xml.c

postgresql8.3.4源码,开源数据库

	return XML_ERR_OK;
}


/*
 * Write an XML declaration.  On output, we adjust the XML declaration
 * as follows.	(These rules are the moral equivalent of the clause
 * "Serialization of an XML value" in the SQL standard.)
 *
 * We try to avoid generating an XML declaration if possible.  This is
 * so that you don't get trivial things like xml '<foo/>' resulting in
 * '<?xml version="1.0"?><foo/>', which would surely be annoying.  We
 * must provide a declaration if the standalone property is specified
 * or if we include an encoding declaration.  If we have a
 * declaration, we must specify a version (XML requires this).
 * Otherwise we only make a declaration if the version is not "1.0",
 * which is the default version specified in SQL:2003.
 */
static bool
print_xml_decl(StringInfo buf, const xmlChar * version,
			   pg_enc encoding, int standalone)
{
	xml_init();

	if ((version && strcmp((char *) version, PG_XML_DEFAULT_VERSION) != 0)
		|| (encoding && encoding != PG_UTF8)
		|| standalone != -1)
	{
		appendStringInfoString(buf, "<?xml");

		if (version)
			appendStringInfo(buf, " version=\"%s\"", version);
		else
			appendStringInfo(buf, " version=\"%s\"", PG_XML_DEFAULT_VERSION);

		if (encoding && encoding != PG_UTF8)
		{
			/*
			 * XXX might be useful to convert this to IANA names (ISO-8859-1
			 * instead of LATIN1 etc.); needs field experience
			 */
			appendStringInfo(buf, " encoding=\"%s\"",
							 pg_encoding_to_char(encoding));
		}

		if (standalone == 1)
			appendStringInfoString(buf, " standalone=\"yes\"");
		else if (standalone == 0)
			appendStringInfoString(buf, " standalone=\"no\"");
		appendStringInfoString(buf, "?>");

		return true;
	}
	else
		return false;
}


/*
 * Convert a C string to XML internal representation
 *
 * TODO maybe, libxml2's xmlreader is better? (do not construct DOM,
 * yet do not use SAX - see xmlreader.c)
 */
static xmlDocPtr
xml_parse(text *data, XmlOptionType xmloption_arg, bool preserve_whitespace,
		  xmlChar * encoding)
{
	int32		len;
	xmlChar    *string;
	xmlChar    *utf8string;
	xmlParserCtxtPtr ctxt;
	xmlDocPtr	doc;

	len = VARSIZE(data) - VARHDRSZ;		/* will be useful later */
	string = xml_text2xmlChar(data);

	utf8string = pg_do_encoding_conversion(string,
										   len,
										   encoding ?
										   xmlChar_to_encoding(encoding) :
										   GetDatabaseEncoding(),
										   PG_UTF8);

	xml_init();
	xmlInitParser();
	ctxt = xmlNewParserCtxt();
	if (ctxt == NULL)
		xml_ereport(ERROR, ERRCODE_OUT_OF_MEMORY,
					"could not allocate parser context");

	if (xmloption_arg == XMLOPTION_DOCUMENT)
	{
		/*
		 * Note, that here we try to apply DTD defaults
		 * (XML_PARSE_DTDATTR) according to SQL/XML:10.16.7.d: 'Default
		 * values defined by internal DTD are applied'. As for external
		 * DTDs, we try to support them too, (see SQL/XML:10.16.7.e)
		 */
		doc = xmlCtxtReadDoc(ctxt, utf8string,
							 NULL,
							 "UTF-8",
							 XML_PARSE_NOENT | XML_PARSE_DTDATTR
							 | (preserve_whitespace ? 0 : XML_PARSE_NOBLANKS));
		if (doc == NULL)
			xml_ereport(ERROR, ERRCODE_INVALID_XML_DOCUMENT,
						"invalid XML document");
	}
	else
	{
		int			res_code;
		size_t		count;
		xmlChar    *version = NULL;
		int			standalone = -1;

		doc = xmlNewDoc(NULL);

		res_code = parse_xml_decl(utf8string,
								  &count, &version, NULL, &standalone);
		if (res_code != 0)
			xml_ereport_by_code(ERROR, ERRCODE_INVALID_XML_CONTENT,
								"invalid XML content: invalid XML declaration",
								res_code);

		res_code = xmlParseBalancedChunkMemory(doc, NULL, NULL, 0,
											   utf8string + count, NULL);
		if (res_code != 0)
			xml_ereport(ERROR, ERRCODE_INVALID_XML_CONTENT,
						"invalid XML content");

		doc->version = xmlStrdup(version);
		doc->encoding = xmlStrdup((xmlChar *) "UTF-8");
		doc->standalone = standalone;
	}

	xmlFreeParserCtxt(ctxt);

	return doc;
}


/*
 * xmlChar<->text convertions
 */
static xmlChar *
xml_text2xmlChar(text *in)
{
	int32		len = VARSIZE(in) - VARHDRSZ;
	xmlChar    *res;

	res = palloc(len + 1);
	memcpy(res, VARDATA(in), len);
	res[len] = '\0';

	return (res);
}


/*
 * Manage the special context used for all libxml allocations
 */
static void
xml_memory_init(void)
{
	/*
	 * Create memory context if not there already.  We make it a child of
	 * TopMemoryContext, even though our current policy is that it doesn't
	 * survive past transaction end, because we want to be really really
	 * sure it doesn't go away before we've called xmlCleanupParser().
	 */
	if (LibxmlContext == NULL)
		LibxmlContext = AllocSetContextCreate(TopMemoryContext,
											  "LibxmlContext",
											  ALLOCSET_DEFAULT_MINSIZE,
											  ALLOCSET_DEFAULT_INITSIZE,
											  ALLOCSET_DEFAULT_MAXSIZE);

	/* Re-establish the callbacks even if already set */
	xmlMemSetup(xml_pfree, xml_palloc, xml_repalloc, xml_pstrdup);
}

static void
xml_memory_cleanup(void)
{
	if (LibxmlContext != NULL)
	{
		/* Give libxml a chance to clean up dangling pointers */
		xmlCleanupParser();

		/* And flush the context */
		MemoryContextDelete(LibxmlContext);
		LibxmlContext = NULL;
	}
}

/*
 * Wrappers for memory management functions
 */
static void *
xml_palloc(size_t size)
{
	return MemoryContextAlloc(LibxmlContext, size);
}


static void *
xml_repalloc(void *ptr, size_t size)
{
	return repalloc(ptr, size);
}


static void
xml_pfree(void *ptr)
{
	pfree(ptr);
}


static char *
xml_pstrdup(const char *string)
{
	return MemoryContextStrdup(LibxmlContext, string);
}


/*
 * Wrapper for "ereport" function for XML-related errors.  The "msg"
 * is the SQL-level message; some can be adopted from the SQL/XML
 * standard.  This function adds libxml's native error messages, if
 * any, as detail.
 */
static void
xml_ereport(int level, int sqlcode, const char *msg)
{
	char	   *detail;

	if (xml_err_buf->len > 0)
	{
		detail = pstrdup(xml_err_buf->data);
		resetStringInfo(xml_err_buf);
	}
	else
		detail = NULL;

	/* libxml error messages end in '\n'; get rid of it */
	if (detail)
	{
		size_t		len;

		len = strlen(detail);
		if (len > 0 && detail[len - 1] == '\n')
			detail[len - 1] = '\0';

		ereport(level,
				(errcode(sqlcode),
				 errmsg("%s", msg),
				 errdetail("%s", detail)));
	}
	else
	{
		ereport(level,
				(errcode(sqlcode),
				 errmsg("%s", msg)));
	}
}


/*
 * Error handler for libxml error messages
 */
static void
xml_errorHandler(void *ctxt, const char *msg,...)
{
	/* Append the formatted text to xml_err_buf */
	for (;;)
	{
		va_list		args;
		bool		success;

		/* Try to format the data. */
		va_start(args, msg);
		success = appendStringInfoVA(xml_err_buf, msg, args);
		va_end(args);

		if (success)
			break;

		/* Double the buffer size and try again. */
		enlargeStringInfo(xml_err_buf, xml_err_buf->maxlen);
	}
}


/*
 * Wrapper for "ereport" function for XML-related errors.  The "msg"
 * is the SQL-level message; some can be adopted from the SQL/XML
 * standard.  This function uses "code" to create a textual detail
 * message.  At the moment, we only need to cover those codes that we
 * may raise in this file.
 */
static void
xml_ereport_by_code(int level, int sqlcode,
					const char *msg, int code)
{
	const char *det;

	switch (code)
	{
		case XML_ERR_INVALID_CHAR:
			det = gettext_noop("Invalid character value.");
			break;
		case XML_ERR_SPACE_REQUIRED:
			det = gettext_noop("Space required.");
			break;
		case XML_ERR_STANDALONE_VALUE:
			det = gettext_noop("standalone accepts only 'yes' or 'no'.");
			break;
		case XML_ERR_VERSION_MISSING:
			det = gettext_noop("Malformed declaration: missing version.");
			break;
		case XML_ERR_MISSING_ENCODING:
			det = gettext_noop("Missing encoding in text declaration.");
			break;
		case XML_ERR_XMLDECL_NOT_FINISHED:
			det = gettext_noop("Parsing XML declaration: '?>' expected.");
			break;
		default:
			det = gettext_noop("Unrecognized libxml error code: %d.");
			break;
	}

	ereport(level,
			(errcode(sqlcode),
			 errmsg("%s", msg),
			 errdetail(det, code)));
}


/*
 * Convert one char in the current server encoding to a Unicode codepoint.
 */
static pg_wchar
sqlchar_to_unicode(char *s)
{
	char	   *utf8string;
	pg_wchar	ret[2];			/* need space for trailing zero */

	utf8string = (char *) pg_do_encoding_conversion((unsigned char *) s,
													pg_mblen(s),
													GetDatabaseEncoding(),
													PG_UTF8);

	pg_encoding_mb2wchar_with_len(PG_UTF8, utf8string, ret, pg_mblen(s));

	return ret[0];
}


static bool
is_valid_xml_namefirst(pg_wchar c)
{
	/* (Letter | '_' | ':') */
	return (xmlIsBaseCharQ(c) || xmlIsIdeographicQ(c)
			|| c == '_' || c == ':');
}


static bool
is_valid_xml_namechar(pg_wchar c)
{
	/* Letter | Digit | '.' | '-' | '_' | ':' | CombiningChar | Extender */
	return (xmlIsBaseCharQ(c) || xmlIsIdeographicQ(c)
			|| xmlIsDigitQ(c)
			|| c == '.' || c == '-' || c == '_' || c == ':'
			|| xmlIsCombiningQ(c)
			|| xmlIsExtenderQ(c));
}
#endif   /* USE_LIBXML */


/*
 * Map SQL identifier to XML name; see SQL/XML:2003 section 9.1.
 */
char *
map_sql_identifier_to_xml_name(char *ident, bool fully_escaped,
							   bool escape_period)
{
#ifdef USE_LIBXML
	StringInfoData buf;
	char	   *p;

	/*
	 * SQL/XML doesn't make use of this case anywhere, so it's probably a
	 * mistake.
	 */
	Assert(fully_escaped || !escape_period);

	initStringInfo(&buf);

	for (p = ident; *p; p += pg_mblen(p))
	{
		if (*p == ':' && (p == ident || fully_escaped))
			appendStringInfo(&buf, "_x003A_");
		else if (*p == '_' && *(p + 1) == 'x')
			appendStringInfo(&buf, "_x005F_");
		else if (fully_escaped && p == ident &&
				 pg_strncasecmp(p, "xml", 3) == 0)
		{
			if (*p == 'x')
				appendStringInfo(&buf, "_x0078_");
			else
				appendStringInfo(&buf, "_x0058_");
		}
		else if (escape_period && *p == '.')
			appendStringInfo(&buf, "_x002E_");
		else
		{
			pg_wchar	u = sqlchar_to_unicode(p);

			if ((p == ident)
				? !is_valid_xml_namefirst(u)
				: !is_valid_xml_namechar(u))
				appendStringInfo(&buf, "_x%04X_", (unsigned int) u);
			else
				appendBinaryStringInfo(&buf, p, pg_mblen(p));
		}
	}

	return buf.data;
#else							/* not USE_LIBXML */
	NO_XML_SUPPORT();
	return NULL;
#endif   /* not USE_LIBXML */
}


/*
 * Map a Unicode codepoint into the current server encoding.
 */
static char *
unicode_to_sqlchar(pg_wchar c)
{
	static unsigned char utf8string[5]; /* need trailing zero */

	if (c <= 0x7F)
	{
		utf8string[0] = c;
	}
	else if (c <= 0x7FF)
	{
		utf8string[0] = 0xC0 | ((c >> 6) & 0x1F);
		utf8string[1] = 0x80 | (c & 0x3F);
	}
	else if (c <= 0xFFFF)
	{
		utf8string[0] = 0xE0 | ((c >> 12) & 0x0F);
		utf8string[1] = 0x80 | ((c >> 6) & 0x3F);
		utf8string[2] = 0x80 | (c & 0x3F);
	}
	else
	{
		utf8string[0] = 0xF0 | ((c >> 18) & 0x07);
		utf8string[1] = 0x80 | ((c >> 12) & 0x3F);
		utf8string[2] = 0x80 | ((c >> 6) & 0x3F);
		utf8string[3] = 0x80 | (c & 0x3F);
	}

	return (char *) pg_do_encoding_conversion(utf8string,
											  pg_mblen((char *) utf8string),
											  PG_UTF8,
											  GetDatabaseEncoding());
}


/*
 * Map XML name to SQL identifier; see SQL/XML:2003 section 9.17.
 */
char *
map_xml_name_to_sql_identifier(char *name)
{
	StringInfoData buf;
	char	   *p;

	initStringInfo(&buf);

	for (p = name; *p; p += pg_mblen(p))
	{
		if (*p == '_' && *(p + 1) == 'x'
			&& isxdigit((unsigned char) *(p + 2))
			&& isxdigit((unsigned char) *(p + 3))
			&& isxdigit((unsigned char) *(p + 4))
			&& isxdigit((unsigned char) *(p + 5))
			&& *(p + 6) == '_')
		{
			unsigned int u;

			sscanf(p + 2, "%X", &u);
			appendStringInfoString(&buf, unicode_to_sqlchar(u));
			p += 6;
		}
		else
			appendBinaryStringInfo(&buf, p, pg_mblen(p));
	}

	return buf.data;
}

/*
 * Map SQL value to XML value; see SQL/XML:2003 section 9.16.
 */
char *
map_sql_value_to_xml_value(Datum value, Oid type)
{
	StringInfoData buf;

	initStringInfo(&buf);

	if (type_is_array(type))
	{
		ArrayType  *array;
		Oid			elmtype;
		int16		elmlen;
		bool		elmbyval;
		char		elmalign;
		int			num_elems;
		Datum	   *elem_values;
		bool	   *elem_nulls;
		int			i;

		array = DatumGetArrayTypeP(value);
		elmtype = ARR_ELEMTYPE(array);
		get_typlenbyvalalign(elmtype, &elmlen, &elmbyval, &elmalign);

		deconstruct_array(array, elmtype,
						  elmlen, elmbyval, elmalign,
						  &elem_values, &elem_nulls,
						  &num_elems);

		for (i = 0; i < num_elems; i++)
		{
			if (elem_nulls[i])
				continue;
			appendStringInfoString(&buf, "<element>");
			appendStringInfoString(&buf,
								   map_sql_value_to_xml_value(elem_values[i],
															  elmtype));
			appendStringInfoString(&buf, "</element>");