mirror of
https://github.com/RGBCube/serenity
synced 2025-07-27 06:47:35 +00:00
LibJS: Transcode UTF-8 strings to UTF-16 and add UTF-16 accessors
LibJS parses JavaScript as UTF-8, so when creating a string, we must transcode it to UTF-16 to handle encoded surrogate pairs. For example, consider the following string: "\ud83d\ude00" The UTF-8 encoding of this surrogate pair is: 0xf0 0x9f 0x98 0x80 However, LibJS will currently store the two surrogates individually as UTF-8 encoded bytes, rather than combining the pair: 0xed 0xa0 0xb8, 0xed 0xb8 0x80 These are not equivalent. So, as String.prototype becomes UTF-16 aware, this encoding will no longer work for abstractions like strict equality.
This commit is contained in:
parent
0e25d2393f
commit
0c42aece36
4 changed files with 73 additions and 3 deletions
|
@ -7,6 +7,7 @@
|
|||
#pragma once
|
||||
|
||||
#include <AK/String.h>
|
||||
#include <AK/Vector.h>
|
||||
#include <LibJS/Heap/Cell.h>
|
||||
|
||||
namespace JS {
|
||||
|
@ -16,14 +17,21 @@ public:
|
|||
explicit PrimitiveString(String);
|
||||
virtual ~PrimitiveString();
|
||||
|
||||
const String& string() const { return m_string; }
|
||||
String const& string() const { return m_string; }
|
||||
|
||||
Vector<u16> const& utf16_string() const;
|
||||
Utf16View utf16_string_view() const;
|
||||
|
||||
private:
|
||||
virtual const char* class_name() const override { return "PrimitiveString"; }
|
||||
|
||||
String m_string;
|
||||
mutable Vector<u16> m_utf16_string;
|
||||
};
|
||||
|
||||
PrimitiveString* js_string(Heap&, Utf16View const&);
|
||||
PrimitiveString* js_string(VM&, Utf16View const&);
|
||||
|
||||
PrimitiveString* js_string(Heap&, String);
|
||||
PrimitiveString* js_string(VM&, String);
|
||||
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue