X-Git-Url: https://diplodocus.org/git/nmh/blobdiff_plain/3af3288f3acdfe29d3c17aefd9e0453ac3204541..07916b2ff:/sbr/fmt_rfc2047.c?ds=sidebyside diff --git a/sbr/fmt_rfc2047.c b/sbr/fmt_rfc2047.c index 25c98c3d..bd703b43 100644 --- a/sbr/fmt_rfc2047.c +++ b/sbr/fmt_rfc2047.c @@ -1,6 +1,4 @@ - -/* - * 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 @@ -11,7 +9,6 @@ #include #ifdef HAVE_ICONV # include -# include #endif static signed char hexindex[] = { @@ -22,6 +19,14 @@ 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 }; @@ -38,8 +43,12 @@ 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; @@ -61,7 +70,7 @@ 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? */ @@ -117,7 +126,7 @@ decode_rfc2047 (char *str, char *dst, size_t dstlen) equals_pending = 1; /* we have a '=' pending */ /* 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 */ @@ -127,13 +136,27 @@ 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; @@ -166,9 +189,9 @@ 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; } @@ -221,7 +244,7 @@ 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)