[clang] f363444 - [clang] Consistently store format specifiers in execution encoding (#195876)

[via cfe-commits]

Author: Sergei Barannikov
Date: 2026-05-05T22:01:24+03:00
New Revision: f36344486169086d0bdb7d973006bf9af0d22aa4

URL: https://github.com/llvm/llvm-project/commit/f36344486169086d0bdb7d973006bf9af0d22aa4
DIFF: https://github.com/llvm/llvm-project/commit/f36344486169086d0bdb7d973006bf9af0d22aa4.diff

LOG: [clang] Consistently store format specifiers in execution encoding (#195876)

`DecomposePrintfHandler::HandlePrintfSpecifier()` parses the format
string and collects specifiers into `Specs`. In most cases the collected
specifiers are in the execution encoding, but there were to places that
used string literals in "host" encoding.

Change them to use a part of the parsed `StringLiteral` instead so that
`Specs` always contain text in the execution encoding. This is achieved
by adding `getCharacters()` method to `OptionalAmount` class, following
`ConversionSpecifier::getCharacters()`.

This is to make #169803 smaller and is an NFC before that PR lands.

Added: 
    

Modified: 
    clang/include/clang/AST/FormatString.h
    clang/lib/Sema/SemaChecking.cpp

Removed: 
    


################################################################################
diff  --git a/clang/include/clang/AST/FormatString.h b/clang/include/clang/AST/FormatString.h
index 586d9f0f8feb0..a3382e1a1d007 100644
--- a/clang/include/clang/AST/FormatString.h
+++ b/clang/include/clang/AST/FormatString.h
@@ -396,6 +396,10 @@ class OptionalAmount {
     return length + UsesDotPrefix;
   }
 
+  StringRef getCharacters() const {
+    return StringRef(start - UsesDotPrefix, length + UsesDotPrefix);
+  }
+
   ArgType getArgType(ASTContext &Ctx) const;
 
   void toString(raw_ostream &os) const;

diff  --git a/clang/lib/Sema/SemaChecking.cpp b/clang/lib/Sema/SemaChecking.cpp
index 12f77d021eb0d..4706fa5d3cde0 100644
--- a/clang/lib/Sema/SemaChecking.cpp
+++ b/clang/lib/Sema/SemaChecking.cpp
@@ -8707,16 +8707,16 @@ bool DecomposePrintfHandler::HandlePrintfSpecifier(
   const auto &FieldWidth = FS.getFieldWidth();
   if (!FieldWidth.isInvalid() && FieldWidth.hasDataArgument()) {
     FieldWidthIndex = Specs.size();
-    Specs.emplace_back(getSpecifierRange(startSpecifier, specifierLen),
-                       getLocationOfByte(FieldWidth.getStart()),
-                       analyze_format_string::LengthModifier::None, "*",
-                       FieldWidth.getArgType(S.Context),
-                       EquatableFormatArgument::FAR_FieldWidth,
-                       EquatableFormatArgument::SS_None,
-                       FieldWidth.usesPositionalArg()
-                           ? FieldWidth.getPositionalArgIndex() - 1
-                           : FieldWidthIndex,
-                       0);
+    Specs.emplace_back(
+        getSpecifierRange(startSpecifier, specifierLen),
+        getLocationOfByte(FieldWidth.getStart()),
+        analyze_format_string::LengthModifier::None, FieldWidth.getCharacters(),
+        FieldWidth.getArgType(S.Context),
+        EquatableFormatArgument::FAR_FieldWidth,
+        EquatableFormatArgument::SS_None,
+        FieldWidth.usesPositionalArg() ? FieldWidth.getPositionalArgIndex() - 1
+                                       : FieldWidthIndex,
+        0);
   }
   // precision?
   const auto &Precision = FS.getPrecision();
@@ -8725,7 +8725,7 @@ bool DecomposePrintfHandler::HandlePrintfSpecifier(
     Specs.emplace_back(
         getSpecifierRange(startSpecifier, specifierLen),
         getLocationOfByte(Precision.getStart()),
-        analyze_format_string::LengthModifier::None, ".*",
+        analyze_format_string::LengthModifier::None, Precision.getCharacters(),
         Precision.getArgType(S.Context), EquatableFormatArgument::FAR_Precision,
         EquatableFormatArgument::SS_None,
         Precision.usesPositionalArg() ? Precision.getPositionalArgIndex() - 1