Deference char pointer to test for empty string instead of strlen(3).

[nmh] / sbr / fmt_rfc2047.c

diff --git a/sbr/fmt_rfc2047.c b/sbr/fmt_rfc2047.c
index 87fddb90cb6c72718aadd1f6dcfc1d0c3eefa921..aa01913b79e19f80b242ca6cd889258d73c6b6b7 100644 (file)
--- a/sbr/fmt_rfc2047.c
+++ b/sbr/fmt_rfc2047.c
@@ -2,8 +2,6 @@
 /*
  * fmt_rfc2047.c -- decode RFC-2047 header format 
  *
- * $Id$
- *
  * 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.
@@ -13,7 +11,6 @@
 #include <h/utils.h>
 #ifdef HAVE_ICONV
 #  include <iconv.h>
-#  include <errno.h>
 #endif
 
 static signed char hexindex[] = {
@@ -24,6 +21,14 @@ static signed char hexindex[] = {
     -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
 };
 
@@ -40,8 +45,12 @@ static signed char index_64[128] = {
 
 #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;
@@ -63,7 +72,7 @@ int
 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?          */
@@ -129,13 +138,27 @@ decode_rfc2047 (char *str, char *dst, size_t dstlen)
            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;
@@ -223,7 +246,7 @@ decode_rfc2047 (char *str, char *dst, size_t dstlen)
            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)
@@ -238,6 +261,7 @@ decode_rfc2047 (char *str, char *dst, size_t dstlen)
            } else {
                /* base64 */
                int c1, c2, c3, c4;
+               c1 = c2 = c3 = c4 = -1;
 
                pp = startofmime;
                while (pp < endofmime) {
@@ -304,8 +328,10 @@ decode_rfc2047 (char *str, char *dst, size_t dstlen)
                            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)