LibWeb: Add TextEncoder encodeInto

Author: https://github.com/bplaat
Commit: 0104225d9b
Pull-request: https://github.com/SerenityOS/serenity/pull/21351

Userland/Libraries/LibWeb/Encoding/TextEncoder.cpp

@@ -30,10 +30,9 @@ void TextEncoder::initialize(JS::Realm& realm)
 }
 
 // https://encoding.spec.whatwg.org/#dom-textencoder-encode
-JS::Uint8Array* TextEncoder::encode(String const& input) const
+JS::NonnullGCPtr<JS::Uint8Array> TextEncoder::encode(String const& input) const
 {
-    // NOTE: The AK::DeprecatedString returned from PrimitiveString::string() is always UTF-8, regardless of the internal string type, so most of these steps are no-ops.
-
+    // NOTE: The AK::String is always UTF-8, so most of these steps are no-ops.
     // 1. Convert input to an I/O queue of scalar values.
     // 2. Let output be the I/O queue of bytes « end-of-queue ».
     // 3. While true:
@@ -48,10 +47,67 @@ JS::Uint8Array* TextEncoder::encode(String const& input) const
     return JS::Uint8Array::create(realm(), array_length, *array_buffer);
 }
 
+// https://encoding.spec.whatwg.org/#dom-textencoder-encodeinto
+TextEncoderEncodeIntoResult TextEncoder::encode_into(String const& source, JS::Handle<JS::Object> const& destination) const
+{
+    auto& destination_array = static_cast<JS::Uint8Array&>(*destination);
+    auto data = destination_array.data();
+
+    // 1. Let read be 0.
+    unsigned long long read = 0;
+    // 2. Let written be 0.
+    unsigned long long written = 0;
+
+    // NOTE: The AK::String is always UTF-8, so most of these steps are no-ops.
+    // 3. Let encoder be an instance of the UTF-8 encoder.
+    // 4. Let unused be the I/O queue of scalar values « end-of-queue ».
+    // 5. Convert source to an I/O queue of scalar values.
+    auto code_points = source.code_points();
+    auto it = code_points.begin();
+
+    // 6. While true:
+    while (true) {
+        // 6.1. Let item be the result of reading from source.
+        // 6.2. Let result be the result of running encoder’s handler on unused and item.
+        // 6.3. If result is finished, then break.
+        if (it.done())
+            break;
+        auto item = *it;
+        auto result = it.underlying_code_point_bytes();
+
+        // 6.4. Otherwise:
+        // 6.4.1. If destination’s byte length − written is greater than or equal to the number of bytes in result, then:
+        if (data.size() - written >= result.size()) {
+            // 6.4.1.1. If item is greater than U+FFFF, then increment read by 2.
+            if (item > 0xffff) {
+                read += 2;
+            }
+            // 6.4.1.2. Otherwise, increment read by 1.
+            else {
+                read++;
+            }
+
+            // 6.4.1.3. Write the bytes in result into destination, with startingOffset set to written.
+            // 6.4.1.4. Increment written by the number of bytes in result.
+            for (auto byte : result)
+                data[written++] = byte;
+        }
+        // 6.4.2. Otherwise, break.
+        else {
+            break;
+        }
+
+        ++it;
+    }
+
+    // 7. Return «[ "read" → read, "written" → written ]».
+    return { read, written };
+}
+
 // https://encoding.spec.whatwg.org/#dom-textencoder-encoding
 FlyString const& TextEncoder::encoding()
 {
-    static const FlyString encoding = "utf-8"_fly_string;
+    static FlyString const encoding = "utf-8"_fly_string;
     return encoding;
 }