Files
word-market/importer/src/export-synonym-derivative.py
T
voidandClaude Sonnet 4.6 f030334243 feat(importer): 添加 Lexis 词书导出工具链
三步主流程(下载目录 -> 下载词书并解密导出 -> 下载并解密 ZPK),
以及可独立调用的 SQLCipher2 / ZPK 解密工具与词根、近义词导出脚本。

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-11-08 21:15:43 +08:00

99 lines
4.2 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#!/usr/bin/env python3
"""Export synonym data from bbdb and derivative/family data from wordroot."""
from __future__ import annotations
import csv
import argparse
import shutil
import subprocess
import sys
import tempfile
from pathlib import Path
ROOT = Path(__file__).resolve().parents[1]
OUT = ROOT / "output" / "synonym-derivative-export"
PACKAGE = "cn.com.langeasy.LangEasyLexis"
KEYS = {
"bbdb": "North_London_bbdb_Forever_20230710",
"wordroot": "North_wordroot_London_Forever_20220601",
}
def connect(path: Path, key: str):
try:
import sqlcipher3.dbapi2 as dbapi
except ImportError as exc:
raise SystemExit("请先安装 sqlcipher3:python -m pip install sqlcipher3") from exc
conn = dbapi.connect(str(path))
conn.execute(f"PRAGMA key='{key}'")
conn.execute("SELECT count(*) FROM sqlite_master").fetchone()
return conn
def adb_export(serial: str | None, remote_name: str, local_path: Path) -> None:
target = ["adb"] + (["-s", serial] if serial else [])
target += ["exec-out", "cat", f"/data/data/{PACKAGE}/databases/{remote_name}"]
with local_path.open("wb") as fh:
result = subprocess.run(target, stdout=fh, stderr=subprocess.PIPE)
if result.returncode != 0:
target = ["adb"] + (["-s", serial] if serial else [])
target += ["exec-out", "run-as", PACKAGE, "cat", f"databases/{remote_name}"]
with local_path.open("wb") as fh:
result = subprocess.run(target, stdout=fh, stderr=subprocess.PIPE)
if result.returncode != 0 or local_path.stat().st_size == 0:
detail = result.stderr.decode(errors="replace").strip()
raise SystemExit(f"ADB 导出失败: {remote_name}: {detail}")
def dump_query(conn, sql: str, name: str) -> int:
cur = conn.execute(sql)
path = OUT / name
with path.open("w", newline="", encoding="utf-8-sig") as fh:
writer = csv.writer(fh)
writer.writerow([d[0] for d in cur.description])
rows = cur.fetchall()
writer.writerows(rows)
return len(rows)
def main() -> int:
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("--serial", help="adb 设备序列号;默认使用当前设备")
args = parser.parse_args()
OUT.mkdir(parents=True, exist_ok=True)
with tempfile.TemporaryDirectory(prefix="lexis-adb-export-") as tmp:
bb_path = Path(tmp) / "bbdb.db"
wr_path = Path(tmp) / "wordroot.db"
adb_export(args.serial, "bbdb.db", bb_path)
adb_export(args.serial, "wordroot.db", wr_path)
bb = connect(bb_path, KEYS["bbdb"])
wr = connect(wr_path, KEYS["wordroot"])
try:
counts = {}
counts["synonym_words.csv"] = dump_query(bb, "SELECT id, word FROM t_synonym_words ORDER BY id", "synonym_words.csv")
counts["synonym_data.csv"] = dump_query(bb, "SELECT * FROM t_synonym_datas ORDER BY word_id, pos, id", "synonym_data.csv")
counts["synonyms-joined.csv"] = dump_query(bb, """SELECT w.word, d.pos, d.interpret, d.zk, d.gk, d.cet4, d.cet6, d.ky, d.ielts, d.zsb, d.other, d.toefl FROM t_synonym_words w JOIN t_synonym_datas d ON d.word_id=w.id ORDER BY w.word, d.pos, d.id""", "synonyms-joined.csv")
counts["derivative-family.csv"] = dump_query(wr, """SELECT id, word, top_id, grade, interpret, prefix, suffix, group1, group2, group3, json FROM word_family ORDER BY top_id, id""", "derivative-family.csv")
counts["derivative-mini-groups.csv"] = dump_query(wr, "SELECT id, word_ids FROM word_family_mini_group ORDER BY id", "derivative-mini-groups.csv")
finally:
bb.close()
wr.close()
(OUT / "synonym-derivative-summary.txt").write_text(
"近义词与派生串记导出\n"
f"近义词单词: {counts['synonym_words.csv']}\n"
f"近义词释义记录: {counts['synonym_data.csv']}\n"
f"近义词关联记录: {counts['synonyms-joined.csv']}\n"
f"派生词族记录: {counts['derivative-family.csv']}\n"
f"派生小组记录: {counts['derivative-mini-groups.csv']}\n",
encoding="utf-8",
)
print("已完成近义词和派生串记导出")
for name, count in counts.items():
print(f"{name}: {count}")
return 0
if __name__ == "__main__":
raise SystemExit(main())