Send only the Referer's scheme and host to Sentry (closes #548)

A Sentry event kept the Referer header verbatim, and a Referer can be
an entrypoint URL: a sender that follows the README's http:// to
https:// redirect sends the URL it was redirected from, and a browser
sends the 404 page's URL under /h/ when it fetches that page's
stylesheet. The Sentry hook now keeps only the Referer's scheme and
host. The access log's reduction moves, unchanged, into a new package,
internal/referer, as SchemeAndHost; the access log and the Sentry hook
both call it there. The comment above sentryKeepsHeader and the
README's Sentry passage say so, and the README's Package Layout lists
the new package.

Model: opus-5-5

internal/referer/referer.go

@@ -0,0 +1,32 @@
+// Package referer reduces a Referer header to its scheme and host, so
+// that a URL path, which on the receiver route carries the entrypoint
+// UUID, never reaches a log line or an error report.
+package referer
+
+import "net/url"
+
+// redacted stands in for a Referer that cannot be reduced to its
+// scheme and host.
+const redacted = "(redacted)"
+
+// SchemeAndHost returns a Referer's scheme and host, never its path or
+// query. The path can be an entrypoint URL, which carries the UUID: a
+// sender that follows a redirect from http:// to https:// sends the
+// URL it was redirected from, and a browser sends the 404 page's URL
+// under /h/ when it fetches that page's stylesheet. A Referer without
+// both a scheme and a host comes back as "(redacted)".
+//
+// It is the access log's referer field, and the Referer header the
+// Sentry hook sends.
+func SchemeAndHost(referer string) string {
+	if referer == "" {
+		return ""
+	}
+
+	parsed, err := url.Parse(referer)
+	if err != nil || parsed.Scheme == "" || parsed.Host == "" {
+		return redacted
+	}
+
+	return parsed.Scheme + "://" + parsed.Host
+}

internal/referer/referer_test.go

@@ -0,0 +1,67 @@
+package referer_test
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"sneak.berlin/go/webhooker/internal/referer"
+)
+
+// entrypointUUID is the secret part of an entrypoint URL; no case may
+// return it.
+const entrypointUUID = "0b6f7d3e-6a39-4e3c-9f0a-2c4d8e1b5a77"
+
+// redacted is what SchemeAndHost returns for a Referer it cannot
+// reduce to a scheme and host.
+const redacted = "(redacted)"
+
+func TestSchemeAndHost(t *testing.T) {
+	t.Parallel()
+
+	for _, tc := range []struct {
+		name    string
+		referer string
+		want    string
+	}{
+		{
+			name:    "no Referer",
+			referer: "",
+			want:    "",
+		},
+		{
+			name: "entrypoint URL with a query",
+			referer: "http://webhooker.example/h/" + entrypointUUID +
+				"?src=ci",
+			want: "http://webhooker.example",
+		},
+		{
+			name:    "host with a port",
+			referer: "https://webhooker.example:8443/h/" + entrypointUUID,
+			want:    "https://webhooker.example:8443",
+		},
+		{
+			name:    "path without a scheme or host",
+			referer: "/h/" + entrypointUUID,
+			want:    redacted,
+		},
+		{
+			name:    "host without a scheme",
+			referer: "webhooker.example/h/" + entrypointUUID,
+			want:    redacted,
+		},
+		{
+			name:    "not a URL",
+			referer: "http://[::1/h/" + entrypointUUID,
+			want:    redacted,
+		},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			got := referer.SchemeAndHost(tc.referer)
+
+			assert.Equal(t, tc.want, got)
+			assert.NotContains(t, got, entrypointUUID)
+		})
+	}
+}