Quoting Mike Fowler <m...@mlfowler.com>:
The following bug has been logged online:
Bug reference: 5534
Logged by: Mike Fowler
Email address: m...@mlfowler.com
PostgreSQL version: 9.0beta2
Operating system: Linux 2.6.31-14-generic #48-Ubuntu SMP
Description: IS DOCUMENT predicate errors instead of returning false
Details:
IS DOCUMENT should return false for a non-well formed document, and indeed
is coded to do such. However, the conversion to the xml type which happens
before the underlying xml_is_document function is even called fails and
exceptions out. I've mentioned this on -hackers with message ID
20100701172553.w5vdy1xbocos8...@www.mlfowler.com
--
Sent via pgsql-bugs mailing list (pgsql-bugs@postgresql.org)
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-bugs
The attached patch is a very small patch that changes parse_expr.c to
not convert everything to xml. This now means that when passed
malformed XML it will return false instead of throwing an exception.
In my mind this acceptable as I don't see anywhere in the standard
that mandates that:
xmlval IS NOT DOCUMENT == xmlval IS CONTENT
Regards,
--
Mike Fowler
Registered Linux user: 379787
*** a/src/backend/parser/parse_expr.c
--- b/src/backend/parser/parse_expr.c
***************
*** 1950,1956 **** transformXmlExpr(ParseState *pstate, XmlExpr *x)
Assert(false);
break;
case IS_DOCUMENT:
! newe = coerce_to_specific_type(pstate, newe, XMLOID,
"IS DOCUMENT");
break;
}
--- 1950,1956 ----
Assert(false);
break;
case IS_DOCUMENT:
! newe = coerce_to_specific_type(pstate, newe, TEXTOID,
"IS DOCUMENT");
break;
}
*** a/src/backend/utils/adt/xml.c
--- b/src/backend/utils/adt/xml.c
***************
*** 795,801 **** xmlvalidate(PG_FUNCTION_ARGS)
bool
! xml_is_document(xmltype *arg)
{
#ifdef USE_LIBXML
bool result;
--- 795,801 ----
bool
! xml_is_document(text *arg)
{
#ifdef USE_LIBXML
bool result;
***************
*** 805,811 **** xml_is_document(xmltype *arg)
/* We want to catch ereport(INVALID_XML_DOCUMENT) and return false */
PG_TRY();
{
! doc = xml_parse((text *) arg, XMLOPTION_DOCUMENT, true,
GetDatabaseEncoding());
result = true;
}
--- 805,811 ----
/* We want to catch ereport(INVALID_XML_DOCUMENT) and return false */
PG_TRY();
{
! doc = xml_parse(arg, XMLOPTION_DOCUMENT, true,
GetDatabaseEncoding());
result = true;
}
*** a/src/include/utils/xml.h
--- b/src/include/utils/xml.h
***************
*** 70,76 **** extern xmltype *xmlelement(XmlExprState *xmlExpr, ExprContext *econtext);
extern xmltype *xmlparse(text *data, XmlOptionType xmloption, bool preserve_whitespace);
extern xmltype *xmlpi(char *target, text *arg, bool arg_is_null, bool *result_is_null);
extern xmltype *xmlroot(xmltype *data, text *version, int standalone);
! extern bool xml_is_document(xmltype *arg);
extern text *xmltotext_with_xmloption(xmltype *data, XmlOptionType xmloption_arg);
extern char *escape_xml(const char *str);
--- 70,76 ----
extern xmltype *xmlparse(text *data, XmlOptionType xmloption, bool preserve_whitespace);
extern xmltype *xmlpi(char *target, text *arg, bool arg_is_null, bool *result_is_null);
extern xmltype *xmlroot(xmltype *data, text *version, int standalone);
! extern bool xml_is_document(text *arg);
extern text *xmltotext_with_xmloption(xmltype *data, XmlOptionType xmloption_arg);
extern char *escape_xml(const char *str);
*** a/src/test/regress/expected/xml.out
--- b/src/test/regress/expected/xml.out
***************
*** 357,362 **** SELECT xml '<foo>bar</foo>' IS DOCUMENT;
--- 357,378 ----
t
(1 row)
+ SELECT xml '<foo>bar</foo' IS DOCUMENT;
+ ERROR: invalid XML content
+ LINE 1: SELECT xml '<foo>bar</foo' IS DOCUMENT;
+ ^
+ DETAIL: Entity: line 1: parser error : expected '>'
+ <foo>bar</foo
+ ^
+ Entity: line 1: parser error : chunk is not well balanced
+ <foo>bar</foo
+ ^
+ SELECT '<foo>bar</foo' IS DOCUMENT;
+ ?column?
+ ----------
+ f
+ (1 row)
+
SELECT xml '<foo>bar</foo><bar>foo</bar>' IS DOCUMENT;
?column?
----------
***************
*** 376,387 **** SELECT xml 'abc' IS NOT DOCUMENT;
(1 row)
SELECT '<>' IS NOT DOCUMENT;
ERROR: invalid XML content
! LINE 1: SELECT '<>' IS NOT DOCUMENT;
! ^
! DETAIL: Entity: line 1: parser error : StartTag: invalid element name
! <>
! ^
SELECT xmlagg(data) FROM xmltest;
xmlagg
--------------------------------------
--- 392,418 ----
(1 row)
SELECT '<>' IS NOT DOCUMENT;
+ ?column?
+ ----------
+ t
+ (1 row)
+
+ SELECT xml '<foo>bar</foo' IS NOT DOCUMENT;
ERROR: invalid XML content
! LINE 1: SELECT xml '<foo>bar</foo' IS NOT DOCUMENT;
! ^
! DETAIL: Entity: line 1: parser error : expected '>'
! <foo>bar</foo
! ^
! Entity: line 1: parser error : chunk is not well balanced
! <foo>bar</foo
! ^
! SELECT '<foo>bar</foo' IS NOT DOCUMENT;
! ?column?
! ----------
! t
! (1 row)
!
SELECT xmlagg(data) FROM xmltest;
xmlagg
--------------------------------------
*** a/src/test/regress/sql/xml.sql
--- b/src/test/regress/sql/xml.sql
***************
*** 112,121 **** SELECT xmlserialize(document 'bad' as text);
--- 112,125 ----
SELECT xml '<foo>bar</foo>' IS DOCUMENT;
+ SELECT xml '<foo>bar</foo' IS DOCUMENT;
+ SELECT '<foo>bar</foo' IS DOCUMENT;
SELECT xml '<foo>bar</foo><bar>foo</bar>' IS DOCUMENT;
SELECT xml '<abc/>' IS NOT DOCUMENT;
SELECT xml 'abc' IS NOT DOCUMENT;
SELECT '<>' IS NOT DOCUMENT;
+ SELECT xml '<foo>bar</foo' IS NOT DOCUMENT;
+ SELECT '<foo>bar</foo' IS NOT DOCUMENT;
SELECT xmlagg(data) FROM xmltest;
--
Sent via pgsql-bugs mailing list (pgsql-bugs@postgresql.org)
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-bugs
