depicts/depicts/human.py

57 lines
1.6 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

from .model import HumanItem
from . import mediawiki, wikibase
import re
re_four_digits = re.compile(r'\b\d{4}\b')
re_iso_date = re.compile(r'\b\d{4}-\d{2}-\d{2}\b')
re_four_and_two = re.compile(r'\b(\d{2})(\d{2})[-](\d{2})\b')
re_catalog_number = re.compile(r'\b\d{4}[^\d]+\d+[^\d]+\d{4}\b')
def query(yob, yod):
if yod < yob:
return []
return HumanItem.query.filter_by(yob=yob, yod=yod).all()
def get_items_from_name(name):
found = []
m = re_four_and_two.search(name)
years = tuple(int(y) for y in re_four_digits.findall(name))
yob1, yod1 = None, None
if m:
century = m.group(1)
yob1 = int(century + m.group(2))
yod1 = int(century + m.group(3))
found += query(yob1, yod1)
if len(years) == 2 and years != (yob1, yod1):
found += query(*years)
return found
def from_name(name):
candidates = get_items_from_name(name)
lookup = {item.qid: item for item in candidates}
qids = list(lookup.keys())
found = []
for entity in mediawiki.get_entities_with_cache(qids, props='labels|descriptions'):
qid = entity['id']
item = lookup[qid]
i = {
'qid': entity['id'],
'year_of_birth': item.year_of_birth,
'year_of_death': item.year_of_death,
}
label = wikibase.get_entity_label(entity)
if label:
i['label'] = label
if 'en' in entity['descriptions']:
i['description'] = entity['descriptions']['en']['value']
found.append(i)
found.sort(key=lambda i: i.get('label', ''))
return found