def setUp(self):
self.parseset_creator = ParseSetCreator()
all_roots = []
lexemes = LexiconLoader.load_from_file(os.path.join(os.path.dirname(__file__), '../../resources/master_dictionary.txt'))
for di in lexemes:
all_roots.extend(RootGenerator.generate(di))
root_map = (RootMapGenerator()).generate(all_roots)
suffix_graph = CopulaSuffixGraph(NumeralSuffixGraph(ProperNounSuffixGraph(BasicSuffixGraph())))
suffix_graph.initialize()
predefined_paths = PredefinedPaths(root_map, suffix_graph)
predefined_paths.create_predefined_paths()
word_root_finder = WordRootFinder(root_map)
digit_numeral_root_finder = DigitNumeralRootFinder()
text_numeral_root_finder = TextNumeralRootFinder(root_map)
proper_noun_from_apostrophe_root_finder = ProperNounFromApostropheRootFinder()
proper_noun_without_apostrophe_root_finder = ProperNounWithoutApostropheRootFinder()
self.parser = UpperCaseSupportingContextlessMorphologicalParser(suffix_graph, predefined_paths,
[word_root_finder, digit_numeral_root_finder, text_numeral_root_finder, proper_noun_from_apostrophe_root_finder, proper_noun_without_apostrophe_root_finder])
def setUpClass(cls):
super(_LikelihoodCalculatorTest, cls).setUpClass()
all_roots = []
lexemes = LexiconLoader.load_from_file(os.path.join(os.path.dirname(__file__), '../../../../../resources/master_dictionary.txt'))
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 = CopulaSuffixGraph(NumeralSuffixGraph(ProperNounSuffixGraph(BasicSuffixGraph())))
suffix_graph.initialize()
predefined_paths = PredefinedPaths(cls.root_map, suffix_graph)
predefined_paths.create_predefined_paths()
word_root_finder = WordRootFinder(cls.root_map)
digit_numeral_root_finder = DigitNumeralRootFinder()
text_numeral_root_finder = TextNumeralRootFinder(cls.root_map)
proper_noun_from_apostrophe_root_finder = ProperNounFromApostropheRootFinder()
proper_noun_without_apostrophe_root_finder = ProperNounWithoutApostropheRootFinder()
cls.contextless_parser = ContextlessMorphologicalParser(suffix_graph, predefined_paths,
[word_root_finder, digit_numeral_root_finder, text_numeral_root_finder,
proper_noun_from_apostrophe_root_finder, proper_noun_without_apostrophe_root_finder])
cls.mongodb_connection = pymongo.Connection(host='127.0.0.1')
cls.collection_map = {
1: cls.mongodb_connection['trnltk']['wordUnigrams999'],
2: cls.mongodb_connection['trnltk']['wordBigrams999'],
3: cls.mongodb_connection['trnltk']['wordTrigrams999']
}
cls.generator = None
def setUpClass(cls):
super(TransitionGeneratorTest, cls).setUpClass()
all_roots = []
lexemes = LexiconLoader.load_from_file(os.path.join(os.path.dirname(__file__), '../../resources/master_dictionary.txt'))
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 = CopulaSuffixGraph(NumeralSuffixGraph(ProperNounSuffixGraph(BasicSuffixGraph())))
suffix_graph.initialize()
predefined_paths = PredefinedPaths(cls.root_map, suffix_graph)
predefined_paths.create_predefined_paths()
word_root_finder = WordRootFinder(cls.root_map)
digit_numeral_root_finder = DigitNumeralRootFinder()
text_numeral_root_finder = TextNumeralRootFinder(cls.root_map)
proper_noun_from_apostrophe_root_finder = ProperNounFromApostropheRootFinder()
proper_noun_without_apostrophe_root_finder = ProperNounWithoutApostropheRootFinder()
cls.parser = ContextlessMorphologicalParser(suffix_graph, predefined_paths,
[word_root_finder, digit_numeral_root_finder, text_numeral_root_finder,
proper_noun_from_apostrophe_root_finder, proper_noun_without_apostrophe_root_finder])
cls.transition_generator = TransitionGenerator(cls.parser)
def setUp(self):
super(PredefinedPathsTest, self).setUp()
logging.basicConfig(level=logging.INFO)
parser_logger.setLevel(logging.INFO)
suffix_applier_logger.setLevel(logging.INFO)
self.predefined_paths = PredefinedPaths(self.root_map,
self.suffix_graph)
def setUpClass(cls):
super(InterpolatingLikelihoodCalculatorCalculationContextTest,
cls).setUpClass()
all_roots = []
lexemes = LexiconLoader.load_from_file(
os.path.join(os.path.dirname(__file__),
'../../../../../resources/master_dictionary.txt'))
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 = CopulaSuffixGraph(
NumeralSuffixGraph(ProperNounSuffixGraph(BasicSuffixGraph())))
suffix_graph.initialize()
predefined_paths = PredefinedPaths(cls.root_map, suffix_graph)
predefined_paths.create_predefined_paths()
word_root_finder = WordRootFinder(cls.root_map)
digit_numeral_root_finder = DigitNumeralRootFinder()
text_numeral_root_finder = TextNumeralRootFinder(cls.root_map)
proper_noun_from_apostrophe_root_finder = ProperNounFromApostropheRootFinder(
)
proper_noun_without_apostrophe_root_finder = ProperNounWithoutApostropheRootFinder(
)
cls.contextless_parser = UpperCaseSupportingContextlessMorphologicalParser(
suffix_graph, predefined_paths, [
word_root_finder, digit_numeral_root_finder,
text_numeral_root_finder,
proper_noun_from_apostrophe_root_finder,
proper_noun_without_apostrophe_root_finder
])
mongodb_connection = pymongo.Connection(host='127.0.0.1')
cls.collection_map = {
1: mongodb_connection['trnltk']['wordUnigrams999'],
2: mongodb_connection['trnltk']['wordBigrams999'],
3: mongodb_connection['trnltk']['wordTrigrams999']
}
database_index_builder = DatabaseIndexBuilder(cls.collection_map)
target_form_given_context_counter = InMemoryCachingTargetFormGivenContextCounter(
cls.collection_map)
ngram_frequency_smoother = CachedSimpleGoodTuringNGramFrequencySmoother(
)
sequence_likelihood_calculator = UniformSequenceLikelihoodCalculator()
wrapped_generator = ContextParsingLikelihoodCalculator(
database_index_builder, target_form_given_context_counter,
ngram_frequency_smoother, sequence_likelihood_calculator)
cls.generator = InterpolatingLikelihoodCalculator(wrapped_generator)
def create(cls, master_dictionary_path, ngram_collection_map):
"""
@type master_dictionary_path: str or unicode
@param ngram_collection_map: list<Collection>
@rtype ContextfulMorphologicalParser
"""
all_roots = []
lexemes = LexiconLoader.load_from_file(master_dictionary_path)
for di in lexemes:
all_roots.extend(RootGenerator.generate(di))
root_map_generator = RootMapGenerator()
root_map = root_map_generator.generate(all_roots)
suffix_graph = CopulaSuffixGraph(NumeralSuffixGraph(ProperNounSuffixGraph(BasicSuffixGraph())))
suffix_graph.initialize()
predefined_paths = PredefinedPaths(root_map, suffix_graph)
predefined_paths.create_predefined_paths()
word_root_finder = WordRootFinder(root_map)
digit_numeral_root_finder = DigitNumeralRootFinder()
text_numeral_root_finder = TextNumeralRootFinder(root_map)
proper_noun_from_apostrophe_root_finder = ProperNounFromApostropheRootFinder()
proper_noun_without_apostrophe_root_finder = ProperNounWithoutApostropheRootFinder()
contextless_parser = UpperCaseSupportingContextlessMorphologicalParser(suffix_graph, predefined_paths,
[word_root_finder, digit_numeral_root_finder, text_numeral_root_finder,
proper_noun_from_apostrophe_root_finder, proper_noun_without_apostrophe_root_finder])
database_index_builder = DatabaseIndexBuilder(ngram_collection_map)
target_form_given_context_counter = InMemoryCachingTargetFormGivenContextCounter(ngram_collection_map)
ngram_frequency_smoother = CachedSimpleGoodTuringNGramFrequencySmoother()
sequence_likelihood_calculator = SequenceLikelihoodCalculator(None)
collocation_metric_calculator = ContextParsingLikelihoodCalculator(database_index_builder,
target_form_given_context_counter, ngram_frequency_smoother,
sequence_likelihood_calculator)
interpolating_collocation_metric_calculator = InterpolatingLikelihoodCalculator(collocation_metric_calculator)
cached_contextless_distribution_smoother = CachedContextlessDistributionSmoother()
contextless_distribution_metric_calculator = ContextlessDistributionCalculator(database_index_builder,
target_form_given_context_counter, cached_contextless_distribution_smoother)
contextful_likelihood_calculator = ContextfulLikelihoodCalculator(interpolating_collocation_metric_calculator,
contextless_distribution_metric_calculator)
sequence_likelihood_calculator._contextful_likelihood_calculator = contextful_likelihood_calculator
contextful_morphological_parser = ContextfulMorphologicalParser(contextless_parser,
contextful_likelihood_calculator)
return contextful_morphological_parser
def setUpClass(cls):
super(StatisticalParserTest, cls).setUpClass()
all_roots = []
lexemes = LexiconLoader.load_from_file(
os.path.join(os.path.dirname(__file__),
'../../resources/master_dictionary.txt'))
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 = CopulaSuffixGraph(NumeralSuffixGraph(
BasicSuffixGraph()))
suffix_graph.initialize()
predefined_paths = PredefinedPaths(cls.root_map, suffix_graph)
predefined_paths.create_predefined_paths()
word_root_finder = WordRootFinder(cls.root_map)
digit_numeral_root_finder = DigitNumeralRootFinder()
text_numeral_root_finder = TextNumeralRootFinder(cls.root_map)
proper_noun_from_apostrophe_root_finder = ProperNounFromApostropheRootFinder(
)
proper_noun_without_apostrophe_root_finder = ProperNounWithoutApostropheRootFinder(
)
contextless_parser = ContextlessMorphologicalParser(
suffix_graph, predefined_paths, [
word_root_finder, digit_numeral_root_finder,
text_numeral_root_finder,
proper_noun_from_apostrophe_root_finder,
proper_noun_without_apostrophe_root_finder
])
parseset_index = "001"
dom = parse(
os.path.join(
os.path.dirname(__file__),
'../../testresources/parsesets/parseset{}.xml'.format(
parseset_index)))
parseset = ParseSetBinding.build(
dom.getElementsByTagName("parseset")[0])
parse_set_word_list = []
for sentence in parseset.sentences:
parse_set_word_list.extend(sentence.words)
complete_word_concordance_index = CompleteWordConcordanceIndex(
parse_set_word_list)
cls.parser = StatisticalParser(contextless_parser,
complete_word_concordance_index)
def create_calculator(cls, parseset_index):
all_roots = []
lexemes = LexiconLoader.load_from_file(os.path.join(os.path.dirname(__file__), '../../../../resources/master_dictionary.txt'))
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 = CopulaSuffixGraph(NumeralSuffixGraph(ProperNounSuffixGraph(BasicSuffixGraph())))
suffix_graph.initialize()
predefined_paths = PredefinedPaths(cls.root_map, suffix_graph)
predefined_paths.create_predefined_paths()
word_root_finder = WordRootFinder(cls.root_map)
digit_numeral_root_finder = DigitNumeralRootFinder()
text_numeral_root_finder = TextNumeralRootFinder(cls.root_map)
proper_noun_from_apostrophe_root_finder = ProperNounFromApostropheRootFinder()
proper_noun_without_apostrophe_root_finder = ProperNounWithoutApostropheRootFinder()
cls.contextless_parser = UpperCaseSupportingContextlessMorphologicalParser(suffix_graph, predefined_paths,
[word_root_finder, digit_numeral_root_finder, text_numeral_root_finder,
proper_noun_from_apostrophe_root_finder, proper_noun_without_apostrophe_root_finder])
mongodb_connection = pymongo.Connection(host='127.0.0.1')
collection_map = {
1: mongodb_connection['trnltk']['wordUnigrams{}'.format(parseset_index)],
2: mongodb_connection['trnltk']['wordBigrams{}'.format(parseset_index)],
3: mongodb_connection['trnltk']['wordTrigrams{}'.format(parseset_index)]
}
database_index_builder = DatabaseIndexBuilder(collection_map)
target_form_given_context_counter = InMemoryCachingTargetFormGivenContextCounter(collection_map)
ngram_frequency_smoother = CachedSimpleGoodTuringNGramFrequencySmoother()
sequence_likelihood_calculator = SequenceLikelihoodCalculator(None)
collocation_metric_calculator = ContextParsingLikelihoodCalculator(database_index_builder, target_form_given_context_counter, ngram_frequency_smoother,
sequence_likelihood_calculator)
interpolating_collocation_metric_calculator = InterpolatingLikelihoodCalculator(collocation_metric_calculator)
contextless_distribution_metric_calculator = ContextlessDistributionCalculator(database_index_builder, target_form_given_context_counter)
contextful_likelihood_calculator = ContextfulLikelihoodCalculator(interpolating_collocation_metric_calculator, contextless_distribution_metric_calculator)
sequence_likelihood_calculator._contextful_likelihood_calculator = contextful_likelihood_calculator
return contextful_likelihood_calculator
def setUp(self):
logging.basicConfig(level=logging.INFO)
parser_logger.setLevel(logging.INFO)
suffix_applier_logger.setLevel(logging.INFO)
self.cloned_root_map = copy(self._org_root_map)
suffix_graph = CopulaSuffixGraph(BasicSuffixGraph())
suffix_graph.initialize()
predefined_paths = PredefinedPaths(self.cloned_root_map, suffix_graph)
predefined_paths.create_predefined_paths()
word_root_finder = WordRootFinder(self.cloned_root_map)
self.parser = ContextlessMorphologicalParser(suffix_graph, predefined_paths,
[word_root_finder])
def setUp(self):
super(PredefinedPathsTest, self).setUp()
logging.basicConfig(level=logging.INFO)
parser_logger.setLevel(logging.INFO)
suffix_applier_logger.setLevel(logging.INFO)
self.predefined_paths = PredefinedPaths(self.root_map, self.suffix_graph)
def setUpClass(cls):
super(_LikelihoodCalculatorTest, cls).setUpClass()
all_roots = []
lexemes = LexiconLoader.load_from_file(
os.path.join(os.path.dirname(__file__),
'../../../../../resources/master_dictionary.txt'))
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 = CopulaSuffixGraph(
NumeralSuffixGraph(ProperNounSuffixGraph(BasicSuffixGraph())))
suffix_graph.initialize()
predefined_paths = PredefinedPaths(cls.root_map, suffix_graph)
predefined_paths.create_predefined_paths()
word_root_finder = WordRootFinder(cls.root_map)
digit_numeral_root_finder = DigitNumeralRootFinder()
text_numeral_root_finder = TextNumeralRootFinder(cls.root_map)
proper_noun_from_apostrophe_root_finder = ProperNounFromApostropheRootFinder(
)
proper_noun_without_apostrophe_root_finder = ProperNounWithoutApostropheRootFinder(
)
cls.contextless_parser = ContextlessMorphologicalParser(
suffix_graph, predefined_paths, [
word_root_finder, digit_numeral_root_finder,
text_numeral_root_finder,
proper_noun_from_apostrophe_root_finder,
proper_noun_without_apostrophe_root_finder
])
cls.mongodb_connection = pymongo.Connection(host='127.0.0.1')
cls.collection_map = {
1: cls.mongodb_connection['trnltk']['wordUnigrams999'],
2: cls.mongodb_connection['trnltk']['wordBigrams999'],
3: cls.mongodb_connection['trnltk']['wordTrigrams999']
}
cls.generator = None
def setUpClass(cls):
all_roots = []
lexemes = LexiconLoader.load_from_file(os.path.join(os.path.dirname(__file__), '../../../../../resources/master_dictionary.txt'))
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 = CopulaSuffixGraph(NumeralSuffixGraph(ProperNounSuffixGraph(BasicSuffixGraph())))
suffix_graph.initialize()
predefined_paths = PredefinedPaths(cls.root_map, suffix_graph)
predefined_paths.create_predefined_paths()
word_root_finder = WordRootFinder(cls.root_map)
digit_numeral_root_finder = DigitNumeralRootFinder()
text_numeral_root_finder = TextNumeralRootFinder(cls.root_map)
proper_noun_from_apostrophe_root_finder = ProperNounFromApostropheRootFinder()
proper_noun_without_apostrophe_root_finder = ProperNounWithoutApostropheRootFinder()
cls.contextless_parser = ContextlessMorphologicalParser(suffix_graph, predefined_paths,
[word_root_finder, digit_numeral_root_finder, text_numeral_root_finder,
proper_noun_from_apostrophe_root_finder, proper_noun_without_apostrophe_root_finder])
mongodb_connection = pymongo.Connection(host='127.0.0.1')
collection_map = {
1: mongodb_connection['trnltk']['wordUnigrams{}'.format(cls.parseset_index)]
}
database_index_builder = DatabaseIndexBuilder(collection_map)
target_form_given_context_counter = TargetFormGivenContextCounter(collection_map)
smoother = CachedContextlessDistributionSmoother()
smoother.initialize()
cls.calculator = ContextlessDistributionCalculator(database_index_builder, target_form_given_context_counter, smoother)
cls.calculator.build_indexes()
def setUpClass(cls):
super(TransitionGeneratorTest, cls).setUpClass()
all_roots = []
lexemes = LexiconLoader.load_from_file(
os.path.join(os.path.dirname(__file__),
'../../resources/master_dictionary.txt'))
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 = CopulaSuffixGraph(
NumeralSuffixGraph(ProperNounSuffixGraph(BasicSuffixGraph())))
suffix_graph.initialize()
predefined_paths = PredefinedPaths(cls.root_map, suffix_graph)
