Modify libpq's string-escaping routines to be aware of encoding considerations

and standard_conforming_strings.  The encoding changes are needed for proper
escaping in multibyte encodings, as per the SQL-injection vulnerabilities
noted in CVE-2006-2313 and CVE-2006-2314.  Concurrent fixes are being applied
to the server to ensure that it rejects queries that may have been corrupted
by attempted SQL injection, but this merely guarantees that unpatched clients
will fail rather than allow injection.  An actual fix requires changing the
client-side code.  While at it we have also fixed these routines to understand
about standard_conforming_strings, so that the upcoming changeover to SQL-spec
string syntax can be somewhat transparent to client code.

Since the existing API of PQescapeString and PQescapeBytea provides no way to
inform them which settings are in use, these functions are now deprecated in
favor of new functions PQescapeStringConn and PQescapeByteaConn.  The new
functions take the PGconn to which the string will be sent as an additional
parameter, and look inside the connection structure to determine what to do.
So as to provide some functionality for clients using the old functions,
libpq stores the latest encoding and standard_conforming_strings values
received from the backend in static variables, and the old functions consult
these variables.  This will work reliably in clients using only one Postgres
connection at a time, or even multiple connections if they all use the same
encoding and string syntax settings; which should cover many practical
scenarios.

Clients that use homebrew escaping methods, such as PHP's addslashes()
function or even hardwired regexp substitution, will require extra effort
to fix :-(.  It is strongly recommended that such code be replaced by use of
PQescapeStringConn/PQescapeByteaConn if at all feasible.

1 files changed, 159 insertions, 45 deletions

diff --git a/src/interfaces/libpq/fe-exec.c b/src/interfaces/libpq/fe-exec.c
index e7cbc08d62b..325edb8d8ff 100644
--- a/src/interfaces/libpq/fe-exec.c
+++ b/src/interfaces/libpq/fe-exec.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $Header: /cvsroot/pgsql/src/interfaces/libpq/fe-exec.c,v 1.153.2.5 2006/05/21 19:57:07 momjian Exp $
+ *	  $Header: /cvsroot/pgsql/src/interfaces/libpq/fe-exec.c,v 1.153.2.6 2006/05/21 20:20:24 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -41,6 +41,12 @@ char	   *const pgresStatus[] = {
 	"PGRES_FATAL_ERROR"
 };
 
+/*
+ * static state needed by PQescapeString and PQescapeBytea; initialize to
+ * values that result in backward-compatible behavior
+ */
+static int	static_client_encoding = PG_SQL_ASCII;
+static bool	static_std_strings = false;
 
 
 static bool PQsendQueryStart(PGconn *conn);
@@ -608,11 +614,22 @@ pqSaveParameterStatus(PGconn *conn, const char *name, const char *value)
 	}
 
 	/*
-	 * Special hacks: remember client_encoding as a numeric value, and
-	 * convert server version to a numeric form as well.
+	 * Special hacks: remember client_encoding and standard_conforming_strings,
+	 * and convert server version to a numeric form.  We keep the first two of
+	 * these in static variables as well, so that PQescapeString and
+	 * PQescapeBytea can behave somewhat sanely (at least in single-
+	 * connection-using programs).
 	 */
 	if (strcmp(name, "client_encoding") == 0)
+	{
 		conn->client_encoding = pg_char_to_encoding(value);
+		static_client_encoding = conn->client_encoding;
+	}
+	else if (strcmp(name, "standard_conforming_strings") == 0)
+	{
+		conn->std_strings = (strcmp(value, "on") == 0);
+		static_std_strings = conn->std_strings;
+	}
 	else if (strcmp(name, "server_version") == 0)
 	{
 		int			cnt;
@@ -2227,7 +2244,7 @@ PQfreeNotify(PGnotify *notify)
 /*
  * Escaping arbitrary strings to get valid SQL literal strings.
  *
- * Replaces "\\" with "\\\\" and "'" with "''".
+ * Replaces "'" with "''", and if not std_strings, replaces "\" with "\\".
  *
  * length is the length of the source string.  (Note: if a terminating NUL
  * is encountered sooner, PQescapeString stops short of "length"; the behavior
@@ -2239,33 +2256,74 @@ PQfreeNotify(PGnotify *notify)
  *
  * Returns the actual length of the output (not counting the terminating NUL).
  */
-size_t
-PQescapeString(char *to, const char *from, size_t length)
+static size_t
+PQescapeStringInternal(PGconn *conn,
+					   char *to, const char *from, size_t length,
+					   int *error,
+					   int encoding, bool std_strings)
 {
 	const char *source = from;
 	char	   *target = to;
 	size_t		remaining = length;
 
+	if (error)
+		*error = 0;
+
 	while (remaining > 0 && *source != '\0')
 	{
-		switch (*source)
+		char	c = *source;
+		int		len;
+		int		i;
+
+		/* Fast path for plain ASCII */
+		if (!IS_HIGHBIT_SET(c))
 		{
-			case '\\':
-				*target++ = '\\';
-				*target++ = '\\';
-				break;
+			/* Apply quoting if needed */
+			if (c == '\'' ||
+				(c == '\\' && !std_strings))
+				*target++ = c;
+			/* Copy the character */
+			*target++ = c;
+			source++;
+			remaining--;
+			continue;
+		}
 
-			case '\'':
-				*target++ = '\'';
-				*target++ = '\'';
-				break;
+		/* Slow path for possible multibyte characters */
+		len = pg_encoding_mblen(encoding, source);
 
-			default:
-				*target++ = *source;
+		/* Copy the character */
+		for (i = 0; i < len; i++)
+		{
+			if (remaining == 0 || *source == '\0')
 				break;
+			*target++ = *source++;
+			remaining--;
+		}
+
+		/*
+		 * If we hit premature end of string (ie, incomplete multibyte
+		 * character), try to pad out to the correct length with spaces.
+		 * We may not be able to pad completely, but we will always be able
+		 * to insert at least one pad space (since we'd not have quoted a
+		 * multibyte character).  This should be enough to make a string that
+		 * the server will error out on.
+		 */
+		if (i < len)
+		{
+			if (error)
+				*error = 1;
+			if (conn)
+				printfPQExpBuffer(&conn->errorMessage,
+						libpq_gettext("incomplete multibyte character\n"));
+			for (; i < len; i++)
+			{
+				if (((size_t) (target - to)) / 2 >= length)
+					break;
+				*target++ = ' ';
+			}
+			break;
 		}
-		source++;
-		remaining--;
 	}
 
 	/* Write the terminating NUL character. */
@@ -2274,72 +2332,109 @@ PQescapeString(char *to, const char *from, size_t length)
 	return target - to;
 }
 
+size_t
+PQescapeStringConn(PGconn *conn,
+				   char *to, const char *from, size_t length,
+				   int *error)
+{
+	if (!conn)
+	{
+		/* force empty-string result */
+		*to = '\0';
+		if (error)
+			*error = 1;
+		return 0;
+	}
+	return PQescapeStringInternal(conn, to, from, length, error,
+								  conn->client_encoding,
+								  conn->std_strings);
+}
+
+size_t
+PQescapeString(char *to, const char *from, size_t length)
+{
+	return PQescapeStringInternal(NULL, to, from, length, NULL,
+								  static_client_encoding,
+								  static_std_strings);
+}
+
 /*
  *		PQescapeBytea	- converts from binary string to the
  *		minimal encoding necessary to include the string in an SQL
  *		INSERT statement with a bytea type column as the target.
  *
  *		The following transformations are applied
- *		'\0' == ASCII  0 == \\000
- *		'\'' == ASCII 39 == \'
- *		'\\' == ASCII 92 == \\\\
- *		anything < 0x20, or > 0x7e ---> \\ooo
- *                                      (where ooo is an octal expression)
+ *		'\0' == ASCII  0 == \000
+ *		'\'' == ASCII 39 == ''
+ *		'\\' == ASCII 92 == \\
+ *		anything < 0x20, or > 0x7e ---> \ooo
+ *										(where ooo is an octal expression)
+ *		If not std_strings, all backslashes sent to the output are doubled.
  */
-unsigned char *
-PQescapeBytea(const unsigned char *bintext, size_t binlen, size_t *bytealen)
+static unsigned char *
+PQescapeByteaInternal(PGconn *conn,
+					  const unsigned char *from, size_t from_length,
+					  size_t *to_length, bool std_strings)
 {
 	const unsigned char *vp;
 	unsigned char *rp;
 	unsigned char *result;
 	size_t		i;
 	size_t		len;
+	size_t		bslash_len = (std_strings ? 1 : 2);
 
