def how_many_infinitives(urn: str, is_csm: bool) -> int:
""" Gives back the number of infinitives in the text. """
aql: str = 'feats=/.*Inf.*/ ->dep[deprel=/(nsubj|nsubj:pass|csubj|csubj:pass)/] feats=/.*Acc.*/'
node_ids: List[str] = CorpusService.find_matches(urn,
aql,
is_csm=is_csm)
aql = 'feats=/.*Acc.*/ ->dep[deprel=/(xcomp|ccomp)/] feats=/.*Inf.*/'
node_ids += CorpusService.find_matches(urn, aql, is_csm=is_csm)
return round(len(node_ids) / 2)
def how_many_ablativi_absoluti(urn: str, is_csm: bool) -> int:
""" Gives back the number of ablativi absoluti in the text. """
aql: str = "tok ->dep[deprel=/(nsubj|nsubj:pass|csubj|csubj:pass)/] feats=/.*Abl.*/"
node_ids: List[str] = CorpusService.find_matches(urn,
aql,
is_csm=is_csm)
return round(len(node_ids) / 2)
def how_many_participles(urn: str, is_csm: bool) -> int:
"""Gives back how many participles are in the text"""
aql: str = "feats=/.*VerbForm=Part.*/"
node_ids: List[str] = CorpusService.find_matches(urn,
aql,
is_csm=is_csm)
return len(node_ids)
def post(exercise_data: dict) -> Union[Response, ConnexionResponse]:
ef: ExerciseForm = ExerciseForm.from_dict(exercise_data)
ef.urn = ef.urn if ef.urn else ""
exercise_type: ExerciseType = ExerciseType(ef.type)
search_values_list: List[str] = json.loads(ef.search_values)
aqls: List[str] = AnnotationService.map_search_values_to_aql(
search_values_list=search_values_list, exercise_type=exercise_type)
search_phenomena: List[Phenomenon] = [
Phenomenon().__getattribute__(x.split("=")[0].upper())
for x in search_values_list
]
# if there is custom text instead of a URN, immediately annotate it
conll_string_or_urn: str = ef.urn if CorpusService.is_urn(
ef.urn) else AnnotationService.get_udpipe(
CorpusService.get_raw_text(ef.urn, False))
try:
# construct graph from CONLL data
response: dict = get_graph_data(
title=ef.urn,
conll_string_or_urn=conll_string_or_urn,
aqls=aqls,
exercise_type=exercise_type,
search_phenomena=search_phenomena)
except ValueError:
return connexion.problem(500, Config.ERROR_TITLE_INTERNAL_SERVER_ERROR,
Config.ERROR_MESSAGE_INTERNAL_SERVER_ERROR)
solutions_dict_list: List[Dict] = response["solutions"]
solutions: List[Solution] = [
Solution.from_dict(x) for x in solutions_dict_list
]
ar: AnnisResponse = make_new_exercise(
conll=response["conll"],
correct_feedback=ef.correct_feedback,
exercise_type=ef.type,
general_feedback=ef.general_feedback,
graph_data_raw=response["graph_data_raw"],
incorrect_feedback=ef.incorrect_feedback,
instructions=ef.instructions,
language=ef.language,
partially_correct_feedback=ef.partially_correct_feedback,
search_values=ef.search_values,
solutions=solutions,
type_translation=ef.type_translation,
urn=ef.urn,
work_author=ef.work_author,
work_title=ef.work_title)
return NetworkService.make_json_response(ar.to_dict())
def how_many_sub_clauses(urn: str, is_csm: bool) -> int:
"""Gives back the number of subordinate clauses in the text. """
aql: str = 'tok ->dep[deprel=/(acl|advcl|ccomp|xcomp)/] upostag="VERB"'
node_ids: List[str] = CorpusService.find_matches(urn,
aql,
is_csm=is_csm)
# TODO: degree of sub clauses; ellipsis not counted
return round(len(node_ids) / 2)
def how_many_main_clauses(urn: str, is_csm: bool) -> int:
""" Gives back how many clauses are in the text. """
# TODO: ellipsis not counted
aql: str = "deps"
node_ids: List[str] = CorpusService.find_matches(urn,
aql,
is_csm=is_csm)
return len(node_ids)
def get(self):
""" Returns matches from ANNIS for a given CTS URN and AQL. """
# get request arguments
args: dict = flask.request.args
urn: str = args["urn"]
aql: str = args["aql"]
return NetworkService.make_json_response(
CorpusService.find_matches(urn, aql, is_csm=True))
def how_many_gerunds(urn: str, is_csm: bool) -> int:
""" Gives back the number of gerunds in the text. """
aql: str = "feats=/.*VerbForm=Ger.*/"
node_ids: List[str] = CorpusService.find_matches(urn,
aql,
is_csm=is_csm)
# TODO: gerundivo
return len(node_ids)
def get(urn: str) -> Union[Response, ConnexionResponse]:
"""Provides the raw text for a requested text passage."""
