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)
208 /* does not work on old maemo glib:
209 * g_date_set_time_t (&date, timet);
211 localtime_r (&timet, &tm);
213 return strftime(s, max, fmt, &tm);
217 modest_text_utils_derived_subject (const gchar *subject, const gchar *prefix)
221 g_return_val_if_fail (prefix, NULL);
224 return g_strdup (prefix);
226 tmp = g_strchug (g_strdup (subject));
228 if (!strncmp (tmp, prefix, strlen (prefix))) {
232 return g_strdup_printf ("%s %s", prefix, subject);
237 modest_text_utils_remove_address (const gchar *address_list, const gchar *address)
239 gchar *dup, *token, *ptr, *result;
240 GString *filtered_emails;
242 g_return_val_if_fail (address_list, NULL);
245 return g_strdup (address_list);
247 /* search for substring */
248 if (!strstr ((const char *) address_list, (const char *) address))
249 return g_strdup (address_list);
251 dup = g_strdup (address_list);
252 filtered_emails = g_string_new (NULL);
254 token = strtok_r (dup, ",", &ptr);
256 while (token != NULL) {
257 /* Add to list if not found */
258 if (!strstr ((const char *) token, (const char *) address)) {
259 if (filtered_emails->len == 0)
260 g_string_append_printf (filtered_emails, "%s", g_strstrip (token));
262 g_string_append_printf (filtered_emails, ",%s", g_strstrip (token));
264 token = strtok_r (NULL, ",", &ptr);
266 result = filtered_emails->str;
270 g_string_free (filtered_emails, FALSE);
277 modest_text_utils_convert_to_html (const gchar *data)
280 gboolean space_seen = FALSE;
288 html = g_string_sized_new (1.5 * len); /* just a guess... */
290 g_string_append_printf (html,
292 "<meta http-equiv=\"content-type\" content=\"text/html; charset=utf8\">"
296 /* replace with special html chars where needed*/
297 for (i = 0; i != len; ++i) {
300 if (space_seen && kar != ' ') {
301 g_string_append_c (html, ' ');
306 case 0: break; /* ignore embedded \0s */
307 case '<' : g_string_append (html, "<"); break;
308 case '>' : g_string_append (html, ">"); break;
309 case '&' : g_string_append (html, "&"); break;
310 case '"' : g_string_append (html, """); break;
311 case '\'' : g_string_append (html, "'"); break;
312 case '\n' : g_string_append (html, "<br>\n"); break;
313 case '\t' : g_string_append (html, " "); break; /* note the space at the end*/
315 if (space_seen) { /* second space in a row */
316 g_string_append (html, "  ");
322 g_string_append_c (html, kar);
326 g_string_append (html, "</tt></body></html>");
327 hyperlinkify_plain_text (html);
329 return g_string_free (html, FALSE);
334 modest_text_utils_split_addresses_list (const gchar *addresses)
336 gchar *current, *start, *last_blank;
337 GSList *result = NULL;
339 start = (gchar *) addresses;
343 while (*current != '\0') {
344 if ((start == current)&&((*current == ' ')||(*current == ','))) {
346 last_blank = current;
347 } else if (*current == ',') {
348 gchar *new_address = NULL;
349 new_address = g_strndup (start, current - last_blank);
350 result = g_slist_prepend (result, new_address);
353 } else if (*current == '\"') {
354 if (current == start) {
358 while ((*current != '\"')&&(*current != '\0'))
365 if (start != current) {
366 gchar *new_address = NULL;
367 new_address = g_strndup (start, current - last_blank);
368 result = g_slist_prepend (result, new_address);
371 result = g_slist_reverse (result);
377 modest_text_utils_address_range_at_position (const gchar *recipients_list,
382 gchar *current = NULL;
383 gint range_start = 0;
386 gboolean is_quoted = FALSE;
389 for (current = (gchar *) recipients_list; *current != '\0'; current = g_utf8_find_next_char (current, NULL)) {
390 gunichar c = g_utf8_get_char (current);
392 if ((c == ',') && (!is_quoted)) {
393 if (index < position) {
394 range_start = index + 1;
398 } else if (c == '\"') {
399 is_quoted = !is_quoted;
400 } else if ((c == ' ') &&(range_start == index)) {
408 *start = range_start;
414 /* ******************************************************************* */
415 /* ************************* UTILIY FUNCTIONS ************************ */
416 /* ******************************************************************* */
419 get_next_line (const gchar * b, const gsize blen, const gchar * iter)
425 return g_string_new("");
433 gs = g_string_new_len (i0, iter - i0);
437 get_indent_level (const char *l)
454 /* if we hit the signature marker "-- ", we return -(indent + 1). This
455 * stops reformatting.
