[PATCH] D133565: [pseudo] Print a random text code for each ambiguous symbol in --print-statistics

[Haojian Wu via Phabricator via cfe-commits]

hokein created this revision.
hokein added a reviewer: sammccall.
Herald added a project: All.
hokein requested review of this revision.
Herald added a subscriber: alextsao1999.
Herald added a project: clang-tools-extra.

I found it useful when diagnosing/investigating ambiguous cases.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D133565

Files:
  clang-tools-extra/pseudo/tool/ClangPseudo.cpp


Index: clang-tools-extra/pseudo/tool/ClangPseudo.cpp
===================================================================
--- clang-tools-extra/pseudo/tool/ClangPseudo.cpp
+++ clang-tools-extra/pseudo/tool/ClangPseudo.cpp
@@ -18,6 +18,7 @@
 #include "clang-pseudo/grammar/LRGraph.h"
 #include "clang-pseudo/grammar/LRTable.h"
 #include "clang/Basic/LangOptions.h"
+#include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/STLFunctionalExtras.h"
 #include "llvm/Support/CommandLine.h"
@@ -185,14 +186,32 @@
       llvm::outs() << "GSS bytes: " << GSS.bytes()
                    << " nodes: " << GSS.nodesCreated() << "\n";
 
+      llvm::DenseMap<clang::pseudo::SymbolID, std::string> AmbiguousSamples;
       for (auto &P : {std::make_pair("Ambiguous", ForestNode::Ambiguous),
                       std::make_pair("Opaque", ForestNode::Opaque)}) {
         clang::pseudo::NodeStats Stats(
-            Root, [&](const auto &N) { return N.kind() == P.second; });
+            Root, [&](const clang::pseudo::ForestNode &N) {
+              if (N.kind() == ForestNode::Ambiguous) {
+                if (AmbiguousSamples.count(N.symbol()) == 0) {
+                  Token::Index Start, Last;
+                  Start = Last = N.startTokenIndex();
+                  for (auto &It : N.descendants()) {
+                    if (It.kind() == ForestNode::Terminal)
+                      Last = std::max(Last, It.startTokenIndex());
+                  }
+                  std::string TextCode;
+                  for (const auto &T :
+                       ParseableStream->tokens().slice(Start, Last - Start + 1))
+                    TextCode += T.text();
+                  AmbiguousSamples.insert({N.symbol(), TextCode});
+                }
+              }
+              return N.kind() == P.second;
+            });
         llvm::outs() << "\n" << Stats.Total << " " << P.first << " nodes:\n";
         for (const auto &S : Stats.BySymbol)
-          llvm::outs() << llvm::formatv("  {0,3} {1}\n", S.second,
-                                        Lang.G.symbolName(S.first));
+          llvm::outs() << llvm::formatv("  {0,3} {1}, sample code: {2}\n", S.second,
+                                        Lang.G.symbolName(S.first), AmbiguousSamples[S.first]);
       }
 
       // Metrics for how imprecise parsing was.


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D133565.458988.patch
Type: text/x-patch
Size: 2351 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20220909/b3fb48d5/attachment.bin>