-
-/*
- * fmt_rfc2047.c -- decode RFC-2047 header format
+/* fmt_rfc2047.c -- decode RFC-2047 header format
*
* This code is Copyright (c) 2002, by the authors of nmh. See the
* COPYRIGHT file in the root directory of the nmh distribution for
* complete copyright information.
*/
-#include <h/mh.h>
-#include <h/utils.h>
+#include "h/mh.h"
+#include "h/utils.h"
#ifdef HAVE_ICONV
# include <iconv.h>
-# include <errno.h>
#endif
-static signed char hexindex[] = {
+static const signed char hexindex[] = {
-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
-1,10,11,12,13,14,15,-1,-1,-1,-1,-1,-1,-1,-1,-1,
-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
-1,10,11,12,13,14,15,-1,-1,-1,-1,-1,-1,-1,-1,-1,
+ -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
+ -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
+ -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
+ -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
+ -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
+ -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
+ -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
+ -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1
};
-static signed char index_64[128] = {
+static const signed char index_64[128] = {
-1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1,
-1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1,
-1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,62, -1,-1,-1,63,
#define char64(c) (((unsigned char) (c) > 127) ? -1 : index_64[(unsigned char) (c)])
-static int
-unqp (unsigned char byte1, unsigned char byte2)
+/*
+ * Decode two quoted-pair characters
+ */
+
+int
+decode_qp (unsigned char byte1, unsigned char byte2)
{
if (hexindex[byte1] == -1 || hexindex[byte2] == -1)
return -1;
- return (hexindex[byte1] << 4 | hexindex[byte2]);
+ return hexindex[byte1] << 4 | hexindex[byte2];
}
/* Check if character is linear whitespace */
decode_rfc2047 (char *str, char *dst, size_t dstlen)
{
char *p, *q, *pp;
- char *startofmime, *endofmime;
+ char *startofmime, *endofmime, *endofcharset;
int c, quoted_printable;
int encoding_found = 0; /* did we decode anything? */
- int between_encodings = 0; /* are we between two encodings? */
- int equals_pending = 0; /* is there a '=' pending? */
int whitespace = 0; /* how much whitespace between encodings? */
#ifdef HAVE_ICONV
- int use_iconv = 0; /* are we converting encoding with iconv? */
iconv_t cd = NULL;
int fromutf8 = 0;
char *saveq, *convbuf = NULL;
if (!strchr (str, '='))
return 0;
+ bool use_iconv = false; /* are we converting encoding with iconv? */
+ bool between_encodings = false;
+ bool equals_pending = false;
for (p = str, q = dst; *p; p++) {
/* reset iconv */
#ifdef HAVE_ICONV
if (use_iconv) {
iconv_close(cd);
- use_iconv = 0;
+ use_iconv = false;
}
#endif
/*
*/
if (equals_pending) {
ADDCHR('=');
- equals_pending = 0;
- between_encodings = 0; /* we have added non-whitespace text */
+ equals_pending = false;
+ between_encodings = false; /* we have added non-whitespace text */
}
if (*p != '=') {
if (between_encodings && is_lws(*p))
whitespace++;
else
- between_encodings = 0; /* we have added non-whitespace text */
+ between_encodings = false; /* we have added non-whitespace text */
ADDCHR(*p);
continue;
}
- equals_pending = 1; /* we have a '=' pending */
+ equals_pending = true;
/* Check for initial =? */
- if (*p == '=' && p[1] && p[1] == '?' && p[2]) {
+ if (*p == '=' && p[1] == '?' && p[2]) {
startofmime = p + 2;
/* Scan ahead for the next '?' character */
if (!*pp)
continue;
+ /*
+ * RFC 2231 specifies that language information can appear
+ * in a charset specification like so:
+ *
+ * =?us-ascii*en?Q?Foo?=
+ *
+ * Right now we don't use language information, so ignore it.
+ */
+
+ for (endofcharset = startofmime;
+ *endofcharset != '*' && endofcharset < pp;
+ endofcharset++)
+ ;
+
/* Check if character set can be handled natively */
- if (!check_charset(startofmime, pp - startofmime)) {
+ if (!check_charset(startofmime, endofcharset - startofmime)) {
#ifdef HAVE_ICONV
/* .. it can't. We'll use iconv then. */
- *pp = '\0';
+ *endofcharset = '\0';
cd = iconv_open(get_charset(), startofmime);
- fromutf8 = !mh_strcasecmp(startofmime, "UTF-8");
+ fromutf8 = !strcasecmp(startofmime, "UTF-8");
*pp = '?';
if (cd == (iconv_t)-1) continue;
- use_iconv = 1;
+ use_iconv = true;
#else
continue;
#endif
*/
endofmime = NULL;
for (pp = startofmime; *pp && *(pp+1); pp++) {
- if (is_lws(*pp)) {
+ if (is_lws(*pp))
break;
- } else if (*pp == '?' && pp[1] == '=') {
+ if (*pp == '?' && pp[1] == '=') {
endofmime = pp;
break;
}
* We've found an encoded word, so we can drop
* the '=' that was pending
*/
- equals_pending = 0;
+ equals_pending = false;
/*
* If we are between two encoded words separated only by
* malloc 0 bytes but skip on to the end
*/
if (endofmime == startofmime && use_iconv) {
- use_iconv = 0;
+ use_iconv = false;
iconv_close(cd);
}
if (use_iconv) {
saveq = q;
savedstlen = dstlen;
- q = convbuf = (char *) mh_xmalloc(endofmime - startofmime);
+ q = convbuf = mh_xmalloc(endofmime - startofmime);
}
/* ADDCHR2 is for adding characters when q is or might be convbuf:
* in this case on buffer-full we want to run iconv before returning.
if (quoted_printable) {
for (pp = startofmime; pp < endofmime; pp++) {
if (*pp == '=') {
- c = unqp (pp[1], pp[2]);
+ c = decode_qp (pp[1], pp[2]);
if (c == -1)
continue;
if (c != 0)
break;
/* skip to next input character */
if (fromutf8) {
- for (start++;(start < q) && ((*start & 192) == 128);start++)
- inbytes--;
+ for (++start, --inbytes;
+ start < q && (*start & 192) == 128;
+ ++start, --inbytes)
+ continue;
} else
start++, inbytes--;
if (start >= q)
p = endofmime + 1;
encoding_found = 1; /* we found (at least 1) encoded word */
- between_encodings = 1; /* we have just decoded something */
+ between_encodings = true; /* we have just decoded something */
whitespace = 0; /* re-initialize amount of whitespace */
}
}
projects / nmh / blobdiff