tiny-forge/internal/staticsite/provider.go

package staticsite

import (
	"context"
	"fmt"
	"io"
	"net/http"
	"os"
	"path/filepath"
	"strings"
	"time"
)

// RepoInfo represents a repository returned by the provider's list/search API.
type RepoInfo struct {
	Owner       string `json:"owner"`
	Name        string `json:"name"`
	FullName    string `json:"full_name"`    // "owner/name"
	Description string `json:"description"`
	Private     bool   `json:"private"`
	HTMLURL     string `json:"html_url"`
}

// GitProvider abstracts Git hosting API operations.
// Implementations exist for Gitea/Forgejo/Gogs, GitHub, and GitLab.
type GitProvider interface {
	// Name returns the provider identifier (e.g., "gitea", "github", "gitlab").
	Name() string

	// TestConnection verifies that the repository is accessible.
	TestConnection(ctx context.Context, owner, repo string) error

	// ListRepos returns repositories accessible with the current token.
	// If query is non-empty, results are filtered by name.
	ListRepos(ctx context.Context, query string) ([]RepoInfo, error)

	// ListBranches returns all branch names for a repository.
	ListBranches(ctx context.Context, owner, repo string) ([]string, error)

	// GetLatestCommitSHA returns the latest commit SHA for a branch.
	GetLatestCommitSHA(ctx context.Context, owner, repo, branch string) (string, error)

	// ListTree returns the full directory tree for a branch.
	ListTree(ctx context.Context, owner, repo, branch string) ([]FolderEntry, error)

	// DownloadFolder downloads all files from a folder path to a local directory.
	DownloadFolder(ctx context.Context, owner, repo, branch, folderPath, destDir string) error
}

// ProviderType identifies a Git hosting provider.
type ProviderType string

const (
	ProviderGitea  ProviderType = "gitea"  // Also works for Forgejo and Gogs.
	ProviderGitHub ProviderType = "github"
	ProviderGitLab ProviderType = "gitlab"
)

// ValidProviderTypes lists all supported provider types.
var ValidProviderTypes = []ProviderType{ProviderGitea, ProviderGitHub, ProviderGitLab}

// NewGitProvider creates a GitProvider for the given type.
// If providerType is empty, it attempts autodetection from the baseURL.
func NewGitProvider(providerType ProviderType, baseURL, token string) (GitProvider, error) {
	if providerType == "" {
		providerType = DetectProvider(baseURL)
	}

	switch providerType {
	case ProviderGitea:
		return NewGiteaContentFetcher(baseURL, token), nil
	case ProviderGitHub:
		return NewGitHubProvider(baseURL, token), nil
	case ProviderGitLab:
		return NewGitLabProvider(baseURL, token), nil
	default:
		return nil, fmt.Errorf("unsupported git provider: %s", providerType)
	}
}

// DetectProvider guesses the provider type from a base URL.
func DetectProvider(baseURL string) ProviderType {
	lower := strings.ToLower(baseURL)
	switch {
	case strings.Contains(lower, "github.com"):
		return ProviderGitHub
	case strings.Contains(lower, "gitlab.com"):
		return ProviderGitLab
	default:
		// Default to Gitea for self-hosted instances (Gitea/Forgejo/Gogs all share the same API).
		return ProviderGitea
	}
}

// DetectProviderWithProbe tries to autodetect the provider by probing known API endpoints.
// Falls back to URL-based detection if probing fails.
func DetectProviderWithProbe(ctx context.Context, baseURL string) ProviderType {
	// First try URL-based detection for well-known hosts.
	urlBased := DetectProvider(baseURL)
	if urlBased == ProviderGitHub || urlBased == ProviderGitLab {
		return urlBased
	}

	// For unknown hosts, probe for Gitea/GitLab API signatures using the
	// SSRF-safe client so a probe URL cannot be used to reach loopback
	// or cloud-metadata addresses.
	client := NewSafeHTTPClient(5 * time.Second)
	base := strings.TrimRight(baseURL, "/")

	// Try Gitea/Forgejo API.
	if resp, err := httpGet(ctx, client, base+"/api/v1/version"); err == nil && resp == http.StatusOK {
		return ProviderGitea
	}

	// Try GitLab API.
	if resp, err := httpGet(ctx, client, base+"/api/v4/version"); err == nil && resp == http.StatusOK {
		return ProviderGitLab
	}

	// Default to Gitea.
	return ProviderGitea
}

// httpGet performs a simple GET and returns the status code.
func httpGet(ctx context.Context, client *http.Client, url string) (int, error) {
	req, err := http.NewRequestWithContext(ctx, http.MethodGet, url, nil)
	if err != nil {
		return 0, err
	}
	resp, err := client.Do(req)
	if err != nil {
		return 0, err
	}
	resp.Body.Close()
	return resp.StatusCode, nil
}

// downloadFileHTTP is a shared helper for downloading a file from a URL.
func downloadFileHTTP(ctx context.Context, client *http.Client, url, localPath string, authHeader func(r *http.Request)) error {
	req, err := http.NewRequestWithContext(ctx, http.MethodGet, url, nil)
	if err != nil {
		return fmt.Errorf("create request: %w", err)
	}
	if authHeader != nil {
		authHeader(req)
	}

	resp, err := client.Do(req)
	if err != nil {
		return fmt.Errorf("execute request: %w", err)
	}
	defer resp.Body.Close()

	if resp.StatusCode != http.StatusOK {
		return fmt.Errorf("unexpected status %d for %s", resp.StatusCode, url)
	}

	if err := os.MkdirAll(filepath.Dir(localPath), 0o755); err != nil {
		return fmt.Errorf("create directory: %w", err)
	}

	file, err := os.Create(localPath)
	if err != nil {
		return fmt.Errorf("create file: %w", err)
	}
	defer file.Close()

	if _, err := io.Copy(file, resp.Body); err != nil {
		return fmt.Errorf("write file: %w", err)
	}

	return nil
}