Clang: Extract Utils::utf8AdvanceCodePoint

Change-Id: I922c7b0f2f0e0d50f34035e9affef4504df59892
Reviewed-by: David Schulz <david.schulz@qt.io>

src/libs/utils/textutils.cpp

@@ -190,5 +190,30 @@ QString utf16LineTextInUtf8Buffer(const QByteArray &utf8Buffer, int currentUtf8O
         utf8Buffer.mid(lineStartUtf8Offset, lineEndUtf8Offset - lineStartUtf8Offset));
 }
 
+static bool isByteOfMultiByteCodePoint(unsigned char byte)
+{
+    return byte & 0x80; // Check if most significant bit is set
+}
+
+bool utf8AdvanceCodePoint(const char *&current)
+{
+    if (Q_UNLIKELY(*current == '\0'))
+        return false;
+
+    // Process multi-byte UTF-8 code point (non-latin1)
+    if (Q_UNLIKELY(isByteOfMultiByteCodePoint(*current))) {
+        unsigned trailingBytesCurrentCodePoint = 1;
+        for (unsigned char c = (*current) << 2; isByteOfMultiByteCodePoint(c); c <<= 1)
+            ++trailingBytesCurrentCodePoint;
+        current += trailingBytesCurrentCodePoint + 1;
+
+    // Process single-byte UTF-8 code point (latin1)
+    } else {
+        ++current;
+    }
+
+    return true;
+}
+
 } // Text
 } // Utils

src/libs/utils/textutils.h

@@ -55,6 +55,7 @@ QTCREATOR_UTILS_EXPORT QTextCursor flippedCursor(const QTextCursor &cursor);
 QTCREATOR_UTILS_EXPORT QTextCursor wordStartCursor(const QTextCursor &cursor);
 QTCREATOR_UTILS_EXPORT QString wordUnderCursor(const QTextCursor &cursor);
 
+QTCREATOR_UTILS_EXPORT bool utf8AdvanceCodePoint(const char *&current);
 QTCREATOR_UTILS_EXPORT int utf8NthLineOffset(const QTextDocument *textDocument,
                                              const QByteArray &buffer,
                                              int line);

src/tools/clangbackend/source/utf8positionfromlinecolumn.cpp

@@ -25,6 +25,8 @@
 
 #include "utf8positionfromlinecolumn.h"
 
+#include <utils/textutils.h>
+
 #include <QtGlobal>
 
 namespace ClangBackEnd {
@@ -77,31 +79,13 @@ bool Utf8PositionFromLineColumn::advanceToColumn(int column)
     return column == 0;
 }
 
-static bool isByteOfMultiByteCodePoint(unsigned char byte)
-{
-    return byte & 0x80; // Check if most significant bit is set
-}
-
 bool Utf8PositionFromLineColumn::advanceCodePoint(bool stopOnNewLine)
 {
     if (Q_UNLIKELY(*m_currentByte == '\0') || (stopOnNewLine && *m_currentByte == '\n'))
         return false;
 
     m_previousByte = m_currentByte;
-
+    return Utils::Text::utf8AdvanceCodePoint(m_currentByte);
-    // Process multi-byte UTF-8 code point (non-latin1)
-    if (Q_UNLIKELY(isByteOfMultiByteCodePoint(*m_currentByte))) {
-        unsigned trailingBytesCurrentCodePoint = 1;
-        for (unsigned char c = (*m_currentByte) << 2; isByteOfMultiByteCodePoint(c); c <<= 1)
-            ++trailingBytesCurrentCodePoint;
-        m_currentByte += trailingBytesCurrentCodePoint + 1;
-
-    // Process single-byte UTF-8 code point (latin1)
-    } else {
-        ++m_currentByte;
-    }
-
-    return true;
 }
 
 } // namespace ClangBackEnd