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

23.53

/pythainlp/util/thai.py

# -*- coding: utf-8 -*-
# SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
# SPDX-License-Identifier: Apache-2.0
"""
Check if it is Thai text
"""

import string
from typing import Tuple

from pythainlp import (
    thai_above_vowels,
    thai_below_vowels,
    thai_consonants,
    thai_digits,
    thai_follow_vowels,
    thai_lead_vowels,
    thai_punctuations,
    thai_signs,
    thai_tonemarks,
    thai_vowels,
)

_DEFAULT_IGNORE_CHARS = string.whitespace + string.digits + string.punctuation
_TH_FIRST_CHAR_ASCII = 3584
_TH_LAST_CHAR_ASCII = 3711


def isthaichar(ch: str) -> bool:
    """Check if a character is a Thai character.

    :param ch: input character
    :type ch: str
    :return: True if ch is a Thai character, otherwise False.
    :rtype: bool

    :Example:
    ::

        from pythainlp.util import isthaichar

        isthaichar("ก")  # THAI CHARACTER KO KAI
        # output: True

        isthaichar("๕")  # THAI DIGIT FIVE
        # output: True
    """
    ch_val = ord(ch)
    if _TH_FIRST_CHAR_ASCII <= ch_val <= _TH_LAST_CHAR_ASCII:
        return True
    return False


def isthai(text: str, ignore_chars: str = ".") -> bool:
    """Check if every character in a string is a Thai character.

    :param text: input text
    :type text: str
    :param ignore_chars: characters to be ignored, defaults to "."
    :type ignore_chars: str, optional
    :return: True if every character in the input string is Thai,
             otherwise False.
    :rtype: bool

    :Example:
    ::

        from pythainlp.util import isthai

        isthai("กาลเวลา")
        # output: True

        isthai("กาลเวลา.")
        # output: True

        isthai("กาล-เวลา")
        # output: False

        isthai("กาล-เวลา +66", ignore_chars="01234567890+-.,")
        # output: True

    """
    if not ignore_chars:
        ignore_chars = ""

    for ch in text:
        if ch not in ignore_chars and not isthaichar(ch):
            return False
    return True


def countthai(text: str, ignore_chars: str = _DEFAULT_IGNORE_CHARS) -> float:
    """Find proportion of Thai characters in a given text

    :param text: input text
    :type text: str
    :param ignore_chars: characters to be ignored, defaults to whitespace,\\
        digits, and punctuation marks.
    :type ignore_chars: str, optional
    :return: proportion of Thai characters in the text (percentage)
    :rtype: float

    :Example:
    ::

        from pythainlp.util import countthai

        countthai("ไทยเอ็นแอลพี 3.0")
        # output: 100.0

        countthai("PyThaiNLP 3.0")
        # output: 0.0

        countthai("ใช้งาน PyThaiNLP 3.0")
        # output: 40.0

        countthai("ใช้งาน PyThaiNLP 3.0", ignore_chars="")
        # output: 30.0
    """
    if not text or not isinstance(text, str):
        return 0.0

    if not ignore_chars:
        ignore_chars = ""

    num_thai = 0
    num_ignore = 0

    for ch in text:
        if ch in ignore_chars:
            num_ignore += 1
        elif isthaichar(ch):
            num_thai += 1

    num_count = len(text) - num_ignore

    if num_count == 0:
        return 0.0

    return (num_thai / num_count) * 100


def display_thai_char(ch: str) -> str:
    """Prefix an underscore (_) to a high-position vowel or a tone mark,
    to ease readability.

    :param ch: input character
    :type ch: str
    :return: "_" + ch
    :rtype: str

    :Example:
    ::

        from pythainlp.util import display_thai_char

        display_thai_char("้")
        # output: "_้"
    """

    if (
        ch in thai_above_vowels
        or ch in thai_tonemarks
        or ch in "\u0e33\u0e4c\u0e4d\u0e4e"
    ):
        # last condition is Sra Aum, Thanthakhat, Nikhahit, Yamakkan
        return "_" + ch
    else:
        return ch


def thai_word_tone_detector(word: str) -> Tuple[str, str]:
    """
    Thai tone detector for word.

    It uses pythainlp.transliterate.pronunciate for converting word to\
        pronunciation.

    :param str word: Thai word.
    :return: Thai pronunciation with tones in each syllable.\
        (l, m, h, r, f or empty if it cannot be detected)
    :rtype: Tuple[str, str]

    :Example:
    ::

        from pythainlp.util import thai_word_tone_detector

        print(thai_word_tone_detector("คนดี"))
        # output: [('คน', 'm'), ('ดี', 'm')]

        print(thai_word_tone_detector("มือถือ"))
        # output: [('มือ', 'm'), ('ถือ', 'r')]
    """
    from ..transliterate import pronunciate
    from ..util.syllable import tone_detector

    _pronunciate = pronunciate(word).split("-")
    return [(i, tone_detector(i.replace("หฺ", "ห"))) for i in _pronunciate]


def count_thai_chars(text: str) -> dict:
    """
    Count Thai characters by type

    This function will give you numbers of Thai characters by type\
        (consonants, vowels, lead_vowels, follow_vowels, above_vowels,\
        below_vowels, tonemarks, signs, thai_digits, punctuations, non_thai)

    :param str text: Text
    :return: Dict with numbers of Thai characters by type
    :rtype: dict

    :Example:
    ::

        from pythainlp.util import count_thai_chars

        count_thai_chars("ทดสอบภาษาไทย")
        # output: {
        # 'vowels': 3,
        # 'lead_vowels': 1,
        # 'follow_vowels': 2,
        # 'above_vowels': 0,
        # 'below_vowels': 0,
        # 'consonants': 9,
        # 'tonemarks': 0,
        # 'signs': 0,
        # 'thai_digits': 0,
        # 'punctuations': 0,
        # 'non_thai': 0
        # }
    """
    _dict = {
        "vowels": 0,
        "lead_vowels": 0,
        "follow_vowels": 0,
        "above_vowels": 0,
        "below_vowels": 0,
        "consonants": 0,
        "tonemarks": 0,
        "signs": 0,
        "thai_digits": 0,
        "punctuations": 0,
        "non_thai": 0,
    }
    for c in text:
        if c in thai_vowels:
            _dict["vowels"] += 1
        if c in thai_lead_vowels:
            _dict["lead_vowels"] += 1
        elif c in thai_follow_vowels:
            _dict["follow_vowels"] += 1
        elif c in thai_above_vowels:
            _dict["above_vowels"] += 1
        elif c in thai_below_vowels:
            _dict["below_vowels"] += 1
        elif c in thai_consonants:
            _dict["consonants"] += 1
        elif c in thai_tonemarks:
            _dict["tonemarks"] += 1
        elif c in thai_signs:
            _dict["signs"] += 1
        elif c in thai_digits:
            _dict["thai_digits"] += 1
        elif c in thai_punctuations:
            _dict["punctuations"] += 1
        else:
            _dict["non_thai"] += 1
    return _dict

1	# -- coding: utf-8 --
2	# SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
3	# SPDX-License-Identifier: Apache-2.0
4	"""
5	Check if it is Thai text
6	"""
7
8	import string	1✔
9	from typing import Tuple	1✔
10
11	from pythainlp import (	1✔
12	thai_above_vowels,
13	thai_below_vowels,
14	thai_consonants,
15	thai_digits,
16	thai_follow_vowels,
17	thai_lead_vowels,
18	thai_punctuations,
19	thai_signs,
20	thai_tonemarks,
21	thai_vowels,
22	)
23
24	_DEFAULT_IGNORE_CHARS = string.whitespace + string.digits + string.punctuation	1✔
25	_TH_FIRST_CHAR_ASCII = 3584	1✔
26	_TH_LAST_CHAR_ASCII = 3711	1✔
27
28
29	def isthaichar(ch: str) -> bool:	1✔
30	"""Check if a character is a Thai character.
31
32	:param ch: input character
33	:type ch: str
34	:return: True if ch is a Thai character, otherwise False.
35	:rtype: bool
36
37	:Example:
38	::
39
40	from pythainlp.util import isthaichar
41
42	isthaichar("ก") # THAI CHARACTER KO KAI
43	# output: True
44
45	isthaichar("๕") # THAI DIGIT FIVE
46	# output: True
47	"""
48	ch_val = ord(ch)	1✔
49	if _TH_FIRST_CHAR_ASCII <= ch_val <= _TH_LAST_CHAR_ASCII:	1✔
50	return True	1✔
51	return False	1✔
52
53
54	def isthai(text: str, ignore_chars: str = ".") -> bool:	1✔
55	"""Check if every character in a string is a Thai character.
56
57	:param text: input text
58	:type text: str
59	:param ignore_chars: characters to be ignored, defaults to "."
60	:type ignore_chars: str, optional
61	:return: True if every character in the input string is Thai,
62	otherwise False.
63	:rtype: bool
64
65	:Example:
66	::
67
68	from pythainlp.util import isthai
69
70	isthai("กาลเวลา")
71	# output: True
72
73	isthai("กาลเวลา.")
74	# output: True
75
76	isthai("กาล-เวลา")
77	# output: False
78
79	isthai("กาล-เวลา +66", ignore_chars="01234567890+-.,")
80	# output: True
81
82	"""
83	if not ignore_chars:	×
84	ignore_chars = ""	×
85
86	for ch in text:	×
87	if ch not in ignore_chars and not isthaichar(ch):	×
88	return False	×
89	return True	×
90
91
92	def countthai(text: str, ignore_chars: str = _DEFAULT_IGNORE_CHARS) -> float:	1✔
93	"""Find proportion of Thai characters in a given text
94
95	:param text: input text
96	:type text: str
97	:param ignore_chars: characters to be ignored, defaults to whitespace,\\
98	digits, and punctuation marks.
99	:type ignore_chars: str, optional
100	:return: proportion of Thai characters in the text (percentage)
101	:rtype: float
102
103	:Example:
104	::
105
106	from pythainlp.util import countthai
107
108	countthai("ไทยเอ็นแอลพี 3.0")
109	# output: 100.0
110
111	countthai("PyThaiNLP 3.0")
112	# output: 0.0
113
114	countthai("ใช้งาน PyThaiNLP 3.0")
115	# output: 40.0
116
117	countthai("ใช้งาน PyThaiNLP 3.0", ignore_chars="")
118	# output: 30.0
119	"""
120	if not text or not isinstance(text, str):	×
121	return 0.0	×
122
123	if not ignore_chars:	×
124	ignore_chars = ""	×
125
126	num_thai = 0	×
127	num_ignore = 0	×
128
129	for ch in text:	×
130	if ch in ignore_chars:	×
131	num_ignore += 1	×
132	elif isthaichar(ch):	×
133	num_thai += 1	×
134
135	num_count = len(text) - num_ignore	×
136
137	if num_count == 0:	×
138	return 0.0	×
139
140	return (num_thai / num_count) * 100	×
141
142
143	def display_thai_char(ch: str) -> str:	1✔
144	"""Prefix an underscore (_) to a high-position vowel or a tone mark,
145	to ease readability.
146
147	:param ch: input character
148	:type ch: str
149	:return: "_" + ch
150	:rtype: str
151
152	:Example:
153	::
154
155	from pythainlp.util import display_thai_char
156
157	display_thai_char("้")
158	# output: "_้"
159	"""
160
161	if (	×
162	ch in thai_above_vowels
163	or ch in thai_tonemarks
164	or ch in "\u0e33\u0e4c\u0e4d\u0e4e"
165	):
166	# last condition is Sra Aum, Thanthakhat, Nikhahit, Yamakkan
167	return "_" + ch	×
168	else:
169	return ch	×
170
171
172	def thai_word_tone_detector(word: str) -> Tuple[str, str]:	1✔
173	"""
174	Thai tone detector for word.
175
176	It uses pythainlp.transliterate.pronunciate for converting word to\
177	pronunciation.
178
179	:param str word: Thai word.
180	:return: Thai pronunciation with tones in each syllable.\
181	(l, m, h, r, f or empty if it cannot be detected)
182	:rtype: Tuple[str, str]
183
184	:Example:
185	::
186
187	from pythainlp.util import thai_word_tone_detector
188
189	print(thai_word_tone_detector("คนดี"))
190	# output: [('คน', 'm'), ('ดี', 'm')]
191
192	print(thai_word_tone_detector("มือถือ"))
193	# output: [('มือ', 'm'), ('ถือ', 'r')]
194	"""
NEW 195	from ..transliterate import pronunciate	×
NEW 196	from ..util.syllable import tone_detector	×
197
198	_pronunciate = pronunciate(word).split("-")	×
199	return [(i, tone_detector(i.replace("หฺ", "ห"))) for i in _pronunciate]	×
200
201
202	def count_thai_chars(text: str) -> dict:	1✔
203	"""
204	Count Thai characters by type
205
206	This function will give you numbers of Thai characters by type\
207	(consonants, vowels, lead_vowels, follow_vowels, above_vowels,\
208	below_vowels, tonemarks, signs, thai_digits, punctuations, non_thai)
209
210	:param str text: Text
211	:return: Dict with numbers of Thai characters by type
212	:rtype: dict
213
214	:Example:
215	::
216
217	from pythainlp.util import count_thai_chars
218
219	count_thai_chars("ทดสอบภาษาไทย")
220	# output: {
221	# 'vowels': 3,
222	# 'lead_vowels': 1,
223	# 'follow_vowels': 2,
224	# 'above_vowels': 0,
225	# 'below_vowels': 0,
226	# 'consonants': 9,
227	# 'tonemarks': 0,
228	# 'signs': 0,
229	# 'thai_digits': 0,
230	# 'punctuations': 0,
231	# 'non_thai': 0
232	# }
233	"""
234	_dict = {	×
235	"vowels": 0,
236	"lead_vowels": 0,
237	"follow_vowels": 0,
238	"above_vowels": 0,
239	"below_vowels": 0,
240	"consonants": 0,
241	"tonemarks": 0,
242	"signs": 0,
243	"thai_digits": 0,
244	"punctuations": 0,
245	"non_thai": 0,
246	}
247	for c in text:	×
248	if c in thai_vowels:	×
249	_dict["vowels"] += 1	×
250	if c in thai_lead_vowels:	×
251	_dict["lead_vowels"] += 1	×
252	elif c in thai_follow_vowels:	×
253	_dict["follow_vowels"] += 1	×
254	elif c in thai_above_vowels:	×
255	_dict["above_vowels"] += 1	×
256	elif c in thai_below_vowels:	×
257	_dict["below_vowels"] += 1	×
258	elif c in thai_consonants:	×
259	_dict["consonants"] += 1	×
260	elif c in thai_tonemarks:	×
261	_dict["tonemarks"] += 1	×
262	elif c in thai_signs:	×
263	_dict["signs"] += 1	×
264	elif c in thai_digits:	×
265	_dict["thai_digits"] += 1	×
266	elif c in thai_punctuations:	×
267	_dict["punctuations"] += 1	×
268	else:
269	_dict["non_thai"] += 1	×
270	return _dict	×

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