def compare_nodes(ngrams, ref_trie, test_trie):
# compare root
compare_node([], ref_trie, test_trie)
# compare random node, may not existe (check exception)
compare_node([420001337] * 10, ref_trie, test_trie)
# compare all ngrams
for n in ngrams:
for i in range(len(n)):
compare_node(n[:i+1], ref_trie, test_trie)
# try a non-existent node: should raise exception in both case
compare_node(n[:i] + [420001337], ref_trie, test_trie)
compare_node(n + [420001337], ref_trie, test_trie) # try a non-existent node
def compare_nodes(ngrams, ref_trie, test_trie):
# compare root
compare_node([], ref_trie, test_trie)
# compare random node, may not existe (check exception)
compare_node([420001337] * 10, ref_trie, test_trie)
# compare all ngrams
for n in ngrams:
for i in range(len(n)):
compare_node(n[:i + 1], ref_trie, test_trie)
# try a non-existent node: should raise exception in both case
compare_node(n[:i] + [420001337], ref_trie, test_trie)
compare_node(n + [420001337], ref_trie,
test_trie) # try a non-existent node
def test_storage_random(storage, ref_class=PyMemoryStorage):
ref = ref_class(default_ngram_length=storage.default_ngram_length)
ref.clear()
storage.clear()
testfile = open("tests/fixtures/btree.txt").read().split("\n")
sentences = (re.findall(r"\w+", sentence) for sentence in testfile)
for sentence in sentences:
ref.add_sentence(sentence)
storage.add_sentence(sentence)
# compare of each ngram of each sentence
for sentence in sentences:
for start in range(len(sentence)):
for length in range(ngram_length):
ngram = sentence[start : start + length]
compare_node(ngram, ref, storage)
def test_storage_random(storage, ref_class=PyMemoryStorage):
ref = ref_class(default_ngram_length=storage.default_ngram_length)
ref.clear()
storage.clear()
testfile = open('tests/fixtures/btree.txt').read().split('\n')
sentences = (re.findall(r'\w+', sentence) for sentence in testfile)
for sentence in sentences:
ref.add_sentence(sentence)
storage.add_sentence(sentence)
# compare of each ngram of each sentence
for sentence in sentences:
for start in range(len(sentence)):
for length in range(ngram_length):
ngram = sentence[start:start+length]
compare_node(ngram, ref, storage)
