From 6cc38f2df36ff977b723620bac20a6435e132e32 Mon Sep 17 00:00:00 2001
From: Bill Wendling <isanbard@gmail.com>
Date: Tue, 8 Oct 2019 04:39:52 +0000
Subject: [PATCH] [IA] Recognize hexadecimal escape sequences

Summary:
Implement support for hexadecimal escape sequences to match how GNU 'as'
handles them. I.e., read all hexadecimal characters and truncate to the
lower 16 bits.

Reviewers: nickdesaulniers, jcai19

Subscribers: llvm-commits, hiraditya

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D68598

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@374018 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/MC/MCParser/AsmParser.cpp       | 18 +++++++++++++++++-
 test/MC/AsmParser/directive_ascii.s |  5 +++++
 2 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/lib/MC/MCParser/AsmParser.cpp b/lib/MC/MCParser/AsmParser.cpp
index 381bf964161..ca6bc252a0d 100644
--- a/lib/MC/MCParser/AsmParser.cpp
+++ b/lib/MC/MCParser/AsmParser.cpp
@@ -2914,11 +2914,27 @@ bool AsmParser::parseEscapedString(std::string &Data) {
     }
 
     // Recognize escaped characters. Note that this escape semantics currently
-    // loosely follows Darwin 'as'. Notably, it doesn't support hex escapes.
+    // loosely follows Darwin 'as'.
     ++i;
     if (i == e)
       return TokError("unexpected backslash at end of string");
 
+    // Recognize hex sequences similarly to GNU 'as'.
+    if (Str[i] == 'x' || Str[i] == 'X') {
+      size_t length = Str.size();
+      if (i + 1 >= length || !isHexDigit(Str[i + 1]))
+        return TokError("invalid hexadecimal escape sequence");
+
+      // Consume hex characters. GNU 'as' reads all hexadecimal characters and
+      // then truncates to the lower 16 bits. Seems reasonable.
+      unsigned Value = 0;
+      while (i + 1 < length && isHexDigit(Str[i + 1]))
+        Value = Value * 16 + hexDigitValue(Str[++i]);
+
+      Data += (unsigned char)(Value & 0xFF);
+      continue;
+    }
+
     // Recognize octal sequences.
     if ((unsigned)(Str[i] - '0') <= 7) {
       // Consume up to three octal characters.
diff --git a/test/MC/AsmParser/directive_ascii.s b/test/MC/AsmParser/directive_ascii.s
index a7ba7bbd5da..604f9721bcc 100644
--- a/test/MC/AsmParser/directive_ascii.s
+++ b/test/MC/AsmParser/directive_ascii.s
@@ -39,3 +39,8 @@ TEST5:
 # CHECK: .byte 0
 TEST6:
         .string "B", "C"
+
+# CHECK: TEST7:
+# CHECK: .ascii "dk"
+TEST7:
+        .ascii "\x64\Xa6B"
-- 
2.40.0