From d125a97ae8abfc7855b23b5c0d2653a8ef3fba82 Mon Sep 17 00:00:00 2001
From: Craig Topper <craig.topper@gmail.com>
Date: Thu, 28 Jan 2016 05:22:54 +0000
Subject: [PATCH] [Lex] Share some common code between decimal and octal
 parsing in NumericLiteralParser.

There were a couple slight variations between the two copies that I don't believe were intentional. For example, only one of the paths checked for digit separations proceeding a '.', but I think the lexer itself splits the token if a digit separator proceeds a period.

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@259022 91177308-0d34-0410-b5e6-96231b3b80d8
---
 include/clang/Lex/LiteralSupport.h |   1 +
 lib/Lex/LiteralSupport.cpp         | 108 +++++++++++++----------------
 2 files changed, 48 insertions(+), 61 deletions(-)

diff --git a/include/clang/Lex/LiteralSupport.h b/include/clang/Lex/LiteralSupport.h
index d568614e2a..dbe9f82374 100644
--- a/include/clang/Lex/LiteralSupport.h
+++ b/include/clang/Lex/LiteralSupport.h
@@ -104,6 +104,7 @@ public:
 private:
 
   void ParseNumberStartingWithZero(SourceLocation TokLoc);
+  void ParseDecimalOrOctalCommon(SourceLocation TokLoc);
 
   static bool isDigitSeparator(char C) { return C == '\''; }
 
diff --git a/lib/Lex/LiteralSupport.cpp b/lib/Lex/LiteralSupport.cpp
index 5b1c49344e..fb9d63b940 100644
--- a/lib/Lex/LiteralSupport.cpp
+++ b/lib/Lex/LiteralSupport.cpp
@@ -536,34 +536,10 @@ NumericLiteralParser::NumericLiteralParser(StringRef TokSpelling,
     s = SkipDigits(s);
     if (s == ThisTokEnd) {
       // Done.
-    } else if (isHexDigit(*s) && !(*s == 'e' || *s == 'E')) {
-      PP.Diag(PP.AdvanceToTokenCharacter(TokLoc, s - ThisTokBegin),
-              diag::err_invalid_digit) << StringRef(s, 1) << 0;
-      hadError = true;
-      return;
-    } else if (*s == '.') {
-      checkSeparator(TokLoc, s, CSK_AfterDigits);
-      s++;
-      saw_period = true;
-      checkSeparator(TokLoc, s, CSK_BeforeDigits);
-      s = SkipDigits(s);
-    }
-    if ((*s == 'e' || *s == 'E')) { // exponent
-      checkSeparator(TokLoc, s, CSK_AfterDigits);
-      const char *Exponent = s;
-      s++;
-      saw_exponent = true;
-      if (*s == '+' || *s == '-')  s++; // sign
-      checkSeparator(TokLoc, s, CSK_BeforeDigits);
-      const char *first_non_digit = SkipDigits(s);
-      if (first_non_digit != s) {
-        s = first_non_digit;
-      } else {
-        PP.Diag(PP.AdvanceToTokenCharacter(TokLoc, Exponent - ThisTokBegin),
-                diag::err_exponent_has_no_digits);
-        hadError = true;
+    } else {
+      ParseDecimalOrOctalCommon(TokLoc);
+      if (hadError)
         return;
-      }
     }
   }
 
@@ -693,6 +669,49 @@ NumericLiteralParser::NumericLiteralParser(StringRef TokSpelling,
   }
 }
 
+/// ParseDecimalOrOctalCommon - This method is called for decimal or octal
+/// numbers. It issues an error for illegal digits, and handles floating point
+/// parsing. If it detects a floating point number, the radix is set to 10.
+void NumericLiteralParser::ParseDecimalOrOctalCommon(SourceLocation TokLoc){
+  assert((radix == 8 || radix == 10) && "Unexpected radix");
+
+  // If we have a hex digit other than 'e' (which denotes a FP exponent) then
+  // the code is using an incorrect base.
+  if (isHexDigit(*s) && *s != 'e' && *s != 'E') {
+    PP.Diag(PP.AdvanceToTokenCharacter(TokLoc, s-ThisTokBegin),
+            diag::err_invalid_digit) << StringRef(s, 1) << (radix == 8 ? 1 : 0);
+    hadError = true;
+    return;
+  }
+
+  if (*s == '.') {
+    checkSeparator(TokLoc, s, CSK_AfterDigits);
+    s++;
+    radix = 10;
+    saw_period = true;
+    checkSeparator(TokLoc, s, CSK_BeforeDigits);
+    s = SkipDigits(s); // Skip suffix.
+  }
+  if (*s == 'e' || *s == 'E') { // exponent
+    checkSeparator(TokLoc, s, CSK_AfterDigits);
+    const char *Exponent = s;
+    s++;
+    radix = 10;
+    saw_exponent = true;
+    if (*s == '+' || *s == '-')  s++; // sign
+    const char *first_non_digit = SkipDigits(s);
+    if (first_non_digit != s) {
+      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;
+      return;
+    }
+  }
+}
+
 /// Determine whether a suffix is a valid ud-suffix. We avoid treating reserved
 /// suffixes as ud-suffixes, because the diagnostic experience is better if we
 /// treat it as an invalid suffix.
@@ -843,40 +862,7 @@ void NumericLiteralParser::ParseNumberStartingWithZero(SourceLocation TokLoc) {
     }
   }
 
-  // If we have a hex digit other than 'e' (which denotes a FP exponent) then
-  // the code is using an incorrect base.
-  if (isHexDigit(*s) && *s != 'e' && *s != 'E') {
-    PP.Diag(PP.AdvanceToTokenCharacter(TokLoc, s-ThisTokBegin),
-            diag::err_invalid_digit) << StringRef(s, 1) << 1;
-    hadError = true;
-    return;
-  }
-
-  if (*s == '.') {
-    s++;
-    radix = 10;
-    saw_period = true;
-    checkSeparator(TokLoc, s, CSK_BeforeDigits);
-    s = SkipDigits(s); // Skip suffix.
-  }
-  if (*s == 'e' || *s == 'E') { // exponent
-    checkSeparator(TokLoc, s, CSK_AfterDigits);
-    const char *Exponent = s;
-    s++;
-    radix = 10;
-    saw_exponent = true;
-    if (*s == '+' || *s == '-')  s++; // sign
-    const char *first_non_digit = SkipDigits(s);
-    if (first_non_digit != s) {
-      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;
-      return;
-    }
-  }
+  ParseDecimalOrOctalCommon(TokLoc);
 }
 
 static bool alwaysFitsInto64Bits(unsigned Radix, unsigned NumDigits) {
-- 
2.50.1