (argc == 6) {
|
|
|
|
++argv_index;
|
|
|
|
int tmp_int;
|
|
|
|
sscanf(argv[++argv_index], "%d", &tmp_int);
|
|
|
|
reverse_policy = static_cast<tesseract::Trie::RTLReversePolicy>(tmp_int);
|
|
|
|
tprintf("Set reverse_policy to %s\n",
|
|
|
|
tesseract::Trie::get_reverse_policy_name(reverse_policy));
|
|
|
|
}
|
2010-11-24 02:34:14 +08:00
|
|
|
if (argc == 7) argv_index += 3;
|
2009-07-11 10:44:07 +08:00
|
|
|
const char* wordlist_filename = argv[++argv_index];
|
|
|
|
const char* dawg_filename = argv[++argv_index];
|
|
|
|
const char* unicharset_file = argv[++argv_index];
|
2011-03-22 05:48:58 +08:00
|
|
|
tprintf("Loading unicharset from '%s'\n", unicharset_file);
|
2010-11-24 02:34:14 +08:00
|
|
|
if (!classify->getDict().getUnicharset().load_from_file(unicharset_file)) {
|
2009-07-11 10:44:07 +08:00
|
|
|
tprintf("Failed to load unicharset from '%s'\n", unicharset_file);
|
2010-11-24 02:34:14 +08:00
|
|
|
delete classify;
|
2009-07-11 10:44:07 +08:00
|
|
|
return 1;
|
|
|
|
}
|
2010-11-24 02:34:14 +08:00
|
|
|
const UNICHARSET &unicharset = classify->getDict().getUnicharset();
|
2012-02-02 11:02:16 +08:00
|
|
|
if (argc == 4 || argc == 6) {
|
2009-07-11 10:44:07 +08:00
|
|
|
tesseract::Trie trie(
|
|
|
|
// the first 3 arguments are not used in this case
|
|
|
|
tesseract::DAWG_TYPE_WORD, "", SYSTEM_DAWG_PERM,
|
2014-02-04 03:18:23 +08:00
|
|
|
unicharset.size(), classify->getDict().dawg_debug_level);
|
2011-03-22 05:48:58 +08:00
|
|
|
tprintf("Reading word list from '%s'\n", wordlist_filename);
|
2013-09-23 23:26:50 +08:00
|
|
|
if (!trie.read_and_add_word_list(wordlist_filename, unicharset,
|
|
|
|
reverse_policy)) {
|
|
|
|
tprintf("Failed to add word list from '%s'\n", wordlist_filename);
|
2008-04-22 08:39:51 +08:00
|
|
|
exit(1);
|
|
|
|
}
|
2011-03-22 05:48:58 +08:00
|
|
|
tprintf("Reducing Trie to SquishedDawg\n");
|
2009-07-11 10:44:07 +08:00
|
|
|
tesseract::SquishedDawg *dawg = trie.trie_to_dawg();
|
2016-12-13 15:08:01 +08:00
|
|
|
if (dawg != nullptr && dawg->NumEdges() > 0) {
|
2011-03-22 05:48:58 +08:00
|
|
|
tprintf("Writing squished DAWG to '%s'\n", dawg_filename);
|
2010-11-30 09:01:13 +08:00
|
|
|
dawg->write_squished_dawg(dawg_filename);
|
|
|
|
} else {
|
2011-03-22 05:48:58 +08:00
|
|
|
tprintf("Dawg is empty, skip producing the output file\n");
|
2010-11-30 09:01:13 +08:00
|
|
|
}
|
2009-07-11 10:44:07 +08:00
|
|
|
delete dawg;
|
2010-11-24 02:34:14 +08:00
|
|
|
} else if (argc == 5) {
|
2011-03-22 05:48:58 +08:00
|
|
|
tprintf("Loading dawg DAWG from '%s'\n", dawg_filename);
|
2009-07-11 10:44:07 +08:00
|
|
|
tesseract::SquishedDawg words(
|
|
|
|
dawg_filename,
|
|
|
|
// these 3 arguments are not used in this case
|
2010-11-24 02:34:14 +08:00
|
|
|
tesseract::DAWG_TYPE_WORD, "", SYSTEM_DAWG_PERM,
|
|
|
|
classify->getDict().dawg_debug_level);
|
2011-03-22 05:48:58 +08:00
|
|
|
tprintf("Checking word list from '%s'\n", wordlist_filename);
|
2009-07-11 10:44:07 +08:00
|
|
|
words.check_for_words(wordlist_filename, unicharset, true);
|
2010-11-24 02:34:14 +08:00
|
|
|
} else { // should never get here
|
2011-03-22 05:48:58 +08:00
|
|
|
tprintf("Invalid command-line options\n");
|
2010-11-24 02:34:14 +08:00
|
|
|
exit(1);
|
2008-04-22 08:39:51 +08:00
|
|
|
}
|
2010-11-24 02:34:14 +08:00
|
|
|
delete classify;
|
2009-07-11 10:44:07 +08:00
|
|
|
return 0;
|
2007-07-18 09:15:07 +08:00
|
|
|
}
|