1// Copyright (c) 2006-2008 The Chromium Authors. All rights reserved.
2//
3// Redistribution and use in source and binary forms, with or without
4// modification, are permitted provided that the following conditions are
5// met:
6//
7//    * Redistributions of source code must retain the above copyright
8// notice, this list of conditions and the following disclaimer.
9//    * Redistributions in binary form must reproduce the above
10// copyright notice, this list of conditions and the following disclaimer
11// in the documentation and/or other materials provided with the
12// distribution.
13//    * Neither the name of Google Inc. nor the names of its
14// contributors may be used to endorse or promote products derived from
15// this software without specific prior written permission.
16//
17// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
18// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
19// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
20// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
21// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
22// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
23// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
24// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
25// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
26// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
27// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
28
29#ifndef BASE_STRING16_H_
30#define BASE_STRING16_H_
31
32// WHAT:
33// A version of std::basic_string that provides 2-byte characters even when
34// wchar_t is not implemented as a 2-byte type. You can access this class as
35// string16. We also define char16, which string16 is based upon.
36//
37// WHY:
38// On Windows, wchar_t is 2 bytes, and it can conveniently handle UTF-16/UCS-2
39// data. Plenty of existing code operates on strings encoded as UTF-16.
40//
41// On many other platforms, sizeof(wchar_t) is 4 bytes by default. We can make
42// it 2 bytes by using the GCC flag -fshort-wchar. But then std::wstring fails
43// at run time, because it calls some functions (like wcslen) that come from
44// the system's native C library -- which was built with a 4-byte wchar_t!
45// It's wasteful to use 4-byte wchar_t strings to carry UTF-16 data, and it's
46// entirely improper on those systems where the encoding of wchar_t is defined
47// as UTF-32.
48//
49// Here, we define string16, which is similar to std::wstring but replaces all
50// libc functions with custom, 2-byte-char compatible routines. It is capable
51// of carrying UTF-16-encoded data.
52
53#include <string>
54
55#include "base/basictypes.h"
56
57#ifdef WIN32
58
59typedef wchar_t char16;
60typedef std::wstring string16;
61
62#else  // !WIN32
63
64typedef uint16 char16;
65
66namespace base {
67
68// char16 versions of the functions required by string16_char_traits; these
69// are based on the wide character functions of similar names ("w" or "wcs"
70// instead of "c16").
71int c16memcmp(const char16* s1, const char16* s2, size_t n);
72size_t c16len(const char16* s);
73const char16* c16memchr(const char16* s, char16 c, size_t n);
74char16* c16memmove(char16* s1, const char16* s2, size_t n);
75char16* c16memcpy(char16* s1, const char16* s2, size_t n);
76char16* c16memset(char16* s, char16 c, size_t n);
77
78struct string16_char_traits {
79  typedef char16 char_type;
80  typedef int int_type;
81
82  typedef std::streamoff off_type;
83  typedef mbstate_t state_type;
84  typedef std::fpos<state_type> pos_type;
85
86  static void assign(char_type& c1, const char_type& c2) {
87    c1 = c2;
88  }
89
90  static bool eq(const char_type& c1, const char_type& c2) {
91    return c1 == c2;
92  }
93  static bool lt(const char_type& c1, const char_type& c2) {
94    return c1 < c2;
95  }
96
97  static int compare(const char_type* s1, const char_type* s2, size_t n) {
98    return c16memcmp(s1, s2, n);
99  }
100
101  static size_t length(const char_type* s) {
102    return c16len(s);
103  }
104
105  static const char_type* find(const char_type* s, size_t n,
106                               const char_type& a) {
107    return c16memchr(s, a, n);
108  }
109
110  static char_type* move(char_type* s1, const char_type* s2, int_type n) {
111    return c16memmove(s1, s2, n);
112  }
113
114  static char_type* copy(char_type* s1, const char_type* s2, size_t n) {
115    return c16memcpy(s1, s2, n);
116  }
117
118  static char_type* assign(char_type* s, size_t n, char_type a) {
119    return c16memset(s, a, n);
120  }
121
122  static int_type not_eof(const int_type& c) {
123    return eq_int_type(c, eof()) ? 0 : c;
124  }
125
126  static char_type to_char_type(const int_type& c) {
127    return char_type(c);
128  }
129
130  static int_type to_int_type(const char_type& c) {
131    return int_type(c);
132  }
133
134  static bool eq_int_type(const int_type& c1, const int_type& c2) {
135    return c1 == c2;
136  }
137
138  static int_type eof() {
139    return static_cast<int_type>(EOF);
140  }
141};
142
143}  // namespace base
144
145// The string class will be explicitly instantiated only once, in string16.cc.
146//
147// std::basic_string<> in GNU libstdc++ contains a static data member,
148// _S_empty_rep_storage, to represent empty strings.  When an operation such
149// as assignment or destruction is performed on a string, causing its existing
150// data member to be invalidated, it must not be freed if this static data
151// member is being used.  Otherwise, it counts as an attempt to free static
152// (and not allocated) data, which is a memory error.
153//
154// Generally, due to C++ template magic, _S_empty_rep_storage will be marked
155// as a coalesced symbol, meaning that the linker will combine multiple
156// instances into a single one when generating output.
157//
158// If a string class is used by multiple shared libraries, a problem occurs.
159// Each library will get its own copy of _S_empty_rep_storage.  When strings
160// are passed across a library boundary for alteration or destruction, memory
161// errors will result.  GNU libstdc++ contains a configuration option,
162// --enable-fully-dynamic-string (_GLIBCXX_FULLY_DYNAMIC_STRING), which
163// disables the static data member optimization, but it's a good optimization
164// and non-STL code is generally at the mercy of the system's STL
165// configuration.  Fully-dynamic strings are not the default for GNU libstdc++
166// libstdc++ itself or for the libstdc++ installations on the systems we care
167// about, such as Mac OS X and relevant flavors of Linux.
168//
169// See also http://gcc.gnu.org/bugzilla/show_bug.cgi?id=24196 .
170//
171// To avoid problems, string classes need to be explicitly instantiated only
172// once, in exactly one library.  All other string users see it via an "extern"
173// declaration.  This is precisely how GNU libstdc++ handles
174// std::basic_string<char> (string) and std::basic_string<wchar_t> (wstring).
175//
176// This also works around a Mac OS X linker bug in ld64-85.2.1 (Xcode 3.1.2),
177// in which the linker does not fully coalesce symbols when dead code
178// stripping is enabled.  This bug causes the memory errors described above
179// to occur even when a std::basic_string<> does not cross shared library
180// boundaries, such as in statically-linked executables.
181//
182// TODO(mark): File this bug with Apple and update this note with a bug number.
183
184extern template class std::basic_string<char16, base::string16_char_traits>;
185
186typedef std::basic_string<char16, base::string16_char_traits> string16;
187
188extern std::ostream& operator<<(std::ostream& out, const string16& str);
189
190#endif  // !WIN32
191
192#endif  // BASE_STRING16_H_
193