annotate src/share/vm/utilities/utf8.hpp @ 4834:74d14a44c398

Added tag jdk7u60-b01 for changeset 8fd0e931efa5
author asaha
date Wed, 27 Nov 2013 14:57:31 -0800
parents 3582bf76420e
children
rev   line source
duke@0 1 /*
trims@2273 2 * Copyright (c) 1997, 2011, Oracle and/or its affiliates. All rights reserved.
duke@0 3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
duke@0 4 *
duke@0 5 * This code is free software; you can redistribute it and/or modify it
duke@0 6 * under the terms of the GNU General Public License version 2 only, as
duke@0 7 * published by the Free Software Foundation.
duke@0 8 *
duke@0 9 * This code is distributed in the hope that it will be useful, but WITHOUT
duke@0 10 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
duke@0 11 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
duke@0 12 * version 2 for more details (a copy is included in the LICENSE file that
duke@0 13 * accompanied this code).
duke@0 14 *
duke@0 15 * You should have received a copy of the GNU General Public License version
duke@0 16 * 2 along with this work; if not, write to the Free Software Foundation,
duke@0 17 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
duke@0 18 *
trims@1472 19 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
trims@1472 20 * or visit www.oracle.com if you need additional information or have any
trims@1472 21 * questions.
duke@0 22 *
duke@0 23 */
duke@0 24
stefank@1879 25 #ifndef SHARE_VM_UTILITIES_UTF8_HPP
stefank@1879 26 #define SHARE_VM_UTILITIES_UTF8_HPP
stefank@1879 27
stefank@1879 28 #include "memory/allocation.hpp"
stefank@1879 29 #include "utilities/top.hpp"
stefank@1879 30
duke@0 31 // Low-level interface for UTF8 strings
duke@0 32
duke@0 33 class UTF8 : AllStatic {
duke@0 34 public:
duke@0 35 // returns the unicode length of a 0-terminated uft8 string
duke@0 36 static int unicode_length(const char* uft8_str);
duke@0 37
duke@0 38 // returns the unicode length of a non-0-terminated uft8 string
duke@0 39 static int unicode_length(const char* uft8_str, int len);
duke@0 40
duke@0 41 // converts a uft8 string to a unicode string
duke@0 42 static void convert_to_unicode(const char* utf8_str, jchar* unicode_buffer, int unicode_length);
duke@0 43
duke@0 44 // decodes the current utf8 character, stores the result in value,
duke@0 45 // and returns the end of the current uft8 chararacter.
duke@0 46 static char* next(const char* str, jchar* value);
duke@0 47
duke@0 48 // decodes the current utf8 character, gets the supplementary character instead of
duke@0 49 // the surrogate pair when seeing a supplementary character in string,
duke@0 50 // stores the result in value, and returns the end of the current uft8 chararacter.
duke@0 51 static char* next_character(const char* str, jint* value);
duke@0 52
duke@0 53 // Utility methods
coleenp@2062 54 static const jbyte* strrchr(const jbyte* base, int length, jbyte c);
coleenp@2062 55 static bool equal(const jbyte* base1, int length1, const jbyte* base2,int length2);
duke@0 56 static bool is_supplementary_character(const unsigned char* str);
duke@0 57 static jint get_supplementary_character(const unsigned char* str);
duke@0 58 };
duke@0 59
duke@0 60
duke@0 61 // Low-level interface for UNICODE strings
duke@0 62
duke@0 63 // A unicode string represents a string in the UTF-16 format in which supplementary
duke@0 64 // characters are represented by surrogate pairs. Index values refer to char code
duke@0 65 // units, so a supplementary character uses two positions in a unicode string.
duke@0 66
duke@0 67 class UNICODE : AllStatic {
duke@0 68 public:
duke@0 69 // returns the utf8 size of a unicode character
duke@0 70 static int utf8_size(jchar c);
duke@0 71
duke@0 72 // returns the utf8 length of a unicode string
duke@0 73 static int utf8_length(jchar* base, int length);
duke@0 74
duke@0 75 // converts a unicode string to utf8 string
duke@0 76 static void convert_to_utf8(const jchar* base, int length, char* utf8_buffer);
duke@0 77
duke@0 78 // converts a unicode string to a utf8 string; result is allocated
duke@0 79 // in resource area unless a buffer is provided.
duke@0 80 static char* as_utf8(jchar* base, int length);
duke@0 81 static char* as_utf8(jchar* base, int length, char* buf, int buflen);
duke@0 82 };
stefank@1879 83
stefank@1879 84 #endif // SHARE_VM_UTILITIES_UTF8_HPP