Patchwork C++14 digit separators..

login
register
mail settings
Submitter Ed Smith-Rowland
Date Oct. 30, 2013, 10:53 p.m.
Message ID <52718DD3.3020700@verizon.net>
Download mbox | patch
Permalink /patch/287361/
State New
Headers show

Comments

Ed Smith-Rowland - Oct. 30, 2013, 10:53 p.m.
On 10/28/2013 09:44 AM, Jason Merrill wrote:
> On 10/28/2013 09:10 AM, Joseph S. Myers wrote:
>> On Sun, 27 Oct 2013, Ed Smith-Rowland wrote:
>>
>>> Here is an implementation for C++14 digit separators (single quote).
>>
>> I tend to think that such features should come with a test that the
>> feature is not enabled for language / standard versions for which it
>> shouldn't be.  That is, something like
>>
>> #define m(x) 0
>> int i = m(1'2)+(3'4);
>
> Good idea.  Other than that, the patch looks good to me.
>
> Jason
>
>
OK,

I had to add some more checks in libcpp.
After reading the standard a few times i figured out the magic words are 
"digit separators" - must have digit on both sides.
I also put in the suggested check above.

bootstrapped and fully tested on x86_64-linux.

Still OK?

Ed

libcpp:

2013-10-30  Edward Smith-Rowland  <3dw4rd@verizon.net>

        implement C++14 digit separators.
	* include/cpplib.h (cpp_options): Add digit_separators flag.
	* internal.h (DIGIT_SEP(c)): New macro.
	* expr.c (cpp_classify_number): Check improper placement of digit sep;
	(cpp_interpret_integer): Skip over digit separators.
	* init.c (lang_flags): Add digit_separators flag; (lang_defaults): Add
	digit separator flags per language; (cpp_set_lang): Set
	digit_separators
	* lex.c (lex_number): Add digits separator to allowable characters for
	C++14.


gcc/c-family:

2013-10-30  Edward Smith-Rowland  <3dw4rd@verizon.net>

	* c-lex.c (interpret_float): Remove digit separators from scratch string
	before building real literal.


gcc/testsuite:

2013-10-30  Edward Smith-Rowland  <3dw4rd@verizon.net>

	* g++.dg/cpp1y/digit-sep.C: New.
	* g++.dg/cpp1y/digit-sep-neg.C: New.
	* g++.dg/cpp1y/digit-sep-cxx11-neg.C: New.


libstdc++-v3:

2013-10-30  Edward Smith-Rowland  <3dw4rd@verizon.net>

        implement C++14 digit separators.
	* include/include/bits/parse_numbers.h: Change struct _Digit<_Base, '`'>
	to struct _Digit<_Base, '\''>.
Jason Merrill - Oct. 31, 2013, 1:35 p.m.
OK.

Jason

Patch

Index: libcpp/include/cpplib.h
===================================================================
--- libcpp/include/cpplib.h	(revision 204189)
+++ libcpp/include/cpplib.h	(working copy)
@@ -437,6 +437,9 @@ 
   /* Nonzero for C++ 2014 Standard binary constants.  */
   unsigned char binary_constants;
 
+  /* Nonzero for C++ 2014 Standard digit separators.  */
+  unsigned char digit_separators;
+
   /* Holds the name of the target (execution) character set.  */
   const char *narrow_charset;
 
Index: libcpp/internal.h
===================================================================
--- libcpp/internal.h	(revision 204189)
+++ libcpp/internal.h	(working copy)
@@ -59,6 +59,8 @@ 
     || (((prevc) == 'p' || (prevc) == 'P') \
         && CPP_OPTION (pfile, extended_numbers))))
 
+#define DIGIT_SEP(c) ((c) == '\'' && CPP_OPTION (pfile, digit_separators))
+
 #define CPP_OPTION(PFILE, OPTION) ((PFILE)->opts.OPTION)
 #define CPP_BUFFER(PFILE) ((PFILE)->buffer)
 #define CPP_BUF_COLUMN(BUF, CUR) ((CUR) - (BUF)->line_base)
Index: libcpp/expr.c
===================================================================
--- libcpp/expr.c	(revision 204189)
+++ libcpp/expr.c	(working copy)
@@ -394,6 +394,7 @@ 
   unsigned int max_digit, result, radix;
   enum {NOT_FLOAT = 0, AFTER_POINT, AFTER_EXPON} float_flag;
   bool seen_digit;
+  bool seen_digit_sep;
 
   if (ud_suffix)
     *ud_suffix = NULL;
@@ -408,6 +409,7 @@ 
   max_digit = 0;
   radix = 10;
   seen_digit = false;
+  seen_digit_sep = false;
 
   /* First, interpret the radix.  */
   if (*str == '0')
@@ -416,16 +418,27 @@ 
       str++;
 
       /* Require at least one hex digit to classify it as hex.  */
-      if ((*str == 'x' || *str == 'X')
-	  && (str[1] == '.' || ISXDIGIT (str[1])))
+      if (*str == 'x' || *str == 'X')
 	{
-	  radix = 16;
-	  str++;
+	  if (str[1] == '.' || ISXDIGIT (str[1]))
+	    {
+	      radix = 16;
+	      str++;
+	    }
+	  else if (DIGIT_SEP (str[1]))
+	    SYNTAX_ERROR_AT (virtual_location,
+			     "digit separator after base indicator");
 	}
-      else if ((*str == 'b' || *str == 'B') && (str[1] == '0' || str[1] == '1'))
+      else if (*str == 'b' || *str == 'B')
 	{
-	  radix = 2;
-	  str++;
+	  if (str[1] == '0' || str[1] == '1')
+	    {
+	      radix = 2;
+	      str++;
+	    }
+	  else if (DIGIT_SEP (str[1]))
+	    SYNTAX_ERROR_AT (virtual_location,
+			     "digit separator after base indicator");
 	}
     }
 
@@ -436,13 +449,24 @@ 
 
       if (ISDIGIT (c) || (ISXDIGIT (c) && radix == 16))
 	{
+	  seen_digit_sep = false;
 	  seen_digit = true;
 	  c = hex_value (c);
 	  if (c > max_digit)
 	    max_digit = c;
 	}
+      else if (DIGIT_SEP (c))
+	{
+	  if (seen_digit_sep)
+	    SYNTAX_ERROR_AT (virtual_location, "adjacent digit separators");
+	  seen_digit_sep = true;
+	}
       else if (c == '.')
 	{
+	  if (seen_digit_sep || DIGIT_SEP (*str))
+	    SYNTAX_ERROR_AT (virtual_location,
+			     "digit separator adjacent to decimal point");
+	  seen_digit_sep = false;
 	  if (float_flag == NOT_FLOAT)
 	    float_flag = AFTER_POINT;
 	  else
@@ -452,6 +476,9 @@ 
       else if ((radix <= 10 && (c == 'e' || c == 'E'))
 	       || (radix == 16 && (c == 'p' || c == 'P')))
 	{
+	  if (seen_digit_sep || DIGIT_SEP (*str))
+	    SYNTAX_ERROR_AT (virtual_location,
+			     "digit separator adjacent to exponent");
 	  float_flag = AFTER_EXPON;
 	  break;
 	}
@@ -463,6 +490,10 @@ 
 	}
     }
 
+  if (seen_digit_sep && float_flag != AFTER_EXPON)
+    SYNTAX_ERROR_AT (virtual_location,
+		     "digit separator outside digit sequence");
+
   /* The suffix may be for decimal fixed-point constants without exponent.  */
   if (radix != 16 && float_flag == NOT_FLOAT)
     {
@@ -520,16 +551,28 @@ 
 
 	  /* Exponent is decimal, even if string is a hex float.  */
 	  if (!ISDIGIT (*str))
-	    SYNTAX_ERROR_AT (virtual_location, "exponent has no digits");
-
+	    {
+	      if (DIGIT_SEP (*str))
+		SYNTAX_ERROR_AT (virtual_location,
+				 "digit separator adjacent to exponent");
+	      else
+		SYNTAX_ERROR_AT (virtual_location, "exponent has no digits");
+	    }
 	  do
-	    str++;
-	  while (ISDIGIT (*str));
+	    {
+	      seen_digit_sep = DIGIT_SEP (*str);
+	      str++;
+	    }
+	  while (ISDIGIT (*str) || DIGIT_SEP (*str));
 	}
       else if (radix == 16)
 	SYNTAX_ERROR_AT (virtual_location,
 			 "hexadecimal floating constants require an exponent");
 
+      if (seen_digit_sep)
+	SYNTAX_ERROR_AT (virtual_location,
+			 "digit separator outside digit sequence");
+
       result = interpret_float_suffix (pfile, str, limit - str);
       if (result == 0)
 	{
@@ -723,6 +766,8 @@ 
 
 	  if (ISDIGIT (c) || (base == 16 && ISXDIGIT (c)))
 	    c = hex_value (c);
+	  else if (DIGIT_SEP (c))
+	    continue;
 	  else
 	    break;
 
Index: libcpp/init.c
===================================================================
--- libcpp/init.c	(revision 204189)
+++ libcpp/init.c	(working copy)
@@ -84,24 +84,25 @@ 
   char rliterals;
   char user_literals;
   char binary_constants;
+  char digit_separators;
 };
 
 static const struct lang_flags lang_defaults[] =
-{ /*              c99 c++ xnum xid std  //   digr ulit rlit udlit bin_cst */
-  /* GNUC89   */  { 0,  0,  1,   0,  0,   1,   1,   0,   0,   0,    0 },
-  /* GNUC99   */  { 1,  0,  1,   0,  0,   1,   1,   1,   1,   0,    0 },
-  /* GNUC11   */  { 1,  0,  1,   0,  0,   1,   1,   1,   1,   0,    0 },
-  /* STDC89   */  { 0,  0,  0,   0,  1,   0,   0,   0,   0,   0,    0 },
-  /* STDC94   */  { 0,  0,  0,   0,  1,   0,   1,   0,   0,   0,    0 },
-  /* STDC99   */  { 1,  0,  1,   0,  1,   1,   1,   0,   0,   0,    0 },
-  /* STDC11   */  { 1,  0,  1,   0,  1,   1,   1,   1,   0,   0,    0 },
-  /* GNUCXX   */  { 0,  1,  1,   0,  0,   1,   1,   0,   0,   0,    0 },
-  /* CXX98    */  { 0,  1,  1,   0,  1,   1,   1,   0,   0,   0,    0 },
-  /* GNUCXX11 */  { 1,  1,  1,   0,  0,   1,   1,   1,   1,   1,    0 },
-  /* CXX11    */  { 1,  1,  1,   0,  1,   1,   1,   1,   1,   1,    0 },
-  /* GNUCXX1Y */  { 1,  1,  1,   0,  0,   1,   1,   1,   1,   1,    1 },
-  /* CXX1Y    */  { 1,  1,  1,   0,  1,   1,   1,   1,   1,   1,    1 },
-  /* ASM      */  { 0,  0,  1,   0,  0,   1,   0,   0,   0,   0,    0 }
+{ /*              c99 c++ xnum xid std  //   digr ulit rlit udlit bin_cst dig_sep */
+  /* GNUC89   */  { 0,  0,  1,   0,  0,   1,   1,   0,   0,   0,    0,      0 },
+  /* GNUC99   */  { 1,  0,  1,   0,  0,   1,   1,   1,   1,   0,    0,      0 },
+  /* GNUC11   */  { 1,  0,  1,   0,  0,   1,   1,   1,   1,   0,    0,      0 },
+  /* STDC89   */  { 0,  0,  0,   0,  1,   0,   0,   0,   0,   0,    0,      0 },
+  /* STDC94   */  { 0,  0,  0,   0,  1,   0,   1,   0,   0,   0,    0,      0 },
+  /* STDC99   */  { 1,  0,  1,   0,  1,   1,   1,   0,   0,   0,    0,      0 },
+  /* STDC11   */  { 1,  0,  1,   0,  1,   1,   1,   1,   0,   0,    0,      0 },
+  /* GNUCXX   */  { 0,  1,  1,   0,  0,   1,   1,   0,   0,   0,    0,      0 },
+  /* CXX98    */  { 0,  1,  1,   0,  1,   1,   1,   0,   0,   0,    0,      0 },
+  /* GNUCXX11 */  { 1,  1,  1,   0,  0,   1,   1,   1,   1,   1,    0,      0 },
+  /* CXX11    */  { 1,  1,  1,   0,  1,   1,   1,   1,   1,   1,    0,      0 },
+  /* GNUCXX1Y */  { 1,  1,  1,   0,  0,   1,   1,   1,   1,   1,    1,      1 },
+  /* CXX1Y    */  { 1,  1,  1,   0,  1,   1,   1,   1,   1,   1,    1,      1 },
+  /* ASM      */  { 0,  0,  1,   0,  0,   1,   0,   0,   0,   0,    0,      0 }
   /* xid should be 1 for GNUC99, STDC99, GNUCXX, CXX98, GNUCXX11, CXX11,
      GNUCXX1Y, and CXX1Y when no longer experimental (when all uses of
      identifiers in the compiler have been audited for correct handling
@@ -128,6 +129,7 @@ 
   CPP_OPTION (pfile, rliterals)			 = l->rliterals;
   CPP_OPTION (pfile, user_literals)		 = l->user_literals;
   CPP_OPTION (pfile, binary_constants)		 = l->binary_constants;
+  CPP_OPTION (pfile, digit_separators)		 = l->digit_separators;
 }
 
 /* Initialize library global state.  */
Index: libcpp/lex.c
===================================================================
--- libcpp/lex.c	(revision 204189)
+++ libcpp/lex.c	(working copy)
@@ -1274,7 +1274,8 @@ 
       cur = pfile->buffer->cur;
 
       /* N.B. ISIDNUM does not include $.  */
-      while (ISIDNUM (*cur) || *cur == '.' || VALID_SIGN (*cur, cur[-1]))
+      while (ISIDNUM (*cur) || *cur == '.' || DIGIT_SEP (*cur)
+	     || VALID_SIGN (*cur, cur[-1]))
 	{
 	  cur++;
 	  NORMALIZE_STATE_UPDATE_IDNUM (nst);
Index: gcc/c-family/c-lex.c
===================================================================
--- gcc/c-family/c-lex.c	(revision 204189)
+++ gcc/c-family/c-lex.c	(working copy)
@@ -774,8 +774,19 @@ 
     }
 
   copy = (char *) alloca (copylen + 1);
-  memcpy (copy, token->val.str.text, copylen);
-  copy[copylen] = '\0';
+  if (cxx_dialect > cxx11)
+    {
+      size_t maxlen = 0;
+      for (size_t i = 0; i < copylen; ++i)
+        if (token->val.str.text[i] != '\'')
+          copy[maxlen++] = token->val.str.text[i];
+      copy[maxlen] = '\0';
+    }
+  else
+    {
+      memcpy (copy, token->val.str.text, copylen);
+      copy[copylen] = '\0';
+    }
 
   real_from_string3 (&real, copy, TYPE_MODE (const_type));
   if (const_type != type)
Index: libstdc++-v3/include/bits/parse_numbers.h
===================================================================
--- libstdc++-v3/include/bits/parse_numbers.h	(revision 204189)
+++ libstdc++-v3/include/bits/parse_numbers.h	(working copy)
@@ -32,7 +32,7 @@ 
 
 #pragma GCC system_header
 
-// From n3642.pdf except I added binary literals and digit separator '`'.
+// From n3642.pdf except I added binary literals and digit separator '\''.
 
 #if __cplusplus > 201103L
 
@@ -221,7 +221,7 @@ 
 
   //  Digit separator
   template<unsigned _Base>
-    struct _Digit<_Base, '`'>
+    struct _Digit<_Base, '\''>
     {
       static constexpr bool valid{false};
       static constexpr unsigned value{0};
Index: gcc/testsuite/g++.dg/cpp1y/digit-sep.C
===================================================================
--- gcc/testsuite/g++.dg/cpp1y/digit-sep.C	(revision 0)
+++ gcc/testsuite/g++.dg/cpp1y/digit-sep.C	(working copy)
@@ -0,0 +1,22 @@ 
+// { dg-options -std=c++1y }
+
+#define assert(E) if(!(E))__builtin_abort();
+
+#define m(x) 0
+
+int
+main()
+{
+  assert(1048576 == 1'048'576);
+  assert(1048576 == 0X100000);
+  assert(1048576 == 0x10'0000);
+  assert(1048576 == 0'004'000'000);
+  assert(1048576 == 0B100000000000000000000);
+  assert(1048576 == 0b0001'0000'0000'0000'0000'0000);
+
+  assert(1.602'176'565e-19 == 1.602176565e-19);
+  assert(1.602'176'565e-1'9 == 1.602176565e-19);
+
+  int i = m(1'2)+(3'4);
+  assert(i == 34);
+}
Index: gcc/testsuite/g++.dg/cpp1y/digit-sep-neg.C
===================================================================
--- gcc/testsuite/g++.dg/cpp1y/digit-sep-neg.C	(revision 0)
+++ gcc/testsuite/g++.dg/cpp1y/digit-sep-neg.C	(working copy)
@@ -0,0 +1,26 @@ 
+// { dg-options -std=c++1y }
+
+int
+main()
+{
+  int i = 0;
+  i = 1048''576; // { dg-error "adjacent digit separators" }
+  i = 0X'100000; // { dg-error "digit separator after base indicator" }
+  i = 0x'100000; // { dg-error "digit separator after base indicator" }
+  i = 0004''000'000); // { dg-error "adjacent digit separators" }
+  i = 0B1'0'0'0'0'0'0'0'0'0'0'0'0'0'0'0'0'0'0'0'0; // OK
+  i = 0b'0001'0000'0000'0000'0000'0000; // { dg-error "digit separator after base indicator" }
+  i = 0b0001'0000'0000'0000'0000'0000'; // { dg-error "digit separator outside digit sequence" }
+  unsigned u = 0b0001'0000'0000'0000'0000'0000'U; // { dg-error "digit separator outside digit sequence" }
+
+  double d = 0.0;
+  d = 1'.602'176'565e-19; // { dg-error "digit separator adjacent to decimal point" }
+  d = 1.'602'176'565e-19; // { dg-error "digit separator adjacent to decimal point" }
+  d = 1.602''176'565e-19; // { dg-error "adjacent digit separators" }
+  d = 1.602'176'565'e-19; // { dg-error "digit separator adjacent to exponent" }
+  d = 1.602'176'565e'-19; // { dg-error "digit separator adjacent to exponent" }
+  d = 1.602'176'565e-'19; // { dg-error "digit separator adjacent to exponent" }
+  d = 1.602'176'565e-1'9; // OK
+  d = 1.602'176'565e-19'; // { dg-error "digit separator outside digit sequence" }
+  float f = 1.602'176'565e-19'F; // { dg-error "digit separator outside digit sequence" }
+}
Index: gcc/testsuite/g++.dg/cpp1y/digit-sep-cxx11-neg.C
===================================================================
--- gcc/testsuite/g++.dg/cpp1y/digit-sep-cxx11-neg.C	(revision 0)
+++ gcc/testsuite/g++.dg/cpp1y/digit-sep-cxx11-neg.C	(working copy)
@@ -0,0 +1,12 @@ 
+// { dg-options -std=c++11 }
+
+#define assert(E) if(!(E))__builtin_abort();
+
+#define m(x) 0
+
+int
+main()
+{
+  int i = m(1'2)+(3'4);
+  assert(i == 0);
+}