Hojun-Cho
62ddc2177b
Every Korean keyboard's 한자 key answers a lone consonant with the KS X 1001 symbol palette, and has since 한글 워드프로세서: ㅁ for ※ ○ △ ㈜, ㄴ for the brackets, ㄹ for the units, ㅇ for the circled numbers. strans sends that key to the same search as a syllable -- Khanja is Ctrl+H at strans.c:830, and startsearch seeds the query with whatever ko.c left pending -- but every one of hanja.dict's 187286 readings is a syllable, so the popup came up with a query in it and nothing to pick: ㅁ: 0 candidates ㄴ: 0 candidates ㄹ: 0 candidates 한: 99 candidates 韓 漢 寒 限 閑 恨 旱 汗 翰 邯 罕 悍 澣 閒 瀚 libhangul ships that palette beside the Hanja table already imported here: data/hanja/mssymbol.txt, same commit, same author, same BSD-3 terms, same key:value:comment format -- and keyed by the compatibility jamo ko.c already holds, U+3141 for ㅁ. So the engine does not change at all; the same dictlookup on the same trie now finds something: ㅁ: 75 candidates ＃ ＆ ＊ ＠ § ※ ☆ ★ ○ ● ◎ ◇ ◆ □ ■ △ ▲ ▽ ▼ ㄴ: 23 candidates ＂ （ ） ［ ］ ｛ ｝ ‘ ’ “ ” 〔 〕 〈 〉 《 》 「 」 ㄹ: 94 candidates ＄ ％ ￦ Ｆ ′ ″ ℃ Å ￠ ￡ ￥ ¤ ℉ ‰ € ㎕ ㎖ ㎗ ℓ 한: 99 candidates 韓 漢 寒 限 閑 恨 旱 汗 翰 邯 罕 悍 澣 閒 瀚 Both scripts widen by one rule -- a syllable reading gives Hanja, a jamo reading gives a symbol -- and hanja.src regenerates byte for byte as it was, because upstream's own non-syllable readings are words like ㄱ자집 whose values were never Hanja and still fall out. 985 of mssymbol.txt's 987 rows survive: its ideographic space and its soft hyphen do not, since a candidate the popup cannot draw is not a candidate, and the row format separates candidates with a space besides. The two keyspaces cannot collide -- one is syllables, one is single jamo -- so the 187286 existing rows are unchanged, byte for byte, and 18 rows join them. mkhanja takes a source list as mkemoji already does, and keeps each upstream header, which is why the licence text now appears twice. 89 unit, check-live, check-stress and valgrind all clean. The five new assertions were checked by breaking the change five ways: dropping mssymbol.src from SOURCES, letting issymbol keep a formatting character, letting a jamo reading keep Hanja, widening isjamo to the vowels, and making mkhanja reject jamo readings. Each fails only the tests that exist for it. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
99 lines
2.8 KiB
Python
Executable File
99 lines
2.8 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""Extract Hanja and symbol readings from libhangul data."""
|
|
|
|
import sys
|
|
import unicodedata
|
|
from pathlib import Path
|
|
|
|
|
|
def ishangul(s):
|
|
return s != "" and all(0xAC00 <= ord(c) <= 0xD7A3 for c in s)
|
|
|
|
|
|
def isjamo(s):
|
|
return len(s) == 1 and 0x3131 <= ord(s) <= 0x314E
|
|
|
|
|
|
def ishanja(s):
|
|
return s != "" and all(0x3400 <= ord(c) <= 0x4DBF
|
|
or 0x4E00 <= ord(c) <= 0x9FFF
|
|
or 0xF900 <= ord(c) <= 0xFAFF for c in s)
|
|
|
|
|
|
def issymbol(s):
|
|
"""One rune the popup can draw and a candidate row can carry: not a
|
|
space, which the row separates candidates with, and not a formatting
|
|
character, which would leave a blank candidate to pick."""
|
|
return (len(s) == 1 and not s.isspace() and not ishanja(s)
|
|
and not unicodedata.category(s).startswith("C"))
|
|
|
|
|
|
def keeps(reading, value):
|
|
"""A syllable reading gives Hanja; a jamo reading gives a symbol."""
|
|
if ishangul(reading):
|
|
return ishanja(value)
|
|
return isjamo(reading) and issymbol(value)
|
|
|
|
|
|
def extract(src, name):
|
|
comments = []
|
|
entries = []
|
|
seen = set()
|
|
leading = True
|
|
for lineno, raw in enumerate(src, 1):
|
|
line = raw.rstrip("\r\n")
|
|
if not line:
|
|
continue
|
|
if line.startswith("#"):
|
|
if leading:
|
|
comments.append(line.rstrip())
|
|
continue
|
|
leading = False
|
|
fields = line.split(":")
|
|
if len(fields) != 3:
|
|
raise ValueError(f"{name}:{lineno}: need key:value:comment")
|
|
reading, value, _ = fields
|
|
if not keeps(reading, value):
|
|
continue
|
|
pair = (value, reading)
|
|
if pair in seen:
|
|
raise ValueError(f"{name}:{lineno}: duplicate reading")
|
|
seen.add(pair)
|
|
entries.append(pair)
|
|
if not entries:
|
|
raise ValueError(f"{name}: no readings")
|
|
return comments, entries
|
|
|
|
|
|
def main():
|
|
sys.stdin.reconfigure(encoding="utf-8")
|
|
sys.stdout.reconfigure(encoding="utf-8")
|
|
sys.stderr.reconfigure(encoding="utf-8")
|
|
if len(sys.argv) > 2:
|
|
print(f"usage: {sys.argv[0]} [libhangul-hanja.txt]", file=sys.stderr)
|
|
return 2
|
|
src = sys.stdin
|
|
name = "<stdin>"
|
|
try:
|
|
if len(sys.argv) == 2:
|
|
name = sys.argv[1]
|
|
src = Path(name).open(encoding="utf-8")
|
|
comments, entries = extract(src, name)
|
|
for line in comments:
|
|
print(line)
|
|
if comments:
|
|
print()
|
|
for value, reading in entries:
|
|
print(f"{value}\t{reading}")
|
|
except (OSError, UnicodeError, ValueError) as error:
|
|
print(error, file=sys.stderr)
|
|
return 1
|
|
finally:
|
|
if src is not sys.stdin:
|
|
src.close()
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|