2009-07-11 10:44:07 +08:00
|
|
|
///////////////////////////////////////////////////////////////////////
|
|
|
|
// File: combine_tessdata
|
|
|
|
// Description: Creates a unified traineddata file from several
|
|
|
|
// data files produced by the training process.
|
|
|
|
// Author: Daria Antonova
|
|
|
|
// Created: Wed Jun 03 11:26:43 PST 2009
|
|
|
|
//
|
|
|
|
// (C) Copyright 2009, 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 "tessdatamanager.h"
|
|
|
|
|
2010-05-21 07:07:24 +08:00
|
|
|
// Main program to combine/extract/overwrite tessdata components
|
|
|
|
// in [lang].traineddata files.
|
|
|
|
//
|
|
|
|
// To combine all the individual tessdata components (unicharset, DAWGs,
|
|
|
|
// classifier templates, ambiguities, language configs) located at, say,
|
|
|
|
// /home/$USER/temp/eng.* run:
|
|
|
|
//
|
|
|
|
// combine_tessdata /home/$USER/temp/eng.
|
|
|
|
//
|
|
|
|
// The result will be a combined tessdata file /home/$USER/temp/eng.traineddata
|
|
|
|
//
|
|
|
|
// Specify option -e if you would like to extract individual components
|
|
|
|
// from a combined traineddata file. For example, to extract language config
|
|
|
|
// file and the unicharset from tessdata/eng.traineddata run:
|
|
|
|
//
|
|
|
|
// combine_tessdata -e tessdata/eng.traineddata
|
|
|
|
// /home/$USER/temp/eng.config /home/$USER/temp/eng.unicharset
|
|
|
|
//
|
|
|
|
// The desired config file and unicharset will be written to
|
|
|
|
// /home/$USER/temp/eng.config /home/$USER/temp/eng.unicharset
|
|
|
|
//
|
|
|
|
// Specify option -o to overwrite individual components of the given
|
|
|
|
// [lang].traineddata file. For example, to overwrite language config
|
|
|
|
// and unichar ambiguities files in tessdata/eng.traineddata use:
|
|
|
|
//
|
|
|
|
// combine_tessdata -o tessdata/eng.traineddata
|
|
|
|
// /home/$USER/temp/eng.config /home/$USER/temp/eng.unicharambigs
|
|
|
|
//
|
|
|
|
// As a result, tessdata/eng.traineddata will contain the new language config
|
|
|
|
// and unichar ambigs, plus all the original DAWGs, classifier teamples, etc.
|
|
|
|
//
|
|
|
|
// Note: the file names of the files to extract to and to overwrite from should
|
|
|
|
// have the appropriate file suffixes (extensions) indicating their tessdata
|
|
|
|
// component type (.unicharset for the unicharset, .unicharambigs for unichar
|
|
|
|
// ambigs, etc). See k*FileSuffix variable in ccutil/tessdatamanager.h.
|
|
|
|
//
|
|
|
|
// Specify option -u to unpack all the components to the specified path:
|
|
|
|
//
|
|
|
|
// combine_tessdata -u tessdata/eng.traineddata /home/$USER/temp/eng.
|
|
|
|
//
|
|
|
|
// This will create /home/$USER/temp/eng.* files with individual tessdata
|
|
|
|
// components from tessdata/eng.traineddata.
|
|
|
|
//
|
2009-07-11 10:44:07 +08:00
|
|
|
int main(int argc, char **argv) {
|
2010-05-21 07:07:24 +08:00
|
|
|
int i;
|
|
|
|
if (argc == 2) {
|
2010-09-28 09:03:17 +08:00
|
|
|
printf("Combining tessdata files\n");
|
2010-05-21 07:07:24 +08:00
|
|
|
STRING output_file = argv[1];
|
|
|
|
output_file += kTrainedDataSuffix;
|
|
|
|
if (!tesseract::TessdataManager::CombineDataFiles(
|
|
|
|
argv[1], output_file.string())) {
|
2010-09-28 09:03:17 +08:00
|
|
|
char* last = &argv[1][strlen(argv[1])-1];
|
2010-05-21 07:07:24 +08:00
|
|
|
printf("Error combining tessdata files into %s\n",
|
|
|
|
output_file.string());
|
2010-09-28 09:03:17 +08:00
|
|
|
if (*last != '.')
|
|
|
|
printf("Hint: the prefix is missing a period (.)\n");
|
2010-05-21 07:07:24 +08:00
|
|
|
}
|
|
|
|
} else if (argc >= 4 && (strcmp(argv[1], "-e") == 0 ||
|
|
|
|
strcmp(argv[1], "-u") == 0)) {
|
|
|
|
// Initialize TessdataManager with the data in the given traineddata file.
|
|
|
|
tesseract::TessdataManager tm;
|
2010-11-24 02:34:14 +08:00
|
|
|
tm.Init(argv[2], 0);
|
2010-05-21 07:07:24 +08:00
|
|
|
printf("Extracting tessdata components from %s\n", argv[2]);
|
|
|
|
if (strcmp(argv[1], "-e") == 0) {
|
|
|
|
for (i = 3; i < argc; ++i) {
|
|
|
|
if (tm.ExtractToFile(argv[i])) {
|
|
|
|
printf("Wrote %s\n", argv[i]);
|
|
|
|
} else {
|
|
|
|
printf("Not extracting %s, since this component"
|
|
|
|
" is not present\n", argv[i]);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
} else { // extract all the components
|
|
|
|
for (i = 0; i < tesseract::TESSDATA_NUM_ENTRIES; ++i) {
|
|
|
|
STRING filename = argv[3];
|
|
|
|
filename += tesseract::kTessdataFileSuffixes[i];
|
|
|
|
if (tm.ExtractToFile(filename.string())) {
|
|
|
|
printf("Wrote %s\n", filename.string());
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
tm.End();
|
|
|
|
} else if (argc >= 4 && strcmp(argv[1], "-o") == 0) {
|
|
|
|
// Rename the current traineddata file to a temporary name.
|
|
|
|
const char *new_traineddata_filename = argv[2];
|
|
|
|
STRING traineddata_filename = new_traineddata_filename;
|
|
|
|
traineddata_filename += ".__tmp__";
|
|
|
|
if (rename(new_traineddata_filename, traineddata_filename.string()) != 0) {
|
|
|
|
tprintf("Failed to create a temporary file %s\n",
|
|
|
|
traineddata_filename.string());
|
|
|
|
exit(1);
|
|
|
|
}
|
|
|
|
|
|
|
|
// Initialize TessdataManager with the data in the given traineddata file.
|
|
|
|
tesseract::TessdataManager tm;
|
2010-11-24 02:34:14 +08:00
|
|
|
tm.Init(traineddata_filename.string(), 0);
|
2010-05-21 07:07:24 +08:00
|
|
|
|
|
|
|
// Write the updated traineddata file.
|
|
|
|
tm.OverwriteComponents(new_traineddata_filename, argv+3, argc-3);
|
|
|
|
tm.End();
|
|
|
|
} else {
|
|
|
|
printf("Usage for combining tessdata components:\n"
|
2010-09-28 09:03:17 +08:00
|
|
|
"%s language_data_path_prefix (e.g. tessdata/eng.)\n", argv[0]);
|
|
|
|
printf("Usage for extracting tessdata components:\n"
|
|
|
|
"%s -e traineddata_file [output_component_file...]\n", argv[0]);
|
|
|
|
printf("Usage for overwriting tessdata components:\n"
|
|
|
|
"%s -o traineddata_file [input_component_file...]\n", argv[0]);
|
|
|
|
printf("Usage for unpacking all tessdata components:\n"
|
|
|
|
"%s -u traineddata_file output_path_prefix"
|
|
|
|
" (e.g. /tmp/eng.)\n", argv[0]);
|
2009-07-11 10:44:07 +08:00
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
}
|