/*
- * $Id: html.c 6014 2008-02-04 18:38:35Z ajc $
- *
* Functions which handle translation between HTML and plain text
- * Copyright (c) 2000-2005 by Art Cancro and others. This program is
- * released under the terms of the GNU General Public License.
+ * Copyright (c) 2000-2010 by the citadel.org team
+ *
+ * This program is open source 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 3 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 program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <stdlib.h>
* screenwidth = desired output screenwidth
* do_citaformat = set to 1 to indent newlines with spaces
*/
-char *html_to_ascii(char *inputmsg, int msglen, int screenwidth, int do_citaformat) {
+char *html_to_ascii(const char *inputmsg, int msglen, int screenwidth, int do_citaformat) {
char inbuf[SIZ];
int inbuf_len = 0;
char outbuf[SIZ];
char tag[1024];
int done_reading = 0;
- char *inptr;
+ const char *inptr;
char *outptr;
size_t outptr_buffer_size;
size_t output_len = 0;
if (inbuf[i]==10) inbuf[i]=32;
if (inbuf[i]==13) inbuf[i]=32;
if (inbuf[i]==9) inbuf[i]=32;
- /*** we like foreign characters now.
- if ((inbuf[i]<32) || (inbuf[i]>126)) {
- inbuf[i] = '?';
- } */
}
for (i=0; !IsEmptyStr(&inbuf[i]); ++i) {
- while ((inbuf[i]==32)&&(inbuf[i+1]==32))
+ while ((inbuf[i]==32)&&(inbuf[i+1]==32)) {
strcpy(&inbuf[i], &inbuf[i+1]);
+ }
}
for (i=0; !IsEmptyStr(&inbuf[i]); ++i) {
strcat(outbuf, nl);
}
+ else if (
+ (!strcasecmp(tag, "B"))
+ || (!strcasecmp(tag, "/B"))
+ || (!strcasecmp(tag, "STRONG"))
+ || (!strcasecmp(tag, "/STRONG"))
+ ) {
+ strcat(outbuf, "*");
+
+ }
+
+ else if (
+ (!strcasecmp(tag, "I"))
+ || (!strcasecmp(tag, "/I"))
+ || (!strcasecmp(tag, "EM"))
+ || (!strcasecmp(tag, "/EM"))
+ ) {
+ strcat(outbuf, "/");
+
+ }
+
+ else if (
+ (!strcasecmp(tag, "U"))
+ || (!strcasecmp(tag, "/U"))
+ ) {
+ strcat(outbuf, "_");
+
+ }
+
else if (!strcasecmp(tag, "BR")) {
strcat(outbuf, nl);
}
strcpy(&outbuf[i+1], &outbuf[i+7]);
}
+ else if (!strncasecmp(&outbuf[i], "’", 7)) {
+ outbuf[i] = '\'';
+ strcpy(&outbuf[i+1], &outbuf[i+7]);
+ }
+
+ else if (!strncasecmp(&outbuf[i], "–", 7)) {
+ outbuf[i] = '-';
+ strcpy(&outbuf[i+1], &outbuf[i+7]);
+ }
+
/* two-digit decimal equivalents */
- else if ((!strncmp(&outbuf[i], "&#", 2))
- && (outbuf[i+4] == ';') ) {
+ else if (outbuf[i] == '&' &&
+ outbuf[i + 1] == '#' &&
+ isdigit(outbuf[i + 2]) &&
+ isdigit(outbuf[i + 3]) &&
+ (outbuf[i+4] == ';') )
+ {
scanch = 0;
sscanf(&outbuf[i+2], "%02d", &scanch);
outbuf[i] = scanch;
}
/* three-digit decimal equivalents */
- else if ((!strncmp(&outbuf[i], "&#", 2))
- && (outbuf[i+5] == ';') ) {
+ else if (outbuf[i] == '&' &&
+ outbuf[i + 1] == '#' &&
+ isdigit(outbuf[i + 2]) &&
+ isdigit(outbuf[i + 3]) &&
+ isdigit(outbuf[i + 4]) &&
+ (outbuf[i + 5] == ';') )
+ {
scanch = 0;
sscanf(&outbuf[i+2], "%03d", &scanch);
outbuf[i] = scanch;
strcpy(&outbuf[i+1], &outbuf[i+6]);
}
+ /* four-digit decimal equivalents */
+ else if (outbuf[i] == '&' &&
+ outbuf[i + 1] == '#' &&
+ isdigit(outbuf[i + 2]) &&
+ isdigit(outbuf[i + 3]) &&
+ isdigit(outbuf[i + 4]) &&
+ isdigit(outbuf[i + 5]) &&
+ (outbuf[i + 6] == ';') )
+ {
+ scanch = 0;
+ sscanf(&outbuf[i+2], "%04d", &scanch);
+ outbuf[i] = scanch;
+ strcpy(&outbuf[i+1], &outbuf[i+7]);
+ }
+
}
/* Make sure the output buffer is big enough */
--output_len;
}
- if (outptr[output_len-1] != '\n') {
+ if ((output_len > 0) && (outptr[output_len-1] != '\n')) {
strcat(outptr, "\n");
++output_len;
}