[llvm] bed625b - [MC, ELF] Emit warning if a string constant contains newline char (#98060)

[via llvm-commits]

Author: Dmitriy Chestnykh
Date: 2024-07-17T02:34:25+03:00
New Revision: bed625b0ad6722e1d29a3ea492dda173eee541dd

URL: https://github.com/llvm/llvm-project/commit/bed625b0ad6722e1d29a3ea492dda173eee541dd
DIFF: https://github.com/llvm/llvm-project/commit/bed625b0ad6722e1d29a3ea492dda173eee541dd.diff

LOG: [MC,ELF] Emit warning if a string constant contains newline char (#98060)

GAS emits warning about newline in the string constant so make the same
behaviour.

Added: 
    llvm/test/MC/ELF/warn-newline-in-escaped-string.s

Modified: 
    llvm/lib/MC/MCParser/AsmLexer.cpp
    llvm/lib/MC/MCParser/AsmParser.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/MC/MCParser/AsmLexer.cpp b/llvm/lib/MC/MCParser/AsmLexer.cpp
index e08404ae0ad92..778ca340e1248 100644
--- a/llvm/lib/MC/MCParser/AsmLexer.cpp
+++ b/llvm/lib/MC/MCParser/AsmLexer.cpp
@@ -646,7 +646,6 @@ AsmToken AsmLexer::LexQuote() {
     return AsmToken(AsmToken::String, StringRef(TokStart, CurPtr - TokStart));
   }
 
-  // TODO: does gas allow multiline string constants?
   while (CurChar != '"') {
     if (CurChar == '\\') {
       // Allow \", etc.

diff  --git a/llvm/lib/MC/MCParser/AsmParser.cpp b/llvm/lib/MC/MCParser/AsmParser.cpp
index ee5bebf324570..d05712bca73cd 100644
--- a/llvm/lib/MC/MCParser/AsmParser.cpp
+++ b/llvm/lib/MC/MCParser/AsmParser.cpp
@@ -3033,6 +3033,11 @@ bool AsmParser::parseEscapedString(std::string &Data) {
   StringRef Str = getTok().getStringContents();
   for (unsigned i = 0, e = Str.size(); i != e; ++i) {
     if (Str[i] != '\\') {
+      if (Str[i] == '\n') {
+        SMLoc NewlineLoc = SMLoc::getFromPointer(Str.data() + i);
+        if (Warning(NewlineLoc, "unterminated string; newline inserted"))
+          return true;
+      }
       Data += Str[i];
       continue;
     }

diff  --git a/llvm/test/MC/ELF/warn-newline-in-escaped-string.s b/llvm/test/MC/ELF/warn-newline-in-escaped-string.s
new file mode 100644
index 0000000000000..64de13969ffb0
--- /dev/null
+++ b/llvm/test/MC/ELF/warn-newline-in-escaped-string.s
@@ -0,0 +1,55 @@
+// RUN: llvm-mc -filetype=obj -triple x86_64 %s 2>&1 -o /dev/null \
+// RUN:   | FileCheck %s --implicit-check-not=warning:
+
+.string "abcd\xFFefg
+12345678"
+
+// CHECK:       [[#@LINE-3]]:21: warning: unterminated string; newline inserted
+// CHECK-NEXT:  .string "abcd\xFFefg
+
+.ascii "some test ascii
+
+sequence
+with
+newlines\x0A
+"
+
+// CHECK:        [[#@LINE-7]]:24: warning: unterminated string; newline inserted
+// CHECK-NEXT:   .ascii "some test ascii
+// CHECK:        [[#@LINE-8]]:1: warning: unterminated string; newline inserted
+// CHECK:        [[#@LINE-8]]:9: warning: unterminated string; newline inserted
+// CHECK-NEXT:   sequence
+// CHECK:        [[#@LINE-9]]:5: warning: unterminated string; newline inserted
+// CHECK-NEXT:   with
+// CHECK:        [[#@LINE-10]]:13: warning: unterminated string; newline inserted
+// CHECK-NEXT:   newlines\x0A
+
+.asciz "another test string
+
+with
+newline characters
+
+
+"
+
+// CHECK:        [[#@LINE-8]]:28: warning: unterminated string; newline inserted
+// CHECK-NEXT:   .asciz "another test string
+// CHECK:        [[#@LINE-9]]:1: warning: unterminated string; newline inserted
+// CHECK:        [[#@LINE-9]]:5: warning: unterminated string; newline inserted
+// CHECK-NEXT:   with
+// CHECK:        [[#@LINE-10]]:19: warning: unterminated string; newline inserted
+// CHECK-NEXT:   newline characters
+// CHECK:        [[#@LINE-11]]:1: warning: unterminated string; newline inserted
+// CHECK:        [[#@LINE-11]]:1: warning: unterminated string; newline inserted
+
+.file "warn-newline
+.s"
+// CHECK:        [[#@LINE-2]]:20: warning: unterminated string; newline inserted
+
+.cv_file 1 "some_an
+other_file.s"
+// CHECK:        [[#@LINE-2]]:20: warning: unterminated string; newline inserted
+
+.ascii "test\nvalid1_string\xFF\n\n\xFF"
+.asciz "\n\n\nvalid2_string\x0A"
+.string "1234\nvalid3_string\xFF\n\xFF\n"