From: Bruce Momjian <bruce@momjian.us>
Date: Thu, 2 Jun 2005 01:23:08 +0000 (+0000)
Subject: Add support for \x hex escapes in backend strings.  Octal was already
X-Git-Tag: REL8_1_0BETA1~677
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=65537ac1b41f18e029b8172b8308189434c310d6;p=postgresql

Add support for \x hex escapes in backend strings.  Octal was already
supported.  This follows the C standard escapes.
---

diff --git a/doc/src/sgml/syntax.sgml b/doc/src/sgml/syntax.sgml
index 6e49e9cee1..45b6a80564 100644
--- a/doc/src/sgml/syntax.sgml
+++ b/doc/src/sgml/syntax.sgml
@@ -1,5 +1,5 @@
 <!--
-$PostgreSQL: pgsql/doc/src/sgml/syntax.sgml,v 1.99 2004/12/23 05:37:40 tgl Exp $
+$PostgreSQL: pgsql/doc/src/sgml/syntax.sgml,v 1.100 2005/06/02 01:23:08 momjian Exp $
 -->
 
 <chapter id="sql-syntax">
@@ -254,17 +254,18 @@ UPDATE "my_table" SET "a" = 5;
 
     <para>
      Another <productname>PostgreSQL</productname> extension is that
-     C-style backslash escapes are available:
-     <literal>\b</literal> is a backspace, <literal>\f</literal> is a
-     form feed, <literal>\n</literal> is a newline,
-     <literal>\r</literal> is a carriage return, <literal>\t</literal>
-     is a tab, and <literal>\<replaceable>xxx</replaceable></literal>,
-     where <replaceable>xxx</replaceable> is an octal number, is a
-     byte with the corresponding code.  (It is your responsibility
-     that the byte sequences you create are valid characters in the
-     server character set encoding.)  Any other character following a
-     backslash is taken literally.  Thus, to include a backslash in a
-     string constant, write two backslashes.
+     C-style backslash escapes are available: <literal>\b</literal> is a
+     backspace, <literal>\f</literal> is a form feed,
+     <literal>\n</literal> is a newline, <literal>\r</literal> is a
+     carriage return, <literal>\t</literal> is a tab. Also supported is
+     <literal>\<replaceable>digits</replaceable></literal>, where
+     <replaceable>ddd</replaceable> represents an octal byte value, and
+     <literal>\x<replaceable>hexdigits</replaceable></literal>, where
+     <replaceable>hexdigits</replaceable> represents a hexadecimal byte value.
+     (It is your responsibility that the byte sequences you create are
+     valid characters in the server character set encoding.) Any other
+     character following a backslash is taken literally. Thus, to
+     include a backslash in a string constant, write two backslashes.
     </para>
 
     <para>
diff --git a/src/backend/parser/scan.l b/src/backend/parser/scan.l
index ef5c1a639f..161a32861f 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 1.122 2005/05/26 01:24:29 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/parser/scan.l,v 1.123 2005/06/02 01:23:08 momjian Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -193,8 +193,9 @@ xnstart			[nN]{quote}
 xqstart			{quote}
 xqdouble		{quote}{quote}
 xqinside		[^\\']+
-xqescape		[\\][^0-7]
+xqescape		[\\][^0-7x]
 xqoctesc		[\\][0-7]{1,3}
+xqhexesc		[\\]x[0-9A-Fa-f]{1,2}
 
 /* $foo$ style quotes ("dollar quoting")
  * The quoted string starts with $foo$ where "foo" is an optional string
@@ -435,6 +436,10 @@ other			.
 					unsigned char c = strtoul(yytext+1, NULL, 8);
 					addlitchar(c);
 				}
+<xq>{xqhexesc}  {
+					unsigned char c = strtoul(yytext+2, NULL, 16);
+					addlitchar(c);
+				}
 <xq>{quotecontinue} {
 					/* ignore */
 				}