def testProperName(self):
self.assertEquals(flatten(englishdict.reading(u"珍・奥斯汀")),
u"Zhen1 · Ao4 si1 ting1")
self.assertEquals(self.flatmeanings(englishdict, u"珍・奥斯汀"), [
u"Jane Austen (1775-1817), English novelist",
u"also written 简・奥斯汀 - Jian3 · Ao4 si1 ting1"
])
def testFrenchDictionary(self):
self.assertEquals(flatten(frenchdict.reading(u"評論")), "ping2 lun4")
self.assertEquals(flatten(frenchdict.reading(u"评论")), "ping2 lun4")
self.assertEquals(self.flatmeanings(frenchdict, u"评论"),
[u"commentaire (n.v.) (n)"])
def testGermanDictionary(self):
self.assertEquals(flatten(germandict.reading(u"请")), "qing3")
self.assertEquals(flatten(germandict.reading(u"請")), "qing3")
self.assertEquals(
self.flatmeanings(germandict, u"請"),
["Bitte ! (u.E.) (Int)", "bitten, einladen (u.E.) (V)"])
def testNumbersWherePinyinLengthDoesntMatchCharacters(self):
self.assertEquals(flatten(englishdict.tonedchars(u"1000000000")),
u"1000000000")
# Invalidated by removal of numbers from the dictionary:
# self.assertEquals(flatten(englishdict.reading(u"1000000000")), u"yi1 shi2 yi4")
self.assertEquals(self.flatmeanings(englishdict, u"1000000000"), None)
def testTonedTokensWithoutTone(self):
toned = englishdict.tonedchars(u"Ｕ盤")
self.assertEquals(flatten(toned), u"Ｕ盤")
self.assertEquals(toned[0][1].toneinfo, ToneInfo(written=2))
def testTonedCharactersPreservesWhitespace(self):
self.assertEquals(flatten(englishdict.tonedchars(u"\t一个")), u"\t一个")
def testTonedTokens(self):
toned = englishdict.tonedchars(u"一个")
self.assertEquals(flatten(toned), u"一个")
self.assertEquals(toned[0][0].toneinfo, ToneInfo(written=1))
self.assertEquals(toned[0][1].toneinfo, ToneInfo(written=4))
def testFallsBackOnCEDICTForMissingPinyinAndForeignLanguage(self):
self.assertEquals(flatten(frenchdict.reading(u"数量积")),
"shu4 liang4 ji1")
self.assertEquals(self.flatmeanings(frenchdict, u"数量积"), None)
def testMissingLanguage(self):
dict = dictionaries('foobar')
self.assertEquals(flatten(dict.reading(u"个")), "ge4")
self.assertEquals(self.flatmeanings(dict, u"个"), None)
def testNumbersWherePinyinLengthDoesntMatchCharacters(self):
self.assertEquals(flatten(englishdict.tonedchars(u"1000000000")), u"1000000000")
# Invalidated by removal of numbers from the dictionary:
# self.assertEquals(flatten(englishdict.reading(u"1000000000")), u"yi1 shi2 yi4")
self.assertEquals(self.flatmeanings(englishdict, u"1000000000"), None)
def testTonedTokenNumbers(self):
# Although it kind of makes sense to return the arabic numbers with tone colors, users don't expect it :-)
toned = englishdict.tonedchars(u"1994")
self.assertEquals(flatten(toned), u"1994")
self.assertFalse(any([hasattr(token, "tone") for token in toned]))
def testTonedTokensWithoutTone(self):
toned = englishdict.tonedchars(u"Ｕ盤")
self.assertEquals(flatten(toned), u"Ｕ盤")
self.assertEquals(toned[0][1].toneinfo, ToneInfo(written=2))
def testTonedCharactersPreservesWhitespace(self):
self.assertEquals(flatten(englishdict.tonedchars(u"\t一个")), u"\t一个")
def reading(self, what):
return flatten(englishdict.reading(what))
def flattenall(self, tokens):
if tokens:
return [flatten(token) for token in tokens]
else:
return None
def testGermanDictionary(self):
self.assertEquals(flatten(germandict.reading(u"请")), "qing3")
self.assertEquals(flatten(germandict.reading(u"請")), "qing3")
self.assertEquals(self.flatmeanings(germandict, u"請"), ["Bitte ! (u.E.) (Int)", "bitten, einladen (u.E.) (V)"])
def testTonedTokens(self):
toned = englishdict.tonedchars(u"一个")