457 if (strcmp (l, "-- ") == 0) {
465 unquote_line (GString * l)
480 g_string_erase (l, 0, p - l->str);
484 append_quoted (GString * buf, int indent, const GString * str,
489 indent = indent < 0 ? abs (indent) - 1 : indent;
490 for (i = 0; i <= indent; i++) {
491 g_string_append (buf, "> ");
494 g_string_append_len (buf, str->str, cutpoint);
496 g_string_append (buf, str->str);
498 g_string_append (buf, "\n");
502 get_breakpoint_utf8 (const gchar * s, gint indent, const gint limit)
505 const gchar *pos, *last;
508 indent = indent < 0 ? abs (indent) - 1 : indent;
512 uni = g_utf8_to_ucs4_fast (s, -1, NULL);
514 if ((index + 2 * indent > limit) && last) {
518 if (g_unichar_isspace (uni[index])) {
521 pos = g_utf8_next_char (pos);
529 get_breakpoint_ascii (const gchar * s, const gint indent, const gint limit)
534 if (last + 2 * indent < limit)
537 for (i = strlen (s); i > 0; i--) {
539 if (i + 2 * indent <= limit) {
550 get_breakpoint (const gchar * s, const gint indent, const gint limit)
553 if (g_utf8_validate (s, -1, NULL)) {
554 return get_breakpoint_utf8 (s, indent, limit);
555 } else { /* assume ASCII */
556 //g_warning("invalid UTF-8 in msg");
557 return get_breakpoint_ascii (s, indent, limit);
562 cite (const time_t sent_date, const gchar *from)
566 /* format sent_date */
567 modest_text_utils_strftime (sent_str, 100, "%c", sent_date);
568 return g_strdup_printf (N_("On %s, %s wrote:\n"),
570 (from) ? from : EMPTY_STRING);
575 modest_text_utils_quote_plain_text (const gchar *text,
580 gint indent, breakpoint, rem_indent = 0;
581 GString *q, *l, *remaining;
584 /* remaining will store the rest of the line if we have to break it */
585 q = g_string_new (cite);
586 remaining = g_string_new ("");
591 l = get_next_line (text, len, iter);
592 iter = iter + l->len + 1;
593 indent = get_indent_level (l->str);
596 if (remaining->len) {
597 if (l->len && indent == rem_indent) {
598 g_string_prepend (l, " ");
599 g_string_prepend (l, remaining->str);
603 get_breakpoint (remaining->str,
606 append_quoted (q, rem_indent,
607 remaining, breakpoint);
608 g_string_erase (remaining, 0,
610 if (remaining->str[0] == ' ') {
611 g_string_erase (remaining, 0,
614 } while (remaining->len);
617 g_string_free (remaining, TRUE);
618 breakpoint = get_breakpoint (l->str, indent, limit);
619 remaining = g_string_new (l->str + breakpoint);
620 if (remaining->str[0] == ' ') {
621 g_string_erase (remaining, 0, 1);