predefined_paths.create_predefined_paths()
word_root_finder = WordRootFinder(cls.root_map)
digit_numeral_root_finder = DigitNumeralRootFinder()
text_numeral_root_finder = TextNumeralRootFinder(cls.root_map)
proper_noun_from_apostrophe_root_finder = ProperNounFromApostropheRootFinder(
)
proper_noun_without_apostrophe_root_finder = ProperNounWithoutApostropheRootFinder(
)
cls.parser = ContextlessMorphologicalParser(
suffix_graph, predefined_paths, [
word_root_finder, digit_numeral_root_finder,
text_numeral_root_finder,
proper_noun_from_apostrophe_root_finder,
proper_noun_without_apostrophe_root_finder
])
cls.transition_generator = TransitionGenerator(cls.parser)
def setUpClass(cls):
super(StatisticalParserTest, cls).setUpClass()
all_roots = []
lexemes = LexiconLoader.load_from_file(os.path.join(os.path.dirname(__file__), '../../resources/master_dictionary.txt'))
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 = CopulaSuffixGraph(NumeralSuffixGraph(BasicSuffixGraph()))
suffix_graph.initialize()
predefined_paths = PredefinedPaths(cls.root_map, suffix_graph)
predefined_paths.create_predefined_paths()
word_root_finder = WordRootFinder(cls.root_map)
digit_numeral_root_finder = DigitNumeralRootFinder()
text_numeral_root_finder = TextNumeralRootFinder(cls.root_map)
proper_noun_from_apostrophe_root_finder = ProperNounFromApostropheRootFinder()
proper_noun_without_apostrophe_root_finder = ProperNounWithoutApostropheRootFinder()
contextless_parser = ContextlessMorphologicalParser(suffix_graph, predefined_paths,
[word_root_finder, digit_numeral_root_finder, text_numeral_root_finder, proper_noun_from_apostrophe_root_finder, proper_noun_without_apostrophe_root_finder])
parseset_index = "001"
dom = parse(os.path.join(os.path.dirname(__file__), '../../testresources/parsesets/parseset{}.xml'.format(parseset_index)))
parseset = ParseSetBinding.build(dom.getElementsByTagName("parseset")[0])
parse_set_word_list = []
for sentence in parseset.sentences:
parse_set_word_list.extend(sentence.words)
complete_word_concordance_index = CompleteWordConcordanceIndex(parse_set_word_list)
cls.parser = StatisticalParser(contextless_parser, complete_word_concordance_index)
from trnltk.morphology.morphotactics.propernounsuffixgraph import ProperNounSuffixGraph
all_roots = []
lexemes = LexiconLoader.load_from_file('trnltk/trnltk/resources/master_dictionary.txt')
for di in lexemes:
all_roots.extend(CircumflexConvertingRootGenerator.generate(di))
root_map_generator = RootMapGenerator()
root_map = root_map_generator.generate(all_roots)
suffix_graph = CopulaSuffixGraph(NumeralSuffixGraph(ProperNounSuffixGraph(BasicSuffixGraph())))
suffix_graph.initialize()
predefined_paths = PredefinedPaths(root_map, suffix_graph)
predefined_paths.create_predefined_paths()
word_root_finder = WordRootFinder(root_map)
text_numeral_root_finder = TextNumeralRootFinder(root_map)
digit_numeral_root_finder = DigitNumeralRootFinder()
proper_noun_from_apostrophe_root_finder = ProperNounFromApostropheRootFinder()
proper_noun_without_apostrophe_root_finder = ProperNounWithoutApostropheRootFinder()
parser = UpperCaseSupportingContextlessMorphologicalParser(suffix_graph, predefined_paths,
[word_root_finder, text_numeral_root_finder, digit_numeral_root_finder,
proper_noun_from_apostrophe_root_finder, proper_noun_without_apostrophe_root_finder])
sentence = sys.argv[1].decode('utf-8')
for word in sentence.split():
class PredefinedPathsTest(unittest.TestCase):
@classmethod
def setUpClass(cls):
super(PredefinedPathsTest, cls).setUpClass()
all_roots = []
lexemes = LexiconLoader.load_from_file(os.path.join(os.path.dirname(__file__), '../../../resources/master_dictionary.txt'))
for di in lexemes:
all_roots.extend(RootGenerator.generate(di))
root_map_generator = RootMapGenerator()
cls.root_map = root_map_generator.generate(all_roots)
cls.morpheme_container_map = {}
cls.suffix_graph = BasicSuffixGraph()
cls.suffix_graph.initialize()
def setUp(self):
super(PredefinedPathsTest, self).setUp()
logging.basicConfig(level=logging.INFO)
parser_logger.setLevel(logging.INFO)
suffix_applier_logger.setLevel(logging.INFO)
self.predefined_paths = PredefinedPaths(self.root_map, self.suffix_graph)
def tearDown(self):
self.predefined_paths = None
self.morpheme_container_map = {}
def test_should_have_paths_for_personal_pronouns(self):
self.predefined_paths._create_predefined_path_of_ben()
self.predefined_paths._create_predefined_path_of_sen()
self.morpheme_container_map = self.predefined_paths._morpheme_container_map
PRON = SyntacticCategory.PRONOUN
PERS = SecondarySyntacticCategory.PERSONAL
# last one ends with transition to derivation state
self.assert_defined_path(u'ben', PRON, PERS,
u'ben(ben)+Pron+Pers+A1sg+Pnon+Nom',
u'ben(ben)+Pron+Pers+A1sg+Pnon+Acc(i[i])',
u'ben(ben)+Pron+Pers+A1sg+Pnon+Loc(de[de])',
u'ben(ben)+Pron+Pers+A1sg+Pnon+Abl(den[den])',
u'ben(ben)+Pron+Pers+A1sg+Pnon+Ins(le[le])',
u'ben(ben)+Pron+Pers+A1sg+Pnon+Ins(imle[imle])',
u'ben(ben)+Pron+Pers+A1sg+Pnon+Gen(im[im])',
u'ben(ben)+Pron+Pers+A1sg+Pnon+AccordingTo(ce[ce])',
u'ben(ben)+Pron+Pers+A1sg+Pnon+Nom')
self.assert_defined_path(u'ban', PRON, PERS,
u'ban(ben)+Pron+Pers+A1sg+Pnon+Dat(a[a])')
# last one ends with transition to derivation state
self.assert_defined_path(u'sen', PRON, PERS,
u'sen(sen)+Pron+Pers+A2sg+Pnon+Nom',
u'sen(sen)+Pron+Pers+A2sg+Pnon+Acc(i[i])',
u'sen(sen)+Pron+Pers+A2sg+Pnon+Loc(de[de])',
u'sen(sen)+Pron+Pers+A2sg+Pnon+Abl(den[den])',
u'sen(sen)+Pron+Pers+A2sg+Pnon+Ins(le[le])',
u'sen(sen)+Pron+Pers+A2sg+Pnon+Ins(inle[inle])',
u'sen(sen)+Pron+Pers+A2sg+Pnon+Gen(in[in])',
u'sen(sen)+Pron+Pers+A2sg+Pnon+AccordingTo(ce[ce])',
u'sen(sen)+Pron+Pers+A2sg+Pnon+Nom')
self.assert_defined_path(u'san', PRON, PERS,
u'san(sen)+Pron+Pers+A2sg+Pnon+Dat(a[a])')
def test_should_have_paths_for_hepsi(self):
parser_logger.setLevel(logging.DEBUG)
suffix_applier_logger.setLevel(logging.DEBUG)
self.predefined_paths._create_predefined_path_of_hepsi()
self.morpheme_container_map = self.predefined_paths._morpheme_container_map
PRON = SyntacticCategory.PRONOUN
# last one ends with transition to derivation state
self.assert_defined_path(u'hepsi', PRON, None,
u'hepsi(hepsi)+Pron+A3pl+P3pl+Nom',
u'hepsi(hepsi)+Pron+A3pl+P3pl+Acc(ni[ni])',
u'hepsi(hepsi)+Pron+A3pl+P3pl+Dat(ne[ne])',
u'hepsi(hepsi)+Pron+A3pl+P3pl+Loc(nde[nde])',
u'hepsi(hepsi)+Pron+A3pl+P3pl+Abl(nden[nden])',
u'hepsi(hepsi)+Pron+A3pl+P3pl+Ins(yle[yle])',
u'hepsi(hepsi)+Pron+A3pl+P3pl+Gen(nin[nin])',
u'hepsi(hepsi)+Pron+A3pl+P3pl+AccordingTo(nce[nce])',
u'hepsi(hepsi)+Pron+A3pl+P3pl+Nom')
# last one ends with transition to derivation state
self.assert_defined_path(u'hep', PRON, None,
u'hep(hepsi)+Pron+A1pl+P1pl(imiz[imiz])+Nom',
u'hep(hepsi)+Pron+A1pl+P1pl(imiz[imiz])+Acc(i[i])',
u'hep(hepsi)+Pron+A1pl+P1pl(imiz[imiz])+Dat(e[e])',
u'hep(hepsi)+Pron+A1pl+P1pl(imiz[imiz])+Loc(de[de])',
u'hep(hepsi)+Pron+A1pl+P1pl(imiz[imiz])+Abl(den[den])',
u'hep(hepsi)+Pron+A1pl+P1pl(imiz[imiz])+Ins(le[le])',
u'hep(hepsi)+Pron+A1pl+P1pl(imiz[imiz])+Gen(in[in])',
u'hep(hepsi)+Pron+A1pl+P1pl(imiz[imiz])+AccordingTo(ce[ce])',
u'hep(hepsi)+Pron+A1pl+P1pl(imiz[imiz])+Nom',
u'hep(hepsi)+Pron+A2pl+P2pl(iniz[iniz])+Nom',
u'hep(hepsi)+Pron+A2pl+P2pl(iniz[iniz])+Acc(i[i])',
u'hep(hepsi)+Pron+A2pl+P2pl(iniz[iniz])+Dat(e[e])',
u'hep(hepsi)+Pron+A2pl+P2pl(iniz[iniz])+Loc(de[de])',
u'hep(hepsi)+Pron+A2pl+P2pl(iniz[iniz])+Abl(den[den])',
u'hep(hepsi)+Pron+A2pl+P2pl(iniz[iniz])+Ins(le[le])',
u'hep(hepsi)+Pron+A2pl+P2pl(iniz[iniz])+Gen(in[in])',
u'hep(hepsi)+Pron+A2pl+P2pl(iniz[iniz])+AccordingTo(ce[ce])',
u'hep(hepsi)+Pron+A2pl+P2pl(iniz[iniz])+Nom')
def test_should_have_paths_for_ques(self):
parser_logger.setLevel(logging.DEBUG)
suffix_applier_logger.setLevel(logging.DEBUG)
self.predefined_paths._create_predefined_path_of_question_particles()
self.morpheme_container_map = self.predefined_paths._morpheme_container_map
QUES = SyntacticCategory.QUESTION
# last one ends with transition to derivation state
self.assert_defined_path(u'mı', QUES, None,
u'mı(mı)+Ques+Pres+A1sg(yım[yım])',
u'mı(mı)+Ques+Pres+A2sg(sın[sın])',
u'mı(mı)+Ques+Pres+A3sg',
u'mı(mı)+Ques+Pres+A1pl(yız[yız])',
u'mı(mı)+Ques+Pres+A2pl(sınız[sınız])',
u'mı(mı)+Ques+Pres+A3pl(lar[lar])',
u'mı(mı)+Ques+Past(ydı[ydı])+A1sg(m[m])',
u'mı(mı)+Ques+Past(ydı[ydı])+A2sg(n[n])',
u'mı(mı)+Ques+Past(ydı[ydı])+A3sg',
u'mı(mı)+Ques+Past(ydı[ydı])+A1pl(k[k])',
u'mı(mı)+Ques+Past(ydı[ydı])+A2pl(nız[nız])',
u'mı(mı)+Ques+Past(ydı[ydı])+A3pl(lar[lar])',
u'mı(mı)+Ques+Narr(ymış[ymış])+A1sg(ım[ım])',
u'mı(mı)+Ques+Narr(ymış[ymış])+A2sg(sın[sın])',
u'mı(mı)+Ques+Narr(ymış[ymış])+A3sg',
u'mı(mı)+Ques+Narr(ymış[ymış])+A1pl(ız[ız])',
u'mı(mı)+Ques+Narr(ymış[ymış])+A2pl(sınız[sınız])',
u'mı(mı)+Ques+Narr(ymış[ymış])+A3pl(lar[lar])')
def test_should_have_paths_for_pronouns_with_implicit_possession(self):
parser_logger.setLevel(logging.DEBUG)
suffix_applier_logger.setLevel(logging.DEBUG)
self.predefined_paths._create_predefined_path_of_bazilari_bazisi()
self.predefined_paths._create_predefined_path_of_kimileri_kimisi_kimi()
self.predefined_paths._create_predefined_path_of_birileri_birisi_biri()
self.predefined_paths._create_predefined_path_of_hicbirisi_hicbiri()
self.predefined_paths._create_predefined_path_of_birbiri()
self.predefined_paths._create_predefined_path_of_cogu_bircogu_coklari_bircoklari()
self.predefined_paths._create_predefined_path_of_birkaci()
self.predefined_paths._create_predefined_path_of_cumlesi()
self.predefined_paths._create_predefined_path_of_digeri_digerleri()
self.morpheme_container_map = self.predefined_paths._morpheme_container_map
PRON = SyntacticCategory.PRONOUN
self.assert_defined_path(u'bazıları', PRON, None, u'bazıları(bazıları)+Pron+A3sg+P3sg', u'bazıları(bazıları)+Pron+A3sg+P1pl(mız[mız])', u'bazıları(bazıları)+Pron+A3sg+P2pl(nız[nız])')
self.assert_defined_path(u'bazısı', PRON, None, u'bazısı(bazısı)+Pron+A3sg+P3sg')
self.assert_defined_path(u'kimileri', PRON, None, u'kimileri(kimileri)+Pron+A3sg+P3sg', u'kimileri(kimileri)+Pron+A3sg+P1pl(miz[miz])', u'kimileri(kimileri)+Pron+A3sg+P2pl(niz[niz])')
self.assert_defined_path(u'kimisi', PRON, None, u'kimisi(kimisi)+Pron+A3sg+P3sg')
self.assert_defined_path(u'kimi', PRON, None, u'kimi(kimi)+Pron+A3sg+P3sg', u'kimi(kimi)+Pron+A3sg+P1pl(miz[miz])', u'kimi(kimi)+Pron+A3sg+P2pl(niz[niz])')
self.assert_defined_path(u'birileri', PRON, None, u'birileri(birileri)+Pron+A3sg+P3sg', u'birileri(birileri)+Pron+A3sg+P1pl(miz[miz])', u'birileri(birileri)+Pron+A3sg+P2pl(niz[niz])')
self.assert_defined_path(u'birisi', PRON, None, u'birisi(birisi)+Pron+A3sg+P3sg')
self.assert_defined_path(u'biri', PRON, None, u'biri(biri)+Pron+A3sg+P3sg', u'biri(biri)+Pron+A3sg+P1pl(miz[miz])', u'biri(biri)+Pron+A3sg+P2pl(niz[niz])')
self.assert_defined_path(u'hiçbirisi', PRON, None, u'hiçbirisi(hiçbirisi)+Pron+A3sg+P3sg')
