aboutsummaryrefslogtreecommitdiffstats
path: root/camel/camel-utf8.c
blob: 5ed5a476d0588cf009a18ca37ea5adf04eb9502b (plain) (blame)
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
253
254
255
256
257

#include <glib.h>
#include "camel-utf8.h"

/**
 * camel_utf8_putc:
 * @ptr: 
 * @c: 
 * 
 * Output a 32 bit unicode character as utf8 octets.  At most 4 octets will
 * be written to @ptr.  @ptr will be advanced to the next character position.
 **/
void
camel_utf8_putc(unsigned char **ptr, guint32 c)
{
    register unsigned char *p = *ptr;

    if (c <= 0x7f)
        *p++ = c;
    else if (c <= 0x7ff) {
        *p++ = 0xc0 | c >> 6;
        *p++ = 0x80 | (c & 0x3f);
    } else if (c <= 0xffff) {
        *p++ = 0xe0 | c >> 12;
        *p++ = 0x80 | ((c >> 6) & 0x3f);
        *p++ = 0x80 | (c & 0x3f);
    } else {
        /* see unicode standard 3.0, S 3.8, max 4 octets */
        *p++ = 0xf0 | c >> 18;
        *p++ = 0x80 | ((c >> 12) & 0x3f);
        *p++ = 0x80 | ((c >> 6) & 0x3f);
        *p++ = 0x80 | (c & 0x3f);
    }

    *ptr = p;
}

/**
 * camel_utf8_getc:
 * @ptr: 
 * 
 * Get a Unicode character from a utf8 stream.  @ptr will be advanced
 * to the next character position.  Invalid utf8 characters will be
 * silently skipped.  @ptr should point to a NUL terminated array.
 * 
 * Return value: The next Unicode character.  @ptr will be advanced to
 * the next character always.
 **/
guint32
camel_utf8_getc(const unsigned char **ptr)
{
    register unsigned char *p = (unsigned char *)*ptr;
    register unsigned char c, r;
    register guint32 v, m;

again:
    r = *p++;
loop:
    if (r < 0x80) {
        *ptr = p;
        v = r;
    } else if (r < 0xf8) { /* valid start char? (max 4 octets) */
        v = r;
        m = 0x7f80; /* used to mask out the length bits */
        do {
            c = *p++;
            if ((c & 0xc0) != 0x80) {
                r = c;
                goto loop;
            }
            v = (v<<6) | (c & 0x3f);
            r<<=1;
            m<<=5;
        } while (r & 0x40);
        
        *ptr = p;

        v &= ~m;
    } else {
        goto again;
    }

    return v;
}

void
g_string_append_u(GString *out, guint32 c)
{
    unsigned char buffer[8];
    unsigned char *p = buffer;

    camel_utf8_putc(&p, c);
    *p = 0;
    g_string_append(out, buffer);
}

static char *utf7_alphabet =
    "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,";

static unsigned char utf7_rank[256] = {
    0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
    0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
    0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x3e,0x3f,0xff,0xff,0xff,
    0x34,0x35,0x36,0x37,0x38,0x39,0x3a,0x3b,0x3c,0x3d,0xff,0xff,0xff,0xff,0xff,0xff,
    0xff,0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,
    0x0f,0x10,0x11,0x12,0x13,0x14,0x15,0x16,0x17,0x18,0x19,0xff,0xff,0xff,0xff,0xff,
    0xff,0x1a,0x1b,0x1c,0x1d,0x1e,0x1f,0x20,0x21,0x22,0x23,0x24,0x25,0x26,0x27,0x28,
    0x29,0x2a,0x2b,0x2c,0x2d,0x2e,0x2f,0x30,0x31,0x32,0x33,0xff,0xff,0xff,0xff,0xff,
    0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
    0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
    0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
    0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
    0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
    0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
    0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
    0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
};

/**
 * camel_utf7_utf8:
 * @ptr: 
 * 
 * Convert a modified utf7 string to utf8.  If the utf7 string
 * contains 8 bit characters, they are treated as iso-8859-1.
 * 
 * The IMAP rules [rfc2060] are used in the utf7 encoding.
 *
 * Return value: The converted string.
 **/
char *
camel_utf7_utf8(const char *ptr)
{
    const unsigned char *p = (unsigned char *)ptr;
    unsigned int c;
    guint32 v=0, x;
    GString *out;
    int i=0;
    int state = 0;
    char *ret;

    out = g_string_new("");
    do {
        c = *p++;
        switch(state) {
        case 0:
            if (c == '&')
                state = 1;
            else
                g_string_append_u(out, c);
            break;
        case 1:
            if (c == '-') {
                g_string_append_c(out, '&');
                state = 0;
            } else if (utf7_rank[c] != 0xff) {
                v = utf7_rank[c];
                i = 6;
                state = 2;
            } else {
                /* invalid */
                g_string_append(out, "&-");
                state = 0;
            }
            break;
        case 2:
            if (c == '-') {
                state = 0;
            } else if (utf7_rank[c] != 0xff) {
                v = (v<<6) | utf7_rank[c];
                i+=6;
                if (i >= 16) {
                    x = (v >> (i-16)) & 0xffff;
                    g_string_append_u(out, x);
                    i-=16;
                }
            } else {
                g_string_append_u(out, c);
                state = 0;
            }
            break;
        }
    } while (c);

    ret = g_strdup(out->str);
    g_string_free(out, TRUE);

    return ret;
}

static void utf7_closeb64(GString *out, guint32 v, guint32 i)
{
    guint32 x;

    if (i>0) {
        x = (v << (6-i)) & 0x3f;
        g_string_append_c(out, utf7_alphabet[x]);
    }
    g_string_append_c(out, '-');
}

/**
 * camel_utf8_utf7:
 * @ptr: 
 * 
 * Convert a utf8 string to a modified utf7 format.
 *
 * The IMAP rules [rfc2060] are used in the utf7 encoding.
 * 
 * Return value: 
 **/
char *
camel_utf8_utf7(const char *ptr)
{
    const unsigned char *p = (unsigned char *)ptr;
    unsigned int c;
    guint32 x, v = 0;
    int state = 0;
    GString *out;
    int i = 0;
    char *ret;

    out = g_string_new("");

    while ( (c = camel_utf8_getc(&p)) ) {
        if (c >= 0x20 && c <= 0x7e) {
            if (state == 1) {
                utf7_closeb64(out, v, i);
                state = 0;
                i = 0;
            }
            if (c == '&')
                g_string_append(out, "&-");
            else
                g_string_append_c(out, c);
        } else {
            if (state == 0) {
                g_string_append_c(out, '&');
                state = 1;
            }
            v = (v << 16) | c;
            i += 16;
            while (i >= 6) {
                x = (v >> (i-6)) & 0x3f;
                g_string_append_c(out, utf7_alphabet[x]);
                i -= 6;
            }
        }
    }

    if (state == 1)
        utf7_closeb64(out, v, i);

    ret = g_strdup(out->str);
    g_string_free(out, TRUE);

    return ret;
}