Rewrite libxml error handling to be more robust.

libxml reports some errors (like invalid xmlns attributes) via the error
handler hook, but still returns a success indicator to the library caller.
This causes us to miss some errors that are important to report.  Since the
"generic" error handler hook doesn't know whether the message it's getting
is for an error, warning, or notice, stop using that and instead start
using the "structured" error handler hook, which gets enough information
to be useful.

While at it, arrange to save and restore the error handler hook setting in
each libxml-using function, rather than assuming we can set and forget the
hook.  This should improve the odds of working nicely with third-party
libraries that also use libxml.

In passing, volatile-ize some local variables that get modified within
PG_TRY blocks.  I noticed this while testing with an older gcc version
than I'd previously tried to compile xml.c with.

Florian Pflug and Tom Lane, with extensive review/testing by Noah Misch

configure

@@ -23655,6 +23655,75 @@ fi
 
 
 
+# Older versions of libxml2 lack the xmlStructuredErrorContext variable
+# (which could be a macro referring to a function, if threading is enabled)
+if test "$with_libxml" = yes ; then
+  { $as_echo "$as_me:$LINENO: checking for xmlStructuredErrorContext" >&5
+$as_echo_n "checking for xmlStructuredErrorContext... " >&6; }
+if test "${pgac_cv_libxml_structerrctx+set}" = set; then
+  $as_echo_n "(cached) " >&6
+else
+  cat >conftest.$ac_ext <<_ACEOF
+/* confdefs.h.  */
+_ACEOF
+cat confdefs.h >>conftest.$ac_ext
+cat >>conftest.$ac_ext <<_ACEOF
+/* end confdefs.h.  */
+#include <libxml/globals.h>
+                void *globptr;
+int
+main ()
+{
+globptr = xmlStructuredErrorContext
+  ;
+  return 0;
+}
+_ACEOF
+rm -f conftest.$ac_objext conftest$ac_exeext
+if { (ac_try="$ac_link"
+case "(($ac_try" in
+  *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;;
+  *) ac_try_echo=$ac_try;;
+esac
+eval ac_try_echo="\"\$as_me:$LINENO: $ac_try_echo\""
+$as_echo "$ac_try_echo") >&5
+  (eval "$ac_link") 2>conftest.er1
+  ac_status=$?
+  grep -v '^ *+' conftest.er1 >conftest.err
+  rm -f conftest.er1
+  cat conftest.err >&5
+  $as_echo "$as_me:$LINENO: \$? = $ac_status" >&5
+  (exit $ac_status); } && {
+	 test -z "$ac_c_werror_flag" ||
+	 test ! -s conftest.err
+       } && test -s conftest$ac_exeext && {
+	 test "$cross_compiling" = yes ||
+	 $as_test_x conftest$ac_exeext
+       }; then
+  pgac_cv_libxml_structerrctx=yes
+else
+  $as_echo "$as_me: failed program was:" >&5
+sed 's/^/| /' conftest.$ac_ext >&5
+
+	pgac_cv_libxml_structerrctx=no
+fi
+
+rm -rf conftest.dSYM
+rm -f core conftest.err conftest.$ac_objext conftest_ipa8_conftest.oo \
+      conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:$LINENO: result: $pgac_cv_libxml_structerrctx" >&5
+$as_echo "$pgac_cv_libxml_structerrctx" >&6; }
+  if test x"$pgac_cv_libxml_structerrctx" = x"yes"; then
+
+cat >>confdefs.h <<\_ACEOF
+#define HAVE_XMLSTRUCTUREDERRORCONTEXT 1
+_ACEOF
+
+  fi
+fi
+
+
 # This test makes sure that run tests work at all.  Sometimes a shared
 # library is found by the linker, but the runtime linker can't find it.
 # This check should come after all modifications of compiler or linker

configure.in

@@ -1519,6 +1519,23 @@ AC_SUBST(LDAP_LIBS_FE)
 AC_SUBST(LDAP_LIBS_BE)
 
 
+# Older versions of libxml2 lack the xmlStructuredErrorContext variable
+# (which could be a macro referring to a function, if threading is enabled)
+if test "$with_libxml" = yes ; then
+  AC_CACHE_CHECK([for xmlStructuredErrorContext], pgac_cv_libxml_structerrctx,
+  [AC_TRY_LINK([#include <libxml/globals.h>
+                void *globptr;],
+               [globptr = xmlStructuredErrorContext],
+               [pgac_cv_libxml_structerrctx=yes],
+               [pgac_cv_libxml_structerrctx=no])])
+  if test x"$pgac_cv_libxml_structerrctx" = x"yes"; then
+    AC_DEFINE(HAVE_XMLSTRUCTUREDERRORCONTEXT,
+             1,
+             [Define to 1 if your libxml has xmlStructuredErrorContext.])
+  fi
+fi
+
+
 # This test makes sure that run tests work at all.  Sometimes a shared
 # library is found by the linker, but the runtime linker can't find it.
 # This check should come after all modifications of compiler or linker

contrib/xml2/xpath.c

@@ -38,7 +38,7 @@ Datum		xpath_table(PG_FUNCTION_ARGS);
 
