xml.c

postgresql8.3.4源码,开源数据库

Datum
xmltotext(PG_FUNCTION_ARGS)
{
	xmltype    *data = PG_GETARG_XML_P(0);

	/* It's actually binary compatible. */
	PG_RETURN_TEXT_P((text *) data);
}


text *
xmltotext_with_xmloption(xmltype *data, XmlOptionType xmloption_arg)
{
	if (xmloption_arg == XMLOPTION_DOCUMENT && !xml_is_document(data))
		ereport(ERROR,
				(errcode(ERRCODE_NOT_AN_XML_DOCUMENT),
				 errmsg("not an XML document")));

	/* It's actually binary compatible, save for the above check. */
	return (text *) data;
}


xmltype *
xmlelement(XmlExprState *xmlExpr, ExprContext *econtext)
{
#ifdef USE_LIBXML
	XmlExpr    *xexpr = (XmlExpr *) xmlExpr->xprstate.expr;
	xmltype    *result;
	List	   *named_arg_strings;
	List	   *arg_strings;
	int			i;
	ListCell   *arg;
	ListCell   *narg;
	xmlBufferPtr buf;
	xmlTextWriterPtr writer;

	/*
	 * We first evaluate all the arguments, then start up libxml and create
	 * the result.	This avoids issues if one of the arguments involves a call
	 * to some other function or subsystem that wants to use libxml on its own
	 * terms.
	 */
	named_arg_strings = NIL;
	i = 0;
	foreach(arg, xmlExpr->named_args)
	{
		ExprState  *e = (ExprState *) lfirst(arg);
		Datum		value;
		bool		isnull;
		char	   *str;

		value = ExecEvalExpr(e, econtext, &isnull, NULL);
		if (isnull)
			str = NULL;
		else
			str = OutputFunctionCall(&xmlExpr->named_outfuncs[i], value);
		named_arg_strings = lappend(named_arg_strings, str);
		i++;
	}

	arg_strings = NIL;
	foreach(arg, xmlExpr->args)
	{
		ExprState  *e = (ExprState *) lfirst(arg);
		Datum		value;
		bool		isnull;
		char	   *str;

		value = ExecEvalExpr(e, econtext, &isnull, NULL);
		/* here we can just forget NULL elements immediately */
		if (!isnull)
		{
			str = map_sql_value_to_xml_value(value,
											 exprType((Node *) e->expr));
			arg_strings = lappend(arg_strings, str);
		}
	}

	/* now safe to run libxml */
	xml_init();

	buf = xmlBufferCreate();
	writer = xmlNewTextWriterMemory(buf, 0);

	xmlTextWriterStartElement(writer, (xmlChar *) xexpr->name);

	forboth(arg, named_arg_strings, narg, xexpr->arg_names)
	{
		char	   *str = (char *) lfirst(arg);
		char	   *argname = strVal(lfirst(narg));

		if (str)
		{
			xmlTextWriterWriteAttribute(writer,
										(xmlChar *) argname,
										(xmlChar *) str);
			pfree(str);
		}
	}

	foreach(arg, arg_strings)
	{
		char	   *str = (char *) lfirst(arg);

		xmlTextWriterWriteRaw(writer, (xmlChar *) str);
	}

	xmlTextWriterEndElement(writer);
	xmlFreeTextWriter(writer);

	result = xmlBuffer_to_xmltype(buf);
	xmlBufferFree(buf);

	return result;
#else
	NO_XML_SUPPORT();
	return NULL;
#endif
}


xmltype *
xmlparse(text *data, XmlOptionType xmloption_arg, bool preserve_whitespace)
{
#ifdef USE_LIBXML
	xmlDocPtr	doc;

	doc = xml_parse(data, xmloption_arg, preserve_whitespace, NULL);
	xmlFreeDoc(doc);

	return (xmltype *) data;
#else
	NO_XML_SUPPORT();
	return NULL;
#endif
}


xmltype *
xmlpi(char *target, text *arg, bool arg_is_null, bool *result_is_null)
{
#ifdef USE_LIBXML
	xmltype    *result;
	StringInfoData buf;

	if (pg_strcasecmp(target, "xml") == 0)
		ereport(ERROR,
				(errcode(ERRCODE_SYNTAX_ERROR), /* really */
				 errmsg("invalid XML processing instruction"),
				 errdetail("XML processing instruction target name cannot be \"%s\".", target)));

	/*
	 * Following the SQL standard, the null check comes after the syntax check
	 * above.
	 */
	*result_is_null = arg_is_null;
	if (*result_is_null)
		return NULL;

	initStringInfo(&buf);

	appendStringInfo(&buf, "<?%s", target);

	if (arg != NULL)
	{
		char	   *string;

		string = _textout(arg);
		if (strstr(string, "?>") != NULL)
			ereport(ERROR,
					(errcode(ERRCODE_INVALID_XML_PROCESSING_INSTRUCTION),
					 errmsg("invalid XML processing instruction"),
			errdetail("XML processing instruction cannot contain \"?>\".")));

		appendStringInfoChar(&buf, ' ');
		appendStringInfoString(&buf, string + strspn(string, " "));
		pfree(string);
	}
	appendStringInfoString(&buf, "?>");

	result = stringinfo_to_xmltype(&buf);
	pfree(buf.data);
	return result;
#else
	NO_XML_SUPPORT();
	return NULL;
#endif
}


xmltype *
xmlroot(xmltype *data, text *version, int standalone)
{
#ifdef USE_LIBXML
	char	   *str;
	size_t		len;
	xmlChar    *orig_version;
	int			orig_standalone;
	StringInfoData buf;

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

	parse_xml_decl((xmlChar *) str, &len, &orig_version, NULL, &orig_standalone);

	if (version)
		orig_version = xml_text2xmlChar(version);
	else
		orig_version = NULL;

	switch (standalone)
	{
		case XML_STANDALONE_YES:
			orig_standalone = 1;
			break;
		case XML_STANDALONE_NO:
			orig_standalone = 0;
			break;
		case XML_STANDALONE_NO_VALUE:
			orig_standalone = -1;
			break;
		case XML_STANDALONE_OMITTED:
			/* leave original value */
			break;
	}

	initStringInfo(&buf);
	print_xml_decl(&buf, orig_version, 0, orig_standalone);
	appendStringInfoString(&buf, str + len);

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


/*
 * Validate document (given as string) against DTD (given as external link)
 *
 * This has been removed because it is a security hole: unprivileged users
 * should not be able to use Postgres to fetch arbitrary external files,
 * which unfortunately is exactly what libxml is willing to do with the DTD
 * parameter.
 */
Datum
xmlvalidate(PG_FUNCTION_ARGS)
{
	ereport(ERROR,
			(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
			 errmsg("xmlvalidate is not implemented")));
	return 0;
}


bool
xml_is_document(xmltype *arg)
{
#ifdef USE_LIBXML
	bool		result;
	xmlDocPtr	doc = NULL;
	MemoryContext ccxt = CurrentMemoryContext;

	PG_TRY();
	{
		doc = xml_parse((text *) arg, XMLOPTION_DOCUMENT, true, NULL);
		result = true;
	}
	PG_CATCH();
	{
		ErrorData  *errdata;
		MemoryContext ecxt;

		ecxt = MemoryContextSwitchTo(ccxt);
		errdata = CopyErrorData();
		if (errdata->sqlerrcode == ERRCODE_INVALID_XML_DOCUMENT)
		{
			FlushErrorState();
			result = false;
		}
		else
		{
			MemoryContextSwitchTo(ecxt);
			PG_RE_THROW();
		}
	}
	PG_END_TRY();

	if (doc)
		xmlFreeDoc(doc);

	return result;
#else							/* not USE_LIBXML */
	NO_XML_SUPPORT();
	return false;
#endif   /* not USE_LIBXML */
}


/*
 * xml cleanup function for transaction end.  This is also called on
 * subtransaction abort; see notes at top of file for rationale.
 */
void
AtEOXact_xml(void)
{
#ifdef USE_LIBXML
	xml_memory_cleanup();
#endif
}


#ifdef USE_LIBXML

/*
 * Set up for use of libxml --- this should be called by each function that
 * is about to use libxml facilities.
 *
 * TODO: xmlChar is utf8-char, make proper tuning (initdb with enc!=utf8 and
 * check)
 */
static void
xml_init(void)
{
	static bool first_time = true;

	if (first_time)
	{
		/* Stuff we need do only once per session */
		MemoryContext oldcontext;

		/*
		 * Currently, we have no pure UTF-8 support for internals -- check if
		 * we can work.
		 */
		if (sizeof(char) != sizeof(xmlChar))
			ereport(ERROR,
					(errmsg("could not initialize XML library"),
					 errdetail("libxml2 has incompatible char type: sizeof(char)=%u, sizeof(xmlChar)=%u.",
							   (int) sizeof(char), (int) sizeof(xmlChar))));

		/* create error buffer in permanent context */
		oldcontext = MemoryContextSwitchTo(TopMemoryContext);
		xml_err_buf = makeStringInfo();
		MemoryContextSwitchTo(oldcontext);

		/* Now that xml_err_buf exists, safe to call xml_errorHandler */
		xmlSetGenericErrorFunc(NULL, xml_errorHandler);

		/* Set up memory allocation our way, too */
		xml_memory_init();

		/* Check library compatibility */
		LIBXML_TEST_VERSION;

		first_time = false;
	}
	else
	{
		/* Reset pre-existing buffer to empty */
		Assert(xml_err_buf != NULL);
		resetStringInfo(xml_err_buf);

		/*
		 * We re-establish the callback functions every time.  This makes it
		 * safe for other subsystems (PL/Perl, say) to also use libxml with
		 * their own callbacks ... so long as they likewise set up the
		 * callbacks on every use.	It's cheap enough to not be worth worrying
		 * about, anyway.
		 */
		xmlSetGenericErrorFunc(NULL, xml_errorHandler);
		xml_memory_init();
	}
}


/*
 * SQL/XML allows storing "XML documents" or "XML content".  "XML
 * documents" are specified by the XML specification and are parsed
 * easily by libxml.  "XML content" is specified by SQL/XML as the
 * production "XMLDecl? content".  But libxml can only parse the
 * "content" part, so we have to parse the XML declaration ourselves
 * to complete this.
 */

#define CHECK_XML_SPACE(p) \
	do { \
		if (!xmlIsBlank_ch(*(p))) \
			return XML_ERR_SPACE_REQUIRED; \
	} while (0)

#define SKIP_XML_SPACE(p) \
	while (xmlIsBlank_ch(*(p))) (p)++

/* Letter | Digit | '.' | '-' | '_' | ':' | CombiningChar | Extender */
/* Beware of multiple evaluations of argument! */
#define PG_XMLISNAMECHAR(c) \
	(xmlIsBaseChar_ch(c) || xmlIsIdeographicQ(c) \
			|| xmlIsDigit_ch(c) \
			|| c == '.' || c == '-' || c == '_' || c == ':' \
			|| xmlIsCombiningQ(c) \
			|| xmlIsExtender_ch(c))

static int
parse_xml_decl(const xmlChar * str, size_t *lenp,
			   xmlChar ** version, xmlChar ** encoding, int *standalone)
{
	const xmlChar *p;
	const xmlChar *save_p;
	size_t		len;
	int			utf8char;
	int			utf8len;

	xml_init();

	if (version)
		*version = NULL;
	if (encoding)
		*encoding = NULL;
	if (standalone)
		*standalone = -1;

	p = str;

	if (xmlStrncmp(p, (xmlChar *) "<?xml", 5) != 0)
		goto finished;

	/* if next char is name char, it's a PI like <?xml-stylesheet ...?> */
	utf8len = strlen((const char *) (p + 5));
	utf8char = xmlGetUTF8Char(p + 5, &utf8len);
	if (PG_XMLISNAMECHAR(utf8char))
		goto finished;

	p += 5;

	/* version */
	CHECK_XML_SPACE(p);
	SKIP_XML_SPACE(p);
	if (xmlStrncmp(p, (xmlChar *) "version", 7) != 0)
		return XML_ERR_VERSION_MISSING;
	p += 7;
	SKIP_XML_SPACE(p);
	if (*p != '=')
		return XML_ERR_VERSION_MISSING;
	p += 1;
	SKIP_XML_SPACE(p);

	if (*p == '\'' || *p == '"')
	{
		const xmlChar *q;

		q = xmlStrchr(p + 1, *p);
		if (!q)
			return XML_ERR_VERSION_MISSING;

		if (version)
			*version = xmlStrndup(p + 1, q - p - 1);
		p = q + 1;
	}
	else
		return XML_ERR_VERSION_MISSING;

	/* encoding */
	save_p = p;
	SKIP_XML_SPACE(p);
	if (xmlStrncmp(p, (xmlChar *) "encoding", 8) == 0)
	{
		CHECK_XML_SPACE(save_p);
		p += 8;
		SKIP_XML_SPACE(p);
		if (*p != '=')
			return XML_ERR_MISSING_ENCODING;
		p += 1;
		SKIP_XML_SPACE(p);

		if (*p == '\'' || *p == '"')
		{
			const xmlChar *q;

			q = xmlStrchr(p + 1, *p);
			if (!q)
				return XML_ERR_MISSING_ENCODING;

			if (encoding)
				*encoding = xmlStrndup(p + 1, q - p - 1);
			p = q + 1;
		}
		else
			return XML_ERR_MISSING_ENCODING;
	}
	else
	{
		p = save_p;
	}

	/* standalone */
	save_p = p;
	SKIP_XML_SPACE(p);
	if (xmlStrncmp(p, (xmlChar *) "standalone", 10) == 0)
	{
		CHECK_XML_SPACE(save_p);
		p += 10;
		SKIP_XML_SPACE(p);
		if (*p != '=')
			return XML_ERR_STANDALONE_VALUE;
		p += 1;
		SKIP_XML_SPACE(p);
		if (xmlStrncmp(p, (xmlChar *) "'yes'", 5) == 0 ||
			xmlStrncmp(p, (xmlChar *) "\"yes\"", 5) == 0)
		{
			*standalone = 1;
			p += 5;
		}
		else if (xmlStrncmp(p, (xmlChar *) "'no'", 4) == 0 ||
				 xmlStrncmp(p, (xmlChar *) "\"no\"", 4) == 0)
		{
			*standalone = 0;
			p += 4;
		}
		else
			return XML_ERR_STANDALONE_VALUE;
	}
	else
	{
		p = save_p;
	}

	SKIP_XML_SPACE(p);
	if (xmlStrncmp(p, (xmlChar *) "?>", 2) != 0)
		return XML_ERR_XMLDECL_NOT_FINISHED;
	p += 2;

finished:
	len = p - str;

	for (p = str; p < str + len; p++)
		if (*p > 127)
			return XML_ERR_INVALID_CHAR;

	if (lenp)
		*lenp = len;