def test_search(repo):
results = LexData.search_lexemes(repo, "first", LexData.language.en,
"Q1084")
assert len(results) == 1
assert results[0].get("id") == "L2"
result = LexData.get_or_create_lexeme(repo, "first", LexData.language.en,
"Q1084")
assert result["id"] == "L2"
# Open a Lexeme
L2 = LexData.Lexeme(repo, "L2")
# Access the claims
print(L2.claims.keys())
# and Forms
print(len(L2.forms))
F1 = L2.forms[0]
print(F1.claims.keys())
# and senses
print(len(L2.senses))
S1 = L2.senses[0]
print(S1.claims.keys())
# Find or create a Lexeme by lemma, language and grammatical form
L2 = LexData.get_or_create_lexeme(repo, "first", lang_en, "Q1084")
# You can easily create forms…
if len(L2.forms) == 0:
L2.create_form("firsts", ["Q146786"])
# …or senses, with or without additional claims
if len(L2.senses) == 0:
L2.create_sense(
{
"en":
"Element in an ordered list which comes before all others according to the ordering",
"de": "einer Ordnung folgend das Element vor allen anderen",
},
claims={"P5137": ["Q19269277"]},
)
repo = LexData.WikidataSession(config.user, config.botpassword)
# first execute creation of lexemes
if new_lexeme_count > 0:
for lexeme in data["new_lexemes"]:
lemma = lexeme["lemma"]
forms = lexeme["forms"]
claims = lexeme["claims"]
wikimedia_language_code = lexeme["language_code"]
language_item_id = lexeme["language_item_id"]
lexical_category = lexeme["lexical_category"]
console.info(f"Creating {lemma} with {len(forms)} forms and {len(claims)} claims")
# Find or create a Lexeme by lemma, language and lexical category
# Configure languages of LexData
lang = LexData.language.Language(wikimedia_language_code, language_item_id)
# Try finding it or create a new lexeme
new_lexeme = LexData.get_or_create_lexeme(repo, lemma, lang, lexical_category)
pprint(new_lexeme)
for form in forms:
# FIXME only supports 1 representation
form_representation: Tuple = form["form_representations"][0] # list of tuples
word: str = form_representation[1]
grammatical_features = form["grammatical_features"] # list of strings
pprint(grammatical_features)
result = new_lexeme.createForm(form_representation[1], grammatical_features)
pprint(result)
# lexeme_data = {
# 'type': 'lexeme',
# #'forms': forms,
# 'lemmas': {lang: {'language': lang, 'value': lemma}},
# 'language': language_item_id,