aboutsummaryrefslogtreecommitdiffstats
path: root/e-util/e-html-utils.c
blob: 03c1c3611792a6fe39920bca7d320aaaab279b4d (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
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
/* -*- Mode: C; tab-width: 8; indent-tabs-mode: t; c-basic-offset: 8 -*- */
/* e-html-utils.c
 * Copyright (C) 2000  Ximian, Inc.
 * Author: Dan Winship <danw@ximian.com>
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation; either version 2 of the
 * License, or (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public
 * License along with this library; if not, write to the
 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 02111-1307, USA.
 */

#include <ctype.h>
#include <stdio.h>
#include <string.h>
#include <glib.h>
#include <gal/unicode/gunicode.h>

#include "e-html-utils.h"

static char *
check_size (char **buffer, int *buffer_size, char *out, int len)
{
    if (out + len + 1> *buffer + *buffer_size) {
        int index = out - *buffer;

        *buffer_size = MAX (index + len + 1, *buffer_size * 2);
        *buffer = g_realloc (*buffer, *buffer_size);
        out = *buffer + index;
    }
    return out;
}

/* 1 = non-email-address chars: ()<>@,;:\"[]    */
/* 2 = trailing garbage:        ,.!?;:>)]}`'-_  */
static int special_chars[] = {
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,    /*  nul - 0x0f */
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,    /* 0x10 - 0x1f */
    1, 2, 1, 0, 0, 0, 0, 2, 1, 3, 0, 0, 3, 2, 2, 0,    /*   sp - /    */
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 3, 1, 0, 3, 2,    /*    0 - ?    */
    1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,    /*    @ - O    */
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 3, 0, 2,    /*    P - _    */
    2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,    /*    ` - o    */
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0     /*    p - del  */
};

#define is_addr_char(c) (isprint (c) && !(special_chars[c] & 1))
#define is_addr_char_no_pipes(c) (is_addr_char(c) && (c) != '|')
#define is_trailing_garbage(c) (!isprint(c) || (special_chars[c] & 2))

static char *
url_extract (const unsigned char **text, gboolean check)
{
    const unsigned char *end = *text, *p;
    char *out;

    while (*end && !isspace (*end) && (*end != '"') && (*end < 0x80))
        end++;

    /* Back up if we probably went too far. */
    while (end > *text && is_trailing_garbage (*(end - 1)))
        end--;

    if (check) {
        /* Make sure we weren't fooled. */
        p = memchr (*text, ':', end - *text);
        if (!p || end - p < 4)
            return NULL;
    }

    out = g_strndup (*text, end - *text);
    *text = end;
    return out;
}

static char *
email_address_extract (const unsigned char **cur, char **out, const unsigned char *linestart)
{
    const unsigned char *start, *end, *dot;
    char *addr;

    /* *cur points to the '@'. Look backward for a valid local-part */
    for (start = *cur; start - 1 >= linestart && is_addr_char_no_pipes (*(start - 1)); start--)
        ;
    if (start == *cur)
        return NULL;

    /* Now look forward for a valid domain part */
    for (end = *cur + 1, dot = NULL; is_addr_char_no_pipes (*end); end++) {
        if (*end == '.' && !dot)
            dot = end;
    }
    if (!dot)
        return NULL;

    /* Remove trailing garbage */
    while (is_trailing_garbage (*(end - 1)))
        end--;
    if (dot > end)
        return NULL;

    addr = g_strndup (start, end - start);
    *out -= *cur - start;
    *cur = end;

    return addr;
}

static gboolean
is_citation (const unsigned char *c, gboolean saw_citation)
{
    gunichar u;
    gint i;

    /* A line that starts with a ">" is a citation, unless it's
     * just mbox From-mangling...
     */
    if (*c == '>') {
        const unsigned char *p;

        if (strncmp (c, ">From ", 6) != 0)
            return TRUE;

        /* If the previous line was a citation, then say this
         * one is too.
         */
        if (saw_citation)
            return TRUE;

        /* Same if the next line is */
        p = (const unsigned char *)strchr ((const char *)c, '\n');
        if (p && *++p == '>')
            return TRUE;

        /* Otherwise, it was just an isolated ">From" line. */
        return FALSE;
    }

    /* Check for "Rupert> " and the like... */
    for (i = 0; c && *c && g_unichar_validate (g_utf8_get_char (c)) && *c != '\n' && i < 10; i ++, c = g_utf8_next_char (c)) {
        u = g_utf8_get_char (c);
        if (u == '>')
            return TRUE;
        if (!g_unichar_isalnum (u))
            return FALSE;
    }
    return FALSE;
}

