-/*
- * Functions which handle translation between HTML and plain text
- * 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
- */
+// Functions which handle translation between HTML and plain text
+// Copyright (c) 2000-2023 by the citadel.org team
+//
+// This program is open source software. Use, duplication, or disclosure
+// is subject to the terms of the GNU General Public License, version 3.
#include <stdlib.h>
#include <unistd.h>
#include <sys/stat.h>
#include <errno.h>
#include <limits.h>
-
-#if TIME_WITH_SYS_TIME
-# include <sys/time.h>
-# include <time.h>
-#else
-# if HAVE_SYS_TIME_H
-# include <sys/time.h>
-# else
-# include <time.h>
-# endif
-#endif
-
+#include <time.h>
#include "libcitadel.h"
-/*
- * Convert HTML to plain text.
- *
- * inputmsg = pointer to raw HTML message
- * screenwidth = desired output screenwidth
- * do_citaformat = set to 1 to indent newlines with spaces
- */
-char *html_to_ascii(const char *inputmsg, int msglen, int screenwidth, int do_citaformat) {
+// Convert HTML to plain text.
+//
+// inputmsg = pointer to raw HTML message
+// msglen = stop reading after this many bytes
+// screenwidth = desired output screenwidth
+// ansi = if nonzero, assume output is to a terminal that supports ANSI escape codes
+//
+char *html_to_ascii(const char *inputmsg, int msglen, int screenwidth, int ansi) {
char inbuf[SIZ];
int inbuf_len = 0;
char outbuf[SIZ];
size_t outptr_buffer_size;
size_t output_len = 0;
int i, j, ch, did_out, rb, scanch;
- int nest = 0; /* Bracket nesting level */
- int blockquote = 0; /* BLOCKQUOTE nesting level */
- int styletag = 0; /* STYLE tag nesting level */
+ int nest = 0; // Bracket nesting level
+ int blockquote = 0; // BLOCKQUOTE nesting level
+ int styletag = 0; // STYLE tag nesting level
int styletag_start = 0;
int bytes_processed = 0;
char nl[128];
+ tag[0] = '\0';
strcpy(nl, "\n");
inptr = inputmsg;
strcpy(inbuf, "");
output_len = 0;
do {
- /* Fill the input buffer */
+ // Fill the input buffer
inbuf_len = strlen(inbuf);
if ( (done_reading == 0) && (inbuf_len < (SIZ-128)) ) {
}
- /* Do some parsing */
+ // Do some parsing
if (!IsEmptyStr(inbuf)) {
-
- /* Fold in all the spacing */
+ // Fold in all the spacing
for (i=0; !IsEmptyStr(&inbuf[i]); ++i) {
if (inbuf[i]==10) inbuf[i]=32;
if (inbuf[i]==13) inbuf[i]=32;
strcpy(tag, "");
}
- else if (ch == '>') { /* We have a tag. */
+ else if (ch == '>') { // We have a tag.
if (nest > 0) --nest;
- /* Unqualify the tag (truncate at first space) */
+ // Unqualify the tag (truncate at first space)
if (strchr(tag, ' ') != NULL) {
strcpy(strchr(tag, ' '), "");
}
else if (
(!strcasecmp(tag, "B"))
- || (!strcasecmp(tag, "/B"))
|| (!strcasecmp(tag, "STRONG"))
+ ) {
+ if (ansi) {
+ strcat(outbuf, "\033[1m");
+ }
+ }
+ else if (
+ (!strcasecmp(tag, "/B"))
|| (!strcasecmp(tag, "/STRONG"))
) {
- strcat(outbuf, "*");
-
+ if (ansi) {
+ strcat(outbuf, "\033[22m");
+ }
}
else if (
(!strcasecmp(tag, "I"))
- || (!strcasecmp(tag, "/I"))
|| (!strcasecmp(tag, "EM"))
- || (!strcasecmp(tag, "/EM"))
) {
- strcat(outbuf, "/");
-
+ if (ansi) {
+ strcat(outbuf, "\033[3m");
+ }
}
else if (
- (!strcasecmp(tag, "U"))
- || (!strcasecmp(tag, "/U"))
+ (!strcasecmp(tag, "/I"))
+ || (!strcasecmp(tag, "/EM"))
) {
- strcat(outbuf, "_");
-
+ if (ansi) {
+ strcat(outbuf, "\033[23m");
+ }
+ }
+
+ else if (!strcasecmp(tag, "U")) {
+ if (ansi) {
+ strcat(outbuf, "\033[4m");
+ }
+ }
+
+ else if (!strcasecmp(tag, "/U")) {
+ if (ansi) {
+ strcat(outbuf, "\033[24m");
+ }
}
else if (!strcasecmp(tag, "BR")) {
else if (!strcasecmp(tag, "BLOCKQUOTE")) {
++blockquote;
strcpy(nl, "\n");
+ if ( (blockquote == 1) && (ansi) ) {
+ strcat(nl, "\033[2m\033[2m");
+ }
for (j=0; j<blockquote; ++j) strcat(nl, ">");
strcat(outbuf, nl);
}
else if (!strcasecmp(tag, "/BLOCKQUOTE")) {
strcat(outbuf, "\n");
--blockquote;
+ if ( (blockquote == 0) && (ansi) ) {
+ strcat(outbuf, "\033[22m\033[22m");
+ }
strcpy(nl, "\n");
for (j=0; j<blockquote; ++j) strcat(nl, ">");
strcat(outbuf, nl);
tag[strlen(tag)] = ch;
}
- else if (!nest) {
+ else if ((!nest) && (styletag == 0)) {
outbuf[strlen(outbuf)+1] = 0;
outbuf[strlen(outbuf)] = ch;
}
strcpy(inbuf, &inbuf[i]);
}
- /* Convert &; tags to the forbidden characters */
+ // Convert &; tags to the forbidden characters
if (!IsEmptyStr(outbuf)) for (i=0; !IsEmptyStr(&outbuf[i]); ++i) {
- /* Character entity references */
+ // Character entity references
if (!strncasecmp(&outbuf[i], " ", 6)) {
outbuf[i] = ' ';
strcpy(&outbuf[i+1], &outbuf[i+6]);
strcpy(&outbuf[i+1], &outbuf[i+7]);
}
- /* two-digit decimal equivalents */
+ 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 (outbuf[i] == '&' &&
outbuf[i + 1] == '#' &&
isdigit(outbuf[i + 2]) &&
strcpy(&outbuf[i+1], &outbuf[i+5]);
}
- /* three-digit decimal equivalents */
+ // three-digit decimal equivalents
else if (outbuf[i] == '&' &&
outbuf[i + 1] == '#' &&
isdigit(outbuf[i + 2]) &&
strcpy(&outbuf[i+1], &outbuf[i+6]);
}
- /* four-digit decimal equivalents */
+ // four-digit decimal equivalents
else if (outbuf[i] == '&' &&
outbuf[i + 1] == '#' &&
isdigit(outbuf[i + 2]) &&
scanch = 0;
sscanf(&outbuf[i+2], "%04d", &scanch);
outbuf[i] = scanch;
- strcpy(&outbuf[i+1], &outbuf[i+6]);
+ strcpy(&outbuf[i+1], &outbuf[i+7]);
}
}
- /* Make sure the output buffer is big enough */
+ // Make sure the output buffer is big enough
if ((output_len + strlen(outbuf) + SIZ) > outptr_buffer_size) {
outptr_buffer_size += SIZ;
outptr = realloc(outptr, outptr_buffer_size);
}
}
- /* Output any lines terminated with hard line breaks */
+ // Output any lines terminated with hard line breaks
do {
did_out = 0;
if (strlen(outbuf) > 0) {
strncpy(&outptr[output_len], outbuf, i+1);
output_len += (i+1);
- if (do_citaformat) {
- strcpy(&outptr[output_len], " ");
- ++output_len;
- }
-
strcpy(outbuf, &outbuf[i+1]);
i = 0;
did_out = 1;
}
} while (did_out);
- /* Add soft line breaks */
+ // Add soft line breaks
if (strlen(outbuf) > (screenwidth - 2 )) {
rb = (-1);
for (i=0; i<(screenwidth-2); ++i) {
output_len += rb;
strcpy(&outptr[output_len], nl);
output_len += strlen(nl);
- if (do_citaformat) {
- strcpy(&outptr[output_len], " ");
- ++output_len;
- }
strcpy(outbuf, &outbuf[rb+1]);
- } else {
- strncpy(&outptr[output_len], outbuf,
- screenwidth-2);
+ }
+ else {
+ strncpy(&outptr[output_len], outbuf, screenwidth-2);
output_len += (screenwidth-2);
strcpy(&outptr[output_len], nl);
output_len += strlen(nl);
- if (do_citaformat) {
- strcpy(&outptr[output_len], " ");
- ++output_len;
- }
strcpy(outbuf, &outbuf[screenwidth-2]);
}
}
strcpy(&outptr[output_len], outbuf);
output_len += strlen(outbuf);
- /* Strip leading/trailing whitespace. We can't do this with
- * striplt() because it uses too many strlen()'s
- */
+ // Strip leading/trailing whitespace.
while ((output_len > 0) && (isspace(outptr[0]))) {
strcpy(outptr, &outptr[1]);
--output_len;
--output_len;
}
+ // Make sure the final line ends with a newline character.
if ((output_len > 0) && (outptr[output_len-1] != '\n')) {
strcat(outptr, "\n");
++output_len;