diff --git a/src/backend/utils/adt/xml.c b/src/backend/utils/adt/xml.c index 24229c2..3e3aed8 100644 --- a/src/backend/utils/adt/xml.c +++ b/src/backend/utils/adt/xml.c @@ -3845,6 +3845,7 @@ 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; @@ -3900,6 +3901,16 @@ xpath_internal(text *xpath_expr_text, xmltype *data, ArrayType *namespaces, string = pg_xmlCharStrndup(datastr, len); xpath_expr = pg_xmlCharStrndup(VARDATA_ANY(xpath_expr_text), xpath_len); + /* + * 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(); @@ -3914,7 +3925,8 @@ 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 bcc585d..f7a8c38 100644 --- a/src/test/regress/expected/xml.out +++ b/src/test/regress/expected/xml.out @@ -670,6 +670,37 @@ SELECT xpath('/nosuchtag', ''); {} (1 row) +-- Round-trip non-ASCII data through xpath(). +DO $$ +DECLARE + xml_declaration text := ''; + degree_symbol text; + res xml[]; +BEGIN + -- Per the documentation, xpath() doesn't work on non-ASCII data when + -- the server encoding is not UTF8. The EXCEPTION block below, + -- currently dead code, will be relevant if we remove this limitation. + IF current_setting('server_encoding') <> 'UTF8' THEN + RAISE LOG 'skip: encoding % unsupported for xml', + current_setting('server_encoding'); + RETURN; + END IF; + + degree_symbol := convert_from('\xc2b0', 'UTF8'); + res := xpath('text()', (xml_declaration || + '' || degree_symbol || '')::xml); + IF degree_symbol <> res[1]::text THEN + RAISE 'expected % (%), got % (%)', + degree_symbol, convert_to(degree_symbol, 'UTF8'), + res[1], convert_to(res[1]::text, 'UTF8'); + END IF; +EXCEPTION + -- character with byte sequence 0xc2 0xb0 in encoding "UTF8" has no equivalent in encoding "LATIN8" + WHEN untranslatable_character THEN RAISE LOG 'skip: %', SQLERRM; + -- default conversion function for encoding "UTF8" to "MULE_INTERNAL" does not exist + WHEN undefined_function THEN RAISE LOG 'skip: %', SQLERRM; +END +$$; -- Test xmlexists and xpath_exists SELECT xmlexists('//town[text() = ''Toronto'']' PASSING BY REF 'Bidford-on-AvonCwmbranBristol'); xmlexists diff --git a/src/test/regress/expected/xml_1.out b/src/test/regress/expected/xml_1.out index d3bd8c9..1a9efa2 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', ''); ^ 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 $$ +DECLARE + xml_declaration text := ''; + degree_symbol text; + res xml[]; +BEGIN + -- Per the documentation, xpath() doesn't work on non-ASCII data when + -- the server encoding is not UTF8. The EXCEPTION block below, + -- currently dead code, will be relevant if we remove this limitation. + IF current_setting('server_encoding') <> 'UTF8' THEN + RAISE LOG 'skip: encoding % unsupported for xml', + current_setting('server_encoding'); + RETURN; + END IF; + + degree_symbol := convert_from('\xc2b0', 'UTF8'); + res := xpath('text()', (xml_declaration || + '' || degree_symbol || '')::xml); + IF degree_symbol <> res[1]::text THEN + RAISE 'expected % (%), got % (%)', + degree_symbol, convert_to(degree_symbol, 'UTF8'), + res[1], convert_to(res[1]::text, 'UTF8'); + END IF; +EXCEPTION + -- character with byte sequence 0xc2 0xb0 in encoding "UTF8" has no equivalent in encoding "LATIN8" + WHEN untranslatable_character THEN RAISE LOG 'skip: %', SQLERRM; + -- default conversion function for encoding "UTF8" to "MULE_INTERNAL" does not exist + WHEN undefined_function THEN RAISE LOG 'skip: %', SQLERRM; +END +$$; +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 'Bidford-on-AvonCwmbranBristol'); ERROR: unsupported XML feature diff --git a/src/test/regress/expected/xml_2.out b/src/test/regress/expected/xml_2.out index ff77132..3868da1 100644 --- a/src/test/regress/expected/xml_2.out +++ b/src/test/regress/expected/xml_2.out @@ -650,6 +650,37 @@ SELECT xpath('/nosuchtag', ''); {} (1 row) +-- Round-trip non-ASCII data through xpath(). +DO $$ +DECLARE + xml_declaration text := ''; + degree_symbol text; + res xml[]; +BEGIN + -- Per the documentation, xpath() doesn't work on non-ASCII data when + -- the server encoding is not UTF8. The EXCEPTION block below, + -- currently dead code, will be relevant if we remove this limitation. + IF current_setting('server_encoding') <> 'UTF8' THEN + RAISE LOG 'skip: encoding % unsupported for xml', + current_setting('server_encoding'); + RETURN; + END IF; + + degree_symbol := convert_from('\xc2b0', 'UTF8'); + res := xpath('text()', (xml_declaration || + '' || degree_symbol || '')::xml); + IF degree_symbol <> res[1]::text THEN + RAISE 'expected % (%), got % (%)', + degree_symbol, convert_to(degree_symbol, 'UTF8'), + res[1], convert_to(res[1]::text, 'UTF8'); + END IF; +EXCEPTION + -- character with byte sequence 0xc2 0xb0 in encoding "UTF8" has no equivalent in encoding "LATIN8" + WHEN untranslatable_character THEN RAISE LOG 'skip: %', SQLERRM; + -- default conversion function for encoding "UTF8" to "MULE_INTERNAL" does not exist + WHEN undefined_function THEN RAISE LOG 'skip: %', SQLERRM; +END +$$; -- Test xmlexists and xpath_exists SELECT xmlexists('//town[text() = ''Toronto'']' PASSING BY REF 'Bidford-on-AvonCwmbranBristol'); xmlexists diff --git a/src/test/regress/sql/xml.sql b/src/test/regress/sql/xml.sql index eb4687f..fdb51c9 100644 --- a/src/test/regress/sql/xml.sql +++ b/src/test/regress/sql/xml.sql @@ -189,6 +189,38 @@ SELECT xpath('count(//*)=3', ''); SELECT xpath('name(/*)', ''); SELECT xpath('/nosuchtag', ''); +-- Round-trip non-ASCII data through xpath(). +DO $$ +DECLARE + xml_declaration text := ''; + degree_symbol text; + res xml[]; +BEGIN + -- Per the documentation, xpath() doesn't work on non-ASCII data when + -- the server encoding is not UTF8. The EXCEPTION block below, + -- currently dead code, will be relevant if we remove this limitation. + IF current_setting('server_encoding') <> 'UTF8' THEN + RAISE LOG 'skip: encoding % unsupported for xml', + current_setting('server_encoding'); + RETURN; + END IF; + + degree_symbol := convert_from('\xc2b0', 'UTF8'); + res := xpath('text()', (xml_declaration || + '' || degree_symbol || '')::xml); + IF degree_symbol <> res[1]::text THEN + RAISE 'expected % (%), got % (%)', + degree_symbol, convert_to(degree_symbol, 'UTF8'), + res[1], convert_to(res[1]::text, 'UTF8'); + END IF; +EXCEPTION + -- character with byte sequence 0xc2 0xb0 in encoding "UTF8" has no equivalent in encoding "LATIN8" + WHEN untranslatable_character THEN RAISE LOG 'skip: %', SQLERRM; + -- default conversion function for encoding "UTF8" to "MULE_INTERNAL" does not exist + WHEN undefined_function THEN RAISE LOG 'skip: %', SQLERRM; +END +$$; + -- Test xmlexists and xpath_exists SELECT xmlexists('//town[text() = ''Toronto'']' PASSING BY REF 'Bidford-on-AvonCwmbranBristol'); SELECT xmlexists('//town[text() = ''Cwmbran'']' PASSING BY REF 'Bidford-on-AvonCwmbranBristol');