Making Iobber work with Wcrft2

iobber/iobber_txt.py

@@ -20,9 +20,7 @@ import sys
 from optparse import OptionParser
 
 import corpus2
-
-from wcrft import tagger
-from wcrft import corpio as tagger_io
+import wcrft2
 
 import chunker
 
@@ -111,7 +109,10 @@ def main(files, tagger_config, tagger_dir, shall_chunk,
 	"""Create a Tagger (WCRFT) and a Chunker (IOBBER) object
 	and get all the input parts processed according to function args."""
 
-	tagr = tagger.Tagger(tagger_config, tagger_dir)
+	tagr = wcrft2.Tagger(tagger_config, tagger_dir)
+	tagset = tagr.get_tagset()
+	maca_conf = tagr.get_maca_config()
+
 	if shall_chunk:
 		chunkr = chunker.Chunker(chunker_config, chunker_dir)
 
@@ -139,16 +140,13 @@ def main(files, tagger_config, tagger_dir, shall_chunk,
 		tagr.load_model()
 		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()))
+			assert (tagset.name() == chunkr.tagset.name()), ('Tagger and chunker config must'
+					+ 'operate on the same tagset: %s v. %s' % (tagset.name(), chunkr.tagset.name()))
 		for in_path, out_path in zip(inputs, outputs):
 			if in_path and verbose:
 				sys.stderr.write('Processing %s...\n' % in_path)
-			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)
+			reader = wcrft2.get_reader(in_path, input_format, tagset, maca_conf)
+			writer = wcrft2.get_writer(out_path, output_format, tagset)
 			while True:
 				par = reader.get_next_chunk() # here `chunk' denotes paragraph
 				if not par: