From 6fcda9aba83449082124825b6d375c0a61e21c42 Mon Sep 17 00:00:00 2001
From: Peter Eisentraut
Date: Wed, 14 Dec 2022 05:40:38 +0100
Subject: 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 <john.naylor@enterprisedb.com>
Reviewed-by: Zhihong Yu <zyu@yugabyte.com>
Reviewed-by: David Rowley <dgrowleyml@gmail.com>
Reviewed-by: Dean Rasheed <dean.a.rasheed@gmail.com>
Discussion: https://www.postgresql.org/message-id/flat/b239564c-cad0-b23e-c57e-166d883cb97d@enterprisedb.com
---
 src/fe_utils/psqlscan.l | 78 +++++++++++++++++++++++++++++++++++++------------
 1 file changed, 60 insertions(+), 18 deletions(-)

(limited to 'src/fe_utils')

diff --git a/src/fe_utils/psqlscan.l b/src/fe_utils/psqlscan.l
index ae531ec2407..cb1fc521384 100644
--- a/src/fe_utils/psqlscan.l
+++ b/src/fe_utils/psqlscan.l
@@ -323,25 +323,40 @@ 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}
 
 /* psql-specific: characters allowed in variable names */
 variable_char	[A-Za-z\200-\377_0-9]
@@ -847,13 +862,31 @@ other			.
 					ECHO;
 				}
 
-{integer}		{
+{decinteger}	{
+					ECHO;
+				}
+{hexinteger}	{
+					ECHO;
+				}
+{octinteger}	{
+					ECHO;
+				}
+{bininteger}	{
+					ECHO;
+				}
+{hexfail}		{
 					ECHO;
 				}
-{decimal}		{
+{octfail}		{
 					ECHO;
 				}
-{decimalfail}	{
+{binfail}		{
+					ECHO;
+				}
+{numeric}		{
+					ECHO;
+				}
+{numericfail}	{
 					/* throw back the .., and treat as integer */
 					yyless(yyleng - 2);
 					ECHO;
@@ -864,10 +897,19 @@ other			.
 {realfail}		{
 					ECHO;
 				}
-{integer_junk}	{
+{decinteger_junk}	{
+					ECHO;
+				}
+{hexinteger_junk}	{
+					ECHO;
+				}
+{octinteger_junk}	{
+					ECHO;
+				}
+{bininteger_junk}	{
 					ECHO;
 				}
-{decimal_junk}	{
+{numeric_junk}	{
 					ECHO;
 				}
 {real_junk}		{
-- 
cgit v1.2.3