From 46fb15f48a2d76beccf8d422f699373b60e954f6 Mon Sep 17 00:00:00 2001 From: Noah Misch Date: Sat, 11 Nov 2017 11:10:53 -0800 Subject: Ignore XML declaration in xpath_internal(), for UTF8 databases. When a value contained an XML declaration naming some other encoding, this function interpreted UTF8 bytes as the named encoding, yielding mojibake. xml_parse() already has similar logic. This would be necessary but not sufficient for non-UTF8 databases, so preserve behavior there until the xpath facility can support such databases comprehensively. Back-patch to 9.3 (all supported versions). Pavel Stehule and Noah Misch Discussion: https://postgr.es/m/CAFj8pRC-dM=tT=QkGi+Achkm+gwPmjyOayGuUfXVumCxkDgYWg@mail.gmail.com --- src/backend/utils/adt/xml.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (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 f5348b34657..8253e508fc6 100644 --- a/src/backend/utils/adt/xml.c +++ b/src/backend/utils/adt/xml.c @@ -3778,6 +3778,7 @@ xpath_internal(text *xpath_expr_text, xmltype *data, ArrayType *namespaces, int32 xpath_len; xmlChar *string; xmlChar *xpath_expr; + size_t xmldecl_len = 0; int i; int ndim; Datum *ns_names_uris; @@ -3838,6 +3839,16 @@ xpath_internal(text *xpath_expr_text, xmltype *data, ArrayType *namespaces, memcpy(xpath_expr, VARDATA(xpath_expr_text), xpath_len); xpath_expr[xpath_len] = '\0'; + /* + * In a UTF8 database, skip any xml declaration, which might assert + * another encoding. Ignore parse_xml_decl() failure, letting + * xmlCtxtReadMemory() report parse errors. Documentation disclaims + * xpath() support for non-ASCII data in non-UTF8 databases, so leave + * those scenarios bug-compatible with historical behavior. + */ + if (GetDatabaseEncoding() == PG_UTF8) + parse_xml_decl(string, &xmldecl_len, NULL, NULL, NULL); + xmlerrcxt = pg_xml_init(PG_XML_STRICTNESS_ALL); PG_TRY(); @@ -3852,7 +3863,8 @@ xpath_internal(text *xpath_expr_text, xmltype *data, ArrayType *namespaces, if (ctxt == NULL || xmlerrcxt->err_occurred) xml_ereport(xmlerrcxt, ERROR, ERRCODE_OUT_OF_MEMORY, "could not allocate parser context"); - doc = xmlCtxtReadMemory(ctxt, (char *) string, len, NULL, NULL, 0); + doc = xmlCtxtReadMemory(ctxt, (char *) string + xmldecl_len, + len - xmldecl_len, NULL, NULL, 0); if (doc == NULL || xmlerrcxt->err_occurred) xml_ereport(xmlerrcxt, ERROR, ERRCODE_INVALID_XML_DOCUMENT, "could not parse XML document"); -- cgit v1.2.3