/**
 * e_text_to_html_full:
 * @input: a NUL-terminated input buffer
 * @flags: some combination of the E_TEXT_TO_HTML_* flags defined
 * in e-html-utils.h
 * @color: color for citation highlighting
 *
 * This takes a buffer of text as input and produces a buffer of
 * "equivalent" HTML, subject to certain transformation rules.
 *
 * The set of possible flags is:
 *
 *   - E_TEXT_TO_HTML_PRE: wrap the output HTML in <PRE> and </PRE>.
 *     Should only be used if @input is the entire buffer to be
 *     converted. If e_text_to_html is being called with small pieces
 *     of data, you should wrap the entire result in <PRE> yourself.
 *
 *   - E_TEXT_TO_HTML_CONVERT_NL: convert "\n" to "<BR>\n" on output.
 *     (should not be used with E_TEXT_TO_HTML_PRE, since that would
 *     result in double-newlines).
 *
 *   - E_TEXT_TO_HTML_CONVERT_SPACES: convert a block of N spaces
 *     into N-1 non-breaking spaces and one normal space. A space
 *     at the start of the buffer is always converted to a
 *     non-breaking space, regardless of the following character,
 *     which probably means you don't want to use this flag on
 *     pieces of data that aren't delimited by at least line breaks.
 *
 *     If E_TEXT_TO_HTML_CONVERT_NL and E_TEXT_TO_HTML_CONVERT_SPACES
 *     are both defined, then TABs will also be converted to spaces.
 *
 *   - E_TEXT_TO_HTML_CONVERT_URLS: wrap <a href="..."> </a> around
 *     strings that look like URLs.
 *
 *   - E_TEXT_TO_HTML_CONVERT_ADDRESSES: wrap <a href="mailto:..."> </a> around
 *     strings that look like mail addresses.
 *
 *   - E_TEXT_TO_HTML_MARK_CITATION: wrap <font color="..."> </font> around
 *     citations (lines beginning with "> ", etc).
 *
 *   - E_TEXT_TO_HTML_ESCAPE_8BIT: flatten everything to US-ASCII
 *
 *   - E_TEXT_TO_HTML_CITE: quote the text with "> " at the start of each
 *     line.
 **/
char *
e_text_to_html_full (const char *input, unsigned int flags, guint32 color)
{
    const unsigned char *cur, *next, *linestart;
    char *buffer = NULL;
    char *out = NULL;
    int buffer_size = 0, col;
    gboolean colored = FALSE, saw_citation = FALSE;

    /* Allocate a translation buffer.  */
    buffer_size = strlen (input) * 2 + 5;
    buffer = g_malloc (buffer_size);

    out = buffer;
    if (flags & E_TEXT_TO_HTML_PRE)
        out += sprintf (out, "<PRE>");

    col = 0;

    for (cur = linestart = input; cur && *cur; cur = next) {
        gunichar u;

        if (flags & E_TEXT_TO_HTML_MARK_CITATION && col == 0) {
            saw_citation = is_citation (cur, saw_citation);
            if (saw_citation) {
                if (!colored) {
                    gchar font [25];

                    g_snprintf (font, 25, "<FONT COLOR=\"#%06x\">", color);

                    check_size (&buffer, &buffer_size, out, 25);
                    out += sprintf (out, "%s", font);
                    colored = TRUE;
                }
            } else if (colored) {
                gchar *no_font = "</FONT>";

                check_size (&buffer, &buffer_size, out, 9);
                out += sprintf (out, "%s", no_font);
                colored = FALSE;
            }

            /* Display mbox-mangled ">From" as "From" */
            if (*cur == '>' && !saw_citation)
                cur++;
        } else if (flags & E_TEXT_TO_HTML_CITE && col == 0) {
            check_size (&buffer, &buffer_size, out, 5);
            out += sprintf (out, "&gt; ");
        }

        u = g_utf8_get_char (cur);
        if (g_unichar_isalpha (u) &&
            (flags & E_TEXT_TO_HTML_CONVERT_URLS)) {
            char *tmpurl = NULL, *refurl = NULL, *dispurl = NULL;

