Add Windows version on PIME
Port the core (Zhuyin parser, classifier, converter, composition engine) to Python as a PIME input method, with the same test cases as the Swift version plus wrapper tests against stand-in PIME modules. scripts/package-windows.sh builds a zip with install/uninstall scripts and a README for testers. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Executable
+37
@@ -0,0 +1,37 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Fills windows/autozhuyin/data/ from the shared Mac resources.
|
||||
|
||||
- lexicon.txt, english-common.txt: copied from Resources/
|
||||
- english-dict.txt: filtered from a system word list (default /usr/share/dict/words,
|
||||
Webster's 2nd edition, public domain), since Windows has no such file
|
||||
- english-bigram.json: precomputed letter-bigram table
|
||||
|
||||
Usage: build_data.py [word-list]
|
||||
"""
|
||||
import json
|
||||
import shutil
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
ROOT = Path(__file__).resolve().parents[2]
|
||||
WIN = ROOT / "windows"
|
||||
sys.path.insert(0, str(WIN))
|
||||
|
||||
from autozhuyin.core.english import train_bigram # noqa: E402
|
||||
|
||||
data = WIN / "autozhuyin" / "data"
|
||||
data.mkdir(parents=True, exist_ok=True)
|
||||
for name in ("lexicon.txt", "english-common.txt"):
|
||||
shutil.copy(ROOT / "Resources" / name, data / name)
|
||||
|
||||
word_list = Path(sys.argv[1] if len(sys.argv) > 1 else "/usr/share/dict/words")
|
||||
words = sorted({w.strip().lower() for w in word_list.read_text(encoding="utf-8").split()
|
||||
if len(w.strip()) > 2 and w.strip().isascii() and w.strip().isalpha()})
|
||||
(data / "english-dict.txt").write_text("\n".join(words) + "\n", encoding="utf-8")
|
||||
|
||||
common = {w.strip().lower() for w in (data / "english-common.txt").read_text(encoding="utf-8").splitlines()
|
||||
if w.strip() and not w.startswith("#")}
|
||||
bigram = train_bigram(sorted(common | set(words)), common)
|
||||
(data / "english-bigram.json").write_text(json.dumps(bigram), encoding="utf-8")
|
||||
|
||||
print("data ready: %d dictionary words, %d bigrams" % (len(words), len(bigram["table"])))
|
||||
Reference in New Issue
Block a user