ar: AnnisResponse = CorpusService.get_corpus(cts_urn=urn, is_csm=False)
if not ar.graph_data.nodes:
return connexion.problem(404, Config.ERROR_TITLE_NOT_FOUND,
Config.ERROR_MESSAGE_CORPUS_NOT_FOUND)
ar.text_complexity = TextComplexityService.text_complexity(
TextComplexityMeasure.all.name, urn, False, ar.graph_data).to_dict()
return NetworkService.make_json_response(ar.to_dict())
def get(self):
""" Returns graph data for a given CTS URN. """
# get request arguments
args: Dict = flask.request.args
cts_urn: str = args["urn"]
ar: AnnisResponse = CorpusService.get_corpus(cts_urn=cts_urn,
is_csm=True)
if not ar.graph_data.nodes:
abort(404)
return NetworkService.make_json_response(ar.to_dict())
def get(frequency_upper_bound: int, query_urn: str, vocabulary: str) -> Response:
""" Retrieves sentence ID and matching degree for each sentence in the query text. """
vc: VocabularyCorpus = VocabularyCorpus[vocabulary]
vocabulary_set: Set[str] = FileService.get_vocabulary_set(vc, frequency_upper_bound)
# punctuation should count as a match because we don't want to count this as part of the vocabulary
for char in string.punctuation:
vocabulary_set.add(char)
ar: AnnisResponse = CorpusService.get_corpus(cts_urn=query_urn, is_csm=False)
sentences: List[Sentence] = check_vocabulary(ar.graph_data, vocabulary_set)
return NetworkService.make_json_response([x.to_dict() for x in sentences])
def post(self):
"""Given the relevant corpus data, gives back search results as graph data."""
args: dict = {}
try:
args = json.loads(flask.request.data.decode("utf-8"))
except JSONDecodeError:
abort(400)
title: str = args["title"]
annotations_or_urn: str = args["annotations"]
aqls: List[str] = args["aqls"]
exercise_type: ExerciseType = ExerciseType[args["exercise_type"]]
search_phenomena: List[Phenomenon] = [
Phenomenon().__getattribute__(x.upper())
for x in args["search_phenomena"]
]
conll: List[TokenList] = CorpusService.get_annotations_from_string(
annotations_or_urn)
ret_val: dict = CorpusService.process_corpus_data(
title, conll, aqls, exercise_type, search_phenomena)
# serialize the results to json
return NetworkService.make_json_response(ret_val)
def get(urn: str) -> Union[Response, ConnexionResponse]:
"""The GET method for the valid references REST API. It provides references for the desired text."""
