• file
• revisions
• annotate
• diff
• comparison
• raw

src/share/vm/utilities/utf8.hpp@f4f596978298 (annotated)

src/share/vm/utilities/utf8.hpp

Mon, 09 Aug 2010 17:51:56 -0700

author

never

date

Mon, 09 Aug 2010 17:51:56 -0700

changeset 2044

f4f596978298

parent 1907

c18cbe5936b8

child 2314

f95d63e2154a

permissions

-rw-r--r--

Merge

duke@435	1	/*
trims@1907	2	* Copyright (c) 1997, 2003, Oracle and/or its affiliates. All rights reserved.
duke@435	3	* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
duke@435	4	*
duke@435	5	* This code is free software; you can redistribute it and/or modify it
duke@435	6	* under the terms of the GNU General Public License version 2 only, as
duke@435	7	* published by the Free Software Foundation.
duke@435	8	*
duke@435	9	* This code is distributed in the hope that it will be useful, but WITHOUT
duke@435	10	* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
duke@435	11	* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
duke@435	12	* version 2 for more details (a copy is included in the LICENSE file that
duke@435	13	* accompanied this code).
duke@435	14	*
duke@435	15	* You should have received a copy of the GNU General Public License version
duke@435	16	* 2 along with this work; if not, write to the Free Software Foundation,
duke@435	17	* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
duke@435	18	*
trims@1907	19	* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
trims@1907	20	* or visit www.oracle.com if you need additional information or have any
trims@1907	21	* questions.
duke@435	22	*
duke@435	23	*/
duke@435	24
duke@435	25	// Low-level interface for UTF8 strings
duke@435	26
duke@435	27	class UTF8 : AllStatic {
duke@435	28	public:
duke@435	29	// returns the unicode length of a 0-terminated uft8 string
duke@435	30	static int unicode_length(const char* uft8_str);
duke@435	31
duke@435	32	// returns the unicode length of a non-0-terminated uft8 string
duke@435	33	static int unicode_length(const char* uft8_str, int len);
duke@435	34
duke@435	35	// converts a uft8 string to a unicode string
duke@435	36	static void convert_to_unicode(const char* utf8_str, jchar* unicode_buffer, int unicode_length);
duke@435	37
duke@435	38	// decodes the current utf8 character, stores the result in value,
duke@435	39	// and returns the end of the current uft8 chararacter.
duke@435	40	static char* next(const char* str, jchar* value);
duke@435	41
duke@435	42	// decodes the current utf8 character, gets the supplementary character instead of
duke@435	43	// the surrogate pair when seeing a supplementary character in string,
duke@435	44	// stores the result in value, and returns the end of the current uft8 chararacter.
duke@435	45	static char* next_character(const char* str, jint* value);
duke@435	46
duke@435	47	// Utility methods
duke@435	48	static jbyte* strrchr(jbyte* base, int length, jbyte c);
duke@435	49	static bool equal(jbyte* base1, int length1, jbyte* base2, int length2);
duke@435	50	static bool is_supplementary_character(const unsigned char* str);
duke@435	51	static jint get_supplementary_character(const unsigned char* str);
duke@435	52	};
duke@435	53
duke@435	54
duke@435	55	// Low-level interface for UNICODE strings
duke@435	56
duke@435	57	// A unicode string represents a string in the UTF-16 format in which supplementary
duke@435	58	// characters are represented by surrogate pairs. Index values refer to char code
duke@435	59	// units, so a supplementary character uses two positions in a unicode string.
duke@435	60
duke@435	61	class UNICODE : AllStatic {
duke@435	62	public:
duke@435	63	// returns the utf8 size of a unicode character
duke@435	64	static int utf8_size(jchar c);
duke@435	65
duke@435	66	// returns the utf8 length of a unicode string
duke@435	67	static int utf8_length(jchar* base, int length);
duke@435	68
duke@435	69	// converts a unicode string to utf8 string
duke@435	70	static void convert_to_utf8(const jchar* base, int length, char* utf8_buffer);
duke@435	71
duke@435	72	// converts a unicode string to a utf8 string; result is allocated
duke@435	73	// in resource area unless a buffer is provided.
duke@435	74	static char* as_utf8(jchar* base, int length);
duke@435	75	static char* as_utf8(jchar* base, int length, char* buf, int buflen);
duke@435	76	};