diff options
Diffstat (limited to 'src/backend/utils/adt/xml.c')
| -rw-r--r-- | src/backend/utils/adt/xml.c | 14 |
1 files changed, 13 insertions, 1 deletions
diff --git a/src/backend/utils/adt/xml.c b/src/backend/utils/adt/xml.c index 268d577b94b..96f187c6ef4 100644 --- a/src/backend/utils/adt/xml.c +++ b/src/backend/utils/adt/xml.c @@ -3780,6 +3780,7 @@ 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; @@ -3840,6 +3841,16 @@ 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(); @@ -3854,7 +3865,8 @@ 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"); |