[+] AuCodepointsFindByteOffsetIgnoreCase

[+] AuCodepointsNextLengthFromCharacter
[*] Clean up questionable iteration code / massive speed up

Include/auROXTL/Strings/auCodepointsUTF8.hpp

@@ -56,6 +56,8 @@ AU_INLINE_CONSTEXPR_17 CodepointOffset_t                 AuCodepointsCount(const
 /// Counts the bytes required to iterate over a UTF8 encoded codepoint
 AU_INLINE_CONSTEXPR_17 CodepointByteOffset_t             AuCodepointsNextLength(const AuROString &in);
 
+AU_INLINE_CONSTEXPR_17 CodepointByteOffset_t             AuCodepointsNextLengthFromCharacter(AuUInt8 uCharacter);
+
 /// Iterates over a UTF8 sequence using OP.
 /// If op returns void, AuCodepointsForEach will continue until EOS or invalid squence.
 /// If op returns bool, AuCodepointsForEach will continue until EOS, invalid squence, or !op.
@@ -85,6 +87,11 @@ static bool                                              AuCodepointsStartsWithI
 static bool                                              AuCodepointsEndsWithIgnoreCase(const AuROString &inA,
                                                                                         const AuROString &inB);
 
+/// Also see: AuCodepointsFindByteOffset, AuCodepointsContainsIgnoreCase
+static CodepointByteOffset_t                             AuCodepointsFindByteOffsetIgnoreCase(const AuROString &inA,
+                                                                                              const AuROString &inB);
+
+/// Also see: AuCodepointsFindByteOffsetIgnoreCase
 static bool                                              AuCodepointsContainsIgnoreCase(const AuROString &inA,
                                                                                         const AuROString &inB);
 

Include/auROXTL/Strings/auCodepointsUTF8.ipp

@@ -37,9 +37,9 @@ AU_STATIC_CONSTEXPR_17 AuOptional<AuUInt32>  AuCodepointsDecodeOne(const AuROStr
         return AuOptional<AuUInt32>();
     }
 
-    auto uLength = in.length();
+    auto uLength = in.Length();
 
-    const char *pItr = in.data();
+    const char *pItr = in.Begin();
     const char *pEnd = pItr + uLength;
 
     while (pItr < pEnd)
@@ -59,9 +59,7 @@ AU_STATIC_CONSTEXPR_17 AuOptional<AuUInt32>  AuCodepointsDecodeOne(const AuROStr
                 return AuOptional<AuUInt32>();
             }
 
-            for (AuUInt8 b = *pItr; (b & 0x80U) != 0; b <<= 1, ++nby)
+            nby = AuCodepointsNextLengthFromCharacter(*pItr);
-            {
-            }
 
             if (nby > kAuCodepointUTF8MaxBytes)
             {
@@ -107,11 +105,11 @@ static AuList<AuUInt32>                AuCodepointsDecode(const AuROString &in)
         return ret;
     }
 
-    auto uLength = in.length();
+    auto uLength = in.Length();
 
     ret.reserve(uLength);
 
-    const char *pItr = in.data();
+    const char *pItr = in.Begin();
     const char *pEnd = pItr + uLength;
 
     while (pItr < pEnd)
@@ -131,9 +129,7 @@ static AuList<AuUInt32>                AuCodepointsDecode(const AuROString &in)
                 return AuList<AuUInt32>();
             }
 
-            for (AuUInt8 b = *pItr; (b & 0x80U) != 0; b <<= 1, ++nby)
+            nby = AuCodepointsNextLengthFromCharacter(*pItr);
-            {
-            }
 
             if (nby > kAuCodepointUTF8MaxBytes)
             {
@@ -243,9 +239,9 @@ AU_OPTIMIZED AuString                 AuCodepointsToUpper(const AuROString &in)
 AU_INLINE_CONSTEXPR_17 CodepointOffset_t AuCodepointsCount(const AuROString &in)
 {
     CodepointOffset_t uCounter (0);
-    auto uLength = in.length();
+    auto uLength = in.Length();
 
-    const char *pItr = in.data();
+    const char *pItr = in.Begin();
     const char *pEnd = pItr + uLength;
 
     while (pItr != pEnd)
@@ -254,58 +250,8 @@ AU_INLINE_CONSTEXPR_17 CodepointOffset_t AuCodepointsCount(const AuROString &in)
         auto         ch = *pItr;
         unsigned int result = (ch & 0xF0);
 
-        if ((ch & 0x80) == 0)
+        nby = AuCodepointsNextLengthFromCharacter(ch);
-        {
+        if (!nby)
-            nby = 1;
-        }
-        else if ((ch & 0xE0) == 0xC0)
-        {
-            nby = 2;
-        }
-        else if (result == 0xE0)
-        {
-            nby = 3;
-        }
-        else if (result == 0xF0)
-        {
-            if ((ch & 0x08) == 0x08)
-            {
-                // Historic UTF8
-                nby = 5;
-            #if defined(AURORA_UTF8_I_SUCK_AND_WANT_MODERN_UTF8_WANT_THROW)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-            }
-            else if ((ch & 0x0c) == 0x0c)
-            {
-                // Special UTF8
-                nby = 6;
-            #if defined(AURORA_UTF8_I_SUCK_AND_WANT_MODERN_UTF8_WANT_THROW)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-            }
-            else if ((ch & 0x0e) == 0x0e)
-            {
-                // Illegal UTF8
-                nby = 7;
-            #if defined(AURORA_UTF8_THROW_WHEN_STUPIDILY_ILLEGAL)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-            }
-            else if ((ch & 0x0f) == 0x0f)
-            {
-                // Not even logical
-            #if defined(AURORA_UTF8_THROW_WHEN_STUPIDILY_ILLEGAL)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-                break;
-            }
-            else
-            {
-                nby = 4;
-            }
-        }
-        else
         {
             break;
         }
@@ -322,10 +268,63 @@ AU_INLINE_CONSTEXPR_17 CodepointOffset_t AuCodepointsCount(const AuROString &in)
     return uCounter;
 }
 
+AU_INLINE_CONSTEXPR_17 CodepointByteOffset_t AuCodepointsNextLengthFromCharacter(AuUInt8 uCharacter)
+{
+#if defined(AU_CPU_ENDIAN_BIG)
+
+    const char uChar = uCharacter;
+    return AuCodepointsNextLength(AuROString(&uChar, 1));
+
+#else
+
+
+#if defined(AU_LANG_CPP_17_)
+
+    if (__builtin_is_constant_evaluated())
+    {
+        const char uChar = uCharacter;
+        return AuCodepointsNextLength(AuROString(&uChar, 1));
+    }
+
+#endif
+
+    if ((uCharacter & 0x80) == 0)
+    {
+        return 1;
+    }
+
+    AuUInt8 uBits(0);
+    if (AuBitScanReverse(uBits, ~(AuUInt32(uCharacter) << 24u)))
+    {
+        return 31 - uBits;
+    }
+    else
+    {
+        return 0;
+    }
+
+#endif
+}
+
 /// Counts the bytes required to iterate over a UTF8 encoded codepoint
 AU_INLINE_CONSTEXPR_17 CodepointByteOffset_t AuCodepointsNextLength(const AuROString &in)
 {
-    if (in.length())
+
+#if defined(AU_LANG_CPP_17_)
+
+    if (!__builtin_is_constant_evaluated())
+    {
+        if (in.Empty())
+        {
+            return 0;
+        }
+
+        return AuCodepointsNextLengthFromCharacter(in.Data()[0]);
+    }
+
+#endif
+
+    if (in.Length())
     {
         auto         ch = in[0];
         unsigned int result = (ch & 0xF0);
@@ -398,9 +397,9 @@ static bool                            AuCodepointsForEach(T op, const AuROStrin
         return true;
     }
 
-    auto uLength = in.length();
+    auto uLength = in.Length();
 
-    const char *pItr = in.data();
+    const char *pItr = in.Begin();
     const char *pEnd = pItr + uLength;
 
     while (pItr < pEnd)
@@ -420,9 +419,7 @@ static bool                            AuCodepointsForEach(T op, const AuROStrin
                 return false;
             }
 
-            for (AuUInt8 b = *pItr; (b & 0x80U) != 0; b <<= 1, ++nby)
+            nby = AuCodepointsNextLengthFromCharacter(*pItr);
-            {
-            }
 
             if (nby > kAuCodepointUTF8MaxBytes)
             {
@@ -479,11 +476,11 @@ static AuString                        AuCodepointsTransform(T op, const AuROStr
         return ret;
     }
 
-    auto uLength = in.length();
+    auto uLength = in.Length();
 
     ret.reserve(uLength);
 
-    const char *pItr = in.data();
+    const char *pItr = in.Begin();
     const char *pEnd = pItr + uLength;
 
     while (pItr < pEnd)
@@ -503,9 +500,7 @@ static AuString                        AuCodepointsTransform(T op, const AuROStr
                 return AuString();
             }
 
-            for (AuUInt8 b = *pItr; (b & 0x80U) != 0; b <<= 1, ++nby)
+            nby = AuCodepointsNextLengthFromCharacter(*pItr);
-            {
-            }
 
             if (nby > kAuCodepointUTF8MaxBytes)
             {
@@ -548,11 +543,11 @@ template <class T>
 AuString                               AuCodepointsTransformASCIIOp(T op, const AuROString &in)
 {
     AuString ret;
-    auto uLength = in.length();
+    auto uLength = in.Length();
 
     ret.resize(uLength);
 
-    const char *pItr = in.data();
+    const char *pItr = in.Begin();
     const char *pEnd = pItr + uLength;
 
     AuUInt32 uCounter (0);
@@ -562,58 +557,9 @@ AuString                               AuCodepointsTransformASCIIOp(T op, const
         auto         ch = *pItr;
         unsigned int result = (ch & 0xF0);
 
-        if ((ch & 0x80) == 0)
+        nby = AuCodepointsNextLengthFromCharacter(ch);
-        {
+
-            nby = 1;
+        if (!nby)
-        }
-        else if ((ch & 0xE0) == 0xC0)
-        {
-            nby = 2;
-        }
-        else if (result == 0xE0)
-        {
-            nby = 3;
-        }
-        else if (result == 0xF0)
-        {
-            if ((ch & 0x08) == 0x08)
-            {
-                // Historic UTF8
-                nby = 5;
-            #if defined(AURORA_UTF8_I_SUCK_AND_WANT_MODERN_UTF8_WANT_THROW)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-            }
-            else if ((ch & 0x0c) == 0x0c)
-            {
-                // Special UTF8
-                nby = 6;
-            #if defined(AURORA_UTF8_I_SUCK_AND_WANT_MODERN_UTF8_WANT_THROW)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-            }
-            else if ((ch & 0x0e) == 0x0e)
-            {
-                // Illegal UTF8
-                nby = 7;
-            #if defined(AURORA_UTF8_THROW_WHEN_STUPIDILY_ILLEGAL)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-            }
-            else if ((ch & 0x0f) == 0x0f)
-            {
-                // Not even logical
-            #if defined(AURORA_UTF8_THROW_WHEN_STUPIDILY_ILLEGAL)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-                break;
-            }
-            else
-            {
-                nby = 4;
-            }
-        }
-        else
         {
             break;
         }
@@ -655,9 +601,9 @@ static bool                            AuCodepointsIsEqualIgnoreCase(const AuROS
         return true;
     }
 
-    const char *pItr  = inA.data();
+    const char *pItr  = inA.Begin();
-    const char *pItr2 = inB.data();
+    const char *pItr2 = inB.Begin();
-    const char *pEnd  = pItr + inA.length();
+    const char *pEnd  = pItr + inA.Length();
 
     while (pItr < pEnd)
     {
@@ -681,9 +627,7 @@ static bool                            AuCodepointsIsEqualIgnoreCase(const AuROS
                 return AuMemcmp(pItr, pItr2, pEnd - pItr) == 0;
             }
 
-            for (AuUInt8 b = *pItr; (b & 0x80U) != 0; b <<= 1, ++nby)
+            nby = AuCodepointsNextLengthFromCharacter(*pItr);
-            {
-            }
 
             if (nby > kAuCodepointUTF8MaxBytes)
             {
@@ -723,9 +667,9 @@ static bool                            AuCodepointsStartsWithIgnoreCase(const Au
         return true;
     }
 
-    const char *pItr  = inA.data();
+    const char *pItr  = inA.Begin();
-    const char *pItr2 = inB.data();
+    const char *pItr2 = inB.Begin();
-    const char *pEnd  = pItr + inB.length();
+    const char *pEnd  = pItr + inB.Length();
     const char *pEnd2 = inB.End();
 
     while (pItr < pEnd)
@@ -754,9 +698,7 @@ static bool                            AuCodepointsStartsWithIgnoreCase(const Au
                 return AuMemcmp(pItr, pItr2, pEnd - pItr) == 0;
             }
 
