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>
183 lines
4.3 KiB
Go
183 lines
4.3 KiB
Go
package handlers
|
|
|
|
import (
|
|
"errors"
|
|
"io"
|
|
"net/http"
|
|
"strconv"
|
|
"time"
|
|
|
|
"github.com/go-chi/chi/v5"
|
|
"sneak.berlin/go/pixa/internal/httpfetcher"
|
|
"sneak.berlin/go/pixa/internal/imgcache"
|
|
)
|
|
|
|
// HandleImage handles the main image proxy route:
|
|
// /v1/image/<host>/<path>/<width>x<height>.<format>
|
|
func (s *Handlers) HandleImage() http.HandlerFunc {
|
|
return func(w http.ResponseWriter, r *http.Request) {
|
|
ctx := r.Context()
|
|
|
|
// Get the wildcard path from chi
|
|
pathParam := chi.URLParam(r, "*")
|
|
|
|
// Parse the URL path
|
|
parsed, err := imgcache.ParseImagePath(pathParam)
|
|
if err != nil {
|
|
s.log.Warn("failed to parse image URL",
|
|
"path", pathParam,
|
|
"error", err,
|
|
)
|
|
s.respondError(w, "invalid image URL: "+err.Error(), http.StatusBadRequest)
|
|
|
|
return
|
|
}
|
|
|
|
// Convert to ImageRequest
|
|
req := parsed.ToImageRequest()
|
|
|
|
// Parse signature params from query string
|
|
query := r.URL.Query()
|
|
req.Signature = query.Get("sig")
|
|
|
|
if expStr := query.Get("exp"); expStr != "" {
|
|
if exp, err := strconv.ParseInt(expStr, 10, 64); err == nil {
|
|
req.Expires = time.Unix(exp, 0)
|
|
}
|
|
}
|
|
|
|
// Parse optional quality and fit params
|
|
if qStr := query.Get("q"); qStr != "" {
|
|
if q, err := strconv.Atoi(qStr); err == nil && q > 0 && q <= 100 {
|
|
req.Quality = q
|
|
}
|
|
}
|
|
|
|
if fit := query.Get("fit"); fit != "" {
|
|
req.FitMode = imgcache.FitMode(fit)
|
|
if err := imgcache.ValidateFitMode(req.FitMode); err != nil {
|
|
s.respondError(w, "invalid fit mode: "+fit, http.StatusBadRequest)
|
|
|
|
return
|
|
}
|
|
}
|
|
|
|
// Default quality if not set
|
|
if req.Quality == 0 {
|
|
req.Quality = 85
|
|
}
|
|
|
|
// Default fit mode if not set
|
|
if req.FitMode == "" {
|
|
req.FitMode = imgcache.FitCover
|
|
}
|
|
|
|
// Validate signature if required
|
|
if err := s.imgSvc.ValidateRequest(req); err != nil {
|
|
s.log.Warn("signature validation failed",
|
|
"host", req.SourceHost,
|
|
"path", req.SourcePath,
|
|
"error", err,
|
|
)
|
|
s.respondError(w, "unauthorized", http.StatusUnauthorized)
|
|
|
|
return
|
|
}
|
|
|
|
// Get cache key for logging
|
|
cacheKey := imgcache.CacheKey(req)
|
|
|
|
// Get the image (from cache or fetch/process)
|
|
startTime := time.Now()
|
|
resp, err := s.imgSvc.Get(ctx, req)
|
|
if err != nil {
|
|
s.log.Error("failed to get image",
|
|
"host", req.SourceHost,
|
|
"path", req.SourcePath,
|
|
"error", err,
|
|
)
|
|
|
|
// Check for specific error types
|
|
if errors.Is(err, httpfetcher.ErrSSRFBlocked) {
|
|
s.respondError(w, "forbidden", http.StatusForbidden)
|
|
|
|
return
|
|
}
|
|
|
|
if errors.Is(err, httpfetcher.ErrUpstreamError) {
|
|
s.respondError(w, "upstream error", http.StatusBadGateway)
|
|
|
|
return
|
|
}
|
|
|
|
s.respondError(w, "internal error", http.StatusInternalServerError)
|
|
|
|
return
|
|
}
|
|
defer func() { _ = resp.Content.Close() }()
|
|
|
|
// Set response headers
|
|
w.Header().Set("Content-Type", resp.ContentType)
|
|
if resp.ContentLength > 0 {
|
|
w.Header().Set("Content-Length", strconv.FormatInt(resp.ContentLength, 10))
|
|
}
|
|
|
|
// Cache control headers
|
|
w.Header().Set("Cache-Control", "public, max-age=31536000, immutable")
|
|
w.Header().Set("X-Pixa-Cache", string(resp.CacheStatus))
|
|
|
|
if resp.ETag != "" {
|
|
w.Header().Set("ETag", resp.ETag)
|
|
|
|
// Check for conditional request (If-None-Match)
|
|
if ifNoneMatch := r.Header.Get("If-None-Match"); ifNoneMatch != "" {
|
|
if ifNoneMatch == resp.ETag {
|
|
w.WriteHeader(http.StatusNotModified)
|
|
|
|
return
|
|
}
|
|
}
|
|
}
|
|
|
|
// Handle HEAD request - return headers only
|
|
if r.Method == http.MethodHead {
|
|
w.WriteHeader(http.StatusOK)
|
|
|
|
return
|
|
}
|
|
|
|
// Stream the response
|
|
w.WriteHeader(http.StatusOK)
|
|
|
|
servedBytes, err := io.Copy(w, resp.Content)
|
|
if err != nil {
|
|
s.log.Error("failed to write response",
|
|
"error", err,
|
|
)
|
|
}
|
|
|
|
// Log cache status and timing after serving
|
|
duration := time.Since(startTime)
|
|
s.log.Info("image served",
|
|
"cache_key", cacheKey,
|
|
"cache_status", resp.CacheStatus,
|
|
"duration_ms", duration.Milliseconds(),
|
|
"format", req.Format,
|
|
"served_bytes", servedBytes,
|
|
"fetched_bytes", resp.FetchedBytes,
|
|
)
|
|
}
|
|
}
|
|
|
|
// HandleRobotsTxt serves robots.txt to prevent search engine crawling.
|
|
func (s *Handlers) HandleRobotsTxt() http.HandlerFunc {
|
|
robotsTxt := []byte("User-agent: *\nDisallow: /\n")
|
|
|
|
return func(w http.ResponseWriter, _ *http.Request) {
|
|
w.Header().Set("Content-Type", "text/plain")
|
|
w.Header().Set("Content-Length", strconv.Itoa(len(robotsTxt)))
|
|
w.WriteHeader(http.StatusOK)
|
|
_, _ = w.Write(robotsTxt)
|
|
}
|
|
}
|