int main(int argc, char** argv) {
int option;
const char* output_directory = ".";
STRING unicharset_file_name;
// Special characters are now included by default.
UNICHARSET unicharset;
setlocale(LC_ALL, "");
// Print usage
if (argc <= 1) {
printf("Usage: %s [-D DIRECTORY] FILE...\n", argv[0]);
exit(1);
}
// Parse arguments
while ((option = tessopt(argc, argv, "D" )) != EOF) {
switch (option) {
case 'D':
output_directory = tessoptarg;
++tessoptind;
break;
}
}
// Save file name
unicharset_file_name = output_directory;
unicharset_file_name += "/";
unicharset_file_name += kUnicharsetFileName;
// Load box files
for (; tessoptind < argc; ++tessoptind) {
printf("Extracting unicharset from %s\n", argv[tessoptind]);
FILE* box_file = fopen(argv[tessoptind], "rb");
if (box_file == NULL) {
printf("Cannot open box file %s\n", argv[tessoptind]);
return -1;
}
TBOX box;
STRING unichar_string;
int line_number = 0;
while (ReadNextBox(&line_number, box_file, &unichar_string, &box)) {
unicharset.unichar_insert(unichar_string.string());
set_properties(&unicharset, unichar_string.string());
}
}
// Write unicharset file
if (unicharset.save_to_file(unicharset_file_name.string())) {
printf("Wrote unicharset file %s.\n", unicharset_file_name.string());
}
else {
printf("Cannot save unicharset file %s.\n", unicharset_file_name.string());
return -1;
}
return 0;
}
/*---------------------------------------------------------------------------*/
void ParseArguments(int argc, char **argv)
/*
** Parameters:
** argc number of command line arguments to parse
** argv command line arguments
** Globals:
** ShowSignificantProtos flag controlling proto display
** ShowInsignificantProtos flag controlling proto display
** Config current clustering parameters
** tessoptarg, tessoptind defined by tessopt sys call
** Argc, Argv global copies of argc and argv
** Operation:
** This routine parses the command line arguments that were
** passed to the program. The legal arguments are:
** -d "turn off display of samples"
** -p "turn off significant protos"
** -n "turn off insignificant proto"
** -S [ spherical | elliptical | mixed | automatic ]
** -M MinSamples "min samples per prototype (%)"
** -B MaxIllegal "max illegal chars per cluster (%)"
** -I Independence "0 to 1"
** -C Confidence "1e-200 to 1.0"
** -D Directory
** -R RoundingAccuracy
** -U InputUnicharsetFile
** -O OutputUnicharsetFile
** Return: none
** Exceptions: Illegal options terminate the program.
** History: 7/24/89, DSJ, Created.
*/
{
int Option;
int ParametersRead;
BOOL8 Error;
Error = FALSE;
while (( Option = tessopt( argc, argv, "F:O:U:R:D:C:I:M:B:S:n:p" )) != EOF )
{
switch ( Option )
{
case 'n':
sscanf(tessoptarg,"%d", &ParametersRead);
ShowInsignificantProtos = ParametersRead;
break;
case 'p':
sscanf(tessoptarg,"%d", &ParametersRead);
ShowSignificantProtos = ParametersRead;
break;
case 'C':
ParametersRead = sscanf( tessoptarg, "%lf", &(Config.Confidence) );
if ( ParametersRead != 1 ) Error = TRUE;
else if ( Config.Confidence > 1 ) Config.Confidence = 1;
else if ( Config.Confidence < 0 ) Config.Confidence = 0;
break;
case 'I':
ParametersRead = sscanf( tessoptarg, "%f", &(Config.Independence) );
if ( ParametersRead != 1 ) Error = TRUE;
else if ( Config.Independence > 1 ) Config.Independence = 1;
else if ( Config.Independence < 0 ) Config.Independence = 0;
break;
case 'M':
ParametersRead = sscanf( tessoptarg, "%f", &(Config.MinSamples) );
if ( ParametersRead != 1 ) Error = TRUE;
else if ( Config.MinSamples > 1 ) Config.MinSamples = 1;
else if ( Config.MinSamples < 0 ) Config.MinSamples = 0;
break;
case 'B':
ParametersRead = sscanf( tessoptarg, "%f", &(Config.MaxIllegal) );
if ( ParametersRead != 1 ) Error = TRUE;
else if ( Config.MaxIllegal > 1 ) Config.MaxIllegal = 1;
else if ( Config.MaxIllegal < 0 ) Config.MaxIllegal = 0;
break;
case 'R':
ParametersRead = sscanf( tessoptarg, "%f", &RoundingAccuracy );
if ( ParametersRead != 1 ) Error = TRUE;
else if ( RoundingAccuracy > 0.01f ) RoundingAccuracy = 0.01f;
else if ( RoundingAccuracy < 0.0f ) RoundingAccuracy = 0.0f;
break;
case 'S':
switch ( tessoptarg[0] )
{
case 's': Config.ProtoStyle = spherical; break;
case 'e': Config.ProtoStyle = elliptical; break;
case 'm': Config.ProtoStyle = mixed; break;
case 'a': Config.ProtoStyle = automatic; break;
default: Error = TRUE;
}
break;
case 'D':
Directory = tessoptarg;
break;
case 'U':
InputUnicharsetFile = tessoptarg;
break;
case 'O':
OutputUnicharsetFile = tessoptarg;
break;
case 'F':
InputFontInfoFile = tessoptarg;
break;
case '?':
Error = TRUE;
break;
}
if ( Error )
{
fprintf (stderr, "usage: %s [-d] [-p] [-n]\n", argv[0] );
fprintf (stderr, "\t[-S ProtoStyle]\n");
fprintf (stderr, "\t[-M MinSamples] [-B MaxBad] [-I Independence]\n");
fprintf (stderr, "\t[-C Confidence] [-D Directory]\n");
fprintf (stderr, "\t[-U InputUnicharsetFile] [-O OutputUnicharsetFile]\n");
fprintf (stderr, "\t[-F FontInfoFile]\n");
fprintf (stderr, "\t[ TrainingPage ... ]\n");
exit (2);
}
}
} // ParseArguments