def main():
# Argument Parser
parser = argparse.ArgumentParser()
parser.add_argument(
"-txt",
dest="txt",
help="The files that contain the training examples",
)
parser.add_argument(
"-annotations",
dest="annotations",
help="The files that contain the labels for the training examples",
)
parser.add_argument(
"-out",
dest="out",
default=None,
help="Directory to output data",
)
parser.add_argument(
"-format",
dest="format",
help="Output format (%s)" % str(' or '.join(Note.supportedFormats())),
)
# Parse the command line arguments
args = parser.parse_args()
# Parse arguments
txt = args.txt
annotations = args.annotations
out_file = args.out
format = args.format
# Ensure annotations are specified
if not txt:
print >> sys.stderr, '\n\tError: Must supply text file'
print >> sys.stderr
exit(1)
elif not os.path.exists(txt):
print >> sys.stderr, '\n\tError: Given text file does not exist'
print >> sys.stderr
exit(1)
# Ensure annotations are specified
extensions = Note.supportedFormatExtensions()
if not annotations:
print >> sys.stderr, '\n\tError: Must supply annotations'
print >> sys.stderr
exit(2)
elif not os.path.exists(txt):
print >> sys.stderr, '\n\tError: Given annotation file does not exist'
print >> sys.stderr
exit(2)
elif os.path.splitext(annotations)[1][1:] not in extensions:
print >> sys.stderr, '\n\tError: annotation must be a supported format'
print >> sys.stderr, '\t\t(.%s)' % str(' or .'.join(extensions))
print >> sys.stderr
exit(2)
# Ensure output format is specified
if (not format) or (format not in Note.supportedFormats()):
print >> sys.stderr, '\n\tError: Must specify supported output format'
print >> sys.stderr, '\t\t(%s)' % str(' or '.join(
Note.supportedFormats()))
print >> sys.stderr
exit(3)
# Automatically find the input file format
in_extension = os.path.splitext(annotations)[1][1:]
for f, ext in Note.dictOfFormatToExtensions().items():
if ext == in_extension:
in_format = f
# Read input data into note object
in_note = Note(in_format)
in_note.read(txt, annotations)
# Convert data to standard format
internal_output = in_note.write_standard()
os_handle, tmp_file = tempfile.mkstemp(dir=tmp_dir, suffix="format_temp")
with open(tmp_file, 'w') as f:
f.write(internal_output)
os.close(os_handle)
#print internal_output
# Read internal standard data into new file with given output format
out_note = Note(format)
out_note.read_standard(txt, tmp_file)
# Output data
out = out_note.write()
if out_file:
with open(out_file, 'w') as out_f:
out_f.write(out)
else:
sys.stdout.write(out)
# Clean up
os.remove(tmp_file)
if out_file:
out_f.close()
def main():
# Argument Parser
parser = argparse.ArgumentParser()
parser.add_argument("-t",
dest = "txt",
help = "The files that contain the training examples",
)
parser.add_argument("-a",
dest = "annotations",
help = "The files that contain the labels for the training examples",
)
parser.add_argument("-o",
dest = "out",
default = None,
help = "Directory to output data",
)
parser.add_argument("-f",
dest = "format",
help = "Output format (%s)"%str(' or '.join(Note.supportedFormats())),
)
# Parse the command line arguments
args = parser.parse_args()
# Parse arguments
txt = args.txt
annotations = args.annotations
out_file = args.out
format = args.format
# Ensure annotations are specified
if not txt:
print >>sys.stderr, '\n\tError: Must supply text file'
print >>sys.stderr
exit(1)
elif not os.path.exists(txt):
print >>sys.stderr, '\n\tError: Given text file does not exist'
print >>sys.stderr
exit(1)
# Ensure annotations are specified
extensions = Note.supportedFormatExtensions()
if not annotations:
print >>sys.stderr, '\n\tError: Must supply annotations'
print >>sys.stderr
exit(2)
elif not os.path.exists(txt):
print >>sys.stderr, '\n\tError: Given annotation file does not exist'
print >>sys.stderr
exit(2)
elif os.path.splitext(annotations)[1][1:] not in extensions:
print >>sys.stderr, '\n\tError: annotation must be a supported format'
print >>sys.stderr, '\t\t(.%s)' %str(' or .'.join(extensions) )
print >>sys.stderr
exit(2)
# Ensure output format is specified
if (not format) or (format not in Note.supportedFormats()):
print >>sys.stderr, '\n\tError: Must specify supported output format'
print >>sys.stderr, '\t\t(%s)' %str(' or '.join(Note.supportedFormats()))
print >>sys.stderr
exit(3)
# Automatically find the input file format
in_extension = os.path.splitext(annotations)[1][1:]
for f,ext in Note.dictOfFormatToExtensions().items():
if ext == in_extension:
in_format = f
# Read input data into note object
in_note = Note(in_format)
in_note.read(txt,annotations)
# Convert data to standard format
internal_output = in_note.write_standard()
os_handle,tmp_file = tempfile.mkstemp(dir=tmp_dir, suffix="format_temp")
with open(tmp_file, 'w') as f:
f.write(internal_output)
os.close(os_handle)
#print internal_output
# Read internal standard data into new file with given output format
out_note = Note(format)
out_note.read_standard(txt,tmp_file)
# Output data
out = out_note.write()
if out_file:
with open(out_file, 'w') as out_f:
out_f.write(out)
else:
sys.stdout.write(out)
# Clean up
os.remove(tmp_file)
if out_file:
out_f.close()
