Fix pg_dump to do the right thing when escaping the contents of large objects.

The previous implementation got it right in most cases but failed in one:
if you pg_dump into an archive with standard_conforming_strings enabled, then
pg_restore to a script file (not directly to a database), the script will set
standard_conforming_strings = on but then emit large object data as
nonstandardly-escaped strings.

At the moment the code is made to emit hex-format bytea strings when dumping
to a script file.  We might want to change to old-style escaping for backwards
compatibility, but that would be slower and bulkier.  If we do, it's just a
matter of reimplementing appendByteaLiteral().

This has been broken for a long time, but given the lack of field complaints
I'm not going to worry about back-patching.

Author: tglsfdc

src/bin/pg_dump/dumputils.c

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1996-2009, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/bin/pg_dump/dumputils.c,v 1.47 2009/07/14 20:24:10 tgl Exp $
+ * $PostgreSQL: pgsql/src/bin/pg_dump/dumputils.c,v 1.48 2009/08/04 21:56:08 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -325,6 +325,55 @@ appendStringLiteralDQ(PQExpBuffer buf, const char *str, const char *dqprefix)
 }
 
 
+/*
+ * Convert a bytea value (presented as raw bytes) to an SQL string literal
+ * and append it to the given buffer.  We assume the specified
+ * standard_conforming_strings setting.
+ *
+ * This is needed in situations where we do not have a PGconn available.
+ * Where we do, PQescapeByteaConn is a better choice.
+ */
+void
+appendByteaLiteral(PQExpBuffer buf, const unsigned char *str, size_t length,
+				   bool std_strings)
+{
+	const unsigned char *source = str;
+	char	   *target;
+
+	static const char hextbl[] = "0123456789abcdef";
+
+	/*
+	 * This implementation is hard-wired to produce hex-format output.
+	 * We do not know the server version the output will be loaded into,
+	 * so making an intelligent format choice is impossible.  It might be
+	 * better to always use the old escaped format.
+	 */
+	if (!enlargePQExpBuffer(buf, 2 * length + 5))
+		return;
+
+	target = buf->data + buf->len;
+	*target++ = '\'';
+	if (!std_strings)
+		*target++ = '\\';
+	*target++ = '\\';
+	*target++ = 'x';
+
+	while (length-- > 0)
+	{
+		unsigned char c = *source++;
+
+		*target++ = hextbl[(c >> 4) & 0xF];
+		*target++ = hextbl[c & 0xF];
+	}
+
+	/* Write the terminating quote and NUL character. */
+	*target++ = '\'';
+	*target = '\0';
+
+	buf->len = target - buf->data;
+}
+
+
 /*
  * Convert backend's version string into a number.
  */

src/bin/pg_dump/dumputils.h

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1996-2009, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/bin/pg_dump/dumputils.h,v 1.24 2009/03/11 03:33:29 adunstan Exp $
+ * $PostgreSQL: pgsql/src/bin/pg_dump/dumputils.h,v 1.25 2009/08/04 21:56:08 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -27,6 +27,9 @@ extern void appendStringLiteralConn(PQExpBuffer buf, const char *str,
 						PGconn *conn);
 extern void appendStringLiteralDQ(PQExpBuffer buf, const char *str,
 					  const char *dqprefix);
+extern void appendByteaLiteral(PQExpBuffer buf,
+							   const unsigned char *str, size_t length,
+							   bool std_strings);
 extern int	parse_version(const char *versionString);
 extern bool parsePGArray(const char *atext, char ***itemarray, int *nitems);
 extern bool buildACLCommands(const char *name, const char *subname,

src/bin/pg_dump/pg_backup_archiver.c

@@ -15,7 +15,7 @@
  *
  *
  * IDENTIFICATION
- *		$PostgreSQL: pgsql/src/bin/pg_dump/pg_backup_archiver.c,v 1.173 2009/07/21 21:46:10 tgl Exp $
+ *		$PostgreSQL: pgsql/src/bin/pg_dump/pg_backup_archiver.c,v 1.174 2009/08/04 21:56:08 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -1249,20 +1249,19 @@ dump_lo_buf(ArchiveHandle *AH)
 	}
 	else
 	{
-		unsigned char *str;
-		size_t		len;
+		PQExpBuffer buf = createPQExpBuffer();
 
-		str = PQescapeBytea((const unsigned char *) AH->lo_buf,
-							AH->lo_buf_used, &len);
-		if (!str)
-			die_horribly(AH, modulename, "out of memory\n");
+		appendByteaLiteralAHX(buf,
+							  (const unsigned char *) AH->lo_buf,
+							  AH->lo_buf_used,
+							  AH);
 
 		/* Hack: turn off writingBlob so ahwrite doesn't recurse to here */
 		AH->writingBlob = 0;
-		ahprintf(AH, "SELECT pg_catalog.lowrite(0, '%s');\n", str);
+		ahprintf(AH, "SELECT pg_catalog.lowrite(0, %s);\n", buf->data);
 		AH->writingBlob = 1;
 
-		free(str);
+		destroyPQExpBuffer(buf);
 	}
 	AH->lo_buf_used = 0;
 }

src/bin/pg_dump/pg_backup_archiver.h

@@ -17,7 +17,7 @@
  *
  *
  * IDENTIFICATION
- *		$PostgreSQL: pgsql/src/bin/pg_dump/pg_backup_archiver.h,v 1.80 2009/07/21 21:46:10 tgl Exp $
+ *		$PostgreSQL: pgsql/src/bin/pg_dump/pg_backup_archiver.h,v 1.81 2009/08/04 21:56:09 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -342,6 +342,9 @@ extern bool checkSeek(FILE *fp);
 #define appendStringLiteralAHX(buf,str,AH) \
 	appendStringLiteral(buf, str, (AH)->public.encoding, (AH)->public.std_strings)
 
+#define appendByteaLiteralAHX(buf,str,len,AH) \
+	appendByteaLiteral(buf, str, len, (AH)->public.std_strings)
+
 /*
  * Mandatory routines for each supported format
  */

src/bin/pg_dump/pg_backup_null.c

@@ -17,12 +17,13 @@
  *
  *
  * IDENTIFICATION
- *		$PostgreSQL: pgsql/src/bin/pg_dump/pg_backup_null.c,v 1.21 2009/07/21 21:46:10 tgl Exp $
+ *		$PostgreSQL: pgsql/src/bin/pg_dump/pg_backup_null.c,v 1.22 2009/08/04 21:56:09 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
 
 #include "pg_backup_archiver.h"
+#include "dumputils.h"
 
 #include <unistd.h>				/* for dup */
 
@@ -101,16 +102,16 @@ _WriteBlobData(ArchiveHandle *AH, const void *data, size_t dLen)
 {
 	if (dLen > 0)
 	{
-		unsigned char *str;
-		size_t		len;
+		PQExpBuffer buf = createPQExpBuffer();
 
-		str = PQescapeBytea((const unsigned char *) data, dLen, &len);
-		if (!str)
-			die_horribly(AH, NULL, "out of memory\n");
+		appendByteaLiteralAHX(buf,
+							  (const unsigned char *) data,
+							  dLen,
+							  AH);
 
-		ahprintf(AH, "SELECT pg_catalog.lowrite(0, '%s');\n", str);
+		ahprintf(AH, "SELECT pg_catalog.lowrite(0, %s);\n", buf->data);
 
-		free(str);
+		destroyPQExpBuffer(buf);
 	}
 	return dLen;
 }