From 251cf2e27bec98274e8bb002608680bdc211319e Mon Sep 17 00:00:00 2001 From: Alvaro Herrera Date: Thu, 7 Mar 2019 15:21:56 -0300 Subject: [PATCH] Fix minor deficiencies in XMLTABLE, xpath(), xmlexists() MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Correctly process nodes of more types than previously. In some cases, nodes were being ignored (nothing was output); in other cases, trying to return them resulted in errors about unrecognized nodes. In yet other cases, necessary escaping (of XML special characters) was not being done. Fix all those (as far as the authors could find) and add regression tests cases verifying the new behavior. I (Álvaro) was of two minds about backpatching these changes. They do seem bugfixes that would benefit most users of the affected functions; but on the other hand it would change established behavior in minor releases, so it seems prudent not to. Authors: Pavel Stehule, Markus Winand, Chapman Flack Discussion: https://postgr.es/m/CAFj8pRA6J25CtAZ2TuRvxK3gat7-bBUYh0rfE2yM7Hj9GD14Dg@mail.gmail.com https://postgr.es/m/8BDB0627-2105-4564-AA76-7849F028B96E@winand.at The elephant in the room as pointed out by Chapman Flack, not fixed in this commit, is that we still have XMLTABLE operating on XPath 1.0 instead of the standard-mandated XQuery (or even its subset XPath 2.0). Fixing that is a major undertaking, however. --- doc/src/sgml/func.sgml | 6 +- src/backend/utils/adt/xml.c | 155 +++++++++++++++------------- src/test/regress/expected/xml.out | 27 ++++- src/test/regress/expected/xml_1.out | 19 ++++ src/test/regress/expected/xml_2.out | 27 ++++- src/test/regress/sql/xml.sql | 8 ++ 6 files changed, 164 insertions(+), 78 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index 7e14478db7..03859a78ea 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -11010,9 +11010,9 @@ $$ AS data; SELECT xmltable.* FROM xmlelements, XMLTABLE('/root' PASSING data COLUMNS element text); - element ----------------------- - Hello2a2 bbbCC + element +------------------------- + Hello2a2 bbbxxxCC ]]> diff --git a/src/backend/utils/adt/xml.c b/src/backend/utils/adt/xml.c index f36aab899a..28b3eaaa20 100644 --- a/src/backend/utils/adt/xml.c +++ b/src/backend/utils/adt/xml.c @@ -1176,6 +1176,36 @@ pg_xmlCharStrndup(const char *str, size_t len) return result; } +/* + * Copy xmlChar string to PostgreSQL-owned memory, freeing the input. + * + * The input xmlChar is freed regardless of success of the copy. + */ +static char * +xml_pstrdup_and_free(xmlChar *str) +{ + char *result; + + if (str) + { + PG_TRY(); + { + result = pstrdup((char *) str); + } + PG_CATCH(); + { + xmlFree(str); + PG_RE_THROW(); + } + PG_END_TRY(); + xmlFree(str); + } + else + result = NULL; + + return result; +} + /* * str is the null-terminated input string. Remaining arguments are * output arguments; each can be NULL if value is not wanted. @@ -3678,15 +3708,17 @@ SPI_sql_row_to_xmlelement(uint64 rownum, StringInfo result, char *tablename, #ifdef USE_LIBXML /* - * Convert XML node to text (dump subtree in case of element, - * return value otherwise) + * Convert XML node to text. + * + * For attribute and text nodes, return the escaped text. For anything else, + * dump the whole subtree. */ static text * xml_xmlnodetoxmltype(xmlNodePtr cur, PgXmlErrorContext *xmlerrcxt) { xmltype *result; - if (cur->type == XML_ELEMENT_NODE) + if (cur->type != XML_ATTRIBUTE_NODE && cur->type != XML_TEXT_NODE) { xmlBufferPtr buf; xmlNodePtr cur_copy; @@ -4479,9 +4511,9 @@ XmlTableGetValue(TableFuncScanState *state, int colnum, /* * There are four possible cases, depending on the number of nodes * returned by the XPath expression and the type of the target column: - * a) XPath returns no nodes. b) One node is returned, and column is - * of type XML. c) One node, column type other than XML. d) Multiple - * nodes are returned. + * a) XPath returns no nodes. b) The target type is XML (return all + * as XML). For non-XML return types: c) One node (return content). + * d) Multiple nodes (error). */ if (xpathobj->type == XPATH_NODESET) { @@ -4494,84 +4526,69 @@ XmlTableGetValue(TableFuncScanState *state, int colnum, { *isnull = true; } - else if (count == 1 && typid == XMLOID) - { - text *textstr; - - /* simple case, result is one value */ - textstr = xml_xmlnodetoxmltype(xpathobj->nodesetval->nodeTab[0], - xtCxt->xmlerrcxt); - cstr = text_to_cstring(textstr); - } - else if (count == 1) + else { - xmlChar *str; - xmlNodePtr node; - - /* - * Most nodes (elements and even attributes) store their data - * in children nodes. If they don't have children nodes, it - * means that they are empty (e.g. ). Text nodes and - * CDATA sections are an exception: they don't have children - * but have content in the Text/CDATA node itself. - */ - node = xpathobj->nodesetval->nodeTab[0]; - if (node->type != XML_CDATA_SECTION_NODE && - node->type != XML_TEXT_NODE) - node = node->xmlChildrenNode; - - str = xmlNodeListGetString(xtCxt->doc, node, 1); - if (str != NULL) + if (typid == XMLOID) { - PG_TRY(); - { - cstr = pstrdup((char *) str); - } - PG_CATCH(); + text *textstr; + StringInfoData str; + + /* Concatenate serialized values */ + initStringInfo(&str); + for (int i = 0; i < count; i++) { - xmlFree(str); - PG_RE_THROW(); + textstr = + xml_xmlnodetoxmltype(xpathobj->nodesetval->nodeTab[i], + xtCxt->xmlerrcxt); + + appendStringInfoText(&str, textstr); } - PG_END_TRY(); - xmlFree(str); + cstr = str.data; } else { - /* Ensure mapping of empty tags to PostgreSQL values. */ - cstr = ""; + xmlChar *str; + + if (count > 1) + ereport(ERROR, + (errcode(ERRCODE_CARDINALITY_VIOLATION), + errmsg("more than one value returned by column XPath expression"))); + + str = xmlXPathCastNodeSetToString(xpathobj->nodesetval); + cstr = str ? xml_pstrdup_and_free(str) : ""; } } + } + else if (xpathobj->type == XPATH_STRING) + { + /* Content should be escaped when target will be XML */ + if (typid == XMLOID) + cstr = escape_xml((char *) xpathobj->stringval); else - { - StringInfoData str; - int i; + cstr = (char *) xpathobj->stringval; + } + else if (xpathobj->type == XPATH_BOOLEAN) + { + char typcategory; + bool typispreferred; + xmlChar *str; - Assert(count > 1); + /* Allow implicit casting from boolean to numbers */ + get_type_category_preferred(typid, &typcategory, &typispreferred); - /* - * When evaluating the XPath expression returns multiple - * nodes, the result is the concatenation of them all. The - * target type must be XML. - */ - if (typid != XMLOID) - ereport(ERROR, - (errcode(ERRCODE_CARDINALITY_VIOLATION), - errmsg("more than one value returned by column XPath expression"))); + if (typcategory != TYPCATEGORY_NUMERIC) + str = xmlXPathCastBooleanToString(xpathobj->boolval); + else + str = xmlXPathCastNumberToString(xmlXPathCastBooleanToNumber(xpathobj->boolval)); - /* Concatenate serialized values */ - initStringInfo(&str); - for (i = 0; i < count; i++) - { - appendStringInfoText(&str, - xml_xmlnodetoxmltype(xpathobj->nodesetval->nodeTab[i], - xtCxt->xmlerrcxt)); - } - cstr = str.data; - } + cstr = xml_pstrdup_and_free(str); } - else if (xpathobj->type == XPATH_STRING) + else if (xpathobj->type == XPATH_NUMBER) { - cstr = (char *) xpathobj->stringval; + xmlChar *str; + + str = xmlXPathCastNumberToString(xpathobj->floatval); + cstr = xml_pstrdup_and_free(str); } else elog(ERROR, "unexpected XPath object type %u", xpathobj->type); diff --git a/src/test/regress/expected/xml.out b/src/test/regress/expected/xml.out index 6e1f885112..2085fa0391 100644 --- a/src/test/regress/expected/xml.out +++ b/src/test/regress/expected/xml.out @@ -1210,9 +1210,9 @@ SELECT xmltable.* FROM xmldata, LATERAL xmltable('/ROWS/ROW[COUNTRY_NAME="Japan" (2 rows) SELECT * FROM xmltable('/root' passing 'a1aa2a bbbbxxxcccc' COLUMNS element text); - element -------------------- - a1aa2a bbbbcccc + element +---------------------- + a1aa2a bbbbxxxcccc (1 row) SELECT * FROM xmltable('/root' passing 'a1aa2a bbbbxxxcccc' COLUMNS element text PATH 'element/text()'); -- should fail @@ -1493,3 +1493,24 @@ SELECT xmltable.* FROM xmltest2, LATERAL xmltable(('/d/r/' || lower(_path) || 'c 14 (4 rows) +-- XPath result can be boolean or number too +SELECT * FROM XMLTABLE('*' PASSING 'a' COLUMNS a xml PATH '.', b text PATH '.', c text PATH '"hi"', d boolean PATH '. = "a"', e integer PATH 'string-length(.)'); + a | b | c | d | e +----------+---+----+---+--- + a | a | hi | t | 1 +(1 row) + +\x +SELECT * FROM XMLTABLE('*' PASSING 'pre&deeppost' COLUMNS x xml PATH 'node()', y xml PATH '/'); +-[ RECORD 1 ]----------------------------------------------------------- +x | pre&deeppost +y | pre&deeppost+ + | + +\x +SELECT * FROM XMLTABLE('.' PASSING XMLELEMENT(NAME a) columns a varchar(20) PATH '""', b xml PATH '""'); + a | b +--------+-------------- + | <foo/> +(1 row) + diff --git a/src/test/regress/expected/xml_1.out b/src/test/regress/expected/xml_1.out index 0eba424346..7f86696973 100644 --- a/src/test/regress/expected/xml_1.out +++ b/src/test/regress/expected/xml_1.out @@ -1343,3 +1343,22 @@ SELECT xmltable.* FROM xmltest2, LATERAL xmltable(('/d/r/' || lower(_path) || 'c --- (0 rows) +-- XPath result can be boolean or number too +SELECT * FROM XMLTABLE('*' PASSING 'a' COLUMNS a xml PATH '.', b text PATH '.', c text PATH '"hi"', d boolean PATH '. = "a"', e integer PATH 'string-length(.)'); +ERROR: unsupported XML feature +LINE 1: SELECT * FROM XMLTABLE('*' PASSING 'a' COLUMNS a xml ... + ^ +DETAIL: This functionality requires the server to be built with libxml support. +HINT: You need to rebuild PostgreSQL using --with-libxml. +\x +SELECT * FROM XMLTABLE('*' PASSING 'pre&deeppost' COLUMNS x xml PATH 'node()', y xml PATH '/'); +ERROR: unsupported XML feature +LINE 1: SELECT * FROM XMLTABLE('*' PASSING 'pre"', b xml PATH '""'); +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. diff --git a/src/test/regress/expected/xml_2.out b/src/test/regress/expected/xml_2.out index 3ec56e4c54..510b09bd03 100644 --- a/src/test/regress/expected/xml_2.out +++ b/src/test/regress/expected/xml_2.out @@ -1190,9 +1190,9 @@ SELECT xmltable.* FROM xmldata, LATERAL xmltable('/ROWS/ROW[COUNTRY_NAME="Japan" (2 rows) SELECT * FROM xmltable('/root' passing 'a1aa2a bbbbxxxcccc' COLUMNS element text); - element -------------------- - a1aa2a bbbbcccc + element +---------------------- + a1aa2a bbbbxxxcccc (1 row) SELECT * FROM xmltable('/root' passing 'a1aa2a bbbbxxxcccc' COLUMNS element text PATH 'element/text()'); -- should fail @@ -1473,3 +1473,24 @@ SELECT xmltable.* FROM xmltest2, LATERAL xmltable(('/d/r/' || lower(_path) || 'c 14 (4 rows) +-- XPath result can be boolean or number too +SELECT * FROM XMLTABLE('*' PASSING 'a' COLUMNS a xml PATH '.', b text PATH '.', c text PATH '"hi"', d boolean PATH '. = "a"', e integer PATH 'string-length(.)'); + a | b | c | d | e +----------+---+----+---+--- + a | a | hi | t | 1 +(1 row) + +\x +SELECT * FROM XMLTABLE('*' PASSING 'pre&deeppost' COLUMNS x xml PATH 'node()', y xml PATH '/'); +-[ RECORD 1 ]----------------------------------------------------------- +x | pre&deeppost +y | pre&deeppost+ + | + +\x +SELECT * FROM XMLTABLE('.' PASSING XMLELEMENT(NAME a) columns a varchar(20) PATH '""', b xml PATH '""'); + a | b +--------+-------------- + | <foo/> +(1 row) + diff --git a/src/test/regress/sql/xml.sql b/src/test/regress/sql/xml.sql index 3b91b56d5a..8057a46178 100644 --- a/src/test/regress/sql/xml.sql +++ b/src/test/regress/sql/xml.sql @@ -595,3 +595,11 @@ INSERT INTO xmltest2 VALUES('2', 'D'); SELECT xmltable.* FROM xmltest2, LATERAL xmltable('/d/r' PASSING x COLUMNS a int PATH '' || lower(_path) || 'c'); SELECT xmltable.* FROM xmltest2, LATERAL xmltable(('/d/r/' || lower(_path) || 'c') PASSING x COLUMNS a int PATH '.'); SELECT xmltable.* FROM xmltest2, LATERAL xmltable(('/d/r/' || lower(_path) || 'c') PASSING x COLUMNS a int PATH 'x' DEFAULT ascii(_path) - 54); + +-- XPath result can be boolean or number too +SELECT * FROM XMLTABLE('*' PASSING 'a' COLUMNS a xml PATH '.', b text PATH '.', c text PATH '"hi"', d boolean PATH '. = "a"', e integer PATH 'string-length(.)'); +\x +SELECT * FROM XMLTABLE('*' PASSING 'pre&deeppost' COLUMNS x xml PATH 'node()', y xml PATH '/'); +\x + +SELECT * FROM XMLTABLE('.' PASSING XMLELEMENT(NAME a) columns a varchar(20) PATH '""', b xml PATH '""'); -- 2.40.0