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 
  30 // Low-level interface for UTF8 strings
  31 
  32 class UTF8 : AllStatic {
  33  public:
  34   // returns the unicode length of a 0-terminated utf8 string
  35   static int unicode_length(const char* utf8_str) {
  36     bool is_latin1, has_multibyte;
  37     return unicode_length(utf8_str, is_latin1, has_multibyte);
  38   }
  39   static int unicode_length(const char* utf8_str, bool& is_latin1, bool& has_multibyte);
  40 
  41   // returns the unicode length of a non-0-terminated utf8 string
  42   static int unicode_length(const char* utf8_str, int len) {
  43     bool is_latin1, has_multibyte;
  44     return unicode_length(utf8_str, len, is_latin1, has_multibyte);
  45   }
  46   static int unicode_length(const char* utf8_str, int len, bool& is_latin1, bool& has_multibyte);
  47 
  48   // converts a utf8 string to a unicode string
  49   template<typename T> static void convert_to_unicode(const char* utf8_str, T* unicode_str, int unicode_length);
  50 
  51   // returns the quoted ascii length of a utf8 string
  52   static int quoted_ascii_length(const char* utf8_str, int utf8_length);
  53 
  54   // converts a utf8 string to quoted ascii
  55   static void as_quoted_ascii(const char* utf8_str, int utf8_length, char* buf, int buflen);
  56 
  57   // converts a quoted ascii string to utf8 string.  returns the original
  58   // string unchanged if nothing needs to be done.
  59   static const char* from_quoted_ascii(const char* quoted_ascii_string);
  60 
  61   // decodes the current utf8 character, stores the result in value,
  62   // and returns the end of the current utf8 chararacter.
  63   template<typename T> static char* next(const char* str, T* value);
  64 
  65   // decodes the current utf8 character, gets the supplementary character instead of
  66   // the surrogate pair when seeing a supplementary character in string,
  67   // stores the result in value, and returns the end of the current utf8 chararacter.
  68   static char* next_character(const char* str, jint* value);
  69 
  70   // Utility methods
  71   static const jbyte* strrchr(const jbyte* base, int length, jbyte c);
  72   static bool   equal(const jbyte* base1, int length1, const jbyte* base2,int length2);
  73   static bool   is_supplementary_character(const unsigned char* str);
  74   static jint   get_supplementary_character(const unsigned char* str);
  75 
  76   static bool   is_legal_utf8(const unsigned char* buffer, int length,
  77                               bool version_leq_47);
  78 };
  79 
  80 
  81 // Low-level interface for UNICODE strings
  82 
  83 // A unicode string represents a string in the UTF-16 format in which supplementary
  84 // characters are represented by surrogate pairs. Index values refer to char code
  85 // units, so a supplementary character uses two positions in a unicode string.
  86 
  87 class UNICODE : AllStatic {
  88  public:
  89   // checks if the given unicode character can be encoded as latin1
  90   static bool is_latin1(jchar c);
  91 
  92   // checks if the given string can be encoded as latin1
  93   static bool is_latin1(const jchar* base, int length);
  94 
  95   // returns the utf8 size of a unicode character
  96   static int utf8_size(jchar c);
  97   static int utf8_size(jbyte c);
  98 
  99   // returns the utf8 length of a unicode string
 100   template<typename T> static int utf8_length(const T* base, int length);
 101 
 102   // converts a unicode string to utf8 string
 103   static void convert_to_utf8(const jchar* base, int length, char* utf8_buffer);
 104 
 105   // converts a unicode string to a utf8 string; result is allocated
 106   // in resource area unless a buffer is provided. The unicode 'length'
 107   // parameter is set to the length of the result utf8 string.
 108   template<typename T> static char* as_utf8(const T* base, int& length);
 109   static char* as_utf8(const jchar* base, int length, char* buf, int buflen);
 110   static char* as_utf8(const jbyte* base, int length, char* buf, int buflen);
 111 
 112   // returns the quoted ascii length of a unicode string
 113   template<typename T> static int quoted_ascii_length(const T* base, int length);
 114 
 115   // converts a unicode string to quoted ascii
 116   template<typename T> static void as_quoted_ascii(const T* base, int length, char* buf, int buflen);
 117 };
 118 
 119 #endif // SHARE_VM_UTILITIES_UTF8_HPP