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

5 files changed, 142 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");
diff --git a/src/test/regress/expected/xml.out b/src/test/regress/expected/xml.out
index b451b63847e..580e401ff65 100644
--- a/src/test/regress/expected/xml.out
+++ b/src/test/regress/expected/xml.out
@@ -670,6 +670,37 @@ SELECT xpath('/nosuchtag', '<root/>');
  {}
 (1 row)
 
+-- Round-trip non-ASCII data through xpath().
+DO $$
+DECLARE
+  xml_declaration text := '<?xml version="1.0" encoding="ISO-8859-1"?>';
+  degree_symbol text;
+  res xml[];
+BEGIN
+  -- Per the documentation, xpath() doesn't work on non-ASCII data when
+  -- the server encoding is not UTF8.  The EXCEPTION block below,
+  -- currently dead code, will be relevant if we remove this limitation.
+  IF current_setting('server_encoding') <> 'UTF8' THEN
+    RAISE LOG 'skip: encoding % unsupported for xml',
+      current_setting('server_encoding');
+    RETURN;
+  END IF;
+
+  degree_symbol := convert_from('\xc2b0', 'UTF8');
+  res := xpath('text()', (xml_declaration ||
+    '<x>' || degree_symbol || '</x>')::xml);
+  IF degree_symbol <> res[1]::text THEN
+    RAISE 'expected % (%), got % (%)',
+      degree_symbol, convert_to(degree_symbol, 'UTF8'),
+      res[1], convert_to(res[1]::text, 'UTF8');
+  END IF;
+EXCEPTION
+  -- character with byte sequence 0xc2 0xb0 in encoding "UTF8" has no equivalent in encoding "LATIN8"
+  WHEN untranslatable_character THEN RAISE LOG 'skip: %', SQLERRM;
+  -- default conversion function for encoding "UTF8" to "MULE_INTERNAL" does not exist
+  WHEN undefined_function THEN RAISE LOG 'skip: %', SQLERRM;
+END
+$$;
 -- Test xmlexists and xpath_exists
 SELECT xmlexists('//town[text() = ''Toronto'']' PASSING BY REF '<towns><town>Bidford-on-Avon</town><town>Cwmbran</town><town>Bristol</town></towns>');
  xmlexists 
diff --git a/src/test/regress/expected/xml_1.out b/src/test/regress/expected/xml_1.out
index d7027030c36..2cc4804e493 100644
--- a/src/test/regress/expected/xml_1.out
+++ b/src/test/regress/expected/xml_1.out
@@ -576,6 +576,41 @@ LINE 1: SELECT xpath('/nosuchtag', '<root/>');
                                    ^
 DETAIL:  This functionality requires the server to be built with libxml support.
 HINT:  You need to rebuild PostgreSQL using --with-libxml.
+-- Round-trip non-ASCII data through xpath().
+DO $$
+DECLARE
+  xml_declaration text := '<?xml version="1.0" encoding="ISO-8859-1"?>';
+  degree_symbol text;
+  res xml[];
+BEGIN
+  -- Per the documentation, xpath() doesn't work on non-ASCII data when
+  -- the server encoding is not UTF8.  The EXCEPTION block below,
+  -- currently dead code, will be relevant if we remove this limitation.
+  IF current_setting('server_encoding') <> 'UTF8' THEN
+    RAISE LOG 'skip: encoding % unsupported for xml',
+      current_setting('server_encoding');
+    RETURN;
+  END IF;
+
+  degree_symbol := convert_from('\xc2b0', 'UTF8');
+  res := xpath('text()', (xml_declaration ||
+    '<x>' || degree_symbol || '</x>')::xml);
+  IF degree_symbol <> res[1]::text THEN
+    RAISE 'expected % (%), got % (%)',
+      degree_symbol, convert_to(degree_symbol, 'UTF8'),
+      res[1], convert_to(res[1]::text, 'UTF8');
+  END IF;
+EXCEPTION
+  -- character with byte sequence 0xc2 0xb0 in encoding "UTF8" has no equivalent in encoding "LATIN8"
+  WHEN untranslatable_character THEN RAISE LOG 'skip: %', SQLERRM;
+  -- default conversion function for encoding "UTF8" to "MULE_INTERNAL" does not exist
+  WHEN undefined_function THEN RAISE LOG 'skip: %', SQLERRM;
+END
+$$;
+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.
+CONTEXT:  PL/pgSQL function inline_code_block line 17 at assignment
 -- Test xmlexists and xpath_exists
 SELECT xmlexists('//town[text() = ''Toronto'']' PASSING BY REF '<towns><town>Bidford-on-Avon</town><town>Cwmbran</town><town>Bristol</town></towns>');
 ERROR:  unsupported XML feature
diff --git a/src/test/regress/expected/xml_2.out b/src/test/regress/expected/xml_2.out
index 23c4e767f0b..3a959480740 100644
--- a/src/test/regress/expected/xml_2.out
+++ b/src/test/regress/expected/xml_2.out
@@ -650,6 +650,37 @@ SELECT xpath('/nosuchtag', '<root/>');
  {}
 (1 row)
 
+-- Round-trip non-ASCII data through xpath().
+DO $$
+DECLARE
+  xml_declaration text := '<?xml version="1.0" encoding="ISO-8859-1"?>';
+  degree_symbol text;
+  res xml[];
+BEGIN
+  -- Per the documentation, xpath() doesn't work on non-ASCII data when
+  -- the server encoding is not UTF8.  The EXCEPTION block below,
+  -- currently dead code, will be relevant if we remove this limitation.
+  IF current_setting('server_encoding') <> 'UTF8' THEN
+    RAISE LOG 'skip: encoding % unsupported for xml',
+      current_setting('server_encoding');
+    RETURN;
+  END IF;
+
+  degree_symbol := convert_from('\xc2b0', 'UTF8');
+  res := xpath('text()', (xml_declaration ||
+    '<x>' || degree_symbol || '</x>')::xml);
+  IF degree_symbol <> res[1]::text THEN
+    RAISE 'expected % (%), got % (%)',
+      degree_symbol, convert_to(degree_symbol, 'UTF8'),
+      res[1], convert_to(res[1]::text, 'UTF8');
+  END IF;
+EXCEPTION
+  -- character with byte sequence 0xc2 0xb0 in encoding "UTF8" has no equivalent in encoding "LATIN8"
+  WHEN untranslatable_character THEN RAISE LOG 'skip: %', SQLERRM;
+  -- default conversion function for encoding "UTF8" to "MULE_INTERNAL" does not exist
+  WHEN undefined_function THEN RAISE LOG 'skip: %', SQLERRM;
+END
+$$;
 -- Test xmlexists and xpath_exists
 SELECT xmlexists('//town[text() = ''Toronto'']' PASSING BY REF '<towns><town>Bidford-on-Avon</town><town>Cwmbran</town><town>Bristol</town></towns>');
  xmlexists 
diff --git a/src/test/regress/sql/xml.sql b/src/test/regress/sql/xml.sql
index 08a0b30067a..ac80d2f1a8c 100644
--- a/src/test/regress/sql/xml.sql
+++ b/src/test/regress/sql/xml.sql
@@ -189,6 +189,38 @@ SELECT xpath('count(//*)=3', '<root><sub/><sub/></root>');
 SELECT xpath('name(/*)', '<root><sub/><sub/></root>');
 SELECT xpath('/nosuchtag', '<root/>');
 
+-- Round-trip non-ASCII data through xpath().
+DO $$
+DECLARE
+  xml_declaration text := '<?xml version="1.0" encoding="ISO-8859-1"?>';
+  degree_symbol text;
+  res xml[];
+BEGIN
+  -- Per the documentation, xpath() doesn't work on non-ASCII data when
+  -- the server encoding is not UTF8.  The EXCEPTION block below,
+  -- currently dead code, will be relevant if we remove this limitation.
+  IF current_setting('server_encoding') <> 'UTF8' THEN
+    RAISE LOG 'skip: encoding % unsupported for xml',
+      current_setting('server_encoding');
+    RETURN;
+  END IF;
+
+  degree_symbol := convert_from('\xc2b0', 'UTF8');
+  res := xpath('text()', (xml_declaration ||
+    '<x>' || degree_symbol || '</x>')::xml);
+  IF degree_symbol <> res[1]::text THEN
+    RAISE 'expected % (%), got % (%)',
+      degree_symbol, convert_to(degree_symbol, 'UTF8'),
+      res[1], convert_to(res[1]::text, 'UTF8');
+  END IF;
+EXCEPTION
+  -- character with byte sequence 0xc2 0xb0 in encoding "UTF8" has no equivalent in encoding "LATIN8"
+  WHEN untranslatable_character THEN RAISE LOG 'skip: %', SQLERRM;
+  -- default conversion function for encoding "UTF8" to "MULE_INTERNAL" does not exist
+  WHEN undefined_function THEN RAISE LOG 'skip: %', SQLERRM;
+END
+$$;
+
 -- Test xmlexists and xpath_exists
 SELECT xmlexists('//town[text() = ''Toronto'']' PASSING BY REF '<towns><town>Bidford-on-Avon</town><town>Cwmbran</town><town>Bristol</town></towns>');
 SELECT xmlexists('//town[text() = ''Cwmbran'']' PASSING BY REF '<towns><town>Bidford-on-Avon</town><town>Cwmbran</town><town>Bristol</town></towns>');