def get_lexibase(path,
name,
columns=None,
preprocessing=None,
namespace=None,
lexibase=False):
wordlist = Wordlist.from_cldf(path,
columns=columns
or ("language_id", "concept_name", "value",
"form", "segments", "comment"),
namespace=namespace
or dict([("language_id", "doculect"),
("concept_name", "concept"),
("value", "value"),
("form", "form"),
("segments", "tokens"),
("comment", "note")]))
if preprocessing:
D = preprocessing(wordlist)
else:
D = {idx: wordlist[idx] for idx in wordlist}
D[0] = wordlist.columns
if not lexibase:
Wordlist(D).output("tsv", filename=name, ignore="all", prettify=False)
else:
lex = LexiBase(D, dbase=name + ".sqlite3")
lex.create(name)
def main():
debug = False
if 'debug' in argv or '--debug' in argv:
debug = True
if 'pinyin' in argv:
py = sinopy.pinyin(argv[argv.index('pinyin') + 1])
print(py)
if 'profile' in argv:
if '--cldf' in argv:
wl = Wordlist.from_cldf(argv[argv.index('profile') + 1],
col='language_id',
row='parameter_id')
wl.add_entries('doculect', 'language_name', lambda x: x)
else:
wl = Wordlist(argv[argv.index('profile') + 1])
column = 'ipa'
language = None
filename = 'orthography.tsv'
if '--column' in argv:
column = argv[argv.index('--column') + 1]
if '--language' in argv:
language = argv[argv.index('--language') + 1]
if '-l' in argv:
language = argv[argv.index('-l') + 1]
if '-o' in argv:
filename = argv[argv.index('-o') + 1]
if '--filename' in argv:
filename = argv[argv.index('--filename') + 1]
segments.write_structure_profile(wl,
column=column,
filename=filename,
debug=debug,
language=language)