def test_language(self):
# Assert language recognition.
self.assertEqual(text.language(u"the cat sat on the mat")[0], "en")
self.assertEqual(text.language(u"de kat zat op de mat")[0], "nl")
self.assertEqual(
text.language(u"le chat s'était assis sur le tapis")[0], "fr")
print("pattern.text.language()")
def test_language(self):
# Assert language recognition.
self.assertEqual(text.language("the cat sat on the mat")[0], "en")
self.assertEqual(text.language("de kat zat op de mat")[0], "nl")
self.assertEqual(
text.language("le chat s'était assis sur le tapis")[0], "fr")
print("pattern.text.language()")
def predict_language(q=""):
#print(q)
iso, confidence = language(q) # (takes some time to load the first time)
return {
"language": iso,
"confidence": round(confidence, 2)
}
def predict_language(q=""):
#print q
iso, confidence = language(q) # (takes some time to load the first time)
return {
"language": iso,
"confidence": round(confidence, 2)
}
print(parse("les chats noirs", chunks=False, language="fr", tagset=UNIVERSAL))
print(parse("i gatti neri", chunks=False, language="it", tagset=UNIVERSAL))
print(parse("de zwarte katten", chunks=False, language="nl", tagset=UNIVERSAL))
print("")
# This comes at the expense of (in this example) losing information about plural nouns (NNS => NN).
# But it may be more comfortable for you to build multilingual apps
# using the universal constants (e.g., PRON, PREP, CONJ),
# instead of learning the Penn Treebank tagset by heart,
# or wonder why the Italian "che" is tagged "PRP", "IN" or "CC"
# (in the universal tagset it is a PRON or a CONJ).
from pattern.text import parsetree
for sentence in parsetree("i gatti neri che sono la mia",
language="it",
tagset=UNIVERSAL):
for word in sentence.words:
if word.tag == PRON:
print(word)
# The language() function in pattern.text can be used to guess the language of a text.
# It returns a (language code, confidence)-tuple.
# It can guess en, es, de, fr, it, nl.
from pattern.text import language
print("")
print(language(u"the cat sat on the mat")) # ("en", 1.00)
print(language(u"de kat zat op de mat")) # ("nl", 0.80)
print(language(u"le chat s'était assis sur le tapis")) # ("fr", 0.86)
print(parse("the black cats" , chunks=False, language="en", tagset=UNIVERSAL))
print(parse("los gatos negros" , chunks=False, language="es", tagset=UNIVERSAL))
print(parse("les chats noirs" , chunks=False, language="fr", tagset=UNIVERSAL))
print(parse("i gatti neri" , chunks=False, language="it", tagset=UNIVERSAL))
print(parse("de zwarte katten" , chunks=False, language="nl", tagset=UNIVERSAL))
print()
# This comes at the expense of (in this example) losing information about plural nouns (NNS => NN).
# But it may be more comfortable for you to build multilingual apps
# using the universal constants (e.g., PRON, PREP, CONJ),
# instead of learning the Penn Treebank tagset by heart,
# or wonder why the Italian "che" is tagged "PRP", "IN" or "CC"
# (in the universal tagset it is a PRON or a CONJ).
from pattern.text import parsetree
for sentence in parsetree("i gatti neri che sono la mia", language="it", tagset=UNIVERSAL):
for word in sentence.words:
if word.tag == PRON:
print(word)
# The language() function in pattern.text can be used to guess the language of a text.
# It returns a (language code, confidence)-tuple.
# It can guess en, es, de, fr, it, nl.
from pattern.text import language
print()
print(language(u"the cat sat on the mat")) # ("en", 1.00)
print(language(u"de kat zat op de mat")) # ("nl", 0.80)
print(language(u"le chat s'était assis sur le tapis")) # ("fr", 0.86)
def predict_language_paid(q="", key=None):
return {"language": language(q)[0]}
def predict_language_paid(q="", key=None):
return {"language": language(q)[0]}
