diff --git a/doc/src/sgml/errcodes.sgml b/doc/src/sgml/errcodes.sgml
index ad556d01516238d9fe2cc7a62f834cb5021d42b4..71b4a8cd4063702a091e2df64a4625a86a0d914d 100644
--- a/doc/src/sgml/errcodes.sgml
+++ b/doc/src/sgml/errcodes.sgml
@@ -1,4 +1,4 @@
-<!-- $PostgreSQL: pgsql/doc/src/sgml/errcodes.sgml,v 1.12 2005/01/06 01:49:24 tgl Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/errcodes.sgml,v 1.13 2005/06/26 19:16:04 tgl Exp $ -->
<appendix id="errcodes-appendix">
<title><productname>PostgreSQL</productname> Error Codes</title>
@@ -370,6 +370,11 @@
<entry>INVALID ESCAPE SEQUENCE</entry>
</row>
+<row>
+<entry><literal>22P06</literal></entry>
+<entry>NONSTANDARD USE OF ESCAPE CHARACTER</entry>
+</row>
+
<row>
<entry><literal>22010</literal></entry>
<entry>INVALID INDICATOR PARAMETER VALUE</entry>
diff --git a/doc/src/sgml/libpq.sgml b/doc/src/sgml/libpq.sgml
index 9c1b94e2be7660e2c4b160824d3aa1543905556c..a5bde7fc76e3cb990797a4fdda12462880b4ae5a 100644
--- a/doc/src/sgml/libpq.sgml
+++ b/doc/src/sgml/libpq.sgml
@@ -1,5 +1,5 @@
<!--
-$PostgreSQL: pgsql/doc/src/sgml/libpq.sgml,v 1.186 2005/06/21 04:02:29 tgl Exp $
+$PostgreSQL: pgsql/doc/src/sgml/libpq.sgml,v 1.187 2005/06/26 19:16:04 tgl Exp $
-->
<chapter id="libpq">
@@ -286,7 +286,7 @@ PGconn *PQconnectdb(const char *conninfo);
Kerberos service name to use when authenticating with Kerberos 4 or 5.
This must match the service name specified in the server
configuration for Kerberos authentication to succeed. (See also
- <xref linkend="kerberos-auth">.)
+ <xref linkend="kerberos-auth">.)
</para>
</listitem>
</varlistentry>
@@ -888,10 +888,13 @@ Parameters reported as of the current release include
<literal>is_superuser</>,
<literal>session_authorization</>,
<literal>DateStyle</>,
-<literal>TimeZone</>, and
-<literal>integer_datetimes</>.
+<literal>TimeZone</>,
+<literal>integer_datetimes</>, and
+<literal>standard_compliant_strings</>.
(<literal>server_encoding</>, <literal>TimeZone</>, and
-<literal>integer_datetimes</> were not reported by releases before 8.0.)
+<literal>integer_datetimes</> were not reported by releases before 8.0;
+<literal>standard_compliant_strings</> was not reported by releases
+before 8.1.)
Note that
<literal>server_version</>,
<literal>server_encoding</> and
@@ -913,6 +916,14 @@ see also <function>PQserverVersion</>, which returns the information
in a numeric form that is much easier to compare against.
</para>
+<para>
+If no value for <literal>standard_compliant_strings</> is reported,
+applications may assume it is <literal>false</>, that is, backslashes
+are treated as escapes in string literals. Also, the presence of this
+parameter may be taken as an indication that the escape string syntax
+(<literal>E'...'</>) is accepted.
