def test_detect_non_ascii(self):
lang = self.translator.detect(unicode("关于中文维基百科"))
assert_equal(lang, 'zh-CN')
lang2 = self.translator.detect(unicode("известен още с псевдонимите"))
assert_equal(lang2, "bg")
lang3 = self.translator.detect(unicode("Избранная статья"))
assert_equal(lang3, "ru")
def test_detect(self, mock_get_json5):
mock_get_json5.return_value = unicode(
'[[["This is a sentence",'
'"This is a sentence","",""]],,"en",,,,,,[["en"]],4]')
lang = self.translator.detect(self.sentence)
assert_equal(lang, "en")
mock_get_json5.return_value = unicode(
'[[["Hello","Hola","",""]],[["interjection",'
'["Hello!","Hi!","Hey!","Hullo!","Hallo!",'
'"Hoy!","Hail!"],[["Hello!",["\xa1Hola!","'
'\xa1Caramba!","\xa1Oiga!","\xa1Diga!","'
'\xa1Bueno!","\xa1Vale!"],,0.39160562],'
'["Hi!",["\xa1Hola!"],,0.24506053],'
'["Hey!",["\xa1Hola!","\xa1Eh!"],,0.038173068]'
',["Hullo!",["\xa1Hola!","\xa1Caramba!",'
'"\xa1Oiga!","\xa1Diga!","\xa1Bueno!",'
'"\xa1Al\xf3!"]],["Hallo!",["\xa1Hola!",'
'"\xa1Caramba!","\xa1Oiga!","\xa1Bueno!"]],'
'["Hoy!",["\xa1Eh!","\xa1Hola!"]],["Hail!",'
'["\xa1Salve!","\xa1Hola!"]]],"\xa1Hola!",9]],'
'"es",,[["Hello",[1],true,false,783,0,1,0]],'
'[["Hola",1,[["Hello",783,true,false],'
'["Hi",214,true,false],["Hola",1,true,false],'
'["Hey",0,true,false],["Welcome",0,true,false]],'
'[[0,4]],"Hola"]],,,[],4]')
lang2 = self.translator.detect("Hola")
assert_equal(lang2, "es")
def test_detect_non_ascii(self):
lang = self.translator.detect(unicode("关于中文维基百科"))
assert_equal(lang, 'zh-CN')
lang2 = self.translator.detect(unicode("известен още с псевдонимите"))
assert_equal(lang2, "bg")
lang3 = self.translator.detect(unicode("Избранная статья"))
assert_equal(lang3, "ru")
def test_detect(self, mock_get_json5):
mock_get_json5.return_value = unicode('[[["This is a sentence",'
'"This is a sentence","",""]],,"en",,,,,,[["en"]],4]')
lang = self.translator.detect(self.sentence)
assert_equal(lang, "en")
mock_get_json5.return_value = unicode('[[["Hello","Hola","",""]],[["interjection",'
'["Hello!","Hi!","Hey!","Hullo!","Hallo!",'
'"Hoy!","Hail!"],[["Hello!",["\xa1Hola!","'
'\xa1Caramba!","\xa1Oiga!","\xa1Diga!","'
'\xa1Bueno!","\xa1Vale!"],,0.39160562],'
'["Hi!",["\xa1Hola!"],,0.24506053],'
'["Hey!",["\xa1Hola!","\xa1Eh!"],,0.038173068]'
',["Hullo!",["\xa1Hola!","\xa1Caramba!",'
'"\xa1Oiga!","\xa1Diga!","\xa1Bueno!",'
'"\xa1Al\xf3!"]],["Hallo!",["\xa1Hola!",'
'"\xa1Caramba!","\xa1Oiga!","\xa1Bueno!"]],'
'["Hoy!",["\xa1Eh!","\xa1Hola!"]],["Hail!",'
'["\xa1Salve!","\xa1Hola!"]]],"\xa1Hola!",9]],'
'"es",,[["Hello",[1],true,false,783,0,1,0]],'
'[["Hola",1,[["Hello",783,true,false],'
'["Hi",214,true,false],["Hola",1,true,false],'
'["Hey",0,true,false],["Welcome",0,true,false]],'
'[[0,4]],"Hola"]],,,[],4]')
lang2 = self.translator.detect("Hola")
assert_equal(lang2, "es")
def test_translate_non_ascii(self):
text = unicode("ذات سيادة كاملة")
translated = self.translator.translate(text, from_lang='ar', to_lang='en')
assert_equal(translated, "With full sovereignty")
text2 = unicode("美丽优于丑陋")
