From: Bruce Momjian Date: Thu, 22 Mar 2007 20:14:58 +0000 (+0000) Subject: Add xmlpath() to evaluate XPath expressions, with namespaces support. X-Git-Tag: REL8_3_BETA1~993 X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=e651bcf3f623265fc0cea9d8ade6937ce89b73eb;p=postgresql Add xmlpath() to evaluate XPath expressions, with namespaces support. Nikolay Samokhvalov --- diff --git a/src/backend/utils/adt/xml.c b/src/backend/utils/adt/xml.c index fa82837fd0..00f661df9d 100644 --- a/src/backend/utils/adt/xml.c +++ b/src/backend/utils/adt/xml.c @@ -7,7 +7,7 @@ * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California * - * $PostgreSQL: pgsql/src/backend/utils/adt/xml.c,v 1.35 2007/03/15 23:12:06 tgl Exp $ + * $PostgreSQL: pgsql/src/backend/utils/adt/xml.c,v 1.36 2007/03/22 20:14:58 momjian Exp $ * *------------------------------------------------------------------------- */ @@ -47,6 +47,8 @@ #include #include #include +#include +#include #endif /* USE_LIBXML */ #include "catalog/namespace.h" @@ -67,6 +69,7 @@ #include "utils/datetime.h" #include "utils/lsyscache.h" #include "utils/memutils.h" +#include "access/tupmacs.h" #include "utils/xml.h" @@ -88,6 +91,7 @@ static xmlChar *xml_text2xmlChar(text *in); static int parse_xml_decl(const xmlChar *str, size_t *lenp, xmlChar **version, xmlChar **encoding, int *standalone); static bool print_xml_decl(StringInfo buf, const xmlChar *version, pg_enc encoding, int standalone); static xmlDocPtr xml_parse(text *data, XmlOptionType xmloption_arg, bool preserve_whitespace, xmlChar *encoding); +static text *xml_xmlnodetotext(xmlNodePtr cur); #endif /* USE_LIBXML */ @@ -1463,7 +1467,6 @@ map_xml_name_to_sql_identifier(char *name) return buf.data; } - /* * Map SQL value to XML value; see SQL/XML:2003 section 9.16. */ @@ -2403,3 +2406,247 @@ SPI_sql_row_to_xmlelement(int rownum, StringInfo result, char *tablename, bool n else appendStringInfoString(result, "\n\n"); } + + +/* + * XPath related functions + */ + +#ifdef USE_LIBXML +/* + * Convert XML node to text (return value only, it's not dumping) + */ +text * +xml_xmlnodetotext(xmlNodePtr cur) +{ + xmlChar *str; + text *result; + size_t len; + + str = xmlXPathCastNodeToString(cur); + len = strlen((char *) str); + result = (text *) palloc(len + VARHDRSZ); + SET_VARSIZE(result, len + VARHDRSZ); + memcpy(VARDATA(result), str, len); + + return result; +} +#endif + +/* + * Evaluate XPath expression and return array of XML values. + * As we have no support of XQuery sequences yet, this functions seems + * to be the most useful one (array of XML functions plays a role of + * some kind of substritution for XQuery sequences). + + * Workaround here: we parse XML data in different way to allow XPath for + * fragments (see "XPath for fragment" TODO comment inside). + */ +Datum +xmlpath(PG_FUNCTION_ARGS) +{ +#ifdef USE_LIBXML + ArrayBuildState *astate = NULL; + xmlParserCtxtPtr ctxt = NULL; + xmlDocPtr doc = NULL; + xmlXPathContextPtr xpathctx = NULL; + xmlXPathCompExprPtr xpathcomp = NULL; + xmlXPathObjectPtr xpathobj = NULL; + int32 len, xpath_len; + xmlChar *string, *xpath_expr; + bool res_is_null = FALSE; + int i; + xmltype *data; + text *xpath_expr_text; + ArrayType *namespaces; + int *dims, ndims, ns_count = 0, bitmask = 1; + char *ptr; + bits8 *bitmap; + char **ns_names = NULL, **ns_uris = NULL; + int16 typlen; + bool typbyval; + char typalign; + + /* the function is not strict, we must check first two args */ + if (PG_ARGISNULL(0) || PG_ARGISNULL(1)) + PG_RETURN_NULL(); + + xpath_expr_text = PG_GETARG_TEXT_P(0); + data = PG_GETARG_XML_P(1); + + /* Namespace mappings passed as text[]. + * Assume that 2-dimensional array has been passed, + * the 1st subarray is array of names, the 2nd -- array of URIs, + * example: ARRAY[ARRAY['myns', 'myns2'], ARRAY['http://example.com', 'http://example2.com']]. + */ + if (!PG_ARGISNULL(2)) + { + namespaces = PG_GETARG_ARRAYTYPE_P(2); + ndims = ARR_NDIM(namespaces); + dims = ARR_DIMS(namespaces); + + /* Sanity check */ + if (ndims != 2) + ereport(ERROR, (errmsg("invalid array passed for namespace mappings"), + errdetail("Only 2-dimensional array may be used for namespace mappings."))); + + Assert(ARR_ELEMTYPE(namespaces) == TEXTOID); + + ns_count = ArrayGetNItems(ndims, dims) / 2; + get_typlenbyvalalign(ARR_ELEMTYPE(namespaces), + &typlen, &typbyval, &typalign); + ns_names = (char **) palloc(ns_count * sizeof(char *)); + ns_uris = (char **) palloc(ns_count * sizeof(char *)); + ptr = ARR_DATA_PTR(namespaces); + bitmap = ARR_NULLBITMAP(namespaces); + bitmask = 1; + + for (i = 0; i < ns_count * 2; i++) + { + if (bitmap && (*bitmap & bitmask) == 0) + ereport(ERROR, (errmsg("neither namespace nor URI may be NULL"))); /* TODO: better message */ + else + { + if (i < ns_count) + ns_names[i] = DatumGetCString(DirectFunctionCall1(textout, + PointerGetDatum(ptr))); + else + ns_uris[i - ns_count] = DatumGetCString(DirectFunctionCall1(textout, + PointerGetDatum(ptr))); + ptr = att_addlength(ptr, typlen, PointerGetDatum(ptr)); + ptr = (char *) att_align(ptr, typalign); + } + + /* advance bitmap pointer if any */ + if (bitmap) + { + bitmask <<= 1; + if (bitmask == 0x100) + { + bitmap++; + bitmask = 1; + } + } + } + } + + len = VARSIZE(data) - VARHDRSZ; + xpath_len = VARSIZE(xpath_expr_text) - VARHDRSZ; + if (xpath_len == 0) + ereport(ERROR, (errmsg("empty XPath expression"))); + + if (xmlStrncmp((xmlChar *) VARDATA(data), (xmlChar *) "..." as dummy root element to enable XPath for fragments */ + /* TODO: (XPath for fragment) find better solution to work with XML fragment! */ + string = xmlStrncatNew((xmlChar *) "", (xmlChar *) VARDATA(data), len); + string = xmlStrncat(string, (xmlChar *) "", 5); + len += 7; + xpath_expr = xmlStrncatNew((xmlChar *) "/x", (xmlChar *) VARDATA(xpath_expr_text), xpath_len); + len += 2; + } + + xml_init(); + + PG_TRY(); + { + /* redundant XML parsing (two parsings for the same value in the same session are possible) */ + ctxt = xmlNewParserCtxt(); + if (ctxt == NULL) + xml_ereport(ERROR, ERRCODE_INTERNAL_ERROR, + "could not allocate parser context"); + doc = xmlCtxtReadMemory(ctxt, (char *) string, len, NULL, NULL, 0); + if (doc == NULL) + xml_ereport(ERROR, ERRCODE_INVALID_XML_DOCUMENT, + "could not parse XML data"); + xpathctx = xmlXPathNewContext(doc); + if (xpathctx == NULL) + xml_ereport(ERROR, ERRCODE_INTERNAL_ERROR, + "could not allocate XPath context"); + xpathctx->node = xmlDocGetRootElement(doc); + if (xpathctx->node == NULL) + xml_ereport(ERROR, ERRCODE_INTERNAL_ERROR, + "could not find root XML element"); + + /* register namespaces, if any */ + if ((ns_count > 0) && ns_names && ns_uris) + for (i = 0; i < ns_count; i++) + if (0 != xmlXPathRegisterNs(xpathctx, (xmlChar *) ns_names[i], (xmlChar *) ns_uris[i])) + ereport(ERROR, + (errmsg("could not register XML namespace with prefix=\"%s\" and href=\"%s\"", ns_names[i], ns_uris[i]))); + + xpathcomp = xmlXPathCompile(xpath_expr); + if (xpathcomp == NULL) + xml_ereport(ERROR, ERRCODE_INTERNAL_ERROR, + "invalid XPath expression"); /* TODO: show proper XPath error details */ + + xpathobj = xmlXPathCompiledEval(xpathcomp, xpathctx); + xmlXPathFreeCompExpr(xpathcomp); + if (xpathobj == NULL) + ereport(ERROR, (errmsg("could not create XPath object"))); + + if (xpathobj->nodesetval == NULL) + res_is_null = TRUE; + + if (!res_is_null && xpathobj->nodesetval->nodeNr == 0) + /* TODO maybe empty array should be here, not NULL? (if so -- fix segfault) */ + /*PG_RETURN_ARRAYTYPE_P(makeArrayResult(astate, CurrentMemoryContext));*/ + res_is_null = TRUE; + + if (!res_is_null) + for (i = 0; i < xpathobj->nodesetval->nodeNr; i++) + { + Datum elem; + bool elemisnull = false; + elem = PointerGetDatum(xml_xmlnodetotext(xpathobj->nodesetval->nodeTab[i])); + astate = accumArrayResult(astate, elem, + elemisnull, XMLOID, + CurrentMemoryContext); + } + + xmlXPathFreeObject(xpathobj); + xmlXPathFreeContext(xpathctx); + xmlFreeParserCtxt(ctxt); + xmlFreeDoc(doc); + xmlCleanupParser(); + } + PG_CATCH(); + { + if (xpathcomp) + xmlXPathFreeCompExpr(xpathcomp); + if (xpathobj) + xmlXPathFreeObject(xpathobj); + if (xpathctx) + xmlXPathFreeContext(xpathctx); + if (doc) + xmlFreeDoc(doc); + if (ctxt) + xmlFreeParserCtxt(ctxt); + xmlCleanupParser(); + + PG_RE_THROW(); + } + PG_END_TRY(); + + if (res_is_null) + { + PG_RETURN_NULL(); + } + else + { + PG_RETURN_ARRAYTYPE_P(makeArrayResult(astate, CurrentMemoryContext)); + } +#else + NO_XML_SUPPORT(); + return 0; +#endif +} diff --git a/src/include/catalog/pg_proc.h b/src/include/catalog/pg_proc.h index 8007129a1b..0a096972ed 100644 --- a/src/include/catalog/pg_proc.h +++ b/src/include/catalog/pg_proc.h @@ -7,7 +7,7 @@ * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California * - * $PostgreSQL: pgsql/src/include/catalog/pg_proc.h,v 1.449 2007/03/20 05:45:00 neilc Exp $ + * $PostgreSQL: pgsql/src/include/catalog/pg_proc.h,v 1.450 2007/03/22 20:14:58 momjian Exp $ * * NOTES * The script catalog/genbki.sh reads this file and generates .bki @@ -4095,6 +4095,10 @@ DESCR("map table contents and structure to XML and XML Schema"); DATA(insert OID = 2930 ( query_to_xml_and_xmlschema PGNSP PGUID 12 100 0 f f t f s 4 142 "25 16 16 25" _null_ _null_ "{query,nulls,tableforest,targetns}" query_to_xml_and_xmlschema - _null_ )); DESCR("map query result and structure to XML and XML Schema"); +DATA(insert OID = 2931 ( xmlpath PGNSP PGUID 12 1 0 f f f f i 3 143 "25 142 1009" _null_ _null_ _null_ xmlpath - _null_ )); +DESCR("evaluate XPath expression, with namespaces support"); +DATA(insert OID = 2932 ( xmlpath PGNSP PGUID 14 1 0 f f f f i 2 143 "25 142" _null_ _null_ _null_ "select pg_catalog.xmlpath($1, $2, NULL)" - _null_ )); +DESCR("evaluate XPath expression"); /* uuid */ DATA(insert OID = 2952 ( uuid_in PGNSP PGUID 12 1 0 f f t f i 1 2950 "2275" _null_ _null_ _null_ uuid_in - _null_ )); diff --git a/src/include/utils/xml.h b/src/include/utils/xml.h index 7cf23b6706..ef06e41b92 100644 --- a/src/include/utils/xml.h +++ b/src/include/utils/xml.h @@ -7,7 +7,7 @@ * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California * - * $PostgreSQL: pgsql/src/include/utils/xml.h,v 1.16 2007/02/16 07:46:55 petere Exp $ + * $PostgreSQL: pgsql/src/include/utils/xml.h,v 1.17 2007/03/22 20:14:58 momjian Exp $ * *------------------------------------------------------------------------- */ @@ -36,6 +36,7 @@ extern Datum xmlconcat2(PG_FUNCTION_ARGS); extern Datum texttoxml(PG_FUNCTION_ARGS); extern Datum xmltotext(PG_FUNCTION_ARGS); extern Datum xmlvalidate(PG_FUNCTION_ARGS); +extern Datum xmlpath(PG_FUNCTION_ARGS); extern Datum table_to_xml(PG_FUNCTION_ARGS); extern Datum query_to_xml(PG_FUNCTION_ARGS); diff --git a/src/test/regress/expected/xml.out b/src/test/regress/expected/xml.out index 97c30600e8..189c22113b 100644 --- a/src/test/regress/expected/xml.out +++ b/src/test/regress/expected/xml.out @@ -401,3 +401,33 @@ SELECT table_name, view_definition FROM information_schema.views xmlview9 | SELECT XMLSERIALIZE(CONTENT 'good'::"xml" AS text) AS "xmlserialize"; (9 rows) +-- Text XPath expressions evaluation +SELECT xmlpath('/value', data) FROM xmltest; + xmlpath +--------- + {one} + {two} +(2 rows) + +SELECT xmlpath(NULL, NULL) IS NULL FROM xmltest; + ?column? +---------- + t + t +(2 rows) + +SELECT xmlpath('', ''); +ERROR: empty XPath expression +CONTEXT: SQL function "xmlpath" statement 1 +SELECT xmlpath('//text()', 'number one'); + xmlpath +---------------- + {"number one"} +(1 row) + +SELECT xmlpath('//loc:piece/@id', 'number one', ARRAY[ARRAY['loc'], ARRAY['http://127.0.0.1']]); + xmlpath +--------- + {1,2} +(1 row) + diff --git a/src/test/regress/expected/xml_1.out b/src/test/regress/expected/xml_1.out index 95b9d73615..3ba6e58d2d 100644 --- a/src/test/regress/expected/xml_1.out +++ b/src/test/regress/expected/xml_1.out @@ -197,3 +197,18 @@ SELECT table_name, view_definition FROM information_schema.views xmlview5 | SELECT XMLPARSE(CONTENT 'x'::text STRIP WHITESPACE) AS "xmlparse"; (2 rows) +-- Text XPath expressions evaluation +SELECT xmlpath('/value', data) FROM xmltest; + xmlpath +--------- +(0 rows) + +SELECT xmlpath(NULL, NULL) IS NULL FROM xmltest; +ERROR: no XML support in this installation +CONTEXT: SQL function "xmlpath" statement 1 +SELECT xmlpath('', ''); +ERROR: no XML support in this installation +SELECT xmlpath('//text()', 'number one'); +ERROR: no XML support in this installation +SELECT xmlpath('//loc:piece/@id', 'number one', ARRAY[ARRAY['loc'], ARRAY['http://127.0.0.1']]); +ERROR: no XML support in this installation diff --git a/src/test/regress/sql/xml.sql b/src/test/regress/sql/xml.sql index 6ed9d8c47a..32ac15610c 100644 --- a/src/test/regress/sql/xml.sql +++ b/src/test/regress/sql/xml.sql @@ -144,3 +144,11 @@ CREATE VIEW xmlview9 AS SELECT xmlserialize(content 'good' as text); SELECT table_name, view_definition FROM information_schema.views WHERE table_name LIKE 'xmlview%' ORDER BY 1; + +-- Text XPath expressions evaluation + +SELECT xmlpath('/value', data) FROM xmltest; +SELECT xmlpath(NULL, NULL) IS NULL FROM xmltest; +SELECT xmlpath('', ''); +SELECT xmlpath('//text()', 'number one'); +SELECT xmlpath('//loc:piece/@id', 'number one', ARRAY[ARRAY['loc'], ARRAY['http://127.0.0.1']]);