cmListFileLexer: Allow a leading UTF-8 Byte-Order-Mark (#11137)

Teach the lexer to read a UTF-8, UTF-16 BE/LE, or UTF-32 BE/LE
Byte-Order-Mark from the start of a file if any is present.  Report an
error on files using UTF-16 or UTF-32 and accept a UTF-8 or missing BOM.

1 files changed, 14 insertions, 1 deletions

diff --git a/Source/cmListFileCache.cxx b/Source/cmListFileCache.cxx
index 898f379..f6ea4b1 100644
--- a/Source/cmListFileCache.cxx
+++ b/Source/cmListFileCache.cxx
@@ -57,13 +57,26 @@ cmListFileParser::~cmListFileParser()
 bool cmListFileParser::ParseFile()
 {
   // Open the file.
-  if(!cmListFileLexer_SetFileName(this->Lexer, this->FileName))
+  cmListFileLexer_BOM bom;
+  if(!cmListFileLexer_SetFileName(this->Lexer, this->FileName, &bom))
     {
     cmSystemTools::Error("cmListFileCache: error can not open file ",
                          this->FileName);
     return false;
     }
 
+  // Verify the Byte-Order-Mark, if any.
+  if(bom != cmListFileLexer_BOM_None &&
+     bom != cmListFileLexer_BOM_UTF8)
+    {
+    cmListFileLexer_SetFileName(this->Lexer, 0, 0);
+    cmOStringStream m;
+    m << "File\n  " << this->FileName << "\n"
+      << "starts with a Byte-Order-Mark that is not UTF-8.";
+    this->Makefile->IssueMessage(cmake::FATAL_ERROR, m.str());
+    return false;
+    }
+
   // Use a simple recursive-descent parser to process the token
   // stream.
   bool haveNewline = true;