translated = self.translator.translate(text2, from_lang="zh-CN", to_lang='en')
assert_equal(translated, "Beautiful is better than ugly")
def test_translate_non_ascii(self):
text = unicode("ذات سيادة كاملة")
translated = self.translator.translate(text, from_lang='ar', to_lang='en')
assert_equal(translated, "With full sovereignty")
text2 = unicode("美丽优于丑陋")
translated = self.translator.translate(text2, from_lang="zh-CN", to_lang='en')
assert_equal(translated, "Beautiful is better than ugly")
def test_translate_non_ascii(self):
blob = tb.TextBlob(unicode("ذات سيادة كاملة"))
translated = blob.translate(from_lang="ar", to="en")
assert_equal(translated, "With full sovereignty")
chinese_blob = tb.TextBlob(unicode("美丽优于丑陋"))
translated = chinese_blob.translate(from_lang="zh-CN", to='en')
assert_equal(translated, "Beautiful is better than ugly")
def test_translate_non_ascii(self):
blob = tb.TextBlob(unicode("ذات سيادة كاملة"))
translated = blob.translate(from_lang="ar", to="en")
assert_equal(translated, "With full sovereignty")
chinese_blob = tb.TextBlob(unicode("美丽优于丑陋"))
translated = chinese_blob.translate(from_lang="zh-CN", to='en')
assert_equal(translated, "Beautiful is better than ugly")
def test_failed_translation_raises_not_translated(self, mock_get_json5):
mock_get_json5.return_value = unicode('{"sentences":[{"trans":'
'"n0tv\\u0026l1d","orig":'
'"n0tv\\u0026l1d","translit":"",'
'"src_translit":""}],'
'"src":"en","server_time":2}')
text = unicode(' n0tv&l1d ')
assert_raises(NotTranslated,
self.translator.translate, text, to_lang="es")
assert_true(mock_get_json5.called_once)
def pos_tags(self):
"""Returns an list of tuples of the form (word, POS tag).
Example:
::
[('At', 'IN'), ('eight', 'CD'), ("o'clock", 'JJ'), ('on', 'IN'),
('Thursday', 'NNP'), ('morning', 'NN')]
:rtype: list of tuples
"""
return [(Word(word, pos_tag=t), unicode(t))
for word, t in self.pos_tagger.tag(self.raw)
if not PUNCTUATION_REGEX.match(unicode(t))]
def test_detect_parses_json5(self, mock_get_json5):
mock_get_json5.return_value = unicode('{"sentences":[{"trans":'
'"This is a sentence.","orig":'
'"This is a sentence.","translit":"",'
'"src_translit":""}],"src":"en",'
'"server_time":1}')
lang = self.translator.detect(self.sentence)
assert_equal(lang, "en")
mock_get_json5.return_value = unicode('{"sentences":[{"trans":'
'"Hello","orig":"Hola",'
'"translit":"","src_translit":""}],'
'"src":"es","server_time":2}')
lang2 = self.translator.detect("Hola")
assert_equal(lang2, "es")
def test_detect_parses_json5(self, mock_get_json5):
mock_get_json5.return_value = unicode('{"sentences":[{"trans":'
'"This is a sentence.","orig":'
'"This is a sentence.","translit":"",'
'"src_translit":""}],"src":"en",'
'"server_time":1}')
lang = self.translator.detect(self.sentence)
assert_equal(lang, "en")
mock_get_json5.return_value = unicode('{"sentences":[{"trans":'
'"Hello","orig":"Hola",'
'"translit":"","src_translit":""}],'
'"src":"es","server_time":2}')
lang2 = self.translator.detect("Hola")
assert_equal(lang2, "es")
def pos_tags(self):
'''Returns an list of tuples of the form (word, POS tag).
