Merge pull request #1975 from lightpanda-io/percent-encode-path

fix: percent-encode pathname in URL.setPathname per URL spec

src/browser/URL.zig

@@ -204,7 +204,7 @@ pub fn ensureEncoded(allocator: Allocator, url: [:0]const u8) ![:0]const u8 {
     return buf.items[0 .. buf.items.len - 1 :0];
 }
 
-const EncodeSet = enum { path, query, userinfo };
+const EncodeSet = enum { path, query, userinfo, fragment };
 
 fn percentEncodeSegment(allocator: Allocator, segment: []const u8, comptime encode_set: EncodeSet) ![]const u8 {
     // Check if encoding is needed
@@ -256,8 +256,10 @@ fn shouldPercentEncode(c: u8, comptime encode_set: EncodeSet) bool {
         ';', '=' => encode_set == .userinfo,
         // Separators: userinfo must encode these
         '/', ':', '@' => encode_set == .userinfo,
-        // '?' is allowed in queries but not in paths or userinfo
+        // '?' is allowed in queries only
         '?' => encode_set != .query,
+        // '#' is allowed in fragments only
+        '#' => encode_set != .fragment,
         // Everything else needs encoding (including space)
         else => true,
     };
@@ -595,11 +597,13 @@ pub fn setPathname(current: [:0]const u8, value: []const u8, allocator: Allocato
     const search = getSearch(current);
     const hash = getHash(current);
 
+    const encoded = try percentEncodeSegment(allocator, value, .path);
+
     // Add / prefix if not present and value is not empty
-    const pathname = if (value.len > 0 and value[0] != '/')
-        try std.fmt.allocPrint(allocator, "/{s}", .{value})
+    const pathname = if (encoded.len > 0 and encoded[0] != '/')
+        try std.fmt.allocPrint(allocator, "/{s}", .{encoded})
     else
-        value;
+        encoded;
 
     return buildUrl(allocator, protocol, host, pathname, search, hash);
 }
@@ -610,11 +614,13 @@ pub fn setSearch(current: [:0]const u8, value: []const u8, allocator: Allocator)
     const pathname = getPathname(current);
     const hash = getHash(current);
 
+    const encoded = try percentEncodeSegment(allocator, value, .query);
+
     // Add ? prefix if not present and value is not empty
-    const search = if (value.len > 0 and value[0] != '?')
-        try std.fmt.allocPrint(allocator, "?{s}", .{value})
+    const search = if (encoded.len > 0 and value[0] != '?')
+        try std.fmt.allocPrint(allocator, "?{s}", .{encoded})
     else
-        value;
+        encoded;
 
     return buildUrl(allocator, protocol, host, pathname, search, hash);
 }
@@ -625,11 +631,13 @@ pub fn setHash(current: [:0]const u8, value: []const u8, allocator: Allocator) !
     const pathname = getPathname(current);
     const search = getSearch(current);
 
+    const encoded = try percentEncodeSegment(allocator, value, .fragment);
+
     // Add # prefix if not present and value is not empty
-    const hash = if (value.len > 0 and value[0] != '#')
-        try std.fmt.allocPrint(allocator, "#{s}", .{value})
+    const hash = if (encoded.len > 0 and encoded[0] != '#')
+        try std.fmt.allocPrint(allocator, "#{s}", .{encoded})
     else
-        value;
+        encoded;
 
     return buildUrl(allocator, protocol, host, pathname, search, hash);
 }
@@ -1422,3 +1430,22 @@ test "URL: getHost" {
     try testing.expectEqualSlices(u8, "example.com:8080", getHost("https://user:pass@example.com:8080/page"));
     try testing.expectEqualSlices(u8, "", getHost("not-a-url"));
 }
+
+test "URL: setPathname percent-encodes" {
+    // Use arena allocator to match production usage (setPathname makes intermediate allocations)
+    var arena = std.heap.ArenaAllocator.init(testing.allocator);
+    defer arena.deinit();
+    const allocator = arena.allocator();
+
+    // Spaces must be encoded as %20
+    const result1 = try setPathname("http://a/", "c d", allocator);
+    try testing.expectEqualSlices(u8, "http://a/c%20d", result1);
+
+    // Already-encoded sequences must not be double-encoded
+    const result2 = try setPathname("https://example.com/path", "/already%20encoded", allocator);
+    try testing.expectEqualSlices(u8, "https://example.com/already%20encoded", result2);
+
+    // Query and hash must be preserved
+    const result3 = try setPathname("https://example.com/path?a=b#hash", "/new path", allocator);
+    try testing.expectEqualSlices(u8, "https://example.com/new%20path?a=b#hash", result3);
+}

src/browser/tests/url.html

@@ -591,6 +591,35 @@
   testing.expectEqual('/new/path', url.pathname);
 }
 
+// Pathname setter must percent-encode spaces and special characters
+{
+  const url = new URL('http://a/');
+  url.pathname = 'c d';
+  testing.expectEqual('http://a/c%20d', url.href);
+}
+
+{
+  const url = new URL('https://example.com/path');
+  url.pathname = '/path with spaces/file name';
+  testing.expectEqual('https://example.com/path%20with%20spaces/file%20name', url.href);
+  testing.expectEqual('/path%20with%20spaces/file%20name', url.pathname);
+}
+
+// Already-encoded sequences should not be double-encoded
+{
+  const url = new URL('https://example.com/path');
+  url.pathname = '/already%20encoded';
+  testing.expectEqual('https://example.com/already%20encoded', url.href);
+}
+
+// This is the exact check the URL polyfill uses to decide if native URL is sufficient
+{
+  const url = new URL('b', 'http://a');
+  url.pathname = 'c d';
+  testing.expectEqual('http://a/c%20d', url.href);
+  testing.expectEqual(true, !!url.searchParams);
+}
+
 {
   const url = new URL('https://example.com/path');
   url.search = '?a=b';
@@ -656,6 +685,20 @@
   testing.expectEqual('', url.hash);
 }
 
+{
+  const url = new URL('https://example.com/path');
+  url.hash = '#a b';
+  testing.expectEqual('https://example.com/path#a%20b', url.href);
+  testing.expectEqual('#a%20b', url.hash);
+}
+
+{
+  const url = new URL('https://example.com/path');
+  url.hash = 'a b';
+  testing.expectEqual('https://example.com/path#a%20b', url.href);
+  testing.expectEqual('#a%20b', url.hash);
+}
+
 {
   const url = new URL('https://example.com/path?a=b');
   url.search = '';
@@ -673,6 +716,20 @@
   testing.expectEqual(null, url.searchParams.get('a'));
 }
 
+{
+  const url = new URL('https://example.com/path?a=b');
+  const sp = url.searchParams;
+  testing.expectEqual('b', sp.get('a'));
+  url.search = 'c=d b';
+
+  testing.expectEqual('d b', url.searchParams.get('c'));
+  testing.expectEqual(null, url.searchParams.get('a'));
+
+  url.search = 'c d=d b';
+  testing.expectEqual('d b', url.searchParams.get('c d'));
+  testing.expectEqual(null, url.searchParams.get('c'));
+}
+
 {
   const url = new URL('https://example.com/path?a=b');
   const sp = url.searchParams;