[Lex] Fix handling numerical literals ending with ' and signed exponent.

For input `0'e+1` lexer tokenized as numeric constant only `0'e`. Later
NumericLiteralParser skipped 0 and ' as digits and parsed `e+1` as valid
exponent going past the end of the token. Because it didn't mark numeric
literal as having an error, it continued parsing and tried to expandUCNs
with StringRef of length -2.

The fix is not to parse exponent when we reached the end of token.

Discovered by OSS-Fuzz:
https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=4588

rdar://problem/36076719

Reviewers: rsmith, t.p.northover

Reviewed By: rsmith

Subscribers: cfe-commits, jkorous-apple

Differential Revision: https://reviews.llvm.org/D41834

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@324419 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Lex/LiteralSupport.cpp b/lib/Lex/LiteralSupport.cpp
index cbec5e6b63856c76a535a764ddbad4636dac66a8..ec342ee3ae2a40802377d9449b20b033cd4285d7 100644 (file)
--- a/lib/Lex/LiteralSupport.cpp
+++ b/lib/Lex/LiteralSupport.cpp
@@ -738,15 +738,17 @@ void NumericLiteralParser::ParseDecimalOrOctalCommon(SourceLocation TokLoc){
     s++;
     radix = 10;
     saw_exponent = true;
-    if (*s == '+' || *s == '-')  s++; // sign
+    if (s != ThisTokEnd && (*s == '+' || *s == '-'))  s++; // sign
     const char *first_non_digit = SkipDigits(s);
     if (containsDigits(s, first_non_digit)) {
       checkSeparator(TokLoc, s, CSK_BeforeDigits);
       s = first_non_digit;
     } else {
-      PP.Diag(PP.AdvanceToTokenCharacter(TokLoc, Exponent-ThisTokBegin),
-              diag::err_exponent_has_no_digits);
-      hadError = true;
+      if (!hadError) {
+        PP.Diag(PP.AdvanceToTokenCharacter(TokLoc, Exponent-ThisTokBegin),
+                diag::err_exponent_has_no_digits);
+        hadError = true;
+      }
       return;
     }
   }
@@ -787,10 +789,12 @@ void NumericLiteralParser::checkSeparator(SourceLocation TokLoc,
   } else if (Pos == ThisTokEnd)
     return;
 
-  if (isDigitSeparator(*Pos))
+  if (isDigitSeparator(*Pos)) {
     PP.Diag(PP.AdvanceToTokenCharacter(TokLoc, Pos - ThisTokBegin),
             diag::err_digit_separator_not_between_digits)
       << IsAfterDigits;
+    hadError = true;
+  }
 }
 
 /// ParseNumberStartingWithZero - This method is called when the first character
@@ -840,12 +844,14 @@ void NumericLiteralParser::ParseNumberStartingWithZero(SourceLocation TokLoc) {
       const char *Exponent = s;
       s++;
       saw_exponent = true;
-      if (*s == '+' || *s == '-')  s++; // sign
+      if (s != ThisTokEnd && (*s == '+' || *s == '-'))  s++; // sign
       const char *first_non_digit = SkipDigits(s);
       if (!containsDigits(s, first_non_digit)) {
-        PP.Diag(PP.AdvanceToTokenCharacter(TokLoc, Exponent-ThisTokBegin),
-                diag::err_exponent_has_no_digits);
-        hadError = true;
+        if (!hadError) {
+          PP.Diag(PP.AdvanceToTokenCharacter(TokLoc, Exponent-ThisTokBegin),
+                  diag::err_exponent_has_no_digits);
+          hadError = true;
+        }
         return;
       }
       checkSeparator(TokLoc, s, CSK_BeforeDigits);

diff --git a/test/Lexer/cxx1y_digit_separators.cpp b/test/Lexer/cxx1y_digit_separators.cpp
index 55366342eda0de5f723905a429d2dc32daa0a938..67dcd7c510ed16f05c7efdd95372d63dd6226560 100644 (file)
--- a/test/Lexer/cxx1y_digit_separators.cpp
+++ b/test/Lexer/cxx1y_digit_separators.cpp
@@ -51,6 +51,8 @@ namespace floating {
   float u = 0x.'p1f; // expected-error {{hexadecimal floating literal requires a significand}}
   float v = 0e'f; // expected-error {{exponent has no digits}}
   float w = 0x0p'f; // expected-error {{exponent has no digits}}
+  float x = 0'e+1; // expected-error {{digit separator cannot appear at end of digit sequence}}
+  float y = 0x0'p+1; // expected-error {{digit separator cannot appear at end of digit sequence}}
 }
 
 #line 123'456