unicharset_extractor.cpp File Reference

#include <cstdlib>
#include "boxread.h"
#include "commandlineflags.h"
#include "genericvector.h"
#include "lang_model_helpers.h"
#include "normstrngs.h"
#include "strngs.h"
#include "tprintf.h"
#include "unicharset.h"
#include "unicharset_training_utils.h"

Go to the source code of this file.

Namespaces
	tesseract

Functions
	STRING_PARAM_FLAG (output_unicharset, "unicharset", "Output file path")
	INT_PARAM_FLAG (norm_mode, 1, "Normalization mode: 1=Combine graphemes, " "2=Split graphemes, 3=Pure unicode")
int	tesseract::Main (int argc, char **argv)
int	main (int argc, char **argv)

Function Documentation

INT_PARAM_FLAG()

INT_PARAM_FLAG	(	norm_mode	,
		1	,
		"Normalization mode:	1 = Combine graphemes,
		" "	2 = Split graphemes
	)

main()

int main	(	int	argc,
		char **	argv
	)

This program reads in a text file consisting of feature samples from a training page in the following format:

   FontName UTF8-char-str xmin ymin xmax ymax page-number
    NumberOfFeatureTypes(N)
      FeatureTypeName1 NumberOfFeatures(M)
         Feature1
         ...
         FeatureM
      FeatureTypeName2 NumberOfFeatures(M)
         Feature1
         ...
         FeatureM
      ...
      FeatureTypeNameN NumberOfFeatures(M)
         Feature1
         ...
         FeatureM
   FontName CharName ...

The result of this program is a binary inttemp file used by the OCR engine.

Parameters

argc	number of command line arguments
argv	array of command line arguments

Returns

none

Note

Exceptions: none

History: Fri Aug 18 08:56:17 1989, DSJ, Created.

History: Mon May 18 1998, Christy Russson, Revistion started.

Definition at line 97 of file unicharset_extractor.cpp.

                                {
  if (argc > 1) {
    tesseract::ParseCommandLineFlags(argv[0], &argc, &argv, true);
  }
  if (argc < 2) {
    tprintf(
        "Usage: %s [--output_unicharset filename] [--norm_mode mode]"
        " box_or_text_file [...]\n",
        argv[0]);
    tprintf("Where mode means:\n");
    tprintf(" 1=combine graphemes (use for Latin and other simple scripts)\n");
    tprintf(" 2=split graphemes (use for Indic/Khmer/Myanmar)\n");
    tprintf(" 3=pure unicode (use for Arabic/Hebrew/Thai/Tibetan)\n");
    tprintf("Reads box or plain text files to extract the unicharset.\n");
    return EXIT_FAILURE;
  }
  return tesseract::Main(argc, argv);
}

STRING_PARAM_FLAG()

STRING_PARAM_FLAG	(	output_unicharset	,
		"unicharset"	,
		"Output file path"
	)