From 8832f0f35896c16efd7de4cf35ef97348c90f2f6 Mon Sep 17 00:00:00 2001
From: Peter Eisentraut <peter_e@gmx.net>
Date: Fri, 29 Dec 2006 10:50:22 +0000
Subject: [PATCH] De-escape XML names when reverse-compiling XML expressions.

---
 src/backend/utils/adt/ruleutils.c | 12 ++----
 src/backend/utils/adt/xml.c       | 72 ++++++++++++++++++++++++++++++-
 src/include/utils/xml.h           |  3 +-
 3 files changed, 76 insertions(+), 11 deletions(-)

diff --git a/src/backend/utils/adt/ruleutils.c b/src/backend/utils/adt/ruleutils.c
index 699b4a9370..136f1386cf 100644
--- a/src/backend/utils/adt/ruleutils.c
+++ b/src/backend/utils/adt/ruleutils.c
@@ -2,7 +2,7 @@
  * ruleutils.c	- Functions to convert stored expressions/querytrees
  *				back to source text
  *
- *	  $PostgreSQL: pgsql/src/backend/utils/adt/ruleutils.c,v 1.238 2006/12/24 00:29:19 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/adt/ruleutils.c,v 1.239 2006/12/29 10:50:22 petere Exp $
  **********************************************************************/
 
 #include "postgres.h"
@@ -3810,11 +3810,8 @@ get_rule_expr(Node *node, deparse_context *context,
 				}
 				if (xexpr->name)
 				{
-					/*
-					 * XXX need to de-escape the name
-					 */
 					appendStringInfo(buf, "NAME %s",
-									 quote_identifier(xexpr->name));
+									 quote_identifier(map_xml_name_to_sql_identifier(xexpr->name)));
 					needcomma = true;
 				}
 				if (xexpr->named_args)
@@ -3834,11 +3831,8 @@ get_rule_expr(Node *node, deparse_context *context,
 						if (needcomma)
 							appendStringInfoString(buf, ", ");
 						get_rule_expr((Node *) e, context, true);
-						/*
-						 * XXX need to de-escape the name
-						 */
 						appendStringInfo(buf, " AS %s",
-										 quote_identifier(argname));
+										 quote_identifier(map_xml_name_to_sql_identifier(argname)));
 						needcomma = true;
 					}
 					if (xexpr->op != IS_XMLFOREST)
diff --git a/src/backend/utils/adt/xml.c b/src/backend/utils/adt/xml.c
index 6cde8d6aa4..6f4c87f824 100644
--- a/src/backend/utils/adt/xml.c
+++ b/src/backend/utils/adt/xml.c
@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2006, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/backend/utils/adt/xml.c,v 1.7 2006/12/28 14:28:36 petere Exp $
+ * $PostgreSQL: pgsql/src/backend/utils/adt/xml.c,v 1.8 2006/12/29 10:50:22 petere Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -882,6 +882,42 @@ sqlchar_to_unicode(char *s)
 }
 
 
+static char *
+unicode_to_sqlchar(pg_wchar c)
+{
+	char utf8string[4] = { '\0', '\0', '\0', '\0' };
+
+	if (c <= 0x7F)
+	{
+		utf8string[0] = c;
+	}
+	else if (c <= 0x7FF)
+	{
+		utf8string[0] = 0xC0 | ((c >> 6) & 0x1F);
+		utf8string[1] = 0x80 | (c & 0x3F);
+	}
+	else if (c <= 0xFFFF)
+	{
+		utf8string[0] = 0xE0 | ((c >> 12) & 0x0F);
+		utf8string[1] = 0x80 | ((c >> 6) & 0x3F);
+		utf8string[2] = 0x80 | (c & 0x3F);
+	}
+	else
+	{
+		utf8string[0] = 0xF0 | ((c >> 18) & 0x07);
+		utf8string[1] = 0x80 | ((c >> 12) & 0x3F);
+		utf8string[2] = 0x80 | ((c >> 6) & 0x3F);
+		utf8string[3] = 0x80 | (c & 0x3F);
+
+	}
+
+	return  (char *) pg_do_encoding_conversion((unsigned char *) utf8string,
+											   pg_mblen(utf8string),
+											   PG_UTF8,
+											   GetDatabaseEncoding());
+}
+
+
 static bool
 is_valid_xml_namefirst(pg_wchar c)
 {
@@ -949,3 +985,37 @@ map_sql_identifier_to_xml_name(char *ident, bool fully_escaped)
 	return NULL;
 #endif /* not USE_LIBXML */
 }
+
+
+/*
+ * The inverse; see SQL/XML:2003 section 9.17.
+ */
+char *
+map_xml_name_to_sql_identifier(char *name)
+{
+	StringInfoData buf;
+	char *p;
+
+	initStringInfo(&buf);
+
+	for (p = name; *p; p += pg_mblen(p))
+	{
+		if (*p == '_' && *(p+1) == 'x'
+			&& isxdigit((unsigned char) *(p+2))
+			&& isxdigit((unsigned char) *(p+3))
+			&& isxdigit((unsigned char) *(p+4))
+			&& isxdigit((unsigned char) *(p+5))
+			&& *(p+6) == '_')
+		{
+			unsigned int u;
+
+			sscanf(p + 2, "%X", &u);
+			appendStringInfoString(&buf, unicode_to_sqlchar(u));
+			p += 6;
+		}
+		else
+			appendBinaryStringInfo(&buf, p, pg_mblen(p));
+	}
+
+	return buf.data;
+}
diff --git a/src/include/utils/xml.h b/src/include/utils/xml.h
index ca50142032..20666a48cc 100644
--- a/src/include/utils/xml.h
+++ b/src/include/utils/xml.h
@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2006, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/utils/xml.h,v 1.4 2006/12/28 14:28:36 petere Exp $
+ * $PostgreSQL: pgsql/src/include/utils/xml.h,v 1.5 2006/12/29 10:50:22 petere Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -37,5 +37,6 @@ extern xmltype *xmlpi(char *target, text *arg);
 extern xmltype *xmlroot(xmltype *data, text *version, int standalone);
 
 extern char *map_sql_identifier_to_xml_name(char *ident, bool fully_escaped);
+extern char *map_xml_name_to_sql_identifier(char *name);
 
 #endif /* XML_H */