def cmd_makecldf(self, args):
dsdir = self.dir / 'raw' / 'Verkerk-DravLex-622ac6e'
dataset = Wordlist.from_metadata(dsdir / 'Wordlist-metadata.json')
# load concepts
concepts = args.writer.add_concepts(
id_factory=lambda c: c.id.split('-')[-1]+ '_' + slug(c.english),
lookup_factory="Name"
)
# load sources from original CLDF, and then the fieldwork source
args.writer.add_sources(*self.raw_dir.read_bib(dsdir / 'sources.bib'))
args.writer.add_sources()
# load languages
args.writer.add_languages()
# load cognates
cogs = {
r['Form_ID']: r for r in self.raw_dir.read_csv(dsdir / 'cognates.csv', dicts=True)
}
# load data
for row in self.raw_dir.read_csv(dsdir / 'forms.csv', dicts=True):
src = row['Source'].split(";") if row['Source'] else ['KolipakamFW']
cog = cogs.get(row['ID'])
for lex in args.writer.add_forms_from_value(
Local_ID=row['ID'],
Language_ID=row['Language_ID'],
Parameter_ID=concepts[row['Parameter_ID']],
Value=row['Form'],
Source=src,
Comment=row['status'],
Loan=True if row['status'] else False
):
args.writer.add_cognate(
lexeme=lex,
ID=cog['ID'],
Source=cog['Source'],
Cognateset_ID=cog['Cognateset_ID'],
Comment=", ".join([cog['Comment'], cog['source_comment']])
)
from xml.etree.ElementTree import fromstring
from xmljson import badgerfish as bf
import sys
import os
import csv
from cariban import util
from pycldf import Wordlist
import re
import pyperclip
lexicon = {}
cariban_data = Wordlist.from_metadata("../cariban_data.json")
for row in cariban_data["FormTable"]:
alt_glossings = row["Glossing"].split("; ")
if len(alt_glossings) == 0 or alt_glossings[0] == "":
meanings = row["Parameter_ID"]
else:
meanings = alt_glossings
lexicon[row["ID"]] = {
"forms": row["Form"],
"meanings": meanings,
"language": row["Language_ID"],
}
# print(lexicon)
def search_lexicon(form, meaning, language):
if len(lexicon) == 0:
return ("X")
if not meaning.isupper():
new_meaning = meaning.replace(".", " ")
else:
from clldutils.path import Path
from clldutils.misc import slug
from pycldf import Wordlist
from clld_phylogeny_plugin.models import Phylogeny, TreeLabel, LanguageTreeLabel
from clld_cognacy_plugin.models import Cognate, Cognateset
from csvw.dsv import reader
import cobl2
from cobl2 import models
import clld_cognacy_plugin.models
data_file_path = Path(cobl2.__file__).parent / '../..' / 'iecor'
ds = Wordlist.from_metadata(data_file_path / 'cldf' / 'cldf-metadata.json')
photos = {
p.stem: p.as_posix() for p in
(Path(cobl2.__file__).parent / '../..' / 'CoBL-public' / 'cobl' / 'static' / 'contributors').iterdir()
if p.suffix == '.jpg'}
for k, v in {
'Kümmel': 'Kuemmel',
'de Vaan': 'deVaan',
'Dewey-Findell': 'Dewey',
}.items():
photos[k] = photos[v]
def main(args):
data = Data()
def original_cldf(self):
for p in self.raw_dir.iterdir():
if p.name.endswith(MD_SUFFIX):
return Wordlist.from_metadata(p)
def main(args): # pragma: no cover
wl = Wordlist.from_metadata(args.data_file('cldf', 'cldf-metadata.json'))
data = Data()
data.add(
common.Contributor, 'barthwolfgang',
id='barthwolfgang',
name="Wolfgang Barth",
url="http://www.dynamicsoflanguage.edu.au/")
#
# FIXME: get dataset attributes from CLDF metadata!
#
dataset = common.Dataset(
id='parabank',
name='Parabank Pronouns',
description='Database of pronouns',
domain='parabank.clld.org',
publisher_name="CoEDL Centre of Excellence for the Dynamics of Language",
publisher_place="Canberra, Australia",
publisher_url="http://www.dynamicsoflanguage.edu.au/",
license='http://creativecommons.org/licenses/by/4.0/',
contact='*****@*****.**',
jsondata={
'license_icon': 'cc-by.png',
'license_name': 'Creative Commons Attribution 4.0'})
DBSession.add(dataset)
for i, editor in enumerate(['barthwolfgang']):
common.Editor(dataset=dataset, contributor=data['Contributor'][editor], ord=i + 1)
contrib = common.Contribution(id='contrib', name='the contribution')
for l in wl['LanguageTable']:
lang = data.add(
models.ParabankLanguage,
l['ID'],
id=l['ID'],
name=l['Name'],
description=l['Notes'],
source=l['Source_Citation'],
classification=l['Classification'],
)
add_language_codes(data, lang, None, glottocode=l['Glottocode'])
for p in wl['ParameterTable']:
data.add(
common.Parameter,
p['ID'],
id=p['ID'],
name='{0} ({1})'.format(p['Name'], p['ID']),
#description=p['Description'],
)
for f in wl['FormTable']:
vsid = '{0}-{1}'.format(f['Parameter_ID'], f['Language_ID'])
vs = data['ValueSet'].get(vsid)
if not vs:
vs = data.add(
common.ValueSet,
vsid,
id=vsid,
language=data['ParabankLanguage'][f['Language_ID']],
parameter=data['Parameter'][f['Parameter_ID']],
contribution=contrib)
DBSession.add(models.Word(
id=f['ID'],
name=f['Form'],
comment=f.get('Comment'),
original=f['Original_parameter'],
valueset=vs))
load_families(
data,
[(l.glottocode, l) for l in data['ParabankLanguage'].values()],
glottolog_repos=args.data_file('glottolog'),
isolates_icon='tcccccc')