+</para>
+
<para>
Although the returned pointer is declared <literal>const</>, it in fact
points to mutable storage associated with the <literal>PGconn</> structure.
diff --git a/doc/src/sgml/protocol.sgml b/doc/src/sgml/protocol.sgml
index cd6fa0e94f0e6fccec0af3cb6ecb062bec0e8255..7ebcfc63a34381e3874ee476664eabccd9e10c10 100644
--- a/doc/src/sgml/protocol.sgml
+++ b/doc/src/sgml/protocol.sgml
@@ -1,4 +1,4 @@
-<!-- $PostgreSQL: pgsql/doc/src/sgml/protocol.sgml,v 1.59 2005/06/22 15:19:43 tgl Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/protocol.sgml,v 1.60 2005/06/26 19:16:04 tgl Exp $ -->
<chapter id="protocol">
<title>Frontend/Backend Protocol</title>
@@ -1072,10 +1072,13 @@
<literal>is_superuser</>,
<literal>session_authorization</>,
<literal>DateStyle</>,
- <literal>TimeZone</>, and
- <literal>integer_datetimes</>.
+ <literal>TimeZone</>,
+ <literal>integer_datetimes</>, and
+ <literal>standard_compliant_strings</>.
(<literal>server_encoding</>, <literal>TimeZone</>, and
- <literal>integer_datetimes</> were not reported by releases before 8.0.)
+ <literal>integer_datetimes</> were not reported by releases before 8.0;
+ <literal>standard_compliant_strings</> was not reported by releases
+ before 8.1.)
Note that
<literal>server_version</>,
<literal>server_encoding</> and
diff --git a/doc/src/sgml/runtime.sgml b/doc/src/sgml/runtime.sgml
index 3841b0dee2d6ab3da034fdcfc87c139c0e5a3a54..c0b3e65ba78a6a39bad6c94c4fedef612b9110f4 100644
--- a/doc/src/sgml/runtime.sgml
+++ b/doc/src/sgml/runtime.sgml
@@ -1,5 +1,5 @@
<!--
-$PostgreSQL: pgsql/doc/src/sgml/runtime.sgml,v 1.331 2005/06/26 03:03:17 momjian Exp $
+$PostgreSQL: pgsql/doc/src/sgml/runtime.sgml,v 1.332 2005/06/26 19:16:04 tgl Exp $
-->
<chapter Id="runtime">
@@ -3766,13 +3766,11 @@ dynamic_library_path = 'C:\tools\postgresql;H:\my_project\lib;$libdir'
<listitem>
<para>
When <literal>on</>, a warning is issued if a backslash
- (<literal>\</>) appears in a ordinary, non-escape syntax
- (<literal>''</>) string. To log the statement that generated the
- warning, set <varname>log_min_error_statement</> to
- <literal>error</>. The default is off.
+ (<literal>\</>) appears in an ordinary string literal
+ (<literal>'...'</> syntax). The default is <literal>off</>.
</para>
<para>
- Escape string syntax (<literal>E''</>) should be used for
+ Escape string syntax (<literal>E'...'</>) should be used for
escapes, because in future versions of
<productname>PostgreSQL</productname> ordinary strings will have
the standard-compliant behavior of treating backslashes
@@ -3988,22 +3986,7 @@ dynamic_library_path = 'C:\tools\postgresql;H:\my_project\lib;$libdir'
</listitem>
</varlistentry>
- <varlistentry id="guc-escape-string-syntax" xreflabel="escape_string_syntax">
- <term><varname>escape_string_syntax</varname> (<type>boolean</type>)</term>
- <indexterm><primary>strings</><secondary>escape</></>
- <indexterm>
- <primary><varname>escape_string_syntax</> configuration parameter</primary>
- </indexterm>
- <listitem>
- <para>
- Reports whether escape string syntax (<literal>E''</>) is
- supported. This variable is used by applications that need to
- determine if escape string syntax can be used in their code.
- </para>
- </listitem>
- </varlistentry>
-
- <varlistentry id="guc-sql-standard-strings" xreflabel="standard_compliant_strings">
+ <varlistentry id="guc-standard-compliant-strings" xreflabel="standard_compliant_strings">
<term><varname>standard_compliant_strings</varname> (<type>boolean</type>)</term>
<indexterm><primary>strings</><secondary>escape</></>
<indexterm>
@@ -4011,10 +3994,16 @@ dynamic_library_path = 'C:\tools\postgresql;H:\my_project\lib;$libdir'
</indexterm>
<listitem>
<para>
- Reports whether ordinary, non-escape syntax strings
- (<literal>''</>) treat backslashes literally, as specified in
- the SQL standard. This variable is used by applications that
- need to know how ordinary strings are processed`.
+ Reports whether ordinary string literals
+ (<literal>'...'</>) treat backslashes literally, as specified in
+ the SQL standard. The value is currently always <literal>false</>,
+ indicating that backslashes are treated as escapes. It is planned
+ that this will change to <literal>true</> in a future
+ <productname>PostgreSQL</productname> release when string literal
+ syntax changes to meet the standard. Applications may check this
+ parameter to determine how string literals will be processed.
+ The presence of this parameter can also be taken as an indication
+ that the escape string syntax (<literal>E'...'</>) is supported.
</para>
</listitem>
</varlistentry>
diff --git a/doc/src/sgml/syntax.sgml b/doc/src/sgml/syntax.sgml
index 3d8d457c561f5d1d99f683d98c184fb83d814e6c..0d3d7f19f1896d3dae07f4b7e8ebe28e1c0f007a 100644
--- a/doc/src/sgml/syntax.sgml
+++ b/doc/src/sgml/syntax.sgml
@@ -1,5 +1,5 @@
<!--
-$PostgreSQL: pgsql/doc/src/sgml/syntax.sgml,v 1.101 2005/06/26 03:03:21 momjian Exp $
+$PostgreSQL: pgsql/doc/src/sgml/syntax.sgml,v 1.102 2005/06/26 19:16:05 tgl Exp $
-->
<chapter id="sql-syntax">
@@ -249,7 +249,7 @@ UPDATE "my_table" SET "a" = 5;
<productname>PostgreSQL</productname> also allows single quotes
to be escaped with a backslash (<literal>\'</literal>). However,
future versions of <productname>PostgreSQL</productname> will not
- support this so applications using this should convert to the
+ allow this, so applications using backslashes should convert to the
standard-compliant method outlined above.
</para>
@@ -276,8 +276,8 @@ UPDATE "my_table" SET "a" = 5;
eventually treat backslashes as literal characters to be
standard-compliant. The proper way to specify escape processing is
to use the escape string syntax to indicate that escape
- processing is desired. Escape string syntax is specified by placing
- the the letter <literal>E</literal> (upper or lower case) before
+ processing is desired. Escape string syntax is specified by writing
+ the letter <literal>E</literal> (upper or lower case) just before
the string, e.g. <literal>E'\041'</>. This method will work in all
future versions of <productname>PostgreSQL</productname>.
</para>
diff --git a/src/backend/parser/scan.l b/src/backend/parser/scan.l
index 4c556a5fba29e0f992cde889bd3d6a43f6f70ba1..f9b0dbdb75b8670596883bb79f3b1ba65bc5be26 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 1.126 2005/06/26 03:03:38 momjian Exp $
+ * $PostgreSQL: pgsql/src/backend/parser/scan.l,v 1.127 2005/06/26 19:16:05 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -48,10 +48,19 @@
extern YYSTYPE yylval;
static int xcdepth = 0; /* depth of nesting in slash-star comments */
-static char *dolqstart; /* current $foo$ quote start string */
-static bool warn_on_first_escape;
+static char *dolqstart; /* current $foo$ quote start string */
+
+/*
+ * GUC variable. This is a DIRECT violation of the warning given at the
+ * head of gram.y, ie flex/bison code must not depend on any GUC variables;
+ * as such, changing its value can induce very unintuitive behavior.
+ * But we shall have to live with it as a short-term thing until the switch
+ * to SQL-standard string syntax is complete.
