pixa/internal/httpfetcher/httpfetcher_internal_test.go

package httpfetcher

import (
	"context"
	"errors"
	"io"
	"net"
	"net/url"
	"testing"
	"testing/fstest"
	"time"

	"sneak.berlin/go/pixa/internal/imagerequest"
)

// testHost is the hostname used by mock fetch tests.
const testHost = "example.com"

func TestIsAllowedContentType(t *testing.T) {
	t.Parallel()

	f := New(&Config{
		Timeout:               30 * time.Second,
		MaxResponseSize:       50 << 20,
		MaxConnectionsPerHost: 20,
		MaxConnections:        64,
	})

	tests := []struct {
		contentType string
		want        bool
	}{
		{imagerequest.FormatJPEG.MIMEType(), true},
		{imagerequest.FormatPNG.MIMEType(), true},
		{imagerequest.FormatWebP.MIMEType(), true},
		{"image/jpeg; charset=utf-8", true},
		{"IMAGE/JPEG", true},
		{"text/html", false},
		{contentTypeOctetStream, false},
		{"", false},
	}

	for _, tc := range tests {
		t.Run(tc.contentType, func(t *testing.T) {
			t.Parallel()

			got := f.isAllowedContentType(tc.contentType)
			if got != tc.want {
				t.Errorf("isAllowedContentType(%q) = %v, want %v", tc.contentType, got, tc.want)
			}
		})
	}
}

func TestIsLocalhost(t *testing.T) {
	t.Parallel()

	tests := []struct {
		host string
		want bool
	}{
		{"localhost", true},
		{"LOCALHOST", true},
		{localhostIPv4, true},
		{localhostIPv6, true},
		{"[::1]", true},
		{"foo.localhost", true},
		{"foo.local", true},
		{testHost, false},
		{"127.0.0.2", false}, // Handled by isPrivateIP, not isLocalhost string match
	}

	for _, tc := range tests {
		t.Run(tc.host, func(t *testing.T) {
			t.Parallel()

			got := isLocalhost(tc.host)
			if got != tc.want {
				t.Errorf("isLocalhost(%q) = %v, want %v", tc.host, got, tc.want)
			}
		})
	}
}

func TestIsPrivateIP(t *testing.T) {
	t.Parallel()

	tests := []struct {
		ip   string
		want bool
	}{
		{localhostIPv4, true},           // loopback
		{"10.0.0.1", true},              // private
		{"192.168.1.1", true},           // private
		{"172.16.0.1", true},            // private
		{"169.254.1.1", true},           // link-local
		{"0.0.0.0", true},               // unspecified
		{"224.0.0.1", true},             // multicast
		{localhostIPv6, true},           // IPv6 loopback
		{"fe80::1", true},               // IPv6 link-local
		{"8.8.8.8", false},              // public
		{"2001:4860:4860::8888", false}, // public IPv6
	}

	for _, tc := range tests {
		t.Run(tc.ip, func(t *testing.T) {
			t.Parallel()

			ip := net.ParseIP(tc.ip)
			if ip == nil {
				t.Fatalf("failed to parse IP %q", tc.ip)
			}

			got := isPrivateIP(ip)
			if got != tc.want {
				t.Errorf("isPrivateIP(%q) = %v, want %v", tc.ip, got, tc.want)
			}
		})
	}

	if !isPrivateIP(nil) {
		t.Error("isPrivateIP(nil) should return true")
	}
}

// TestIsPrivateIPJudgesEmbeddedIPv4Address checks IPv6 addresses that hold an
// IPv4 address in their last four bytes: the IPv4-compatible form (::/96) and
// the NAT64 form (64:ff9b::/96). One holding a loopback, private or
// link-local IPv4 address is refused as that address is, and one holding a
// public IPv4 address in the IPv4-compatible form passes.
func TestIsPrivateIPJudgesEmbeddedIPv4Address(t *testing.T) {
	t.Parallel()

	tests := []struct {
		ip   string
		want bool
	}{
		{"::127.0.0.1", true},       // loopback
		{"::10.0.0.1", true},        // private
		{"::169.254.169.254", true}, // link-local
		{"64:ff9b::7f00:1", true},   // NAT64 form of 127.0.0.1
		{"::8.8.8.8", false},        // public
	}

	for _, tc := range tests {
		t.Run(tc.ip, func(t *testing.T) {
			t.Parallel()

			ip := net.ParseIP(tc.ip)
			if ip == nil {
				t.Fatalf("failed to parse IP %q", tc.ip)
			}

			got := isPrivateIP(ip)
			t.Logf("isPrivateIP(%s) = %v", ip, got)

			if got != tc.want {
				t.Errorf("isPrivateIP(%q) = %v, want %v", tc.ip, got, tc.want)
			}
		})
	}
}

func TestValidateURL_RejectsNonHTTPS(t *testing.T) {
	t.Parallel()

	err := validateURL(t.Context(), &url.URL{Scheme: "http", Host: testHost}, false)
	if !errors.Is(err, ErrUnsupportedScheme) {
		t.Errorf("validateURL http = %v, want ErrUnsupportedScheme", err)
	}
}

func TestValidateURL_AllowsHTTPWhenConfigured(t *testing.T) {
	t.Parallel()

	// Use a host that won't resolve (explicit .invalid TLD) so we don't hit DNS.
	err := validateURL(t.Context(),
		&url.URL{Scheme: "http", Host: "nonexistent.invalid"}, true)
	// We expect a host resolution error, not ErrUnsupportedScheme.
	if errors.Is(err, ErrUnsupportedScheme) {
		t.Error("validateURL with AllowHTTP should not return ErrUnsupportedScheme")
	}
}

func TestValidateURL_RejectsLocalhost(t *testing.T) {
	t.Parallel()

	err := validateURL(t.Context(), &url.URL{Scheme: "https", Host: "localhost"}, false)
	if !errors.Is(err, ErrSSRFBlocked) {
		t.Errorf("validateURL localhost = %v, want ErrSSRFBlocked", err)
	}
}

func TestValidateURL_EmptyHost(t *testing.T) {
	t.Parallel()

	err := validateURL(t.Context(), &url.URL{Scheme: "https"}, false)
	if !errors.Is(err, ErrInvalidHost) {
		t.Errorf("validateURL empty host = %v, want ErrInvalidHost", err)
	}
}

func TestMockFetcher_FetchesFile(t *testing.T) {
	t.Parallel()

	mockFS := fstest.MapFS{
		"example.com/images/photo.jpg": &fstest.MapFile{Data: []byte("fake-jpeg-data")},
	}

	m := NewMock(mockFS)

	result, err := m.Fetch(context.Background(),
		imagerequest.Source{Host: testHost, Path: "/images/photo.jpg"}, "", "")
	if err != nil {
		t.Fatalf("Fetch() error = %v", err)
	}

	defer func() { _ = result.Content.Close() }()

	if result.ContentType != imagerequest.FormatJPEG.MIMEType() {
		t.Errorf("ContentType = %q, want image/jpeg", result.ContentType)
	}

	data, err := io.ReadAll(result.Content)
	if err != nil {
		t.Fatalf("read content: %v", err)
	}

	if string(data) != "fake-jpeg-data" {
		t.Errorf("Content = %q, want %q", string(data), "fake-jpeg-data")
	}

	if result.ContentLength != int64(len("fake-jpeg-data")) {
		t.Errorf("ContentLength = %d, want %d", result.ContentLength, len("fake-jpeg-data"))
	}
}

func TestMockFetcher_MissingFileReturnsUpstreamError(t *testing.T) {
	t.Parallel()

	mockFS := fstest.MapFS{}
	m := NewMock(mockFS)

	_, err := m.Fetch(context.Background(),
		imagerequest.Source{Host: testHost, Path: "/missing.jpg"}, "", "")
	if !errors.Is(err, ErrUpstreamError) {
		t.Errorf("Fetch() error = %v, want ErrUpstreamError", err)
	}
}

func TestMockFetcher_RespectsContextCancellation(t *testing.T) {
	t.Parallel()

	mockFS := fstest.MapFS{
		"example.com/photo.jpg": &fstest.MapFile{Data: []byte("data")},
	}
	m := NewMock(mockFS)

	ctx, cancel := context.WithCancel(context.Background())
	cancel()

	_, err := m.Fetch(ctx, imagerequest.Source{Host: testHost, Path: "/photo.jpg"}, "", "")
	if !errors.Is(err, context.Canceled) {
		t.Errorf("Fetch() error = %v, want context.Canceled", err)
	}
}

func TestDetectContentTypeFromPath(t *testing.T) {
	t.Parallel()

	tests := []struct {
		path string
		want string
	}{
		{"foo/bar.jpg", imagerequest.FormatJPEG.MIMEType()},
		{"foo/bar.JPG", imagerequest.FormatJPEG.MIMEType()},
		{"foo/bar.jpeg", imagerequest.FormatJPEG.MIMEType()},
		{"foo/bar.png", imagerequest.FormatPNG.MIMEType()},
		{"foo/bar.gif", imagerequest.FormatGIF.MIMEType()},
		{"foo/bar.webp", imagerequest.FormatWebP.MIMEType()},
		{"foo/bar.avif", imagerequest.FormatAVIF.MIMEType()},
		{"foo/bar.svg", contentTypeSVG},
		{"foo/bar.bin", contentTypeOctetStream},
		{"foo/bar", contentTypeOctetStream},
	}

	for _, tc := range tests {
		t.Run(tc.path, func(t *testing.T) {
			t.Parallel()

			got := detectContentTypeFromPath(tc.path)
			if got != tc.want {
				t.Errorf("detectContentTypeFromPath(%q) = %q, want %q", tc.path, got, tc.want)
			}
		})
	}
}

func TestLimitedReader_EnforcesLimit(t *testing.T) {
	t.Parallel()

	src := make([]byte, 100)
	r := &limitedReader{
		reader:    &byteReader{data: src},
		remaining: 50,
	}

	buf := make([]byte, 100)

	n, err := r.Read(buf)
	if err != nil {
		t.Fatalf("first Read error = %v", err)
	}

	if n > 50 {
		t.Errorf("read %d bytes, should be capped at 50", n)
	}

	// Drain until limit is exhausted.
	total := n
	for total < 50 {
		nn, err := r.Read(buf)
		if err != nil {
			t.Fatalf("during drain: %v", err)
		}

		total += nn
	}

	// Now the limit is exhausted — next read should error.
	_, err = r.Read(buf)
	if !errors.Is(err, ErrResponseTooLarge) {
		t.Errorf("exhausted Read error = %v, want ErrResponseTooLarge", err)
	}
}

// byteReader is a minimal io.Reader over a byte slice for testing.
type byteReader struct {
	data []byte
	pos  int
}

func (r *byteReader) Read(p []byte) (int, error) {
	if r.pos >= len(r.data) {
		return 0, io.EOF
	}

	n := copy(p, r.data[r.pos:])
	r.pos += n

	return n, nil
}