On Sun, Sep 24, 2023 at 11:12:10AM -0300, Crystal Kolipe wrote:
> On Sun, Sep 24, 2023 at 12:37:08PM +0200, Walter Alejandro Iglesias wrote:
> > +static int
> > +not_utf8(FILE *message, int len)
> > +{
> > + int n, ulen;
> > + unsigned char s[len];
>
> Please re-read Omar's advice about large unbounded arrays.
Better?
Index: send.c
===================================================================
RCS file: /cvs/src/usr.bin/mail/send.c,v
retrieving revision 1.26
diff -u -p -r1.26 send.c
--- send.c 8 Mar 2023 04:43:11 -0000 1.26
+++ send.c 24 Sep 2023 14:54:25 -0000
@@ -32,6 +32,11 @@
#include "rcv.h"
#include "extern.h"
+#include "locale.h"
+
+/* To check charset of the message and add the appropiate MIME headers */
+static char nutf8;
+static int not_utf8(FILE *s, int len);
static volatile sig_atomic_t sendsignal; /* Interrupted by a signal? */
@@ -341,6 +346,11 @@ mail1(struct header *hp, int printheader
else
puts("Null message body; hope that's ok");
}
+
+ /* Check non valid UTF-8 characters in the message */
+ nutf8 = not_utf8(mtf, fsize(mtf));
+ rewind(mtf);
+
/*
* Now, take the user names from the combined
* to and cc lists and do all the alias
@@ -520,15 +530,30 @@ puthead(struct header *hp, FILE *fo, int
gotcha = 0;
from = hp->h_from ? hp->h_from : value("from");
if (from != NULL)
- fprintf(fo, "From: %s\n", from), gotcha++;
+ fprintf(fo, "From: %s\n", from),
+ gotcha++;
if (hp->h_to != NULL && w & GTO)
- fmt("To:", hp->h_to, fo, w&GCOMMA), gotcha++;
+ fmt("To:", hp->h_to, fo, w&GCOMMA),
+ gotcha++;
if (hp->h_subject != NULL && w & GSUBJECT)
- fprintf(fo, "Subject: %s\n", hp->h_subject), gotcha++;
+ fprintf(fo, "Subject: %s\n", hp->h_subject),
+ gotcha++;
+ if (nutf8 == 0)
+ fprintf(fo, "MIME-Version: 1.0\n"
+ "Content-Type: text/plain; charset=us-ascii\n"
+ "Content-Transfer-Encoding: 7bit\n"),
+ gotcha++;
+ else if (nutf8 == 1)
+ fprintf(fo, "MIME-Version: 1.0\n"
+ "Content-Type: text/plain; charset=utf-8\n"
+ "Content-Transfer-Encoding: 8bit\n"),
+ gotcha++;
if (hp->h_cc != NULL && w & GCC)
- fmt("Cc:", hp->h_cc, fo, w&GCOMMA), gotcha++;
+ fmt("Cc:", hp->h_cc, fo, w&GCOMMA),
+ gotcha++;
if (hp->h_bcc != NULL && w & GBCC)
- fmt("Bcc:", hp->h_bcc, fo, w&GCOMMA), gotcha++;
+ fmt("Bcc:", hp->h_bcc, fo, w&GCOMMA),
+ gotcha++;
if (gotcha && w & GNL)
(void)putc('\n', fo);
return(0);
@@ -609,4 +634,44 @@ sendint(int s)
{
sendsignal = s;
+}
+
+/* Search non valid UTF-8 characters in the message */
+static int
+not_utf8(FILE *message, int len)
+{
+ int c, count, n, ulen;
+ size_t i, resize;
+ size_t jump = 100;
+ unsigned char *s = NULL;
+
+ setlocale(LC_CTYPE, "en_US.UTF-8");
+
+ if (s == NULL && (s = malloc(jump)) == NULL)
+ err(1, NULL);
+
+ i = count = 0;
+ while ((c = getc(message)) != EOF) {
+ if (s == NULL || count == jump) {
+ if ((s = realloc(s, i + jump + 1)) == NULL)
+ err(1, NULL);
+ count = 0;
+ }
+ s[i++] = c;
+ count++;
+ }
+
+ s[i] = '\0';
+
+ ulen = mbstowcs(NULL, s, 0);
+
+ if (ulen == len)
+ n = 0;
+ else if (ulen < 0)
+ n = 2;
+ else if (ulen < len)
+ n = 1;
+
+ free(s);
+ return n;
}
--
Walter
