utf8.hpp revision 1472:c18cbe5936b8
1/* 2 * Copyright (c) 1997, 2003, 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// Low-level interface for UTF8 strings 26 27class UTF8 : AllStatic { 28 public: 29 // returns the unicode length of a 0-terminated uft8 string 30 static int unicode_length(const char* uft8_str); 31 32 // returns the unicode length of a non-0-terminated uft8 string 33 static int unicode_length(const char* uft8_str, int len); 34 35 // converts a uft8 string to a unicode string 36 static void convert_to_unicode(const char* utf8_str, jchar* unicode_buffer, int unicode_length); 37 38 // decodes the current utf8 character, stores the result in value, 39 // and returns the end of the current uft8 chararacter. 40 static char* next(const char* str, jchar* value); 41 42 // decodes the current utf8 character, gets the supplementary character instead of 43 // the surrogate pair when seeing a supplementary character in string, 44 // stores the result in value, and returns the end of the current uft8 chararacter. 45 static char* next_character(const char* str, jint* value); 46 47 // Utility methods 48 static jbyte* strrchr(jbyte* base, int length, jbyte c); 49 static bool equal(jbyte* base1, int length1, jbyte* base2, int length2); 50 static bool is_supplementary_character(const unsigned char* str); 51 static jint get_supplementary_character(const unsigned char* str); 52}; 53 54 55// Low-level interface for UNICODE strings 56 57// A unicode string represents a string in the UTF-16 format in which supplementary 58// characters are represented by surrogate pairs. Index values refer to char code 59// units, so a supplementary character uses two positions in a unicode string. 60 61class UNICODE : AllStatic { 62 public: 63 // returns the utf8 size of a unicode character 64 static int utf8_size(jchar c); 65 66 // returns the utf8 length of a unicode string 67 static int utf8_length(jchar* base, int length); 68 69 // converts a unicode string to utf8 string 70 static void convert_to_utf8(const jchar* base, int length, char* utf8_buffer); 71 72 // converts a unicode string to a utf8 string; result is allocated 73 // in resource area unless a buffer is provided. 74 static char* as_utf8(jchar* base, int length); 75 static char* as_utf8(jchar* base, int length, char* buf, int buflen); 76}; 77