def setUpClass(cls):
super(MorphemeContainerContextlessProbabilityGeneratorWithContainersTest, cls).setUpClass()
all_roots = []
lexicon_lines = u'''
duvar
tutku
saç
oğul [A:LastVowelDrop]
demek [A:RootChange, Passive_In, Passive_InIl]
bu [P:Det]
'''.strip().splitlines()
lexemes = LexiconLoader.load_from_lines(lexicon_lines)
for di in lexemes:
all_roots.extend(RootGenerator.generate(di))
root_map_generator = RootMapGenerator()
cls.root_map = root_map_generator.generate(all_roots)
suffix_graph = BasicSuffixGraph()
suffix_graph.initialize()
word_root_finder = WordRootFinder(cls.root_map)
cls.contextless_parser = ContextlessMorphologicalParser(suffix_graph, None,
[word_root_finder])
def setUpClass(cls):
super(
MorphemeContainerContextlessProbabilityGeneratorWithContainersTest,
cls).setUpClass()
all_roots = []
lexicon_lines = u'''
duvar
tutku
saç
oğul [A:LastVowelDrop]
demek [A:RootChange, Passive_In, Passive_InIl]
bu [P:Det]
'''.strip().splitlines()
lexemes = LexiconLoader.load_from_lines(lexicon_lines)
for di in lexemes:
all_roots.extend(RootGenerator.generate(di))
root_map_generator = RootMapGenerator()
cls.root_map = root_map_generator.generate(all_roots)
suffix_graph = BasicSuffixGraph()
suffix_graph.initialize()
word_root_finder = WordRootFinder(cls.root_map)
cls.contextless_parser = ContextlessMorphologicalParser(
suffix_graph, None, [word_root_finder])
def setUpClass(cls):
super(FormatterTest, cls).setUpClass()
all_roots = []
dictionary_content = ["kitap", "yapmak"]
lexemes = LexiconLoader.load_from_lines(dictionary_content)
for di in lexemes:
all_roots.extend(RootGenerator.generate(di))
cls.root_map = RootMapGenerator().generate(all_roots)
def setUpClass(cls):
super(FormatterTest, cls).setUpClass()
all_roots = []
dictionary_content = ["kitap", "yapmak"]
lexemes = LexiconLoader.load_from_lines(dictionary_content)
for di in lexemes:
all_roots.extend(RootGenerator.generate(di))
cls.root_map = RootMapGenerator().generate(all_roots)
def test_should_load_lexicon_from_str(self):
dictionary_content = u'''
a [P:Interj]
aba [P:Adj]
abadî
abat [P:Adj; A:NoVoicing]
Abdal
abdest [A:NoVoicing]
abes [P:Adj]
abes [P:Adv]
ablak [P:Adj; A:NoVoicing]
abuk [P:Adj, Dup;A:NoVoicing, NoSuffix]
acemborusu [A:CompoundP3sg; R:acemboru]
acembuselik
aciz [A:LastVowelDrop]
âciz [P:Adj]
açık [P:Adj]
ad
ad [P:Noun; A:Doubling, InverseHarmony]
addetmek [A:Voicing, Aorist_A]
addolmak [A:Causative_dIr]
ahlat [A:NoVoicing, Plural]
akşam [P:Noun, Time]
atamak [A:Causative_It]
sürtmek
yemek [P:Noun]
yemek [A:Causative_dIr]
ürkmek [A:Causative_It]
'''
dictionary_lines = dictionary_content.split('\n')
dictionary_lines = [l.strip() for l in dictionary_lines]
dictionary_lines = filter(lambda line: line, dictionary_lines)
lexemes = LexiconLoader.load_from_lines(dictionary_lines)
assert_that(lexemes, has_length(len(dictionary_lines)), str(len(lexemes)-len(dictionary_lines)))
assert_that(lexemes, has_item(Lexeme(u'a', u'a', SyntacticCategory.INTERJECTION, None, None)))
assert_that(lexemes, has_item(Lexeme(u'aba', u'aba', SyntacticCategory.ADJECTIVE, None, {LexemeAttribute.NoVoicing})))
assert_that(lexemes, has_item(Lexeme(u'abadî', u'abadî', SyntacticCategory.NOUN, None, {LexemeAttribute.NoVoicing})))
assert_that(lexemes, has_item(Lexeme(u'abat', u'abat', SyntacticCategory.ADJECTIVE, None, {LexemeAttribute.NoVoicing})))
assert_that(lexemes, has_item(Lexeme(u'Abdal', u'Abdal', SyntacticCategory.NOUN, SecondarySyntacticCategory.PROPER_NOUN, {LexemeAttribute.NoVoicing})))
assert_that(lexemes, has_item(Lexeme(u'abdest', u'abdest', SyntacticCategory.NOUN, None, {LexemeAttribute.NoVoicing})))
assert_that(lexemes, has_item(Lexeme(u'abes', u'abes', SyntacticCategory.ADJECTIVE, None, {LexemeAttribute.NoVoicing})))
assert_that(lexemes, has_item(Lexeme(u'abes', u'abes', SyntacticCategory.ADVERB, None, None)))
assert_that(lexemes, has_item(Lexeme(u'ablak', u'ablak', SyntacticCategory.ADJECTIVE, None, {LexemeAttribute.NoVoicing})))
assert_that(lexemes, has_item(Lexeme(u'abuk', u'abuk', SyntacticCategory.ADJECTIVE, SecondarySyntacticCategory.DUPLICATOR, {LexemeAttribute.NoSuffix, LexemeAttribute.NoVoicing})))
assert_that(lexemes, has_item(Lexeme(u'acemborusu', u'acemboru', SyntacticCategory.NOUN, None, {LexemeAttribute.CompoundP3sg, LexemeAttribute.NoVoicing})))
assert_that(lexemes, has_item(Lexeme(u'acembuselik', u'acembuselik', SyntacticCategory.NOUN, None, {LexemeAttribute.Voicing})))
assert_that(lexemes, has_item(Lexeme(u'aciz', u'aciz', SyntacticCategory.NOUN, None, {LexemeAttribute.LastVowelDrop, LexemeAttribute.NoVoicing})))
assert_that(lexemes, has_item(Lexeme(u'âciz', u'âciz', SyntacticCategory.ADJECTIVE, None, {LexemeAttribute.NoVoicing})))
assert_that(lexemes, has_item(Lexeme(u'açık', u'açık', SyntacticCategory.ADJECTIVE, None, {LexemeAttribute.Voicing})))
assert_that(lexemes, has_item(Lexeme(u'ad', u'ad', SyntacticCategory.NOUN, None, {LexemeAttribute.NoVoicing})))
assert_that(lexemes, has_item(Lexeme(u'ad', u'ad', SyntacticCategory.NOUN, None, {LexemeAttribute.Doubling, LexemeAttribute.InverseHarmony, LexemeAttribute.NoVoicing})))
assert_that(lexemes, has_item(Lexeme(u'addetmek', u'addet', SyntacticCategory.VERB, None, {LexemeAttribute.Aorist_A, LexemeAttribute.Causative_dIr, LexemeAttribute.Voicing})))
assert_that(lexemes, has_item(Lexeme(u'addolmak', u'addol', SyntacticCategory.VERB, None, {LexemeAttribute.Aorist_I, LexemeAttribute.Causative_dIr, LexemeAttribute.NoVoicing, LexemeAttribute.Passive_In})))
assert_that(lexemes, has_item(Lexeme(u'ahlat', u'ahlat', SyntacticCategory.NOUN, None, {LexemeAttribute.NoVoicing, LexemeAttribute.Plural})))
assert_that(lexemes, has_item(Lexeme(u'akşam', u'akşam', SyntacticCategory.NOUN, SecondarySyntacticCategory.TIME, {LexemeAttribute.NoVoicing})))
assert_that(lexemes, has_item(Lexeme(u'atamak', u'ata', SyntacticCategory.VERB, None, {LexemeAttribute.Aorist_I, LexemeAttribute.Causative_It, LexemeAttribute.NoVoicing, LexemeAttribute.Passive_In, LexemeAttribute.ProgressiveVowelDrop})))
assert_that(lexemes, has_item(Lexeme(u'sürtmek', u'sürt', SyntacticCategory.VERB, None, {LexemeAttribute.Aorist_A, LexemeAttribute.Causative_Ir, LexemeAttribute.NoVoicing})))
assert_that(lexemes, has_item(Lexeme(u'yemek', u'yemek', SyntacticCategory.NOUN, None, {LexemeAttribute.Voicing})))
assert_that(lexemes, has_item(Lexeme(u'yemek', u'ye', SyntacticCategory.VERB, None, {LexemeAttribute.Aorist_A, LexemeAttribute.Causative_dIr, LexemeAttribute.NoVoicing, LexemeAttribute.Passive_In, LexemeAttribute.ProgressiveVowelDrop})))
assert_that(lexemes, has_item(Lexeme(u'ürkmek', u'ürk', SyntacticCategory.VERB, None, {LexemeAttribute.Aorist_A, LexemeAttribute.Causative_It, LexemeAttribute.NoVoicing})))