training/combine_tessdata.cpp File Reference

#include "tessdatamanager.h"

Go to the source code of this file.

Functions
int	main (int argc, char **argv)

---

Function Documentation

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 66 of file combine_tessdata.cpp.

                                {
  int i;
  if (argc == 2) {
    printf("Combining tessdata files\n");
    STRING lang = argv[1];
    char* last = &argv[1][strlen(argv[1])-1];
    if (*last != '.')
      lang += '.';
    STRING output_file = lang;
    output_file += kTrainedDataSuffix;
    if (!tesseract::TessdataManager::CombineDataFiles(
        lang.string(), output_file.string())) {
      printf("Error combining tessdata files into %s\n",
             output_file.string());
    } else {
      printf("Output %s created successfully.\n", output_file.string());
    }
  } 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;
    tm.Init(argv[2], 0);
    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];
        char* last = &argv[3][strlen(argv[3])-1];
        if (*last != '.')
          filename += '.';
        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;
    tm.Init(traineddata_filename.string(), 0);

    // Write the updated traineddata file.
    tm.OverwriteComponents(new_traineddata_filename, argv+3, argc-3);
    tm.End();
  } else {
    printf("Usage for combining tessdata components:\n"
           "  %s language_data_path_prefix\n"
           "  (e.g. %s tessdata/eng.)\n\n", argv[0], argv[0]);
    printf("Usage for extracting tessdata components:\n"
           "  %s -e traineddata_file [output_component_file...]\n"
           "  (e.g. %s -e eng.traineddata eng.unicharset)\n\n",
           argv[0], argv[0]);
    printf("Usage for overwriting tessdata components:\n"
           "  %s -o traineddata_file [input_component_file...]\n"
           "  (e.g. %s -o eng.traineddata eng.unicharset)\n\n",
           argv[0], argv[0]);
    printf("Usage for unpacking all tessdata components:\n"
           "  %s -u traineddata_file output_path_prefix\n"
           "  (e.g. %s -u eng.traineddata tmp/eng.)\n", argv[0], argv[0]);
    return 1;
  }
}