self.assert_defined_path(u'hiçbiri', PRON, None, u'hiçbiri(hiçbiri)+Pron+A3sg+P3sg', u'hiçbiri(hiçbiri)+Pron+A3sg+P1pl(miz[miz])', u'hiçbiri(hiçbiri)+Pron+A3sg+P2pl(niz[niz])')
self.assert_defined_path(u'birbiri', PRON, None, u'birbiri(birbiri)+Pron+A3sg+P3sg', u'birbiri(birbiri)+Pron+A1pl+P1pl(miz[miz])', u'birbiri(birbiri)+Pron+A2pl+P2pl(niz[niz])')
self.assert_defined_path(u'birbir', PRON, None, u'birbir(birbiri)+Pron+A3pl+P3pl(leri[leri])')
self.assert_defined_path(u'çoğu', PRON, None, u'çoğu(çoğu)+Pron+A3sg+P3sg', u'çoğu(çoğu)+Pron+A3sg+P1pl(muz[muz])', u'çoğu(çoğu)+Pron+A3sg+P2pl(nuz[nuz])')
self.assert_defined_path(u'birçoğu', PRON, None, u'birçoğu(birçoğu)+Pron+A3sg+P3sg', u'birçoğu(birçoğu)+Pron+A3sg+P1pl(muz[muz])', u'birçoğu(birçoğu)+Pron+A3sg+P2pl(nuz[nuz])')
self.assert_defined_path(u'çokları', PRON, None, u'çokları(çokları)+Pron+A3sg+P3pl')
self.assert_defined_path(u'birçokları', PRON, None, u'birçokları(birçokları)+Pron+A3sg+P3pl')
self.assert_defined_path(u'birkaçı', PRON, None, u'birkaçı(birkaçı)+Pron+A3sg+P3sg', u'birkaçı(birkaçı)+Pron+A3sg+P1pl(mız[mız])', u'birkaçı(birkaçı)+Pron+A3sg+P2pl(nız[nız])')
self.assert_defined_path(u'cümlesi', PRON, None, u'cümlesi(cümlesi)+Pron+A3sg+P3sg')
self.assert_defined_path(u'diğeri', PRON, None, u'diğeri(diğeri)+Pron+A3sg+P3sg', u'diğeri(diğeri)+Pron+A3sg+P1pl(miz[miz])', u'diğeri(diğeri)+Pron+A3sg+P2pl(niz[niz])')
self.assert_defined_path(u'diğerleri', PRON, None, u'diğerleri(diğerleri)+Pron+A3sg+P3pl', u'diğerleri(diğerleri)+Pron+A3sg+P1pl(miz[miz])', u'diğerleri(diğerleri)+Pron+A3sg+P2pl(niz[niz])')
def test_should_have_paths_for_irregular_pronouns(self):
parser_logger.setLevel(logging.DEBUG)
suffix_applier_logger.setLevel(logging.DEBUG)
self.predefined_paths._create_predefined_path_of_herkes()
self.morpheme_container_map = self.predefined_paths._morpheme_container_map
PRON = SyntacticCategory.PRONOUN
self.assert_defined_path(u'herkes', PRON, None, u'herkes(herkes)+Pron+A3sg+Pnon')
def test_should_have_paths_for_pronouns_bura_sura_ora(self):
parser_logger.setLevel(logging.DEBUG)
suffix_applier_logger.setLevel(logging.DEBUG)
self.predefined_paths._create_predefined_path_of_ora_bura_sura_nere()
self.morpheme_container_map = self.predefined_paths._morpheme_container_map
PRON = SyntacticCategory.PRONOUN
self.assert_defined_path(u'or', PRON, None, u'or(ora)+Pron+A3sg+Pnon+Loc(da[da])', u'or(ora)+Pron+A3sg+Pnon+Abl(dan[dan])')
self.assert_defined_path(u'bur', PRON, None, u'bur(bura)+Pron+A3sg+Pnon+Loc(da[da])', u'bur(bura)+Pron+A3sg+Pnon+Abl(dan[dan])')
self.assert_defined_path(u'şur', PRON, None, u'şur(şura)+Pron+A3sg+Pnon+Loc(da[da])', u'şur(şura)+Pron+A3sg+Pnon+Abl(dan[dan])')
self.assert_defined_path(u'ner', PRON, SecondarySyntacticCategory.QUESTION, u'ner(nere)+Pron+Ques+A3sg+Pnon+Loc(de[de])', u'ner(nere)+Pron+Ques+A3sg+Pnon+Abl(den[den])')
def test_should_have_paths_for_iceri_disari(self):
parser_logger.setLevel(logging.DEBUG)
suffix_applier_logger.setLevel(logging.DEBUG)
self.predefined_paths._create_predefined_path_of_iceri_disari()
self.morpheme_container_map = self.predefined_paths._morpheme_container_map
NOUN = SyntacticCategory.NOUN
self.assert_defined_path(u'içer', NOUN, None, u'i\xe7er(i\xe7eri)+Noun+A3sg+Pnon+Loc(de[de])', u'i\xe7er(i\xe7eri)+Noun+A3sg+Pnon+Abl(den[den])', u'i\xe7er(i\xe7eri)+Noun+A3sg+P3sg(si[si])')
self.assert_defined_path(u'dışar', NOUN, None, u'd\u0131\u015far(d\u0131\u015far\u0131)+Noun+A3sg+Pnon+Loc(da[da])', u'd\u0131\u015far(d\u0131\u015far\u0131)+Noun+A3sg+Pnon+Abl(dan[dan])', u'd\u0131\u015far(d\u0131\u015far\u0131)+Noun+A3sg+P3sg(s\u0131[s\u0131])')
def assert_defined_path(self, root, syntactic_category, secondary_syntactic_category, *args):
assert_that(self.predefined_morpheme_containers(root, syntactic_category, secondary_syntactic_category), AreMorphemeContainersMatch([a for a in args]))
def predefined_morpheme_containers(self, root_str, syntactic_category, secondary_syntactic_category):
predefined_morpheme_containers = []
for root in self.morpheme_container_map.keys():
if root.str==root_str and root.lexeme.syntactic_category==syntactic_category and root.lexeme.secondary_syntactic_category==secondary_syntactic_category:
predefined_morpheme_containers.extend(self.morpheme_container_map[root])
return [formatter.format_morpheme_container_for_tests(r) for r in predefined_morpheme_containers]
class PredefinedPathsTest(unittest.TestCase):
@classmethod
def setUpClass(cls):
super(PredefinedPathsTest, cls).setUpClass()
all_roots = []
lexemes = LexiconLoader.load_from_file(
os.path.join(os.path.dirname(__file__),
'../../../resources/master_dictionary.txt'))
for di in lexemes:
all_roots.extend(RootGenerator.generate(di))
root_map_generator = RootMapGenerator()
cls.root_map = root_map_generator.generate(all_roots)
cls.morpheme_container_map = {}
cls.suffix_graph = BasicSuffixGraph()
cls.suffix_graph.initialize()
def setUp(self):
super(PredefinedPathsTest, self).setUp()
logging.basicConfig(level=logging.INFO)
parser_logger.setLevel(logging.INFO)
suffix_applier_logger.setLevel(logging.INFO)
self.predefined_paths = PredefinedPaths(self.root_map,
self.suffix_graph)
def tearDown(self):
self.predefined_paths = None
self.morpheme_container_map = {}
def test_should_have_paths_for_personal_pronouns(self):
self.predefined_paths._create_predefined_path_of_ben()
self.predefined_paths._create_predefined_path_of_sen()
self.morpheme_container_map = self.predefined_paths._morpheme_container_map
PRON = SyntacticCategory.PRONOUN
PERS = SecondarySyntacticCategory.PERSONAL
# last one ends with transition to derivation state
self.assert_defined_path(
u'ben', PRON, PERS, u'ben(ben)+Pron+Pers+A1sg+Pnon+Nom',
u'ben(ben)+Pron+Pers+A1sg+Pnon+Acc(i[i])',
u'ben(ben)+Pron+Pers+A1sg+Pnon+Loc(de[de])',
u'ben(ben)+Pron+Pers+A1sg+Pnon+Abl(den[den])',
u'ben(ben)+Pron+Pers+A1sg+Pnon+Ins(le[le])',
u'ben(ben)+Pron+Pers+A1sg+Pnon+Ins(imle[imle])',
u'ben(ben)+Pron+Pers+A1sg+Pnon+Gen(im[im])',
u'ben(ben)+Pron+Pers+A1sg+Pnon+AccordingTo(ce[ce])',
u'ben(ben)+Pron+Pers+A1sg+Pnon+Nom')
self.assert_defined_path(u'ban', PRON, PERS,
u'ban(ben)+Pron+Pers+A1sg+Pnon+Dat(a[a])')
# last one ends with transition to derivation state
self.assert_defined_path(
u'sen', PRON, PERS, u'sen(sen)+Pron+Pers+A2sg+Pnon+Nom',
u'sen(sen)+Pron+Pers+A2sg+Pnon+Acc(i[i])',
u'sen(sen)+Pron+Pers+A2sg+Pnon+Loc(de[de])',
u'sen(sen)+Pron+Pers+A2sg+Pnon+Abl(den[den])',
u'sen(sen)+Pron+Pers+A2sg+Pnon+Ins(le[le])',
u'sen(sen)+Pron+Pers+A2sg+Pnon+Ins(inle[inle])',
u'sen(sen)+Pron+Pers+A2sg+Pnon+Gen(in[in])',
u'sen(sen)+Pron+Pers+A2sg+Pnon+AccordingTo(ce[ce])',
u'sen(sen)+Pron+Pers+A2sg+Pnon+Nom')
self.assert_defined_path(u'san', PRON, PERS,
u'san(sen)+Pron+Pers+A2sg+Pnon+Dat(a[a])')
def test_should_have_paths_for_hepsi(self):
parser_logger.setLevel(logging.DEBUG)
suffix_applier_logger.setLevel(logging.DEBUG)
self.predefined_paths._create_predefined_path_of_hepsi()
self.morpheme_container_map = self.predefined_paths._morpheme_container_map
PRON = SyntacticCategory.PRONOUN
# last one ends with transition to derivation state
self.assert_defined_path(
u'hepsi', PRON, None, u'hepsi(hepsi)+Pron+A3pl+P3pl+Nom',
u'hepsi(hepsi)+Pron+A3pl+P3pl+Acc(ni[ni])',
u'hepsi(hepsi)+Pron+A3pl+P3pl+Dat(ne[ne])',
u'hepsi(hepsi)+Pron+A3pl+P3pl+Loc(nde[nde])',
u'hepsi(hepsi)+Pron+A3pl+P3pl+Abl(nden[nden])',
u'hepsi(hepsi)+Pron+A3pl+P3pl+Ins(yle[yle])',
u'hepsi(hepsi)+Pron+A3pl+P3pl+Gen(nin[nin])',
u'hepsi(hepsi)+Pron+A3pl+P3pl+AccordingTo(nce[nce])',
u'hepsi(hepsi)+Pron+A3pl+P3pl+Nom')
# last one ends with transition to derivation state
self.assert_defined_path(
u'hep', PRON, None, u'hep(hepsi)+Pron+A1pl+P1pl(imiz[imiz])+Nom',
u'hep(hepsi)+Pron+A1pl+P1pl(imiz[imiz])+Acc(i[i])',
u'hep(hepsi)+Pron+A1pl+P1pl(imiz[imiz])+Dat(e[e])',
u'hep(hepsi)+Pron+A1pl+P1pl(imiz[imiz])+Loc(de[de])',
u'hep(hepsi)+Pron+A1pl+P1pl(imiz[imiz])+Abl(den[den])',
u'hep(hepsi)+Pron+A1pl+P1pl(imiz[imiz])+Ins(le[le])',
u'hep(hepsi)+Pron+A1pl+P1pl(imiz[imiz])+Gen(in[in])',
u'hep(hepsi)+Pron+A1pl+P1pl(imiz[imiz])+AccordingTo(ce[ce])',
u'hep(hepsi)+Pron+A1pl+P1pl(imiz[imiz])+Nom',
u'hep(hepsi)+Pron+A2pl+P2pl(iniz[iniz])+Nom',
u'hep(hepsi)+Pron+A2pl+P2pl(iniz[iniz])+Acc(i[i])',
u'hep(hepsi)+Pron+A2pl+P2pl(iniz[iniz])+Dat(e[e])',
u'hep(hepsi)+Pron+A2pl+P2pl(iniz[iniz])+Loc(de[de])',
u'hep(hepsi)+Pron+A2pl+P2pl(iniz[iniz])+Abl(den[den])',
u'hep(hepsi)+Pron+A2pl+P2pl(iniz[iniz])+Ins(le[le])',
u'hep(hepsi)+Pron+A2pl+P2pl(iniz[iniz])+Gen(in[in])',
u'hep(hepsi)+Pron+A2pl+P2pl(iniz[iniz])+AccordingTo(ce[ce])',
u'hep(hepsi)+Pron+A2pl+P2pl(iniz[iniz])+Nom')
def test_should_have_paths_for_ques(self):
parser_logger.setLevel(logging.DEBUG)
suffix_applier_logger.setLevel(logging.DEBUG)
self.predefined_paths._create_predefined_path_of_question_particles()
self.morpheme_container_map = self.predefined_paths._morpheme_container_map
QUES = SyntacticCategory.QUESTION
# last one ends with transition to derivation state
self.assert_defined_path(
u'mı', QUES, None, u'mı(mı)+Ques+Pres+A1sg(yım[yım])',
u'mı(mı)+Ques+Pres+A2sg(sın[sın])', u'mı(mı)+Ques+Pres+A3sg',
u'mı(mı)+Ques+Pres+A1pl(yız[yız])',
u'mı(mı)+Ques+Pres+A2pl(sınız[sınız])',
u'mı(mı)+Ques+Pres+A3pl(lar[lar])',
u'mı(mı)+Ques+Past(ydı[ydı])+A1sg(m[m])',
u'mı(mı)+Ques+Past(ydı[ydı])+A2sg(n[n])',
u'mı(mı)+Ques+Past(ydı[ydı])+A3sg',
u'mı(mı)+Ques+Past(ydı[ydı])+A1pl(k[k])',
u'mı(mı)+Ques+Past(ydı[ydı])+A2pl(nız[nız])',
u'mı(mı)+Ques+Past(ydı[ydı])+A3pl(lar[lar])',
u'mı(mı)+Ques+Narr(ymış[ymış])+A1sg(ım[ım])',
u'mı(mı)+Ques+Narr(ymış[ymış])+A2sg(sın[sın])',
u'mı(mı)+Ques+Narr(ymış[ymış])+A3sg',
u'mı(mı)+Ques+Narr(ymış[ymış])+A1pl(ız[ız])',
u'mı(mı)+Ques+Narr(ymış[ymış])+A2pl(sınız[sınız])',
u'mı(mı)+Ques+Narr(ymış[ymış])+A3pl(lar[lar])')
def test_should_have_paths_for_pronouns_with_implicit_possession(self):
parser_logger.setLevel(logging.DEBUG)
suffix_applier_logger.setLevel(logging.DEBUG)
self.predefined_paths._create_predefined_path_of_bazilari_bazisi()
self.predefined_paths._create_predefined_path_of_kimileri_kimisi_kimi()
self.predefined_paths._create_predefined_path_of_birileri_birisi_biri()
self.predefined_paths._create_predefined_path_of_hicbirisi_hicbiri()
self.predefined_paths._create_predefined_path_of_birbiri()
self.predefined_paths._create_predefined_path_of_cogu_bircogu_coklari_bircoklari(
)
self.predefined_paths._create_predefined_path_of_birkaci()
self.predefined_paths._create_predefined_path_of_cumlesi()
self.predefined_paths._create_predefined_path_of_digeri_digerleri()
self.morpheme_container_map = self.predefined_paths._morpheme_container_map
PRON = SyntacticCategory.PRONOUN
self.assert_defined_path(
u'bazıları', PRON, None, u'bazıları(bazıları)+Pron+A3sg+P3sg',
u'bazıları(bazıları)+Pron+A3sg+P1pl(mız[mız])',
u'bazıları(bazıları)+Pron+A3sg+P2pl(nız[nız])')
