import re
import csv
from pathlib import Path

SRC = Path(r"d:\Github\docs\config\LanguageDataTwo.csv")
if not SRC.exists():
    print(f"Source not found: {SRC}")
    raise SystemExit(1)

# 备份原文件
bak = SRC.with_suffix(SRC.suffix + ".bak")
if not bak.exists():
    bak.write_bytes(SRC.read_bytes())

out_rows = []
with SRC.open("r", encoding="utf-8") as f:
    for raw in f:
        line = raw.rstrip("\n")
        if not line.strip():
            continue
        # 跳过首部注释行（以#开头）
        if line.lstrip().startswith("#"):
            continue
        # 将连续两个或以上空格替换为制表符，便于分割（原文件里有制表或多空格分隔）
        norm = re.sub(r"[ \u00A0]{2,}", "\t", line)
        # 以制表符分割（如果没有制表符，会退化为按任意空格分割）
        parts = [p.strip() for p in re.split(r"\t+", norm)]
        # 如果分割后超过4列，则把第0,1固定，剩下的尽量合并为 English 和 Chinese 两列
        if len(parts) >= 4:
            id_, key = parts[0], parts[1]
            # English 可能包含制表/空格，取中间所有并把最后一列当作中文
            eng = " ".join(parts[2:-1]).strip()
            chi = parts[-1].strip()
            out_rows.append((id_, key, eng, chi))
        elif len(parts) == 3:
            id_, key, rest = parts
            # 无法区分 English / Chinese，尝试按中文字符后半部分切分（保守策略）
            m = re.search(r"[\u4e00-\u9fff]+", rest)
            if m:
                idx = m.start()
                eng = rest[:idx].strip()
                chi = rest[idx:].strip()
            else:
                eng = rest
                chi = ""
            out_rows.append((id_, key, eng, chi))
        else:
            # 无法解析的行，跳过或记录为备注行
            # 记录为空的键以便人工检查
            out_rows.append(("", "", line.strip(), ""))

# 写入标准 CSV（全部字段用双引号包裹）
with SRC.open("w", encoding="utf-8", newline="") as out:
    writer = csv.writer(out, quoting=csv.QUOTE_ALL)
    writer.writerow(["Id", "key", "English", "ChineseSimplified"])
    for r in out_rows:
        writer.writerow(r)

print(f"Formatted CSV written to {SRC} (backup at {bak})")