-
-
Save daviehh/fbb0f46e8c49f7cf3d2fc5574a925854 to your computer and use it in GitHub Desktop.
add furigana to kanji-hiragana pair
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import re | |
f_nx = lambda x: x != "" | |
def rt_pattern(kanji, hira): | |
return f"<ruby> {kanji} <rt> {hira} </rt></ruby>" | |
def to_furigana(kanji, hira): | |
kana_range = "\u3040-\u30ff" | |
re_kanj = f"([^{kana_range}]*)" | |
re_kana = f"([{kana_range}]*)" | |
is_hira = re.compile(f"[{kana_range}]+").search | |
kj_l = re.split(f"([{kana_range}]+)", kanji) | |
kgr = list(filter(f_nx, kj_l)) | |
h_re = [f"({si})" if is_hira(si) else re_kana for si in kgr] | |
hrex = "".join(h_re) | |
hgr = re.search(hrex, hira).groups() | |
assert len(hgr) == len(kgr) | |
furi_l = [hgr[i] if hgr[i] == kgr[i] else rt_pattern(kgr[i], hgr[i]) for i in range(len(kgr))] | |
return "".join(furi_l).strip() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment