From 278f30528fa455c16be86b4c8c6b8fe7d9ad26dc Mon Sep 17 00:00:00 2001
From: Peter Eisentraut <peter@eisentraut.org>
Date: Thu, 25 Nov 2021 08:41:48 +0100
Subject: [PATCH v5 5/6] Reject trailing junk after numeric literals

After this, the PostgreSQL lexers no longer accept numeric literals
with trailing non-digits, such as 123abc, which would be scanned as
two tokens: 123 and abc.  This is undocumented and surprising, and it
might also interfere with some extended numeric literal syntax being
contemplated for the future.
---
 src/backend/parser/scan.l                | 27 ++++++----
 src/fe_utils/psqlscan.l                  | 21 +++++---
 src/interfaces/ecpg/preproc/pgc.l        |  4 ++
 src/test/regress/expected/numerology.out | 68 +++++++++---------------
 4 files changed, 61 insertions(+), 59 deletions(-)

diff --git a/src/backend/parser/scan.l b/src/backend/parser/scan.l
index 4e02815803..42646171e5 100644
--- a/src/backend/parser/scan.l
+++ b/src/backend/parser/scan.l
@@ -399,6 +399,10 @@ real			({integer}|{decimal})[Ee][-+]?{digit}+
 realfail1		({integer}|{decimal})[Ee]
 realfail2		({integer}|{decimal})[Ee][-+]
 
+integer_junk	{integer}{ident_start}
+decimal_junk	{decimal}{ident_start}
+real_junk		{real}{ident_start}
+
 param			\${integer}
 
 other			.
@@ -996,19 +1000,24 @@ other			.
 					return FCONST;
 				}
 {realfail1}		{
-					/*
-					 * throw back the [Ee], and figure out whether what
-					 * remains is an {integer} or {decimal}.
-					 */
-					yyless(yyleng - 1);
 					SET_YYLLOC();
-					return process_integer_literal(yytext, yylval);
+					yyerror("trailing junk after numeric literal");
 				}
 {realfail2}		{
-					/* throw back the [Ee][+-], and proceed as above */
-					yyless(yyleng - 2);
 					SET_YYLLOC();
-					return process_integer_literal(yytext, yylval);
+					yyerror("trailing junk after numeric literal");
+				}
+{integer_junk}	{
+					SET_YYLLOC();
+					yyerror("trailing junk after numeric literal");
+				}
+{decimal_junk}	{
+					SET_YYLLOC();
+					yyerror("trailing junk after numeric literal");
+				}
+{real_junk}		{
+					SET_YYLLOC();
+					yyerror("trailing junk after numeric literal");
 				}
 
 
diff --git a/src/fe_utils/psqlscan.l b/src/fe_utils/psqlscan.l
index 9aac166aa0..4cd5e69d00 100644
--- a/src/fe_utils/psqlscan.l
+++ b/src/fe_utils/psqlscan.l
@@ -337,6 +337,10 @@ real			({integer}|{decimal})[Ee][-+]?{digit}+
 realfail1		({integer}|{decimal})[Ee]
 realfail2		({integer}|{decimal})[Ee][-+]
 
+integer_junk	{integer}{ident_start}
+decimal_junk	{decimal}{ident_start}
+real_junk		{real}{ident_start}
+
 param			\${integer}
 
 /* psql-specific: characters allowed in variable names */
@@ -856,17 +860,18 @@ other			.
 					ECHO;
 				}
 {realfail1}		{
-					/*
-					 * throw back the [Ee], and figure out whether what
-					 * remains is an {integer} or {decimal}.
-					 * (in psql, we don't actually care...)
-					 */
-					yyless(yyleng - 1);
 					ECHO;
 				}
 {realfail2}		{
-					/* throw back the [Ee][+-], and proceed as above */
-					yyless(yyleng - 2);
+					ECHO;
+				}
+{integer_junk}	{
+					ECHO;
+				}
+{decimal_junk}	{
+					ECHO;
+				}
+{real_junk}		{
 					ECHO;
 				}
 
diff --git a/src/interfaces/ecpg/preproc/pgc.l b/src/interfaces/ecpg/preproc/pgc.l
index 7c3bf52bfa..e641095496 100644
--- a/src/interfaces/ecpg/preproc/pgc.l
+++ b/src/interfaces/ecpg/preproc/pgc.l
@@ -365,6 +365,10 @@ real			({integer}|{decimal})[Ee][-+]?{digit}+
 realfail1		({integer}|{decimal})[Ee]
 realfail2		({integer}|{decimal})[Ee][-+]
 
+integer_junk	{integer}{ident_start}
+decimal_junk	{decimal}{ident_start}
+real_junk		{real}{ident_start}
+
 param			\${integer}
 
 /* special characters for other dbms */
diff --git a/src/test/regress/expected/numerology.out b/src/test/regress/expected/numerology.out
index 32c6d80c03..2f176ccb52 100644
--- a/src/test/regress/expected/numerology.out
+++ b/src/test/regress/expected/numerology.out
@@ -6,57 +6,41 @@
 -- Trailing junk in numeric literals
 --
 SELECT 123abc;
- abc 
------
- 123
-(1 row)
-
+ERROR:  trailing junk after numeric literal at or near "123a"
+LINE 1: SELECT 123abc;
+               ^
 SELECT 0x0o;
- x0o 
------
-   0
-(1 row)
-
+ERROR:  trailing junk after numeric literal at or near "0x"
+LINE 1: SELECT 0x0o;
+               ^
 SELECT 1_2_3;
- _2_3 
-------
-    1
-(1 row)
-
+ERROR:  trailing junk after numeric literal at or near "1_"
+LINE 1: SELECT 1_2_3;
+               ^
 SELECT 0.a;
- a 
----
- 0
-(1 row)
-
+ERROR:  trailing junk after numeric literal at or near "0.a"
+LINE 1: SELECT 0.a;
+               ^
 SELECT 0.0a;
-  a  
------
- 0.0
-(1 row)
-
+ERROR:  trailing junk after numeric literal at or near "0.0a"
+LINE 1: SELECT 0.0a;
+               ^
 SELECT .0a;
-  a  
------
- 0.0
-(1 row)
-
+ERROR:  trailing junk after numeric literal at or near ".0a"
+LINE 1: SELECT .0a;
+               ^
 SELECT 0.0e1a;
- a 
----
- 0
-(1 row)
-
+ERROR:  trailing junk after numeric literal at or near "0.0e1a"
+LINE 1: SELECT 0.0e1a;
+               ^
 SELECT 0.0e;
-  e  
------
- 0.0
-(1 row)
-
+ERROR:  trailing junk after numeric literal at or near "0.0e"
+LINE 1: SELECT 0.0e;
+               ^
 SELECT 0.0e+a;
-ERROR:  syntax error at or near "+"
+ERROR:  trailing junk after numeric literal at or near "0.0e+"
 LINE 1: SELECT 0.0e+a;
-                   ^
+               ^
 --
 -- Test implicit type conversions
 -- This fails for Postgres v6.1 (and earlier?)
-- 
2.33.1