+ */
bool escape_string_warning;
+static bool warn_on_first_escape;
+
/*
* literalbuf is used to accumulate literal values when multiple rules
* are needed to parse a single literal. Call startlit to reset buffer
@@ -66,6 +75,7 @@ static int literalalloc; /* current allocated buffer size */
static void addlit(char *ytext, int yleng);
static void addlitchar(unsigned char ychar);
static char *litbufdup(void);
+static int pg_err_position(void);
static void check_escape_warning(void);
/*
@@ -188,9 +198,8 @@ xhinside [^']*
/* National character */
xnstart [nN]{quote}
-/* Quote string does not warn about escapes */
+/* Quoted string that allows backslash escapes */
xestart [eE]{quote}
-xeinside [^']*
/* Extended quote
* xqdouble implements embedded quote, ''''
@@ -446,17 +455,21 @@ other .
{
if (warn_on_first_escape && escape_string_warning)
ereport(WARNING,
- (errcode(ERRCODE_INVALID_USE_OF_ESCAPE_CHARACTER),
- errmsg("Invalid use of \\' in a normal string"),
- errhint("Use '' to place quotes in strings, or use the escape string syntax (E'').")));
+ (errcode(ERRCODE_NONSTANDARD_USE_OF_ESCAPE_CHARACTER),
+ errmsg("nonstandard use of \\' in a string literal"),
+ errhint("Use '' to write quotes in strings, or use the escape string syntax (E'...')."),
+ errposition(pg_err_position())));
+ warn_on_first_escape = false; /* warn only once per string */
}
else if (yytext[1] == '\\')
{
if (warn_on_first_escape && escape_string_warning)
ereport(WARNING,
- (errcode(ERRCODE_INVALID_USE_OF_ESCAPE_CHARACTER),
- errmsg("Invalid use of \\\\ in a normal string"),
- errhint("Use the escape string syntax for backslashes, e.g. E'\\\\'.")));
+ (errcode(ERRCODE_NONSTANDARD_USE_OF_ESCAPE_CHARACTER),
+ errmsg("nonstandard use of \\\\ in a string literal"),
+ errhint("Use the escape string syntax for backslashes, e.g., E'\\\\'."),
+ errposition(pg_err_position())));
+ warn_on_first_escape = false; /* warn only once per string */
}
else
check_escape_warning();
@@ -707,14 +720,20 @@ other .
%%
-void
-yyerror(const char *message)
+static int
+pg_err_position(void)
{
const char *loc = token_start ? token_start : yytext;
- int cursorpos;
/* in multibyte encodings, return index in characters not bytes */
- cursorpos = pg_mbstrlen_with_len(scanbuf, loc - scanbuf) + 1;
+ return pg_mbstrlen_with_len(scanbuf, loc - scanbuf) + 1;
+}
+
+void
+yyerror(const char *message)
+{
+ const char *loc = token_start ? token_start : yytext;
+ int cursorpos = pg_err_position();
if (*loc == YY_END_OF_BUFFER_CHAR)
{
@@ -852,8 +871,9 @@ check_escape_warning(void)
{
if (warn_on_first_escape && escape_string_warning)
ereport(WARNING,
- (errcode(ERRCODE_INVALID_USE_OF_ESCAPE_CHARACTER),
- errmsg("Invalid use of escapes in an ordinary string"),
- errhint("Use the escape string syntax for escapes, e.g. E'\\r\\n'.")));
+ (errcode(ERRCODE_NONSTANDARD_USE_OF_ESCAPE_CHARACTER),
+ errmsg("nonstandard use of escape in a string literal"),
+ errhint("Use the escape string syntax for escapes, e.g., E'\\r\\n'."),
+ errposition(pg_err_position())));
warn_on_first_escape = false; /* warn only once per string */
}
diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index 1738604942615a179627518ee1c926bfa5753b85..0ab8e742336ae1eabdf6b16d313ea40a41856e09 100644
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -10,7 +10,7 @@
* Written by Peter Eisentraut <peter_e@gmx.net>.
*
* IDENTIFICATION
- * $PostgreSQL: pgsql/src/backend/utils/misc/guc.c,v 1.269 2005/06/26 03:03:41 momjian Exp $
+ * $PostgreSQL: pgsql/src/backend/utils/misc/guc.c,v 1.270 2005/06/26 19:16:06 tgl Exp $
*
*--------------------------------------------------------------------
*/
@@ -190,7 +190,6 @@ static int max_index_keys;
static int max_identifier_length;
static int block_size;
static bool integer_datetimes;
-static bool escape_string_syntax;
static bool standard_compliant_strings;
/* should be static, but commands/variable.c needs to get at it */
@@ -877,26 +876,16 @@ static struct config_bool ConfigureNamesBool[] =
{
{"escape_string_warning", PGC_USERSET, COMPAT_OPTIONS_PREVIOUS,
- gettext_noop("Warn about backslash escapes in ordinary, non-escape-syntax strings."),
+ gettext_noop("Warn about backslash escapes in ordinary string literals."),
NULL
},
&escape_string_warning,
false, NULL, NULL
},
- {
- {"escape_string_syntax", PGC_INTERNAL, PRESET_OPTIONS,
- gettext_noop("Escape string syntax (E'') is supported."),
- NULL,
- GUC_REPORT | GUC_NOT_IN_SAMPLE | GUC_DISALLOW_IN_FILE
- },
- &escape_string_syntax,
- true, NULL, NULL
- },
-
{
{"standard_compliant_strings", PGC_INTERNAL, PRESET_OPTIONS,
- gettext_noop("'' strings treat backslashes literally."),
+ gettext_noop("'...' strings treat backslashes literally."),
NULL,
GUC_REPORT | GUC_NOT_IN_SAMPLE | GUC_DISALLOW_IN_FILE
},
diff --git a/src/bin/psql/psqlscan.l b/src/bin/psql/psqlscan.l
index a093b3703f5d6ad31f73088d24a995ecb0269904..f62fe6224f9d740e88afab2f6f73d5f79d24f99f 100644
--- a/src/bin/psql/psqlscan.l
+++ b/src/bin/psql/psqlscan.l
@@ -33,7 +33,7 @@
* Portions Copyright (c) 1994, Regents of the University of California
*
* IDENTIFICATION
- * $PostgreSQL: pgsql/src/bin/psql/psqlscan.l,v 1.14 2005/06/02 17:45:19 tgl Exp $
+ * $PostgreSQL: pgsql/src/bin/psql/psqlscan.l,v 1.15 2005/06/26 19:16:06 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -235,17 +235,18 @@ quotefail {quote}{whitespace}*"-"
xbstart [bB]{quote}
xbinside [^']*
-/* Hexadecimal number
- */
+/* Hexadecimal number */
xhstart [xX]{quote}
xhinside [^']*
-/* National character
- */
+/* National character */
xnstart [nN]{quote}
+/* Quoted string that allows backslash escapes */
+xestart [eE]{quote}
+
/* Extended quote
- * xqdouble implements embedded quote
+ * xqdouble implements embedded quote, ''''
*/
xqstart {quote}
xqdouble {quote}{quote}
@@ -450,6 +451,10 @@ other .
