Created
December 18, 2014 10:10
-
-
Save xrotwang/6d19429bfc7931ed29db to your computer and use it in GitHub Desktop.
Get list of phonologies from glottolog
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import json | |
from sqlalchemy import not_ | |
from sqlalchemy.orm import joinedload | |
from clld.scripts.util import parsed_args | |
from clld.db.meta import DBSession | |
from glottolog3.models import Ref, Doctype, Languoid, Provider | |
def main(args): | |
with open(args.data_file('phoible-isocodes.json')) as fp: | |
covered = json.load(fp).keys() | |
q = DBSession.query(Ref).join(Ref.languages).join(Ref.doctypes).join(Ref.providers)\ | |
.filter(Doctype.pk.in_([3, 8, 11]))\ | |
.filter(Provider.pk == 21)\ | |
.filter(not_(Languoid.hid.in_(covered)))\ | |
.options(joinedload(Ref.languages)) | |
print q.count() | |
with open(args.data_file('phoible-phonologies.bib'), 'w') as fp: | |
for ref in q: | |
rec = ref.bibtex() | |
rec['glottolog_url'] = 'http://glottolog.org/resource/reference/id/%s' % ref.id | |
rec['languages'] = ', '.join('%s [%s][%s]' % (l.name, l.id, l.hid) for l in ref.languages if l.hid not in covered) | |
fp.write('\n%s' % unicode(rec).encode('utf8')) | |
if __name__ == '__main__': | |
main(parsed_args()) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment