Avoid regression in the size of XML input that we will accept.

tglsfdc · ewie · tglsfdc · commit 589d6e6408b4 · 2025-07-28T16:50:42.000-04:00
This mostly reverts commit 6082b3d, "Use xmlParseInNodeContext not xmlParseBalancedChunkMemory". It turns out that xmlParseInNodeContext will reject text chunks exceeding 10MB, while (in most libxml2 versions) xmlParseBalancedChunkMemory will not. The bleeding-edge libxml2 bug that we needed to work around a year ago is presumably no longer a factor, and the argument that xmlParseBalancedChunkMemory is semi-deprecated is not enough to justify a functionality regression. Hence, go back to doing it the old way. Reported-by: Michael Paquier <michael@paquier.xyz> Author: Michael Paquier <michael@paquier.xyz> Co-authored-by: Erik Wienhold <ewie@ewie.name> Reviewed-by: Tom Lane <tgl@sss.pgh.pa.us> Discussion: https://postgr.es/m/aIGknLuc8b8ega2X@paquier.xyz Backpatch-through: 13
diff --git a/src/backend/utils/adt/xml.c b/src/backend/utils/adt/xml.c
@@ -1529,6 +1529,7 @@ xml_parse(text *data, XmlOptionType xmloption_arg, bool preserve_whitespace,
 	PgXmlErrorContext *xmlerrcxt;
 	volatile xmlParserCtxtPtr ctxt = NULL;
 	volatile xmlDocPtr doc = NULL;
+	volatile int save_keep_blanks = -1;
 
 	len = VARSIZE_ANY_EXHDR(data);	/* will be useful later */
 	string = xml_text2xmlChar(data);
@@ -1545,7 +1546,6 @@ xml_parse(text *data, XmlOptionType xmloption_arg, bool preserve_whitespace,
 	PG_TRY();
 	{
 		bool		parse_as_document = false;
-		int			options;
 		int			res_code;
 		size_t		count = 0;
 		xmlChar    *version = NULL;
@@ -1571,25 +1571,28 @@ xml_parse(text *data, XmlOptionType xmloption_arg, bool preserve_whitespace,
 				parse_as_document = true;
 		}
 
-		/*
-		 * Select parse options.
-		 *
-		 * Note that here we try to apply DTD defaults (XML_PARSE_DTDATTR)
-		 * according to SQL/XML:2008 GR 10.16.7.d: 'Default values defined by
-		 * internal DTD are applied'.  As for external DTDs, we try to support
-		 * them too (see SQL/XML:2008 GR 10.16.7.e), but that doesn't really
-		 * happen because xmlPgEntityLoader prevents it.
-		 */
-		options = XML_PARSE_NOENT | XML_PARSE_DTDATTR
-			| (preserve_whitespace ? 0 : XML_PARSE_NOBLANKS);
-
 		if (parse_as_document)
 		{
+			int			options;
+
+			/* set up parser context used by xmlCtxtReadDoc */
 			ctxt = xmlNewParserCtxt();
 			if (ctxt == NULL || xmlerrcxt->err_occurred)
 				xml_ereport(xmlerrcxt, ERROR, ERRCODE_OUT_OF_MEMORY,
 							"could not allocate parser context");
 
+			/*
+			 * Select parse options.
+			 *
+			 * Note that here we try to apply DTD defaults (XML_PARSE_DTDATTR)
+			 * according to SQL/XML:2008 GR 10.16.7.d: 'Default values defined
+			 * by internal DTD are applied'.  As for external DTDs, we try to
+			 * support them too (see SQL/XML:2008 GR 10.16.7.e), but that
+			 * doesn't really happen because xmlPgEntityLoader prevents it.
+			 */
+			options = XML_PARSE_NOENT | XML_PARSE_DTDATTR
+				| (preserve_whitespace ? 0 : XML_PARSE_NOBLANKS);
+
 			doc = xmlCtxtReadDoc(ctxt, utf8string,
 								 NULL,	/* no URL */
 								 "UTF-8",
@@ -1608,43 +1611,36 @@ xml_parse(text *data, XmlOptionType xmloption_arg, bool preserve_whitespace,
 		}
 		else
 		{
-			xmlNodePtr	root;
-
-			/* set up document with empty root node to be the context node */
+			/* set up document that xmlParseBalancedChunkMemory will add to */
 			doc = xmlNewDoc(version);
 			Assert(doc->encoding == NULL);
 			doc->encoding = xmlStrdup((const xmlChar *) "UTF-8");
 			doc->standalone = standalone;
 
-			root = xmlNewNode(NULL, (const xmlChar *) "content-root");
-			if (root == NULL || xmlerrcxt->err_occurred)
-				xml_ereport(xmlerrcxt, ERROR, ERRCODE_OUT_OF_MEMORY,
-							"could not allocate xml node");
-			/* This attaches root to doc, so we need not free it separately. */
-			xmlDocSetRootElement(doc, root);
+			/* set parse options --- have to do this the ugly way */
+			save_keep_blanks = xmlKeepBlanksDefault(preserve_whitespace ? 1 : 0);
 
 			/* allow empty content */
 			if (*(utf8string + count))
 			{
 				xmlNodePtr	node_list = NULL;
-				xmlParserErrors res;
 
-				res = xmlParseInNodeContext(root,
-											(char *) utf8string + count,
-											strlen((char *) utf8string + count),
-											options,
-											&node_list);
+				res_code = xmlParseBalancedChunkMemory(doc, NULL, NULL, 0,
+													   utf8string + count,
+													   &node_list);
 
 				xmlFreeNodeList(node_list);
 
-				if (res != XML_ERR_OK || xmlerrcxt->err_occurred)
+				if (res_code != 0 || xmlerrcxt->err_occurred)
 					xml_ereport(xmlerrcxt, ERROR, ERRCODE_INVALID_XML_CONTENT,
 								"invalid XML content");
 			}
 		}
 	}
 	PG_CATCH();
 	{
+		if (save_keep_blanks != -1)
+			xmlKeepBlanksDefault(save_keep_blanks);
 		if (doc != NULL)
 			xmlFreeDoc(doc);
 		if (ctxt != NULL)
@@ -1656,6 +1652,9 @@ xml_parse(text *data, XmlOptionType xmloption_arg, bool preserve_whitespace,
 	}
 	PG_END_TRY();
 
+	if (save_keep_blanks != -1)
+		xmlKeepBlanksDefault(save_keep_blanks);
+
 	if (ctxt != NULL)
 		xmlFreeParserCtxt(ctxt);
 