 /* exported for use by xslt_proc.c */
 
-void		pgxml_parser_init(void);
+PgXmlErrorContext *pgxml_parser_init(PgXmlStrictness strictness);
 
 /* workspace for pgxml_xpath() */
 
@@ -68,18 +68,27 @@ static void cleanup_workspace(xpath_workspace *workspace);
 
 /*
  * Initialize for xml parsing.
+ *
+ * As with the underlying pg_xml_init function, calls to this MUST be followed
+ * by a PG_TRY block that guarantees that pg_xml_done is called.
  */
-void
-pgxml_parser_init(void)
+PgXmlErrorContext *
+pgxml_parser_init(PgXmlStrictness strictness)
 {
+	PgXmlErrorContext *xmlerrcxt;
+
 	/* Set up error handling (we share the core's error handler) */
-	pg_xml_init();
+	xmlerrcxt = pg_xml_init(strictness);
+
+	/* Note: we're assuming an elog cannot be thrown by the following calls */
 
 	/* Initialize libxml */
 	xmlInitParser();
 
 	xmlSubstituteEntitiesDefault(1);
 	xmlLoadExtDtdDefaultValue = 1;
+
+	return xmlerrcxt;
 }
 
 
@@ -98,16 +107,33 @@ Datum
 xml_is_well_formed(PG_FUNCTION_ARGS)
 {
 	text	   *t = PG_GETARG_TEXT_P(0);		/* document buffer */
+	bool		result = false;
 	int32		docsize = VARSIZE(t) - VARHDRSZ;
 	xmlDocPtr	doctree;
+	PgXmlErrorContext *xmlerrcxt;
+
+	xmlerrcxt = pgxml_parser_init(PG_XML_STRICTNESS_LEGACY);
+
+	PG_TRY();
+	{
+		doctree = xmlParseMemory((char *) VARDATA(t), docsize);
+
+		result = (doctree != NULL);
+
+		if (doctree != NULL)
+			xmlFreeDoc(doctree);
+	}
+	PG_CATCH();
+	{
+		pg_xml_done(xmlerrcxt, true);
 
-	pgxml_parser_init();
+		PG_RE_THROW();
+	}
+	PG_END_TRY();
 
-	doctree = xmlParseMemory((char *) VARDATA(t), docsize);
-	if (doctree == NULL)
-		PG_RETURN_BOOL(false);	/* i.e. not well-formed */
-	xmlFreeDoc(doctree);
-	PG_RETURN_BOOL(true);
+	pg_xml_done(xmlerrcxt, false);
+
+	PG_RETURN_BOOL(result);
 }
 
 
@@ -399,41 +425,52 @@ static xmlXPathObjectPtr
 pgxml_xpath(text *document, xmlChar *xpath, xpath_workspace *workspace)
 {
 	int32		docsize = VARSIZE(document) - VARHDRSZ;
-	xmlXPathObjectPtr res;
+	PgXmlErrorContext *xmlerrcxt;
 	xmlXPathCompExprPtr comppath;
 
 	workspace->doctree = NULL;
 	workspace->ctxt = NULL;
 	workspace->res = NULL;
 
-	pgxml_parser_init();
+	xmlerrcxt = pgxml_parser_init(PG_XML_STRICTNESS_LEGACY);
 
-	workspace->doctree = xmlParseMemory((char *) VARDATA(document), docsize);
-	if (workspace->doctree == NULL)
-		return NULL;			/* not well-formed */
+	PG_TRY();
+	{
+		workspace->doctree = xmlParseMemory((char *) VARDATA(document),
+											docsize);
+		if (workspace->doctree != NULL)
+		{
+			workspace->ctxt = xmlXPathNewContext(workspace->doctree);
+			workspace->ctxt->node = xmlDocGetRootElement(workspace->doctree);
 
-	workspace->ctxt = xmlXPathNewContext(workspace->doctree);
-	workspace->ctxt->node = xmlDocGetRootElement(workspace->doctree);
+			/* compile the path */
+			comppath = xmlXPathCompile(xpath);
+			if (comppath == NULL)
+				xml_ereport(xmlerrcxt, ERROR, ERRCODE_EXTERNAL_ROUTINE_EXCEPTION,
+							"XPath Syntax Error");
 
-	/* compile the path */
-	comppath = xmlXPathCompile(xpath);
-	if (comppath == NULL)
+			/* Now evaluate the path expression. */
+			workspace->res = xmlXPathCompiledEval(comppath, workspace->ctxt);
+
+			xmlXPathFreeCompExpr(comppath);
+		}
+	}
+	PG_CATCH();
 	{
 		cleanup_workspace(workspace);
-		xml_ereport(ERROR, ERRCODE_EXTERNAL_ROUTINE_EXCEPTION,
-					"XPath Syntax Error");
-	}
 
-	/* Now evaluate the path expression. */
-	res = xmlXPathCompiledEval(comppath, workspace->ctxt);
-	workspace->res = res;
+		pg_xml_done(xmlerrcxt, true);
 
-	xmlXPathFreeCompExpr(comppath);
+		PG_RE_THROW();
+	}
+	PG_END_TRY();
 
-	if (res == NULL)
+	if (workspace->res == NULL)
 		cleanup_workspace(workspace);
 
-	return res;
+	pg_xml_done(xmlerrcxt, false);
+
+	return workspace->res;
 }
 
 /* Clean up after processing the result of pgxml_xpath() */
@@ -534,6 +571,8 @@ xpath_table(PG_FUNCTION_ARGS)
 								 * document */
 	bool		had_values;		/* To determine end of nodeset results */
 	StringInfoData query_buf;
+	PgXmlErrorContext *xmlerrcxt;
+	volatile xmlDocPtr doctree = NULL;
 
 	/* We only have a valid tuple description in table function mode */
 	if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo))
@@ -659,14 +698,15 @@ xpath_table(PG_FUNCTION_ARGS)
 	 * Setup the parser.  This should happen after we are done evaluating the
 	 * query, in case it calls functions that set up libxml differently.
 	 */
-	pgxml_parser_init();
+	xmlerrcxt = pgxml_parser_init(PG_XML_STRICTNESS_LEGACY);
 
+	PG_TRY();
+	{
 	/* For each row i.e. document returned from SPI */
 	for (i = 0; i < proc; i++)
 	{
 		char	   *pkey;
 		char	   *xmldoc;
-		xmlDocPtr	doctree;
 		xmlXPathContextPtr ctxt;
 		xmlXPathObjectPtr res;
 		xmlChar    *resstr;
@@ -718,11 +758,9 @@ xpath_table(PG_FUNCTION_ARGS)
 					/* compile the path */
 					comppath = xmlXPathCompile(xpaths[j]);
 					if (comppath == NULL)
-					{
-						xmlFreeDoc(doctree);
-						xml_ereport(ERROR, ERRCODE_EXTERNAL_ROUTINE_EXCEPTION,
+						xml_ereport(xmlerrcxt, ERROR,
+									ERRCODE_EXTERNAL_ROUTINE_EXCEPTION,
 									"XPath Syntax Error");
-					}
 
 					/* Now evaluate the path expression. */
 					res = xmlXPathCompiledEval(comppath, ctxt);
@@ -737,8 +775,7 @@ xpath_table(PG_FUNCTION_ARGS)
 								if (res->nodesetval != NULL &&
 									rownr < res->nodesetval->nodeNr)
 								{
-									resstr =
-										xmlXPathCastNodeToString(res->nodesetval->nodeTab[rownr]);
+									resstr = xmlXPathCastNodeToString(res->nodesetval->nodeTab[rownr]);
 									had_values = true;
 								}
 								else
@@ -776,13 +813,31 @@ xpath_table(PG_FUNCTION_ARGS)
 			} while (had_values);
 		}
 
-		xmlFreeDoc(doctree);
+		if (doctree != NULL)
+			xmlFreeDoc(doctree);
+		doctree = NULL;
 
 		if (pkey)
 			pfree(pkey);
 		if (xmldoc)
 			pfree(xmldoc);
 	}
+	}
+	PG_CATCH();
+	{
+		if (doctree != NULL)
+			xmlFreeDoc(doctree);
+
+		pg_xml_done(xmlerrcxt, true);
+
+		PG_RE_THROW();
+	}
+	PG_END_TRY();
+
+	if (doctree != NULL)
+		xmlFreeDoc(doctree);
+
+	pg_xml_done(xmlerrcxt, false);
 
 	tuplestore_donestoring(tupstore);
 

contrib/xml2/xslt_proc.c

@@ -38,7 +38,7 @@ Datum		xslt_process(PG_FUNCTION_ARGS);
 #ifdef USE_LIBXSLT
 
 /* declarations to come from xpath.c */
-extern void pgxml_parser_init(void);
+extern PgXmlErrorContext *pgxml_parser_init(PgXmlStrictness strictness);
 
 /* local defs */
 static const char **parse_params(text *paramstr);
@@ -56,13 +56,14 @@ xslt_process(PG_FUNCTION_ARGS)
 	text	   *ssheet = PG_GETARG_TEXT_P(1);
 	text	   *paramstr;
 	const char **params;
-	xsltStylesheetPtr stylesheet = NULL;
-	xmlDocPtr	doctree;
-	xmlDocPtr	restree;
-	xmlDocPtr	ssdoc = NULL;
-	xmlChar    *resstr;
-	int			resstat;
-	int			reslen;
+	PgXmlErrorContext *xmlerrcxt;
+	volatile xsltStylesheetPtr stylesheet = NULL;
+	volatile xmlDocPtr doctree = NULL;
+	volatile xmlDocPtr restree = NULL;
+	volatile xmlDocPtr ssdoc = NULL;
+	volatile int resstat = -1;
+	xmlChar    *resstr = NULL;
+	int			reslen = 0;
 
 	if (fcinfo->nargs == 3)
 	{
@@ -77,9 +78,11 @@ xslt_process(PG_FUNCTION_ARGS)
 	}
 
