[PATCH] D61559: Fix the crash when formatting unsupported encodings

[Owen Pan via Phabricator via cfe-commits]

owenpan created this revision.
owenpan added reviewers: klimek, djasper, sammccall, MyDeveloperDay, krasimir.
owenpan added a project: clang.
Herald added a subscriber: cfe-commits.

See PR33946 <https://bugs.llvm.org/show_bug.cgi?id=33946>.


Repository:
  rC Clang

https://reviews.llvm.org/D61559

Files:
  clang/tools/clang-format/ClangFormat.cpp


Index: clang/tools/clang-format/ClangFormat.cpp
===================================================================
--- clang/tools/clang-format/ClangFormat.cpp
+++ clang/tools/clang-format/ClangFormat.cpp
@@ -257,6 +257,35 @@
   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
+  // http://en.wikipedia.org/wiki/Byte_order_mark for more information.
+  StringRef BufStr = Code->getBuffer();
+  const char *InvalidBOM = llvm::StringSwitch<const char *>(BufStr)
+    .StartsWith("\xFE\xFF", "UTF-16 (BE)")
+    .StartsWith("\xFF\xFE", "UTF-16 (LE)")
+    .StartsWith(llvm::StringLiteral::withInnerNUL("\x00\x00\xFE\xFF"),
+                                                  "UTF-32 (BE)")
+    .StartsWith(llvm::StringLiteral::withInnerNUL("\xFF\xFE\x00\x00"),
+                                                  "UTF-32 (LE)")
+    .StartsWith("\x2B\x2F\x76", "UTF-7")
+    .StartsWith("\xF7\x64\x4C", "UTF-1")
+    .StartsWith("\xDD\x73\x66\x73", "UTF-EBCDIC")
+    .StartsWith("\x0E\xFE\xFF", "SDSU")
+    .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;



Index: clang/tools/clang-format/ClangFormat.cpp
===================================================================
--- clang/tools/clang-format/ClangFormat.cpp
+++ clang/tools/clang-format/ClangFormat.cpp
@@ -257,6 +257,35 @@
   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
+  // http://en.wikipedia.org/wiki/Byte_order_mark for more information.
+  StringRef BufStr = Code->getBuffer();
+  const char *InvalidBOM = llvm::StringSwitch<const char *>(BufStr)
+    .StartsWith("\xFE\xFF", "UTF-16 (BE)")
+    .StartsWith("\xFF\xFE", "UTF-16 (LE)")
+    .StartsWith(llvm::StringLiteral::withInnerNUL("\x00\x00\xFE\xFF"),
+                                                  "UTF-32 (BE)")
+    .StartsWith(llvm::StringLiteral::withInnerNUL("\xFF\xFE\x00\x00"),
+                                                  "UTF-32 (LE)")
+    .StartsWith("\x2B\x2F\x76", "UTF-7")
+    .StartsWith("\xF7\x64\x4C", "UTF-1")
+    .StartsWith("\xDD\x73\x66\x73", "UTF-EBCDIC")
+    .StartsWith("\x0E\xFE\xFF", "SDSU")
+    .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;

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