Mercurial > jdk8-mips64-public > hotspot / annotate
src/share/vm/utilities/utf8.hpp@3582bf76420e (annotated)
src/share/vm/utilities/utf8.hpp
Thu, 27 Jan 2011 16:11:27 -0800
- author
- coleenp
- date
- Thu, 27 Jan 2011 16:11:27 -0800
- changeset 2497
- 3582bf76420e
- parent 2314
- f95d63e2154a
- child 2708
- 1d1603768966
- permissions
- -rw-r--r--
6990754: Use native memory and reference counting to implement SymbolTable
Summary: move symbols from permgen into C heap and reference count them
Reviewed-by: never, acorn, jmasa, stefank
| duke@435 | 1 | /* |
| stefank@2314 | 2 | * Copyright (c) 1997, 2010, 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 | |
| stefank@2314 | 25 | #ifndef SHARE_VM_UTILITIES_UTF8_HPP |
| stefank@2314 | 26 | #define SHARE_VM_UTILITIES_UTF8_HPP |
| stefank@2314 | 27 | |
| stefank@2314 | 28 | #include "memory/allocation.hpp" |
| stefank@2314 | 29 | #include "utilities/top.hpp" |
| stefank@2314 | 30 | |
| duke@435 | 31 | // Low-level interface for UTF8 strings |
| duke@435 | 32 | |
| duke@435 | 33 | class UTF8 : AllStatic { |
| duke@435 | 34 | public: |
| duke@435 | 35 | // returns the unicode length of a 0-terminated uft8 string |
| duke@435 | 36 | static int unicode_length(const char* uft8_str); |
| duke@435 | 37 | |
| duke@435 | 38 | // returns the unicode length of a non-0-terminated uft8 string |
| duke@435 | 39 | static int unicode_length(const char* uft8_str, int len); |
| duke@435 | 40 | |
| duke@435 | 41 | // converts a uft8 string to a unicode string |
| duke@435 | 42 | static void convert_to_unicode(const char* utf8_str, jchar* unicode_buffer, int unicode_length); |
| duke@435 | 43 | |
| duke@435 | 44 | // decodes the current utf8 character, stores the result in value, |
| duke@435 | 45 | // and returns the end of the current uft8 chararacter. |
| duke@435 | 46 | static char* next(const char* str, jchar* value); |
| duke@435 | 47 | |
| duke@435 | 48 | // decodes the current utf8 character, gets the supplementary character instead of |
| duke@435 | 49 | // the surrogate pair when seeing a supplementary character in string, |
| duke@435 | 50 | // stores the result in value, and returns the end of the current uft8 chararacter. |
| duke@435 | 51 | static char* next_character(const char* str, jint* value); |
| duke@435 | 52 | |
| duke@435 | 53 | // Utility methods |
| coleenp@2497 | 54 | static const jbyte* strrchr(const jbyte* base, int length, jbyte c); |
| coleenp@2497 | 55 | static bool equal(const jbyte* base1, int length1, const jbyte* base2,int length2); |
| duke@435 | 56 | static bool is_supplementary_character(const unsigned char* str); |
| duke@435 | 57 | static jint get_supplementary_character(const unsigned char* str); |
| duke@435 | 58 | }; |
| duke@435 | 59 | |
| duke@435 | 60 | |
| duke@435 | 61 | // Low-level interface for UNICODE strings |
| duke@435 | 62 | |
| duke@435 | 63 | // A unicode string represents a string in the UTF-16 format in which supplementary |
| duke@435 | 64 | // characters are represented by surrogate pairs. Index values refer to char code |
| duke@435 | 65 | // units, so a supplementary character uses two positions in a unicode string. |
| duke@435 | 66 | |
| duke@435 | 67 | class UNICODE : AllStatic { |
| duke@435 | 68 | public: |
| duke@435 | 69 | // returns the utf8 size of a unicode character |
| duke@435 | 70 | static int utf8_size(jchar c); |
| duke@435 | 71 | |
| duke@435 | 72 | // returns the utf8 length of a unicode string |
| duke@435 | 73 | static int utf8_length(jchar* base, int length); |
| duke@435 | 74 | |
| duke@435 | 75 | // converts a unicode string to utf8 string |
| duke@435 | 76 | static void convert_to_utf8(const jchar* base, int length, char* utf8_buffer); |
| duke@435 | 77 | |
| duke@435 | 78 | // converts a unicode string to a utf8 string; result is allocated |
| duke@435 | 79 | // in resource area unless a buffer is provided. |
| duke@435 | 80 | static char* as_utf8(jchar* base, int length); |
| duke@435 | 81 | static char* as_utf8(jchar* base, int length, char* buf, int buflen); |
| duke@435 | 82 | }; |
| stefank@2314 | 83 | |
| stefank@2314 | 84 | #endif // SHARE_VM_UTILITIES_UTF8_HPP |
