[llvm] Add support for the .base64 directive (fixes #165499) (PR #165549)

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-llvm-mc

Author: Ben Kallus (kenballus)

<details>
<summary>Changes</summary>

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.

---
Full diff: https://github.com/llvm/llvm-project/pull/165549.diff


1 Files Affected:

- (modified) llvm/lib/MC/MCParser/AsmParser.cpp (+21) 


``````````diff
diff --git a/llvm/lib/MC/MCParser/AsmParser.cpp b/llvm/lib/MC/MCParser/AsmParser.cpp
index dd1bc2be5feb4..54bb1451a5a73 100644
--- a/llvm/lib/MC/MCParser/AsmParser.cpp
+++ b/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"
@@ -530,6 +531,7 @@ class AsmParser : public MCAsmParser {
     DK_LTO_SET_CONDITIONAL,
     DK_CFI_MTE_TAGGED_FRAME,
     DK_MEMTAG,
+    DK_BASE64,
     DK_END
   };
 
@@ -552,6 +554,7 @@ 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", ...
@@ -1953,6 +1956,8 @@ 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);
@@ -3076,6 +3081,21 @@ bool AsmParser::parseDirectiveAscii(StringRef IDVal, bool ZeroTerminated) {
   return parseMany(parseOp);
 }
 
+/// parseDirectiveBase64:
+//    ::= .base64 "string"
+bool AsmParser::parseDirectiveBase64() {
+  std::vector<char> Decoded;
+
+  std::string str;
+
+  if (parseEscapedString(str) || str.empty() || decodeBase64(str, Decoded)) {
+    return true;
+  }
+
+  getStreamer().emitBytes(std::string(Decoded.begin(), Decoded.end()));
+  return false;
+}
+
 /// parseDirectiveReloc
 ///  ::= .reloc expression , identifier [ , expression ]
 bool AsmParser::parseDirectiveReloc(SMLoc DirectiveLoc) {
@@ -5345,6 +5365,7 @@ 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;

``````````

</details>


https://github.com/llvm/llvm-project/pull/165549