From f417583f319bd60d1e32cdf9d0242e42f86101bf Mon Sep 17 00:00:00 2001
From: YingChi Long <me@inclyc.cn>
Date: Wed, 3 Aug 2022 10:07:31 +0800
Subject: [PATCH] [clang] format string checking for conpile-time evaluated str
 literal

This patch enhances clang's ability to check compile-time determinable
string literals as format strings, and can give FixIt hints at literals
(unlike gcc). Issue https://github.com/llvm/llvm-project/issues/55805
mentiond two compile-time string cases. And this patch partially fixes
one.

```
constexpr const char* foo() {
  return "%s %d";
}
int main() {
   printf(foo(), "abc", "def");
   return 0;
}
```

This patch enables clang check format string for this:

```
<source>:4:24: warning: format specifies type 'int' but the argument has type 'const char *' [-Wformat]
  printf(foo(), "abc", "def");
         ~~~~~         ^~~~~
<source>:2:42: note: format string is defined here
constexpr const char *foo() { return "%s %d"; }
                                         ^~
                                         %s
1 warning generated.
```

Reviewed By: aaron.ballman

Signed-off-by: YingChi Long <me@inclyc.cn>

Differential Revision: https://reviews.llvm.org/D130906
---
 clang/docs/ReleaseNotes.rst           |  2 ++
 clang/lib/Sema/SemaChecking.cpp       | 23 +++++++++++++++++-
 clang/test/SemaCXX/format-strings.cpp | 45 +++++++++++++++++++++++++++++++++++
 3 files changed, 69 insertions(+), 1 deletion(-)

diff --git a/clang/docs/ReleaseNotes.rst b/clang/docs/ReleaseNotes.rst
index 878effe..85d360e 100644
--- a/clang/docs/ReleaseNotes.rst
+++ b/clang/docs/ReleaseNotes.rst
@@ -67,6 +67,8 @@ Improvements to Clang's diagnostics
   enum without a fixed underlying type is set to a value outside the range of
   the enumeration's values. Fixes
   `Issue 50055: <https://github.com/llvm/llvm-project/issues/50055>`_.
+- Clang will now check compile-time determinable string literals as format strings.
+  This fixes `Issue 55805: <https://github.com/llvm/llvm-project/issues/55805>`_.
 
 Non-comprehensive list of changes in this release
 -------------------------------------------------
diff --git a/clang/lib/Sema/SemaChecking.cpp b/clang/lib/Sema/SemaChecking.cpp
index 6b60312..6428be1 100644
--- a/clang/lib/Sema/SemaChecking.cpp
+++ b/clang/lib/Sema/SemaChecking.cpp
@@ -8473,6 +8473,9 @@ static void CheckFormatString(
     llvm::SmallBitVector &CheckedVarArgs, UncoveredArgHandler &UncoveredArg,
     bool IgnoreStringsWithoutSpecifiers);
 
+static const Expr *maybeConstEvalStringLiteral(ASTContext &Context,
+                                               const Expr *E);
+
 // Determine if an expression is a string literal or constant string.
 // If this function returns false on the arguments to a function expecting a
 // format string, we will usually need to emit a warning.
@@ -8713,7 +8716,11 @@ tryAgain:
         }
       }
     }
-
+    if (const auto *SLE = maybeConstEvalStringLiteral(S.Context, E))
+      return checkFormatStringExpr(S, SLE, Args, APK, format_idx, firstDataArg,
+                                   Type, CallType, /*InFunctionCall*/ false,
+                                   CheckedVarArgs, UncoveredArg, Offset,
+                                   IgnoreStringsWithoutSpecifiers);
     return SLCT_NotALiteral;
   }
   case Stmt::ObjCMessageExprClass: {
@@ -8823,6 +8830,20 @@ tryAgain:
   }
 }
 
+// If this expression can be evaluated at compile-time,
+// check if the result is a StringLiteral and return it
+// otherwise return nullptr
+static const Expr *maybeConstEvalStringLiteral(ASTContext &Context,
+                                               const Expr *E) {
+  Expr::EvalResult Result;
+  if (E->EvaluateAsRValue(Result, Context) && Result.Val.isLValue()) {
+    const auto *LVE = Result.Val.getLValueBase().dyn_cast<const Expr *>();
+    if (isa_and_nonnull<StringLiteral>(LVE))
+      return LVE;
+  }
+  return nullptr;
+}
+
 Sema::FormatStringType Sema::GetFormatStringType(const FormatAttr *Format) {
   return llvm::StringSwitch<FormatStringType>(Format->getType()->getName())
       .Case("scanf", FST_Scanf)
diff --git a/clang/test/SemaCXX/format-strings.cpp b/clang/test/SemaCXX/format-strings.cpp
index a0dcf01..2378eea 100644
--- a/clang/test/SemaCXX/format-strings.cpp
+++ b/clang/test/SemaCXX/format-strings.cpp
@@ -163,3 +163,48 @@ void f() {
   t::func4("Hello %s"); // expected-warning {{more '%' conversions than data arguments}}
 }
 }
+#if __cplusplus >= 201103L
+namespace evaluated {
+
+constexpr const char *basic() { 
+  return 
+"%s %d"; // expected-note {{format string is defined here}}
+}
+
+constexpr const char *correct_fmt() { 
+  return 
+"%d %d";
+}
+
+constexpr const char *string_linebreak() { 
+  return 
+"%d %d"
+"%d %s"; // expected-note {{format string is defined here}}
+}
+
+/*non-constexpr*/ const char *not_literal() { 
+  return 
+"%d %d"
+"%d %s";
+}
+
+constexpr const char *inner_call() {
+  return "%d %s"; // expected-note {{format string is defined here}}
+}
+
+constexpr const char *wrap_constexpr() {
+  return inner_call();
+}
+
+
+void f() {
+  printf(basic(), 1, 2); // expected-warning {{format specifies type 'char *' but the argument has type 'int'}}
+  printf(correct_fmt(), 1, 2);
+  printf(string_linebreak(), 1, 2, 3, 4); // expected-warning {{format specifies type 'char *' but the argument has type 'int'}}
+  printf(not_literal(), 1, 2, 3, 4); // expected-warning {{format string is not a string literal}}
+  printf(wrap_constexpr(), 1, 2); // expected-warning {{format specifies type 'char *' but the argument has type 'int'}}
+}
+
+
+}
+#endif
-- 
2.7.4