AK: Implement Utf8CodepointIterator::peek(size_t)

This adds a peek method for Utf8CodepointIterator, which enables it to
be used in some parsing cases where peeking is necessary.

peek(0) is equivalent to operator*, expect that peek() does not contain
any assertions and will just return an empty Optional<u32>.

This also implements a test case for iterating UTF-8.

AK/Utf8View.cpp

@@ -240,4 +240,21 @@ u32 Utf8CodepointIterator::operator*() const
     return code_point_value_so_far;
 }
 
+Optional<u32> Utf8CodepointIterator::peek(size_t offset) const
+{
+    if (offset == 0) {
+        if (this->done())
+            return {};
+        return this->operator*();
+    }
+
+    auto new_iterator = *this;
+    for (size_t index = 0; index < offset; ++index) {
+        ++new_iterator;
+        if (new_iterator.done())
+            return {};
+    }
+    return *new_iterator;
+}
+
 }

AK/Utf8View.h

@@ -25,6 +25,8 @@ public:
     bool operator!=(const Utf8CodepointIterator&) const;
     Utf8CodepointIterator& operator++();
     u32 operator*() const;
+    // NOTE: This returns {} if the peek is at or past EOF.
+    Optional<u32> peek(size_t offset = 0) const;
 
     ssize_t operator-(const Utf8CodepointIterator& other) const
     {

Tests/AK/TestUtf8.cpp

@@ -67,3 +67,39 @@ TEST_CASE(validate_invalid_ut8)
     EXPECT(!utf8_4.validate(valid_bytes));
     EXPECT(valid_bytes == 0);
 }
+
+TEST_CASE(iterate_utf8)
+{
+    Utf8View view("Some weird characters \u00A9\u266A\uA755");
+    Utf8CodepointIterator iterator = view.begin();
+
+    EXPECT(*iterator == 'S');
+    EXPECT(iterator.peek().has_value() && iterator.peek().value() == 'S');
+    EXPECT(iterator.peek(0).has_value() && iterator.peek(0).value() == 'S');
+    EXPECT(iterator.peek(1).has_value() && iterator.peek(1).value() == 'o');
+    EXPECT(iterator.peek(22).has_value() && iterator.peek(22).value() == 0x00A9);
+    EXPECT(iterator.peek(24).has_value() && iterator.peek(24).value() == 0xA755);
+    EXPECT(!iterator.peek(25).has_value());
+
+    ++iterator;
+
+    EXPECT(*iterator == 'o');
+    EXPECT(iterator.peek(23).has_value() && iterator.peek(23).value() == 0xA755);
+
+    for (size_t i = 0; i < 23; ++i)
+        ++iterator;
+
+    EXPECT(!iterator.done());
+    EXPECT(*iterator == 0xA755);
+    EXPECT(iterator.peek().has_value() && iterator.peek().value() == 0xA755);
+    EXPECT(!iterator.peek(1).has_value());
+
+    ++iterator;
+
+    EXPECT(iterator.done());
+    EXPECT(!iterator.peek(0).has_value());
+    EXPECT_CRASH("Dereferencing Utf8CodepointIterator which is already done.", [&iterator] {
+        *iterator;
+        return Test::Crash::Failure::DidNotCrash;
+    });
+}