def test_unicode_tree_categories():
tree = charstree.unicode_tree()
expected = list(
set([
unicodedata.category(hunichr(i))
for i in range(0, sys.maxunicode + 1)
]))
actual = charstree.categories(tree)
assert sorted(expected) == sorted(actual)
def is_good(self, char):
if char in self.blacklist_characters:
return False
categories = charstree.categories(self.unicode_tree)
if unicodedata.category(char) not in categories:
return False
codepoint = ord(char)
return self.min_codepoint <= codepoint <= self.max_codepoint
def is_good(self, char):
if char in self.blacklist_characters:
return False
categories = charstree.categories(self.unicode_tree)
if unicodedata.category(char) not in categories:
return False
codepoint = ord(char)
return self.min_codepoint <= codepoint <= self.max_codepoint
def draw_parameter(self, random):
ascii_categories = charstree.categories(self.ascii_tree)
unicode_categories = charstree.categories(self.unicode_tree)
spaces_categories = charstree.categories(self.spaces_tree)
alphabet_size = 1 + dist.geometric(random, 0.1)
alphabet = []
buckets = 10
ascii_chance = random.randint(1, buckets)
if spaces_categories and ascii_chance < buckets:
space_chance = random.randint(1, buckets - ascii_chance)
else:
space_chance = 0
while len(alphabet) < alphabet_size:
choice = random.randint(1, buckets)
if ascii_categories and choice <= ascii_chance:
category = random.choice(ascii_categories)
tree = self.ascii_tree
elif spaces_categories and choice <= ascii_chance + space_chance:
category = random.choice(spaces_categories)
tree = self.spaces_tree
else:
category = random.choice(unicode_categories)
tree = self.unicode_tree
codepoint = charstree.random_codepoint(tree, category, random)
alphabet.append(hunichr(codepoint))
if u'\n' not in alphabet and not random.randint(0, 6):
if self.is_good(u'\n'):
alphabet.append(u'\n')
return tuple(alphabet)
def draw_parameter(self, random):
ascii_categories = charstree.categories(self.ascii_tree)
unicode_categories = charstree.categories(self.unicode_tree)
spaces_categories = charstree.categories(self.spaces_tree)
alphabet_size = 1 + dist.geometric(random, 0.1)
alphabet = []
buckets = 10
ascii_chance = random.randint(1, buckets)
if spaces_categories and ascii_chance < buckets:
space_chance = random.randint(1, buckets - ascii_chance)
else:
space_chance = 0
while len(alphabet) < alphabet_size:
choice = random.randint(1, buckets)
if ascii_categories and choice <= ascii_chance:
category = random.choice(ascii_categories)
tree = self.ascii_tree
elif spaces_categories and choice <= ascii_chance + space_chance:
category = random.choice(spaces_categories)
tree = self.spaces_tree
else:
category = random.choice(unicode_categories)
tree = self.unicode_tree
codepoint = charstree.random_codepoint(tree, category, random)
alphabet.append(hunichr(codepoint))
if u'\n' not in alphabet and not random.randint(0, 6):
if self.is_good(u'\n'):
alphabet.append(u'\n')
return tuple(alphabet)
def test_ascii_tree_categories():
tree = charstree.ascii_tree()
expected = list(
set([unicodedata.category(hunichr(i)) for i in range(0, 128)]))
actual = charstree.categories(tree)
assert sorted(expected) == sorted(actual)
