1 /* 2 * Copyright (c) 1997, 2013, 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 33 class UTF8 : AllStatic { 34 public: 35 // returns the unicode length of a 0-terminated utf8 string 36 static int unicode_length(const char* utf8_str); 37 38 // returns the unicode length of a non-0-terminated utf8 string 39 static int unicode_length(const char* utf8_str, int len); 40 41 // converts a utf8 string to a unicode string 42 static void convert_to_unicode(const char* utf8_str, jchar* unicode_buffer, int unicode_length); 43 44 // returns the quoted ascii length of a utf8 string 45 static int quoted_ascii_length(const char* utf8_str, int utf8_length); 46 47 // converts a utf8 string to quoted ascii 48 static void as_quoted_ascii(const char* utf8_str, int utf8_length, char* buf, int buflen); 49 50 // converts a quoted ascii string to utf8 string. returns the original 51 // string unchanged if nothing needs to be done. 52 static const char* from_quoted_ascii(const char* quoted_ascii_string); 53 54 // decodes the current utf8 character, stores the result in value, 55 // and returns the end of the current utf8 chararacter. 56 static char* next(const char* str, jchar* value); 57 58 // decodes the current utf8 character, gets the supplementary character instead of 59 // the surrogate pair when seeing a supplementary character in string, 60 // stores the result in value, and returns the end of the current utf8 chararacter. 61 static char* next_character(const char* str, jint* value); 62 63 // Utility methods 64 static const jbyte* strrchr(const jbyte* base, int length, jbyte c); 65 static bool equal(const jbyte* base1, int length1, const jbyte* base2,int length2); 66 static bool is_supplementary_character(const unsigned char* str); 67 static jint get_supplementary_character(const unsigned char* str); 68 }; 69 70 71 // Low-level interface for UNICODE strings 72 73 // A unicode string represents a string in the UTF-16 format in which supplementary 74 // characters are represented by surrogate pairs. Index values refer to char code 75 // units, so a supplementary character uses two positions in a unicode string. 76 77 class UNICODE : AllStatic { 78 public: 79 // returns the utf8 size of a unicode character 80 static int utf8_size(jchar c); 81 82 // returns the utf8 length of a unicode string 83 static int utf8_length(jchar* base, int length); 84 85 // converts a unicode string to utf8 string 86 static void convert_to_utf8(const jchar* base, int length, char* utf8_buffer); 87 88 // converts a unicode string to a utf8 string; result is allocated 89 // in resource area unless a buffer is provided. 90 static char* as_utf8(jchar* base, int length); 91 static char* as_utf8(jchar* base, int length, char* buf, int buflen); 92 93 // returns the quoted ascii length of a unicode string 94 static int quoted_ascii_length(jchar* base, int length); 95 96 // converts a utf8 string to quoted ascii 97 static void as_quoted_ascii(const jchar* base, int length, char* buf, int buflen); 98 }; 99 100 #endif // SHARE_VM_UTILITIES_UTF8_HPP | 1 /* 2 * Copyright (c) 1997, 2015, 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 33 class UTF8 : AllStatic { 34 public: 35 // returns the unicode length of a 0-terminated utf8 string 36 static int unicode_length(const char* utf8_str) { 37 bool is_latin1, has_multibyte; 38 return unicode_length(utf8_str, is_latin1, has_multibyte); 39 } 40 static int unicode_length(const char* utf8_str, bool& is_latin1, bool& has_multibyte); 41 42 // returns the unicode length of a non-0-terminated utf8 string 43 static int unicode_length(const char* utf8_str, int len) { 44 bool is_latin1, has_multibyte; 45 return unicode_length(utf8_str, len, is_latin1, has_multibyte); 46 } 47 static int unicode_length(const char* utf8_str, int len, bool& is_latin1, bool& has_multibyte); 48 49 // converts a utf8 string to a unicode string 50 template<typename T> static void convert_to_unicode(const char* utf8_str, T* unicode_str, int unicode_length); 51 52 // returns the quoted ascii length of a utf8 string 53 static int quoted_ascii_length(const char* utf8_str, int utf8_length); 54 55 // converts a utf8 string to quoted ascii 56 static void as_quoted_ascii(const char* utf8_str, int utf8_length, char* buf, int buflen); 57 58 // converts a quoted ascii string to utf8 string. returns the original 59 // string unchanged if nothing needs to be done. 60 static const char* from_quoted_ascii(const char* quoted_ascii_string); 61 62 // decodes the current utf8 character, stores the result in value, 63 // and returns the end of the current utf8 chararacter. 64 template<typename T> static char* next(const char* str, T* value); 65 66 // decodes the current utf8 character, gets the supplementary character instead of 67 // the surrogate pair when seeing a supplementary character in string, 68 // stores the result in value, and returns the end of the current utf8 chararacter. 69 static char* next_character(const char* str, jint* value); 70 71 // Utility methods 72 static const jbyte* strrchr(const jbyte* base, int length, jbyte c); 73 static bool equal(const jbyte* base1, int length1, const jbyte* base2,int length2); 74 static bool is_supplementary_character(const unsigned char* str); 75 static jint get_supplementary_character(const unsigned char* str); 76 }; 77 78 79 // Low-level interface for UNICODE strings 80 81 // A unicode string represents a string in the UTF-16 format in which supplementary 82 // characters are represented by surrogate pairs. Index values refer to char code 83 // units, so a supplementary character uses two positions in a unicode string. 84 85 class UNICODE : AllStatic { 86 public: 87 // checks if the given unicode character can be encoded as latin1 88 static bool is_latin1(jchar c); 89 90 // checks if the given string can be encoded as latin1 91 static bool is_latin1(jchar* base, int length); 92 93 // returns the utf8 size of a unicode character 94 static int utf8_size(jchar c); 95 static int utf8_size(jbyte c); 96 97 // returns the utf8 length of a unicode string 98 static int utf8_length(jchar* base, int length); 99 static int utf8_length(jbyte* base, int length); 100 101 // converts a unicode string to utf8 string 102 static void convert_to_utf8(const jchar* base, int length, char* utf8_buffer); 103 104 // converts a unicode string to a utf8 string; result is allocated 105 // in resource area unless a buffer is provided. 106 static char* as_utf8(jchar* base, int length); 107 static char* as_utf8(jbyte* base, int length); 108 static char* as_utf8(jchar* base, int length, char* buf, int buflen); 109 static char* as_utf8(jbyte* base, int length, char* buf, int buflen); 110 111 // returns the quoted ascii length of a unicode string 112 template<typename T> static int quoted_ascii_length(T* base, int length); 113 114 // converts a unicode string to quoted ascii 115 template<typename T> static void as_quoted_ascii(const T* base, int length, char* buf, int buflen); 116 }; 117 118 #endif // SHARE_VM_UTILITIES_UTF8_HPP |