wanakana-python 1.0.3

A port of WanaKana, a JS library by Tofugu

ワナカナ <--> WanaKana <--> わなかな
Python utility library for detecting and transliterating Hiragana, Katakana, and Romaji

This library uses Semantic Versioning

See what this means here

Demo

Visit the website to see WanaKana in action.

Usage

Install

pip install wanakana-python

import wanakana
# or
from wanakana import to_kana, is_romaji

Documentation

Extended API reference (Note that function names are converted to snake_case)

Quick Reference

### TEXT CHECKING UTILITIES ###
wanakana.is_japanese('泣き虫。！〜２￥ｚｅｎｋａｋｕ')
# => True

wanakana.is_kana('あーア') # FIXME: returns False
# => True

wanakana.is_hiragana('すげー')
# => True

wanakana.is_katakana('ゲーム')
# => True

wanakana.is_kanji('切腹')
# => True
wanakana.is_kanji('勢い')
# => False

wanakana.is_romaji('Tōkyō and Ōsaka')
# => True

wanakana.to_kana('ONAJI buttsuuji')
# => 'オナジ ぶっつうじ'
wanakana.to_kana('座禅‘zazen’スタイル')
# => '座禅「ざぜん」スタイル'
wanakana.to_kana('batsuge-mu')
# => 'ばつげーむ'
wanakana.to_kana('wanakana', custom_kana_mapping={'na': 'に', 'ka': 'bana'}) # FIXME: custom_kana_mapping ignored
# => 'わにbanaに'

wanakana.to_hiragana('toukyou, オオサカ') # FIXME: does not convert kana
# => 'とうきょう、　おおさか'
wanakana.to_hiragana('only カナ', ignore_romaji=True)
# => 'only かな'
wanakana.to_hiragana('wi', use_obsolete_kana=True)
# => 'ゐ'

wanakana.to_katakana('toukyou, おおさか')
# => 'トウキョウ、　オオサカ'
wanakana.to_katakana('only かな', ignore_romaji=True)
# => 'only カナ'
wanakana.to_katakana('wi', use_obsolete_kana=True)
# => 'ヰ'

wanakana.to_romaji('ひらがな　カタカナ')
# => 'hiragana katakana'
wanakana.to_romaji('ひらがな　カタカナ', uppercase_katakana=True)
# => 'hiragana KATAKANA'
wanakana.to_romaji('つじぎり', custom_romaji_mapping={'じ': 'zi', 'つ': 'tu', 'り': 'li' })
# => 'tuzigili'

### EXTRA UTILITIES ###
wanakana.strip_okurigana('お祝い')
# => 'お祝'
wanakana.strip_okurigana('踏み込む')
# => '踏み込'
wanakana.strip_okurigana('お腹', leading=True)
# => '腹'
wanakana.strip_okurigana('ふみこむ', match_kanji='踏み込む')
# => 'ふみこ'
wanakana.strip_okurigana('おみまい', match_kanji='お祝い', leading=True)
# => 'みまい'

wanakana.tokenise('ふふフフ')
# => ['ふふ', 'フフ']
wanakana.tokenise('hello 田中さん')
# => ['hello', ' ', '田中', 'さん']
wanakana.tokenise('I said 私はすごく悲しい', compact=True)
# => [ 'I said ', '私はすごく悲しい']

# FIXME: tokenise does not work correctly when using detailed

Contributors

• Starwort – Author

Credits

Port of WanaKana