AK: Add some more utility methods to Utf8View

Author: https://github.com/bugaevc
Commit: https://github.com/SerenityOS/serenity/commit/c379f43d2a1
Pull-request: https://github.com/SerenityOS/serenity/pull/520
Reviewed-by: https://github.com/awesomekling

AK/Utf8View.cpp

@@ -2,6 +2,11 @@
 
 namespace AK {
 
+Utf8View::Utf8View(const String& string)
+    : m_string(string)
+{
+}
+
 Utf8View::Utf8View(const StringView& string)
     : m_string(string)
 {
@@ -14,7 +19,7 @@ const unsigned char* Utf8View::begin_ptr() const
 
 const unsigned char* Utf8View::end_ptr() const
 {
-    return (const unsigned char*)m_string.characters_without_null_termination() + m_string.length();
+    return begin_ptr() + m_string.length();
 }
 
 Utf8CodepointIterator Utf8View::begin() const
@@ -27,6 +32,20 @@ Utf8CodepointIterator Utf8View::end() const
     return { end_ptr(), 0 };
 }
 
+int Utf8View::byte_offset_of(const Utf8CodepointIterator& it) const
+{
+    ASSERT(it.m_ptr >= begin_ptr());
+    ASSERT(it.m_ptr <= end_ptr());
+
+    return it.m_ptr - begin_ptr();
+}
+
+Utf8View Utf8View::substring_view(int byte_offset, int byte_length) const
+{
+    StringView string = m_string.substring_view(byte_offset, byte_length);
+    return Utf8View { string };
+}
+
 static inline bool decode_first_byte(
     unsigned char byte,
     int& out_codepoint_length_in_bytes,

AK/Utf8View.h

@@ -26,6 +26,7 @@ private:
 
 class Utf8View {
 public:
+    explicit Utf8View(const String&);
     explicit Utf8View(const StringView&);
     ~Utf8View() {}
 
@@ -34,6 +35,12 @@ public:
     Utf8CodepointIterator begin() const;
     Utf8CodepointIterator end() const;
 
+    const unsigned char* bytes() const { return begin_ptr(); }
+    int byte_length() const { return m_string.length(); }
+    int byte_offset_of(const Utf8CodepointIterator&) const;
+    Utf8View substring_view(int byte_offset, int byte_length) const;
+    bool is_empty() const { return m_string.is_empty(); }
+
     bool validate() const;
 
 private: