sporada/nlp
1
0
Fork 0
mirror of https://gitlab.ub.uni-bielefeld.de/sfb1288inf/nlp.git synced 2024-12-26 21:14:18 +00:00
Code Issues Projects Releases Wiki Activity

Remove id xml attribute from output file

Browse Source
This commit is contained in:
Patrick Jentsch 2020-01-27 15:59:32 +01:00
parent b0a402b3ac
commit 5f20f9be40
1 changed files with 5 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
spacy_nlp
View File

@ -40,11 +40,9 @@ with open(args.i) as input_file:
# Create and open the output file # Create and open the output file
output_file = open(args.o, 'w+') output_file = open(args.o, 'w+')
output_file.write( output_file.write('<?xml version="1.0" encoding="UTF-8"?>\n'
'<?xml version="1.0" encoding="UTF-8"?>\n'
'<corpus>\n' '<corpus>\n'
'<text id="{}">\n'.format(os.path.basename(args.i).rsplit(".", 1)[0]) '<text>\n')
)
for text in texts: for text in texts:
# Run spacy nlp over the text (partial string if above 1 million chars) # Run spacy nlp over the text (partial string if above 1 million chars)
doc = nlp(text) doc = nlp(text)
@ -66,9 +64,7 @@ for text in texts:
) )
) )
output_file.write('</s>\n') output_file.write('</s>\n')
output_file.write( output_file.write('</text>\n'
'</text>\n' '</corpus>')
'</corpus>'
)
output_file.close() output_file.close()