#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import math
try:
import property
except ModuleNotFoundError:
from util import property
SENTENCE_BREAK_PROPERTY = "data/ucd/auxiliary/SentenceBreakProperty.txt"
code_props = property.read(SENTENCE_BREAK_PROPERTY)
for i in range(len(code_props)):
if code_props[i] is None:
code_props[i] = 'Other'
prop_names = set(code_props)
prop_names.remove('Other')
prop_vals = {}
prop_vals['Other'] = 0
for p in sorted(prop_names):
prop_vals[p] = len(prop_vals)
# compatibility decompositions
import math
try:
import property
import unicode_data
except ModuleNotFoundError:
from util import property
from util import unicode_data
WORD_BREAK_PROPERTY = "data/ucd/auxiliary/WordBreakProperty.txt"
PROP_LIST = "data/ucd/PropList.txt"
DERIVED_CORE_PROPERTIES = "data/ucd/DerivedCoreProperties.txt"
code_props = property.read(WORD_BREAK_PROPERTY)
word_break_property = property.read(WORD_BREAK_PROPERTY, sets=True)
prop_list = property.read(PROP_LIST, sets=True)
white_space = prop_list['White_Space']
derived_core_properties = property.read(DERIVED_CORE_PROPERTIES, sets=True)
default_ignorable = derived_core_properties['Default_Ignorable_Code_Point']
for code in range(len(unicode_data.uchars)):
u = unicode_data.uchars[code]
if u is None or u.decomp is None:
continue
d = unicode_data.decompose(code)
if d is None:
continue
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import math
try:
import property
except ModuleNotFoundError:
from util import property
EMOJI_DATA = "data/ucd/emoji/emoji-data.txt"
GRAPHEME_BREAK_PROPERTY = "data/ucd/auxiliary/GraphemeBreakProperty.txt"
code_props = property.read(GRAPHEME_BREAK_PROPERTY)
emoji_props = property.read(EMOJI_DATA, sets=True)
for i in range(len(code_props)):
if code_props[i] is None:
code_props[i] = 'Other'
for i in emoji_props['Extended_Pictographic']:
assert code_props[i] == 'Other'
code_props[i] = 'Extended_Pictographic'
prop_names = set(code_props)
prop_names.remove('Other')
prop_vals = {}
prop_vals['Other'] = 0