C++ scanner: Properly handle UTF-8 byte order mark

Includes in the first line of a source file starting with a byte order
mark would not get detected, resulting in failure to recompile after a
header file change.
Skip over the BOM before passing the data to the lexer.

Task-number: QBS-1348
Done-with: Ola Røer Thorsen <ola@silentwings.no>
Change-Id: I894a5b1667e49be5f8ce9b5cc66e4e796fd073f1
Reviewed-by: Ola Røer Thorsen <ola@silentwings.no>
Reviewed-by: Oswald Buddenhagen <oswald.buddenhagen@qt.io>
Reviewed-by: Joerg Bornemann <joerg.bornemann@qt.io>

1 files changed, 10 insertions, 0 deletions

diff --git a/src/plugins/scanner/cpp/cppscanner.cpp b/src/plugins/scanner/cpp/cppscanner.cpp
index 7e5cbe146..1d7fb7c84 100644
--- a/src/plugins/scanner/cpp/cppscanner.cpp
+++ b/src/plugins/scanner/cpp/cppscanner.cpp
@@ -248,6 +248,16 @@ static void *openScanner(const unsigned short *filePath, const char *fileTags, i
         return nullptr;
 
     opaque->fileContent = reinterpret_cast<char *>(vmap);
+
+    // Check for UTF-8 Byte Order Mark (BOM). Skip if found.
+    if (mapl >= 3
+            && opaque->fileContent[0] == char(0xef)
+            && opaque->fileContent[1] == char(0xbb)
+            && opaque->fileContent[2] == char(0xbf)) {
+        opaque->fileContent += 3;
+        mapl -= 3;
+    }
+
     CPlusPlus::Lexer lex(opaque->fileContent, opaque->fileContent + mapl);
     scanCppFile(opaque.get(), lex, flags & ScanForFileTagsFlag, flags & ScanForDependenciesFlag);
     return opaque.release();