sporada/nopaque
1
0
Fork 0
mirror of https://gitlab.ub.uni-bielefeld.de/sfb1288inf/nopaque.git synced 2024-12-24 10:34:17 +00:00
Code Issues Projects Releases Wiki Activity

Add test snippet for fast cpos boundary calculation for s_attrs

Browse Source
This commit is contained in:
Patrick Jentsch 2023-06-22 14:19:14 +02:00
parent 2739dc4b4f
commit f84ac48975
1 changed files with 15 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
app/corpora/cqi_over_socketio/cqi_corpora_corpus.py
View File

@ -50,6 +50,21 @@ def cqi_corpora_corpus_update_db(cqi_client: cqi.CQiClient, corpus_name: str):
@cqi_over_socketio
def cqi_corpora_corpus_get_visualization_data(cqi_client: cqi.CQiClient, corpus_name: str):
cqi_corpus = cqi_client.corpora.get(corpus_name)
##########################################################################
# A faster way to get cpos boundaries for smaller s_attrs #
##########################################################################
# cqi_corpus.query('Last', '<s> []* </s>;')
# cqi_subcorpus = cqi_corpus.subcorpora.get('Last')
# print(cqi_subcorpus.size)
# first_match = 0
# last_match = cqi_subcorpus.attrs['size'] - 1
# match_boundaries = zip(
# list(range(first_match, last_match + 1)),
# cqi_subcorpus.dump(cqi_subcorpus.attrs['fields']['match'], first_match, last_match),
# cqi_subcorpus.dump(cqi_subcorpus.attrs['fields']['matchend'], first_match, last_match)
# )
# for x in match_boundaries:
# print(x)
cqi_p_attrs = {
p_attr.name: p_attr
for p_attr in cqi_corpus.positional_attributes.list()