From 05d249717d652f0b16960d8a58611e222f1f907b Mon Sep 17 00:00:00 2001
From: Tom Lane <tgl@sss.pgh.pa.us>
Date: Sat, 10 Oct 2009 03:50:15 +0000
Subject: [PATCH] Improve similar_escape() in two different ways:

* Stop escaping ? and {.  As of SQL:2008, SIMILAR TO is defined to have
POSIX-compatible interpretation of ? as well as {m,n} and related constructs,
so we should allow these things through to our regex engine.

* Escape ^ and $.  It appears that our regex engine will treat ^^ at the
beginning of the string the same as ^, and similarly for $$ at the end of
the string, which meant that SIMILAR TO was effectively ignoring ^ at the
start of the pattern and $ at the end.  Since these are not supposed to be
metacharacters, this is a bug.

The second part of this is arguably a back-patchable bug fix, but I'm
hesitant to do that because it might break applications that are expecting
something like "col SIMILAR TO '^foo$'" to work like a POSIX pattern.
Seems safer to only change it at a major version boundary.

Per discussion of an example from Doug Gorley.
---
 doc/src/sgml/func.sgml         | 32 ++++++++++++++++++++++++++++----
 src/backend/utils/adt/regexp.c |  8 ++++----
 2 files changed, 32 insertions(+), 8 deletions(-)

diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml
index da558668c8a..211a450ce30 100644
--- a/doc/src/sgml/func.sgml
+++ b/doc/src/sgml/func.sgml
@@ -1,4 +1,4 @@
-<!-- $PostgreSQL: pgsql/doc/src/sgml/func.sgml,v 1.488 2009/10/09 21:02:55 petere Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/func.sgml,v 1.489 2009/10/10 03:50:15 tgl Exp $ -->
 
  <chapter id="functions">
   <title>Functions and Operators</title>
@@ -3154,6 +3154,31 @@ cast(-44 as bit(12))           <lineannotation>111111010100</lineannotation>
       or more times.
      </para>
     </listitem>
+    <listitem>
+     <para>
+      <literal>?</literal> denotes repetition of the previous item zero
+      or one time.
+     </para>
+    </listitem>
+    <listitem>
+     <para>
+      <literal>{</><replaceable>m</><literal>}</literal> denotes repetition
+      of the previous item exactly <replaceable>m</> times.
+     </para>
+    </listitem>
+    <listitem>
+     <para>
+      <literal>{</><replaceable>m</><literal>,}</literal> denotes repetition
+      of the previous item <replaceable>m</> or more times.
+     </para>
+    </listitem>
+    <listitem>
+     <para>
+      <literal>{</><replaceable>m</><literal>,</><replaceable>n</><literal>}</>
+      denotes repetition of the previous item at least <replaceable>m</> and
+      not more than <replaceable>n</> times.
+     </para>
+    </listitem>
     <listitem>
      <para>
       Parentheses <literal>()</literal> can be used to group items into
@@ -3168,9 +3193,8 @@ cast(-44 as bit(12))           <lineannotation>111111010100</lineannotation>
     </listitem>
    </itemizedlist>
 
-    Notice that bounded repetition operators (<literal>?</> and
-    <literal>{...}</>) are not provided, though they exist in POSIX.
-    Also, the period (<literal>.</>) is not a metacharacter.
+    Notice that the period (<literal>.</>) is not a metacharacter
+    for <function>SIMILAR TO</>.
    </para>
 
    <para>
diff --git a/src/backend/utils/adt/regexp.c b/src/backend/utils/adt/regexp.c
index e4e3c776658..118d42d2a0a 100644
--- a/src/backend/utils/adt/regexp.c
+++ b/src/backend/utils/adt/regexp.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/adt/regexp.c,v 1.82 2009/06/11 14:49:04 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/adt/regexp.c,v 1.83 2009/10/10 03:50:15 tgl Exp $
  *
  *		Alistair Crooks added the code for the regex caching
  *		agc - cached the regular expressions used - there's a good chance
@@ -639,7 +639,7 @@ textregexreplace(PG_FUNCTION_ARGS)
 
 /*
  * similar_escape()
- * Convert a SQL99 regexp pattern to POSIX style, so it can be used by
+ * Convert a SQL:2008 regexp pattern to POSIX style, so it can be used by
  * our regexp engine.
  */
 Datum
@@ -740,8 +740,8 @@ similar_escape(PG_FUNCTION_ARGS)
 		}
 		else if (pchar == '_')
 			*r++ = '.';
-		else if (pchar == '\\' || pchar == '.' || pchar == '?' ||
-				 pchar == '{')
+		else if (pchar == '\\' || pchar == '.' ||
+				 pchar == '^' || pchar == '$')
 		{
 			*r++ = '\\';
 			*r++ = pchar;