def ingest_lexica(session, num_lexica, num_wf_min, num_wf_max, vocabulary):
"""Run multiple (random built) lexicon ingestions."""
lexica = generate_lexica(num_lexica, num_wf_min, num_wf_max + 1,
vocabulary)
for i, wfs in enumerate(lexica):
name = f'Lexicon {i}'
LOGGER.info('Generating %s', name)
add_lexicon(session, lexicon_name=name, vocabulary=True, wfs=wfs)
def test_delete_lexicon(dbsession):
name = 'test lexicon'
wfs = pd.DataFrame()
wfs['wordform'] = ['wf1', 'wf2', 'wf3']
lex = add_lexicon(dbsession, lexicon_name=name, vocabulary=True, wfs=wfs)
print('lexicon id:', lex.lexicon_id)
delete_lexicon(dbsession, lex.lexicon_id)
# Wordforms should not be deleted
wrdfrms = dbsession.query(Wordform).all()
assert len(wrdfrms) == 3
r = dbsession.execute(select([Lexicon])).fetchall()
result = [row for row in r]
print(result)
assert len(result) == 0
# Lexicon should be deleted
lexica = dbsession.query(Lexicon).all()
assert len(lexica) == 0
# Wordforms are not associated with a lexicon
# (i.e., lexical_source_wordform is empty)
for wf in wrdfrms:
print('Wordform:', wf.wordform)
print('Wordform lexica:', wf.wf_lexica)
assert wf.wf_lexica == []
r = dbsession.execute(select([lexical_source_wordform])).fetchall()
result = [row for row in r]
print(len(result))
assert len(result) == 0
def test_add_lexicon(dbsession):
name = 'test lexicon'
wfs = pd.DataFrame()
wfs['wordform'] = ['wf1', 'wf2', 'wf3']
print(dbsession)
add_lexicon(dbsession, lexicon_name=name, vocabulary=True, wfs=wfs)
wrdfrms = dbsession.query(Wordform).order_by(Wordform.wordform_id).all()
assert len(wrdfrms) == 3
lexicons = dbsession.query(Lexicon).all()
assert len(lexicons) == 1
assert lexicons[0].lexicon_name == name
assert len(lexicons[0].lexicon_wordforms) == 3
wrdfrms = sorted([w.wordform for w in lexicons[0].lexicon_wordforms])
assert wrdfrms == list(wfs['wordform'])
def test_get_wf_mapping_lexicon(dbsession):
name = 'test lexicon'
wfs = pd.DataFrame()
wfs['wordform'] = ['wf1', 'wf2', 'wf3']
print(dbsession)
lex = add_lexicon(dbsession, lexicon_name=name, vocabulary=True, wfs=wfs)
wf_mapping = get_wf_mapping(dbsession, lexicon=lex)
for w in wfs['wordform']:
assert w in wf_mapping.keys()
def test_write_wf_links_data(dbsession, fs):
wfl_file = 'wflinks'
wfls_file = 'wflsources'
name = 'linked test lexicon'
wfs = pd.DataFrame()
wfs['wordform'] = ['wf1', 'wf2', 'wf3', 'wf1s', 'wf2s', 'wf3s']
lex = add_lexicon(dbsession, lexicon_name=name, vocabulary=True, wfs=wfs)
wfs = pd.DataFrame()
wfs['lemma'] = ['wf1', 'wf2', 'wf3']
wfs['variant'] = ['wf1s', 'wf2s', 'wf3s']
wfm = get_wf_mapping(dbsession, lexicon=lex)
links_file = open(wfl_file, 'w')
sources_file = open(wfls_file, 'w')
num_l, num_s = write_wf_links_data(
dbsession,
wf_mapping=wfm,
links_df=wfs,
wf_from_name='lemma',
wf_to_name='variant',
lexicon_id=lex.lexicon_id,
wf_from_correct=True,
wf_to_correct=True,
links_file=links_file,
sources_file=sources_file,
)
links_file.close()
sources_file.close()
links_file = open(wfl_file, 'r')
sources_file = open(wfls_file, 'r')
assert num_l == 3 * 2
assert num_s == 3 * 2
wflinks = []
for wf1, wf2 in zip(wfs['lemma'], wfs['variant']):
wflinks.append({"wordform_from": wfm[wf1], "wordform_to": wfm[wf2]})
wflinks.append({"wordform_from": wfm[wf2], "wordform_to": wfm[wf1]})
wflsources = []
for wfl in wflinks:
wflsources.append({
"wordform_from": wfl['wordform_from'],
"wordform_to": wfl['wordform_to'],
"lexicon_id": lex.lexicon_id,
"wordform_from_correct": True,
"wordform_to_correct": True
})
for wfls1, wfls2 in zip(read_json_lines(sources_file), wflsources):
assert wfls1 == wfls2
links_file.close()
sources_file.close()