From 40bc4c260508e8a2579bd2106e1f81b6795d147b Mon Sep 17 00:00:00 2001
From: Peter Eisentraut <peter_e@gmx.net>
Date: Tue, 5 May 2009 18:32:17 +0000
Subject: [PATCH] Disable the use of Unicode escapes in string constants (U&'')
 when standard_conforming_strings is not on, for security reasons.

---
 doc/src/sgml/syntax.sgml              | 13 ++++++++-
 src/backend/parser/scan.l             |  7 ++++-
 src/test/regress/expected/strings.out | 39 +++++++++++++++++++++++++++
 src/test/regress/sql/strings.sql      | 19 +++++++++++++
 4 files changed, 76 insertions(+), 2 deletions(-)

diff --git a/doc/src/sgml/syntax.sgml b/doc/src/sgml/syntax.sgml
index 48bf5a4feb8..cf929f0b72e 100644
--- a/doc/src/sgml/syntax.sgml
+++ b/doc/src/sgml/syntax.sgml
@@ -1,4 +1,4 @@
-<!-- $PostgreSQL: pgsql/doc/src/sgml/syntax.sgml,v 1.131 2009/04/27 16:27:36 momjian Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/syntax.sgml,v 1.132 2009/05/05 18:32:17 petere Exp $ -->
 
 <chapter id="sql-syntax">
  <title>SQL Syntax</title>
@@ -499,6 +499,17 @@ U&amp;'d!0061t!+000061' UESCAPE '!'
      specified.
     </para>
 
+    <para>
+     Also, the Unicode escape syntax for string constants only works
+     when the configuration
+     parameter <xref linkend="guc-standard-conforming-strings"> is
+     turned on.  This is because otherwise this syntax could confuse
+     clients that parse the SQL statements to the point that it could
+     lead to SQL injections and similar security issues.  If the
+     parameter is set to off, this syntax will be rejected with an
+     error message.
+    </para>
+
     <para>
      To include the escape character in the string literally, write it
      twice.
diff --git a/src/backend/parser/scan.l b/src/backend/parser/scan.l
index 8551cd27538..eb0fc10c8f3 100644
--- a/src/backend/parser/scan.l
+++ b/src/backend/parser/scan.l
@@ -24,7 +24,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/parser/scan.l,v 1.151 2009/04/19 21:08:54 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/parser/scan.l,v 1.152 2009/05/05 18:32:17 petere Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -469,6 +469,11 @@ other			.
 					startlit();
 				}
 {xusstart}		{
+					if (!standard_conforming_strings)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("unsafe use of string constant with Unicode escapes"),
+								 errdetail("String constants with Unicode escapes cannot be used when standard_conforming_strings is off.")));
 					SET_YYLLOC();
 					BEGIN(xus);
 					startlit();
diff --git a/src/test/regress/expected/strings.out b/src/test/regress/expected/strings.out
index 6b9dc5df9f4..831fb9e2037 100644
--- a/src/test/regress/expected/strings.out
+++ b/src/test/regress/expected/strings.out
@@ -22,6 +22,7 @@ ERROR:  syntax error at or near "' - third line'"
 LINE 3: ' - third line'
         ^
 -- Unicode escapes
+SET standard_conforming_strings TO on;
 SELECT U&'d\0061t\+000061' AS U&"d\0061t\+000061";
  data 
 ------
@@ -34,6 +35,18 @@ SELECT U&'d!0061t\+000061' UESCAPE '!' AS U&"d*0061t\+000061" UESCAPE '*';
  dat\+000061
 (1 row)
 
+SELECT U&' \' UESCAPE '!' AS "tricky";
+ tricky 
+--------
+  \
+(1 row)
+
+SELECT 'tricky' AS U&"\" UESCAPE '!';
+   \    
+--------
+ tricky
+(1 row)
+
 SELECT U&'wrong: \061';
 ERROR:  invalid Unicode escape value at or near "\061'"
 LINE 1: SELECT U&'wrong: \061';
@@ -46,6 +59,32 @@ SELECT U&'wrong: +0061' UESCAPE '+';
 ERROR:  invalid Unicode escape character at or near "+'"
 LINE 1: SELECT U&'wrong: +0061' UESCAPE '+';
                                          ^
+SET standard_conforming_strings TO off;
+SELECT U&'d\0061t\+000061' AS U&"d\0061t\+000061";
+ERROR:  unsafe use of string constant with Unicode escapes
+DETAIL:  String constants with Unicode escapes cannot be used when standard_conforming_strings is off.
+SELECT U&'d!0061t\+000061' UESCAPE '!' AS U&"d*0061t\+000061" UESCAPE '*';
+ERROR:  unsafe use of string constant with Unicode escapes
+DETAIL:  String constants with Unicode escapes cannot be used when standard_conforming_strings is off.
+SELECT U&' \' UESCAPE '!' AS "tricky";
+ERROR:  unsafe use of string constant with Unicode escapes
+DETAIL:  String constants with Unicode escapes cannot be used when standard_conforming_strings is off.
+SELECT 'tricky' AS U&"\" UESCAPE '!';
+   \    
+--------
+ tricky
+(1 row)
+
+SELECT U&'wrong: \061';
+ERROR:  unsafe use of string constant with Unicode escapes
+DETAIL:  String constants with Unicode escapes cannot be used when standard_conforming_strings is off.
+SELECT U&'wrong: \+0061';
+ERROR:  unsafe use of string constant with Unicode escapes
+DETAIL:  String constants with Unicode escapes cannot be used when standard_conforming_strings is off.
+SELECT U&'wrong: +0061' UESCAPE '+';
+ERROR:  unsafe use of string constant with Unicode escapes
+DETAIL:  String constants with Unicode escapes cannot be used when standard_conforming_strings is off.
+RESET standard_conforming_strings;
 --
 -- test conversions between various string types
 -- E021-10 implicit casting among the character data types
diff --git a/src/test/regress/sql/strings.sql b/src/test/regress/sql/strings.sql
index 0da88c7b29e..a28c75ac044 100644
--- a/src/test/regress/sql/strings.sql
+++ b/src/test/regress/sql/strings.sql
@@ -17,13 +17,32 @@ SELECT 'first line'
 	AS "Illegal comment within continuation";
 
 -- Unicode escapes
+SET standard_conforming_strings TO on;
+
+SELECT U&'d\0061t\+000061' AS U&"d\0061t\+000061";
+SELECT U&'d!0061t\+000061' UESCAPE '!' AS U&"d*0061t\+000061" UESCAPE '*';
+
+SELECT U&' \' UESCAPE '!' AS "tricky";
+SELECT 'tricky' AS U&"\" UESCAPE '!';
+
+SELECT U&'wrong: \061';
+SELECT U&'wrong: \+0061';
+SELECT U&'wrong: +0061' UESCAPE '+';
+
+SET standard_conforming_strings TO off;
+
 SELECT U&'d\0061t\+000061' AS U&"d\0061t\+000061";
 SELECT U&'d!0061t\+000061' UESCAPE '!' AS U&"d*0061t\+000061" UESCAPE '*';
 
+SELECT U&' \' UESCAPE '!' AS "tricky";
+SELECT 'tricky' AS U&"\" UESCAPE '!';
+
 SELECT U&'wrong: \061';
 SELECT U&'wrong: \+0061';
 SELECT U&'wrong: +0061' UESCAPE '+';
 
+RESET standard_conforming_strings;
+
 --
 -- test conversions between various string types
 -- E021-10 implicit casting among the character data types
-- 
GitLab