From ee27c767bd2062c81f0affc0e8992f60a755f099 Mon Sep 17 00:00:00 2001
From: =?utf8?q?Rafa=C5=82=20Jelonek?=
 <71409580+rjelonek@users.noreply.github.com>
Date: Mon, 11 Jan 2021 09:28:41 +0100
Subject: [PATCH] [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
---
 clang/lib/Format/Format.cpp                 |  4 +++-
 clang/unittests/Format/SortIncludesTest.cpp | 36 +++++++++++++++++++++++++++++
 2 files changed, 39 insertions(+), 1 deletion(-)

diff --git a/clang/lib/Format/Format.cpp b/clang/lib/Format/Format.cpp
index 54424ae..5adfed5f 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 d64c978..6dc9d98 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
-- 
2.7.4