Non-decimal integer literals

Add support for hexadecimal, octal, and binary integer literals:

    0x42F
    0o273
    0b100101

per SQL:202x draft.

This adds support in the lexer as well as in the integer type input
functions.

Reviewed-by: John Naylor <[email protected]>
Reviewed-by: Zhihong Yu <[email protected]>
Reviewed-by: David Rowley <[email protected]>
Reviewed-by: Dean Rasheed <[email protected]>
Discussion: https://www.postgresql.org/message-id/flat/[email protected]

Author: petere

doc/src/sgml/syntax.sgml

@@ -694,6 +694,40 @@ $function$
 </literallayout>
     </para>
 
+    <para>
+     Additionally, non-decimal integer constants can be used in these forms:
+<synopsis>
+0x<replaceable>hexdigits</replaceable>
+0o<replaceable>octdigits</replaceable>
+0b<replaceable>bindigits</replaceable>
+</synopsis>
+     <replaceable>hexdigits</replaceable> is one or more hexadecimal digits
+     (0-9, A-F), <replaceable>octdigits</replaceable> is one or more octal
+     digits (0-7), <replaceable>bindigits</replaceable> is one or more binary
+     digits (0 or 1).  Hexadecimal digits and the radix prefixes can be in
+     upper or lower case.  Note that only integers can have non-decimal forms,
+     not numbers with fractional parts.
+    </para>
+
+    <para>
+     These are some examples of this:
+<literallayout>0b100101
+0B10011001
+0o273
+0O755
+0x42f
+0XFFFF
+</literallayout>
+    </para>
+
+    <note>
+     <para>
+      Nondecimal integer constants are currently only supported in the range
+      of the <type>bigint</type> type (see <xref
+      linkend="datatype-numeric-table"/>).
+     </para>
+    </note>
+
     <para>
      <indexterm><primary>integer</primary></indexterm>
      <indexterm><primary>bigint</primary></indexterm>

src/backend/catalog/information_schema.sql

@@ -119,7 +119,7 @@ RETURN
          WHEN 1700 /*numeric*/ THEN
               CASE WHEN $2 = -1
                    THEN null
-                   ELSE (($2 - 4) >> 16) & 65535
+                   ELSE (($2 - 4) >> 16) & 0xFFFF
                    END
          WHEN 700 /*float4*/ THEN 24 /*FLT_MANT_DIG*/
          WHEN 701 /*float8*/ THEN 53 /*DBL_MANT_DIG*/
@@ -147,7 +147,7 @@ RETURN
        WHEN $1 IN (1700) THEN
             CASE WHEN $2 = -1
                  THEN null
-                 ELSE ($2 - 4) & 65535
+                 ELSE ($2 - 4) & 0xFFFF
                  END
        ELSE null
   END;
@@ -163,7 +163,7 @@ RETURN
        WHEN $1 IN (1083, 1114, 1184, 1266) /* time, timestamp, same + tz */
            THEN CASE WHEN $2 < 0 THEN 6 ELSE $2 END
        WHEN $1 IN (1186) /* interval */
-           THEN CASE WHEN $2 < 0 OR $2 & 65535 = 65535 THEN 6 ELSE $2 & 65535 END
+           THEN CASE WHEN $2 < 0 OR $2 & 0xFFFF = 0xFFFF THEN 6 ELSE $2 & 0xFFFF END
        ELSE null
   END;
 

src/backend/catalog/sql_features.txt

@@ -527,6 +527,7 @@ T652	SQL-dynamic statements in SQL routines			NO
 T653	SQL-schema statements in external routines			YES	
 T654	SQL-dynamic statements in external routines			NO	
 T655	Cyclically dependent routines			YES	
+T661	Non-decimal integer literals			YES	SQL:202x draft
 T811	Basic SQL/JSON constructor functions			NO	
 T812	SQL/JSON: JSON_OBJECTAGG			NO	
 T813	SQL/JSON: JSON_ARRAYAGG with ORDER BY			NO	

src/backend/parser/parse_node.c

@@ -385,11 +385,46 @@ make_const(ParseState *pstate, A_Const *aconst)
 			{
 				/* could be an oversize integer as well as a float ... */
 
+				int			base = 10;
+				char	   *startptr;
+				int			sign;
+				char	   *testvalue;
 				int64		val64;
 				char	   *endptr;
 
+				startptr = aconst->val.fval.fval;
+				if (startptr[0] == '-')
+				{
+					sign = -1;
+					startptr++;
+				}
+				else
+					sign = +1;
+				if (startptr[0] == '0')
+				{
+					if (startptr[1] == 'b' || startptr[1] == 'B')
+					{
+						base = 2;
+						startptr += 2;
+					}
+					else if (startptr[1] == 'o' || startptr[1] == 'O')
+					{
+						base = 8;
+						startptr += 2;
+					}
+					if (startptr[1] == 'x' || startptr[1] == 'X')
+					{
+						base = 16;
+						startptr += 2;
+					}
+				}
+
+				if (sign == +1)
+					testvalue = startptr;
+				else
+					testvalue = psprintf("-%s", startptr);
 				errno = 0;
-				val64 = strtoi64(aconst->val.fval.fval, &endptr, 10);
+				val64 = strtoi64(testvalue, &endptr, base);
 				if (errno == 0 && *endptr == '\0')
 				{
 					/*

src/backend/parser/scan.l

@@ -124,7 +124,7 @@ static void addlit(char *ytext, int yleng, core_yyscan_t yyscanner);
 static void addlitchar(unsigned char ychar, core_yyscan_t yyscanner);
 static char *litbufdup(core_yyscan_t yyscanner);
 static unsigned char unescape_single_char(unsigned char c, core_yyscan_t yyscanner);
-static int	process_integer_literal(const char *token, YYSTYPE *lval);
+static int	process_integer_literal(const char *token, YYSTYPE *lval, int base);
 static void addunicode(pg_wchar c, yyscan_t yyscanner);
 
