From f85c91a1867b45742bb28e4578ca2b4a0976383f Mon Sep 17 00:00:00 2001 From: Tom Lane Date: Wed, 10 Jul 2024 20:15:52 -0400 Subject: Make our back branches compatible with libxml2 2.13.x. This back-patches HEAD commits 066e8ac6e, 6082b3d5d, e7192486d, and 896cd266f into supported branches. Changes: * Use xmlAddChildList not xmlAddChild in XMLSERIALIZE (affects v16 and up only). This was a flat-out coding mistake that we got away with due to lax checking in previous versions of xmlAddChild. * Use xmlParseInNodeContext not xmlParseBalancedChunkMemory. This is to dodge a bug in xmlParseBalancedChunkMemory in libxm2 releases 2.13.0-2.13.2. While that bug is now fixed upstream and will probably never be seen in any production-oriented distro, it is currently a problem on some more-bleeding-edge-friendly platforms. * Suppress "chunk is not well balanced" errors from libxml2, unless it is the only error. This eliminates an error-reporting discrepancy between 2.13 and older releases. This error is almost always redundant with previous errors, if not flat-out inappropriate, which is why 2.13 changed the behavior and why nobody's likely to miss it. Erik Wienhold and Tom Lane, per report from Frank Streitzig. Discussion: https://postgr.es/m/trinity-b0161630-d230-4598-9ebc-7a23acdb37cb-1720186432160@3c-app-gmx-bap25 Discussion: https://postgr.es/m/trinity-361ba18b-541a-4fe7-bc63-655ae3a7d599-1720259822452@3c-app-gmx-bs01 --- src/backend/utils/adt/xml.c | 90 +++++++++++++++++++++++++++++++++------------ 1 file changed, 66 insertions(+), 24 deletions(-) (limited to 'src/backend/utils/adt/xml.c') diff --git a/src/backend/utils/adt/xml.c b/src/backend/utils/adt/xml.c index 9f4e7750030..0255349aa43 100644 --- a/src/backend/utils/adt/xml.c +++ b/src/backend/utils/adt/xml.c @@ -736,7 +736,7 @@ xmltotext_with_options(xmltype *data, XmlOptionType xmloption_arg, bool indent) /* This attaches root to doc, so we need not free it separately. */ xmlDocSetRootElement(doc, root); - xmlAddChild(root, content_nodes); + xmlAddChildList(root, content_nodes); /* * We use this node to insert newlines in the dump. Note: in at @@ -1675,9 +1675,9 @@ xml_doctype_in_content(const xmlChar *str) * XmlOptionType actually used to parse the input (typically the same as * xmloption_arg, but a DOCTYPE node in the input can force DOCUMENT mode). * - * If parsed_nodes isn't NULL and the input is not an XML document, the list - * of parsed nodes from the xmlParseBalancedChunkMemory call will be returned - * to *parsed_nodes. + * If parsed_nodes isn't NULL and we parse in CONTENT mode, the list + * of parsed nodes from the xmlParseInNodeContext call will be returned + * to *parsed_nodes. (It is caller's responsibility to free that.) * * Errors normally result in ereport(ERROR), but if escontext is an * ErrorSaveContext, then "safe" errors are reported there instead, and the @@ -1729,6 +1729,7 @@ xml_parse(text *data, XmlOptionType xmloption_arg, PG_TRY(); { bool parse_as_document = false; + int options; int res_code; size_t count = 0; xmlChar *version = NULL; @@ -1737,11 +1738,6 @@ xml_parse(text *data, XmlOptionType xmloption_arg, /* Any errors here are reported as hard ereport's */ xmlInitParser(); - ctxt = xmlNewParserCtxt(); - if (ctxt == NULL || xmlerrcxt->err_occurred) - xml_ereport(xmlerrcxt, ERROR, ERRCODE_OUT_OF_MEMORY, - "could not allocate parser context"); - /* Decide whether to parse as document or content */ if (xmloption_arg == XMLOPTION_DOCUMENT) parse_as_document = true; @@ -1764,6 +1760,18 @@ xml_parse(text *data, XmlOptionType xmloption_arg, 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); + /* initialize output parameters */ if (parsed_xmloptiontype != NULL) *parsed_xmloptiontype = parse_as_document ? XMLOPTION_DOCUMENT : @@ -1773,18 +1781,16 @@ xml_parse(text *data, XmlOptionType xmloption_arg, if (parse_as_document) { - /* - * 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) - */ + ctxt = xmlNewParserCtxt(); + if (ctxt == NULL || xmlerrcxt->err_occurred) + xml_ereport(xmlerrcxt, ERROR, ERRCODE_OUT_OF_MEMORY, + "could not allocate parser context"); + doc = xmlCtxtReadDoc(ctxt, utf8string, - NULL, + NULL, /* no URL */ "UTF-8", - XML_PARSE_NOENT | XML_PARSE_DTDATTR - | (preserve_whitespace ? 0 : XML_PARSE_NOBLANKS)); + options); + if (doc == NULL || xmlerrcxt->err_occurred) { /* Use original option to decide which error code to report */ @@ -1801,6 +1807,9 @@ xml_parse(text *data, XmlOptionType xmloption_arg, } else { + xmlNodePtr root; + + /* set up document with empty root node to be the context node */ doc = xmlNewDoc(version); if (doc == NULL || xmlerrcxt->err_occurred) xml_ereport(xmlerrcxt, ERROR, ERRCODE_OUT_OF_MEMORY, @@ -1813,19 +1822,38 @@ xml_parse(text *data, XmlOptionType xmloption_arg, "could not allocate XML document"); 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); + /* allow empty content */ if (*(utf8string + count)) { - res_code = xmlParseBalancedChunkMemory(doc, NULL, NULL, 0, - utf8string + count, - parsed_nodes); - if (res_code != 0 || xmlerrcxt->err_occurred) + xmlNodePtr node_list = NULL; + xmlParserErrors res; + + res = xmlParseInNodeContext(root, + (char *) utf8string + count, + strlen((char *) utf8string + count), + options, + &node_list); + + if (res != XML_ERR_OK || xmlerrcxt->err_occurred) { + xmlFreeNodeList(node_list); xml_errsave(escontext, xmlerrcxt, ERRCODE_INVALID_XML_CONTENT, "invalid XML content"); goto fail; } + + if (parsed_nodes != NULL) + *parsed_nodes = node_list; + else + xmlFreeNodeList(node_list); } } @@ -1845,7 +1873,8 @@ fail: } PG_END_TRY(); - xmlFreeParserCtxt(ctxt); + if (ctxt != NULL) + xmlFreeParserCtxt(ctxt); pg_xml_done(xmlerrcxt, false); @@ -2064,6 +2093,19 @@ xml_errorHandler(void *data, PgXmlErrorPtr error) switch (domain) { case XML_FROM_PARSER: + + /* + * XML_ERR_NOT_WELL_BALANCED is typically reported after some + * other, more on-point error. Furthermore, libxml2 2.13 reports + * it under a completely different set of rules than prior + * versions. To avoid cross-version behavioral differences, + * suppress it so long as we already logged some error. + */ + if (error->code == XML_ERR_NOT_WELL_BALANCED && + xmlerrcxt->err_occurred) + return; + /* fall through */ + case XML_FROM_NONE: case XML_FROM_MEMORY: case XML_FROM_IO: -- cgit v1.2.3