Further fixes for quoted-list GUC values in pg_dump and ruleutils.c.

Commits 742869946 et al turn out to be a couple bricks shy of a load.
We were dumping the stored values of GUC_LIST_QUOTE variables as they
appear in proconfig or setconfig catalog columns.  However, although that
quoting rule looks a lot like SQL-identifier double quotes, there are two
critical differences: empty strings ("") are legal, and depending on which
variable you're considering, values longer than NAMEDATALEN might be valid
too.  So the current technique fails altogether on empty-string list
entries (as reported by Steven Winfield in bug #15248) and it also risks
truncating file pathnames during dump/reload of GUC values that are lists
of pathnames.

To fix, split the stored value without any downcasing or truncation,
and then emit each element as a SQL string literal.

This is a tad annoying, because we now have three copies of the
comma-separated-string splitting logic in varlena.c as well as a fourth
one in dumputils.c.  (Not to mention the randomly-different-from-those
splitting logic in libpq...)  I looked at unifying these, but it would
be rather a mess unless we're willing to tweak the API definitions of
SplitIdentifierString, SplitDirectoriesString, or both.  That might be
worth doing in future; but it seems pretty unsafe for a back-patched
bug fix, so for now accept the duplication.

Back-patch to all supported branches, as the previous fix was.

Discussion: https://postgr.es/m/7585.1529435872@sss.pgh.pa.us

1 files changed, 111 insertions, 0 deletions

diff --git a/src/bin/pg_dump/dumputils.c b/src/bin/pg_dump/dumputils.c
index 9888718aab1..cb0df7c8237 100644
--- a/src/bin/pg_dump/dumputils.c
+++ b/src/bin/pg_dump/dumputils.c
@@ -14,6 +14,8 @@
  */
 #include "postgres_fe.h"
 
+#include <ctype.h>
+
 #include "dumputils.h"
 #include "fe_utils/string_utils.h"
 
@@ -869,3 +871,112 @@ variable_is_guc_list_quote(const char *name)
 	else
 		return false;
 }
+
+/*
+ * SplitGUCList --- parse a string containing identifiers or file names
+ *
+ * This is used to split the value of a GUC_LIST_QUOTE GUC variable, without
+ * presuming whether the elements will be taken as identifiers or file names.
+ * See comparable code in src/backend/utils/adt/varlena.c.
+ *
+ * Inputs:
+ *	rawstring: the input string; must be overwritable!	On return, it's
+ *			   been modified to contain the separated identifiers.
+ *	separator: the separator punctuation expected between identifiers
+ *			   (typically '.' or ',').  Whitespace may also appear around
+ *			   identifiers.
+ * Outputs:
+ *	namelist: receives a malloc'd, null-terminated array of pointers to
+ *			  identifiers within rawstring.  Caller should free this
+ *			  even on error return.
+ *
+ * Returns true if okay, false if there is a syntax error in the string.
+ */
+bool
+SplitGUCList(char *rawstring, char separator,
+			 char ***namelist)
+{
+	char	   *nextp = rawstring;
+	bool		done = false;
+	char	  **nextptr;
+
+	/*
+	 * Since we disallow empty identifiers, this is a conservative
+	 * overestimate of the number of pointers we could need.  Allow one for
+	 * list terminator.
+	 */
+	*namelist = nextptr = (char **)
+		pg_malloc((strlen(rawstring) / 2 + 2) * sizeof(char *));
+	*nextptr = NULL;
+
+	while (isspace((unsigned char) *nextp))
+		nextp++;				/* skip leading whitespace */
+
+	if (*nextp == '\0')
+		return true;			/* allow empty string */
+
+	/* At the top of the loop, we are at start of a new identifier. */
+	do
+	{
+		char	   *curname;
+		char	   *endp;
+
+		if (*nextp == '"')
+		{
+			/* Quoted name --- collapse quote-quote pairs */
+			curname = nextp + 1;
+			for (;;)
+			{
+				endp = strchr(nextp + 1, '"');
+				if (endp == NULL)
+					return false;	/* mismatched quotes */
+				if (endp[1] != '"')
+					break;		/* found end of quoted name */
+				/* Collapse adjacent quotes into one quote, and look again */
+				memmove(endp, endp + 1, strlen(endp));
+				nextp = endp;
+			}
+			/* endp now points at the terminating quote */
+			nextp = endp + 1;
+		}
+		else
+		{
+			/* Unquoted name --- extends to separator or whitespace */
+			curname = nextp;
+			while (*nextp && *nextp != separator &&
+				   !isspace((unsigned char) *nextp))
+				nextp++;
+			endp = nextp;
+			if (curname == nextp)
+				return false;	/* empty unquoted name not allowed */
+		}
+
+		while (isspace((unsigned char) *nextp))
+			nextp++;			/* skip trailing whitespace */
+
+		if (*nextp == separator)
+		{
+			nextp++;
+			while (isspace((unsigned char) *nextp))
+				nextp++;		/* skip leading whitespace for next */
+			/* we expect another name, so done remains false */
+		}
+		else if (*nextp == '\0')
+			done = true;
+		else
+			return false;		/* invalid syntax */
+
+		/* Now safe to overwrite separator with a null */
+		*endp = '\0';
+
+		/*
+		 * Finished isolating current name --- add it to output array
+		 */
+		*nextptr++ = curname;
+
+		/* Loop back if we didn't reach end of string */
+	} while (!done);
+
+	*nextptr = NULL;
+	return true;
+}