Remove unused code

This commit is contained in:
Edward Betts 2021-11-14 08:01:19 +00:00
parent 5693bc6265
commit 4f6f0ed086
2 changed files with 75 additions and 6 deletions

View file

@ -1,3 +1,6 @@
from collections import defaultdict
import re
hq_pid = "P159"
coords_pid = "P625"
@ -50,3 +53,74 @@ def get_entity_coords(claims):
hq_pid: read_hq_coords(claims),
}
return {pid: values for pid, values in ret.items() if values}
def names_from_entity(entity, skip_lang=None):
if skip_lang is None:
skip_lang = set()
ret = defaultdict(list)
cat_start = 'Category:'
for k, v in entity['labels'].items():
if k in skip_lang:
continue
ret[v['value']].append(('label', k))
for k, v in entity['sitelinks'].items():
if k + 'wiki' in skip_lang:
continue
title = v['title']
if title.startswith(cat_start):
title = title[len(cat_start):]
first_letter = title[0]
if first_letter.isupper():
lc_first_title = first_letter.lower() + title[1:]
if lc_first_title in ret:
title = lc_first_title
ret[title].append(('sitelink', k))
for lang, value_list in entity.get('aliases', {}).items():
if lang in skip_lang or len(value_list) > 3:
continue
for name in value_list:
ret[name['value']].append(('alias', lang))
commonscats = entity.get('claims', {}).get('P373', [])
for i in commonscats:
if 'datavalue' not in i['mainsnak']:
continue
value = i['mainsnak']['datavalue']['value']
ret[value].append(('commonscat', None))
officialname = entity.get('claims', {}).get('P1448', [])
for i in officialname:
if 'datavalue' not in i['mainsnak']:
continue
value = i['mainsnak']['datavalue']['value']
ret[value['text']].append(('officialname', value['language']))
nativelabel = entity.get('claims', {}).get('P1705', [])
for i in nativelabel:
if 'datavalue' not in i['mainsnak']:
continue
value = i['mainsnak']['datavalue']['value']
ret[value['text']].append(('nativelabel', value['language']))
image = entity.get('claims', {}).get('P18', [])
for i in image:
if 'datavalue' not in i['mainsnak']:
continue
value = i['mainsnak']['datavalue']['value']
m = re.search(r'\.[a-z]{3,4}$', value)
if m:
value = value[:m.start()]
for pattern in r' - geograph\.org\.uk - \d+$', r'[, -]*0\d{2,}$':
m = re.search(pattern, value)
if m:
value = value[:m.start()]
break
ret[value].append(('image', None))
return ret

View file

@ -1,16 +1,11 @@
from matcher import utils
def test_pluralize_label():
v = {"language": "en", "value": "building"}
assert utils.pluralize_label(v) == "buildings"
v = {"language": "en", "value": "mine"}
assert utils.pluralize_label(v) == "mines"
def test_format_wikibase_time_year():
v = {"time": "+1950-00-00T00:00:00Z", "precision": 9}
assert utils.format_wikibase_time(v) == "1950"
def test_format_wikibase_time_century():
v = {"time": "+0800-00-00T00:00:00Z", "precision": 7}
assert utils.format_wikibase_time(v) == "8th century"