[BinaryFormat] Teach identify_magic about Tapi files.

[ributzka]

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.

[vsk]

LGTM, but it'd be good to get a second +1 from someone more familiar with libObject internals.

[lhames]

LGTM so far, but I'd like to see the follow up patches to see where it's going. :)

[Bigcheese]

Is the intent for TAPI files to be a subset of YAML? This only detects one very specific way of starting a YAML file.

Other than that this looks fine.

[compnerd]

Unfortunately, the TAPI releases are in the wild, so we need to support the old files. It would be nice to have some sort of marker on the file (similar to a shebang) to indicate that it is a TAPI file.

[ributzka]

We do have that now. All TAPI files start now with "--- !tapi". It is only
that the first version doesn't have that marker and that is why we have to
fall back to this extra check.

[ributzka]

New version is tracked here: D66149

llvm/include/llvm/BinaryFormat/Magic.h

enum Impl {
     macho_dsym_companion,                     ///< Mach-O dSYM companion file
     macho_kext_bundle,                        ///< Mach-O kext bundle file
     macho_universal_binary,                   ///< Mach-O universal binary
     coff_cl_gl_object,   ///< Microsoft cl.exe's intermediate code file
     coff_object,         ///< COFF object file
     coff_import_library, ///< COFF import library
     pecoff_executable,   ///< PECOFF executable file
     windows_resource,    ///< Windows compiled resource file (.res)
-    wasm_object          ///< WebAssembly Object file
+    wasm_object,         ///< WebAssembly Object 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

case 'M': // Possible MS-DOS stub on Windows PE file
     }
     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: // Tapi File '-'
+    if (startswith(Magic, "---\narchs:") || startswith(Magic, "--- !tapi"))
+      return file_magic::tapi_file;
+
   default:
     break;
   }
   return file_magic::unknown;
 }
 
 std::error_code llvm::identify_magic(const Twine &Path, file_magic &Result) {
   int FD;

llvm/lib/Object/Binary.cpp

Expected<std::unique_ptr<Binary>> object::createBinary(MemoryBufferRef Buffer,
   case file_magic::wasm_object:
     return ObjectFile::createSymbolicFile(Buffer, Type, Context);
   case file_magic::macho_universal_binary:
     return MachOUniversalBinary::create(Buffer);
   case file_magic::windows_resource:
     return WindowsResource::createWindowsResource(Buffer);
   case file_magic::unknown:
   case file_magic::coff_cl_gl_object:
+  case file_magic::tapi_file:
     // Unrecognized object file format.
     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 =

llvm/lib/Object/ObjectFile.cpp

ObjectFile::createObjectFile(MemoryBufferRef Object, file_magic Type) {
 
   switch (Type) {
   case file_magic::unknown:
   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::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 errorOrToExpected(createELFObjectFile(Object));
   case file_magic::macho_object:

llvm/lib/Object/SymbolicFile.cpp

case file_magic::bitcode:
     if (Context)
       return IRObjectFile::create(Object, *Context);
     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::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_dsym_companion[] =
     "\xfe\xed\xfa\xce........\x00\x00\x00\x0a............";
 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 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_dynamic_linker),
       DEFINE(macho_bundle),
       DEFINE(macho_dynamically_linked_shared_lib_stub),
       DEFINE(macho_dsym_companion),
       DEFINE(macho_kext_bundle),
       DEFINE(windows_resource),
       {"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);