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
|
/* -*- Mode: C; tab-width: 8; indent-tabs-mode: t; c-basic-offset: 8 -*- */
/* e-html-utils.c
* Copyright (C) 2000 Helix Code, Inc.
* Author: Dan Winship <danw@helixcode.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 "e-html-utils.h"
#include <ctype.h>
#include <stdio.h>
#include <string.h>
#include <glib.h>
static int etth_interesting[] = {
4, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, /* 0x00 - 0x0f */
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, /* 0x10 - 0x1f */
1, 2, 1, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, /* sp - / */
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 2, 1, 2, 1, 2, /* 0 - ? */
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, 2, 2, 2, 2, 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, 2, 2, 2, 2, 2, /* p - del */
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, /* 0x80 - 0x8f */
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, /* 0x90 - 0x9f */
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, /* 0xa0 - 0xaf */
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, /* 0xb0 - 0xbf */
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, /* 0xc0 - 0xcf */
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, /* 0xd0 - 0xdf */
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, /* 0xe0 - 0xef */
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3 /* 0xf0 - 0xff */
};
#define ETTH_SPECIAL 1
#define ETTH_PUNCTUATION 2
#define ETTH_ESCAPED 3
#define ETTH_EOF 4
static char *
check_size (char **buffer, int *buffer_size, char *out, int len)
{
if (out + len > *buffer + *buffer_size) {
int index = out - *buffer;
*buffer_size *= 2;
*buffer = g_realloc (*buffer, *buffer_size);
out = *buffer + index;
}
return out;
}
static char *
url_extract (const unsigned char **text, gboolean check)
{
const unsigned char *end = *text, *p;
char *out;
while (*end && !isspace (*end) && *end != '"')
end++;
/* Back up if we probably went too far. */
while (end > *text && strchr (",.!?;:>)", *(end - 1)))
end--;
if (check) {
/* Make sure we weren't fooled. */
p = memchr (*text, ':', end - *text);
if (!p || end - p < 3)
return NULL;
}
out = g_strndup (*text, end - *text);
*text = end;
return out;
}
/**
* e_text_to_html:
* @input: a NUL-terminated input buffer
* @flags: some combination of the E_TEXT_TO_HTML_* flags defined
* in e-html-utils.h
*
* 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.
**/
char *
e_text_to_html (const char *input, unsigned int flags)
{
const unsigned char *cur = input, *end;
char *buffer = NULL;
char *out = NULL;
int buffer_size = 0, col;
/* 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>\n");
col = 0;
while (*cur) {
if (isalpha (*cur) && (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) &&
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);
}
}
/* Skip until we need to care. */
end = cur;
while (!etth_interesting[*end] ||
(etth_interesting[*end] == ETTH_PUNCTUATION &&
!(flags & E_TEXT_TO_HTML_CONVERT_URLS)))
end++;
out = check_size (&buffer, &buffer_size, out,
end - cur + 10);
memcpy (out, cur, end - cur);
out += end - cur;
col += end - cur;
if (!*end)
break;
cur = end;
switch (*cur) {
case '<':
strcpy (out, "<");
out += 4;
col++;
break;
case '>':
strcpy (out, ">");
out += 4;
col++;
break;
case '&':
strcpy (out, "&");
out += 5;
col++;
break;
case '"':
strcpy (out, """);
out += 6;
col++;
break;
case '\n':
if (flags & E_TEXT_TO_HTML_CONVERT_NL) {
strcpy (out, "<br>");
out += 4;
}
*out++ = *cur;
col = 0;
break;
case '\t':
if (flags & (E_TEXT_TO_HTML_CONVERT_SPACES |
E_TEXT_TO_HTML_CONVERT_NL)) {
do {
strcpy (out, " ");
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, " ");
out += 6;
col++;
break;
}
}
/* otherwise, FALL THROUGH */
default:
if ((*cur >= 0x20 && *cur < 0x80) ||
(*cur == '\r' || *cur == '\t')) {
/* Default case, just copy. */
*out++ = *cur;
} else
out += g_snprintf(out, 9, "&#%d;", *cur);
col++;
break;
}
cur++;
}
out = check_size (&buffer, &buffer_size, out, 7);
if (flags & E_TEXT_TO_HTML_PRE)
strcpy (out, "</PRE>");
else
*out = '\0';
return buffer;
}
|
