UTF-8: Add Utf8CodepointIterator::codepoint_length_in_bytes()

This allows you to retrieve the length (in bytes) of the codepoint the
iterator is currently pointing at.

2 files changed, 12 insertions, 0 deletions

diff --git a/AK/Utf8View.cpp b/AK/Utf8View.cpp
index b63f674c9a..d5b73f4319 100644
--- a/AK/Utf8View.cpp
+++ b/AK/Utf8View.cpp
@@ -139,6 +139,16 @@ Utf8CodepointIterator& Utf8CodepointIterator::operator++()
     return *this;
 }
 
+int Utf8CodepointIterator::codepoint_length_in_bytes() const
+{
+    ASSERT(m_length > 0);
+    int codepoint_length_in_bytes;
+    u32 value;
+    bool first_byte_makes_sense = decode_first_byte(*m_ptr, codepoint_length_in_bytes, value);
+    ASSERT(first_byte_makes_sense);
+    return codepoint_length_in_bytes;
+}
+
 u32 Utf8CodepointIterator::operator*() const
 {
     ASSERT(m_length > 0);
diff --git a/AK/Utf8View.h b/AK/Utf8View.h
index 5db0e1b7ea..cbc61aeead 100644
--- a/AK/Utf8View.h
+++ b/AK/Utf8View.h
@@ -18,6 +18,8 @@ public:
     Utf8CodepointIterator& operator++();
     u32 operator*() const;
 
+    int codepoint_length_in_bytes() const;
+
 private:
     Utf8CodepointIterator(const unsigned char*, int);
     const unsigned char* m_ptr { nullptr };