xml.c

postgresql8.3.4源码,开源数据库

/*-------------------------------------------------------------------------
 *
 * xml.c
 *	  XML data type support.
 *
 *
 * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 * $PostgreSQL: pgsql/src/backend/utils/adt/xml.c,v 1.68.2.4 2008/09/16 00:49:49 tgl Exp $
 *
 *-------------------------------------------------------------------------
 */

/*
 * Generally, XML type support is only available when libxml use was
 * configured during the build.  But even if that is not done, the
 * type and all the functions are available, but most of them will
 * fail.  For one thing, this avoids having to manage variant catalog
 * installations.  But it also has nice effects such as that you can
 * dump a database containing XML type data even if the server is not
 * linked with libxml.	Thus, make sure xml_out() works even if nothing
 * else does.
 */

/*
 * Notes on memory management:
 *
 * Via callbacks, libxml is told to use palloc and friends for memory
 * management, within a context that we reset at transaction end (and also at
 * subtransaction abort) to prevent memory leaks.  Resetting at transaction or
 * subtransaction abort is necessary since we might have thrown a longjmp
 * while some data structures were not linked from anywhere persistent.
 * Resetting at transaction commit might not be necessary, but seems a good
 * idea to forestall long-term leaks.
 *
 * Sometimes libxml allocates global structures in the hope that it can reuse
 * them later on.  Therefore, before resetting LibxmlContext, we must tell
 * libxml to discard any global data it has.  The libxml API documentation is
 * not very good about specifying this, but for now we assume that
 * xmlCleanupParser() will get rid of anything we need to worry about.
 *
 * We use palloc --- which will throw a longjmp on error --- for allocation
 * callbacks that officially should act like malloc, ie, return NULL on
 * out-of-memory.  This is a bit risky since there is a chance of leaving
 * persistent libxml data structures in an inconsistent partially-constructed
 * state, perhaps leading to crash in xmlCleanupParser().  However, as of
 * early 2008 it is *known* that libxml can crash on out-of-memory due to
 * inadequate checks for NULL returns, so this behavior seems the lesser
 * of two evils.
 */

#include "postgres.h"

#ifdef USE_LIBXML
#include <libxml/chvalid.h>
#include <libxml/parser.h>
#include <libxml/tree.h>
#include <libxml/uri.h>
#include <libxml/xmlerror.h>
#include <libxml/xmlwriter.h>
#include <libxml/xpath.h>
#include <libxml/xpathInternals.h>
#endif   /* USE_LIBXML */

#include "catalog/namespace.h"
#include "catalog/pg_type.h"
#include "commands/dbcommands.h"
#include "executor/executor.h"
#include "executor/spi.h"
#include "fmgr.h"
#include "lib/stringinfo.h"
#include "libpq/pqformat.h"
#include "mb/pg_wchar.h"
#include "miscadmin.h"
#include "nodes/execnodes.h"
#include "parser/parse_expr.h"
#include "utils/array.h"
#include "utils/builtins.h"
#include "utils/date.h"
#include "utils/datetime.h"
#include "utils/lsyscache.h"
#include "utils/memutils.h"
#include "access/tupmacs.h"
#include "utils/xml.h"


/* GUC variables */
XmlBinaryType xmlbinary;
XmlOptionType xmloption;

#ifdef USE_LIBXML

static StringInfo xml_err_buf = NULL;
static MemoryContext LibxmlContext = NULL;

static void xml_init(void);
static void xml_memory_init(void);
static void xml_memory_cleanup(void);
static void *xml_palloc(size_t size);
static void *xml_repalloc(void *ptr, size_t size);
static void xml_pfree(void *ptr);
static char *xml_pstrdup(const char *string);
static void xml_ereport(int level, int sqlcode, const char *msg);
static void xml_errorHandler(void *ctxt, const char *msg,...);
static void xml_ereport_by_code(int level, int sqlcode,
					const char *msg, int errcode);
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_xmlnodetoxmltype(xmlNodePtr cur);
#endif   /* USE_LIBXML */

static StringInfo query_to_xml_internal(const char *query, char *tablename,
					  const char *xmlschema, bool nulls, bool tableforest,
					  const char *targetns, bool top_level);
static const char *map_sql_table_to_xmlschema(TupleDesc tupdesc, Oid relid,
						 bool nulls, bool tableforest, const char *targetns);
static const char *map_sql_schema_to_xmlschema_types(Oid nspid,
								  List *relid_list, bool nulls,
								  bool tableforest, const char *targetns);
static const char *map_sql_catalog_to_xmlschema_types(List *nspid_list,
								   bool nulls, bool tableforest,
								   const char *targetns);
static const char *map_sql_type_to_xml_name(Oid typeoid, int typmod);
static const char *map_sql_typecoll_to_xmlschema_types(List *tupdesc_list);
static const char *map_sql_type_to_xmlschema_type(Oid typeoid, int typmod);
static void SPI_sql_row_to_xmlelement(int rownum, StringInfo result,
						  char *tablename, bool nulls, bool tableforest,
						  const char *targetns, bool top_level);

#define NO_XML_SUPPORT() \
	ereport(ERROR, \
			(errcode(ERRCODE_FEATURE_NOT_SUPPORTED), \
			 errmsg("unsupported XML feature"), \
			 errdetail("This functionality requires the server to be built with libxml support."), \
			 errhint("You need to rebuild PostgreSQL using --with-libxml.")))


#define _textin(str) DirectFunctionCall1(textin, CStringGetDatum(str))
#define _textout(x) DatumGetCString(DirectFunctionCall1(textout, PointerGetDatum(x)))


/* from SQL/XML:2003 section 4.7 */
#define NAMESPACE_XSD "http://www.w3.org/2001/XMLSchema"
#define NAMESPACE_XSI "http://www.w3.org/2001/XMLSchema-instance"
#define NAMESPACE_SQLXML "http://standards.iso.org/iso/9075/2003/sqlxml"


#ifdef USE_LIBXML

static int
xmlChar_to_encoding(xmlChar * encoding_name)
{
	int			encoding = pg_char_to_encoding((char *) encoding_name);

	if (encoding < 0)
		ereport(ERROR,
				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
				 errmsg("invalid encoding name \"%s\"",
						(char *) encoding_name)));
	return encoding;
}
#endif


Datum
xml_in(PG_FUNCTION_ARGS)
{
#ifdef USE_LIBXML
	char	   *s = PG_GETARG_CSTRING(0);
	size_t		len;
	xmltype    *vardata;
	xmlDocPtr	doc;

	len = strlen(s);
	vardata = palloc(len + VARHDRSZ);
	SET_VARSIZE(vardata, len + VARHDRSZ);
	memcpy(VARDATA(vardata), s, len);

	/*
	 * Parse the data to check if it is well-formed XML data.  Assume that
	 * ERROR occurred if parsing failed.
	 */
	doc = xml_parse(vardata, xmloption, true, NULL);
	xmlFreeDoc(doc);

	PG_RETURN_XML_P(vardata);
#else
	NO_XML_SUPPORT();
	return 0;
#endif
}


#define PG_XML_DEFAULT_VERSION "1.0"


static char *
xml_out_internal(xmltype *x, pg_enc target_encoding)
{
	char	   *str;
	size_t		len;

#ifdef USE_LIBXML
	xmlChar    *version;
	int			standalone;
	int			res_code;
#endif

	len = VARSIZE(x) - VARHDRSZ;
	str = palloc(len + 1);
	memcpy(str, VARDATA(x), len);
	str[len] = '\0';

#ifdef USE_LIBXML
	if ((res_code = parse_xml_decl((xmlChar *) str,
								   &len, &version, NULL, &standalone)) == 0)
	{
		StringInfoData buf;

		initStringInfo(&buf);

		if (!print_xml_decl(&buf, version, target_encoding, standalone))
		{
			/*
			 * If we are not going to produce an XML declaration, eat a single
			 * newline in the original string to prevent empty first lines in
			 * the output.
			 */
			if (*(str + len) == '\n')
				len += 1;
		}
		appendStringInfoString(&buf, str + len);

		if (version)
			xmlFree(version);
		pfree(str);

		return buf.data;
	}

	xml_ereport_by_code(WARNING, ERRCODE_INTERNAL_ERROR,
						"could not parse XML declaration in stored value",
						res_code);
#endif
	return str;
}


