Suggest typo corrections for preprocessor directives

When a preprocessor directive is unknown outside of a skipped
conditional block, we give an error diagnostic because we don't know
how to proceed with preprocessing. But when the directive is in a
skipped conditional block, we would not diagnose it on the theory that
the directive may be known to an implementation other than Clang.

Now, for unknown directives inside a skipped conditional block, we
diagnose the unknown directive as a warning if it is sufficiently
similar to a directive specific to preprocessor conditional blocks. For
example, we'll warn about `#esle` and suggest `#else` but we won't warn
about `#progma` because it's not a directive specific to preprocessor
conditional blocks.

Fixes #51598

Differential Revision: https://reviews.llvm.org/D124726

clang/docs/ReleaseNotes.rst

@@ -225,6 +225,13 @@ Improvements to Clang's diagnostics
 - Clang now checks for stack resource exhaustion when recursively parsing
   declarators in order to give a diagnostic before we run out of stack space.
   This fixes `Issue 51642 <https://github.com/llvm/llvm-project/issues/51642>`_.
+- Unknown preprocessor directives in a skipped conditional block are now given
+  a typo correction suggestion if the given directive is sufficiently similar
+  to another preprocessor conditional directive. For example, if ``#esle``
+  appears in a skipped block, we will warn about the unknown directive and
+  suggest ``#else`` as an alternative. ``#elifdef`` and ``#elifndef`` are only
+  suggested when in C2x or C++2b mode. Fixes
+  `Issue 51598 <https://github.com/llvm/llvm-project/issues/51598>`_.
 
 Non-comprehensive list of changes in this release
 -------------------------------------------------

clang/include/clang/Basic/DiagnosticLexKinds.td

@@ -430,8 +430,10 @@ def ext_pp_opencl_variadic_macros : Extension<
 def ext_pp_gnu_line_directive : Extension<
   "this style of line directive is a GNU extension">,
   InGroup<GNULineMarker>;
-
-def err_pp_invalid_directive : Error<"invalid preprocessing directive">;
+def err_pp_invalid_directive : Error<
+  "invalid preprocessing directive%select{|, did you mean '#%1'?}0">;
+def warn_pp_invalid_directive : Warning<
+  err_pp_invalid_directive.Text>, InGroup<DiagGroup<"unknown-directives">>;
 def err_pp_directive_required : Error<
   "%0 must be used within a preprocessing directive">;
 def err_pp_file_not_found : Error<"'%0' file not found">, DefaultFatal;

clang/include/clang/Lex/Preprocessor.h

@@ -2238,6 +2238,16 @@ private:
   /// Return true if an error occurs parsing the arg list.
   bool ReadMacroParameterList(MacroInfo *MI, Token& LastTok);
 
+  /// Provide a suggestion for a typoed directive. If there is no typo, then
+  /// just skip suggesting.
+  ///
+  /// \param Tok - Token that represents the directive
+  /// \param Directive - String reference for the directive name
+  /// \param EndLoc - End location for fixit
+  void SuggestTypoedDirective(const Token &Tok,
+                              StringRef Directive,
+                              const SourceLocation &EndLoc) const;
+
   /// We just read a \#if or related directive and decided that the
   /// subsequent tokens are in the \#if'd out portion of the
   /// file.  Lex the rest of the file, until we see an \#endif.  If \p

clang/lib/Lex/PPDirectives.cpp

@@ -266,6 +266,51 @@ static bool warnByDefaultOnWrongCase(StringRef Include) {
     .Default(false);
 }
 
+/// Find a similar string in `Candidates`.
+///
+/// \param LHS a string for a similar string in `Candidates`
+///
+/// \param Candidates the candidates to find a similar string.
+///
+/// \returns a similar string if exists. If no similar string exists,
+/// returns None.
+static Optional<StringRef> findSimilarStr(
+    StringRef LHS, const std::vector<StringRef> &Candidates) {
+  // We need to check if `Candidates` has the exact case-insensitive string
+  // because the Levenshtein distance match does not care about it.
+  for (StringRef C : Candidates) {
+    if (LHS.equals_insensitive(C)) {
+      return C;
+    }
+  }
+
+  // Keep going with the Levenshtein distance match.
+  // If the LHS size is less than 3, use the LHS size minus 1 and if not,
+  // use the LHS size divided by 3.
+  size_t Length = LHS.size();
+  size_t MaxDist = Length < 3 ? Length - 1 : Length / 3;
+
+  Optional<std::pair<StringRef, size_t>> SimilarStr = None;
+  for (StringRef C : Candidates) {
+    size_t CurDist = LHS.edit_distance(C, true);
+    if (CurDist <= MaxDist) {
+      if (!SimilarStr.hasValue()) {
+        // The first similar string found.
+        SimilarStr = {C, CurDist};
+      } else if (CurDist < SimilarStr->second) {
+        // More similar string found.
+        SimilarStr = {C, CurDist};
+      }
+    }
+  }
+
+  if (SimilarStr.hasValue()) {
+    return SimilarStr->first;
+  } else {
+    return None;
+  }
+}
+
 bool Preprocessor::CheckMacroName(Token &MacroNameTok, MacroUse isDefineUndef,
                                   bool *ShadowFlag) {
   // Missing macro name?
@@ -433,6 +478,25 @@ Optional<unsigned> Preprocessor::getSkippedRangeForExcludedConditionalBlock(
   return BytesToSkip - LengthDiff;
 }
 
