utf8.hpp revision 2273:1d1603768966 
1/*
2 * Copyright (c) 1997, 2011, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation.
8 *
9 * This code is distributed in the hope that it will be useful, but WITHOUT
10 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
11 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
12 * version 2 for more details (a copy is included in the LICENSE file that
13 * accompanied this code).
14 *
15 * You should have received a copy of the GNU General Public License version
16 * 2 along with this work; if not, write to the Free Software Foundation,
17 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
18 *
19 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
20 * or visit www.oracle.com if you need additional information or have any
21 * questions.
22 *
23 */
24
25#ifndef SHARE_VM_UTILITIES_UTF8_HPP
26#define SHARE_VM_UTILITIES_UTF8_HPP
27
28#include "memory/allocation.hpp"
29#include "utilities/top.hpp"
30
31// Low-level interface for UTF8 strings
32
33class UTF8 : AllStatic {
34 public:
35  // returns the unicode length of a 0-terminated uft8 string
36  static int unicode_length(const char* uft8_str);
37
38  // returns the unicode length of a non-0-terminated uft8 string
39  static int unicode_length(const char* uft8_str, int len);
40
41  // converts a uft8 string to a unicode string
42  static void convert_to_unicode(const char* utf8_str, jchar* unicode_buffer, int unicode_length);
43
44  // decodes the current utf8 character, stores the result in value,
45  // and returns the end of the current uft8 chararacter.
46  static char* next(const char* str, jchar* value);
47
48  // decodes the current utf8 character, gets the supplementary character instead of
49  // the surrogate pair when seeing a supplementary character in string,
50  // stores the result in value, and returns the end of the current uft8 chararacter.
51  static char* next_character(const char* str, jint* value);
52
53  // Utility methods
54  static const jbyte* strrchr(const jbyte* base, int length, jbyte c);
55  static bool   equal(const jbyte* base1, int length1, const jbyte* base2,int length2);
56  static bool   is_supplementary_character(const unsigned char* str);
57  static jint   get_supplementary_character(const unsigned char* str);
58};
59
60
61// Low-level interface for UNICODE strings
62
63// A unicode string represents a string in the UTF-16 format in which supplementary
64// characters are represented by surrogate pairs. Index values refer to char code
65// units, so a supplementary character uses two positions in a unicode string.
66
67class UNICODE : AllStatic {
68 public:
69  // returns the utf8 size of a unicode character
70  static int utf8_size(jchar c);
71
72  // returns the utf8 length of a unicode string
73  static int utf8_length(jchar* base, int length);
74
75  // converts a unicode string to utf8 string
76  static void convert_to_utf8(const jchar* base, int length, char* utf8_buffer);
77
78  // converts a unicode string to a utf8 string; result is allocated
79  // in resource area unless a buffer is provided.
80  static char* as_utf8(jchar* base, int length);
81  static char* as_utf8(jchar* base, int length, char* buf, int buflen);
82};
83
84#endif // SHARE_VM_UTILITIES_UTF8_HPP
85