bookhoard/internal/services/podcast_http.go

// SSRF-guarded HTTP fetching for the podcast fetcher (plan §7).
//
// This is the code path that turns USER-SUPPLIED URLs into server
// fetches — treat it as a security boundary, not a convenience wrapper:
//
//   - https-only schemes (feed URL, enclosure, artwork, EVERY redirect hop)
//   - private/loopback/link-local/multicast/unspecified IP ranges blocked
//     at DIAL time via Dialer.Control — the check sees the RESOLVED
//     address, so a DNS name that rebinding-resolves to 127.0.0.1 (or a
//     redirect into the internal network) is refused at the socket, not
//     merely at URL-parse time
//   - hard response size caps on every body (feed XML, artwork, enclosures)
//
// Go's redirect follower re-dials through the same dialer per hop, so
// the IP guard re-applies automatically; the scheme guard re-applies
// via CheckRedirect.
package services

import (
	"context"
	"crypto/tls"
	"errors"
	"fmt"
	"io"
	"net"
	"net/http"
	"net/url"
	"syscall"
	"time"
)

// Response size caps (bytes). Feeds are XML; artwork is an image;
// enclosures are audio episodes — the enclosure cap is deliberately the
// large one (audiobook chapters run long) but still bounded.
const (
	maxFeedSizeBytes     = 25 << 20 // 25 MiB
	maxArtworkSizeBytes  = 20 << 20 // 20 MiB
	maxEnclosureCapBytes = 1 << 30  // 1 GiB
)

// ErrBlockedPrivateAddress marks SSRF-guard rejections (dial-time IP or
// scheme checks). Handlers surface it as a validation failure, and the
// download worker records it as the download_error text.
var ErrBlockedPrivateAddress = errors.New("address blocked: private, loopback, or otherwise non-public")

// podcastHTTPClient builds the shared guard client. Timeout is generous
// (podcast servers are slow) but bounded; enclosures stream through a
// LimitReader so a lying Content-Length cannot exhaust disk.
func podcastHTTPClient() *http.Client {
	dialer := &net.Dialer{
		Timeout: 15 * time.Second,
		Control: func(network, address string, _ syscall.RawConn) error {
			return guardDialAddress(address)
		},
	}
	transport := &http.Transport{
		DialContext:           dialer.DialContext,
		TLSHandshakeTimeout:   15 * time.Second,
		ResponseHeaderTimeout: 60 * time.Second,
		// Enclosure downloads are long; idle conn reuse still applies.
		IdleConnTimeout: 90 * time.Second,
		TLSClientConfig: &tls.Config{MinVersion: tls.VersionTLS12},
		Proxy:           nil, // never route through a user-controllable proxy
	}
	return &http.Client{
		Transport: transport,
		Timeout:   15 * time.Minute, // outer bound (biggest enclosures on slow lines)
		CheckRedirect: func(req *http.Request, via []*http.Request) error {
			if len(via) >= 10 {
				return fmt.Errorf("stopped after 10 redirects")
			}
			if err := guardURLScheme(req.URL); err != nil {
				return err
			}
			return nil
		},
	}
}

// guardDialAddress validates the RESOLVED host:port at dial time.
func guardDialAddress(address string) error {
	host, _, err := net.SplitHostPort(address)
	if err != nil {
		return fmt.Errorf("dial guard: %w", err)
	}
	ip := net.ParseIP(host)
	if ip == nil {
		return fmt.Errorf("dial guard: unparseable address %q", host)
	}
	if !isPublicIP(ip) {
		return ErrBlockedPrivateAddress
	}
	return nil
}

// guardURLScheme enforces https on any URL we are about to touch.
func guardURLScheme(u *url.URL) error {
	if u == nil || u.Scheme != "https" {
		return fmt.Errorf("only https feed/enclosure URLs are supported")
	}
	return nil
}

// isPublicIP reports whether ip is a routable public unicast address.
// Everything loopback/private/link-local/multicast/unspecified —
// including IPv4-mapped IPv6 spellings of those — is rejected.
func isPublicIP(ip net.IP) bool {
	if ip == nil {
		return false
	}
	// Normalize IPv4-mapped IPv6 (::ffff:10.0.0.1) to its v4 form so
	// the v4 range checks below actually fire.
	if ip4 := ip.To4(); ip4 != nil {
		ip = ip4
	}
	if ip.IsLoopback() || ip.IsPrivate() || ip.IsLinkLocalUnicast() ||
		ip.IsLinkLocalMulticast() || ip.IsInterfaceLocalMulticast() ||
		ip.IsMulticast() || ip.IsUnspecified() {
		return false
	}
	return true
}

// guardFetch performs a GET with the scheme/IP guards, conditional-GET
// validators, and a hard body cap. Returns the body bytes, the FINAL
// URL after redirects (new-feed-url / migration detection), validators
// to persist, and whether the server answered 304 Not Modified.
type fetchResult struct {
	Body       []byte
	FinalURL   string
	ETag       string
	LastModified string
	NotModified bool
	StatusCode int
}

// podcastHTTPClientFactory is the indirection TESTS use: the SSRF suite
// exercises the REAL client; fetch-driven integration tests swap in a
// client that trusts httptest's loopback TLS cert. Never reassign
// outside tests (use SetPodcastHTTPClientForTests).
var podcastHTTPClientFactory = podcastHTTPClient

// SetPodcastHTTPClientForTests swaps the fetch client. nil restores the
// production client (SSRF guards intact).
func SetPodcastHTTPClientForTests(c *http.Client) {
	if c == nil {
		podcastHTTPClientFactory = podcastHTTPClient
		return
	}
	podcastHTTPClientFactory = func() *http.Client { return c }
}

func guardFetch(ctx context.Context, rawURL, etag, lastModified string, maxSize int64) (*fetchResult, error) {
	u, err := url.Parse(rawURL)
	if err != nil {
		return nil, fmt.Errorf("invalid URL: %w", err)
	}
	if err := guardURLScheme(u); err != nil {
		return nil, err
	}

	req, err := http.NewRequestWithContext(ctx, http.MethodGet, rawURL, nil)
	if err != nil {
		return nil, err
	}
	// A recognizable UA; some podcast hosts 403 empty/default agents.
	req.Header.Set("User-Agent", "Bookhoard/1.0 (podcast fetcher; +https://github.com/bookhoard)")
	req.Header.Set("Accept", "*/*")
	if etag != "" {
		req.Header.Set("If-None-Match", etag)
	}
	if lastModified != "" {
		req.Header.Set("If-Modified-Since", lastModified)
	}

	resp, err := podcastHTTPClientFactory().Do(req)
	if err != nil {
		// Unwrap redirect/scheme guard errors so callers can classify.
		return nil, err
	}
	defer func() { _ = resp.Body.Close() }()

	res := &fetchResult{
		FinalURL:   resp.Request.URL.String(),
		ETag:       resp.Header.Get("ETag"),
		LastModified: resp.Header.Get("Last-Modified"),
		StatusCode: resp.StatusCode,
	}
	if resp.StatusCode == http.StatusNotModified {
		res.NotModified = true
		return res, nil
	}
	if resp.StatusCode != http.StatusOK {
		return res, fmt.Errorf("fetch %s: HTTP %d", rawURL, resp.StatusCode)
	}

	body, err := io.ReadAll(io.LimitReader(resp.Body, maxSize+1))
	if err != nil {
		return res, fmt.Errorf("fetch %s: %w", rawURL, err)
	}
	if int64(len(body)) > maxSize {
		return res, fmt.Errorf("fetch %s: response exceeds %d byte cap", rawURL, maxSize)
	}
	res.Body = body
	return res, nil
}