app/services/challenge_loader.py

"""Map raw Supabase rows to the ``TrainingData`` shape the frontend expects.

Each ``_map_*_row_to_training(row, team_role) -> dict`` function knows
the columns of one challenge table and returns a consistent object so
the frontend editor can render any challenge type.
"""

import base64 as _b64
import json


_CODE_LANG_BY_EXT = {
    "html": "html", "js": "javascript", "ts": "typescript",
    "py": "python", "json": "json", "csv": "text",
    "pem": "text", "log": "text", "txt": "text", "bin": "binary",
}


def _parse_hints(raw) -> list:
    if isinstance(raw, list):
        return raw
    if isinstance(raw, str):
        try:
            parsed = json.loads(raw)
            return parsed if isinstance(parsed, list) else []
        except (json.JSONDecodeError, TypeError):
            return []
    return []


def _infer_code_language(filename, team_role: str) -> str:
    if not filename:
        return "text"
    ext = filename.rsplit(".", 1)[-1].lower() if "." in filename else ""
    return _CODE_LANG_BY_EXT.get(ext, "text")


def map_encryption_row_to_training(row: dict, team_role: str) -> dict:
    """Map a row from ``encryption_challenges`` to TrainingData."""
    files = row.get("files") or {}
    file_meta = row.get("file_metadata") or {}
    first_filename = next(iter(files), None)
    code = ""
    if first_filename:
        try:
            code = _b64.b64decode(files[first_filename]).decode("utf-8", errors="replace")
        except Exception:
            code = ""

    return {
        "id": row.get("id"),
        "scenarioId": row.get("id"),
        "title": row.get("title", ""),
        "story": row.get("story", ""),
        # Challenge type is always 'crypto' for rows coming from
        # encryption_challenges — the ``module`` column is no longer
        # authoritative after the 011 normalization migration.
        "type": "crypto",
        "topic": row.get("topic") or row.get("module", "encryption-basics"),
        "task": row.get("task_outline", ""),
        "code": code,
        "codeLanguage": _infer_code_language(first_filename, team_role),
        "htmlPreview": code if (first_filename or "").endswith(".html") else None,
        "logData": code if (first_filename or "").endswith((".log", ".txt")) else None,
        "configData": code if (first_filename or "").endswith((".json", ".csv", ".pem")) else None,
        "vulnerabilityLocation": None,
        "hints": _parse_hints(row.get("hints")),
        "expectedAnswer": row.get("flag_preview", ""),       # CyberArena{...}
        "expectedAnswerHash": row.get("flag_hash", ""),      # server-side check
        "explanation": "العلم يظهر في مخرجات الطرفية بعد تنفيذ الأمر الصحيح.",
        "xpReward": row.get("xp_reward", 100),
        "difficulty": row.get("difficulty", "متوسط"),
        "files": files,
        "fileMetadata": file_meta,
        "commandOutputs": row.get("command_outputs") or {},
        "toolsWhitelist": row.get("tools_whitelist") or [],
        "challengeType": "crypto",
    }


def map_code_fixing_row_to_training(row: dict, team_role: str) -> dict:
    """Map a row from ``code_fixing_challenges`` to TrainingData."""
    return {
        "id": row.get("id"),
        "scenarioId": row.get("id"),
        "title": row.get("title", ""),
        "story": row.get("story", ""),
        "type": "code-fixing",
        "topic": row.get("topic") or row.get("module", "code-fixing"),
        "task": row.get("task_outline", ""),

        # Additional fields for code-fixing
        "language": row.get("language", "PYTHON"),
        "vulnerable_code": row.get("vulnerable_code", ""),
        "vulnerability_type": row.get("vulnerability_type", ""),
        "vulnerability_description": row.get("vulnerability_description", ""),
        "difficulty": row.get("difficulty", "متوسط"),
        "xpReward": row.get("xp_reward", 150),
        "hints": _parse_hints(row.get("hints")),
    }


def map_log_analysis_row_to_training(row: dict, team_role: str) -> dict:
    """Map a row from ``log_analysis_challenges`` to TrainingData."""
    from app.core.config import SUPABASE_URL
    storage_path = row.get("storage_path", "")
    is_inline = storage_path.startswith("inline://")
    actual_path = storage_path.replace("inline://", "") if is_inline else storage_path

    log_url = ""
    if not is_inline and SUPABASE_URL and actual_path:
        log_url = f"{SUPABASE_URL}/storage/v1/object/public/log-analysis-files/{actual_path}"

    return {
        "id": row.get("id"),
        "scenarioId": row.get("id"),
        "title": row.get("title", ""),
        "story": row.get("story", ""),
        "type": "log-analysis",
        "topic": row.get("topic") or row.get("module", "log-analysis"),
        "task": row.get("task_outline", ""),
        # Log-analysis specific
        "log_type": row.get("log_type", "auth"),
        "storage_path": storage_path,
        "log_url": log_url,
        "is_inline": is_inline,
        "file_size_bytes": row.get("file_size_bytes", 0),
        "vulnerability_description": row.get("vulnerability_description", ""),
        "difficulty": row.get("difficulty", "متوسط"),
        "xpReward": row.get("xp_reward", 150),
        "hints": _parse_hints(row.get("hints")),
    }


def map_vuln_hunter_row_to_training(row: dict, team_role: str) -> dict:
    """Map a row from ``vulnerability_hunter_challenges`` to TrainingData.

    Consumed by the Cyberpunk-themed VulnerabilityHunterEditor.
    """
    return {
        "id": row.get("id"),
        "scenarioId": row.get("id"),
        "title": row.get("title", ""),
        "story": row.get("story", ""),
        "type": "vulnerability-hunter",
        "topic": row.get("topic") or row.get("module", "vulnerability-hunter"),
        "task": row.get("task_outline", ""),
        "language": row.get("language", "PYTHON"),
        "vulnerable_code": row.get("vulnerable_code", ""),
        "vulnerability_type": row.get("vulnerability_type", ""),
        "vulnerability_class": row.get("vulnerability_class", ""),
        "vulnerability_description": row.get("vulnerability_description", ""),
        "difficulty": row.get("difficulty", "متوسط"),
        "xpReward": row.get("xp_reward", 150),
        "hints": _parse_hints(row.get("hints")),
    }


def map_web_exploit_row_to_training(row: dict, team_role: str) -> dict:
    """Map a row from ``web_exploitation_challenges`` to TrainingData."""
    return {
        "id": row.get("id"),
        "scenarioId": row.get("id"),
        "title": row.get("title", ""),
        "story": row.get("story", ""),
        "type": "web-exploitation",
        "topic": row.get("topic") or row.get("module", "web-exploitation"),
        "task": row.get("task_outline", ""),
        "vulnerability_type": row.get("vulnerability_type", ""),
        "vulnerability_class": row.get("vulnerability_class", ""),
        "vulnerability_description": row.get("vulnerability_description", ""),
        "http_request": row.get("http_request", ""),
        "http_response": row.get("http_response", ""),
        "flag_preview": row.get("flag_preview", ""),
        "flag_hash": row.get("flag_hash", ""),
        "difficulty": row.get("difficulty", "متوسط"),
        "xpReward": row.get("xp_reward", 200),
        "hints": _parse_hints(row.get("hints")),
        "challengeType": "web-exploitation",
    }


def map_steganography_row_to_training(row: dict, team_role: str) -> dict:
    """Map a row from ``steganography_challenges`` to TrainingData."""
    files = row.get("files") or {}
    file_meta = row.get("file_metadata") or {}
    first_filename = next(iter(files), None)
    code = ""
    if first_filename:
        try:
            # Safely attempt to decode as UTF-8, but fall back or truncate for binaries
            code = _b64.b64decode(files[first_filename]).decode("utf-8", errors="ignore")[:300]
        except Exception:
            code = ""

    return {
        "id": row.get("id"),
        "scenarioId": row.get("id"),
        "title": row.get("title", ""),
        "story": row.get("story", ""),
        "type": "steganography",
        "topic": row.get("topic") or row.get("module", "steganography"),
        "task": row.get("task_outline", ""),
        "code": code,
        "codeLanguage": _infer_code_language(first_filename, team_role),
        "htmlPreview": None,
        "logData": None,
        "configData": None,
        "vulnerabilityLocation": None,
        "hints": _parse_hints(row.get("hints")),
        "expectedAnswer": row.get("flag_preview", ""),       # CyberArena{...}
        "expectedAnswerHash": row.get("flag_hash", ""),      # server-side check
        "explanation": "العلم مخفي داخل ملف الصورة المعطى. استخدم أدوات التحقيق مثل file أو strings أو unzip.",
        "xpReward": row.get("xp_reward", 120),
        "difficulty": row.get("difficulty", "متوسط"),
        "files": files,
        "fileMetadata": file_meta,
        "commandOutputs": row.get("command_outputs") or {},
        "toolsWhitelist": row.get("tools_whitelist") or [],
        "challengeType": "steganography",
    }