            if (!strncasecmp (cur, "http://", 7) ||
                !strncasecmp (cur, "https://", 8) ||
                !strncasecmp (cur, "ftp://", 6) ||
                !strncasecmp (cur, "nntp://", 7) ||
                !strncasecmp (cur, "mailto:", 7) ||
                !strncasecmp (cur, "news:", 5)) {
                tmpurl = url_extract (&cur, TRUE);
                if (tmpurl) {
                    refurl = e_text_to_html (tmpurl, 0);
                    dispurl = g_strdup (refurl);
                }
            } else if (!strncasecmp (cur, "www.", 4) &&
                   (*(cur + 4) < 0x80) &&
                   g_unichar_isalnum (*(cur + 4))) {
                tmpurl = url_extract (&cur, FALSE);
                dispurl = e_text_to_html (tmpurl, 0);
                refurl = g_strdup_printf ("http://%s",
                              dispurl);
            }

            if (tmpurl) {
                out = check_size (&buffer, &buffer_size, out,
                          strlen (refurl) +
                          strlen (dispurl) + 15);
                out += sprintf (out,
                        "<a href=\"%s\">%s</a>",
                        refurl, dispurl);
                col += strlen (tmpurl);
                g_free (tmpurl);
                g_free (refurl);
                g_free (dispurl);
            }

            if (!*cur)
                break;
            u = g_utf8_get_char (cur);
        }

        if (u == '@' && (flags & E_TEXT_TO_HTML_CONVERT_ADDRESSES)) {
            char *addr, *dispaddr, *outaddr;

            addr = email_address_extract (&cur, &out, linestart);
            if (addr) {
                dispaddr = e_text_to_html (addr, 0);
                outaddr = g_strdup_printf ("<a href=\"mailto:%s\">%s</a>",
                               addr, dispaddr);
                out = check_size (&buffer, &buffer_size, out, strlen (outaddr));
                out += sprintf (out, "%s", outaddr);
                col += strlen (addr);
                g_free (addr);
                g_free (dispaddr);
                g_free (outaddr);

                u = g_utf8_get_char (cur);
            }
        }

        if (!g_unichar_validate (u)) {
            /* Sigh. Someone sent undeclared 8-bit data.
             * Assume it's iso-8859-1.
             */
            u = *cur;
            next = cur + 1;
        } else
            next = g_utf8_next_char (cur);

        out = check_size (&buffer, &buffer_size, out, 10);

        switch (u) {
        case '<':
            strcpy (out, "&lt;");
            out += 4;
            col++;
            break;

        case '>':
            strcpy (out, "&gt;");
            out += 4;
            col++;
            break;

        case '&':
            strcpy (out, "&amp;");
            out += 5;
            col++;
            break;

        case '"':
            strcpy (out, "&quot;");
            out += 6;
            col++;
            break;

        case '\n':
            if (flags & E_TEXT_TO_HTML_CONVERT_NL) {
                strcpy (out, "<br>");
                out += 4;
            }
            *out++ = *cur;
            linestart = cur;
            col = 0;
            break;

        case '\t':
            if (flags & (E_TEXT_TO_HTML_CONVERT_SPACES |
                     E_TEXT_TO_HTML_CONVERT_NL)) {
                do {
                    out = check_size (&buffer, &buffer_size,
                            out, 7);
                    strcpy (out, "&nbsp;");
                    out += 6;
                    col++;
                } while (col % 8);
                break;
            }
            /* otherwise, FALL THROUGH */

        case ' ':
            if (flags & E_TEXT_TO_HTML_CONVERT_SPACES) {
                if (cur == (const unsigned char *)input ||
                    *(cur + 1) == ' ' || *(cur + 1) == '\t') {
                    strcpy (out, "&nbsp;");
                    out += 6;
                    col++;
                    break;
                }
            }
            /* otherwise, FALL THROUGH */

        default:
            if ((u >= 0x20 && u < 0x80) ||
                (u == '\r' || u == '\t')) {
                /* Default case, just copy. */
                *out++ = u;
            } else {
                if (flags & E_TEXT_TO_HTML_ESCAPE_8BIT)
                    *out++ = '?';
                else
                    out += g_snprintf(out, 9, "&#%d;", u);
            }
            col++;
            break;
        }
    }

    out = check_size (&buffer, &buffer_size, out, 7);
    if (flags & E_TEXT_TO_HTML_PRE)
        strcpy (out, "</PRE>");
    else
        *out = '\0';

    return buffer;
}

char *
e_text_to_html (const char *input, unsigned int flags)
{
    return e_text_to_html_full (input, flags, 0);
}