def test_registers_escape():
graph = nfa.Nfa()
construction = c.ConstructionState(graph, '\\', accept)
construction._set_up()
construction._perform_step(0)
assert graph.starts == []
assert construction.escape_next
def test_alternation_left_kleene():
graph = nfa.Nfa()
construction = const.ConstructionState(graph, 'a*|b|c', accept)
construction.construct()
graph.remove_empty_transitions()
dfa_graph = conv.NfaToDfaConverter(graph).start_conversion()
res = list(dfa_graph.search(''))
assert len(res) == 1
assert res[0][0] == accept
res = list(dfa_graph.search('aaaaa'))
assert len(res) == 1
assert res[0][0] == accept
res = list(dfa_graph.search('c'))
assert len(res) == 1
assert res[0][0] == accept
res = list(dfa_graph.search('b'))
assert len(res) == 1
assert res[0][0] == accept
res = list(dfa_graph.search('bb'))
assert len(res) == 0
res = list(dfa_graph.search('cc'))
assert len(res) == 0
res = list(dfa_graph.search('ac'))
assert len(res) == 0
def test_handles_multiple_alternations():
graph = nfa.Nfa()
construction = c.ConstructionState(graph, 'a|b|c', accept)
construction.construct()
assert graph.starts == [0]
assert graph.states[-1].accepts == [accept]
assert graph.states[-2].accepts == [accept]
assert graph.states[-3].accepts == [accept]
def test_handles_escaped_symbol(mocker):
graph = nfa.Nfa()
construction = c.ConstructionState(graph, '?', accept)
construction._set_up()
assert graph.starts == []
construction.escape_next = True
spy = mocker.spy(construction, "_process_symbol")
construction._perform_step(0)
spy.assert_called_once_with('?')
def test_adds_acceptance():
graph = nfa.Nfa()
construction = c.ConstructionState(graph, "a|b", accept)
construction.construct()
assert graph.starts == [0]
assert graph.states[-1].accepts == [accept]
assert graph.states[-2].accepts == [accept]
assert graph.states[3].non_word_char_transitions == {7}
assert graph.states[5].non_word_char_transitions == {6}
assert graph.states[1].non_word_char_transitions == set()
assert graph.states[1].empty_transitions == {2, 4}
def _init(self):
all_deprecated = set(t.extract_deprecated(self.graph))
concepts = set(
t.extract_by_type_uri(self.graph,
self.concept_type_uri,
remove=all_deprecated))
thesauri = set(
t.extract_by_type_uri(self.graph,
self.sub_thesaurus_type_uri,
remove=all_deprecated))
self.concept_map_ = dict(zip(map(str, concepts), range(len(concepts))))
thesaurus_features = ThesaurusFeatureTransformation(
self.graph, concepts, thesauri, self.thesaurus_relation_type_uri,
self.thesaurus_relation_is_specialisation)
labels = t.retrieve_concept_labels(self.graph,
allowed=concepts,
langs=self.langs)
nfautomat = nfa.Nfa()
if self.handle_title_case:
case_handler = case_handlers.title_case_handler
else:
case_handler = case_handlers.sentence_case_handler
expansion_funs = expansion.collect_expansion_functions(
extract_upper_case_from_braces=self.extract_upper_case_from_braces,
extract_any_case_from_braces=self.extract_any_case_from_braces,
expand_ampersand_with_spaces=self.expand_ampersand_with_spaces,
expand_abbreviation_with_punctuation=(
self.expand_abbreviation_with_punctuation),
)
if self.simple_english_plural_rules:
plural_fun = expansion.simple_english_plural_fun
else:
def plural_fun(x):
return x
for concept, label in labels:
expanded = label
for f in expansion_funs:
expanded = f(expanded)
_handle_construction(
construction.ConstructionState(
nfautomat, plural_fun(case_handler(expanded)),
str(concept)), concept, label)
nfautomat.remove_empty_transitions()
converter = conversion.NfaToDfaConverter(nfautomat)
self.dfa_ = converter.start_conversion()
self.pipeline_ = Pipeline([
("Combined Features",
ColumnTransformer([("Thesaurus Features", thesaurus_features, 0),
("Text Features", mk_text_features(), 1)])),
("Classifier",
DecisionTreeClassifier(min_samples_leaf=25, max_leaf_nodes=100))
])
def epsilon_tree():
graph = nfa.Nfa()
for _ in range(17):
graph.add_state()
for i in range(8):
graph.add_empty_transition(i, 2*i+1)
graph.add_empty_transition(i, 2*i+2)
graph.add_symbol_transition(i, 2*i+1, symbol0)
graph.add_symbol_transition(i, 2*i+2, symbol0)
graph.add_non_word_char_transition(i, 2*i+1)
graph.add_non_word_char_transition(i, 2*i+2)
return graph
def test_init_with_empty_graph():
graph = nfa.Nfa()
construction = c.ConstructionState(graph, expression, accept)
construction._set_up()
assert len(graph.states) == 3
assert graph.starts == []
assert graph.states[0].non_word_char_transitions == {1}
assert graph.states[1].empty_transitions == {2}
assert construction.append_to == [2]
assert construction.expression == expression
assert construction.before_braces == [[1], [2]]
assert construction.dangling_alternations.stack == []
assert not construction.escape_next
assert construction.accept == accept
def regression_test_graph():
automaton = nfa.Nfa()
concept_tuples = [
(label_global, id_global),
(label_economic, id_economic),
(label_crisis, id_crisis),
(label_global_economic, id_global_economic),
(label_economic_crisis, id_economic_crisis),
(label_global_economic_crisis, id_global_economic_crisis),
]
for label, concept_id in concept_tuples:
const.ConstructionState(automaton, label, concept_id).construct()
automaton.remove_empty_transitions()
dfa = conv.NfaToDfaConverter(automaton).start_conversion()
return dfa
def input_graph():
graph = nfa.Nfa()
for _ in range(6):
graph.add_state()
graph.add_start(0)
graph.add_start(1)
graph.add_symbol_transition(0, 2, symbol0)
graph.add_symbol_transition(1, 0, symbol0)
graph.add_symbol_transition(0, 3, symbol1)
graph.add_symbol_transition(1, 3, symbol1)
graph.add_symbol_transition(2, 4, symbol0)
graph.add_symbol_transition(4, 5, symbol1)
graph.add_non_word_char_transition(1, 5)
graph.add_acceptance(5, accept)
return graph
def two_state_graph():
graph = nfa.Nfa()
graph.add_state()
graph.add_state()
return graph