4699361508

Build Type

push

github

Committed by GitHub

Commit Message

Merge pull request #789 from PyThaiNLP/4.0

Run Details

22 of 22 new or added lines in 6 files covered. (100.0%)

5749 of 6246 relevant lines covered (92.04%)

0.92 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

93.33

/pythainlp/tokenize/tltk.py

# -*- coding: utf-8 -*-
# Copyright (C) 2016-2023 PyThaiNLP Project
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# 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.
from typing import List
try:
    from tltk.nlp import word_segment as tltk_segment
    from tltk.nlp import syl_segment
except ImportError:
    raise ImportError("Not found tltk! Please install tltk by pip install tltk")


def segment(text: str) -> List[str]:
    if not text or not isinstance(text, str):
        return []
    text = text.replace(" ", "<u/>")
    _temp = tltk_segment(text).replace("<u/>", " ").replace("<s/>", "")
    _temp = _temp.split("|")
    if _temp[-1] == "":
        del _temp[-1]
    return _temp


def syllable_tokenize(text: str) -> List[str]:
    if not text or not isinstance(text, str):
        return []
    _temp = syl_segment(text)
    _temp = _temp.split("~")
    if _temp[-1] == "<s/>":
        del _temp[-1]
    return _temp


def sent_tokenize(text: str) -> List[str]:
    text = text.replace(" ", "<u/>")
    _temp = tltk_segment(text).replace("<u/>", " ").replace("|", "")
    _temp = _temp.split("<s/>")
    if _temp[-1] == "":
        del _temp[-1]
    return _temp

1	# -- coding: utf-8 --
2	# Copyright (C) 2016-2023 PyThaiNLP Project
3	#
4	# Licensed under the Apache License, Version 2.0 (the "License");
5	# you may not use this file except in compliance with the License.
6	# You may obtain a copy of the License at
7	#
8	# http://www.apache.org/licenses/LICENSE-2.0
9	#
10	# Unless required by applicable law or agreed to in writing, software
11	# distributed under the License is distributed on an "AS IS" BASIS,
12	# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13	# See the License for the specific language governing permissions and
14	# limitations under the License.
15	from typing import List	1✔
16	try:	1✔
17	from tltk.nlp import word_segment as tltk_segment	1✔
18	from tltk.nlp import syl_segment	1✔
19	except ImportError:	×
20	raise ImportError("Not found tltk! Please install tltk by pip install tltk")	×
21
22
23	def segment(text: str) -> List[str]:	1✔
24	if not text or not isinstance(text, str):	1✔
25	return []	1✔
26	text = text.replace(" ", "<u/>")	1✔
27	_temp = tltk_segment(text).replace("<u/>", " ").replace("<s/>", "")	1✔
28	_temp = _temp.split("\|")	1✔
29	if _temp[-1] == "":	1✔
30	del _temp[-1]	1✔
31	return _temp	1✔
32
33
34	def syllable_tokenize(text: str) -> List[str]:	1✔
35	if not text or not isinstance(text, str):	1✔
36	return []	1✔
37	_temp = syl_segment(text)	1✔
38	_temp = _temp.split("~")	1✔
39	if _temp[-1] == "<s/>":	1✔
40	del _temp[-1]	1✔
41	return _temp	1✔
42
43
44	def sent_tokenize(text: str) -> List[str]:	1✔
45	text = text.replace(" ", "<u/>")	1✔
46	_temp = tltk_segment(text).replace("<u/>", " ").replace("\|", "")	1✔
47	_temp = _temp.split("<s/>")	1✔
48	if _temp[-1] == "":	1✔
49	del _temp[-1]	1✔
50	return _temp	1✔

PyThaiNLP / pythainlp / 4699361508

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous