all repos — openbox @ a7207b7d8367af47ddb7e2733cb963148fd0379f

openbox fork - make it a bit more like ryudo

otk/ustring.cc (raw)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
// -*- mode: C++; indent-tabs-mode: nil; c-basic-offset: 2; -*-

#ifdef    HAVE_CONFIG_H
#  include "../config.h"
#endif // HAVE_CONFIG_H

#include "ustring.hh"

extern "C" {
#include <assert.h>
}

namespace otk {

// helper functions

// The number of bytes to skip to find the next character in the string
static const char utf8_skip[256] = {
  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
  2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
  3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,6,6,1,1
};

// takes a pointer into a utf8 string and returns a unicode character for the
// first character at the pointer
unichar utf8_get_char (const char *p)
{
  unichar result = static_cast<unsigned char>(*p);

  // if its not a 7-bit ascii character
  if((result & 0x80) != 0) {
    // len is the number of bytes this character takes up in the string
    unsigned char len = utf8_skip[result];
    result &= 0x7F >> len;

    while(--len != 0) {
      result <<= 6;
      result |= static_cast<unsigned char>(*++p) & 0x3F;
    }
  }
    
  return result;
}
  
// takes a pointer into a string and finds its offset
static ustring::size_type utf8_ptr_to_offset(const char *str, const char *pos)
{
  ustring::size_type offset = 0;

  while (str < pos) {
    str += utf8_skip[static_cast<unsigned char>(*str)];
    offset++;
  }

  return offset;
}

// takes an offset into a string and returns a pointer to it
const char *utf8_offset_to_ptr(const char *str, ustring::size_type offset)
{
  while (offset--)
    str += utf8_skip[static_cast<unsigned char>(*str)];
  return str;
}

// First overload: stop on '\0' character.
ustring::size_type utf8_byte_offset(const char* str, ustring::size_type offset)
{
  if(offset == ustring::npos)
    return ustring::npos;

  const char* p = str;

  for(; offset != 0; --offset)
  {
    if(*p == '\0')
      return ustring::npos;

    p += utf8_skip[static_cast<unsigned char>(*p)];
  }

  return (p - str);
}

// Second overload: stop when reaching maxlen.
ustring::size_type utf8_byte_offset(const char* str, ustring::size_type offset,
				    ustring::size_type maxlen)
{
  if(offset == ustring::npos)
    return ustring::npos;

  const char *const pend = str + maxlen;
  const char* p = str;

  for(; offset != 0; --offset)
  {
    if(p >= pend)
      return ustring::npos;

    p += utf8_skip[static_cast<unsigned char>(*p)];
  }

  return (p - str);
}


// ustring methods

ustring::ustring(bool utf8)
  : _utf8(utf8)
{
}

ustring::~ustring()
{
}

ustring::ustring(const ustring& other)
  : _string(other._string), _utf8(other._utf8)
{
}

ustring& ustring::operator=(const ustring& other)
{
  _string = other._string;
  _utf8 = other._utf8;
  return *this;
}

ustring::ustring(const std::string& src, bool utf8)
  : _string(src), _utf8(utf8)
{
}

ustring::ustring(const char* src, bool utf8)
  : _string(src), _utf8(utf8)
{
}

ustring& ustring::operator+=(const ustring& src)
{
  assert(_utf8 == src._utf8);
  _string += src._string;
  return *this;
}

ustring& ustring::operator+=(const char* src)
{
  _string += src;
  return *this;
}

ustring& ustring::operator+=(char c)
{
  _string += c;
  return *this;
}

ustring::size_type ustring::size() const
{
  if (_utf8) {
    const char *const pdata = _string.data();
    return utf8_ptr_to_offset(pdata, pdata + _string.size());
  } else
    return _string.size();
}

ustring::size_type ustring::bytes() const
{
  return _string.size();
}

ustring::size_type ustring::capacity() const
{
  return _string.capacity();
}

ustring::size_type ustring::max_size() const
{
  return _string.max_size();
}

bool ustring::empty() const
{
  return _string.empty();
}

void ustring::clear()
{
  _string.erase();
}

ustring& ustring::erase(ustring::size_type i, ustring::size_type n)
{
  if (_utf8) {
    // find a proper offset
    size_type utf_i = utf8_byte_offset(_string.c_str(), i);
    if (utf_i != npos) {
      // if the offset is not npos, find a proper length for 'n'
      size_type utf_n = utf8_byte_offset(_string.data() + utf_i, n,
					 _string.size() - utf_i);
      _string.erase(utf_i, utf_n);
    }
  } else
    _string.erase(i, n);

  return *this;
}

void ustring::resize(ustring::size_type n, char c)
{
  if (_utf8) {
    const size_type size_now = size();
    if(n < size_now)
      erase(n, npos);
    else if(n > size_now)
      _string.append(n - size_now, c);
  } else
    _string.resize(n, c);
}

ustring::value_type ustring::operator[](ustring::size_type i) const
{
  return utf8_get_char(utf8_offset_to_ptr(_string.data(), i));
}

const char* ustring::data() const
{
  return _string.data();
}

const char* ustring::c_str() const
{
  return _string.c_str();
}

bool ustring::utf8() const
{
  return _utf8;
}

void ustring::setUtf8(bool utf8)
{
  _utf8 = utf8;
}

}