Codestyle

spacy_nlp

@@ -7,29 +7,25 @@ import spacy
 import textwrap
 
 parser = argparse.ArgumentParser(
-    description='Tag a text file with spaCy and save it as a verticalized text file.'
-)
-parser.add_argument(
-    'i',
-    metavar='txt-sourcefile',
-)
-parser.add_argument(
-    '-l',
-    choices=['de', 'el', 'en', 'es', 'fr', 'it', 'nl', 'pt'],
-    dest='lang',
-    required=True
-)
-parser.add_argument(
-    'o',
-    metavar='vrt-destfile',
+    description=('Tag a text file with spaCy and save it as a verticalized '
+                 'text file.')
 )
+parser.add_argument('i', metavar='txt-sourcefile')
+parser.add_argument('-l',
+                    choices=['de', 'el', 'en', 'es', 'fr', 'it', 'nl', 'pt'],
+                    dest='lang',
+                    required=True)
+parser.add_argument('o', metavar='vrt-destfile')
 args = parser.parse_args()
 
-SPACY_MODELS = {
-    'de': 'de_core_news_sm', 'el': 'el_core_news_sm', 'en': 'en_core_web_sm',
-    'es': 'es_core_news_sm', 'fr': 'fr_core_news_sm', 'it': 'it_core_news_sm',
-    'nl': 'nl_core_news_sm', 'pt': 'pt_core_news_sm'
-}
+SPACY_MODELS = {'de': 'de_core_news_sm',
+                'el': 'el_core_news_sm',
+                'en': 'en_core_web_sm',
+                'es': 'es_core_news_sm',
+                'fr': 'fr_core_news_sm',
+                'it': 'it_core_news_sm',
+                'nl': 'nl_core_news_sm',
+                'pt': 'pt_core_news_sm'}
 
 # Set the language model for spacy
 nlp = spacy.load(SPACY_MODELS[args.lang])
@@ -45,9 +41,9 @@ with open(args.i) as input_file:
 output_file = open(args.o, 'w+')
 
 output_file.write(
-    '<?xml version="1.0" encoding="UTF-8"?>\n<corpus>\n<text id="%s">\n' % (
-        os.path.basename(args.i).rsplit(".", 1)[0]
-    )
+    '<?xml version="1.0" encoding="UTF-8"?>\n'
+    '<corpus>\n'
+    '<text id="{}">\n'.format(os.path.basename(args.i).rsplit(".", 1)[0])
 )
 for text in texts:
     # Run spacy nlp over the text (partial string if above 1 million chars)
@@ -61,11 +57,18 @@ for text in texts:
             # Write all information in .vrt style to the output file
             # text, lemma, simple_pos, pos, ner
             output_file.write(
-                token.text + '\t' + token.lemma_ + '\t'
-                + token.pos_ + '\t' + token.tag_ + '\t'
-                + (token.ent_type_ if token.ent_type_ != '' else 'NULL') + '\n'
+                '{}\t{}\t{}\t{}\t{}\n'.format(
+                    token.text,
+                    token.lemma_,
+                    token.pos_,
+                    token.tag_,
+                    token.ent_type_ if token.ent_type_ != '' else 'NULL'
+                )
             )
         output_file.write('</s>\n')
-output_file.write('</text>\n</corpus>')
+output_file.write(
+    '</text>\n'
+    '</corpus>'
+)
 
 output_file.close()