Add E'' syntax so eventually normal strings can treat backslashes

literally.

Add GUC variables:

        "escape_string_warning" - warn about backslashes in non-E strings
        "escape_string_syntax" - supports E'' syntax?
        "standard_compliant_strings" - treats backslashes literally in ''

Update code to use E'' when escapes are used.

3 files changed, 83 insertions, 4 deletions

diff --git a/src/backend/parser/scan.l b/src/backend/parser/scan.l
index 0a250e8dbe8..4c556a5fba2 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 1.125 2005/06/15 16:28:06 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/parser/scan.l,v 1.126 2005/06/26 03:03:38 momjian Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -48,7 +48,9 @@
 extern YYSTYPE yylval;
 
 static int		xcdepth = 0;	/* depth of nesting in slash-star comments */
-static char    *dolqstart;      /* current $foo$ quote start string */
+static char	   *dolqstart;      /* current $foo$ quote start string */
+static bool		warn_on_first_escape;
+bool			escape_string_warning;
 
 /*
  * literalbuf is used to accumulate literal values when multiple rules
@@ -64,6 +66,7 @@ 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 void check_escape_warning(void);
 
 /*
  * When we parse a token that requires multiple lexer rules to process,
@@ -185,6 +188,10 @@ xhinside		[^']*
 /* National character */
 xnstart			[nN]{quote}
 
+/* Quote string does not warn about escapes */
+xestart			[eE]{quote}
+xeinside		[^']*
+
 /* Extended quote
  * xqdouble implements embedded quote, ''''
  */
@@ -410,6 +417,13 @@ other			.
 				}
 
 {xqstart}		{
+					warn_on_first_escape = true;
+					token_start = yytext;
+					BEGIN(xq);
+					startlit();
+				}
+{xestart}		{
+					warn_on_first_escape = false;
 					token_start = yytext;
 					BEGIN(xq);
 					startlit();
@@ -428,14 +442,36 @@ other			.
 					addlit(yytext, yyleng);
 				}
 <xq>{xqescape}  {
+					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 '' to place quotes in strings, or use the escape string syntax (E'').")));
+					}
+					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'\\\\'.")));
+					}
+					else
+						check_escape_warning();
 					addlitchar(unescape_single_char(yytext[1]));
 				}
 <xq>{xqoctesc}  {
 					unsigned char c = strtoul(yytext+1, NULL, 8);
+
+					check_escape_warning();
 					addlitchar(c);
 				}
 <xq>{xqhexesc}  {
 					unsigned char c = strtoul(yytext+2, NULL, 16);
+
+					check_escape_warning();
 					addlitchar(c);
 				}
 <xq>{quotecontinue} {
@@ -810,3 +846,14 @@ unescape_single_char(unsigned char c)
 			return c;
 	}
 }
+
+static void
+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'.")));
+	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 05ce93cf58f..17386049426 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 1.268 2005/06/17 22:32:47 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/misc/guc.c,v 1.269 2005/06/26 03:03:41 momjian Exp $
  *
  *--------------------------------------------------------------------
  */
@@ -189,7 +189,9 @@ static int	max_function_args;
 static int	max_index_keys;
 static int	max_identifier_length;
 static int	block_size;
-static bool integer_datetimes;
+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 */
 char	   *session_authorization_string;
@@ -873,6 +875,35 @@ static struct config_bool ConfigureNamesBool[] =
 		false, NULL, NULL
 	},
 
+	{
+		{"escape_string_warning", PGC_USERSET, COMPAT_OPTIONS_PREVIOUS,
+			gettext_noop("Warn about backslash escapes in ordinary, non-escape-syntax strings."),
+			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."),
+			NULL,
+			GUC_REPORT | GUC_NOT_IN_SAMPLE | GUC_DISALLOW_IN_FILE
+		},
+		&standard_compliant_strings,
+		false, NULL, NULL
+	},
+
 	/* End-of-list marker */
 	{
 		{NULL, 0, 0, NULL, NULL}, NULL, false, NULL, NULL
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index 4c5a1ed59e3..72f447c76b4 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -330,6 +330,7 @@
 #regex_flavor = advanced	# advanced, extended, or basic
 #sql_inheritance = true
 #default_with_oids = false
+#escape_string_warning = false
 
 # - Other Platforms & Clients -