public/browser
1
0
Fork 0
mirror of https://github.com/lightpanda-io/browser.git synced 2026-03-21 20:24:42 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

Set charset based on BOM

Browse Source 
Small follow up to https://github.com/lightpanda-io/browser/pull/1837 If we
sniff the content type from the byte order mark (BOM), then we should set the
charset. This has higher precedence than sniffing the content type from the
content of the document (e.g. meta tags)
This commit is contained in:
Karl Seguin
2026-03-16 17:54:01 +08:00
parent 18b635936c
commit 422320d9ac
1 changed files with 36 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
src/browser/Mime.zig
View File

@@ -309,15 +309,30 @@ pub fn sniff(body: []const u8) ?Mime {
if (content[0] != '<') {
if (std.mem.startsWith(u8, content, &.{ 0xEF, 0xBB, 0xBF })) {
// UTF-8 BOM
return .{ .content_type = .{ .text_plain = {} } };
return .{
.content_type = .{ .text_plain = {} },
.charset = default_charset,
.charset_len = default_charset_len,
.is_default_charset = false,
};
}
if (std.mem.startsWith(u8, content, &.{ 0xFE, 0xFF })) {
// UTF-16 big-endian BOM
return .{ .content_type = .{ .text_plain = {} } };
return .{
.content_type = .{ .text_plain = {} },
.charset = .{ 'U', 'T', 'F', '-', '1', '6', 'B', 'E' } ++ .{0} ** 33,
.charset_len = 8,
.is_default_charset = false,
};
}
if (std.mem.startsWith(u8, content, &.{ 0xFF, 0xFE })) {
// UTF-16 little-endian BOM
return .{ .content_type = .{ .text_plain = {} } };
return .{
.content_type = .{ .text_plain = {} },
.charset = .{ 'U', 'T', 'F', '-', '1', '6', 'L', 'E' } ++ .{0} ** 33,
.charset_len = 8,
.is_default_charset = false,
};
}
return null;
}
@@ -671,6 +686,24 @@ test "Mime: sniff" {
try expectHTML("<!-->");
try expectHTML(" \n\t <!-->");
{
const mime = Mime.sniff(&.{ 0xEF, 0xBB, 0xBF }).?;
try testing.expectEqual(.text_plain, std.meta.activeTag(mime.content_type));
try testing.expectEqual("UTF-8", mime.charsetString());
}
{
const mime = Mime.sniff(&.{ 0xFE, 0xFF }).?;
try testing.expectEqual(.text_plain, std.meta.activeTag(mime.content_type));
try testing.expectEqual("UTF-16BE", mime.charsetString());
}
{
const mime = Mime.sniff(&.{ 0xFF, 0xFE }).?;
try testing.expectEqual(.text_plain, std.meta.activeTag(mime.content_type));
try testing.expectEqual("UTF-16LE", mime.charsetString());
}
}
const Expectation = struct {