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

2 files changed, 34 insertions, 15 deletions

diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 19f38cc0fd..24b951e7bd 100644
--- a/src/include/pg_config.h.in
+++ b/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
 
diff --git a/src/include/utils/xml.h b/src/include/utils/xml.h
index 6359cd6043..f9f6f56859 100644
--- a/src/include/utils/xml.h
+++ b/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 */