Code review for escape-strings patch. Sync psql and plpgsql lexers

with main, avoid using a SQL-defined SQLSTATE for what is most definitely not a SQL-compatible error condition, fix documentation omissions, adhere to message style guidelines, don't use two GUC_REPORT variables when one is sufficient. Nothing done about pg_dump issues.
2025-09-02 04:21:28 +03:00 · 2005-06-26 19:16:07 +00:00
parent 3cbd6bc308
commit d395aecffa
10 changed files with 136 additions and 84 deletions
--- 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			.

 %%

+static int
+pg_err_position(void)
+{
+	const char *loc = token_start ? token_start : yytext;
+
+	/* in multibyte encodings, return index in characters not bytes */
+	return pg_mbstrlen_with_len(scanbuf, loc - scanbuf) + 1;
+}
+
 void
 yyerror(const char *message)
 {
 	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;
+	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 */
 }
--- 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
 		},
--- 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);
--- 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')
--- 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
+	else if (*yytext == 'E' || *yytext == 'e')
 	{
-		/* Token is a '...' string */
+		/* Token is an E'...' string */
 		result = (char *) palloc(yyleng + 1);	/* more than enough room */
 		len = 0;
-		for (cp = yytext; *cp; cp++)
+		for (cp = yytext + 2; *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 == '\\')
+			{
+				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 + 1; *cp; cp++)
+		{
+			if (*cp == '\'')
+			{
+				if (cp[1] == '\'')
+					result[len++] = *cp++;
+				/* else it must be string end quote */
 			}
 			else if (*cp == '\\')
 			{