Example:
::
[('At', 'IN'), ('eight', 'CD'), ("o'clock", 'JJ'), ('on', 'IN'),
('Thursday', 'NNP'), ('morning', 'NN')]
:rtype: list of tuples
'''
return [(Word(word, pos_tag=t), unicode(t))
for word, t in self.pos_tagger.tag(self.raw)
if not PUNCTUATION_REGEX.match(unicode(t))]
def test_translate_detects_language_by_default(self, mock_detect,
mock_get_json5, mock_get_language, mock_get_translation):
mock_get_language.return_value = 'ar'
mock_get_translation.return_value = 'Fully sovereign'
text = unicode("ذات سيادة كاملة")
blob = tb.TextBlob(text)
assert_true(mock_detect.called_once_with(text))
def test_translate_detects_language_by_default(self, mock_detect,
mock_get_json5, mock_get_language, mock_get_translation):
mock_get_language.return_value = 'ar'
mock_get_translation.return_value = 'Fully sovereign'
text = unicode("ذات سيادة كاملة")
blob = tb.TextBlob(text)
assert_true(mock_detect.called_once_with(text))
def pos_tags(self):
"""Returns an list of tuples of the form (word, POS tag).
Example:
::
[('At', 'IN'), ('eight', 'CD'), ("o'clock", 'JJ'), ('on', 'IN'),
('Thursday', 'NNP'), ('morning', 'NN')]
:rtype: list of tuples
"""
if isinstance(self, TextBlob):
return [val for sublist in [s.pos_tags for s in self.sentences] for val in sublist]
else:
return [(Word(unicode(word), pos_tag=t), unicode(t))
for word, t in self.pos_tagger.tag(self)
if not PUNCTUATION_REGEX.match(unicode(t))]
def test_translate(self, mock_get_json5):
mock_get_json5.return_value = unicode('{"sentences":[{"trans":'
'"Esta es una frase.","orig":'
'"This is a sentence.","translit":"",'
'"src_translit":""}],"src":"en",'
'"server_time":2}')
t = self.translator.translate(self.sentence, to_lang="es")
assert_equal(t, "Esta es una frase.")
assert_true(mock_get_json5.called_once)
def test_translate(self, mock_get_json5):
mock_get_json5.return_value = unicode('{"sentences":[{"trans":'
'"Esta es una frase.","orig":'
'"This is a sentence.","translit":"",'
'"src_translit":""}],"src":"en",'
'"server_time":2}')
t = self.translator.translate(self.sentence, to_lang="es")
assert_equal(t, "Esta es una frase.")
assert_true(mock_get_json5.called_once)
def pos_tags(self):
"""Returns an list of tuples of the form (word, POS tag).
Example:
::
[('At', 'IN'), ('eight', 'CD'), ("o'clock", 'JJ'), ('on', 'IN'),
('Thursday', 'NNP'), ('morning', 'NN')]
:rtype: list of tuples
"""
if isinstance(self, TextBlob):
return [
val for sublist in [s.pos_tags for s in self.sentences]
for val in sublist
]
else:
return [(Word(word, pos_tag=t), unicode(t))
for word, t in self.pos_tagger.tag(self)
if not PUNCTUATION_REGEX.match(unicode(t))]
def __repr__(self):
'''Returns a string representation for debugging.'''
class_name = self.__class__.__name__
# String representation of words
strings = [unicode(w) for w in self._collection]
if len(self) > 60:
return '{cls}({beginning}...{end})'.format(cls=class_name,
beginning=strings[:3],
end=strings[-3:])
else:
return '{cls}({lst})'.format(cls=class_name, lst=strings)
def __repr__(self):
'''Returns a string representation for debugging.'''
class_name = self.__class__.__name__
# String representation of words
strings = [unicode(w) for w in self._collection]
if len(self) > 60:
return '{cls}({beginning}...{end})'.format(cls=class_name,
beginning=strings[:3],
end=strings[-3:])
else:
return '{cls}({lst})'.format(cls=class_name, lst=strings)
def test_translate(self, mock_get_json5):
mock_get_json5.return_value = unicode('[[["Esta es una frase","This is a '
'sentence","",""]],,"en",,[["Esta es una",[1],true,false,374,0,3,0]'
',["frase",[2],true,false,470,3,4,0]],[["This is a",1,[["Esta es'
' una",374,true,false],["Se trata de una",6,true,false],'
'["Este es un",0,true,false],["Se trata de un",0,true,false],'
'["Esto es un",0,true,false]],[[0,9]],"This is a sentence"],'
'["sentence",2,[["frase",470,true,false],["sentencia",6,true,false],'
'["oraci\xf3n",0,true,false],["pena",0,true,false],["condena"'
',0,true,false]],[[10,18]],""]],,,[["en"]],29]')
t = self.translator.translate(self.sentence, to_lang="es")
assert_equal(t, "Esta es una frase")
assert_true(mock_get_json5.called_once)
def test_translate(self, mock_get_json5):
mock_get_json5.return_value = unicode(
'[[["Esta es una frase","This is a '
'sentence","",""]],,"en",,[["Esta es una",[1],true,false,374,0,3,0]'
',["frase",[2],true,false,470,3,4,0]],[["This is a",1,[["Esta es'
' una",374,true,false],["Se trata de una",6,true,false],'
'["Este es un",0,true,false],["Se trata de un",0,true,false],'
'["Esto es un",0,true,false]],[[0,9]],"This is a sentence"],'
'["sentence",2,[["frase",470,true,false],["sentencia",6,true,false],'
'["oraci\xf3n",0,true,false],["pena",0,true,false],["condena"'
',0,true,false]],[[10,18]],""]],,,[["en"]],29]')
t = self.translator.translate(self.sentence, to_lang="es")
assert_equal(t, "Esta es una frase")
assert_true(mock_get_json5.called_once)
def test_translate_detects_language_by_default(self, mock_translate):
text = unicode("ذات سيادة كاملة")
mock_translate.return_value = "With full sovereignty"
blob = tb.TextBlob(text)
blob.translate()
assert_true(mock_translate.called_once_with(text, from_lang='auto'))
def test_translate_detects_language_by_default(self):
blob = tb.TextBlob(unicode("ذات سيادة كاملة"))
assert_equal(blob.translate(), "With full sovereignty")
def test_detect_non_ascii(self):
blob = tb.TextBlob(unicode("ذات سيادة كاملة"))
assert_equal(blob.detect_language(), "ar")
def parse(s, *args, **kwargs):
""" Returns a tagged Unicode string.
"""
return parser.parse(unicode(s), *args, **kwargs)
def parsetree(s, *args, **kwargs):
""" Returns a parsed Text from the given string.
"""
return Text(parse(unicode(s), *args, **kwargs))
def test_detect_non_ascii(self):
blob = tb.TextBlob(unicode("ذات سيادة كاملة"))
assert_equal(blob.detect_language(), "ar")
def positive(s, threshold=0.1, **kwargs):
""" Returns True if the given sentence has a positive sentiment (polarity >= threshold).
"""
return polarity(unicode(s), **kwargs) >= threshold
def parse(s, *args, **kwargs):
""" Returns a tagged Unicode string.
"""
return parser.parse(unicode(s), *args, **kwargs)
def positive(s, threshold=0.1, **kwargs):
""" Returns True if the given sentence has a positive sentiment (polarity >= threshold).
"""
return polarity(unicode(s), **kwargs) >= threshold
def subjectivity(s, **kwargs):
""" Returns the sentence subjectivity (objective/subjective) between 0.0 and 1.0.
"""
return sentiment(unicode(s), **kwargs)[1]
def subjectivity(s, **kwargs):
""" Returns the sentence subjectivity (objective/subjective) between 0.0 and 1.0.
"""
return sentiment(unicode(s), **kwargs)[1]
def polarity(s, **kwargs):
""" Returns the sentence polarity (positive/negative) between -1.0 and 1.0.
"""
return sentiment(unicode(s), **kwargs)[0]
def test_translate_detects_language_by_default(self):
blob = tb.TextBlob(unicode("ذات سيادة كاملة"))
assert_equal(blob.translate(), "With full sovereignty")
def parsetree(s, *args, **kwargs):
""" Returns a parsed Text from the given string.
"""
return Text(parse(unicode(s), *args, **kwargs))
def polarity(s, **kwargs):
""" Returns the sentence polarity (positive/negative) between -1.0 and 1.0.
"""
return sentiment(unicode(s), **kwargs)[0]