Datum
xml_out(PG_FUNCTION_ARGS)
{
	xmltype    *x = PG_GETARG_XML_P(0);

	/*
	 * xml_out removes the encoding property in all cases.	This is because we
	 * cannot control from here whether the datum will be converted to a
	 * different client encoding, so we'd do more harm than good by including
	 * it.
	 */
	PG_RETURN_CSTRING(xml_out_internal(x, 0));
}


Datum
xml_recv(PG_FUNCTION_ARGS)
{
#ifdef USE_LIBXML
	StringInfo	buf = (StringInfo) PG_GETARG_POINTER(0);
	xmltype    *result;
	char	   *str;
	char	   *newstr;
	int			nbytes;
	xmlDocPtr	doc;
	xmlChar    *encoding = NULL;

	/*
	 * Read the data in raw format. We don't know yet what the encoding is, as
	 * that information is embedded in the xml declaration; so we have to
	 * parse that before converting to server encoding.
	 */
	nbytes = buf->len - buf->cursor;
	str = (char *) pq_getmsgbytes(buf, nbytes);

	/*
	 * We need a null-terminated string to pass to parse_xml_decl().  Rather
	 * than make a separate copy, make the temporary result one byte bigger
	 * than it needs to be.
	 */
	result = palloc(nbytes + 1 + VARHDRSZ);
	SET_VARSIZE(result, nbytes + VARHDRSZ);
	memcpy(VARDATA(result), str, nbytes);
	str = VARDATA(result);
	str[nbytes] = '\0';

	parse_xml_decl((xmlChar *) str, NULL, NULL, &encoding, NULL);

	/*
	 * Parse the data to check if it is well-formed XML data.  Assume that
	 * xml_parse will throw ERROR if not.
	 */
	doc = xml_parse(result, xmloption, true, encoding);
	xmlFreeDoc(doc);

	/* Now that we know what we're dealing with, convert to server encoding */
	newstr = (char *) pg_do_encoding_conversion((unsigned char *) str,
												nbytes,
												encoding ?
											  xmlChar_to_encoding(encoding) :
												PG_UTF8,
												GetDatabaseEncoding());

	if (newstr != str)
	{
		pfree(result);

		nbytes = strlen(newstr);

		result = palloc(nbytes + VARHDRSZ);
		SET_VARSIZE(result, nbytes + VARHDRSZ);
		memcpy(VARDATA(result), newstr, nbytes);

		pfree(newstr);
	}

	PG_RETURN_XML_P(result);
#else
	NO_XML_SUPPORT();
	return 0;
#endif
}


Datum
xml_send(PG_FUNCTION_ARGS)
{
	xmltype    *x = PG_GETARG_XML_P(0);
	char	   *outval;
	StringInfoData buf;

	/*
	 * xml_out_internal doesn't convert the encoding, it just prints the right
	 * declaration. pq_sendtext will do the conversion.
	 */
	outval = xml_out_internal(x, pg_get_client_encoding());

	pq_begintypsend(&buf);
	pq_sendtext(&buf, outval, strlen(outval));
	pfree(outval);
	PG_RETURN_BYTEA_P(pq_endtypsend(&buf));
}


#ifdef USE_LIBXML
static void
appendStringInfoText(StringInfo str, const text *t)
{
	appendBinaryStringInfo(str, VARDATA(t), VARSIZE(t) - VARHDRSZ);
}
#endif


static xmltype *
stringinfo_to_xmltype(StringInfo buf)
{
	int32		len;
	xmltype    *result;

	len = buf->len + VARHDRSZ;
	result = palloc(len);
	SET_VARSIZE(result, len);
	memcpy(VARDATA(result), buf->data, buf->len);

	return result;
}


static xmltype *
cstring_to_xmltype(const char *string)
{
	int32		len;
	xmltype    *result;

	len = strlen(string) + VARHDRSZ;
	result = palloc(len);
	SET_VARSIZE(result, len);
	memcpy(VARDATA(result), string, len - VARHDRSZ);

	return result;
}


#ifdef USE_LIBXML
static xmltype *
xmlBuffer_to_xmltype(xmlBufferPtr buf)
{
	int32		len;
	xmltype    *result;

	len = xmlBufferLength(buf) + VARHDRSZ;
	result = palloc(len);
	SET_VARSIZE(result, len);
	memcpy(VARDATA(result), xmlBufferContent(buf), len - VARHDRSZ);

	return result;
}
#endif


Datum
xmlcomment(PG_FUNCTION_ARGS)
{
#ifdef USE_LIBXML
	text	   *arg = PG_GETARG_TEXT_P(0);
	char	   *argdata = VARDATA(arg);
	int			len = VARSIZE(arg) - VARHDRSZ;
	StringInfoData buf;
	int			i;

	/* check for "--" in string or "-" at the end */
	for (i = 1; i < len; i++)
	{
		if (argdata[i] == '-' && argdata[i - 1] == '-')
			ereport(ERROR,
					(errcode(ERRCODE_INVALID_XML_COMMENT),
					 errmsg("invalid XML comment")));
	}
	if (len > 0 && argdata[len - 1] == '-')
		ereport(ERROR,
				(errcode(ERRCODE_INVALID_XML_COMMENT),
				 errmsg("invalid XML comment")));

	initStringInfo(&buf);
	appendStringInfo(&buf, "<!--");
	appendStringInfoText(&buf, arg);
	appendStringInfo(&buf, "-->");

	PG_RETURN_XML_P(stringinfo_to_xmltype(&buf));
#else
	NO_XML_SUPPORT();
	return 0;
#endif
}



/*
 * TODO: xmlconcat needs to merge the notations and unparsed entities
 * of the argument values.	Not very important in practice, though.
 */
xmltype *
xmlconcat(List *args)
{
#ifdef USE_LIBXML
	int			global_standalone = 1;
	xmlChar    *global_version = NULL;
	bool		global_version_no_value = false;
	StringInfoData buf;
	ListCell   *v;

	initStringInfo(&buf);
	foreach(v, args)
	{
		xmltype    *x = DatumGetXmlP(PointerGetDatum(lfirst(v)));
		size_t		len;
		xmlChar    *version;
		int			standalone;
		char	   *str;

		len = VARSIZE(x) - VARHDRSZ;
		str = palloc(len + 1);
		memcpy(str, VARDATA(x), len);
		str[len] = '\0';

		parse_xml_decl((xmlChar *) str, &len, &version, NULL, &standalone);

		if (standalone == 0 && global_standalone == 1)
			global_standalone = 0;
		if (standalone < 0)
			global_standalone = -1;

		if (!version)
			global_version_no_value = true;
		else if (!global_version)
			global_version = xmlStrdup(version);
		else if (xmlStrcmp(version, global_version) != 0)
			global_version_no_value = true;

		appendStringInfoString(&buf, str + len);
		pfree(str);
	}

	if (!global_version_no_value || global_standalone >= 0)
	{
		StringInfoData buf2;

		initStringInfo(&buf2);

		print_xml_decl(&buf2,
					   (!global_version_no_value) ? global_version : NULL,
					   0,
					   global_standalone);

		appendStringInfoString(&buf2, buf.data);
		buf = buf2;
	}

	return stringinfo_to_xmltype(&buf);
#else
	NO_XML_SUPPORT();
	return NULL;
#endif
}


/*
 * XMLAGG support
 */
Datum
xmlconcat2(PG_FUNCTION_ARGS)
{
	if (PG_ARGISNULL(0))
	{
		if (PG_ARGISNULL(1))
			PG_RETURN_NULL();
		else
			PG_RETURN_XML_P(PG_GETARG_XML_P(1));
	}
	else if (PG_ARGISNULL(1))
		PG_RETURN_XML_P(PG_GETARG_XML_P(0));
	else
		PG_RETURN_XML_P(xmlconcat(list_make2(PG_GETARG_XML_P(0),
											 PG_GETARG_XML_P(1))));
}


Datum
texttoxml(PG_FUNCTION_ARGS)
{
	text	   *data = PG_GETARG_TEXT_P(0);

	PG_RETURN_XML_P(xmlparse(data, xmloption, true));
}