 	/*
 	 * empty string has 1 char ('\0')
 	 */
 	len = 1;
 
-	vp = bintext;
-	for (i = binlen; i > 0; i--, vp++)
+	vp = from;
+	for (i = from_length; i > 0; i--, vp++)
 	{
 		if (*vp < 0x20 || *vp > 0x7e)
-			len += 5;			/* '5' is for '\\ooo' */
+			len += bslash_len + 3;
 		else if (*vp == '\'')
 			len += 2;
 		else if (*vp == '\\')
-			len += 4;
+			len += bslash_len + bslash_len;
 		else
 			len++;
 	}
 
+	*to_length = len;
 	rp = result = (unsigned char *) malloc(len);
 	if (rp == NULL)
+	{
+		if (conn)
+			printfPQExpBuffer(&conn->errorMessage,
+							  libpq_gettext("out of memory\n"));
 		return NULL;
+	}
 
-	vp = bintext;
-	*bytealen = len;
-
-	for (i = binlen; i > 0; i--, vp++)
+	vp = from;
+	for (i = from_length; i > 0; i--, vp++)
 	{
 		if (*vp < 0x20 || *vp > 0x7e)
 		{
-			(void) sprintf(rp, "\\\\%03o", *vp);
-			rp += 5;
+			if (!std_strings)
+				*rp++ = '\\';
+			(void) sprintf((char *) rp, "\\%03o", *vp);
+			rp += 4;
 		}
 		else if (*vp == '\'')
 		{
-			rp[0] = '\'';
-			rp[1] = '\'';
-			rp += 2;
+			*rp++ = '\'';
+			*rp++ = '\'';
 		}
 		else if (*vp == '\\')
 		{
-			rp[0] = '\\';
-			rp[1] = '\\';
-			rp[2] = '\\';
-			rp[3] = '\\';
-			rp += 4;
+			if (!std_strings)
+			{
+				*rp++ = '\\';
+				*rp++ = '\\';
+			}
+			*rp++ = '\\';
+			*rp++ = '\\';
 		}
 		else
 			*rp++ = *vp;
@@ -2349,6 +2444,25 @@ PQescapeBytea(const unsigned char *bintext, size_t binlen, size_t *bytealen)
 	return result;
 }
 
+unsigned char *
+PQescapeByteaConn(PGconn *conn,
+				  const unsigned char *from, size_t from_length,
+				  size_t *to_length)
+{
+	if (!conn)
+		return NULL;
+	return PQescapeByteaInternal(conn, from, from_length, to_length,
+								 conn->std_strings);
+}
+
+unsigned char *
+PQescapeBytea(const unsigned char *from, size_t from_length, size_t *to_length)
+{
+	return PQescapeByteaInternal(NULL, from, from_length, to_length,
+								 static_std_strings);
+}
+
+
 #define ISFIRSTOCTDIGIT(CH) ((CH) >= '0' && (CH) <= '3')
 #define ISOCTDIGIT(CH) ((CH) >= '0' && (CH) <= '7')
 #define OCTVAL(CH) ((CH) - '0')
@@ -2358,7 +2472,7 @@ PQescapeBytea(const unsigned char *bintext, size_t binlen, size_t *bytealen)
  *		of a bytea, strtext, into binary, filling a buffer. It returns a
  *		pointer to the buffer (or NULL on error), and the size of the
  *		buffer in retbuflen. The pointer may subsequently be used as an
- *		argument to the function free(3). It is the reverse of PQescapeBytea.
+ *		argument to the function PQfreemem.
  *
  *		The following transformations are made:
  *		\\	 == ASCII 92 == \