 	/* Setup parser */
-	pgxml_parser_init();
+	xmlerrcxt = pgxml_parser_init(PG_XML_STRICTNESS_LEGACY);
 
-	/* Check to see if document is a file or a literal */
+	PG_TRY();
+	{
+		/* Check to see if document is a file or a literal */
 
 	if (VARDATA(doct)[0] == '<')
 		doctree = xmlParseMemory((char *) VARDATA(doct), VARSIZE(doct) - VARHDRSZ);
@@ -87,7 +90,7 @@ xslt_process(PG_FUNCTION_ARGS)
 		doctree = xmlParseFile(text_to_cstring(doct));
 
 	if (doctree == NULL)
-		xml_ereport(ERROR, ERRCODE_EXTERNAL_ROUTINE_EXCEPTION,
+		xml_ereport(xmlerrcxt, ERROR, ERRCODE_EXTERNAL_ROUTINE_EXCEPTION,
 					"error parsing XML document");
 
 	/* Same for stylesheet */
@@ -96,35 +99,44 @@ xslt_process(PG_FUNCTION_ARGS)
 		ssdoc = xmlParseMemory((char *) VARDATA(ssheet),
 							   VARSIZE(ssheet) - VARHDRSZ);
 		if (ssdoc == NULL)
-		{
-			xmlFreeDoc(doctree);
-			xml_ereport(ERROR, ERRCODE_EXTERNAL_ROUTINE_EXCEPTION,
+			xml_ereport(xmlerrcxt, ERROR, ERRCODE_EXTERNAL_ROUTINE_EXCEPTION,
 						"error parsing stylesheet as XML document");
-		}
 
 		stylesheet = xsltParseStylesheetDoc(ssdoc);
 	}
 	else
 		stylesheet = xsltParseStylesheetFile((xmlChar *) text_to_cstring(ssheet));
 
-
 	if (stylesheet == NULL)
-	{
-		xmlFreeDoc(doctree);
-		xsltCleanupGlobals();
-		xml_ereport(ERROR, ERRCODE_EXTERNAL_ROUTINE_EXCEPTION,
+		xml_ereport(xmlerrcxt, ERROR, ERRCODE_EXTERNAL_ROUTINE_EXCEPTION,
 					"failed to parse stylesheet");
-	}
 
 	restree = xsltApplyStylesheet(stylesheet, doctree, params);
 	resstat = xsltSaveResultToString(&resstr, &reslen, restree, stylesheet);
+	}
+	PG_CATCH();
+	{
+		if (stylesheet != NULL)
+			xsltFreeStylesheet(stylesheet);
+		if (restree != NULL)
+			xmlFreeDoc(restree);
+		if (doctree != NULL)
+			xmlFreeDoc(doctree);
+		xsltCleanupGlobals();
+
+		pg_xml_done(xmlerrcxt, true);
+
+		PG_RE_THROW();
+	}
+	PG_END_TRY();
 
 	xsltFreeStylesheet(stylesheet);
 	xmlFreeDoc(restree);
 	xmlFreeDoc(doctree);
-
 	xsltCleanupGlobals();
 
+	pg_xml_done(xmlerrcxt, false);
+
 	if (resstat < 0)
 		PG_RETURN_NULL();
 

src/include/pg_config.h.in

@@ -671,6 +671,9 @@
 /* Define to 1 if you have the <winldap.h> header file. */
 #undef HAVE_WINLDAP_H
 
+/* Define to 1 if your libxml has xmlStructuredErrorContext. */
+#undef HAVE_XMLSTRUCTUREDERRORCONTEXT
+
 /* Define to the appropriate snprintf format for 64-bit ints. */
 #undef INT64_FORMAT
 

src/include/utils/xml.h

@@ -21,6 +21,31 @@
 
 typedef struct varlena xmltype;
 
+typedef enum
+{
+	XML_STANDALONE_YES,
+	XML_STANDALONE_NO,
+	XML_STANDALONE_NO_VALUE,
+	XML_STANDALONE_OMITTED
+}	XmlStandaloneType;
+
+typedef enum
+{
+	XMLBINARY_BASE64,
+	XMLBINARY_HEX
+}	XmlBinaryType;
+
+typedef enum
+{
+	PG_XML_STRICTNESS_LEGACY,		/* ignore errors unless function result
+									 * indicates error condition */
+	PG_XML_STRICTNESS_WELLFORMED,	/* ignore non-parser messages */
+	PG_XML_STRICTNESS_ALL			/* report all notices/warnings/errors */
+}	PgXmlStrictness;
+
+/* struct PgXmlErrorContext is private to xml.c */
+typedef struct PgXmlErrorContext PgXmlErrorContext;
+
 #define DatumGetXmlP(X)		((xmltype *) PG_DETOAST_DATUM(X))
 #define XmlPGetDatum(X)		PointerGetDatum(X)
 
