summaryrefslogtreecommitdiff
path: root/src/unicode.c
blob: a2dcacb320067dcecd81501c881809a797f520f2 (plain)
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

#include "usuals.h"
#include "ntfs.h"

/*
 * Transcode UCS2 to UTF8. 
 *
 * Since the nature of the transformation is that the 
 * resulting length is unpredictable, this function
 * allocates it's own memory.
 */
char* unicode_transcode16to8(const ntfs_char* src, size_t len)
{
  char* ret = NULL;
  size_t alloc = 0;
  size_t pos = 0;
  const ntfs_char* c;
  const ntfs_char* e;

  /* Allocate 1.25 times the length initially */
  alloc = len + (len / 4) + 1;
  ret = (char*)mallocf(alloc * sizeof(char));

  c = src;
  e = c + len;

  for( ; c < e; c++)
  {
    /* Make sure we have enough memory */
    if(pos + 4 >= alloc)
    {
      alloc += (len / 2) + 1;
      ret = (char*)reallocf(ret, alloc * sizeof(char));
    }

    /* Encode as one character */
    if(*c <= 0x007F)
    {
      ret[pos++] = (char)*c;
    }

    /* Encode as two characters */
    else if(*c <= 0x07FF)
    {
      ret[pos++] = (char)(192 | (*c >> 6));
      ret[pos++] = (char)(128 | (*c & 63));
    }

    /* Encode as three characters */
    else 
    {
      ret[pos++] = (char)(224 | (*c >> 12));
      ret[pos++] = (char)(128 | ((*c >> 6) & 63));
      ret[pos++] = (char)(128 | (*c & 63));
    }
  }

  ret[pos] = 0;
  return ret;
}

/*
 * Transcode UTF-8 to UCS2
 * 
 * Since a semi predictable length of the resulting data is 
 * known, the caller should allocate the memory for this conversion.
 */
ntfs_char* unicode_transcode8to16(const char* src, ntfs_char* out, size_t len)
{
  /* Note: out should always be at least as long as src in chars */

  size_t pos = 0;
  const char* c;
  const char* e;

  c = src;
  e = c + len;

  for( ; c < e; c++)
  {
    /* We never have to reallocate here. We will always
       be using the same or less number of output characters 
       than input chars. That's just the nature of the encoding. */
    
    /* First 4 bits set */
    if((c + 3) < e && 
       (c[0] & 0xF8) == 0xF0 && 
       (c[1] & 0xC0) == 0x80 &&
       (c[2] & 0xC0) == 0x80 &&
       (c[3] & 0xC0) == 0x80)
    {
      out[pos++] = (ntfs_char)(((ntfs_char)c[0] & 7) << 18 |
                             ((ntfs_char)c[1] & 63) << 12 |
                             ((ntfs_char)c[2] & 63) << 6 |
                             ((ntfs_char)c[3] & 63));
      c += 3;
    }

    /* First 3 bits set */
    else if((c + 2) < e && 
            (c[0] & 0xF0) == 0xE0 &&
            (c[1] & 0xC0) == 0x80 &&
            (c[2] & 0xC0) == 0x80)
    {
      out[pos++] = (ntfs_char)(((ntfs_char)c[0] & 15) << 12 |
                             ((ntfs_char)c[1] & 63) << 6 |
                             ((ntfs_char)c[2] & 63));
      c += 2;
    }

    /* First 2 bits set */
    else if((c + 1) < e && 
            (c[0] & 0xE0) == 0xC0 &&
            (c[1] & 0xC0) == 0x80)
    {
      out[pos++] = (ntfs_char)(((ntfs_char)c[0] & 31) << 6 |
                             ((ntfs_char)c[1] & 63));
      c += 1;
    }

    /* First bit set */
    else if(!(c[0] & 0x80))  
    {
      out[pos++] = (ntfs_char)c[0];
    }

    /* Invalid encoding */
    else
    {
      out[pos++] = L'?';
    }
  }

  out[pos] = 0;
  return out;
}