11625814262

Committed 01 Nov 2024 07:14AM UTC coverage: 20.782% (+20.8%) from 0.0%

Build # 11625814262

Build Type

Pull #952

github

Committed by

web-flow

Commit Message

Merge c8385dcae into 515fe7ced

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

Run Details

45 of 80 new or added lines in 48 files covered. (56.25%)

1537 of 7396 relevant lines covered (20.78%)

0.21 hits per line

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

0.0

/pythainlp/tokenize/nlpo3.py

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

from nlpo3 import load_dict as nlpo3_load_dict
from nlpo3 import segment as nlpo3_segment

from pythainlp.corpus import path_pythainlp_corpus
from pythainlp.corpus.common import _THAI_WORDS_FILENAME

_NLPO3_DEFAULT_DICT_NAME = "_67a47bf9"
_NLPO3_DEFAULT_DICT = nlpo3_load_dict(
    path_pythainlp_corpus(_THAI_WORDS_FILENAME), _NLPO3_DEFAULT_DICT_NAME
)


def load_dict(file_path: str, dict_name: str) -> bool:
    """Load a dictionary file into an in-memory dictionary collection.

    The loaded dictionary will be accessible through the assigned dict_name.
    *** This function does not override an existing dict name. ***

    :param file_path: Path to a dictionary file
    :type file_path: str
    :param dict_name: A unique dictionary name, used for reference.
    :type dict_name: str
    :return bool

    :See Also:
        * \
            https://github.com/PyThaiNLP/nlpo3
    """
    msg, success = nlpo3_load_dict(file_path=file_path, dict_name=dict_name)
    if bool is False:
        print(msg, file=stderr)
    return success


def segment(
    text: str,
    custom_dict: str = _NLPO3_DEFAULT_DICT_NAME,
    safe_mode: bool = False,
    parallel_mode: bool = False,
) -> List[str]:
    """Break text into tokens.

    Python binding for nlpO3. It is newmm engine in Rust.

    :param str text: text to be tokenized
    :param str custom_dict: dictionary name, as assigned with load_dict(),\
        defaults to pythainlp/corpus/common/words_th.txt
    :param bool safe_mode: reduce chance for long processing time for long text\
        with many ambiguous breaking points, defaults to False
    :param bool parallel_mode: Use multithread mode, defaults to False

    :return: list of tokens
    :rtype: List[str]

    :See Also:
        * \
            https://github.com/PyThaiNLP/nlpo3
    """
    return nlpo3_segment(
        text=text,
        dict_name=custom_dict,
        safe=safe_mode,
        parallel=parallel_mode,
    )

1	# -- coding: utf-8 --
2	# SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
3	# SPDX-License-Identifier: Apache-2.0
4	from sys import stderr	×
5	from typing import List	×
6
7	from nlpo3 import load_dict as nlpo3_load_dict	×
NEW 8	from nlpo3 import segment as nlpo3_segment	×
9
10	from pythainlp.corpus import path_pythainlp_corpus	×
NEW 11	from pythainlp.corpus.common import _THAI_WORDS_FILENAME	×
12
13	_NLPO3_DEFAULT_DICT_NAME = "_67a47bf9"	×
14	_NLPO3_DEFAULT_DICT = nlpo3_load_dict(	×
15	path_pythainlp_corpus(_THAI_WORDS_FILENAME), _NLPO3_DEFAULT_DICT_NAME
16	)
17
18
19	def load_dict(file_path: str, dict_name: str) -> bool:	×
20	"""Load a dictionary file into an in-memory dictionary collection.
21
22	The loaded dictionary will be accessible through the assigned dict_name.
23	* This function does not override an existing dict name. *
24
25	:param file_path: Path to a dictionary file
26	:type file_path: str
27	:param dict_name: A unique dictionary name, used for reference.
28	:type dict_name: str
29	:return bool
30
31	:See Also:
32	* \
33	https://github.com/PyThaiNLP/nlpo3
34	"""
35	msg, success = nlpo3_load_dict(file_path=file_path, dict_name=dict_name)	×
36	if bool is False:	×
37	print(msg, file=stderr)	×
38	return success	×
39
40
41	def segment(	×
42	text: str,
43	custom_dict: str = _NLPO3_DEFAULT_DICT_NAME,
44	safe_mode: bool = False,
45	parallel_mode: bool = False,
46	) -> List[str]:
47	"""Break text into tokens.
48
49	Python binding for nlpO3. It is newmm engine in Rust.
50
51	:param str text: text to be tokenized
52	:param str custom_dict: dictionary name, as assigned with load_dict(),\
53	defaults to pythainlp/corpus/common/words_th.txt
54	:param bool safe_mode: reduce chance for long processing time for long text\
55	with many ambiguous breaking points, defaults to False
56	:param bool parallel_mode: Use multithread mode, defaults to False
57
58	:return: list of tokens
59	:rtype: List[str]
60
61	:See Also:
62	* \
63	https://github.com/PyThaiNLP/nlpo3
64	"""
65	return nlpo3_segment(	×
66	text=text,
67	dict_name=custom_dict,
68	safe=safe_mode,
69	parallel=parallel_mode,
70	)

PyThaiNLP / pythainlp / 11625814262

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