mirror of
https://github.com/qurator-spk/page2tsv.git
synced 2025-07-12 11:39:53 +02:00
make code more robust
This commit is contained in:
parent
8d8bf517b9
commit
80cf64abcf
1 changed files with 1 additions and 1 deletions
|
@ -346,7 +346,7 @@ def tsv2tsv(tsv_in_file, tsv_out_file, ner_rest_endpoint, noproxy,
|
||||||
prev_pos = 0
|
prev_pos = 0
|
||||||
for idx, _ in tsv_out.iterrows():
|
for idx, _ in tsv_out.iterrows():
|
||||||
|
|
||||||
if prev_pos != 0 and not tsv_out.loc[idx, 'NE-TAG'].startswith('I-') and \
|
if prev_pos != 0 and not str(tsv_out.loc[idx, 'NE-TAG']).startswith('I-') and \
|
||||||
tsv_out.loc[idx, 'No.'] == 0 or len(tsv_out.loc[idx, 'TOKEN']) == 0:
|
tsv_out.loc[idx, 'No.'] == 0 or len(tsv_out.loc[idx, 'TOKEN']) == 0:
|
||||||
word_pos = 0
|
word_pos = 0
|
||||||
|
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue