[BinaryFormat] Teach identify_magic about Tapi files.

[cishida]

Summary

Tapi files are YAML files that start with the !tapi tag. The only execption are
TBD v1 files, which don't have a tag. In that case we have to scan a little
further and check if the first key "archs" exists.

This is the first patch in a series of patches to add libObject support for
text-based dynamic library (.tbd) files.

This patch is practically exactly the same as D37820, that was never pushed to master,
and is needed for future commits related to reading tbd files for llvm-nm

[steven_wu]

few small comments. Otherwise, LGTM.

llvm/include/llvm/BinaryFormat/Magic.h

52

tapi_file is not very clear what it actually refer to. Maybe something like tapi_dylib_stub (I am not very happy with this as well)?

llvm/lib/BinaryFormat/Magic.cpp

214

maybe reverse the order of the condition?

[cishida]

llvm/include/llvm/BinaryFormat/Magic.h

52

what about tbd_file? or tapi_tbd_file? that way it can be deduced that tbd is short for the comment provided and would match the file extension?

[ributzka]

llvm/include/llvm/BinaryFormat/Magic.h

52

I didn't use TBD file on purpose, because that is the current file extension. The file type is tapi and there might be other tapi files in the future that will have different file extensions.

[ributzka]

llvm/lib/BinaryFormat/Magic.cpp

214

+1

[cishida]

Reverse order of conditional for file_magic

[cishida]

• Reverse order of conditional for file_magic

[cishida]

This comment was removed by cishida.

[cishida]

Reverse order of conditional for file_magic

llvm/include/llvm/BinaryFormat/Magic.h

enum Impl {
     coff_object,         ///< COFF object file
     coff_import_library, ///< COFF import library
     pecoff_executable,   ///< PECOFF executable file
     windows_resource,    ///< Windows compiled resource file (.res)
     xcoff_object_32,     ///< 32-bit XCOFF object file
     xcoff_object_64,     ///< 64-bit XCOFF object file
     wasm_object,         ///< WebAssembly Object file
     pdb,                 ///< Windows PDB debug info file
+    tapi_file,           ///< Text-based Dynamic Library Stub file
   };
 
   bool is_object() const { return V != unknown; }
 
   file_magic() = default;
   file_magic(Impl V) : V(V) {}
   operator Impl() const { return V; }
 

llvm/lib/BinaryFormat/Magic.cpp

if (startswith(Magic, "MDMP"))
       return file_magic::minidump;
     break;
 
   case 0x64: // x86-64 or ARM64 Windows.
     if (Magic[1] == char(0x86) || Magic[1] == char(0xaa))
       return file_magic::coff_object;
     break;
 
+  case 0x2d: // YAML '-'
+    if (startswith(Magic, "---\narchs:") || startswith(Magic, "--- !tapi"))
+      return file_magic::tapi_file;
+    break;
+
   default:
     break;
   }
   return file_magic::unknown;
 }
 
 std::error_code llvm::identify_magic(const Twine &Path, file_magic &Result) {
   auto FileOrError = MemoryBuffer::getFile(Path, -1LL, false);
   if (!FileOrError)
     return FileOrError.getError();
 
   std::unique_ptr<MemoryBuffer> FileBuffer = std::move(*FileOrError);
   Result = identify_magic(FileBuffer->getBuffer());
 
   return std::error_code();
 }

llvm/lib/Object/Binary.cpp

case file_magic::pdb:
     // PDB does not support the Binary interface.
     return errorCodeToError(object_error::invalid_file_type);
   case file_magic::unknown:
   case file_magic::coff_cl_gl_object:
     // Unrecognized object file format.
     return errorCodeToError(object_error::invalid_file_type);
   case file_magic::minidump:
     return MinidumpFile::create(Buffer);
+  case file_magic::tapi_file:
+    // Placeholder until TAPI is supported for lib/Object
+    return errorCodeToError(object_error::invalid_file_type);
   }
   llvm_unreachable("Unexpected Binary File Type");
 }
 
 Expected<OwningBinary<Binary>> object::createBinary(StringRef Path) {
   ErrorOr<std::unique_ptr<MemoryBuffer>> FileOrErr =
       MemoryBuffer::getFileOrSTDIN(Path, /*FileSize=*/-1,
                                    /*RequiresNullTerminator=*/false);

llvm/lib/Object/ObjectFile.cpp

ObjectFile::createObjectFile(MemoryBufferRef Object, file_magic Type) {
   case file_magic::bitcode:
   case file_magic::coff_cl_gl_object:
   case file_magic::archive:
   case file_magic::macho_universal_binary:
   case file_magic::windows_resource:
   case file_magic::pdb:
   case file_magic::minidump:
     return errorCodeToError(object_error::invalid_file_type);
+  case file_magic::tapi_file:
+    return errorCodeToError(object_error::invalid_file_type);
   case file_magic::elf:
   case file_magic::elf_relocatable:
   case file_magic::elf_executable:
   case file_magic::elf_shared_object:
   case file_magic::elf_core:
     return createELFObjectFile(Object);
   case file_magic::macho_object:
   case file_magic::macho_executable:

llvm/lib/Object/SymbolicFile.cpp

case file_magic::bitcode:
     LLVM_FALLTHROUGH;
   case file_magic::unknown:
   case file_magic::archive:
   case file_magic::coff_cl_gl_object:
   case file_magic::macho_universal_binary:
   case file_magic::windows_resource:
   case file_magic::pdb:
   case file_magic::minidump:
+  case file_magic::tapi_file:
     return errorCodeToError(object_error::invalid_file_type);
   case file_magic::elf:
   case file_magic::elf_executable:
   case file_magic::elf_shared_object:
   case file_magic::elf_core:
   case file_magic::macho_executable:
   case file_magic::macho_fixed_virtual_memory_shared_lib:
   case file_magic::macho_core:

llvm/unittests/BinaryFormat/TestFileMagic.cpp

const char macho_kext_bundle[] =
     "\xfe\xed\xfa\xce........\x00\x00\x00\x0b............";
 const char windows_resource[] =
     "\x00\x00\x00\x00\x020\x00\x00\x00\xff\xff\x00\x00\xff\xff\x00\x00";
 const char macho_dynamically_linked_shared_lib_stub[] =
     "\xfe\xed\xfa\xce........\x00\x00\x00\x09............";
 const char ms_dos_stub_broken[] = "\x4d\x5a\x20\x20";
 const char pdb[] = "Microsoft C/C++ MSF 7.00\r\n\x1a"
                    "DS\x00\x00\x00";
+const char tapi_file[] = "--- !tapi-tbd-v1\n";
+const char tapi_file_tbd_v1[] = "---\narchs: [";
 
 TEST_F(MagicTest, Magic) {
   struct type {
     const char *filename;
     const char *magic_str;
     size_t magic_str_len;
     file_magic magic;
   } types[] = {
#define DEFINE(magic) {#magic, magic, sizeof(magic), file_magic::magic}
       DEFINE(macho_bundle),
       DEFINE(macho_dynamically_linked_shared_lib_stub),
       DEFINE(macho_dsym_companion),
       DEFINE(macho_kext_bundle),
       DEFINE(windows_resource),
       DEFINE(pdb),
       {"ms_dos_stub_broken", ms_dos_stub_broken, sizeof(ms_dos_stub_broken),
        file_magic::unknown},
+      DEFINE(tapi_file),
+      {"tapi_file_tbd_v1", tapi_file_tbd_v1, sizeof(tapi_file_tbd_v1),
+       file_magic::tapi_file},
 #undef DEFINE
   };
 
   // Create some files filled with magic.
   for (type *i = types, *e = types + (sizeof(types) / sizeof(type)); i != e;
        ++i) {
     SmallString<128> file_pathname(TestDirectory);
     llvm::sys::path::append(file_pathname, i->filename);