From: Owen Pan <owenpiano@gmail.com>
Date: Wed, 8 May 2019 14:11:12 +0000 (+0000)
Subject: [clang-format] Fix the crash when formatting unsupported encodings
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=d8337696a9075f7e9b6555296fb9b9363cd87c91;p=clang

[clang-format] Fix the crash when formatting unsupported encodings

Fixes PR33946

Differential Revision: https://reviews.llvm.org/D61559

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@360257 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/tools/clang-format/ClangFormat.cpp b/tools/clang-format/ClangFormat.cpp
index 655a8d8e87..60a7feb711 100644
--- a/tools/clang-format/ClangFormat.cpp
+++ b/tools/clang-format/ClangFormat.cpp
@@ -257,6 +257,36 @@ static bool format(StringRef FileName) {
   std::unique_ptr<llvm::MemoryBuffer> Code = std::move(CodeOrErr.get());
   if (Code->getBufferSize() == 0)
     return false; // Empty files are formatted correctly.
+
+  // Check to see if the buffer has a UTF Byte Order Mark (BOM).
+  // We only support UTF-8 with and without a BOM right now.  See
+  // https://en.wikipedia.org/wiki/Byte_order_mark#Byte_order_marks_by_encoding
+  // for more information.
+  StringRef BufStr = Code->getBuffer();
+  const char *InvalidBOM = llvm::StringSwitch<const char *>(BufStr)
+    .StartsWith(llvm::StringLiteral::withInnerNUL("\x00\x00\xFE\xFF"),
+                                                  "UTF-32 (BE)")
+    .StartsWith(llvm::StringLiteral::withInnerNUL("\xFF\xFE\x00\x00"),
+                                                  "UTF-32 (LE)")
+    .StartsWith("\xFE\xFF", "UTF-16 (BE)")
+    .StartsWith("\xFF\xFE", "UTF-16 (LE)")
+    .StartsWith("\x2B\x2F\x76", "UTF-7")
+    .StartsWith("\xF7\x64\x4C", "UTF-1")
+    .StartsWith("\xDD\x73\x66\x73", "UTF-EBCDIC")
+    .StartsWith("\x0E\xFE\xFF", "SCSU")
+    .StartsWith("\xFB\xEE\x28", "BOCU-1")
+    .StartsWith("\x84\x31\x95\x33", "GB-18030")
+    .Default(nullptr);
+
+  if (InvalidBOM) {
+    errs() << "error: encoding with unsupported byte order mark \""
+           << InvalidBOM << "\" detected";
+    if (FileName != "-")
+      errs() << " in file '" << FileName << "'";
+    errs() << ".\n";
+    return true;
+  }
+
   std::vector<tooling::Range> Ranges;
   if (fillRanges(Code.get(), Ranges))
     return true;