github_api.py

#!/usr/bin/env python3
"""
github_api.py — ATYPIK v24.0
Telechargement repo sans git (API GitHub + ZIP).
Compatible HF Spaces.
"""

import os
import json
import zipfile
import urllib.request
import tempfile
from pathlib import Path
from typing import List, Dict, Optional

GITHUB_TOKEN = os.getenv("GITHUB_TOKEN", "")

def _api_request(url: str) -> dict:
    req = urllib.request.Request(url)
    req.add_header("Accept", "application/vnd.github+json")
    if GITHUB_TOKEN:
        req.add_header("Authorization", f"Bearer {GITHUB_TOKEN}")
    with urllib.request.urlopen(req, timeout=30) as resp:
        return json.loads(resp.read().decode("utf-8"))

def download_repo(repo_url: str, branch: str = "main", dest: Optional[Path] = None) -> Path:
    parts = repo_url.rstrip("/").replace(".git", "").split("/")
    owner, repo = parts[-2], parts[-1]
    zip_url = f"https://github.com/{owner}/{repo}/archive/refs/heads/{branch}.zip"
    dest = dest or Path(tempfile.mkdtemp(prefix="repo_"))
    zip_path = dest / "repo.zip"
    req = urllib.request.Request(zip_url)
    req.add_header("User-Agent", "ATYPIK-Agent")
    with urllib.request.urlopen(req, timeout=60) as resp:
        zip_path.write_bytes(resp.read())
    with zipfile.ZipFile(zip_path, 'r') as z:
        z.extractall(dest)
    extracted = list(dest.glob(f"{repo}-*"))
    if extracted:
        return extracted[0]
    return dest

def get_file_content(repo_url: str, filepath: str, branch: str = "main") -> str:
    parts = repo_url.rstrip("/").replace(".git", "").split("/")
    owner, repo = parts[-2], parts[-1]
    raw_url = f"https://raw.githubusercontent.com/{owner}/{repo}/{branch}/{filepath}"
    req = urllib.request.Request(raw_url)
    req.add_header("User-Agent", "ATYPIK-Agent")
    with urllib.request.urlopen(req, timeout=30) as resp:
        return resp.read().decode("utf-8")

def list_repo_files(repo_url: str, branch: str = "main") -> List[str]:
    parts = repo_url.rstrip("/").replace(".git", "").split("/")
    owner, repo = parts[-2], parts[-1]
    api_url = f"https://api.github.com/repos/{owner}/{repo}/git/trees/{branch}?recursive=1"
    data = _api_request(api_url)
    files = []
    for item in data.get("tree", []):
        if item.get("type") == "blob":
            files.append(item["path"])
    return files