svn-git-server/svn_mirror/config.py

"""Configuration loading and validation."""

import os
from dataclasses import dataclass, field
from typing import Dict, Optional

import yaml


class ConfigError(Exception):
    pass


def _check_type(val, typ, path: str):
    if not isinstance(val, typ):
        raise ConfigError(f"{path}: expected {typ.__name__}, got {type(val).__name__}")


def _check_optional(val, typ, path: str):
    if val is not None and not isinstance(val, typ):
        raise ConfigError(f"{path}: expected {typ.__name__} or null, got {type(val).__name__}")


@dataclass
class SVNConfig:
    url: str
    layout: str = "std"
    trunk: str = "trunk"
    branches: str = "branches"
    tags: str = "tags"

    @classmethod
    def from_dict(cls, d: dict, prefix: str) -> "SVNConfig":
        url = d.get("url")
        if not url:
            raise ConfigError(f"{prefix}.url: required")
        _check_type(url, str, f"{prefix}.url")

        layout = d.get("layout", "std")
        _check_type(layout, str, f"{prefix}.layout")
        if layout not in ("std", "custom"):
            raise ConfigError(f"{prefix}.layout: must be 'std' or 'custom'")

        trunk = d.get("trunk", "trunk")
        branches = d.get("branches", "branches")
        tags = d.get("tags", "tags")
        for name, val in [("trunk", trunk), ("branches", branches), ("tags", tags)]:
            _check_type(val, str, f"{prefix}.{name}")

        return cls(url=url, layout=layout, trunk=trunk, branches=branches, tags=tags)


@dataclass
class GiteaConfig:
    owner: str
    repo: str
    repos_path: Optional[str] = None
    webhook_secret: Optional[str] = None
    webhook_host: str = "0.0.0.0"
    webhook_port: int = 8080
    api_url: Optional[str] = None
    api_token: Optional[str] = None

    @property
    def repo_dir(self) -> str:
        """Return the expected on-disk path to Gitea's bare repo."""
        if self.repos_path:
            return f"{self.repos_path.rstrip('/')}/{self.owner}/{self.repo}.git"
        # Common defaults if repos_path not configured
        for base in ("/var/lib/gitea/data/repositories",
                     "/data/git/repositories",
                     "/home/git/repositories"):
            candidate = f"{base}/{self.owner}/{self.repo}.git"
            import os
            if os.path.isdir(candidate):
                return candidate
        raise ConfigError(
            f"gitea.repos_path not set and no default Gitea repo found "
            f"for {self.owner}/{self.repo}"
        )

    @classmethod
    def from_dict(cls, d: dict, prefix: str) -> "GiteaConfig":
        owner = d.get("owner")
        if not owner:
            raise ConfigError(f"{prefix}.owner: required")
        _check_type(owner, str, f"{prefix}.owner")

        repo = d.get("repo")
        if not repo:
            raise ConfigError(f"{prefix}.repo: required")
        _check_type(repo, str, f"{prefix}.repo")

        repos_path = d.get("repos_path")
        _check_optional(repos_path, str, f"{prefix}.repos_path")

        webhook_secret = d.get("webhook_secret")
        _check_optional(webhook_secret, str, f"{prefix}.webhook_secret")

        webhook_host = d.get("webhook_host", "0.0.0.0")
        _check_type(webhook_host, str, f"{prefix}.webhook_host")

        webhook_port = d.get("webhook_port", 8080)
        _check_type(webhook_port, int, f"{prefix}.webhook_port")

        api_url = d.get("api_url")
        _check_optional(api_url, str, f"{prefix}.api_url")

        api_token = d.get("api_token")
        _check_optional(api_token, str, f"{prefix}.api_token")

        return cls(
            owner=owner, repo=repo,
            repos_path=repos_path,
            webhook_secret=webhook_secret,
            webhook_host=webhook_host,
            webhook_port=webhook_port,
            api_url=api_url, api_token=api_token,
        )


@dataclass
class MirrorConfig:
    id: str
    svn: SVNConfig
    gitea: GiteaConfig
    authors: Dict[str, str] = field(default_factory=dict)
    sync_interval: int = 120
    enabled: bool = True

    @classmethod
    def from_dict(cls, d: dict) -> "MirrorConfig":
        mid = d.get("id")
        if not mid:
            raise ConfigError("mirror.id: required")
        _check_type(mid, str, "mirror.id")

        svn_raw = d.get("svn")
        if not svn_raw:
            raise ConfigError(f"mirror '{mid}'.svn: required")
        _check_type(svn_raw, dict, f"mirror '{mid}'.svn")

        gitea_raw = d.get("gitea")
        if not gitea_raw:
            raise ConfigError(f"mirror '{mid}'.gitea: required")
        _check_type(gitea_raw, dict, f"mirror '{mid}'.gitea")

        svn = SVNConfig.from_dict(svn_raw, f"mirror '{mid}'.svn")
        gitea = GiteaConfig.from_dict(gitea_raw, f"mirror '{mid}'.gitea")

        authors = d.get("authors", {})
        _check_type(authors, dict, f"mirror '{mid}'.authors")
        for k, v in authors.items():
            _check_type(k, str, f"mirror '{mid}'.authors key")
            _check_type(v, str, f"mirror '{mid}'.authors.{k}")

        sync_interval = d.get("sync_interval", 120)
        _check_type(sync_interval, int, f"mirror '{mid}'.sync_interval")

        enabled = d.get("enabled", True)
        _check_type(enabled, bool, f"mirror '{mid}'.enabled")

        return cls(
            id=mid,
            svn=svn,
            gitea=gitea,
            authors=authors,
            sync_interval=sync_interval,
            enabled=enabled,
        )


@dataclass
class AppConfig:
    data_dir: str = "/var/svn-mirror"
    mirrors: Dict[str, MirrorConfig] = field(default_factory=dict)

    @classmethod
    def load(cls, path: str) -> "AppConfig":
        if not os.path.exists(path):
            raise ConfigError(f"Config file not found: {path}")

        with open(path) as f:
            raw = yaml.safe_load(f)

        if not raw:
            raise ConfigError("Empty config file")

        data_dir = raw.get("data_dir", "/var/svn-mirror")
        _check_type(data_dir, str, "data_dir")

        mirrors_raw = raw.get("mirrors", [])
        _check_type(mirrors_raw, list, "mirrors")

        mirrors = {}
        for i, entry in enumerate(mirrors_raw):
            _check_type(entry, dict, f"mirrors[{i}]")
            mc = MirrorConfig.from_dict(entry)
            if mc.id in mirrors:
                raise ConfigError(f"Duplicate mirror id: {mc.id}")
            mirrors[mc.id] = mc

        return cls(data_dir=data_dir, mirrors=mirrors)