BEGIN(xq);
ECHO;
}
+{xestart} {
+ BEGIN(xq);
+ ECHO;
+ }
<xq>{quotestop} |
<xq>{quotefail} {
yyless(1);
diff --git a/src/include/utils/errcodes.h b/src/include/utils/errcodes.h
index 646193def499a1e6d672512e1c8334dbdfbb5ff6..636c3f7a379e1f6984f3f41d7b9af0d6e5425daa 100644
--- a/src/include/utils/errcodes.h
+++ b/src/include/utils/errcodes.h
@@ -11,7 +11,7 @@
*
* Copyright (c) 2003-2005, PostgreSQL Global Development Group
*
- * $PostgreSQL: pgsql/src/include/utils/errcodes.h,v 1.17 2005/01/01 20:44:30 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/utils/errcodes.h,v 1.18 2005/06/26 19:16:06 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -126,6 +126,7 @@
#define ERRCODE_INVALID_ESCAPE_CHARACTER MAKE_SQLSTATE('2','2', '0','1','9')
#define ERRCODE_INVALID_ESCAPE_OCTET MAKE_SQLSTATE('2','2', '0','0','D')
#define ERRCODE_INVALID_ESCAPE_SEQUENCE MAKE_SQLSTATE('2','2', '0','2','5')
+#define ERRCODE_NONSTANDARD_USE_OF_ESCAPE_CHARACTER MAKE_SQLSTATE('2','2', 'P','0','6')
#define ERRCODE_INVALID_INDICATOR_PARAMETER_VALUE MAKE_SQLSTATE('2','2', '0','1','0')
#define ERRCODE_INVALID_LIMIT_VALUE MAKE_SQLSTATE('2','2', '0','2','0')
#define ERRCODE_INVALID_PARAMETER_VALUE MAKE_SQLSTATE('2','2', '0','2','3')
diff --git a/src/pl/plpgsql/src/scan.l b/src/pl/plpgsql/src/scan.l
index 680a58fc018bd33d1bb37759639fb661e620ba76..e69c8f17b02a60c98d4ef9012edc4aeb8c49f935 100644
--- a/src/pl/plpgsql/src/scan.l
+++ b/src/pl/plpgsql/src/scan.l
@@ -4,7 +4,7 @@
* procedural language
*
* IDENTIFICATION
- * $PostgreSQL: pgsql/src/pl/plpgsql/src/scan.l,v 1.41 2005/06/22 01:35:02 neilc Exp $
+ * $PostgreSQL: pgsql/src/pl/plpgsql/src/scan.l,v 1.42 2005/06/26 19:16:07 tgl Exp $
*
* This software is copyrighted by Jan Wieck - Hamburg.
*
@@ -291,6 +291,12 @@ dump { return O_DUMP; }
start_charpos = yytext;
BEGIN(IN_STRING);
}
+[eE]' {
+ /* for now, treat the same as a regular literal */
+ start_lineno = plpgsql_scanner_lineno();
+ start_charpos = yytext;
+ BEGIN(IN_STRING);
+ }
<IN_STRING>\\. { }
<IN_STRING>\\ { /* can only happen with \ at EOF */ }
<IN_STRING>'' { }
@@ -563,18 +569,41 @@ plpgsql_get_string_value(void)
memcpy(result, yytext + dolqlen, len);
result[len] = '\0';
}
+ else if (*yytext == 'E' || *yytext == 'e')
+ {
+ /* Token is an E'...' string */
+ result = (char *) palloc(yyleng + 1); /* more than enough room */
+ len = 0;
+ for (cp = yytext + 2; *cp; cp++)
+ {
+ if (*cp == '\'')
+ {
+ if (cp[1] == '\'')
+ result[len++] = *cp++;
+ /* else it must be string end quote */
+ }
+ else if (*cp == '\\')
+ {
+ if (cp[1] != '\0') /* just a paranoid check */
+ result[len++] = *(++cp);
+ }
+ else
+ result[len++] = *cp;
+ }
+ result[len] = '\0';
+ }
else
{
/* Token is a '...' string */
result = (char *) palloc(yyleng + 1); /* more than enough room */
len = 0;
- for (cp = yytext; *cp; cp++)
+ for (cp = yytext + 1; *cp; cp++)
{
if (*cp == '\'')
{
if (cp[1] == '\'')
result[len++] = *cp++;
- /* else it must be string start or end quote */
+ /* else it must be string end quote */
}
else if (*cp == '\\')
{