Changed version and added main methods

iobber/iobber.py

@@ -77,18 +77,23 @@ def go():
 	config_fname = args[0]
 	files = args[1:]
 
-	tagr = chunker.Chunker(config_fname, options.data_dir,
-		verbose = options.verbose)
+	main(config_fname, files, options.out_path, options.data_dir,
+		options.verbose, options.input_format, options.output_format,
+		options.preserve_chunks, options.batch, options.is_training)
 
-	if options.is_training:
+def main(config_fname, files, out_path, data_dir, verbose, input_format, output_format, preserve_chunks, batch, is_training):	
+	tagr = chunker.Chunker(config_fname, data_dir,
+		verbose = verbose)
+	
+	if is_training:
 		# chunker training
 		assert len(files) == 1, 'must provide path to training file'
-		tagr.train_and_save(files[0], options.input_format)
+		tagr.train_and_save(files[0], input_format)
 	else:
 		# normal chunker performance
 		inputs = []
 		outputs = []
-		if options.batch: # read each arg as input path list
+		if batch: # read each arg as input path list
 			for pathpath in files:
 				inputs.extend(lines(pathpath))
 			outputs = [path + '.chunked' for path in inputs]
@@ -98,17 +103,17 @@ def go():
 				outputs.append(None)
 			else:
 				inputs.append(files[0])
-				outputs.append(options.out_path)
+				outputs.append(out_path)
 		else: # multiple paths as args
 			inputs = files
 			outputs = [path + '.chunked' for path in inputs]
 		tagr.load_model()
 		for in_path, out_path in zip(inputs, outputs):
-			if in_path and options.verbose:
+			if in_path and verbose:
 				sys.stderr.write('Processing %s...\n' % in_path)
 			tagr.tag_input(in_path, out_path,
-				options.input_format, options.output_format,
-				options.preserve_chunks)
+				input_format, output_format,
+				preserve_chunks)
 
 if __name__ == '__main__':
 	go()
\ No newline at end of file

iobber/iobber_txt.py

@@ -91,17 +91,27 @@ def go():
 	
 	files = args
 	
-	tagr = tagger.Tagger(options.tagger_config, options.tagger_dir)
-	if options.shall_chunk:
-		chunkr = chunker.Chunker(options.chunker_config, options.chunker_dir)
+	main(files, options.tagger_config, options.tagger_dir, options.shall_chunk,
+		options.chunker_config, options.chunker_dir, options.maca_config,
+		options.batch, options.out_path, options.verbose,
+		options.input_format, options.output_format)
 
-	if options.maca_config != '':
-		tagr.maca_config = options.maca_config
+def main(files, tagger_config, tagger_dir, shall_chunk,
+		chunker_config, chunker_dir, maca_config,
+		batch, out_path, verbose,
+		input_format, output_format):
+
+	tagr = tagger.Tagger(tagger_config, tagger_dir)
+	if shall_chunk:
+		chunkr = chunker.Chunker(chunker_config, chunker_dir)
+
+	if maca_config != '':
+		tagr.maca_config = maca_config
 
 	# tag and chunk
 	inputs = []
 	outputs = []
-	if options.batch: # read each arg as input path list
+	if batch: # read each arg as input path list
 		for pathpath in files:
 			inputs.extend(lines(pathpath))
 		outputs = [path + '.tag' for path in inputs]
@@ -111,23 +121,23 @@ def go():
 			outputs.append(None)
 		else:
 			inputs.append(files[0])
-			outputs.append(options.out_path)
+			outputs.append(out_path)
 	else: # multiple paths as args
 		inputs = files
 		outputs = [path + '.tag' for path in inputs]
 	if inputs:
 		tagr.load_model()
-		if options.shall_chunk:
+		if shall_chunk:
 			chunkr.load_model()
 			assert (tagr.tagset.name()
 					== chunkr.tagset.name()), ('Tagger and chunker config must'
 							+ 'operate on the same tagset: %s v. %s' % (tagr.tagset.name(),
 								chunkr.tagset.name()))
 		for in_path, out_path in zip(inputs, outputs):
-			if in_path and options.verbose:
+			if in_path and verbose:
 				sys.stderr.write('Processing %s...\n' % in_path)
-			reader = tagger_io.get_reader(in_path, tagr.tagset, options.input_format, tagr.maca_config)
-			writer = tagger_io.get_writer(out_path, tagr.tagset, options.output_format)
+			reader = tagger_io.get_reader(in_path, tagr.tagset, input_format, tagr.maca_config)
+			writer = tagger_io.get_writer(out_path, tagr.tagset, output_format)
 			while True:
 				par = reader.get_next_chunk() # here `chunk' denotes paragraph
 				if not par:
@@ -146,7 +156,7 @@ def go():
 					new_sent = corpus2.AnnotatedSentence.cast_as_sentence(new_asent)
 					# preserve_ambiguity = False
 					tagr.tag_sentence(new_sent, False)
-					if options.shall_chunk:
+					if shall_chunk:
 						chunkr.tag_sentence(new_sent)
 					# create a new paragraph with the new sentence
 					new_par.append(new_sent)

setup.py

@@ -4,10 +4,10 @@
 from setuptools import setup
 
 setup(name='iobber',
-	version='1.0.1',
+	version='1.1.0',
 	description='Chunker for Slavic languages based on CRF++ and WCCL',
-	author= "Adam Radziszewski",
-	author_email="adam.radziszewski@pwr.wroc.pl",
+	author= "Adam Radziszewski, Adam Pawlaczek",
+	author_email="adam.radziszewski@pwr.wroc.pl, adam@pawlaczek.eu",
 	packages=[
 		'iobber'
 	],