1 /* Copyright (c) 2006, Nokia Corporation
4 * Redistribution and use in source and binary forms, with or without
5 * modification, are permitted provided that the following conditions are
8 * * Redistributions of source code must retain the above copyright
9 * notice, this list of conditions and the following disclaimer.
10 * * Redistributions in binary form must reproduce the above copyright
11 * notice, this list of conditions and the following disclaimer in the
12 * documentation and/or other materials provided with the distribution.
13 * * Neither the name of the Nokia Corporation nor the names of its
14 * contributors may be used to endorse or promote products derived from
15 * this software without specific prior written permission.
17 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS
18 * IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
19 * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
20 * PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER
21 * OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
22 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
23 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
24 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
25 * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
26 * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
27 * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
34 #include <glib/gi18n.h>
36 #include <modest-tny-platform-factory.h>
37 #include <modest-text-utils.h>
38 #include <modest-runtime.h>
43 #endif /*HAVE_CONFIG_H */
46 #define FORWARD_STRING _("-----Forwarded Message-----")
47 #define FROM_STRING _("From:")
48 #define SENT_STRING _("Sent:")
49 #define TO_STRING _("To:")
50 #define SUBJECT_STRING _("Subject:")
51 #define EMPTY_STRING ""
54 * we need these regexps to find URLs in plain text e-mails
56 typedef struct _url_match_pattern_t url_match_pattern_t;
57 struct _url_match_pattern_t {
63 typedef struct _url_match_t url_match_t;
70 #define MAIL_VIEWER_URL_MATCH_PATTERNS { \
71 { "(file|rtsp|http|ftp|https)://[-A-Za-z0-9_$.+!*(),;:@%&=?/~#]+[-A-Za-z0-9_$%&=?/~#]",\
73 { "www\\.[-a-z0-9.]+[-a-z0-9](:[0-9]*)?(/[-A-Za-z0-9_$.+!*(),;:@%&=?/~#]*[^]}\\),?!;:\"]?)?",\
75 { "ftp\\.[-a-z0-9.]+[-a-z0-9](:[0-9]*)?(/[-A-Za-z0-9_$.+!*(),;:@%&=?/~#]*[^]}\\),?!;:\"]?)?",\
77 { "(voipto|callto|chatto|jabberto|xmpp):[-_a-z@0-9.\\+]+", \
79 { "mailto:[-_a-z0-9.\\+]+@[-_a-z0-9.]+", \
81 { "[-_a-z0-9.\\+]+@[-_a-z0-9.]+",\
86 static gchar* cite (const time_t sent_date, const gchar *from);
87 static void hyperlinkify_plain_text (GString *txt);
88 static gint cmp_offsets_reverse (const url_match_t *match1, const url_match_t *match2);
89 static void chk_partial_match (const url_match_t *match, guint* offset);
90 static GSList* get_url_matches (GString *txt);
92 static GString* get_next_line (const char *b, const gsize blen, const gchar * iter);
93 static int get_indent_level (const char *l);
94 static void unquote_line (GString * l);
95 static void append_quoted (GString * buf, const int indent, const GString * str,
97 static int get_breakpoint_utf8 (const gchar * s, const gint indent, const gint limit);
98 static int get_breakpoint_ascii (const gchar * s, const gint indent, const gint limit);
99 static int get_breakpoint (const gchar * s, const gint indent, const gint limit);
101 static gchar* modest_text_utils_quote_plain_text (const gchar *text,
105 static gchar* modest_text_utils_quote_html (const gchar *text,
110 /* ******************************************************************* */
111 /* ************************* PUBLIC FUNCTIONS ************************ */
112 /* ******************************************************************* */
115 modest_text_utils_quote (const gchar *text,
116 const gchar *content_type,
118 const time_t sent_date,
121 gchar *retval, *cited;
123 g_return_val_if_fail (text, NULL);
124 g_return_val_if_fail (content_type, NULL);
126 cited = cite (sent_date, from);
128 if (content_type && strcmp (content_type, "text/html") == 0)
129 /* TODO: extract the <body> of the HTML and pass it to
131 retval = modest_text_utils_quote_html (text, cited, limit);
133 retval = modest_text_utils_quote_plain_text (text, cited, limit);
142 modest_text_utils_cite (const gchar *text,
143 const gchar *content_type,
149 g_return_val_if_fail (text, NULL);
150 g_return_val_if_fail (content_type, NULL);
152 tmp = cite (sent_date, from);
153 retval = g_strdup_printf ("%s%s\n", tmp, text);
160 modest_text_utils_inline (const gchar *text,
161 const gchar *content_type,
165 const gchar *subject)
168 const gchar *plain_format = "%s\n%s %s\n%s %s\n%s %s\n%s %s\n\n%s";
169 const gchar *html_format = \
170 "%s<br>\n<table width=\"100%\" border=\"0\" cellspacing=\"2\" cellpadding=\"2\">\n" \
171 "<tr><td>%s</td><td>%s</td></tr>\n" \
172 "<tr><td>%s</td><td>%s</td></tr>\n" \
173 "<tr><td>%s</td><td>%s</td></tr>\n" \
174 "<tr><td>%s</td><td>%s</td></tr>\n" \
178 g_return_val_if_fail (text, NULL);
179 g_return_val_if_fail (content_type, NULL);
180 g_return_val_if_fail (text, NULL);
182 modest_text_utils_strftime (sent_str, 100, "%c", sent_date);
184 if (!strcmp (content_type, "text/html"))
185 /* TODO: extract the <body> of the HTML and pass it to
187 format = html_format;
189 format = plain_format;
191 return g_strdup_printf (format,
193 FROM_STRING, (from) ? from : EMPTY_STRING,
194 SENT_STRING, sent_str,
195 TO_STRING, (to) ? to : EMPTY_STRING,
196 SUBJECT_STRING, (subject) ? subject : EMPTY_STRING,
200 /* just to prevent warnings:
201 * warning: `%x' yields only last 2 digits of year in some locales
204 modest_text_utils_strftime(char *s, gsize max, const char *fmt, time_t timet)
207 /* static GDate date; */
209 /* does not work on old maemo glib:
210 * g_date_set_time_t (&date, timet);
212 /* g_date_set_time (&date, (GTime) timet); */
213 localtime_r (&timet, &tm);
215 /* return g_date_strftime (s, max, fmt, (const GDate*) &date); */
216 return strftime(s, max, fmt, &tm);
220 modest_text_utils_derived_subject (const gchar *subject, const gchar *prefix)
224 g_return_val_if_fail (prefix, NULL);
227 return g_strdup (prefix);
229 tmp = g_strchug (g_strdup (subject));
231 if (!strncmp (tmp, prefix, strlen (prefix))) {
235 return g_strdup_printf ("%s %s", prefix, subject);
240 modest_text_utils_remove_address (const gchar *address_list, const gchar *address)
242 gchar *dup, *token, *ptr, *result;
243 GString *filtered_emails;
245 g_return_val_if_fail (address_list, NULL);
248 return g_strdup (address_list);
250 /* search for substring */
251 if (!strstr ((const char *) address_list, (const char *) address))
252 return g_strdup (address_list);
254 dup = g_strdup (address_list);
255 filtered_emails = g_string_new (NULL);
257 token = strtok_r (dup, ",", &ptr);
259 while (token != NULL) {
260 /* Add to list if not found */
261 if (!strstr ((const char *) token, (const char *) address)) {
262 if (filtered_emails->len == 0)
263 g_string_append_printf (filtered_emails, "%s", g_strstrip (token));
265 g_string_append_printf (filtered_emails, ",%s", g_strstrip (token));
267 token = strtok_r (NULL, ",", &ptr);
269 result = filtered_emails->str;
273 g_string_free (filtered_emails, FALSE);
279 modest_text_utils_convert_to_html (const gchar *data)
282 gboolean first_space = TRUE;
290 html = g_string_sized_new (len + 100); /* just a guess... */
292 g_string_append_printf (html,
295 "<meta http-equiv=\"content-type\""
296 " content=\"text/html; charset=utf8\">"
300 /* replace with special html chars where needed*/
301 for (i = 0; i != len; ++i) {
305 case 0: break; /* ignore embedded \0s */
306 case '<' : g_string_append (html, "<"); break;
307 case '>' : g_string_append (html, ">"); break;
308 case '&' : g_string_append (html, """); break;
309 case '\n': g_string_append (html, "<br>\n"); break;
312 g_string_append (html, first_space ? " " : " ");
314 } else if (kar == '\t')
315 g_string_append (html, " ");
319 /* optimization trick: accumulate 'normal' chars, then copy */
321 kar = data [++charnum + i];
323 } while ((i + charnum < len) &&
324 (kar > '>' || (kar != '<' && kar != '>'
325 && kar != '&' && kar != ' '
326 && kar != '\n' && kar != '\t')));
327 g_string_append_len (html, &data[i], charnum);
333 g_string_append (html, "</tt></body></html>");
334 hyperlinkify_plain_text (html);
336 return g_string_free (html, FALSE);
340 modest_text_utils_split_addresses_list (const gchar *addresses)
342 gchar *current, *start, *last_blank;
343 GSList *result = NULL;
345 start = (gchar *) addresses;
349 while (*current != '\0') {
350 if ((start == current)&&((*current == ' ')||(*current == ','))) {
352 last_blank = current;
353 } else if (*current == ',') {
354 gchar *new_address = NULL;
355 new_address = g_strndup (start, current - last_blank);
356 result = g_slist_prepend (result, new_address);
359 } else if (*current == '\"') {
360 if (current == start) {
364 while ((*current != '\"')&&(*current != '\0'))
371 if (start != current) {
372 gchar *new_address = NULL;
373 new_address = g_strndup (start, current - last_blank);
374 result = g_slist_prepend (result, new_address);
377 result = g_slist_reverse (result);
383 modest_text_utils_address_range_at_position (const gchar *recipients_list,
388 gchar *current = NULL;
389 gint range_start = 0;
392 gboolean is_quoted = FALSE;
395 for (current = (gchar *) recipients_list; *current != '\0'; current = g_utf8_find_next_char (current, NULL)) {
396 gunichar c = g_utf8_get_char (current);
398 if ((c == ',') && (!is_quoted)) {
399 if (index < position) {
400 range_start = index + 1;
404 } else if (c == '\"') {
405 is_quoted = !is_quoted;
406 } else if ((c == ' ') &&(range_start == index)) {
414 *start = range_start;
420 /* ******************************************************************* */
421 /* ************************* UTILIY FUNCTIONS ************************ */
422 /* ******************************************************************* */
425 get_next_line (const gchar * b, const gsize blen, const gchar * iter)
431 return g_string_new("");
439 gs = g_string_new_len (i0, iter - i0);
443 get_indent_level (const char *l)
460 /* if we hit the signature marker "-- ", we return -(indent + 1). This
461 * stops reformatting.
463 if (strcmp (l, "-- ") == 0) {
471 unquote_line (GString * l)
486 g_string_erase (l, 0, p - l->str);
490 append_quoted (GString * buf, int indent, const GString * str,
495 indent = indent < 0 ? abs (indent) - 1 : indent;
496 for (i = 0; i <= indent; i++) {
497 g_string_append (buf, "> ");
500 g_string_append_len (buf, str->str, cutpoint);
502 g_string_append (buf, str->str);
504 g_string_append (buf, "\n");
508 get_breakpoint_utf8 (const gchar * s, gint indent, const gint limit)
511 const gchar *pos, *last;
514 indent = indent < 0 ? abs (indent) - 1 : indent;
518 uni = g_utf8_to_ucs4_fast (s, -1, NULL);
520 if ((index + 2 * indent > limit) && last) {
524 if (g_unichar_isspace (uni[index])) {
527 pos = g_utf8_next_char (pos);
535 get_breakpoint_ascii (const gchar * s, const gint indent, const gint limit)
540 if (last + 2 * indent < limit)
543 for (i = strlen (s); i > 0; i--) {
545 if (i + 2 * indent <= limit) {
556 get_breakpoint (const gchar * s, const gint indent, const gint limit)
559 if (g_utf8_validate (s, -1, NULL)) {
560 return get_breakpoint_utf8 (s, indent, limit);
