add Encoding::num_bytes_in_code_point()

src/core/Encoding.cc

@@ -60,3 +60,24 @@ Encoding::Type Encoding::detect_encoding(const uint8_t * buffer, size_t length)
 
     return UTF_8;
 }
+
+uint8_t Encoding::num_bytes_in_code_point(Type type, const uint8_t * encoded)
+{
+    switch (type)
+    {
+    case UTF_8:
+        {
+            if ((*encoded & 0x80u) == 0u)
+                return 1u;
+            encoded++;
+            uint8_t n = 1u;
+            while ((*encoded++ & 0xC0u) == 0x80u)
+                n++;
+            return n;
+        }
+        break;
+    case CP_1252:
+        return 1u;
+    }
+    return 0u;
+}

src/core/Encoding.h

@@ -14,6 +14,7 @@ public:
     };
 
     static Type detect_encoding(const uint8_t * buffer, size_t length);
+    static uint8_t num_bytes_in_code_point(Type type, const uint8_t * encoded);
 };
 
 #endif