 #define yyerror(msg)  scanner_yyerror(msg, yyscanner)
@@ -385,25 +385,40 @@ operator		{op_chars}+
  * Unary minus is not part of a number here.  Instead we pass it separately to
  * the parser, and there it gets coerced via doNegate().
  *
- * {decimalfail} is used because we would like "1..10" to lex as 1, dot_dot, 10.
+ * {numericfail} is used because we would like "1..10" to lex as 1, dot_dot, 10.
  *
  * {realfail} is added to prevent the need for scanner
  * backup when the {real} rule fails to match completely.
  */
-digit			[0-9]
-
-integer			{digit}+
-decimal			(({digit}*\.{digit}+)|({digit}+\.{digit}*))
-decimalfail		{digit}+\.\.
-real			({integer}|{decimal})[Ee][-+]?{digit}+
-realfail		({integer}|{decimal})[Ee][-+]
-
-integer_junk	{integer}{ident_start}
-decimal_junk	{decimal}{ident_start}
+decdigit		[0-9]
+hexdigit		[0-9A-Fa-f]
+octdigit		[0-7]
+bindigit		[0-1]
+
+decinteger		{decdigit}+
+hexinteger		0[xX]{hexdigit}+
+octinteger		0[oO]{octdigit}+
+bininteger		0[bB]{bindigit}+
+
+hexfail			0[xX]
+octfail			0[oO]
+binfail			0[bB]
+
+numeric			(({decinteger}\.{decinteger}?)|(\.{decinteger}))
+numericfail		{decdigit}+\.\.
+
+real			({decinteger}|{numeric})[Ee][-+]?{decdigit}+
+realfail		({decinteger}|{numeric})[Ee][-+]
+
+decinteger_junk	{decinteger}{ident_start}
+hexinteger_junk	{hexinteger}{ident_start}
+octinteger_junk	{octinteger}{ident_start}
+bininteger_junk	{bininteger}{ident_start}
+numeric_junk	{numeric}{ident_start}
 real_junk		{real}{ident_start}
 
-param			\${integer}
-param_junk		\${integer}{ident_start}
+param			\${decinteger}
+param_junk		\${decinteger}{ident_start}
 
 other			.
 
@@ -983,20 +998,44 @@ other			.
 					yyerror("trailing junk after parameter");
 				}
 
-{integer}		{
+{decinteger}	{
+					SET_YYLLOC();
+					return process_integer_literal(yytext, yylval, 10);
+				}
+{hexinteger}	{
+					SET_YYLLOC();
+					return process_integer_literal(yytext, yylval, 16);
+				}
+{octinteger}	{
+					SET_YYLLOC();
+					return process_integer_literal(yytext, yylval, 8);
+				}
+{bininteger}	{
+					SET_YYLLOC();
+					return process_integer_literal(yytext, yylval, 2);
+				}
+{hexfail}		{
+					SET_YYLLOC();
+					yyerror("invalid hexadecimal integer");
+				}
+{octfail}		{
 					SET_YYLLOC();
-					return process_integer_literal(yytext, yylval);
+					yyerror("invalid octal integer");
 				}
-{decimal}		{
+{binfail}		{
+					SET_YYLLOC();
+					yyerror("invalid binary integer");
+				}
+{numeric}		{
 					SET_YYLLOC();
 					yylval->str = pstrdup(yytext);
 					return FCONST;
 				}
-{decimalfail}	{
+{numericfail}	{
 					/* throw back the .., and treat as integer */
 					yyless(yyleng - 2);
 					SET_YYLLOC();
-					return process_integer_literal(yytext, yylval);
+					return process_integer_literal(yytext, yylval, 10);
 				}
 {real}			{
 					SET_YYLLOC();
@@ -1007,11 +1046,23 @@ other			.
 					SET_YYLLOC();
 					yyerror("trailing junk after numeric literal");
 				}
-{integer_junk}	{
+{decinteger_junk}	{
+					SET_YYLLOC();
+					yyerror("trailing junk after numeric literal");
+				}
+{hexinteger_junk}	{
+					SET_YYLLOC();
+					yyerror("trailing junk after numeric literal");
+				}
+{octinteger_junk}	{
+					SET_YYLLOC();
+					yyerror("trailing junk after numeric literal");
+				}
+{bininteger_junk}	{
 					SET_YYLLOC();
 					yyerror("trailing junk after numeric literal");
 				}
-{decimal_junk}	{
+{numeric_junk}	{
 					SET_YYLLOC();
 					yyerror("trailing junk after numeric literal");
 				}
@@ -1307,17 +1358,17 @@ litbufdup(core_yyscan_t yyscanner)
 }
 
 /*
- * Process {integer}.  Note this will also do the right thing with {decimal},
- * ie digits and a decimal point.
+ * Process {decinteger}, {hexinteger}, etc.  Note this will also do the right
+ * thing with {numeric}, ie digits and a decimal point.
  */
 static int
-process_integer_literal(const char *token, YYSTYPE *lval)
+process_integer_literal(const char *token, YYSTYPE *lval, int base)
 {
 	int			val;
 	char	   *endptr;
 
 	errno = 0;
-	val = strtoint(token, &endptr, 10);
+	val = strtoint(base == 10 ? token : token + 2, &endptr, base);
 	if (*endptr != '\0' || errno == ERANGE)
 	{
 		/* integer too large (or contains decimal pt), treat it as a float */