561 } else { /* assume ASCII */
562 //g_warning("invalid UTF-8 in msg");
563 return get_breakpoint_ascii (s, indent, limit);
568 cite (const time_t sent_date, const gchar *from)
572 /* format sent_date */
573 modest_text_utils_strftime (sent_str, 100, "%c", sent_date);
574 return g_strdup_printf (N_("On %s, %s wrote:\n"),
576 (from) ? from : EMPTY_STRING);
581 modest_text_utils_quote_plain_text (const gchar *text,
586 gint indent, breakpoint, rem_indent = 0;
587 GString *q, *l, *remaining;
590 /* remaining will store the rest of the line if we have to break it */
591 q = g_string_new (cite);
592 remaining = g_string_new ("");
597 l = get_next_line (text, len, iter);
598 iter = iter + l->len + 1;
599 indent = get_indent_level (l->str);
602 if (remaining->len) {
603 if (l->len && indent == rem_indent) {
604 g_string_prepend (l, " ");
605 g_string_prepend (l, remaining->str);
609 get_breakpoint (remaining->str,
612 append_quoted (q, rem_indent,
613 remaining, breakpoint);
614 g_string_erase (remaining, 0,
616 if (remaining->str[0] == ' ') {
617 g_string_erase (remaining, 0,
620 } while (remaining->len);
623 g_string_free (remaining, TRUE);
624 breakpoint = get_breakpoint (l->str, indent, limit);
625 remaining = g_string_new (l->str + breakpoint);
626 if (remaining->str[0] == ' ') {
627 g_string_erase (remaining, 0, 1);
630 append_quoted (q, indent, l, breakpoint);
631 g_string_free (l, TRUE);
632 } while ((iter < text + len) || (remaining->str[0]));
634 return g_string_free (q, FALSE);
638 modest_text_utils_quote_html (const gchar *text,
642 const gchar *format = \
643 "<!DOCTYPE html PUBLIC \"-//W3C//DTD HTML 4.01 Transitional//EN\">\n" \
647 "<blockquote type=\"cite\">\n%s\n</blockquote>\n" \
651 return g_strdup_printf (format, cite, text);
655 cmp_offsets_reverse (const url_match_t *match1, const url_match_t *match2)
657 return match2->offset - match1->offset;
663 * check if the match is inside an existing match... */
665 chk_partial_match (const url_match_t *match, guint* offset)
667 if (*offset >= match->offset && *offset < match->offset + match->len)
672 get_url_matches (GString *txt)
675 guint rv, i, offset = 0;
676 GSList *match_list = NULL;
678 static url_match_pattern_t patterns[] = MAIL_VIEWER_URL_MATCH_PATTERNS;
679 const size_t pattern_num = sizeof(patterns)/sizeof(url_match_pattern_t);
681 /* initalize the regexps */
682 for (i = 0; i != pattern_num; ++i) {
683 patterns[i].preg = g_slice_new0 (regex_t);
685 /* this should not happen */
686 g_return_val_if_fail (regcomp (patterns[i].preg, patterns[i].regex,
687 REG_ICASE|REG_EXTENDED|REG_NEWLINE) == 0, NULL);
689 /* find all the matches */
690 for (i = 0; i != pattern_num; ++i) {
694 if ((rv = regexec (patterns[i].preg, txt->str + offset, 1, &rm, 0)) != 0) {
695 g_return_val_if_fail (rv == REG_NOMATCH, NULL); /* this should not happen */
696 break; /* try next regexp */
701 /* FIXME: optimize this */
702 /* to avoid partial matches on something that was already found... */
703 /* check_partial_match will put -1 in the data ptr if that is the case */
704 test_offset = offset + rm.rm_so;
705 g_slist_foreach (match_list, (GFunc)chk_partial_match, &test_offset);
707 /* make a list of our matches (<offset, len, prefix> tupels)*/
708 if (test_offset != -1) {
709 url_match_t *match = g_slice_new (url_match_t);
710 match->offset = offset + rm.rm_so;
711 match->len = rm.rm_eo - rm.rm_so;
712 match->prefix = patterns[i].prefix;
713 match_list = g_slist_prepend (match_list, match);
719 for (i = 0; i != pattern_num; ++i) {
720 regfree (patterns[i].preg);
721 g_slice_free (regex_t, patterns[i].preg);
722 } /* don't free patterns itself -- it's static */
724 /* now sort the list, so the matches are in reverse order of occurence.
725 * that way, we can do the replacements starting from the end, so we don't need
726 * to recalculate the offsets
728 match_list = g_slist_sort (match_list,
729 (GCompareFunc)cmp_offsets_reverse);
736 hyperlinkify_plain_text (GString *txt)
739 GSList *match_list = get_url_matches (txt);
741 /* we will work backwards, so the offsets stay valid */
742 for (cursor = match_list; cursor; cursor = cursor->next) {
744 url_match_t *match = (url_match_t*) cursor->data;
745 gchar *url = g_strndup (txt->str + match->offset, match->len);
746 gchar *repl = NULL; /* replacement */
748 /* the prefix is NULL: use the one that is already there */
749 repl = g_strdup_printf ("<a href=\"%s%s\">%s</a>",
750 match->prefix ? match->prefix : EMPTY_STRING,
753 /* replace the old thing with our hyperlink
754 * replacement thing */
755 g_string_erase (txt, match->offset, match->len);
756 g_string_insert (txt, match->offset, repl);
761 g_slice_free (url_match_t, match);
764 g_slist_free (match_list);
770 modest_text_utils_get_display_address (gchar *address)
777 g_return_val_if_fail (g_utf8_validate (address, -1, NULL), NULL);
779 g_strchug (address); /* remove leading whitespace */
781 /* <email@address> from display name */
782 cursor = g_strstr_len (address, strlen(address), "<");
783 if (cursor == address) /* there's nothing else? leave it */
788 /* remove (bla bla) from display name */
789 cursor = g_strstr_len (address, strlen(address), "(");
790 if (cursor == address) /* there's nothing else? leave it */
795 g_strchomp (address); /* remove trailing whitespace */
803 modest_text_utils_get_subject_prefix_len (const gchar *sub)
806 static const gchar* prefix[] = {
807 "Re:", "RE:", "Fwd:", "FWD:", "FW:", NULL
810 if (!sub || (sub[0] != 'R' && sub[0] != 'F')) /* optimization */
816 if (g_str_has_prefix(sub, prefix[i])) {
817 int prefix_len = strlen(prefix[i]);
818 if (sub[prefix_len] == ' ')
819 ++prefix_len; /* ignore space after prefix as well */
829 modest_text_utils_utf8_strcmp (const gchar* s1, const gchar *s2, gboolean insensitive)
834 /* work even when s1 and/or s2 == NULL */
835 if (G_UNLIKELY(s1 == s2))
838 /* if it's not case sensitive */
840 return strcmp (s1 ? s1 : "", s2 ? s2 : "");
842 n1 = g_utf8_collate_key (s1 ? s1 : "", -1);
843 n2 = g_utf8_collate_key (s2 ? s2 : "", -1);
845 result = strcmp (n1, n2);
855 modest_text_utils_get_display_date (time_t date)
858 const guint BUF_SIZE = 64;
859 gchar date_buf[BUF_SIZE];
860 gchar now_buf [BUF_SIZE];
864 modest_text_utils_strftime (date_buf, BUF_SIZE, "%d/%m/%Y", date);
865 modest_text_utils_strftime (now_buf, BUF_SIZE, "%d/%m/%Y", now); /* today */
867 /* if this is today, get the time instead of the date */
868 if (strcmp (date_buf, now_buf) == 0)
869 modest_text_utils_strftime (date_buf, BUF_SIZE, "%H:%M %P", date);
871 return g_strdup(date_buf);
875 modest_text_utils_validate_email_address (const gchar *email_address)
878 const gchar *c = NULL, *domain = NULL;
879 static gchar *rfc822_specials = "()<>@,;:\\\"[]";
881 /* first we validate the name portion (name@domain) */
882 for (c = email_address; *c; c++) {
884 (c == email_address ||
890 if (*c == '\\' && (*++c == ' '))
892 if (*c <= ' ' || *c >= 127)
905 if (*c <= ' ' || *c >= 127)
907 if (strchr(rfc822_specials, *c))
910 if (c == email_address || *(c - 1) == '.')
913 /* next we validate the domain portion (name@domain) */
914 if (!*(domain = ++c))
918 if (c == domain || *(c - 1) == '.')
922 if (*c <= ' ' || *c >= 127)
924 if (strchr(rfc822_specials, *c))
928 return (count >= 1) ? TRUE : FALSE;
935 modest_text_utils_get_display_size (guint size)
938 const guint MB=1024 * KB;
939 const guint GB=1024 * MB;
940 const guint TB=1024 * GB;
943 return g_strdup_printf (_("%0.1f Kb"), (double)size / KB);
945 return g_strdup_printf (_("%d Kb"), size / KB);
947 return g_strdup_printf (_("%d Mb"), size / MB);
949 return g_strdup_printf (_("%d Gb"), size/ GB);
951 return g_strdup_printf (_("Very big"));