@@ -60,16 +85,13 @@ extern Datum database_to_xml(PG_FUNCTION_ARGS);
 extern Datum database_to_xmlschema(PG_FUNCTION_ARGS);
 extern Datum database_to_xml_and_xmlschema(PG_FUNCTION_ARGS);
 
-typedef enum
-{
-	XML_STANDALONE_YES,
-	XML_STANDALONE_NO,
-	XML_STANDALONE_NO_VALUE,
-	XML_STANDALONE_OMITTED
-}	XmlStandaloneType;
+extern void pg_xml_init_library(void);
+extern PgXmlErrorContext *pg_xml_init(PgXmlStrictness strictness);
+extern void pg_xml_done(PgXmlErrorContext *errcxt, bool isError);
+extern bool pg_xml_error_occurred(PgXmlErrorContext *errcxt);
+extern void xml_ereport(PgXmlErrorContext *errcxt, int level, int sqlcode,
+						const char *msg);
 
-extern void pg_xml_init(void);
-extern void xml_ereport(int level, int sqlcode, const char *msg);
 extern xmltype *xmlconcat(List *args);
 extern xmltype *xmlelement(XmlExprState *xmlExpr, ExprContext *econtext);
 extern xmltype *xmlparse(text *data, XmlOptionType xmloption, bool preserve_whitespace);
@@ -83,12 +105,6 @@ extern char *map_sql_identifier_to_xml_name(char *ident, bool fully_escaped, boo
 extern char *map_xml_name_to_sql_identifier(char *name);
 extern char *map_sql_value_to_xml_value(Datum value, Oid type, bool xml_escape_strings);
 
-typedef enum
-{
-	XMLBINARY_BASE64,
-	XMLBINARY_HEX
-}	XmlBinaryType;
-
 extern int	xmlbinary;			/* XmlBinaryType, but int for guc enum */
 
 extern int	xmloption;			/* XmlOptionType, but int for guc enum */

src/test/regress/expected/xml.out

@@ -8,7 +8,7 @@ INSERT INTO xmltest VALUES (3, '<wrong');
 ERROR:  invalid XML content
 LINE 1: INSERT INTO xmltest VALUES (3, '<wrong');
                                        ^
-DETAIL:  Entity: line 1: parser error : Couldn't find end of Start Tag wrong line 1
+DETAIL:  line 1: Couldn't find end of Start Tag wrong line 1
 <wrong
       ^
 SELECT * FROM xmltest;
@@ -62,7 +62,7 @@ SELECT xmlconcat('bad', '<syntax');
 ERROR:  invalid XML content
 LINE 1: SELECT xmlconcat('bad', '<syntax');
                                 ^
-DETAIL:  Entity: line 1: parser error : Couldn't find end of Start Tag syntax line 1
+DETAIL:  line 1: Couldn't find end of Start Tag syntax line 1
 <syntax
        ^
 SELECT xmlconcat('<foo/>', NULL, '<?xml version="1.1" standalone="no"?><bar/>');
@@ -206,9 +206,54 @@ SELECT xmlparse(content '<abc>x</abc>');
  <abc>x</abc>
 (1 row)
 
+SELECT xmlparse(content '<invalidentity>&</invalidentity>');
+ERROR:  invalid XML content
+DETAIL:  line 1: xmlParseEntityRef: no name
+<invalidentity>&</invalidentity>
+                ^
+line 1: chunk is not well balanced
+<invalidentity>&</invalidentity>
+                                ^
+SELECT xmlparse(content '<undefinedentity>&idontexist;</undefinedentity>');
+ERROR:  invalid XML content
+DETAIL:  line 1: Entity 'idontexist' not defined
+<undefinedentity>&idontexist;</undefinedentity>
+                             ^
+line 1: chunk is not well balanced
+<undefinedentity>&idontexist;</undefinedentity>
+                                               ^
+SELECT xmlparse(content '<invalidns xmlns=''&lt;''/>');
+         xmlparse          
+---------------------------
+ <invalidns xmlns='&lt;'/>
+(1 row)
+
+SELECT xmlparse(content '<relativens xmlns=''relative''/>');
+            xmlparse            
+--------------------------------
+ <relativens xmlns='relative'/>
+(1 row)
+
+SELECT xmlparse(content '<twoerrors>&idontexist;</unbalanced>');
+ERROR:  invalid XML content
+DETAIL:  line 1: Entity 'idontexist' not defined
+<twoerrors>&idontexist;</unbalanced>
+                       ^
+line 1: Opening and ending tag mismatch: twoerrors line 1 and unbalanced
+<twoerrors>&idontexist;</unbalanced>
+                                    ^
+line 1: chunk is not well balanced
+<twoerrors>&idontexist;</unbalanced>
+                                    ^
+SELECT xmlparse(content '<nosuchprefix:tag/>');
+      xmlparse       
+---------------------
+ <nosuchprefix:tag/>
+(1 row)
+
 SELECT xmlparse(document 'abc');
 ERROR:  invalid XML document
-DETAIL:  Entity: line 1: parser error : Start tag expected, '<' not found
+DETAIL:  line 1: Start tag expected, '<' not found
 abc
 ^
 SELECT xmlparse(document '<abc>x</abc>');
@@ -217,6 +262,48 @@ SELECT xmlparse(document '<abc>x</abc>');
  <abc>x</abc>
 (1 row)
 
+SELECT xmlparse(document '<invalidentity>&</abc>');
+ERROR:  invalid XML document
+DETAIL:  line 1: xmlParseEntityRef: no name
+<invalidentity>&</abc>
+                ^
+line 1: Opening and ending tag mismatch: invalidentity line 1 and abc
+<invalidentity>&</abc>
+                      ^
+SELECT xmlparse(document '<undefinedentity>&idontexist;</abc>');
+ERROR:  invalid XML document
+DETAIL:  line 1: Entity 'idontexist' not defined
+<undefinedentity>&idontexist;</abc>
+                             ^
+line 1: Opening and ending tag mismatch: undefinedentity line 1 and abc
+<undefinedentity>&idontexist;</abc>
+                                   ^
+SELECT xmlparse(document '<invalidns xmlns=''&lt;''/>');
+         xmlparse          
+---------------------------
+ <invalidns xmlns='&lt;'/>
+(1 row)
+
+SELECT xmlparse(document '<relativens xmlns=''relative''/>');
+            xmlparse            
+--------------------------------
+ <relativens xmlns='relative'/>
+(1 row)
+
+SELECT xmlparse(document '<twoerrors>&idontexist;</unbalanced>');
+ERROR:  invalid XML document
+DETAIL:  line 1: Entity 'idontexist' not defined
+<twoerrors>&idontexist;</unbalanced>
+                       ^
+line 1: Opening and ending tag mismatch: twoerrors line 1 and unbalanced
+<twoerrors>&idontexist;</unbalanced>
+                                    ^
+SELECT xmlparse(document '<nosuchprefix:tag/>');
+      xmlparse       
+---------------------
+ <nosuchprefix:tag/>
+(1 row)
+
 SELECT xmlpi(name foo);
   xmlpi  
 ---------
@@ -379,7 +466,7 @@ SELECT '<>' IS NOT DOCUMENT;
 ERROR:  invalid XML content
 LINE 1: SELECT '<>' IS NOT DOCUMENT;
                ^
-DETAIL:  Entity: line 1: parser error : StartTag: invalid element name
+DETAIL:  line 1: StartTag: invalid element name
 <>
  ^
 SELECT xmlagg(data) FROM xmltest;
@@ -425,7 +512,7 @@ EXECUTE foo ('bad');
 ERROR:  invalid XML document
 LINE 1: EXECUTE foo ('bad');
                      ^
-DETAIL:  Entity: line 1: parser error : Start tag expected, '<' not found
+DETAIL:  line 1: Start tag expected, '<' not found
 bad
 ^
 SET XML OPTION CONTENT;
@@ -679,6 +766,36 @@ SELECT xml_is_well_formed('<pg:foo xmlns:pg="http://postgresql.org/stuff">bar</p
  t
 (1 row)
 
+SELECT xml_is_well_formed('<invalidentity>&</abc>');
+ xml_is_well_formed 
+--------------------
+ f
+(1 row)
+
+SELECT xml_is_well_formed('<undefinedentity>&idontexist;</abc>');
+ xml_is_well_formed 
+--------------------
+ f
+(1 row)
+
+SELECT xml_is_well_formed('<invalidns xmlns=''&lt;''/>');
+ xml_is_well_formed 
+--------------------
+ t
+(1 row)
+
+SELECT xml_is_well_formed('<relativens xmlns=''relative''/>');
+ xml_is_well_formed 
+--------------------
+ t
+(1 row)
+
+SELECT xml_is_well_formed('<twoerrors>&idontexist;</unbalanced>');
+ xml_is_well_formed 
+--------------------
+ f
+(1 row)
+
 SET xmloption TO CONTENT;
 SELECT xml_is_well_formed('abc');
  xml_is_well_formed 
@@ -686,3 +803,36 @@ SELECT xml_is_well_formed('abc');
  t
 (1 row)
 
+-- Since xpath() deals with namespaces, it's a bit stricter about
+-- what's well-formed and what's not. If we don't obey these rules
+-- (i.e. ignore namespace-related errors from libxml), xpath()
+-- fails in subtle ways. The following would for example produce
+-- the xml value
+--   <invalidns xmlns='<'/>
+-- which is invalid because '<' may not appear un-escaped in
+-- attribute values.
+-- Since different libxml versions emit slightly different
+-- error messages, we suppress the DETAIL in this test.
+\set VERBOSITY terse
+SELECT xpath('/*', '<invalidns xmlns=''&lt;''/>');
+ERROR:  could not parse XML document
+\set VERBOSITY default
+-- Again, the XML isn't well-formed for namespace purposes
+SELECT xpath('/*', '<nosuchprefix:tag/>');
+ERROR:  could not parse XML document
+DETAIL:  line 1: Namespace prefix nosuchprefix on tag is not defined
+<nosuchprefix:tag/>
+                 ^
+CONTEXT:  SQL function "xpath" statement 1
+-- XPath deprecates relative namespaces, but they're not supposed to
+-- throw an error, only a warning.
+SELECT xpath('/*', '<relativens xmlns=''relative''/>');
+WARNING:  line 1: xmlns: URI relative is not absolute
+<relativens xmlns='relative'/>
+                            ^
+CONTEXT:  SQL function "xpath" statement 1
+                xpath                 
+--------------------------------------
+ {"<relativens xmlns=\"relative\"/>"}
+(1 row)
+

src/test/regress/expected/xml_1.out

@@ -172,6 +172,30 @@ SELECT xmlparse(content '<abc>x</abc>');
 ERROR:  unsupported XML feature
 DETAIL:  This functionality requires the server to be built with libxml support.
 HINT:  You need to rebuild PostgreSQL using --with-libxml.
+SELECT xmlparse(content '<invalidentity>&</invalidentity>');
+ERROR:  unsupported XML feature
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
+SELECT xmlparse(content '<undefinedentity>&idontexist;</undefinedentity>');
+ERROR:  unsupported XML feature
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
+SELECT xmlparse(content '<invalidns xmlns=''&lt;''/>');
+ERROR:  unsupported XML feature
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
+SELECT xmlparse(content '<relativens xmlns=''relative''/>');
+ERROR:  unsupported XML feature
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
+SELECT xmlparse(content '<twoerrors>&idontexist;</unbalanced>');
+ERROR:  unsupported XML feature
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
+SELECT xmlparse(content '<nosuchprefix:tag/>');
+ERROR:  unsupported XML feature
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
 SELECT xmlparse(document 'abc');
 ERROR:  unsupported XML feature
 DETAIL:  This functionality requires the server to be built with libxml support.
@@ -180,6 +204,30 @@ SELECT xmlparse(document '<abc>x</abc>');
 ERROR:  unsupported XML feature
 DETAIL:  This functionality requires the server to be built with libxml support.
 HINT:  You need to rebuild PostgreSQL using --with-libxml.
+SELECT xmlparse(document '<invalidentity>&</abc>');
+ERROR:  unsupported XML feature
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
+SELECT xmlparse(document '<undefinedentity>&idontexist;</abc>');
+ERROR:  unsupported XML feature
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
+SELECT xmlparse(document '<invalidns xmlns=''&lt;''/>');
+ERROR:  unsupported XML feature
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
+SELECT xmlparse(document '<relativens xmlns=''relative''/>');
+ERROR:  unsupported XML feature
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
+SELECT xmlparse(document '<twoerrors>&idontexist;</unbalanced>');
+ERROR:  unsupported XML feature
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
+SELECT xmlparse(document '<nosuchprefix:tag/>');
+ERROR:  unsupported XML feature
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
 SELECT xmlpi(name foo);
 ERROR:  unsupported XML feature
 DETAIL:  This functionality requires the server to be built with libxml support.
@@ -627,8 +675,57 @@ SELECT xml_is_well_formed('<pg:foo xmlns:pg="http://postgresql.org/stuff">bar</p
 ERROR:  unsupported XML feature
 DETAIL:  This functionality requires the server to be built with libxml support.
 HINT:  You need to rebuild PostgreSQL using --with-libxml.
+SELECT xml_is_well_formed('<invalidentity>&</abc>');
+ERROR:  unsupported XML feature
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
+SELECT xml_is_well_formed('<undefinedentity>&idontexist;</abc>');
+ERROR:  unsupported XML feature
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
+SELECT xml_is_well_formed('<invalidns xmlns=''&lt;''/>');
+ERROR:  unsupported XML feature
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
+SELECT xml_is_well_formed('<relativens xmlns=''relative''/>');
+ERROR:  unsupported XML feature
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
+SELECT xml_is_well_formed('<twoerrors>&idontexist;</unbalanced>');
+ERROR:  unsupported XML feature
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
 SET xmloption TO CONTENT;
 SELECT xml_is_well_formed('abc');
 ERROR:  unsupported XML feature
 DETAIL:  This functionality requires the server to be built with libxml support.
 HINT:  You need to rebuild PostgreSQL using --with-libxml.
+-- Since xpath() deals with namespaces, it's a bit stricter about
+-- what's well-formed and what's not. If we don't obey these rules
+-- (i.e. ignore namespace-related errors from libxml), xpath()
+-- fails in subtle ways. The following would for example produce
+-- the xml value
+--   <invalidns xmlns='<'/>
+-- which is invalid because '<' may not appear un-escaped in
+-- attribute values.
+-- Since different libxml versions emit slightly different
+-- error messages, we suppress the DETAIL in this test.
+\set VERBOSITY terse
+SELECT xpath('/*', '<invalidns xmlns=''&lt;''/>');
+ERROR:  unsupported XML feature at character 20
+\set VERBOSITY default
+-- Again, the XML isn't well-formed for namespace purposes
+SELECT xpath('/*', '<nosuchprefix:tag/>');
+ERROR:  unsupported XML feature
+LINE 1: SELECT xpath('/*', '<nosuchprefix:tag/>');
+                           ^
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
+-- XPath deprecates relative namespaces, but they're not supposed to
+-- throw an error, only a warning.
+SELECT xpath('/*', '<relativens xmlns=''relative''/>');
+ERROR:  unsupported XML feature
+LINE 1: SELECT xpath('/*', '<relativens xmlns=''relative''/>');
+                           ^
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.

