Allow underscores in integer and numeric constants.

This allows underscores to be used in integer and numeric literals,
and their corresponding type input functions, for visual grouping.
For example:

    1_500_000_000
    3.14159_26535_89793
    0xffff_ffff
    0b_1001_0001

A single underscore is allowed between any 2 digits, or immediately
after the base prefix indicator of non-decimal integers, per SQL:202x
draft.

Peter Eisentraut and Dean Rasheed

Discussion: https://postgr.es/m/84aae844-dc55-a4be-86d9-4f0fa405cc97%40enterprisedb.com

2 files changed, 18 insertions, 52 deletions

diff --git a/src/backend/parser/parse_node.c b/src/backend/parser/parse_node.c
index f1967a33bc0..5020b9f0810 100644
--- a/src/backend/parser/parse_node.c
+++ b/src/backend/parser/parse_node.c
@@ -19,6 +19,7 @@
 #include "catalog/pg_type.h"
 #include "mb/pg_wchar.h"
 #include "nodes/makefuncs.h"
+#include "nodes/miscnodes.h"
 #include "nodes/nodeFuncs.h"
 #include "nodes/subscripting.h"
 #include "parser/parse_coerce.h"
@@ -385,47 +386,11 @@ 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;
+				ErrorSaveContext escontext = {T_ErrorSaveContext};
 				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;
-					}
-					else 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(testvalue, &endptr, base);
-				if (errno == 0 && *endptr == '\0')
+				val64 = pg_strtoint64_safe(aconst->val.fval.fval, (Node *) &escontext);
+				if (!escontext.error_occurred)
 				{
 					/*
 					 * It might actually fit in int32. Probably only INT_MIN
diff --git a/src/backend/parser/scan.l b/src/backend/parser/scan.l
index 1e821d4c9e2..b2216a9eacd 100644
--- a/src/backend/parser/scan.l
+++ b/src/backend/parser/scan.l
@@ -37,10 +37,12 @@
 
 #include "common/string.h"
 #include "gramparse.h"
+#include "nodes/miscnodes.h"
 #include "parser/parser.h"		/* only needed for GUC variables */
 #include "parser/scansup.h"
 #include "port/pg_bitutils.h"
 #include "mb/pg_wchar.h"
+#include "utils/builtins.h"
 }
 
 %{
@@ -395,19 +397,19 @@ 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}+
+decinteger		{decdigit}(_?{decdigit})*
+hexinteger		0[xX](_?{hexdigit})+
+octinteger		0[oO](_?{octdigit})+
+bininteger		0[bB](_?{bindigit})+
 
-hexfail			0[xX]
-octfail			0[oO]
-binfail			0[bB]
+hexfail			0[xX]_?
+octfail			0[oO]_?
+binfail			0[bB]_?
 
 numeric			(({decinteger}\.{decinteger}?)|(\.{decinteger}))
 numericfail		{decdigit}+\.\.
 
-real			({decinteger}|{numeric})[Ee][-+]?{decdigit}+
+real			({decinteger}|{numeric})[Ee][-+]?{decinteger}
 realfail		({decinteger}|{numeric})[Ee][-+]
 
 decinteger_junk	{decinteger}{ident_start}
@@ -1364,12 +1366,11 @@ litbufdup(core_yyscan_t yyscanner)
 static int
 process_integer_literal(const char *token, YYSTYPE *lval, int base)
 {
-	int			val;
-	char	   *endptr;
+	ErrorSaveContext escontext = {T_ErrorSaveContext};
+	int32		val;
 
-	errno = 0;
-	val = strtoint(base == 10 ? token : token + 2, &endptr, base);
-	if (*endptr != '\0' || errno == ERANGE)
+	val = pg_strtoint32_safe(token, (Node *) &escontext);
+	if (escontext.error_occurred)
 	{
 		/* integer too large (or contains decimal pt), treat it as a float */
 		lval->str = pstrdup(token);