def test_str_includes_node_finality(self):
non_final = TokenSet()
final = TokenSet()
other_final = TokenSet()
final.final = True
other_final.final = True
assert str(non_final) != str(final)
assert str(other_final) == str(final)
def test_str_includes_all_edges(self):
zero_edges = TokenSet()
one_edge = TokenSet()
two_edges = TokenSet()
one_edge.edges["a"] = 1
two_edges.edges["a"] = 1
two_edges.edges["b"] = 1
assert str(zero_edges) != str(one_edge)
assert str(two_edges) != str(one_edge)
assert str(two_edges) != str(zero_edges)
def test_str_includes_edge_id(self):
child_a = TokenSet()
child_b = TokenSet()
parent_a = TokenSet()
parent_b = TokenSet()
parent_c = TokenSet()
parent_a.edges["a"] = child_a
parent_b.edges["a"] = child_b
parent_c.edges["a"] = child_b
assert str(parent_b) == str(parent_c)
assert str(parent_a) != str(parent_c)
assert str(parent_a) != str(parent_b)
def insert(self, word):
if word < self.previous_word:
raise BaseLunrException("Out of order word insertion")
common_prefix = 0
for i in range(min(len(word), len(self.previous_word))):
if word[i] != self.previous_word[i]:
break
common_prefix += 1
self.minimize(common_prefix)
node = (self.root if not self.unchecked_nodes else
self.unchecked_nodes[-1]["child"])
for i in range(common_prefix, len(word)):
next_node = TokenSet()
char = word[i]
node.edges[char] = next_node
self.unchecked_nodes.append({
"parent": node,
"char": char,
"child": next_node
})
node = next_node
node.final = True
self.previous_word = word
def __init__(self):
self.previous_word = ""
self.root = TokenSet()
self.unchecked_nodes = []
self.minimized_nodes = {}
