Add warning for non-UTF-8 files

src/c4group/C4ComponentHost.cpp

@@ -98,16 +98,20 @@ bool C4ComponentHost::Load(C4GroupSet &hGroupSet,
 
 void C4ComponentHost::FinishLoad(const StdStrBuf & name, C4Group &hGroup)
 {
-	Data.EnsureUnicode();
+	// Store actual filename
+	hGroup.FindEntry(name.getData(), &Filename);
+	CopyFilePathFromGroup(hGroup);
+
+	if (Data.EnsureUnicode())
+	{
+		LogF("WARNING: File is not encoded as UTF-8 (%s)", FilePath.getData());
+	}
 	// Skip those stupid "zero width no-break spaces" (also known as Byte Order Marks)
 	if (Data[0] == '\xEF' && Data[1] == '\xBB' && Data[2] == '\xBF')
 	{
 		Data.Move(3,Data.getSize()-3);
 		Data.Shrink(3);
 	}
-	// Store actual filename
-	hGroup.FindEntry(name.getData(), &Filename);
-	CopyFilePathFromGroup(hGroup);
 	// Notify
 	OnLoad();
 }

src/lib/StdBuf.cpp

@@ -433,7 +433,8 @@ void StdStrBuf::AppendCharacter(uint32_t unicodechar)
 	else /* not an unicode code point, ignore */ {}
 }
 
-void StdStrBuf::EnsureUnicode()
+// Returns true if charset was converted.
+bool StdStrBuf::EnsureUnicode()
 {
 	// assume that it's windows-1252 and convert to utf-8
 	if (!IsValidUtf8(getData(), getLength()))
@@ -477,7 +478,9 @@ void StdStrBuf::EnsureUnicode()
 		}
 		buf.SetLength(j);
 		Take(std::move(buf));
+		return true;
 	}
+	return false;
 }
 
 bool StdStrBuf::TrimSpaces()

src/lib/StdBuf.h

@@ -659,8 +659,8 @@ public:
 	// get an indexed section from the string like Section1;Section2;Section3
 	bool GetSection(size_t idx, StdStrBuf *psOutSection, char cSeparator=';') const;
 
-	// Checks whether the content is valid UTF-8, and if not, convert it from windows-1252 to UTF-8.
-	void EnsureUnicode();
+	// Checks whether the content is valid UTF-8, and if not, convert it from windows-1252 to UTF-8 and return true.
+	bool EnsureUnicode();
 
 	// convert to lower case
 	void ToLowerCase();