MC: make ELF .type handling more GNU AS compatible

GAS documents the .type directive as having an optional comma following the key
symbol name when using the STT_<TYPE_IN_UPPER_CASE> form.  However, it treats
the comma as optional in all cases.  This makes the IAS support both forms of
inputs.  Furthermore, the prefixed forms take either the upper case name or the
lower case alias.

The tests are split into two separate sets as the hash character serves as a
comment character on x86, which is tested in the second set by using arm-elf
which uses the at symbol as a comment character.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@210407 91177308-0d34-0410-b5e6-96231b3b80d8

5 files changed, 115 insertions, 38 deletions

diff --git a/lib/MC/MCParser/ELFAsmParser.cpp b/lib/MC/MCParser/ELFAsmParser.cpp
index 95c4971c52..78bb6c7aad 100644
--- a/lib/MC/MCParser/ELFAsmParser.cpp
+++ b/lib/MC/MCParser/ELFAsmParser.cpp
@@ -561,6 +561,19 @@ bool ELFAsmParser::ParseDirectivePrevious(StringRef DirName, SMLoc) {
   return false;
 }
 
+static MCSymbolAttr MCAttrForString(StringRef Type) {
+  return StringSwitch<MCSymbolAttr>(Type)
+          .Cases("STT_FUNC", "function", MCSA_ELF_TypeFunction)
+          .Cases("STT_OBJECT", "object", MCSA_ELF_TypeObject)
+          .Cases("STT_TLS", "tls_object", MCSA_ELF_TypeTLS)
+          .Cases("STT_COMMON", "common", MCSA_ELF_TypeCommon)
+          .Cases("STT_NOTYPE", "notype", MCSA_ELF_TypeNoType)
+          .Cases("STT_GNU_IFUNC", "gnu_indirect_function",
+                 MCSA_ELF_TypeIndFunction)
+          .Case("gnu_unique_object", MCSA_ELF_TypeGnuUniqueObject)
+          .Default(MCSA_Invalid);
+}
+
 /// ParseDirectiveELFType
 ///  ::= .type identifier , STT_<TYPE_IN_UPPER_CASE>
 ///  ::= .type identifier , #attribute
@@ -575,53 +588,36 @@ bool ELFAsmParser::ParseDirectiveType(StringRef, SMLoc) {
   // Handle the identifier as the key symbol.
   MCSymbol *Sym = getContext().GetOrCreateSymbol(Name);
 
-  if (getLexer().isNot(AsmToken::Comma))
-    return TokError("unexpected token in '.type' directive");
-  Lex();
-
-  StringRef Type;
-  SMLoc TypeLoc;
-  MCSymbolAttr Attr;
-  if (getLexer().is(AsmToken::Identifier)) {
-    TypeLoc = getLexer().getLoc();
-    if (getParser().parseIdentifier(Type))
-      return TokError("expected symbol type in directive");
-    Attr = StringSwitch<MCSymbolAttr>(Type)
-               .Case("STT_FUNC", MCSA_ELF_TypeFunction)
-               .Case("STT_OBJECT", MCSA_ELF_TypeObject)
-               .Case("STT_TLS", MCSA_ELF_TypeTLS)
-               .Case("STT_COMMON", MCSA_ELF_TypeCommon)
-               .Case("STT_NOTYPE", MCSA_ELF_TypeNoType)
-               .Case("STT_GNU_IFUNC", MCSA_ELF_TypeIndFunction)
-               .Default(MCSA_Invalid);
-  } else if (getLexer().is(AsmToken::Hash) || getLexer().is(AsmToken::At) ||
-             getLexer().is(AsmToken::Percent) ||
-             getLexer().is(AsmToken::String)) {
-    if (!getLexer().is(AsmToken::String))
-      Lex();
+  // NOTE the comma is optional in all cases.  It is only documented as being
+  // optional in the first case, however, GAS will silently treat the comma as
+  // optional in all cases.  Furthermore, although the documentation states that
+  // the first form only accepts STT_<TYPE_IN_UPPER_CASE>, in reality, GAS
+  // accepts both the upper case name as well as the lower case aliases.
+  if (getLexer().is(AsmToken::Comma))
+    Lex();
 
-    TypeLoc = getLexer().getLoc();
-    if (getParser().parseIdentifier(Type))
-      return TokError("expected symbol type in directive");
-    Attr = StringSwitch<MCSymbolAttr>(Type)
-               .Case("function", MCSA_ELF_TypeFunction)
-               .Case("object", MCSA_ELF_TypeObject)
-               .Case("tls_object", MCSA_ELF_TypeTLS)
-               .Case("common", MCSA_ELF_TypeCommon)
-               .Case("notype", MCSA_ELF_TypeNoType)
-               .Case("gnu_unique_object", MCSA_ELF_TypeGnuUniqueObject)
-               .Case("gnu_indirect_function", MCSA_ELF_TypeIndFunction)
-               .Default(MCSA_Invalid);
-  } else
+  if (getLexer().isNot(AsmToken::Identifier) &&
+      getLexer().isNot(AsmToken::Hash) && getLexer().isNot(AsmToken::At) &&
+      getLexer().isNot(AsmToken::Percent) && getLexer().isNot(AsmToken::String))
     return TokError("expected STT_<TYPE_IN_UPPER_CASE>, '#<type>', '@<type>', "
                     "'%<type>' or \"<type>\"");
 
+  if (getLexer().isNot(AsmToken::String) &&
+      getLexer().isNot(AsmToken::Identifier))
+    Lex();
+
+  SMLoc TypeLoc = getLexer().getLoc();
+
+  StringRef Type;
+  if (getParser().parseIdentifier(Type))
+    return TokError("expected symbol type in directive");
+
+  MCSymbolAttr Attr = MCAttrForString(Type);
   if (Attr == MCSA_Invalid)
     return Error(TypeLoc, "unsupported attribute in '.type' directive");
 
   if (getLexer().isNot(AsmToken::EndOfStatement))
     return TokError("unexpected token in '.type' directive");
-
   Lex();
 
   getStreamer().EmitSymbolAttribute(Sym, Attr);
diff --git a/test/MC/ELF/gnu-type-diagnostics.s b/test/MC/ELF/gnu-type-diagnostics.s
new file mode 100644
index 0000000000..df87d6df08
--- /dev/null
+++ b/test/MC/ELF/gnu-type-diagnostics.s
@@ -0,0 +1,18 @@
+// RUN: not llvm-mc -triple i686-elf -filetype asm -o /dev/null %s 2>&1 | FileCheck %s
+
+	.type TYPE FUNC
+// CHECK: error: unsupported attribute in '.type' directive
+// CHECK: .type TYPE FUNC
+// CHECK:            ^
+
+	.type type stt_func
+// CHECK: error: unsupported attribute in '.type' directive
+// CHECK: .type type stt_func
+// CHECK:            ^
+
+	.type symbol 32
+// CHECK: error: expected STT_<TYPE_IN_UPPER_CASE>, '#<type>', '@<type>', '%<type>' or "<type>"
+// CHECK: .type symbol 32
+// CHECK:              ^
+
+
diff --git a/test/MC/ELF/gnu-type-hash-diagnostics.s b/test/MC/ELF/gnu-type-hash-diagnostics.s
new file mode 100644
index 0000000000..eb364755c4
--- /dev/null
+++ b/test/MC/ELF/gnu-type-hash-diagnostics.s
@@ -0,0 +1,9 @@
+@ RUN: not llvm-mc -triple arm-elf -filetype asm -o /dev/null %s 2>&1 | FileCheck %s
+
+	.syntax unified
+
+	.type TYPE #32
+// CHECK: error: expected symbol type in directive
+// CHECK: .type TYPE #32
+// CHECK:             ^
+
diff --git a/test/MC/ELF/gnu-type-hash.s b/test/MC/ELF/gnu-type-hash.s
new file mode 100644
index 0000000000..ae5c47c567
--- /dev/null
+++ b/test/MC/ELF/gnu-type-hash.s
@@ -0,0 +1,16 @@
+@ RUN: llvm-mc -triple arm-elf -filetype asm -o - %s | FileCheck %s
+
+	.syntax unified
+
+	.type TYPE #STT_FUNC
+// CHECK: .type TYPE,%function
+
+	.type type #function
+// CHECK: .type type,%function
+
+	.type comma_TYPE, #STT_FUNC
+// CHECK: .type comma_TYPE,%function
+
+	.type comma_type, #function
+// CHECK: .type comma_type,%function
+
diff --git a/test/MC/ELF/gnu-type.s b/test/MC/ELF/gnu-type.s
new file mode 100644
index 0000000000..19029e48ee
--- /dev/null
+++ b/test/MC/ELF/gnu-type.s
@@ -0,0 +1,38 @@
+// RUN: llvm-mc -triple i686-elf -filetype asm -o - %s | FileCheck %s
+
+	.type TYPE STT_FUNC
+// CHECK: .type TYPE,@function
+
+	.type comma_TYPE, STT_FUNC
+// CHECK: .type comma_TYPE,@function
+
+	.type at_TYPE, @STT_FUNC
+// CHECK: .type at_TYPE,@function
+
+	.type percent_TYPE, %STT_FUNC
+// CHECK: .type percent_TYPE,@function
+
+	.type string_TYPE, "STT_FUNC"
+// CHECK: .type string_TYPE,@function
+
+	.type type function
+// CHECK: .type type,@function
+
+	.type comma_type, function
+// CHECK: .type comma_type,@function
+
+	.type at_type, @function
+// CHECK: .type at_type,@function
+
+	.type percent_type, %function
+// CHECK: .type percent_type,@function
+
+	.type string_type, "function"
+// CHECK: .type string_type,@function
+
+	.type special gnu_unique_object
+// CHECK: .type special,@gnu_unique_object
+
+	.type comma_special, gnu_unique_object
+// CHECK: .type comma_special,@gnu_unique_object
+