llm_wiki/raw/教育AI研究/tools/fix_institution_archives_frontmatter.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import sys
import io
import re
import datetime
from pathlib import Path
from typing import Dict, List, Optional, Tuple

if sys.platform == "win32":
    sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding="utf-8")
    sys.stderr = io.TextIOWrapper(sys.stderr.buffer, encoding="utf-8")


def get_country_from_filename(filename: str) -> str:
    name = Path(filename).stem
    if (
        "清华" in name
        or "北大" in name
        or "复旦" in name
        or "上交" in name
        or "北师大" in name
    ):
        return "中国"
    elif (
        "MIT" in name
        or "斯坦福" in name
        or "CMU" in name
        or "哈佛" in name
        or "剑桥" in name
        or "卡内基" in name
    ):
        return "美国/英国"
    elif "Google" in name or "Microsoft" in name or "OpenAI" in name:
        return "国际"
    elif "upGrad" in name or "Physics" in name or "AI-Samarth" in name:
        return "印度"
    elif "Topica" in name:
        return "东南亚"
    elif "好未来" in name or "猿辅导" in name or "作业帮" in name:
        return "中国"
    return "其他"


def get_industry_from_filename(filename: str) -> str:
    name = Path(filename).stem
    if any(
        x in name
        for x in [
            "清华",
            "北大",
            "复旦",
            "上交",
            "北师大",
            "MIT",
            "斯坦福",
            "CMU",
            "哈佛",
            "剑桥",
            "卡内基",
            "ETH",
        ]
    ):
        return "高校"
    elif any(x in name for x in ["Google", "Microsoft", "OpenAI"]):
        return "科技巨头"
    elif any(x in name for x in ["好未来", "猿辅导", "作业帮"]):
        return "中国教育科技"
    elif any(
        x in name
        for x in ["upGrad", "Physics", "Topica", "MagicSchool", "Synthesis", "SchoolAI"]
    ):
        return "EdTech创业"
    return "其他"


def update_institution_frontmatter(file_path: Path) -> bool:
    try:
        content = file_path.read_text(encoding="utf-8")

        if not content.startswith("---"):
            print(f"⚠️ No frontmatter in {file_path.name}")
            return False

        fm_match = re.match(r"^---\n(.*?)\n---", content, re.DOTALL)
        if not fm_match:
            print(f"⚠️ Cannot parse frontmatter in {file_path.name}")
            return False

        fm_text = fm_match.group(1)
        body = content[fm_match.end() :]

        existing_fm = {}
        for line in fm_text.split("\n"):
            if ":" in line:
                key, value = line.split(":", 1)
                existing_fm[key.strip()] = value.strip()

        country = existing_fm.get("country", get_country_from_filename(file_path.name))
        industry = existing_fm.get(
            "industry", get_industry_from_filename(file_path.name)
        )

        quality = existing_fm.get("quality", "A级")
        quality_score = existing_fm.get("quality_score", 85)

        new_fm_lines = [
            "---",
            "categories:",
            '  - "[[LLM Wiki]]"',
            '  - "[[教育AI研究项目]]"',
            "tags:",
            "  - wiki",
            "  - institution",
            "  - education-ai",
            f"  - {country}",
            f"  - {industry}",
            f"type: institution",
            f"created: {existing_fm.get('created', datetime.date.today().isoformat())}",
        ]

        if "title" in existing_fm:
            new_fm_lines.append(f"title: {existing_fm['title']}")
        if "updated" in existing_fm:
            new_fm_lines.append(f"updated: {existing_fm['updated']}")
        new_fm_lines.append(f"quality: {quality}")
        new_fm_lines.append(f"quality_score: {quality_score}")
        new_fm_lines.append(f"country: {country}")
        new_fm_lines.append(f"industry: {industry}")

        if "source" in existing_fm:
            new_fm_lines.append(f"source: {existing_fm['source']}")

        new_fm_lines.append("---")

        new_content = "\n".join(new_fm_lines) + body
        file_path.write_text(new_content, encoding="utf-8")

        print(
            f"✅ Updated: {file_path.name} ({country}, {industry}, quality={quality})"
        )
        return True

    except Exception as e:
        print(f"❌ Error updating {file_path.name}: {e}")
        return False


def main():
    print("=" * 60)
    print("Institution Archives Frontmatter Batch Update Tool")
    print("=" * 60)
    print(f"Execution time: {datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
    print()

    archives_dir = Path(__file__).parent.parent / "机构档案"

    if not archives_dir.exists():
        print(f"❌ Institution archives directory not found: {archives_dir}")
        return

    archive_files = [f for f in archives_dir.glob("*.md") if "框架" not in f.name]
    print(f"Found {len(archive_files)} institution archive files")
    print()

    success_count = 0
    fail_count = 0

    for archive_file in archive_files:
        result = update_institution_frontmatter(archive_file)
        if result:
            success_count += 1
        else:
            fail_count += 1

    print()
    print("=" * 60)
    print("Update Complete")
    print("=" * 60)
    print(f"Total files: {len(archive_files)}")
    print(f"Successfully updated: {success_count}")
    print(f"Failed: {fail_count}")
    print("=" * 60)


if __name__ == "__main__":
    main()