[llvm] 6f41510 - [llvm-rc] Accept filenames provided as multiple string literals (#68881)

[via llvm-commits]

Author: Martin Storsjö
Date: 2023-10-16T23:16:25+03:00
New Revision: 6f41510d4f4848ca4dde203d24bae26587be1f8c

URL: https://github.com/llvm/llvm-project/commit/6f41510d4f4848ca4dde203d24bae26587be1f8c
DIFF: https://github.com/llvm/llvm-project/commit/6f41510d4f4848ca4dde203d24bae26587be1f8c.diff

LOG: [llvm-rc] Accept filenames provided as multiple string literals (#68881)

GNU windres supports this, while MS rc.exe doesn't.

MS rc.exe only supports treating consecutive string literals as if they
were fused into one in a few fixed locations (most of which are already
supported), while GNU windres supports this essentially anywhere in any
string. See
b989fcbae6f179ad887d19ceef83ace1c00b87cc for one recent change that
extended support for this in one specific resource.

A reasonable use case for multiple concatenated string literals that GNU
windres accepts is `1 ICON DIR "/name.ico"`, where the directory is
provided via the preprocessor, expanding to another string literal; this
is https://github.com/llvm/llvm-project/issues/51286.

Extend the parser to try to consume all consecutive string tokens,
whenever reading a filename. Adjust the handling of user data resources
read from a file to use the readFilename() helper.

While this probably doesn't cover every single case where GNU windres
might accept concatenated string literals, this is the primary missing
case that has been reported so far.

Added: 
    llvm/test/tools/llvm-rc/Inputs/split-path.rc
    llvm/test/tools/llvm-rc/split-path.test

Modified: 
    llvm/tools/llvm-rc/ResourceScriptParser.cpp
    llvm/tools/llvm-rc/ResourceScriptParser.h

Removed: 
    


################################################################################
diff  --git a/llvm/test/tools/llvm-rc/Inputs/split-path.rc b/llvm/test/tools/llvm-rc/Inputs/split-path.rc
new file mode 100644
index 000000000000000..fb510e89698f747
--- /dev/null
+++ b/llvm/test/tools/llvm-rc/Inputs/split-path.rc
@@ -0,0 +1,2 @@
+100 ICON "subdir" "/icon-new.ico"
+101 24 "subdir" "/empty.manifest"

diff  --git a/llvm/test/tools/llvm-rc/split-path.test b/llvm/test/tools/llvm-rc/split-path.test
new file mode 100644
index 000000000000000..a12fd2bc32c1161
--- /dev/null
+++ b/llvm/test/tools/llvm-rc/split-path.test
@@ -0,0 +1,7 @@
+; RUN: rm -rf %t
+; RUN: mkdir %t
+; RUN: cd %t
+; RUN: mkdir subdir
+; RUN: cp %p/Inputs/icon-new.ico subdir
+; RUN: touch subdir/empty.manifest
+; RUN: llvm-windres --no-preprocess %p/Inputs/split-path.rc %t/split-path.res

diff  --git a/llvm/tools/llvm-rc/ResourceScriptParser.cpp b/llvm/tools/llvm-rc/ResourceScriptParser.cpp
index 9e1047448831b37..4f02fa502d24fd5 100644
--- a/llvm/tools/llvm-rc/ResourceScriptParser.cpp
+++ b/llvm/tools/llvm-rc/ResourceScriptParser.cpp
@@ -238,7 +238,24 @@ Expected<StringRef> RCParser::readString() {
 Expected<StringRef> RCParser::readFilename() {
   if (!isNextTokenKind(Kind::String) && !isNextTokenKind(Kind::Identifier))
     return getExpectedError("string");
-  return read().value();
+  const RCToken &Token = read();
+  StringRef Str = Token.value();
+  if (Token.kind() != Kind::String)
+    return Str;
+  while (isNextTokenKind(Kind::String)) {
+    const RCToken &NextToken = read();
+    StringRef Next = NextToken.value();
+    bool IsWide = Str.consume_front_insensitive("L");
+    Next.consume_front_insensitive("L");
+    bool StrUnquoted = Str.consume_front("\"") && Str.consume_back("\"");
+    bool NextUnquoted = Next.consume_front("\"") && Next.consume_back("\"");
+    assert(StrUnquoted && NextUnquoted);
+    (void)StrUnquoted;
+    (void)NextUnquoted;
+
+    Str = Saver.save(Twine(IsWide ? "L" : "") + "\"" + Str + Next + "\"");
+  }
+  return Str;
 }
 
 Expected<StringRef> RCParser::readIdentifier() {
@@ -499,9 +516,10 @@ RCParser::ParseType RCParser::parseUserDefinedResource(IntOrString Type) {
   // Check if this is a file resource.
   switch (look().kind()) {
   case Kind::String:
-  case Kind::Identifier:
-    return std::make_unique<UserDefinedResource>(Type, read().value(),
-                                                 MemoryFlags);
+  case Kind::Identifier: {
+    ASSIGN_OR_RETURN(Filename, readFilename());
+    return std::make_unique<UserDefinedResource>(Type, *Filename, MemoryFlags);
+  }
   default:
     break;
   }

diff  --git a/llvm/tools/llvm-rc/ResourceScriptParser.h b/llvm/tools/llvm-rc/ResourceScriptParser.h
index 5c01cec0f151e8b..603afd8d73fb1aa 100644
--- a/llvm/tools/llvm-rc/ResourceScriptParser.h
+++ b/llvm/tools/llvm-rc/ResourceScriptParser.h
@@ -18,6 +18,7 @@
 #include "ResourceScriptToken.h"
 
 #include "llvm/Support/Compiler.h"
+#include "llvm/Support/StringSaver.h"
 #include "llvm/Support/raw_ostream.h"
 
 #include <system_error>
@@ -185,6 +186,9 @@ class RCParser {
   std::vector<RCToken> Tokens;
   LocIter CurLoc;
   const LocIter End;
+
+  BumpPtrAllocator Alloc;
+  StringSaver Saver{Alloc};
 };
 
 } // namespace rc