624 append_quoted (q, indent, l, breakpoint);
625 g_string_free (l, TRUE);
626 } while ((iter < text + len) || (remaining->str[0]));
628 return g_string_free (q, FALSE);
632 modest_text_utils_quote_html (const gchar *text,
636 const gchar *format = \
637 "<!DOCTYPE html PUBLIC \"-//W3C//DTD HTML 4.01 Transitional//EN\">\n" \
641 "<blockquote type=\"cite\">\n%s\n</blockquote>\n" \
645 return g_strdup_printf (format, cite, text);
649 cmp_offsets_reverse (const url_match_t *match1, const url_match_t *match2)
651 return match2->offset - match1->offset;
657 * check if the match is inside an existing match... */
659 chk_partial_match (const url_match_t *match, guint* offset)
661 if (*offset >= match->offset && *offset < match->offset + match->len)
666 get_url_matches (GString *txt)
669 guint rv, i, offset = 0;
670 GSList *match_list = NULL;
672 static url_match_pattern_t patterns[] = MAIL_VIEWER_URL_MATCH_PATTERNS;
673 const size_t pattern_num = sizeof(patterns)/sizeof(url_match_pattern_t);
675 /* initalize the regexps */
676 for (i = 0; i != pattern_num; ++i) {
677 patterns[i].preg = g_slice_new0 (regex_t);
679 /* this should not happen */
680 g_return_val_if_fail (regcomp (patterns[i].preg, patterns[i].regex,
681 REG_ICASE|REG_EXTENDED|REG_NEWLINE) == 0, NULL);
683 /* find all the matches */
684 for (i = 0; i != pattern_num; ++i) {
688 if ((rv = regexec (patterns[i].preg, txt->str + offset, 1, &rm, 0)) != 0) {
689 g_return_val_if_fail (rv == REG_NOMATCH, NULL); /* this should not happen */
690 break; /* try next regexp */
695 /* FIXME: optimize this */
696 /* to avoid partial matches on something that was already found... */
697 /* check_partial_match will put -1 in the data ptr if that is the case */
698 test_offset = offset + rm.rm_so;
699 g_slist_foreach (match_list, (GFunc)chk_partial_match, &test_offset);
701 /* make a list of our matches (<offset, len, prefix> tupels)*/
702 if (test_offset != -1) {
703 url_match_t *match = g_slice_new (url_match_t);
704 match->offset = offset + rm.rm_so;
705 match->len = rm.rm_eo - rm.rm_so;
706 match->prefix = patterns[i].prefix;
707 match_list = g_slist_prepend (match_list, match);
713 for (i = 0; i != pattern_num; ++i) {
714 regfree (patterns[i].preg);
715 g_slice_free (regex_t, patterns[i].preg);
716 } /* don't free patterns itself -- it's static */
718 /* now sort the list, so the matches are in reverse order of occurence.
719 * that way, we can do the replacements starting from the end, so we don't need
720 * to recalculate the offsets
722 match_list = g_slist_sort (match_list,
723 (GCompareFunc)cmp_offsets_reverse);
730 hyperlinkify_plain_text (GString *txt)
733 GSList *match_list = get_url_matches (txt);
735 /* we will work backwards, so the offsets stay valid */
736 for (cursor = match_list; cursor; cursor = cursor->next) {
738 url_match_t *match = (url_match_t*) cursor->data;
739 gchar *url = g_strndup (txt->str + match->offset, match->len);
740 gchar *repl = NULL; /* replacement */
742 /* the prefix is NULL: use the one that is already there */
743 repl = g_strdup_printf ("<a href=\"%s%s\">%s</a>",
744 match->prefix ? match->prefix : EMPTY_STRING,
747 /* replace the old thing with our hyperlink
748 * replacement thing */
749 g_string_erase (txt, match->offset, match->len);
750 g_string_insert (txt, match->offset, repl);
755 g_slice_free (url_match_t, match);
758 g_slist_free (match_list);
764 modest_text_utils_get_display_address (gchar *address)
771 g_return_val_if_fail (g_utf8_validate (address, -1, NULL), NULL);
773 g_strchug (address); /* remove leading whitespace */
775 /* <email@address> from display name */
776 cursor = g_strstr_len (address, strlen(address), "<");
777 if (cursor == address) /* there's nothing else? leave it */
782 /* remove (bla bla) from display name */
783 cursor = g_strstr_len (address, strlen(address), "(");
784 if (cursor == address) /* there's nothing else? leave it */
789 g_strchomp (address); /* remove trailing whitespace */
797 modest_text_utils_get_subject_prefix_len (const gchar *sub)
800 static const gchar* prefix[] = {
801 "Re:", "RE:", "Fwd:", "FWD:", "FW:", NULL
804 if (!sub || (sub[0] != 'R' && sub[0] != 'F')) /* optimization */
810 if (g_str_has_prefix(sub, prefix[i])) {
811 int prefix_len = strlen(prefix[i]);
812 if (sub[prefix_len] == ' ')
813 ++prefix_len; /* ignore space after prefix as well */
823 modest_text_utils_utf8_strcmp (const gchar* s1, const gchar *s2, gboolean insensitive)
828 /* work even when s1 and/or s2 == NULL */
829 if (G_UNLIKELY(s1 == s2))
832 /* if it's not case sensitive */
834 return strcmp (s1 ? s1 : "", s2 ? s2 : "");
836 n1 = g_utf8_collate_key (s1 ? s1 : "", -1);
837 n2 = g_utf8_collate_key (s2 ? s2 : "", -1);
839 result = strcmp (n1, n2);
849 modest_text_utils_get_display_date (time_t date)
852 const guint BUF_SIZE = 64;
853 gchar date_buf[BUF_SIZE];
854 gchar now_buf [BUF_SIZE];
858 modest_text_utils_strftime (date_buf, BUF_SIZE, "%d/%m/%Y", date);
859 modest_text_utils_strftime (now_buf, BUF_SIZE, "%d/%m/%Y", now); /* today */
860 /* modest_text_utils_strftime (date_buf, BUF_SIZE, "%x", date); */
861 /* modest_text_utils_strftime (now_buf, BUF_SIZE, "%x", now); /\* today *\/ */
863 /* if this is today, get the time instead of the date */
864 if (strcmp (date_buf, now_buf) == 0)
865 modest_text_utils_strftime (date_buf, BUF_SIZE, "%H:%M %P", date);
867 return g_strdup(date_buf);
871 modest_text_utils_validate_email_address (const gchar *email_address)
874 const gchar *c = NULL, *domain = NULL;
875 static gchar *rfc822_specials = "()<>@,;:\\\"[]";
877 /* first we validate the name portion (name@domain) */
878 for (c = email_address; *c; c++) {
880 (c == email_address ||
886 if (*c == '\\' && (*++c == ' '))
888 if (*c <= ' ' || *c >= 127)
901 if (*c <= ' ' || *c >= 127)
903 if (strchr(rfc822_specials, *c))
906 if (c == email_address || *(c - 1) == '.')
909 /* next we validate the domain portion (name@domain) */
910 if (!*(domain = ++c))
914 if (c == domain || *(c - 1) == '.')
918 if (*c <= ' ' || *c >= 127)
920 if (strchr(rfc822_specials, *c))
924 return (count >= 1) ? TRUE : FALSE;
931 modest_text_utils_get_display_size (guint size)
934 const guint MB=1024 * KB;
935 const guint GB=1024 * MB;
936 const guint TB=1024 * GB;
939 return g_strdup_printf (_("%0.1f Kb"), (double)size / KB);
941 return g_strdup_printf (_("%d Kb"), size / KB);
943 return g_strdup_printf (_("%d Mb"), size / MB);
945 return g_strdup_printf (_("%d Gb"), size/ GB);
947 return g_strdup_printf (_("Very big"));