try:
reff: List[str] = CustomCorpusService.get_custom_corpus_reff(
urn) if CustomCorpusService.is_custom_corpus_urn(
urn) else CorpusService.get_standard_corpus_reff(urn)
except ValueError:
return connexion.problem(400, Config.ERROR_TITLE_BAD_REQUEST,
Config.ERROR_MESSAGE_BAD_REQUEST)
if not reff:
return connexion.problem(404, Config.ERROR_TITLE_NOT_FOUND,
Config.ERROR_MESSAGE_CORPUS_NOT_FOUND)
return NetworkService.make_json_response(reff)
def get(urn: str):
""" Returns results for a frequency query from ANNIS for a given CTS URN and AQL. """
fa: List[FrequencyItem] = CorpusService.get_frequency_analysis(urn,
is_csm=True)
# map the abbreviated values found by ANNIS to our own model
skip_set: Set[Phenomenon] = {Phenomenon.LEMMA, Phenomenon.DEPENDENCY}
for fi in fa:
for i in range(len(fi.values)):
if fi.phenomena[i] in skip_set:
continue
value_map: Dict[str, List[str]] = AnnotationService.phenomenon_map[
fi.phenomena[i]]
fi.values[i] = next(
(x for x in value_map if fi.values[i] in value_map[x]), None)
return NetworkService.make_json_response([x.to_dict() for x in fa])
def post(vocabulary_data: dict):
""" Indicates for each token of a corpus whether it is covered by a reference vocabulary. """
vf: VocabularyForm = VocabularyForm.from_dict(vocabulary_data)
vc: VocabularyCorpus = VocabularyCorpus[vf.vocabulary]
vocabulary_set: Set[str] = FileService.get_vocabulary_set(vc, vf.frequency_upper_bound)
# punctuation should count as a match because we don't want to count this as part of the vocabulary
for char in string.punctuation:
vocabulary_set.add(char)
ar: AnnisResponse = CorpusService.get_corpus(cts_urn=vf.query_urn, is_csm=False)
for node in ar.graph_data.nodes:
if not is_match(target_lemma=node.udep_lemma, vocabulary_set=vocabulary_set):
node.is_oov = True
ar: AnnisResponse = AnnisResponse(
solutions=[], uri="", exercise_id="", graph_data=ar.graph_data)
ar.text_complexity = TextComplexityService.text_complexity(
TextComplexityMeasure.all.name, vf.query_urn, False, ar.graph_data).to_dict()
return NetworkService.make_json_response(ar.to_dict())
def get(eid: str) -> Union[Response, ConnexionResponse]:
exercise: TExercise = DatabaseService.query(Exercise,
filter_by=dict(eid=eid),
first=True)
if not exercise:
return connexion.problem(404, Config.ERROR_TITLE_NOT_FOUND,
Config.ERROR_MESSAGE_EXERCISE_NOT_FOUND)
ar: AnnisResponse = CorpusService.get_corpus(cts_urn=exercise.urn,
is_csm=False)
if not ar.graph_data.nodes:
return connexion.problem(404, Config.ERROR_TITLE_NOT_FOUND,
Config.ERROR_MESSAGE_CORPUS_NOT_FOUND)
exercise.last_access_time = datetime.utcnow().timestamp()
DatabaseService.commit()
exercise_type: ExerciseType = ExerciseType(exercise.exercise_type)
ar.solutions = json.loads(exercise.solutions)
ar.uri = NetworkService.get_exercise_uri(exercise)
ar.exercise_id = exercise.eid
ar.exercise_type = exercise_type.value
return NetworkService.make_json_response(ar.to_dict())
def update_exercises(is_csm: bool) -> None:
"""Deletes old exercises."""
if DatabaseService.has_table(Config.DATABASE_TABLE_EXERCISE):
exercises: List[Exercise] = DatabaseService.query(Exercise)
now: datetime = datetime.utcnow()
for exercise in exercises:
exercise_datetime: datetime = datetime.fromtimestamp(
exercise.last_access_time)
# delete exercises that have not been accessed for a while, are not compatible anymore, or contain
# corrupted / empty data
if (now - exercise_datetime).total_seconds() > Config.INTERVAL_EXERCISE_DELETE or \
not exercise.urn or not json.loads(exercise.solutions):
db.session.delete(exercise)
DatabaseService.commit()
# manually add text complexity measures for old exercises
elif not exercise.text_complexity:
ar: AnnisResponse = CorpusService.get_corpus(exercise.urn,
is_csm=is_csm)
tc: TextComplexity = TextComplexityService.text_complexity(
TextComplexityMeasure.all.name, exercise.urn, is_csm,
ar.graph_data)
exercise.text_complexity = tc.all
DatabaseService.commit()
def get(measure: str, urn: str):
"""Gives users measures of text complexity for a given text."""
ar: AnnisResponse = CorpusService.get_corpus(urn, is_csm=False)
tc: TextComplexity = TextComplexityService.text_complexity(
measure, urn, False, ar.graph_data)
return NetworkService.make_json_response(tc.to_dict())
