Fix minor deficiencies in XMLTABLE, xpath(), xmlexists()

Correctly process nodes of more types than previously.  In some cases,
nodes were being ignored (nothing was output); in other cases, trying to
return them resulted in errors about unrecognized nodes.  In yet other
cases, necessary escaping (of XML special characters) was not being
done.  Fix all those (as far as the authors could find) and add
regression tests cases verifying the new behavior.

I (Álvaro) was of two minds about backpatching these changes.  They do
seem bugfixes that would benefit most users of the affected functions;
but on the other hand it would change established behavior in minor
releases, so it seems prudent not to.

Authors: Pavel Stehule, Markus Winand, Chapman Flack
Discussion:
   https://postgr.es/m/CAFj8pRA6J25CtAZ2TuRvxK3gat7-bBUYh0rfE2yM7Hj9GD14Dg@mail.gmail.com
   https://postgr.es/m/8BDB0627-2105-4564-AA76-7849F028B96E@winand.at

The elephant in the room as pointed out by Chapman Flack, not fixed in
this commit, is that we still have XMLTABLE operating on XPath 1.0
instead of the standard-mandated XQuery (or even its subset XPath 2.0).
Fixing that is a major undertaking, however.

1 files changed, 86 insertions, 69 deletions

diff --git a/src/backend/utils/adt/xml.c b/src/backend/utils/adt/xml.c
index f36aab899a4..28b3eaaa201 100644
--- a/src/backend/utils/adt/xml.c
+++ b/src/backend/utils/adt/xml.c
@@ -1177,6 +1177,36 @@ pg_xmlCharStrndup(const char *str, size_t len)
 }
 
 /*
+ * Copy xmlChar string to PostgreSQL-owned memory, freeing the input.
+ *
+ * The input xmlChar is freed regardless of success of the copy.
+ */
+static char *
+xml_pstrdup_and_free(xmlChar *str)
+{
+	char	   *result;
+
+	if (str)
+	{
+		PG_TRY();
+		{
+			result = pstrdup((char *) str);
+		}
+		PG_CATCH();
+		{
+			xmlFree(str);
+			PG_RE_THROW();
+		}
+		PG_END_TRY();
+		xmlFree(str);
+	}
+	else
+		result = NULL;
+
+	return result;
+}
+
+/*
  * str is the null-terminated input string.  Remaining arguments are
  * output arguments; each can be NULL if value is not wanted.
  * version and encoding are returned as locally-palloc'd strings.
@@ -3678,15 +3708,17 @@ SPI_sql_row_to_xmlelement(uint64 rownum, StringInfo result, char *tablename,
 #ifdef USE_LIBXML
 
 /*
- * Convert XML node to text (dump subtree in case of element,
- * return value otherwise)
+ * Convert XML node to text.
+ *
+ * For attribute and text nodes, return the escaped text.  For anything else,
+ * dump the whole subtree.
  */
 static text *
 xml_xmlnodetoxmltype(xmlNodePtr cur, PgXmlErrorContext *xmlerrcxt)
 {
 	xmltype    *result;
 
-	if (cur->type == XML_ELEMENT_NODE)
+	if (cur->type != XML_ATTRIBUTE_NODE && cur->type != XML_TEXT_NODE)
 	{
 		xmlBufferPtr buf;
 		xmlNodePtr	cur_copy;
@@ -4479,9 +4511,9 @@ XmlTableGetValue(TableFuncScanState *state, int colnum,
 		/*
 		 * There are four possible cases, depending on the number of nodes
 		 * returned by the XPath expression and the type of the target column:
-		 * a) XPath returns no nodes.  b) One node is returned, and column is
-		 * of type XML.  c) One node, column type other than XML.  d) Multiple
-		 * nodes are returned.
+		 * a) XPath returns no nodes.  b) The target type is XML (return all
+		 * as XML).  For non-XML return types:  c) One node (return content).
+		 * d) Multiple nodes (error).
 		 */
 		if (xpathobj->type == XPATH_NODESET)
 		{
@@ -4494,84 +4526,69 @@ XmlTableGetValue(TableFuncScanState *state, int colnum,
 			{
 				*isnull = true;
 			}
-			else if (count == 1 && typid == XMLOID)
-			{
-				text	   *textstr;
-
-				/* simple case, result is one value */
-				textstr = xml_xmlnodetoxmltype(xpathobj->nodesetval->nodeTab[0],
-											   xtCxt->xmlerrcxt);
-				cstr = text_to_cstring(textstr);
-			}
-			else if (count == 1)
+			else
 			{
-				xmlChar    *str;
-				xmlNodePtr	node;
-
-				/*
-				 * Most nodes (elements and even attributes) store their data
-				 * in children nodes. If they don't have children nodes, it
-				 * means that they are empty (e.g. <element/>). Text nodes and
-				 * CDATA sections are an exception: they don't have children
-				 * but have content in the Text/CDATA node itself.
-				 */
-				node = xpathobj->nodesetval->nodeTab[0];
-				if (node->type != XML_CDATA_SECTION_NODE &&
-					node->type != XML_TEXT_NODE)
-					node = node->xmlChildrenNode;
-
-				str = xmlNodeListGetString(xtCxt->doc, node, 1);
-				if (str != NULL)
+				if (typid == XMLOID)
 				{
-					PG_TRY();
-					{
-						cstr = pstrdup((char *) str);
-					}
-					PG_CATCH();
+					text	   *textstr;
+					StringInfoData str;
+
+					/* Concatenate serialized values */
+					initStringInfo(&str);
+					for (int i = 0; i < count; i++)
 					{
-						xmlFree(str);
-						PG_RE_THROW();
+						textstr =
+							xml_xmlnodetoxmltype(xpathobj->nodesetval->nodeTab[i],
+												 xtCxt->xmlerrcxt);
+
+						appendStringInfoText(&str, textstr);
 					}
-					PG_END_TRY();
-					xmlFree(str);
+					cstr = str.data;
 				}
 				else
 				{
-					/* Ensure mapping of empty tags to PostgreSQL values. */
-					cstr = "";
+					xmlChar    *str;
+
+					if (count > 1)
+						ereport(ERROR,
+								(errcode(ERRCODE_CARDINALITY_VIOLATION),
+								 errmsg("more than one value returned by column XPath expression")));
+
+					str = xmlXPathCastNodeSetToString(xpathobj->nodesetval);
+					cstr = str ? xml_pstrdup_and_free(str) : "";
 				}
 			}
+		}
+		else if (xpathobj->type == XPATH_STRING)
+		{
+			/* Content should be escaped when target will be XML */
+			if (typid == XMLOID)
+				cstr = escape_xml((char *) xpathobj->stringval);
 			else
-			{
-				StringInfoData str;
-				int			i;
+				cstr = (char *) xpathobj->stringval;
+		}
+		else if (xpathobj->type == XPATH_BOOLEAN)
+		{
+			char		typcategory;
+			bool		typispreferred;
+			xmlChar    *str;
 
-				Assert(count > 1);
+			/* Allow implicit casting from boolean to numbers */
+			get_type_category_preferred(typid, &typcategory, &typispreferred);
 
-				/*
-				 * When evaluating the XPath expression returns multiple
-				 * nodes, the result is the concatenation of them all. The
-				 * target type must be XML.
-				 */
-				if (typid != XMLOID)
-					ereport(ERROR,
-							(errcode(ERRCODE_CARDINALITY_VIOLATION),
-							 errmsg("more than one value returned by column XPath expression")));
+			if (typcategory != TYPCATEGORY_NUMERIC)
+				str = xmlXPathCastBooleanToString(xpathobj->boolval);
+			else
+				str = xmlXPathCastNumberToString(xmlXPathCastBooleanToNumber(xpathobj->boolval));
 
-				/* Concatenate serialized values */
-				initStringInfo(&str);
-				for (i = 0; i < count; i++)
-				{
-					appendStringInfoText(&str,
-										 xml_xmlnodetoxmltype(xpathobj->nodesetval->nodeTab[i],
-															  xtCxt->xmlerrcxt));
-				}
-				cstr = str.data;
-			}
+			cstr = xml_pstrdup_and_free(str);
 		}
-		else if (xpathobj->type == XPATH_STRING)
+		else if (xpathobj->type == XPATH_NUMBER)
 		{
-			cstr = (char *) xpathobj->stringval;
+			xmlChar    *str;
+
+			str = xmlXPathCastNumberToString(xpathobj->floatval);
+			cstr = xml_pstrdup_and_free(str);
 		}
 		else
 			elog(ERROR, "unexpected XPath object type %u", xpathobj->type);