corpus-merge

#!/usr/bin/python
# -*- coding: utf-8 -*-
import sys
from optparse import OptionParser
from collections import defaultdict as dd
from itertools import repeat, izip
import corpus2

descr = """%prog [options] CORPUSFILES
Reads corpus files and outputs everything.
Available input formats: """ + ' '.join(corpus2.TokenReader.available_reader_types()) + """
""" + ' '.join(corpus2.TokenReader.available_reader_types_help()) + """
Available output formats: """ + ' '.join(corpus2.TokenWriter.available_writer_types()) + """
""" + ' '.join(corpus2.TokenWriter.available_writer_types_help())


def sentences(rdr):
	"""Yields subsequent sentences from a reader."""
	while True:
		sent = rdr.get_next_sentence()
		if not sent:
			break
		yield sent


def chunks(rdr):
	"""Yields subsequent sentences from a reader."""
	while True:
		chunk = rdr.get_next_chunk()
		if not chunk:
			break
		yield chunk

def go():
	parser = OptionParser(usage=descr)
	parser.add_option('-i', '--input-format', type='string', action='store',
		dest='input_format', default='xces',
		help='set the input format; default: xces-fast')
	parser.add_option('-o', '--output-format', type='string', action='store',
		dest='output_format', default='xces',
		help='set the output format; default: xces')
	parser.add_option('-t', '--tagset', type='string', action='store',
		dest='tagset', default='kipi',
		help='set the tagset used in input; default: kipi')
	parser.add_option('-C', '--chunks', action='store_true',
		dest='chunks', default=False,
		help='Process chunks (select chunks/sentences, not tokens)')
	parser.add_option('-v', '--verbose', action='store_true',
		dest='verbose', default=False,
		help='verbose mode')
	parser.add_option('--input-list', default=None, help='file with a list of input files')
	(options, args) = parser.parse_args()
	
	if options.input_list is not None:
		with open(options.input_list) as listfile:
			for line in listfile:
				args.append(line.strip())

	if len(args) < 1:
		print 'You need to provide at least one input corpus.'
		print 'See %s --help' % sys.argv[0]
		sys.exit(1)
	
	inpath = args[0]
	# load a tagset, create a reader
	tagset = corpus2.get_named_tagset(options.tagset)
	writer = corpus2.TokenWriter.create_stdout_writer(options.output_format, tagset)
	for arg in args:
		reader = corpus2.TokenReader.create_path_reader(options.input_format, tagset, arg)
		if options.chunks:
			for chunk in chunks(reader):
				writer.write_chunk(chunk)
		else:
			for sent in sentences(reader):
				writer.write_sentence(sent)

if __name__ == '__main__':
	go()