[clang] [analyzer] Introduce per-entry-point statistics (PR #131175)

[Mikael Holmén via cfe-commits]

================
@@ -0,0 +1,201 @@
+//===- EntryPointStats.cpp --------------------------------------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "clang/StaticAnalyzer/Core/PathSensitive/EntryPointStats.h"
+#include "clang/AST/DeclBase.h"
+#include "clang/Analysis/AnalysisDeclContext.h"
+#include "llvm/ADT/STLExtras.h"
+#include "llvm/ADT/StringExtras.h"
+#include "llvm/ADT/StringRef.h"
+#include "llvm/Support/FileSystem.h"
+#include "llvm/Support/ManagedStatic.h"
+#include "llvm/Support/raw_ostream.h"
+#include <iterator>
+
+using namespace clang;
+using namespace ento;
+
+namespace {
+struct Registry {
+  std::vector<BoolEPStat *> BoolStats;
+  std::vector<CounterEPStat *> CounterStats;
+  std::vector<UnsignedMaxEPStat *> UnsignedMaxStats;
+  std::vector<UnsignedEPStat *> UnsignedStats;
+
+  bool IsLocked = false;
+
+  struct Snapshot {
+    const Decl *EntryPoint;
+    std::vector<bool> BoolStatValues;
+    std::vector<unsigned> UnsignedStatValues;
+
+    void dumpAsCSV(llvm::raw_ostream &OS) const;
+  };
+
+  std::vector<Snapshot> Snapshots;
+};
+} // namespace
+
+static llvm::ManagedStatic<Registry> StatsRegistry;
+
+namespace {
+template <typename Callback> void enumerateStatVectors(const Callback &Fn) {
+  Fn(StatsRegistry->BoolStats);
+  Fn(StatsRegistry->CounterStats);
+  Fn(StatsRegistry->UnsignedMaxStats);
+  Fn(StatsRegistry->UnsignedStats);
+}
+} // namespace
+
+static void checkStatName(const EntryPointStat *M) {
+#ifdef NDEBUG
+  return;
+#endif // NDEBUG
+  constexpr std::array AllowedSpecialChars = {
+      '+', '-', '_', '=', ':', '(',  ')', '@', '!', '~',
+      '$', '%', '^', '&', '*', '\'', ';', '<', '>', '/'};
+  for (unsigned char C : M->name()) {
+    if (!std::isalnum(C) && !llvm::is_contained(AllowedSpecialChars, C)) {
+      llvm::errs() << "Stat name \"" << M->name() << "\" contains character '"
+                   << C << "' (" << static_cast<int>(C)
+                   << ") that is not allowed.";
+      assert(false && "The Stat name contains unallowed character");
+    }
+  }
+}
+
+void EntryPointStat::lockRegistry() {
+  auto CmpByNames = [](const EntryPointStat *L, const EntryPointStat *R) {
+    return L->name() < R->name();
+  };
+  enumerateStatVectors(
+      [CmpByNames](auto &Stats) { llvm::sort(Stats, CmpByNames); });
+  enumerateStatVectors(
+      [](const auto &Stats) { llvm::for_each(Stats, checkStatName); });
+  StatsRegistry->IsLocked = true;
+}
+
+static bool isRegistered(llvm::StringLiteral Name) {
----------------
mikaelholmen wrote:

Make this "[[maybe_unused]]" ?
When compiling without asserts we get
```
../../clang/lib/StaticAnalyzer/Core/EntryPointStats.cpp:83:13: error: unused function 'isRegistered' [-Werror,-Wunused-function]
   83 | static bool isRegistered(llvm::StringLiteral Name) {
      |             ^~~~~~~~~~~~
1 error generated.
```

https://github.com/llvm/llvm-project/pull/131175