diff --git a/nlp b/nlp index 482ca7a..3866106 100755 --- a/nlp +++ b/nlp @@ -92,7 +92,7 @@ class NLPWorkflow(WorkflowRunner): max(1, int(self.n_cores / len(self.jobs))) ) for index, job in enumerate(self.jobs): - cmd = 'spacy_nlp -l "{}" "{}" "{}" "{}"'.format( + cmd = 'spacy_nlp -l "{}" "{}" "{}" {}'.format( self.lang, job['path'], os.path.join(job['output_dir'], job['name'] + '.vrt'), diff --git a/spacy_nlp b/spacy_nlp index d65dd81..a8863ec 100755 --- a/spacy_nlp +++ b/spacy_nlp @@ -42,7 +42,7 @@ if args.check_encoding: bytes = input_file.read() encoding = chardet.detect(bytes)['encoding'] else: - encoding='utf-8' + encoding = 'utf-8' # Read text from the input file and if neccessary split it into parts with a # length of less than 1 million characters. with open(args.i, encoding=encoding) as input_file: