Add support for the .base64 directive (#165549)

Starting in version 15, GCC emits a `.base64` directive instead of
`.string` or `.ascii` for char arrays of length `>= 3`.

See [this godbolt link](https://godbolt.org/z/ebhe3oenv) for an example.

This patch adds support for the .base64 directive to AsmParser.cpp, so
tools like `llvm-mc` can process the output of GCC more effectively.

This addresses #165499.

Author: kenballus

llvm/lib/MC/MCParser/AsmParser.cpp

@@ -46,6 +46,7 @@
 #include "llvm/MC/MCSymbolMachO.h"
 #include "llvm/MC/MCTargetOptions.h"
 #include "llvm/MC/MCValue.h"
+#include "llvm/Support/Base64.h"
 #include "llvm/Support/Casting.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/ErrorHandling.h"
@@ -528,6 +529,7 @@ class AsmParser : public MCAsmParser {
     DK_LTO_SET_CONDITIONAL,
     DK_CFI_MTE_TAGGED_FRAME,
     DK_MEMTAG,
+    DK_BASE64,
     DK_END
   };
 
@@ -550,6 +552,7 @@ class AsmParser : public MCAsmParser {
 
   // ".ascii", ".asciz", ".string"
   bool parseDirectiveAscii(StringRef IDVal, bool ZeroTerminated);
+  bool parseDirectiveBase64();                  // ".base64"
   bool parseDirectiveReloc(SMLoc DirectiveLoc); // ".reloc"
   bool parseDirectiveValue(StringRef IDVal,
                            unsigned Size);       // ".byte", ".long", ...
@@ -1951,6 +1954,8 @@ bool AsmParser::parseStatement(ParseStatementInfo &Info,
     case DK_ASCIZ:
     case DK_STRING:
       return parseDirectiveAscii(IDVal, true);
+    case DK_BASE64:
+      return parseDirectiveBase64();
     case DK_BYTE:
     case DK_DC_B:
       return parseDirectiveValue(IDVal, 1);
@@ -3074,6 +3079,37 @@ bool AsmParser::parseDirectiveAscii(StringRef IDVal, bool ZeroTerminated) {
   return parseMany(parseOp);
 }
 
+/// parseDirectiveBase64:
+//    ::= .base64 "string" (, "string" )*
+bool AsmParser::parseDirectiveBase64() {
+  auto parseOp = [&]() -> bool {
+    if (checkForValidSection())
+      return true;
+
+    if (getTok().isNot(AsmToken::String)) {
+      return true;
+    }
+
+    std::vector<char> Decoded;
+    std::string const str = getTok().getStringContents().str();
+    if (check(str.empty(), "expected nonempty string")) {
+      return true;
+    }
+
+    llvm::Error e = decodeBase64(str, Decoded);
+    if (e) {
+      consumeError(std::move(e));
+      return Error(Lexer.getLoc(), "failed to base64 decode string data");
+    }
+
+    getStreamer().emitBytes(std::string(Decoded.begin(), Decoded.end()));
+    Lex();
+    return false;
+  };
+
+  return check(parseMany(parseOp), "expected string");
+}
+
 /// parseDirectiveReloc
 ///  ::= .reloc expression , identifier [ , expression ]
 bool AsmParser::parseDirectiveReloc(SMLoc DirectiveLoc) {
@@ -5343,6 +5379,7 @@ void AsmParser::initializeDirectiveKindMap() {
   DirectiveKindMap[".asciz"] = DK_ASCIZ;
   DirectiveKindMap[".string"] = DK_STRING;
   DirectiveKindMap[".byte"] = DK_BYTE;
+  DirectiveKindMap[".base64"] = DK_BASE64;
   DirectiveKindMap[".short"] = DK_SHORT;
   DirectiveKindMap[".value"] = DK_VALUE;
   DirectiveKindMap[".2byte"] = DK_2BYTE;

llvm/test/MC/AsmParser/directive_base64.s

@@ -0,0 +1,37 @@
+# RUN: llvm-mc -triple i386-unknown-unknown %s | FileCheck %s
+# RUN: not llvm-mc -triple i386-unknown-unknown -defsym=ERR=1 -o /dev/null %s 2>&1 | FileCheck %s --check-prefix=CHECK-ERROR
+
+        .data
+# CHECK-LABEL: TEST0:
+# CHECK-NEXT: .byte 0
+TEST0:
+        .base64 "AA=="
+
+# CHECK-LABEL: TEST1:
+# CHECK-NEXT: .ascii "abcxyz"
+TEST1:
+        .base64 "YWJjeHl6"
+
+# CHECK-LABEL: TEST2:
+# CHECK-NEXT: .byte 1
+# CHECK-NEXT: .byte 2
+TEST2:
+        .base64 "AQ=="
+        .base64 "Ag=="
+
+# CHECK-LABEL: TEST3:
+# CHECK-NEXT: .byte 1
+# CHECK-NEXT: .byte 2
+TEST3:
+        .base64 "AQ==", "Ag=="
+
+.ifdef ERR
+# CHECK-ERROR: [[#@LINE+1]]:17: error: expected string
+        .base64 not-a-string
+
+# CHECK-ERROR: [[#@LINE+1]]:17: error: failed to base64 decode string data
+        .base64 "AA"
+
+# CHECK-ERROR: [[#@LINE+1]]:17: error: expected nonempty string
+        .base64 ""
+.endif