[PATCH] D66511: [clang-scan-deps] Skip UTF-8 BOM in source minimizer

[Alexandre Ganea via Phabricator via cfe-commits]

aganea created this revision.
aganea added reviewers: arphaman, dexonsmith, Bigcheese.
aganea added a project: clang.
Herald added a subscriber: tschuett.

As per title.


Repository:
  rC Clang

https://reviews.llvm.org/D66511

Files:
  lib/Lex/DependencyDirectivesSourceMinimizer.cpp
  test/Lexer/minimize_source_to_dependency_directives_utf8bom.c


Index: test/Lexer/minimize_source_to_dependency_directives_utf8bom.c
===================================================================
--- test/Lexer/minimize_source_to_dependency_directives_utf8bom.c
+++ test/Lexer/minimize_source_to_dependency_directives_utf8bom.c
@@ -0,0 +1,10 @@
+// Test UTF8 BOM at start of file
+// RUN: printf '\xef\xbb\xbf' > %t.c
+// RUN: echo '#ifdef TEST\n' >> %t.c
+// RUN: echo '#include <string>' >> %t.c
+// RUN: echo '#endif' >> %t.c
+// RUN: %clang_cc1 -DTEST -print-dependency-directives-minimized-source %t.c 
2>&1 | FileCheck %s
+
+// CHECK:      #ifdef TEST
+// CHECK-NEXT: #include <string>
+// CHECK-NEXT: #endif
Index: lib/Lex/DependencyDirectivesSourceMinimizer.cpp
===================================================================
--- lib/Lex/DependencyDirectivesSourceMinimizer.cpp
+++ lib/Lex/DependencyDirectivesSourceMinimizer.cpp
@@ -812,7 +812,14 @@
   return lexDefault(Kind, Id.Name, First, End);
 }
 
+static void skipUTF8ByteOrderMark(const char *&First, const char *const End) {
+  if ((End - First) >= 3 && First[0] == '\xef' && First[1] == '\xbb' &&
+      First[2] == '\xbf')
+    First += 3;
+}
+
 bool Minimizer::minimizeImpl(const char *First, const char *const End) {
+  skipUTF8ByteOrderMark(First, End);
   while (First != End)
     if (lexPPLine(First, End))
       return true;



Index: test/Lexer/minimize_source_to_dependency_directives_utf8bom.c
===================================================================
--- test/Lexer/minimize_source_to_dependency_directives_utf8bom.c
+++ test/Lexer/minimize_source_to_dependency_directives_utf8bom.c
@@ -0,0 +1,10 @@
+// Test UTF8 BOM at start of file
+// RUN: printf '\xef\xbb\xbf' > %t.c
+// RUN: echo '#ifdef TEST\n' >> %t.c
+// RUN: echo '#include <string>' >> %t.c
+// RUN: echo '#endif' >> %t.c
+// RUN: %clang_cc1 -DTEST -print-dependency-directives-minimized-source %t.c 2>&1 | FileCheck %s
+
+// CHECK:      #ifdef TEST
+// CHECK-NEXT: #include <string>
+// CHECK-NEXT: #endif
Index: lib/Lex/DependencyDirectivesSourceMinimizer.cpp
===================================================================
--- lib/Lex/DependencyDirectivesSourceMinimizer.cpp
+++ lib/Lex/DependencyDirectivesSourceMinimizer.cpp
@@ -812,7 +812,14 @@
   return lexDefault(Kind, Id.Name, First, End);
 }
 
+static void skipUTF8ByteOrderMark(const char *&First, const char *const End) {
+  if ((End - First) >= 3 && First[0] == '\xef' && First[1] == '\xbb' &&
+      First[2] == '\xbf')
+    First += 3;
+}
+
 bool Minimizer::minimizeImpl(const char *First, const char *const End) {
+  skipUTF8ByteOrderMark(First, End);
   while (First != End)
     if (lexPPLine(First, End))
       return true;

_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits