clawbot
b6e9ac2a93
All checks were successful
check / check (push) Successful in 4s
Extracts the HTTP fetcher concern out of `internal/imgcache/` into its own `internal/httpfetcher/` package, per the plan in [issue #39](#39). This is one of four planned extractions; only the fetcher is moved here so the diff stays reviewable. The remaining three (signature, magic, urlparser) will land in separate PRs. ## What moved From `internal/imgcache/fetcher.go` and `internal/imgcache/mock_fetcher.go` into `internal/httpfetcher/`: - `HTTPFetcher` type, its `New` constructor, and `Config` (formerly `FetcherConfig`) with `DefaultConfig` - SSRF-safe dialer, `validateURL`, `isPrivateIP`, `isLocalhost`, `extractHost` - Per-host connection semaphore (rate limiting) and `limitedReader` - Content-type validation (`isAllowedContentType`, `detectContentTypeFromPath`) - All related error values (`ErrSSRFBlocked`, `ErrUpstreamError`, `ErrUpstreamTimeout`, `ErrPayloadTooLarge`, `ErrDisallowedContentType`) - All related constants (`DefaultFetchTimeout`, `DefaultMaxPayloadBytes`, `DefaultMaxConnectionsPerHost`, etc.) - The `Fetcher` interface and `FetchResult` type (moved here to keep the import edge one-way: `imgcache` depends on `httpfetcher`, never the reverse) - `MockFetcher` test helper ## Renames (no stuttering) - `NewHTTPFetcher` → `httpfetcher.New` - `FetcherConfig` → `httpfetcher.Config` - `DefaultFetcherConfig` → `httpfetcher.DefaultConfig` - `NewMockFetcher` → `httpfetcher.NewMock` The `ServiceConfig.FetcherConfig` field name is retained — it describes what kind of config the field holds (not a stutter). ## Behavior Pure refactor. No behavior changes. All existing tests pass; unit tests for the new package are included. `docker build .` passes (fmt-check, lint, test, build). refs #39 Co-authored-by: clawbot <clawbot@eeqj.de> Co-authored-by: Jeffrey Paul <sneak@noreply.example.org> Reviewed-on: #43 Co-authored-by: clawbot <clawbot@noreply.example.org> Co-committed-by: clawbot <clawbot@noreply.example.org>
116 lines
2.6 KiB
Go
116 lines
2.6 KiB
Go
package httpfetcher
|
|
|
|
import (
|
|
"context"
|
|
"errors"
|
|
"fmt"
|
|
"io"
|
|
"io/fs"
|
|
"net/http"
|
|
"strings"
|
|
)
|
|
|
|
// MockFetcher implements Fetcher using an embedded filesystem.
|
|
// Files are organized as: hostname/path/to/file.ext
|
|
// URLs like https://example.com/images/photo.jpg map to example.com/images/photo.jpg.
|
|
type MockFetcher struct {
|
|
fs fs.FS
|
|
}
|
|
|
|
// NewMock creates a new mock fetcher backed by the given filesystem.
|
|
func NewMock(fsys fs.FS) *MockFetcher {
|
|
return &MockFetcher{fs: fsys}
|
|
}
|
|
|
|
// Fetch retrieves content from the mock filesystem.
|
|
func (m *MockFetcher) Fetch(ctx context.Context, url string) (*FetchResult, error) {
|
|
// Check context cancellation
|
|
select {
|
|
case <-ctx.Done():
|
|
return nil, ctx.Err()
|
|
default:
|
|
}
|
|
|
|
// Parse URL to get filesystem path
|
|
path, err := urlToFSPath(url)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
// Open the file
|
|
f, err := m.fs.Open(path)
|
|
if err != nil {
|
|
if errors.Is(err, fs.ErrNotExist) {
|
|
return nil, fmt.Errorf("%w: status 404", ErrUpstreamError)
|
|
}
|
|
|
|
return nil, fmt.Errorf("failed to open mock file: %w", err)
|
|
}
|
|
|
|
// Get file info for content length
|
|
stat, err := f.Stat()
|
|
if err != nil {
|
|
_ = f.Close()
|
|
|
|
return nil, fmt.Errorf("failed to stat mock file: %w", err)
|
|
}
|
|
|
|
// Detect content type from extension
|
|
contentType := detectContentTypeFromPath(path)
|
|
|
|
return &FetchResult{
|
|
Content: f.(io.ReadCloser),
|
|
ContentLength: stat.Size(),
|
|
ContentType: contentType,
|
|
Headers: make(http.Header),
|
|
}, nil
|
|
}
|
|
|
|
// urlToFSPath converts a URL to a filesystem path.
|
|
// https://example.com/images/photo.jpg -> example.com/images/photo.jpg
|
|
func urlToFSPath(rawURL string) (string, error) {
|
|
// Strip scheme
|
|
url := rawURL
|
|
if idx := strings.Index(url, "://"); idx != -1 {
|
|
url = url[idx+3:]
|
|
}
|
|
|
|
// Remove query string
|
|
if idx := strings.Index(url, "?"); idx != -1 {
|
|
url = url[:idx]
|
|
}
|
|
|
|
// Remove fragment
|
|
if idx := strings.Index(url, "#"); idx != -1 {
|
|
url = url[:idx]
|
|
}
|
|
|
|
if url == "" {
|
|
return "", errors.New("empty URL path")
|
|
}
|
|
|
|
return url, nil
|
|
}
|
|
|
|
// detectContentTypeFromPath returns the MIME type based on file extension.
|
|
func detectContentTypeFromPath(path string) string {
|
|
path = strings.ToLower(path)
|
|
|
|
switch {
|
|
case strings.HasSuffix(path, ".jpg"), strings.HasSuffix(path, ".jpeg"):
|
|
return "image/jpeg"
|
|
case strings.HasSuffix(path, ".png"):
|
|
return "image/png"
|
|
case strings.HasSuffix(path, ".gif"):
|
|
return "image/gif"
|
|
case strings.HasSuffix(path, ".webp"):
|
|
return "image/webp"
|
|
case strings.HasSuffix(path, ".avif"):
|
|
return "image/avif"
|
|
case strings.HasSuffix(path, ".svg"):
|
|
return "image/svg+xml"
|
|
default:
|
|
return "application/octet-stream"
|
|
}
|
|
}
|