11626163864

Committed 01 Nov 2024 07:49AM UTC coverage: 14.17% (+14.2%) from 0.0%

Build # 11626163864

Build Type

Pull #952

github

Committed by

web-flow

Commit Message

Merge 8f2551bc9 into 89ea62ebc

Pull Request Pull Request #952: Specify a limited test suite

Run Details

44 of 80 new or added lines in 48 files covered. (55.0%)

1048 of 7396 relevant lines covered (14.17%)

0.14 hits per line

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

0.0

/pythainlp/tokenize/tltk.py

# -*- coding: utf-8 -*-
# SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
# SPDX-License-Identifier: Apache-2.0
from typing import List

try:
    from tltk.nlp import syl_segment
    from tltk.nlp import word_segment as tltk_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	# SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
3	# SPDX-License-Identifier: Apache-2.0
4	from typing import List	×
5
6	try:	×
7	from tltk.nlp import syl_segment	×
NEW 8	from tltk.nlp import word_segment as tltk_segment	×
9	except ImportError:	×
10	raise ImportError("Not found tltk! Please install tltk by pip install tltk")	×
11
12
13	def segment(text: str) -> List[str]:	×
14	if not text or not isinstance(text, str):	×
15	return []	×
16	text = text.replace(" ", "<u/>")	×
17	_temp = tltk_segment(text).replace("<u/>", " ").replace("<s/>", "")	×
18	_temp = _temp.split("\|")	×
19	if _temp[-1] == "":	×
20	del _temp[-1]	×
21	return _temp	×
22
23
24	def syllable_tokenize(text: str) -> List[str]:	×
25	if not text or not isinstance(text, str):	×
26	return []	×
27	_temp = syl_segment(text)	×
28	_temp = _temp.split("~")	×
29	if _temp[-1] == "<s/>":	×
30	del _temp[-1]	×
31	return _temp	×
32
33
34	def sent_tokenize(text: str) -> List[str]:	×
35	text = text.replace(" ", "<u/>")	×
36	_temp = tltk_segment(text).replace("<u/>", " ").replace("\|", "")	×
37	_temp = _temp.split("<s/>")	×
38	if _temp[-1] == "":	×
39	del _temp[-1]	×
40	return _temp	×

PyThaiNLP / pythainlp / 11626163864

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