self.assertEquals(flatten(toned), u"一个")
self.assertEquals(toned[0][0].toneinfo, ToneInfo(written=1))
self.assertEquals(toned[0][1].toneinfo, ToneInfo(written=4))
def testEnglishDictionary(self):
self.assertEquals(flatten(englishdict.reading(u"鼓聲")), "gu3 sheng1")
self.assertEquals(flatten(englishdict.reading(u"鼓声")), "gu3 sheng1")
self.assertEquals(self.flatmeanings(englishdict, u"鼓聲"), ["sound of a drum", "drumbeat"])
def testErhuaSpacedInReadingForKnownWords(self):
self.assertEquals(flatten(englishdict.reading(u"两头儿")), "liang3 tou2r")
def testFrenchDictionary(self):
self.assertEquals(flatten(frenchdict.reading(u"評論")), "ping2 lun4")
self.assertEquals(flatten(frenchdict.reading(u"评论")), "ping2 lun4")
self.assertEquals(self.flatmeanings(frenchdict, u"评论"), [u"commentaire (n.v.) (n)"])
def flattenall(self, tokens):
if tokens:
return [flatten(token) for token in tokens]
else:
return None
def testWordsWhosePrefixIsNotInDictionary(self):
self.assertEquals(flatten(germandict.reading(u"生日")), "sheng1 ri4")
self.assertEquals(self.flatmeanings(germandict, u"生日"), [u"Geburtstag (S)"])
def reading(self, what):
return flatten(englishdict.reading(what))
def testProperName(self):
self.assertEquals(flatten(englishdict.reading(u"珍・奥斯汀")), u"Zhen1 · Ao4 si1 ting1")
self.assertEquals(self.flatmeanings(englishdict, u"珍・奥斯汀"), [u"Jane Austen (1775-1817), English novelist", u"also written 简・奥斯汀 - Jian3 · Ao4 si1 ting1"])
def testTonedTokenNumbers(self):
# Although it kind of makes sense to return the arabic numbers with tone colors, users don't expect it :-)
toned = englishdict.tonedchars(u"1994")
self.assertEquals(flatten(toned), u"1994")
self.assertFalse(any([hasattr(token, "tone") for token in toned]))
def testShortPinyin(self):
self.assertEquals(flatten(englishdict.reading(u"股指")), "gu3 zhi3")
self.assertEquals(self.flatmeanings(englishdict, u"股指"), [u"stock market index", u"share price index", u"abbr. for 股票指数 - gu3 piao4 zhi3 shu4"])
def testMissingLanguage(self):
dict = dictionaries('foobar')
self.assertEquals(flatten(dict.reading(u"个")), "ge4")
self.assertEquals(self.flatmeanings(dict, u"个"), None)
def testPinyinFromUnihan(self):
self.assertEquals(flatten(englishdict.reading(u"諓")), "jian4")
self.assertEquals(self.flatmeanings(englishdict, u"諓"), None)
def testEnglishDictionary(self):
self.assertEquals(flatten(englishdict.reading(u"鼓聲")), "gu3 sheng1")
self.assertEquals(flatten(englishdict.reading(u"鼓声")), "gu3 sheng1")
self.assertEquals(self.flatmeanings(englishdict, u"鼓聲"),
["sound of a drum", "drumbeat"])
def testFallsBackOnCEDICTForMissingPinyinAndForeignLanguage(self):
self.assertEquals(flatten(frenchdict.reading(u"数量积")), "shu4 liang4 ji1")
self.assertEquals(self.flatmeanings(frenchdict, u"数量积"), None)
def testWordsWhosePrefixIsNotInDictionary(self):
self.assertEquals(flatten(germandict.reading(u"生日")), "sheng1 ri4")
self.assertEquals(self.flatmeanings(germandict, u"生日"),
[u"Geburtstag (S)"])
def testPinyinFromUnihan(self):
self.assertEquals(flatten(englishdict.reading(u"諓")), "jian4")
self.assertEquals(self.flatmeanings(englishdict, u"諓"), None)
def testShortPinyin(self):
self.assertEquals(flatten(englishdict.reading(u"股指")), "gu3 zhi3")
self.assertEquals(self.flatmeanings(englishdict, u"股指"), [
u"stock market index", u"share price index",
u"abbr. for 股票指数 - gu3 piao4 zhi3 shu4"
])
def testErhuaSpacedInReadingForKnownWords(self):
self.assertEquals(flatten(englishdict.reading(u"两头儿")), "liang3 tou2r")
