def _extract_entities(self, message: Message) -> List[Dict[Text, Any]]:
"""Extract entities of the given type from the given user message."""
entities = []
flags = 0 # default flag
if not self.case_sensitive:
flags = re.IGNORECASE
for pattern in self.patterns:
matches = re.finditer(pattern["pattern"],
message.get(TEXT),
flags=flags)
matches = list(matches)
for match in matches:
start_index = match.start()
end_index = match.end()
entities.append({
ENTITY_ATTRIBUTE_TYPE:
pattern["name"],
ENTITY_ATTRIBUTE_START:
start_index,
ENTITY_ATTRIBUTE_END:
end_index,
ENTITY_ATTRIBUTE_VALUE:
message.get(TEXT)[start_index:end_index],
})
return entities
def test_entity_synonyms_substitute_two_entity():
example = Message(
text="Looking for a chines restaurant in New York tomorrow",
data={
"entities": [{
"entity": "type",
"value": "chinese",
"start": 14,
"end": 20
}, {
"entity": "city",
"value": "New York",
"start": 35,
"end": 43
}]
})
ent_synonyms = {"chines": "chinese", "new york": "NYC"}
EntitySynonymBegin(synonyms=ent_synonyms).process(example)
assert example.text == "Looking for a chinese restaurant in NYC tomorrow"
e_type = list(
filter(lambda e: e["entity"] == 'type', example.get("entities")))[0]
e_city = list(
filter(lambda e: e["entity"] == 'city', example.get("entities")))[0]
assert e_type["start"] == 14
assert e_type["end"] == 21
assert e_city["start"] == 36
assert e_city["end"] == 39
def test_entity_sweeper():
entities = [{
"entity": "cuisine",
"value": "chinese",
"start": 0,
"end": 6
}, {
"entity": "time",
"value": "whatever",
"start": 0,
"end": 6
}]
sweeper = Sweeper(component_config={'entity_names': ['time']})
message = Message("xxx", {'entities': entities})
sweeper.process(message)
assert len(message.get('entities')) == 1
assert message.get('entities')[0]["entity"] == "cuisine"
def test_entity_synonyms_substitute_three_entity():
example = Message(
text=
"Looking for a chines restaurant in New York tomorrow for three people",
data={
"entities": [
{
"entity": "type",
"value": "chines",
"start": 14,
"end": 20
},
{
"entity": "city",
"value": "New York",
"start": 35,
"end": 43
},
{
"entity": "count",
"value": "three",
"start": 57,
"end": 62
},
]
},
)
ent_synonyms = {"chines": "chinese", "new york": "NYC", "three": "3"}
EntitySynonymBegin(synonyms=ent_synonyms).process(example)
assert (example.text ==
"Looking for a chinese restaurant in NYC tomorrow for 3 people")
e_type = list(
filter(lambda e: e["entity"] == "type", example.get("entities")))[0]
e_city = list(
filter(lambda e: e["entity"] == "city", example.get("entities")))[0]
e_count = list(
filter(lambda e: e["entity"] == "count", example.get("entities")))[0]
assert e_type["start"] == 14
assert e_type["end"] == 21
assert e_city["start"] == 36
assert e_city["end"] == 39
assert e_count["start"] == 53
assert e_count["end"] == 54
def process(self, message: Message, **kwargs: Any) -> None:
if not self.patterns:
return
extracted_entities = self._extract_entities(message)
extracted_entities = self.add_extractor_name(extracted_entities)
message.set(ENTITIES,
message.get(ENTITIES, []) + extracted_entities,
add_to_output=True)
def test_entity_synonyms_substitute_one_entity():
example = Message(text="Looking for a chines restaurant",
data={
"entities": [{
"entity": "type",
"value": "chinese",
"start": 14,
"end": 20
}]
})
ent_synonyms = {"chines": "chinese"}
EntitySynonymBegin(synonyms=ent_synonyms).process(example)
assert example.text == "Looking for a chinese restaurant"
e_type = list(
filter(lambda e: e["entity"] == 'type', example.get("entities")))[0]
assert e_type["start"] == 14
assert e_type["end"] == 21
def test_classification(self, trained_classifier, message, intent):
text = Message(message)
trained_classifier.process(text)
assert text.get("intent").get("name", "NOT_CLASSIFIED") == intent
