mirror of
https://github.com/ilri/csv-metadata-quality.git
synced 2024-11-22 05:45:02 +01:00
csv_metadata_quality/check.py: Simplify AGROVOC check
I recycled this code from a separate agrovoc-lookup.py script that checks lines in a text file to see if they are valid AGROVOC terms or not. There I was concerned about skipping comments or something I think, but we don't need to check that here. We simply check the term that is in the field and inform the user if it's valid or not.
This commit is contained in:
parent
6d02f5026a
commit
884e8f970d
@ -212,7 +212,6 @@ def agrovoc(field, field_name):
|
||||
"""
|
||||
|
||||
from datetime import timedelta
|
||||
import re
|
||||
import requests
|
||||
import requests_cache
|
||||
|
||||
@ -222,18 +221,6 @@ def agrovoc(field, field_name):
|
||||
|
||||
# Try to split multi-value field on "||" separator
|
||||
for value in field.split('||'):
|
||||
# match lines beginning with words, paying attention to subjects with
|
||||
# special characters like spaces, quotes, dashes, parentheses, etc:
|
||||
# SUBJECT
|
||||
# ANOTHER SUBJECT
|
||||
# XANTHOMONAS CAMPESTRIS PV. MANIHOTIS
|
||||
# WOMEN'S PARTICIPATION
|
||||
# COMMUNITY-BASED FOREST MANAGEMENT
|
||||
# INTERACCIÓN GENOTIPO AMBIENTE
|
||||
# COCOA (PLANT)
|
||||
pattern = re.compile(r'^[\w\-\.\'\(\)]+?[\w\s\-\.\'\(\)]+$')
|
||||
|
||||
if pattern.match(value):
|
||||
request_url = f'http://agrovoc.uniroma2.it/agrovoc/rest/v1/agrovoc/search?query={value}'
|
||||
|
||||
# enable transparent request cache with thirty days expiry
|
||||
|
Loading…
Reference in New Issue
Block a user