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

1 files changed, 32 insertions, 0 deletions

diff --git a/src/test/regress/sql/xml.sql b/src/test/regress/sql/xml.sql
index ce87d426842..62a4736275f 100644
--- a/src/test/regress/sql/xml.sql
+++ b/src/test/regress/sql/xml.sql
@@ -186,6 +186,38 @@ 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>');