X-Git-Url: https://diplodocus.org/git/nmh/blobdiff_plain/1388183fc96a86e5fbbb9d43cebdedd9f44ab64f..ec173fd2c:/sbr/fmt_rfc2047.c?ds=inline

diff --git a/sbr/fmt_rfc2047.c b/sbr/fmt_rfc2047.c
index 9d5b6d3c..8022c2f6 100644
--- a/sbr/fmt_rfc2047.c
+++ b/sbr/fmt_rfc2047.c
@@ -1,22 +1,19 @@
-
-/*
- * fmt_rfc2047.c -- decode RFC-2047 header format 
- *
- * $Id$
+/* 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 "fmt_rfc2047.h"
+#include "check_charset.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,
@@ -24,10 +21,18 @@ 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
 };
 
-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,
@@ -40,12 +45,16 @@ 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;
-    return (hexindex[byte1] << 4 | hexindex[byte2]);
+    return hexindex[byte1] << 4 | hexindex[byte2];
 }
 
 /* Check if character is linear whitespace */
@@ -63,15 +72,12 @@ 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?          */
-    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;
+    iconv_t cd = NULL;
     int fromutf8 = 0;
     char *saveq, *convbuf = NULL;
     size_t savedstlen;
@@ -87,13 +93,18 @@ decode_rfc2047 (char *str, char *dst, size_t dstlen)
     if (!strchr (str, '='))
 	return 0;
 
+#ifdef HAVE_ICONV
+    bool use_iconv = false; /* are we converting encoding with iconv? */
+#endif
+    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
 	/*
@@ -102,8 +113,8 @@ decode_rfc2047 (char *str, char *dst, size_t dstlen)
 	 */
 	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 != '=') {
@@ -111,15 +122,15 @@ decode_rfc2047 (char *str, char *dst, size_t dstlen)
 	    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 */
@@ -129,16 +140,30 @@ 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;
+		use_iconv = true;
 #else
 		continue;
 #endif
@@ -168,9 +193,9 @@ decode_rfc2047 (char *str, char *dst, size_t dstlen)
 	     */
 	    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;
 		}
@@ -182,7 +207,7 @@ decode_rfc2047 (char *str, char *dst, size_t dstlen)
 	     * 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
@@ -201,14 +226,14 @@ decode_rfc2047 (char *str, char *dst, size_t dstlen)
 	     * 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.
@@ -223,7 +248,7 @@ 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 +263,7 @@ 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 +330,10 @@ 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)
@@ -331,7 +359,7 @@ decode_rfc2047 (char *str, char *dst, size_t dstlen)
 	    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 */
 	}
     }