-            for (AuUInt8 b = *pItr; (b & 0x80U) != 0; b <<= 1, ++nby)
+            nby = AuCodepointsNextLengthFromCharacter(*pItr);
-            {
-            }
 
             if (nby > kAuCodepointUTF8MaxBytes)
             {
@@ -776,7 +718,7 @@ static bool                            AuCodepointsStartsWithIgnoreCase(const Au
                 return AuMemcmp(pItr, pItr2, pEnd - pItr) == 0;
             }
 
-            if (nby > pEnd2 - pItr2)
+            if (nby > AuUInt(pEnd2 - pItr2))
             {
                 return false;
             }
@@ -828,8 +770,8 @@ static bool                            AuCodepointsEndsWithIgnoreCase(const AuRO
             return false;
         }
 
-        auto pItr  = inA.data() + uOffset  - nby;
+        auto pItr  = inA.Begin() + uOffset  - nby;
-        auto pItr2 = inB.data() + uOffset2 - nby;
+        auto pItr2 = inB.Begin() + uOffset2 - nby;
 
         if ((c = *pItr) <= 0x7FU)
         {
@@ -856,54 +798,44 @@ static bool                            AuCodepointsEndsWithIgnoreCase(const AuRO
     return true;
 }
 
-static bool                                              AuCodepointsContainsIgnoreCase(const AuROString &inA,
+static CodepointByteOffset_t                             AuCodepointsFindByteOffsetIgnoreCase(const AuROString &inA,
-                                                                                        const AuROString &inB)
+                                                                                              const AuROString &inB)
 {
     if (inA.size() < inB.size())
     {
-        return false;
+        return AuROString::npos;
     }
 
-    const char *pItr  = inA.data();
+    const char *pItr  = inA.Begin();
-    const char *pItr2 = inB.data();
+    const char *pItr2 = inB.Begin();
-    const char *pEnd  = pItr + inA.length();
+    const char *pEnd  = pItr + inA.Length();
-    const char *pEnd2 = inB.end();
+    const char *pEnd2 = inB.End();
 
     while (pItr < pEnd)
     {
-        AuUInt32 c (0);
         AuUInt32 nby (0);
 
-        if ((c = *pItr) <= 0x7FU)
+        nby = AuCodepointsNextLengthFromCharacter(*pItr);
+        if (!nby)
         {
-            nby = 1;
+            break;
-        }
-        else
-        {
-            if ((*pItr & 0xC0U) != 0xC0U)
-            {
-                if (pEnd - pItr != pEnd2 - pItr2)
-                {
-                    return false;
-                }
-
-                return AuMemcmp(pItr, pItr2, pEnd - pItr) == 0;
-            }
-
-            for (AuUInt8 b = *pItr; (b & 0x80U) != 0; b <<= 1, ++nby)
-            {
-            }
         }
 
         if (AuCodepointsStartsWithIgnoreCase(AuROString(pItr, AuUInt(pEnd - pItr)), inB))
         {
-            return true;
+            return pItr - inA.Begin();
         }
 
         pItr  += nby;
     }
 
-    return false;
+    return AuROString::npos;
+}
+
+static bool                                              AuCodepointsContainsIgnoreCase(const AuROString &inA,
+                                                                                        const AuROString &inB)
+{
+    return AuCodepointsFindByteOffsetIgnoreCase(inA, inB) != AuROString::npos;
 }
 
 /// Returns the byte offset of the codepoint index or AuROString::npos
@@ -911,9 +843,9 @@ AU_INLINE_CONSTEXPR_17 CodepointByteOffset_t AuCodepointsGetByteOffset(const AuR
                                                                        CodepointOffset_t uCodepointIndex)
 {
     AuUInt uCounter (0);
-    auto uLength = in.length();
+    auto uLength = in.Length();
 
-    const char *pStart = in.data();
+    const char *pStart = in.Begin();
     const char *pItr   = pStart;
     const char *pEnd   = pStart + uLength;
 
@@ -928,58 +860,8 @@ AU_INLINE_CONSTEXPR_17 CodepointByteOffset_t AuCodepointsGetByteOffset(const AuR
             return CodepointByteOffset_t(pItr - pStart);
         }
 
-        if ((ch & 0x80) == 0)
+        nby = AuCodepointsNextLengthFromCharacter(ch);
-        {
+        if (!nby)
-            nby = 1;
-        }
-        else if ((ch & 0xE0) == 0xC0)
-        {
-            nby = 2;
-        }
-        else if (result == 0xE0)
-        {
-            nby = 3;
-        }
-        else if (result == 0xF0)
-        {
-            if ((ch & 0x08) == 0x08)
-            {
-                // Historic UTF8
-                nby = 5;
-            #if defined(AURORA_UTF8_I_SUCK_AND_WANT_MODERN_UTF8_WANT_THROW)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-            }
-            else if ((ch & 0x0c) == 0x0c)
-            {
-                // Special UTF8
-                nby = 6;
-            #if defined(AURORA_UTF8_I_SUCK_AND_WANT_MODERN_UTF8_WANT_THROW)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-            }
-            else if ((ch & 0x0e) == 0x0e)
-            {
-                // Illegal UTF8
-            #if defined(AURORA_UTF8_THROW_WHEN_STUPIDILY_ILLEGAL)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-                nby = 7;
-            }
-            else if ((ch & 0x0f) == 0x0f)
-            {
-                // Not even logical
-            #if defined(AURORA_UTF8_THROW_WHEN_STUPIDILY_ILLEGAL)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-                break;
-            }
-            else
-            {
-                nby = 4;
-            }
-        }
-        else
         {
             break;
         }
@@ -1001,9 +883,9 @@ AU_INLINE_CONSTEXPR_17 CodepointByteOffset_t AuCodepointsGetByteLength(const AuR
                                                                         CodepointOffset_t uCodepointIndex)
 {
     AuUInt uCounter (0);
-    auto uLength = in.length();
+    auto uLength = in.Length();
 
-    const char *pStart = in.data();
+    const char *pStart = in.Begin();
     const char *pItr   = pStart;
     const char *pEnd   = pStart + uLength;
 
@@ -1013,52 +895,8 @@ AU_INLINE_CONSTEXPR_17 CodepointByteOffset_t AuCodepointsGetByteLength(const AuR
         auto         ch = *pItr;
         unsigned int result = (ch & 0xF0);
 
-        if ((ch & 0x80) == 0)
+        nby = AuCodepointsNextLengthFromCharacter(ch);
-        {
+        if (!nby)
-            nby = 1;
-        }
-        else if ((ch & 0xE0) == 0xC0)
-        {
-            nby = 2;
-        }
-        else if (result == 0xE0)
-        {
-            nby = 3;
-        }
-        else if (result == 0xF0)
-        {
-            if ((ch & 0x08) == 0x08)
-            {
-                // Historic UTF8
-                nby = 5;
-            #if defined(AURORA_UTF8_I_SUCK_AND_WANT_MODERN_UTF8_WANT_THROW)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-            }
-            else if ((ch & 0x0c) == 0x0c)
-            {
-                // Special UTF8
-                nby = 6;
-            #if defined(AURORA_UTF8_I_SUCK_AND_WANT_MODERN_UTF8_WANT_THROW)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-            }
-            else if ((ch & 0x0e) == 0x0e)
-            {
-                // Illegal UTF8
-                nby = 7;
-            }
-            else if ((ch & 0x0f) == 0x0f)
-            {
-                // Not even logical
-                break;
-            }
-            else
-            {
-                nby = 4;
-            }
-        }
-        else
         {
             break;
         }
@@ -1098,10 +936,10 @@ static CodepointByteOffset_t           AuCodepointsFindByteOffset(const AuROStri
                                                                   CodepointByteOffset_t uStartPosition)
 {      
     AuUInt uCounter    = 0;
-    auto uLength       = in.length();
+    auto uLength       = in.Length();
-    auto uFindLength   = find.length();
+    auto uFindLength   = find.Length();
 
-    const char *pStart = in.data();
+    const char *pStart = in.Begin();
     const char *pItr   = pStart;
     const char *pEnd   = pStart + uLength;
 
@@ -1115,9 +953,9 @@ static CodepointByteOffset_t           AuCodepointsFindByteOffset(const AuROStri
         if (uByteOffset >= uStartPosition)
         {
             AuROString suffixView(pItr, pEnd);
-            if (suffixView.length() > uFindLength)
+            if (suffixView.Length() > uFindLength)
             {
-                suffixView = AuROString ( suffixView.data(), uFindLength );
+                suffixView = AuROString ( suffixView.Begin(), uFindLength );
             }
 
             if (suffixView == find)
@@ -1126,58 +964,8 @@ static CodepointByteOffset_t           AuCodepointsFindByteOffset(const AuROStri
             }
         }
 
-        if ((ch & 0x80) == 0)
+        nby = AuCodepointsNextLengthFromCharacter(ch);
-        {
+        if (!nby)
-            nby = 1;
-        }
-        else if ((ch & 0xE0) == 0xC0)
-        {
-            nby = 2;
-        }
-        else if (result == 0xE0)
-        {
-            nby = 3;
-        }
-        else if (result == 0xF0)
-        {
-            if ((ch & 0x08) == 0x08)
-            {
-                // Historic UTF8
-                nby = 5;
-            #if defined(AURORA_UTF8_I_SUCK_AND_WANT_MODERN_UTF8_WANT_THROW)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-            }
-            else if ((ch & 0x0c) == 0x0c)
-            {
-                // Special UTF8
-                nby = 6;
-            #if defined(AURORA_UTF8_I_SUCK_AND_WANT_MODERN_UTF8_WANT_THROW)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-            }
-            else if ((ch & 0x0e) == 0x0e)
-            {
-                // Illegal UTF8
-                nby = 7;
-            #if defined(AURORA_UTF8_THROW_WHEN_STUPIDILY_ILLEGAL)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-            }
-            else if ((ch & 0x0f) == 0x0f)
-            {
-                // Not even logical
-            #if defined(AURORA_UTF8_THROW_WHEN_STUPIDILY_ILLEGAL)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-                break;
-            }
-            else
-            {
-                nby = 4;
-            }
-        }
-        else
         {
             break;
         }
@@ -1202,10 +990,10 @@ AU_STATIC_CONSTEXPR_17 CodepointByteOffset_t      AuCodepointsFindByteOffsetUnsa
                                                                                    CodepointByteOffset_t uStartPosition)
 {      
     AuUInt uCounter    = 0;
-    auto uLength       = in.length();
+    auto uLength       = in.Length();
-    auto uFindLength   = find.length();
+    auto uFindLength   = find.Length();
 
-    const char *pStart = in.data();
+    const char *pStart = in.Begin();
     const char *pItr   = pStart + uStartPosition;
     const char *pEnd   = pStart + uLength;
 
@@ -1218,9 +1006,9 @@ AU_STATIC_CONSTEXPR_17 CodepointByteOffset_t      AuCodepointsFindByteOffsetUnsa
 
         {
             AuROString suffixView(pItr, pEnd);
-            if (suffixView.length() > uFindLength)
+            if (suffixView.Length() > uFindLength)
             {
-                suffixView = AuROString ( suffixView.data(), uFindLength );
+                suffixView = AuROString ( suffixView.Begin(), uFindLength );
             }
 
             if (suffixView == find)
@@ -1229,58 +1017,8 @@ AU_STATIC_CONSTEXPR_17 CodepointByteOffset_t      AuCodepointsFindByteOffsetUnsa
             }
         }
 
-        if ((ch & 0x80) == 0)
+        nby = AuCodepointsNextLengthFromCharacter(ch);
-        {
+        if (!nby)
-            nby = 1;
-        }
-        else if ((ch & 0xE0) == 0xC0)
-        {
-            nby = 2;
-        }
-        else if (result == 0xE0)
-        {
-            nby = 3;
-        }
-        else if (result == 0xF0)
-        {
-            if ((ch & 0x08) == 0x08)
-            {
-                // Historic UTF8
-                nby = 5;
-            #if defined(AURORA_UTF8_I_SUCK_AND_WANT_MODERN_UTF8_WANT_THROW)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-            }
-            else if ((ch & 0x0c) == 0x0c)
-            {
-                // Special UTF8
-                nby = 6;
-            #if defined(AURORA_UTF8_I_SUCK_AND_WANT_MODERN_UTF8_WANT_THROW)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-            }
-            else if ((ch & 0x0e) == 0x0e)
-            {
-                // Illegal UTF8
-                nby = 7;
-            #if defined(AURORA_UTF8_THROW_WHEN_STUPIDILY_ILLEGAL)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-            }
-            else if ((ch & 0x0f) == 0x0f)
-            {
-                // Not even logical
-            #if defined(AURORA_UTF8_THROW_WHEN_STUPIDILY_ILLEGAL)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-                break;
-            }
-            else
-            {
-                nby = 4;
-            }
-        }
-        else
         {
             break;
         }
@@ -1303,9 +1041,9 @@ AU_STATIC_CONSTEXPR_17 CodepointByteOffset_t      AuCodepointsFindPreviousValidB
                                                                                                     CodepointOffset_t uStartPosition)
 {      
     AuUInt uCounter    = 0;
-    auto uLength       = in.length();
+    auto uLength       = in.Length();
 
-    const char *pStart = in.data();
+    const char *pStart = in.Begin();
     const char *pItr   = pStart;
     const char *pEnd   = pStart + uLength;
 
@@ -1320,58 +1058,8 @@ AU_STATIC_CONSTEXPR_17 CodepointByteOffset_t      AuCodepointsFindPreviousValidB
         auto         ch = *pItr;
         unsigned int result = (ch & 0xF0);
 
-        if ((ch & 0x80) == 0)
+        nby = AuCodepointsNextLengthFromCharacter(ch);
-        {
+        if (!nby)
-            nby = 1;
-        }
-        else if ((ch & 0xE0) == 0xC0)
-        {
-            nby = 2;
-        }
-        else if (result == 0xE0)
-        {
-            nby = 3;
-        }
-        else if (result == 0xF0)
-        {
-            if ((ch & 0x08) == 0x08)
-            {
-                // Historic UTF8
-                nby = 5;
-            #if defined(AURORA_UTF8_I_SUCK_AND_WANT_MODERN_UTF8_WANT_THROW)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-            }
-            else if ((ch & 0x0c) == 0x0c)
-            {
-                // Special UTF8
-                nby = 6;
-            #if defined(AURORA_UTF8_I_SUCK_AND_WANT_MODERN_UTF8_WANT_THROW)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-            }
-            else if ((ch & 0x0e) == 0x0e)
-            {
-                // Illegal UTF8
-                nby = 7;
-            #if defined(AURORA_UTF8_THROW_WHEN_STUPIDILY_ILLEGAL)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-            }
-            else if ((ch & 0x0f) == 0x0f)
-            {
-                // Not even logical
-            #if defined(AURORA_UTF8_THROW_WHEN_STUPIDILY_ILLEGAL)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-                break;
-            }
-            else
-            {
-                nby = 4;
-            }
-        }
-        else
         {
             break;
         }
@@ -1400,7 +1088,7 @@ AU_STATIC_CONSTEXPR_17 CodepointByteOffset_t      AuCodepointsFindPreviousValidB
 AU_STATIC_CONSTEXPR_17 CodepointByteOffset_t      AuCodepointsFindPreviousValidByteOffsetFromByteOffset(const AuROString &in,
                                                                                                         CodepointByteOffset_t uStartPosition)
 {      
-    const char * pStart = in.data();
+    const char * pStart = in.Begin();
     const char * pItr   = pStart + uStartPosition - 1;
 
     if (uStartPosition == 0)
@@ -1446,10 +1134,10 @@ static CodepointOffset_t               AuCodepointsFindCodepointOffset(const AuR
                                                                        CodepointOffset_t uStartPosition)
 {      
     AuUInt uCounter (0);
-    auto uLength       = in.length();
+    auto uLength       = in.Length();
-    auto uFindLength   = find.length();
+    auto uFindLength   = find.Length();
 
-    const char *pStart = in.data();
+    const char *pStart = in.Begin();
     const char *pItr   = pStart;
     const char *pEnd   = pStart + uLength;
 
@@ -1462,9 +1150,9 @@ static CodepointOffset_t               AuCodepointsFindCodepointOffset(const AuR
         if (uCounter >= uStartPosition)
         {
             AuROString suffixView(pItr, pEnd);
-            if (suffixView.length() > uFindLength)
+            if (suffixView.Length() > uFindLength)
             {
-                suffixView = AuROString ( suffixView.data(), uFindLength );
+                suffixView = AuROString ( suffixView.Begin(), uFindLength );
             }
 
             if (suffixView == find)
@@ -1473,58 +1161,8 @@ static CodepointOffset_t               AuCodepointsFindCodepointOffset(const AuR
             }
         }
 
-        if ((ch & 0x80) == 0)
+        nby = AuCodepointsNextLengthFromCharacter(ch);
-        {
+        if (!nby)
-            nby = 1;
-        }
-        else if ((ch & 0xE0) == 0xC0)
-        {
-            nby = 2;
-        }
-        else if (result == 0xE0)
-        {
-            nby = 3;
-        }
-        else if (result == 0xF0)
-        {
-            if ((ch & 0x08) == 0x08)
-            {
-                // Historic UTF8
-                nby = 5;
-            #if defined(AURORA_UTF8_I_SUCK_AND_WANT_MODERN_UTF8_WANT_THROW)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-            }
-            else if ((ch & 0x0c) == 0x0c)
-            {
-                // Special UTF8
-                nby = 6;
-            #if defined(AURORA_UTF8_I_SUCK_AND_WANT_MODERN_UTF8_WANT_THROW)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-            }
-            else if ((ch & 0x0e) == 0x0e)
-            {
-                // Illegal UTF8
-                nby = 7;
-            #if defined(AURORA_UTF8_THROW_WHEN_STUPIDILY_ILLEGAL)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-            }
-            else if ((ch & 0x0f) == 0x0f)
-            {
-                // Not even logical
-            #if defined(AURORA_UTF8_THROW_WHEN_STUPIDILY_ILLEGAL)
-                AU_THROW_CONST_STRING("Illegal UTF8");
-            #endif
-                break;
-            }
-            else
-            {
-                nby = 4;
-            }
-        }
-        else
         {
             break;
         }
@@ -1582,14 +1220,18 @@ static AuString &                      AuCodepointsReplaceAll(AuString &str,
                                                               const AuROString &to)
 {
     AuUInt uStartPosition (0);
+#if !defined(AU_LANG_CPP_17_)
+    std::string hack(to);
+#endif
+
     while ((uStartPosition = AuCodepointsFindByteOffsetUnsafe(str, from, uStartPosition)) != AuROString::npos)
     {
     #if defined(AU_LANG_CPP_17_)
-        str.replace(uStartPosition, from.length(), to);
+        str.replace(uStartPosition, from.Length(), to);
     #else
-        str.replace(uStartPosition, from.length(), std::string(to).c_str(), 0, to.length());
+        str.replace(uStartPosition, from.Length(), hack.c_str(), 0, to.Length());
     #endif
-        uStartPosition += to.length();
+        uStartPosition += to.Length();
     }
     return str;
 }
@@ -1606,16 +1248,16 @@ static AuList<AuROString>              AuCodepointsSplitString(const AuROString
         uPos = AuCodepointsFindByteOffsetUnsafe(str, delim, uPrev);
         if (uPos == AuROString::npos)
         {
-            uPos = str.length();
+            uPos = str.Length();
         }
         auto token = str.substr(uPrev, uPos - uPrev);
         if ((!token.empty()) && bIgnoreEmpty)
         {
             tokens.push_back(token);
         }
-        uPrev = uPos + delim.length();
+        uPrev = uPos + delim.Length();
     }
-    while (uPos < str.length() && uPrev < str.length());
+    while (uPos < str.Length() && uPrev < str.Length());
     return tokens;
 }
 

Include/auROXTL/auStringUtils.hpp

@@ -63,7 +63,6 @@
 
 #include <auROXTL/Strings/auStringUtils.hpp>
 #include <auROXTL/Strings/auCodepointsUTF8.hpp>
-#include <auROXTL/Strings/auCodepointsUTF8.ipp>
 
 #if !defined(AURORA_RUNTIME_TO_STRING)
     #define AURORA_RUNTIME_TO_STRING std::to_string

Include/auROXTLUtils.hpp

@@ -33,6 +33,7 @@
 #include <auROXTL/auContainerUtils.hpp>
 #include <auROXTL/auListUtils.hpp>
 #include <auROXTL/auStringUtils.hpp>
+#include <auROXTL/Strings/auCodepointsUTF8.hpp>
 #include <auROXTL/Iterators/auUTF8Iterator.ipp>
 #include <auROXTL/Iterators/auReverseIterator.ipp>
 #include <auROXTL/auTupleUtils.hpp>
@@ -84,6 +85,9 @@ namespace __audetail
 
 #include <auROXTL/Strings/auLinerParserAndSplitter.ipp>
 
+#include <auROXTL/Strings/auCodepointsUTF8.hpp>
+#include <auROXTL/Strings/auCodepointsUTF8.ipp>
+
 struct IAuNullDelegate
 {
     virtual void OnCall() = 0;