sporada/nlp
1
0
Fork 0
mirror of https://gitlab.ub.uni-bielefeld.de/sfb1288inf/nlp.git synced 2024-12-26 07:54:18 +00:00
Code Issues Projects Releases Wiki Activity

Fix last errors

Browse Source
This commit is contained in:
Stephan Porada 2020-02-12 14:25:08 +01:00
parent 1a3e4a0a02
commit 79043f3dd7
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
nlp
View File

@ -92,7 +92,7 @@ class NLPWorkflow(WorkflowRunner):
max(1, int(self.n_cores / len(self.jobs))) max(1, int(self.n_cores / len(self.jobs)))
) )
for index, job in enumerate(self.jobs): for index, job in enumerate(self.jobs):
cmd = 'spacy_nlp -l "{}" "{}" "{}" "{}"'.format( cmd = 'spacy_nlp -l "{}" "{}" "{}" {}'.format(
self.lang, self.lang,
job['path'], job['path'],
os.path.join(job['output_dir'], job['name'] + '.vrt'), os.path.join(job['output_dir'], job['name'] + '.vrt'),

2
spacy_nlp
View File

@ -42,7 +42,7 @@ if args.check_encoding:
bytes = input_file.read() bytes = input_file.read()
encoding = chardet.detect(bytes)['encoding'] encoding = chardet.detect(bytes)['encoding']
else: else:
encoding='utf-8' encoding = 'utf-8'
# Read text from the input file and if neccessary split it into parts with a # Read text from the input file and if neccessary split it into parts with a
# length of less than 1 million characters. # length of less than 1 million characters.
with open(args.i, encoding=encoding) as input_file: with open(args.i, encoding=encoding) as input_file: