LibTextCodec: Make utf-16be and utf-16le codecs actually work

There were two problems:

1. They didn't handle surrogates
2. They used signed chars, leading to eg 0x00e4 being treated as 0xffe4

Also add a basic test that catches both issues.
There's some code duplication with Utf16CodePointIterator::operator*(),
but let's get things working first.

Tests/LibTextCodec/TestTextDecoders.cpp

@@ -23,3 +23,37 @@ TEST_CASE(test_utf8_decode)
 
     EXPECT(decoder.to_utf8(test_string) == test_string);
 }
+
+TEST_CASE(test_utf16be_decode)
+{
+    auto decoder = TextCodec::UTF16BEDecoder();
+    // This is the output of `python3 -c "print('säk😀'.encode('utf-16be'))"`.
+    auto test_string = "\x00s\x00\xe4\x00k\xd8=\xde\x00"sv;
+
+    Vector<u32> processed_code_points;
+    decoder.process(test_string, [&](u32 code_point) {
+        processed_code_points.append(code_point);
+    });
+    EXPECT(processed_code_points.size() == 4);
+    EXPECT(processed_code_points[0] == 0x73);
+    EXPECT(processed_code_points[1] == 0xE4);
+    EXPECT(processed_code_points[2] == 0x6B);
+    EXPECT(processed_code_points[3] == 0x1F600);
+}
+
+TEST_CASE(test_utf16le_decode)
+{
+    auto decoder = TextCodec::UTF16LEDecoder();
+    // This is the output of `python3 -c "print('säk😀'.encode('utf-16le'))"`.
+    auto test_string = "s\x00\xe4\x00k\x00=\xd8\x00\xde"sv;
+
+    Vector<u32> processed_code_points;
+    decoder.process(test_string, [&](u32 code_point) {
+        processed_code_points.append(code_point);
+    });
+    EXPECT(processed_code_points.size() == 4);
+    EXPECT(processed_code_points[0] == 0x73);
+    EXPECT(processed_code_points[1] == 0xE4);
+    EXPECT(processed_code_points[2] == 0x6B);
+    EXPECT(processed_code_points[3] == 0x1F600);
+}

Userland/Libraries/LibTextCodec/Decoder.cpp

@@ -7,11 +7,14 @@
 
 #include <AK/DeprecatedString.h>
 #include <AK/StringBuilder.h>
+#include <AK/Utf16View.h>
 #include <AK/Utf8View.h>
 #include <LibTextCodec/Decoder.h>
 
 namespace TextCodec {
 
+static constexpr u32 replacement_code_point = 0xfffd;
+
 namespace {
 Latin1Decoder s_latin1_decoder;
 UTF8Decoder s_utf8_decoder;
@@ -234,10 +237,40 @@ DeprecatedString UTF8Decoder::to_utf8(StringView input)
 
 void UTF16BEDecoder::process(StringView input, Function<void(u32)> on_code_point)
 {
+    // rfc2781, 2.2 Decoding UTF-16
     size_t utf16_length = input.length() - (input.length() % 2);
     for (size_t i = 0; i < utf16_length; i += 2) {
-        u16 code_point = (input[i] << 8) | input[i + 1];
-        on_code_point(code_point);
+        // 1) If W1 < 0xD800 or W1 > 0xDFFF, the character value U is the value
+        //    of W1. Terminate.
+        u16 w1 = (static_cast<u8>(input[i]) << 8) | static_cast<u8>(input[i + 1]);
+        if (!is_unicode_surrogate(w1)) {
+            on_code_point(w1);
+            continue;
+        }
+
+        // 2) Determine if W1 is between 0xD800 and 0xDBFF. If not, the sequence
+        //    is in error and no valid character can be obtained using W1.
+        //    Terminate.
+        // 3) If there is no W2 (that is, the sequence ends with W1), or if W2
+        //    is not between 0xDC00 and 0xDFFF, the sequence is in error.
+        //    Terminate.
+        if (!Utf16View::is_high_surrogate(w1) || i + 2 == utf16_length) {
+            on_code_point(replacement_code_point);
+            continue;
+        }
+
+        u16 w2 = (static_cast<u8>(input[i + 2]) << 8) | static_cast<u8>(input[i + 3]);
+        if (!Utf16View::is_low_surrogate(w2)) {
+            on_code_point(replacement_code_point);
+            continue;
+        }
+
+        // 4) Construct a 20-bit unsigned integer U', taking the 10 low-order
+        //    bits of W1 as its 10 high-order bits and the 10 low-order bits of
+        //    W2 as its 10 low-order bits.
+        // 5) Add 0x10000 to U' to obtain the character value U. Terminate.
+        on_code_point(Utf16View::decode_surrogate_pair(w1, w2));
+        i += 2;
     }
 }
 
@@ -255,10 +288,40 @@ DeprecatedString UTF16BEDecoder::to_utf8(StringView input)
 
 void UTF16LEDecoder::process(StringView input, Function<void(u32)> on_code_point)
 {
+    // rfc2781, 2.2 Decoding UTF-16
     size_t utf16_length = input.length() - (input.length() % 2);
     for (size_t i = 0; i < utf16_length; i += 2) {
-        u16 code_point = input[i] | (input[i + 1] << 8);
-        on_code_point(code_point);
+        // 1) If W1 < 0xD800 or W1 > 0xDFFF, the character value U is the value
+        //    of W1. Terminate.
+        u16 w1 = static_cast<u8>(input[i]) | (static_cast<u8>(input[i + 1]) << 8);
+        if (!is_unicode_surrogate(w1)) {
+            on_code_point(w1);
+            continue;
+        }
+
+        // 2) Determine if W1 is between 0xD800 and 0xDBFF. If not, the sequence
+        //    is in error and no valid character can be obtained using W1.
+        //    Terminate.
+        // 3) If there is no W2 (that is, the sequence ends with W1), or if W2
+        //    is not between 0xDC00 and 0xDFFF, the sequence is in error.
+        //    Terminate.
+        if (!Utf16View::is_high_surrogate(w1) || i + 2 == utf16_length) {
+            on_code_point(replacement_code_point);
+            continue;
+        }
+
+        u16 w2 = static_cast<u8>(input[i + 2]) | (static_cast<u8>(input[i + 3]) << 8);
+        if (!Utf16View::is_low_surrogate(w2)) {
+            on_code_point(replacement_code_point);
+            continue;
+        }
+
+        // 4) Construct a 20-bit unsigned integer U', taking the 10 low-order
+        //    bits of W1 as its 10 high-order bits and the 10 low-order bits of
+        //    W2 as its 10 low-order bits.
+        // 5) Add 0x10000 to U' to obtain the character value U. Terminate.
+        on_code_point(Utf16View::decode_surrogate_pair(w1, w2));
+        i += 2;
     }
 }