# -*- coding: utf-8 -*-
"""
Convert digits
"""
_arabic_thai = {
"0": "๐",
"1": "๑",
"2": "๒",
"3": "๓",
"4": "๔",
"5": "๕",
"6": "๖",
"7": "๗",
"8": "๘",
"9": "๙",
}
_thai_arabic = {
"๐": "0",
"๑": "1",
"๒": "2",
"๓": "3",
"๔": "4",
"๕": "5",
"๖": "6",
"๗": "7",
"๘": "8",
"๙": "9",
}
_digit_spell = {
"0": "ศูนย์",
"1": "หนึ่ง",
"2": "สอง",
"3": "สาม",
"4": "สี่",
"5": "ห้า",
"6": "หก",
"7": "เจ็ด",
"8": "แปด",
"9": "เก้า",
}
_spell_digit = {
"ศูนย์": "0",
"หนึ่ง": "1",
"สอง": "2",
"สาม": "3",
"สี่": "4",
"ห้า": "5",
"หก": "6",
"เจ็ด": "7",
"แปด": "8",
"เก้า": "9",
}
_arabic_thai_translate_table = str.maketrans(_arabic_thai)
_thai_arabic_translate_table = str.maketrans(_thai_arabic)
_digit_spell_translate_table = str.maketrans(_digit_spell)
[docs]def thai_digit_to_arabic_digit(text: str) -> str:
"""
This function convert Thai digits (i.e. ๑, ๓, ๑๐) to Arabic digits
(i.e. 1, 3, 10).
:param str text: Text with Thai digits such as '๑', '๒', '๓'
:return: Text with Thai digits being converted to Arabic digits
such as '1', '2', '3'
:rtype: str
:Example:
::
from pythainlp.util import thai_digit_to_arabic_digit
text = 'เป็นจำนวน ๑๒๓,๔๐๐.๒๕ บาท'
thai_digit_to_arabic_digit(text)
# output: เป็นจำนวน 123,400.25 บาท
"""
if not text or not isinstance(text, str):
return ""
return text.translate(_thai_arabic_translate_table)
[docs]def arabic_digit_to_thai_digit(text: str) -> str:
"""
This function convert Arabic digits (i.e. 1, 3, 10) to Thai digits
(i.e. ๑, ๓, ๑๐).
:param str text: Text with Arabic digits such as '1', '2', '3'
:return: Text with Arabic digits being converted to Thai digits
such as '๑', '๒', '๓'
:rtype: str
:Example:
::
from pythainlp.util import arabic_digit_to_thai_digit
text = 'เป็นจำนวน 123,400.25 บาท'
arabic_digit_to_thai_digit(text)
# output: เป็นจำนวน ๑๒๓,๔๐๐.๒๕ บาท
"""
if not text or not isinstance(text, str):
return ""
# Convert Arabic to Thai numerals
return text.translate(_arabic_thai_translate_table)
[docs]def digit_to_text(text: str) -> str:
"""
:param str text: Text with digits such as '1', '2', '๓', '๔'
:return: Text with digits being spelled out in Thai
"""
if not text or not isinstance(text, str):
return ""
# Convert Thai numerals to Arabic
text = text.translate(_thai_arabic_translate_table)
# Spell out Arabic numerals in Thai text
text = text.translate(_digit_spell_translate_table)
return text
[docs]def text_to_arabic_digit(text: str) -> str:
"""
This function convert Thai spelled out digits to Arabic digits.
:param text: A digit spelled out in Thai
:return: An Arabic digit such as '1', '2', '3' if the text is
Thai digit spelled out (ศูนย์, หนึ่ง, สอง, ..., เก้า).
Otherwise, it returns an empty string.
:rtype: str
:Example:
::
from pythainlp.util import text_to_arabic_digit
text_to_arabic_digit("ศูนย์")
# output: 0
text_to_arabic_digit("หนึ่ง")
# output: 1
text_to_arabic_digit("แปด")
# output: 8
text_to_arabic_digit("เก้า")
# output: 9
# For text that is not Thai digit spelled out
text_to_arabic_digit("สิบ") == ""
# output: True
text_to_arabic_digit("เก้าร้อย") == ""
# output: True
"""
if not text or text not in _spell_digit:
return ""
return _spell_digit[text]
[docs]def text_to_thai_digit(text: str) -> str:
"""
This function convert Thai spelled out digits to Thai digits.
:param text: A digit spelled out in Thai
:return: A Thai digit such as '๑', '๒', '๓' if the text is Thai digit
spelled out (ศูนย์, หนึ่ง, สอง, ..., เก้า).
Otherwise, it returns an empty string.
:rtype: str
:Example:
::
from pythainlp.util import text_to_thai_digit
text_to_thai_digit("ศูนย์")
# output: ๐
text_to_thai_digit("หนึ่ง")
# output: ๑
text_to_thai_digit("แปด")
# output: ๘
text_to_thai_digit("เก้า")
# output: ๙
# For text that is not Thai digit spelled out
text_to_thai_digit("สิบ") == ""
# output: True
text_to_thai_digit("เก้าร้อย") == ""
# output: True
"""
return arabic_digit_to_thai_digit(text_to_arabic_digit(text))