self.assert_defined_path(u'bazısı', PRON, None,
u'bazısı(bazısı)+Pron+A3sg+P3sg')
self.assert_defined_path(
u'kimileri', PRON, None, u'kimileri(kimileri)+Pron+A3sg+P3sg',
u'kimileri(kimileri)+Pron+A3sg+P1pl(miz[miz])',
u'kimileri(kimileri)+Pron+A3sg+P2pl(niz[niz])')
self.assert_defined_path(u'kimisi', PRON, None,
u'kimisi(kimisi)+Pron+A3sg+P3sg')
self.assert_defined_path(u'kimi', PRON, None,
u'kimi(kimi)+Pron+A3sg+P3sg',
u'kimi(kimi)+Pron+A3sg+P1pl(miz[miz])',
u'kimi(kimi)+Pron+A3sg+P2pl(niz[niz])')
self.assert_defined_path(
u'birileri', PRON, None, u'birileri(birileri)+Pron+A3sg+P3sg',
u'birileri(birileri)+Pron+A3sg+P1pl(miz[miz])',
u'birileri(birileri)+Pron+A3sg+P2pl(niz[niz])')
self.assert_defined_path(u'birisi', PRON, None,
u'birisi(birisi)+Pron+A3sg+P3sg')
self.assert_defined_path(u'biri', PRON, None,
u'biri(biri)+Pron+A3sg+P3sg',
u'biri(biri)+Pron+A3sg+P1pl(miz[miz])',
u'biri(biri)+Pron+A3sg+P2pl(niz[niz])')
self.assert_defined_path(u'hiçbirisi', PRON, None,
u'hiçbirisi(hiçbirisi)+Pron+A3sg+P3sg')
self.assert_defined_path(u'hiçbiri', PRON, None,
u'hiçbiri(hiçbiri)+Pron+A3sg+P3sg',
u'hiçbiri(hiçbiri)+Pron+A3sg+P1pl(miz[miz])',
u'hiçbiri(hiçbiri)+Pron+A3sg+P2pl(niz[niz])')
self.assert_defined_path(u'birbiri', PRON, None,
u'birbiri(birbiri)+Pron+A3sg+P3sg',
u'birbiri(birbiri)+Pron+A1pl+P1pl(miz[miz])',
u'birbiri(birbiri)+Pron+A2pl+P2pl(niz[niz])')
self.assert_defined_path(
u'birbir', PRON, None,
u'birbir(birbiri)+Pron+A3pl+P3pl(leri[leri])')
self.assert_defined_path(u'çoğu', PRON, None,
u'çoğu(çoğu)+Pron+A3sg+P3sg',
u'çoğu(çoğu)+Pron+A3sg+P1pl(muz[muz])',
u'çoğu(çoğu)+Pron+A3sg+P2pl(nuz[nuz])')
self.assert_defined_path(u'birçoğu', PRON, None,
u'birçoğu(birçoğu)+Pron+A3sg+P3sg',
u'birçoğu(birçoğu)+Pron+A3sg+P1pl(muz[muz])',
u'birçoğu(birçoğu)+Pron+A3sg+P2pl(nuz[nuz])')
self.assert_defined_path(u'çokları', PRON, None,
u'çokları(çokları)+Pron+A3sg+P3pl')
self.assert_defined_path(u'birçokları', PRON, None,
u'birçokları(birçokları)+Pron+A3sg+P3pl')
self.assert_defined_path(u'birkaçı', PRON, None,
u'birkaçı(birkaçı)+Pron+A3sg+P3sg',
u'birkaçı(birkaçı)+Pron+A3sg+P1pl(mız[mız])',
u'birkaçı(birkaçı)+Pron+A3sg+P2pl(nız[nız])')
self.assert_defined_path(u'cümlesi', PRON, None,
u'cümlesi(cümlesi)+Pron+A3sg+P3sg')
self.assert_defined_path(u'diğeri', PRON, None,
u'diğeri(diğeri)+Pron+A3sg+P3sg',
u'diğeri(diğeri)+Pron+A3sg+P1pl(miz[miz])',
u'diğeri(diğeri)+Pron+A3sg+P2pl(niz[niz])')
self.assert_defined_path(
u'diğerleri', PRON, None, u'diğerleri(diğerleri)+Pron+A3sg+P3pl',
u'diğerleri(diğerleri)+Pron+A3sg+P1pl(miz[miz])',
u'diğerleri(diğerleri)+Pron+A3sg+P2pl(niz[niz])')
def test_should_have_paths_for_irregular_pronouns(self):
parser_logger.setLevel(logging.DEBUG)
suffix_applier_logger.setLevel(logging.DEBUG)
self.predefined_paths._create_predefined_path_of_herkes()
self.morpheme_container_map = self.predefined_paths._morpheme_container_map
PRON = SyntacticCategory.PRONOUN
self.assert_defined_path(u'herkes', PRON, None,
u'herkes(herkes)+Pron+A3sg+Pnon')
def test_should_have_paths_for_pronouns_bura_sura_ora(self):
parser_logger.setLevel(logging.DEBUG)
suffix_applier_logger.setLevel(logging.DEBUG)
self.predefined_paths._create_predefined_path_of_ora_bura_sura_nere()
self.morpheme_container_map = self.predefined_paths._morpheme_container_map
PRON = SyntacticCategory.PRONOUN
self.assert_defined_path(u'or', PRON, None,
u'or(ora)+Pron+A3sg+Pnon+Loc(da[da])',
u'or(ora)+Pron+A3sg+Pnon+Abl(dan[dan])')
self.assert_defined_path(u'bur', PRON, None,
u'bur(bura)+Pron+A3sg+Pnon+Loc(da[da])',
u'bur(bura)+Pron+A3sg+Pnon+Abl(dan[dan])')
self.assert_defined_path(u'şur', PRON, None,
u'şur(şura)+Pron+A3sg+Pnon+Loc(da[da])',
u'şur(şura)+Pron+A3sg+Pnon+Abl(dan[dan])')
self.assert_defined_path(
u'ner', PRON, SecondarySyntacticCategory.QUESTION,
u'ner(nere)+Pron+Ques+A3sg+Pnon+Loc(de[de])',
u'ner(nere)+Pron+Ques+A3sg+Pnon+Abl(den[den])')
def test_should_have_paths_for_iceri_disari(self):
parser_logger.setLevel(logging.DEBUG)
suffix_applier_logger.setLevel(logging.DEBUG)
self.predefined_paths._create_predefined_path_of_iceri_disari()
self.morpheme_container_map = self.predefined_paths._morpheme_container_map
NOUN = SyntacticCategory.NOUN
self.assert_defined_path(
u'içer', NOUN, None,
u'i\xe7er(i\xe7eri)+Noun+A3sg+Pnon+Loc(de[de])',
u'i\xe7er(i\xe7eri)+Noun+A3sg+Pnon+Abl(den[den])',
u'i\xe7er(i\xe7eri)+Noun+A3sg+P3sg(si[si])')
self.assert_defined_path(
u'dışar', NOUN, None,
u'd\u0131\u015far(d\u0131\u015far\u0131)+Noun+A3sg+Pnon+Loc(da[da])',
u'd\u0131\u015far(d\u0131\u015far\u0131)+Noun+A3sg+Pnon+Abl(dan[dan])',
u'd\u0131\u015far(d\u0131\u015far\u0131)+Noun+A3sg+P3sg(s\u0131[s\u0131])'
)
def assert_defined_path(self, root, syntactic_category,
secondary_syntactic_category, *args):
assert_that(
self.predefined_morpheme_containers(root, syntactic_category,
secondary_syntactic_category),
AreMorphemeContainersMatch([a for a in args]))
def predefined_morpheme_containers(self, root_str, syntactic_category,
secondary_syntactic_category):
predefined_morpheme_containers = []
for root in self.morpheme_container_map.keys():
if root.str == root_str and root.lexeme.syntactic_category == syntactic_category and root.lexeme.secondary_syntactic_category == secondary_syntactic_category:
predefined_morpheme_containers.extend(
self.morpheme_container_map[root])
return [
formatter.format_morpheme_container_for_tests(r)
for r in predefined_morpheme_containers
]
