def test_dump_trainable_entities(entity_extractor: Optional[Text],
expected_output: Text):
training_data_json = {
"rasa_nlu_data": {
"common_examples": [{
"text":
"test",
"intent":
"greet",
"entities": [{
"start": 0,
"end": 4,
"value": "random",
"entity": "word"
}],
}]
}
}
if entity_extractor is not None:
training_data_json["rasa_nlu_data"]["common_examples"][0]["entities"][
0]["extractor"] = entity_extractor
training_data_object = RasaReader().read_from_json(training_data_json)
md_dump = MarkdownWriter().dumps(training_data_object)
assert md_dump.splitlines()[1] == expected_output
def task(source, dest, cred_file, percent):
# load Rasa NLU training data
r = MarkdownReader()
with open(source, "r") as fin:
nlu = fin.read()
nlu_train = r.reads(nlu)
translate_client = translate.Client.from_service_account_json(cred_file)
def trans(text):
trans_text = translate_client.translate(text,
source_language="en",
target_language="zh-TW")
logger.info(u'origin: {}, translated: {}'.format(
example.text, trans_text['translatedText']))
return trans_text['translatedText']
nlu_train.training_examples = random_select_samples(
nlu_train.training_examples, percent)
for example in nlu_train.training_examples:
example.text = trans(example.text)
if example.get("entities"):
for entity in example.get("entities"):
entity["value"] = trans(entity['value'])
# Generate Rasa NLU translated training data
w = MarkdownWriter()
w.dump(dest, nlu_train)
def test_dump_entities(entity: Dict[Text, Any], expected_output: Text):
training_data_json = {
"rasa_nlu_data": {
"common_examples": [
{"text": "test", "intent": "greet", "entities": [entity]}
]
}
}
training_data_object = RasaReader().read_from_json(training_data_json)
md_dump = MarkdownWriter().dumps(training_data_object)
assert md_dump.splitlines()[1] == expected_output
def nlu_as_markdown(self) -> Text:
"""Generates the markdown representation of the NLU part of TrainingData."""
from rasa.nlu.training_data.formats import ( # pytype: disable=pyi-error
MarkdownWriter,
)
return MarkdownWriter().dumps(self)
def _as_md_message(parse_data: Dict[Text, Any]) -> Text:
"""Display the parse data of a message in markdown format."""
from rasa.nlu.training_data.formats import MarkdownWriter
if parse_data.get("text", "").startswith(INTENT_MESSAGE_PREFIX):
return parse_data.get("text")
if not parse_data.get("entities"):
parse_data["entities"] = []
# noinspection PyProtectedMember
return MarkdownWriter()._generate_message_md(parse_data)
def md_format_message(text, intent, entities):
from rasa.nlu.training_data.formats import MarkdownWriter, MarkdownReader
message_from_md = MarkdownReader()._parse_training_example(text)
deserialised_entities = deserialise_entities(entities)
return MarkdownWriter()._generate_message_md(
{
"text": message_from_md.text,
"intent": intent,
"entities": deserialised_entities,
}
)
def as_markdown(self) -> Text:
"""Generates the markdown representation of the TrainingData."""
from rasa.nlu.training_data.formats import MarkdownWriter
return MarkdownWriter().dumps(self)