src/test/regress/sql/xml.sql

@@ -62,9 +62,21 @@ SELECT xmlelement(name foo, xmlattributes('<>&"''' as funny, xml 'b<a/>r' as fun
 
 SELECT xmlparse(content 'abc');
 SELECT xmlparse(content '<abc>x</abc>');
+SELECT xmlparse(content '<invalidentity>&</invalidentity>');
+SELECT xmlparse(content '<undefinedentity>&idontexist;</undefinedentity>');
+SELECT xmlparse(content '<invalidns xmlns=''&lt;''/>');
+SELECT xmlparse(content '<relativens xmlns=''relative''/>');
+SELECT xmlparse(content '<twoerrors>&idontexist;</unbalanced>');
+SELECT xmlparse(content '<nosuchprefix:tag/>');
 
 SELECT xmlparse(document 'abc');
 SELECT xmlparse(document '<abc>x</abc>');
+SELECT xmlparse(document '<invalidentity>&</abc>');
+SELECT xmlparse(document '<undefinedentity>&idontexist;</abc>');
+SELECT xmlparse(document '<invalidns xmlns=''&lt;''/>');
+SELECT xmlparse(document '<relativens xmlns=''relative''/>');
+SELECT xmlparse(document '<twoerrors>&idontexist;</unbalanced>');
+SELECT xmlparse(document '<nosuchprefix:tag/>');
 
 
 SELECT xmlpi(name foo);
@@ -208,6 +220,32 @@ SELECT xml_is_well_formed('<foo><bar>baz</foo>');
 SELECT xml_is_well_formed('<local:data xmlns:local="http://127.0.0.1"><local:piece id="1">number one</local:piece><local:piece id="2" /></local:data>');
 SELECT xml_is_well_formed('<pg:foo xmlns:pg="http://postgresql.org/stuff">bar</my:foo>');
 SELECT xml_is_well_formed('<pg:foo xmlns:pg="http://postgresql.org/stuff">bar</pg:foo>');
+SELECT xml_is_well_formed('<invalidentity>&</abc>');
+SELECT xml_is_well_formed('<undefinedentity>&idontexist;</abc>');
+SELECT xml_is_well_formed('<invalidns xmlns=''&lt;''/>');
+SELECT xml_is_well_formed('<relativens xmlns=''relative''/>');
+SELECT xml_is_well_formed('<twoerrors>&idontexist;</unbalanced>');
 
 SET xmloption TO CONTENT;
 SELECT xml_is_well_formed('abc');
+
+-- Since xpath() deals with namespaces, it's a bit stricter about
+-- what's well-formed and what's not. If we don't obey these rules
+-- (i.e. ignore namespace-related errors from libxml), xpath()
+-- fails in subtle ways. The following would for example produce
+-- the xml value
+--   <invalidns xmlns='<'/>
+-- which is invalid because '<' may not appear un-escaped in
+-- attribute values.
+-- Since different libxml versions emit slightly different
+-- error messages, we suppress the DETAIL in this test.
+\set VERBOSITY terse
+SELECT xpath('/*', '<invalidns xmlns=''&lt;''/>');
+\set VERBOSITY default
+
+-- Again, the XML isn't well-formed for namespace purposes
+SELECT xpath('/*', '<nosuchprefix:tag/>');
+
+-- XPath deprecates relative namespaces, but they're not supposed to
+-- throw an error, only a warning.
+SELECT xpath('/*', '<relativens xmlns=''relative''/>');