+void Preprocessor::SuggestTypoedDirective(const Token &Tok,
+                                          StringRef Directive,
+                                          const SourceLocation &EndLoc) const {
+  std::vector<StringRef> Candidates = {
+      "if", "ifdef", "ifndef", "elif", "else", "endif"
+  };
+  if (LangOpts.C2x || LangOpts.CPlusPlus2b)
+    Candidates.insert(Candidates.end(), {"elifdef", "elifndef"});
+
+  if (Optional<StringRef> Sugg = findSimilarStr(Directive, Candidates)) {
+    CharSourceRange DirectiveRange =
+        CharSourceRange::getCharRange(Tok.getLocation(), EndLoc);
+    std::string SuggValue = Sugg.getValue().str();
+
+    auto Hint = FixItHint::CreateReplacement(DirectiveRange, "#" + SuggValue);
+    Diag(Tok, diag::warn_pp_invalid_directive) << 1 << SuggValue << Hint;
+  }
+}
+
 /// SkipExcludedConditionalBlock - We just read a \#if or related directive and
 /// decided that the subsequent tokens are in the \#if'd out portion of the
 /// file.  Lex the rest of the file, until we see an \#endif.  If
@@ -556,6 +620,8 @@ void Preprocessor::SkipExcludedConditionalBlock(SourceLocation HashTokenLoc,
         CurPPLexer->pushConditionalLevel(Tok.getLocation(), /*wasskipping*/true,
                                        /*foundnonskip*/false,
                                        /*foundelse*/false);
+      } else {
+        SuggestTypoedDirective(Tok, Directive, endLoc);
       }
     } else if (Directive[0] == 'e') {
       StringRef Sub = Directive.substr(1);
@@ -716,7 +782,11 @@ void Preprocessor::SkipExcludedConditionalBlock(SourceLocation HashTokenLoc,
             break;
           }
         }
+      } else {
+        SuggestTypoedDirective(Tok, Directive, endLoc);
       }
+    } else {
+      SuggestTypoedDirective(Tok, Directive, endLoc);
     }
 
     CurPPLexer->ParsingPreprocessorDirective = false;
@@ -1193,7 +1263,8 @@ void Preprocessor::HandleDirective(Token &Result) {
   }
 
   // If we reached here, the preprocessing token is not valid!
-  Diag(Result, diag::err_pp_invalid_directive);
+  // Start suggesting if a similar directive found.
+  Diag(Result, diag::err_pp_invalid_directive) << 0;
 
   // Read the rest of the PP line.
   DiscardUntilEndOfDirective();

clang/test/Preprocessor/suggest-typoed-directive.c

@@ -0,0 +1,47 @@
+// RUN: %clang_cc1 -fsyntax-only -verify=pre-c2x-cpp2b %s
+// RUN: %clang_cc1 -std=c2x -fsyntax-only -verify=c2x-cpp2b %s
+// RUN: %clang_cc1 -x c++ -std=c++2b -fsyntax-only -verify=c2x-cpp2b %s
+
+// id:        pre-c2x-cpp2b-warning@+12 {{invalid preprocessing directive, did you mean '#if'?}}
+// ifd:       pre-c2x-cpp2b-warning@+12 {{invalid preprocessing directive, did you mean '#if'?}}
+// ifde:      pre-c2x-cpp2b-warning@+12 {{invalid preprocessing directive, did you mean '#ifdef'?}}
+// elf:       pre-c2x-cpp2b-warning@+12 {{invalid preprocessing directive, did you mean '#elif'?}}
+// elsif:     pre-c2x-cpp2b-warning@+12 {{invalid preprocessing directive, did you mean '#elif'?}}
+// elseif:    pre-c2x-cpp2b-warning@+12 {{invalid preprocessing directive, did you mean '#elif'?}}
+// elfidef:   not suggested to '#elifdef'
+// elfindef:  not suggested to '#elifdef'
+// elfinndef: not suggested to '#elifndef'
+// els:       pre-c2x-cpp2b-warning@+12 {{invalid preprocessing directive, did you mean '#else'?}}
+// endi:      pre-c2x-cpp2b-warning@+12 {{invalid preprocessing directive, did you mean '#endif'?}}
+#ifdef UNDEFINED
+#id
+#ifd
+#ifde
+#elf
+#elsif
+#elseif
+#elfidef
+#elfindef
+#elfinndef
+#els
+#endi
+#endif
+// id:        c2x-cpp2b-warning@-12 {{invalid preprocessing directive, did you mean '#if'?}}
+// ifd:       c2x-cpp2b-warning@-12 {{invalid preprocessing directive, did you mean '#if'?}}
+// ifde:      c2x-cpp2b-warning@-12 {{invalid preprocessing directive, did you mean '#ifdef'?}}
+// elf:       c2x-cpp2b-warning@-12 {{invalid preprocessing directive, did you mean '#elif'?}}
+// elsif:     c2x-cpp2b-warning@-12 {{invalid preprocessing directive, did you mean '#elif'?}}
+// elseif:    c2x-cpp2b-warning@-12 {{invalid preprocessing directive, did you mean '#elif'?}}
+// elfidef:   c2x-cpp2b-warning@-12 {{invalid preprocessing directive, did you mean '#elifdef'?}}
+// elfindef:  c2x-cpp2b-warning@-12 {{invalid preprocessing directive, did you mean '#elifdef'?}}
+// elfinndef: c2x-cpp2b-warning@-12 {{invalid preprocessing directive, did you mean '#elifndef'?}}
+// els:       c2x-cpp2b-warning@-12 {{invalid preprocessing directive, did you mean '#else'?}}
+// endi:      c2x-cpp2b-warning@-12 {{invalid preprocessing directive, did you mean '#endif'?}}
+
+#ifdef UNDEFINED
+#i // no diagnostic
+#endif
+
+#if special_compiler
+#special_compiler_directive // no diagnostic
+#endif