From 9d80f7fd68c5a1c243f1d90a05d8fec028f1c9e8 Mon Sep 17 00:00:00 2001
From: tobi <31960611+tsmethurst@users.noreply.github.com>
Date: Mon, 22 Jan 2024 15:33:01 +0100
Subject: [feature] Allow "charset=utf8" in incoming AP POST requests (#2564)

* [feature] Allow "charset=utf8" in incoming AP POST requests

* changed my mind

* document POSTing to a GtS inbox

* correct link
---
 internal/federation/federatingactor.go      | 17 +++++++++++------
 internal/federation/federatingactor_test.go | 20 ++++++++++++++++++++
 2 files changed, 31 insertions(+), 6 deletions(-)

(limited to 'internal')

diff --git a/internal/federation/federatingactor.go b/internal/federation/federatingactor.go
index 8fc47462d..b91165bb1 100644
--- a/internal/federation/federatingactor.go
+++ b/internal/federation/federatingactor.go
@@ -40,7 +40,7 @@ import (
 // - application/activity+json
 // - application/ld+json;profile=https://w3.org/ns/activitystreams
 //
-// Where for the above we are leniant with whitespace and quotes.
+// Where for the above we are leniant with whitespace, quotes, and charset.
 func IsASMediaType(ct string) bool {
 	var (
 		// First content-type part,
@@ -48,7 +48,8 @@ func IsASMediaType(ct string) bool {
 		p1 string = ct //nolint:revive
 
 		// Second content-type part,
-		// contains AS IRI if provided
+		// contains AS IRI or charset
+		// if provided.
 		p2 string
 	)
 
@@ -56,7 +57,11 @@ func IsASMediaType(ct string) bool {
 	sep := strings.IndexByte(ct, ';')
 	if sep >= 0 {
 		p1 = ct[:sep]
+
+		// Trim all start/end
+		// space of second part.
 		p2 = ct[sep+1:]
+		p2 = strings.Trim(p2, " ")
 	}
 
 	// Trim any ending space from the
@@ -65,12 +70,12 @@ func IsASMediaType(ct string) bool {
 
 	switch p1 {
 	case "application/activity+json":
-		return p2 == ""
+		// Accept with or without charset.
+		// This should be case insensitive.
+		// https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Content-Type#charset
+		return p2 == "" || strings.EqualFold(p2, "charset=utf-8")
 
 	case "application/ld+json":
-		// Trim all start/end space.
-		p2 = strings.Trim(p2, " ")
-
 		// Drop any quotes around the URI str.
 		p2 = strings.ReplaceAll(p2, "\"", "")
 
diff --git a/internal/federation/federatingactor_test.go b/internal/federation/federatingactor_test.go
index 348d501d6..d07b56537 100644
--- a/internal/federation/federatingactor_test.go
+++ b/internal/federation/federatingactor_test.go
@@ -164,6 +164,22 @@ func TestIsASMediaType(t *testing.T) {
 			Input:  "application/activity+json",
 			Expect: true,
 		},
+		{
+			Input:  "application/activity+json; charset=utf-8",
+			Expect: true,
+		},
+		{
+			Input:  "application/activity+json;charset=utf-8",
+			Expect: true,
+		},
+		{
+			Input:  "application/activity+json ;charset=utf-8",
+			Expect: true,
+		},
+		{
+			Input:  "application/activity+json ; charset=utf-8",
+			Expect: true,
+		},
 		{
 			Input:  "application/ld+json;profile=https://www.w3.org/ns/activitystreams",
 			Expect: true,
@@ -196,6 +212,10 @@ func TestIsASMediaType(t *testing.T) {
 			Input:  "application/ld+json; profile=\"https://www.w3.org/ns/activitystreams\"",
 			Expect: true,
 		},
+		{
+			Input:  "application/ld+json",
+			Expect: false,
+		},
 	} {
 		if federation.IsASMediaType(test.Input) != test.Expect {
 			t.Errorf("did not get expected result %v for input: %s", test.Expect, test.Input)
-- 
cgit v1.2.3