[PATCH] D114003: LiteralSupport: Don't assert() on invalid input

[Daan De Meyer via Phabricator via cfe-commits]

DaanDeMeyer updated this revision to Diff 387723.
DaanDeMeyer added a comment.

Addressed comments by adding two new errors, one for character literals and one for numeric literals.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D114003/new/

https://reviews.llvm.org/D114003

Files:
  clang/include/clang/Basic/DiagnosticLexKinds.td
  clang/lib/Lex/LiteralSupport.cpp


Index: clang/lib/Lex/LiteralSupport.cpp
===================================================================
--- clang/lib/Lex/LiteralSupport.cpp
+++ clang/lib/Lex/LiteralSupport.cpp
@@ -693,12 +693,6 @@
     : SM(SM), LangOpts(LangOpts), Diags(Diags),
       ThisTokBegin(TokSpelling.begin()), ThisTokEnd(TokSpelling.end()) {
 
-  // This routine assumes that the range begin/end matches the regex for integer
-  // and FP constants (specifically, the 'pp-number' regex), and assumes that
-  // the byte at "*end" is both valid and not part of the regex.  Because of
-  // this, it doesn't have to check for 'overscan' in various places.
-  assert(!isPreprocessingNumberBody(*ThisTokEnd) && "didn't maximally munch?");
-
   s = DigitsBegin = ThisTokBegin;
   saw_exponent = false;
   saw_period = false;
@@ -718,6 +712,16 @@
   isAccum = false;
   hadError = false;
 
+  // This routine assumes that the range begin/end matches the regex for integer
+  // and FP constants (specifically, the 'pp-number' regex), and assumes that
+  // the byte at "*end" is both valid and not part of the regex.  Because of
+  // this, it doesn't have to check for 'overscan' in various places.
+  if (isPreprocessingNumberBody(*ThisTokEnd)) {
+    Diags.Report(TokLoc, diag::err_lexing_numeric);
+    hadError = true;
+    return;
+  }
+
   if (*s == '0') { // parse radix
     ParseNumberStartingWithZero(TokLoc);
     if (hadError)
@@ -1432,7 +1436,12 @@
     ++begin;
 
   // Skip over the entry quote.
-  assert(begin[0] == '\'' && "Invalid token lexed");
+  if (begin[0] != '\'') {
+    PP.Diag(Loc, diag::err_lexing_char);
+    HadError = true;
+    return;
+  }
+
   ++begin;
 
   // Remove an optional ud-suffix.
Index: clang/include/clang/Basic/DiagnosticLexKinds.td
===================================================================
--- clang/include/clang/Basic/DiagnosticLexKinds.td
+++ clang/include/clang/Basic/DiagnosticLexKinds.td
@@ -269,7 +269,9 @@
 def warn_bad_character_encoding : ExtWarn<
   "illegal character encoding in character literal">,
   InGroup<InvalidSourceEncoding>;
-def err_lexing_string : Error<"failure when lexing a string">;
+def err_lexing_string : Error<"failure when lexing a string literal">;
+def err_lexing_char : Error<"failure when lexing a character literal">;
+def err_lexing_numeric : Error<"failure when lexing a numeric literal">;
 def err_placeholder_in_source : Error<"editor placeholder in source file">;
 
 //===----------------------------------------------------------------------===//


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D114003.387723.patch
Type: text/x-patch
Size: 2530 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20211116/0b8eef24/attachment.bin>