[clang] ee27c76 - [clang-format] Skip UTF8 Byte Order Mark while sorting includes

[Marek Kurdej via cfe-commits]

Author: Rafał Jelonek
Date: 2021-01-11T09:32:55+01:00
New Revision: ee27c767bd2062c81f0affc0e8992f60a755f099

URL: https://github.com/llvm/llvm-project/commit/ee27c767bd2062c81f0affc0e8992f60a755f099
DIFF: https://github.com/llvm/llvm-project/commit/ee27c767bd2062c81f0affc0e8992f60a755f099.diff

LOG: [clang-format] Skip UTF8 Byte Order Mark while sorting includes

If file contain BOM then first instruction (include or clang-format off) is ignored

Reviewed By: MyDeveloperDay

Differential Revision: https://reviews.llvm.org/D94201

Added: 
    

Modified: 
    clang/lib/Format/Format.cpp
    clang/unittests/Format/SortIncludesTest.cpp

Removed: 
    


################################################################################
diff  --git a/clang/lib/Format/Format.cpp b/clang/lib/Format/Format.cpp
index 54424ae190e2..5adfed5f3d32 100644
--- a/clang/lib/Format/Format.cpp
+++ b/clang/lib/Format/Format.cpp
@@ -2253,7 +2253,9 @@ tooling::Replacements sortCppIncludes(const FormatStyle &Style, StringRef Code,
                                       StringRef FileName,
                                       tooling::Replacements &Replaces,
                                       unsigned *Cursor) {
-  unsigned Prev = 0;
+  unsigned Prev = llvm::StringSwitch<size_t>(Code)
+                      .StartsWith("\xEF\xBB\xBF", 3) // UTF-8 BOM
+                      .Default(0);
   unsigned SearchFrom = 0;
   llvm::Regex IncludeRegex(CppIncludeRegexPattern);
   SmallVector<StringRef, 4> Matches;

diff  --git a/clang/unittests/Format/SortIncludesTest.cpp b/clang/unittests/Format/SortIncludesTest.cpp
index d64c97820003..6dc9d9850c59 100644
--- a/clang/unittests/Format/SortIncludesTest.cpp
+++ b/clang/unittests/Format/SortIncludesTest.cpp
@@ -879,6 +879,42 @@ TEST_F(SortIncludesTest, DoNotRegroupGroupsInGoogleObjCStyle) {
                  "#include \"a.h\""));
 }
 
+TEST_F(SortIncludesTest, skipUTF8ByteOrderMarkMerge) {
+  Style.IncludeBlocks = Style.IBS_Merge;
+  std::string Code = "\xEF\xBB\xBF#include \"d.h\"\r\n"
+                     "#include \"b.h\"\r\n"
+                     "\r\n"
+                     "#include \"c.h\"\r\n"
+                     "#include \"a.h\"\r\n"
+                     "#include \"e.h\"\r\n";
+
+  std::string Expected = "\xEF\xBB\xBF#include \"e.h\"\r\n"
+                         "#include \"a.h\"\r\n"
+                         "#include \"b.h\"\r\n"
+                         "#include \"c.h\"\r\n"
+                         "#include \"d.h\"\r\n";
+
+  EXPECT_EQ(Expected, sort(Code, "e.cpp", 1));
+}
+
+TEST_F(SortIncludesTest, skipUTF8ByteOrderMarkPreserve) {
+  Style.IncludeBlocks = Style.IBS_Preserve;
+  std::string Code = "\xEF\xBB\xBF#include \"d.h\"\r\n"
+                     "#include \"b.h\"\r\n"
+                     "\r\n"
+                     "#include \"c.h\"\r\n"
+                     "#include \"a.h\"\r\n"
+                     "#include \"e.h\"\r\n";
+
+  std::string Expected = "\xEF\xBB\xBF#include \"b.h\"\r\n"
+                         "#include \"d.h\"\r\n"
+                         "\r\n"
+                         "#include \"a.h\"\r\n"
+                         "#include \"c.h\"\r\n"
+                         "#include \"e.h\"\r\n";
+
+  EXPECT_EQ(Expected, sort(Code, "e.cpp", 2));
+}
 } // end namespace
 } // end namespace format
 } // end namespace clang