static void mime_content_type(MIME_NODE *node, const HEADER_OPTS *header_info)
{
const char *cp;
ssize_t tok_count;
MIME_STATE *state = node->state;
#define PARSE_CONTENT_TYPE_HEADER(state, ptr) \
header_token(state->token, MIME_MAX_TOKEN, \
state->token_buffer, ptr, RFC2045_TSPECIALS, ';')
cp = STR(node->buffer) + strlen(header_info->name) + 1;
if ((tok_count = PARSE_CONTENT_TYPE_HEADER(state, &cp)) <= 0) {
/*
* other/whatever.
*/
node->ctype = MIME_CTYPE_OTHER;
return;
}
/* tok_count > 0 */
/*
* message/whatever body parts start with another block of message
* headers that we may want to look at. The partial and external-body
* subtypes cannot be subjected to 8-bit -> 7-bit conversion, so we
* must properly recognize them.
*/
if (TOKEN_MATCH(state->token[0], "message")) {
node->ctype = MIME_CTYPE_MESSAGE;
node->stype = MIME_STYPE_OTHER;
if (tok_count >= 3 && state->token[1].type == '/') {
if (TOKEN_MATCH(state->token[2], "rfc822"))
node->stype = MIME_STYPE_RFC822;
else if (TOKEN_MATCH(state->token[2], "partial"))
node->stype = MIME_STYPE_PARTIAL;
else if (TOKEN_MATCH(state->token[2], "external-body"))
node->stype = MIME_STYPE_EXTERN_BODY;
}
}
/*
* multipart/digest has default content type message/rfc822,
* multipart/whatever has default content type text/plain.
*/
else if (TOKEN_MATCH(state->token[0], "multipart")) {
node->ctype = MIME_CTYPE_MULTIPART;
if (tok_count >= 3 && state->token[1].type == '/') {
if (TOKEN_MATCH(state->token[2], "digest")) {
node->ctype = MIME_CTYPE_MESSAGE;
node->stype = MIME_STYPE_RFC822;
} else if (TOKEN_MATCH(state->token[2], "alternative")) {
node->stype = MIME_STYPE_ALTERNATIVE;
} else if (TOKEN_MATCH(state->token[2], "related")) {
node->stype = MIME_STYPE_RELATED;
} else if (TOKEN_MATCH(state->token[2], "mixed")) {
node->stype = MIME_STYPE_MIXED;
} else {
node->stype = MIME_STYPE_OTHER;
}
} else {
node->ctype = MIME_CTYPE_TEXT;
node->stype = MIME_STYPE_PLAIN;
}
/*
* Yes, this is supposed to capture multiple boundary strings,
* which are illegal and which could be used to hide content in
* an implementation dependent manner. The code below allows us
* to find embedded message headers as long as the sender uses
* only one of these same-level boundary strings.
*
* Yes, this is supposed to ignore the boundary value type.
*/
while ((tok_count = PARSE_CONTENT_TYPE_HEADER(state, &cp)) >= 0) {
if (tok_count < 3 || state->token[1].type != '=')
continue;
if (TOKEN_MATCH(state->token[0], "boundary")) {
if (node->boundary == NULL)
node->boundary = acl_vstring_alloc(256);
/* 需要添加 "--" 做为分隔符的前导符 */
SCP(node->boundary, "--");
SCAT(node->boundary, state->token[2].u.value);
break;
}
}
}
/*
* text/whatever. Right now we don't really care if it is plain or
* not, but we may want to recognize subtypes later, and then this
* code can serve as an example.
*/
else if (TOKEN_MATCH(state->token[0], "text")) {
node->ctype = MIME_CTYPE_TEXT;
if (tok_count >= 3 && state->token[1].type == '/') {
if (TOKEN_MATCH(state->token[2], "plain"))
node->stype = MIME_STYPE_PLAIN;
else if (TOKEN_MATCH(state->token[2], "html"))
node->stype = MIME_STYPE_HTML;
else
node->stype = MIME_STYPE_OTHER;
} else
node->stype = MIME_STYPE_OTHER;
while ((tok_count = PARSE_CONTENT_TYPE_HEADER(state, &cp)) >= 0) {
if (tok_count < 3 || state->token[1].type != '=')
continue;
if (TOKEN_MATCH(state->token[0], "charset")
&& node->charset == NULL)
{
node->charset = acl_mystrdup(state->token[2].u.value);
break;
}
}
/* 如果没有字符集, 则缺省采用 gb2312 */
if (node->charset == NULL)
node->charset = acl_mystrdup("gb2312");
}
else if (TOKEN_MATCH(state->token[0], "image")) {
node->ctype = MIME_CTYPE_IMAGE;
if (tok_count >= 3 && state->token[1].type == '/') {
if (TOKEN_MATCH(state->token[2], "jpeg"))
node->stype = MIME_STYPE_JPEG;
else if (TOKEN_MATCH(state->token[2], "gif"))
node->stype = MIME_STYPE_GIF;
else if (TOKEN_MATCH(state->token[2], "bmp"))
node->stype = MIME_STYPE_BMP;
else if (TOKEN_MATCH(state->token[2], "png"))
node->stype = MIME_STYPE_PNG;
else
node->stype = MIME_STYPE_OTHER;
} else
node->stype = MIME_STYPE_OTHER;
while ((tok_count = PARSE_CONTENT_TYPE_HEADER(state, &cp)) >= 0) {
if (tok_count < 3 || state->token[1].type != '=')
continue;
if (TOKEN_MATCH(state->token[0], "name")
&& node->header_name == NULL)
{
node->header_name = acl_mystrdup(state->token[2].u.value);
break;
}
}
}
else if (TOKEN_MATCH(state->token[0], "application")) {
node->ctype = MIME_CTYPE_APPLICATION;
if (tok_count >= 3 && state->token[1].type == '/') {
if (TOKEN_MATCH(state->token[2], "octet-stream"))
node->stype = MIME_STYPE_OCTET_STREAM;
else
node->stype = MIME_STYPE_OTHER;
}
while ((tok_count = PARSE_CONTENT_TYPE_HEADER(state, &cp)) >= 0) {
if (tok_count < 3 || state->token[1].type != '=')
continue;
if (TOKEN_MATCH(state->token[0], "name")
&& node->header_name == NULL)
{
node->header_name = acl_mystrdup(state->token[2].u.value);
break;
}
}
}
}
static void mime_state_content_type(MIME_STATE *state,
HEADER_OPTS *header_info)
{
const char *cp;
int tok_count;
int def_ctype;
int def_stype;
#define TOKEN_MATCH(tok, text) \
((tok).type == HEADER_TOK_TOKEN && strcasecmp((tok).u.value, (text)) == 0)
#define RFC2045_TSPECIALS "()<>@,;:\\\"/[]?="
#define PARSE_CONTENT_TYPE_HEADER(state, ptr) \
header_token(state->token, MIME_MAX_TOKEN, \
state->token_buffer, ptr, RFC2045_TSPECIALS, ';')
cp = STR(state->output_buffer) + strlen(header_info->name) + 1;
if ((tok_count = PARSE_CONTENT_TYPE_HEADER(state, &cp)) > 0) {
/*
* text/whatever. Right now we don't really care if it is plain or
* not, but we may want to recognize subtypes later, and then this
* code can serve as an example.
*/
if (TOKEN_MATCH(state->token[0], "text")) {
state->curr_ctype = MIME_CTYPE_TEXT;
if (tok_count >= 3
&& state->token[1].type == '/'
&& TOKEN_MATCH(state->token[2], "plain"))
state->curr_stype = MIME_STYPE_PLAIN;
else
state->curr_stype = MIME_STYPE_OTHER;
return;
}
/*
* message/whatever body parts start with another block of message
* headers that we may want to look at. The partial and external-body
* subtypes cannot be subjected to 8-bit -> 7-bit conversion, so we
* must properly recognize them.
*/
if (TOKEN_MATCH(state->token[0], "message")) {
state->curr_ctype = MIME_CTYPE_MESSAGE;
state->curr_stype = MIME_STYPE_OTHER;
if (tok_count >= 3
&& state->token[1].type == '/') {
if (TOKEN_MATCH(state->token[2], "rfc822"))
state->curr_stype = MIME_STYPE_RFC822;
else if (TOKEN_MATCH(state->token[2], "partial"))
state->curr_stype = MIME_STYPE_PARTIAL;
else if (TOKEN_MATCH(state->token[2], "external-body"))
state->curr_stype = MIME_STYPE_EXTERN_BODY;
}
return;
}
/*
* multipart/digest has default content type message/rfc822,
* multipart/whatever has default content type text/plain.
*/
if (TOKEN_MATCH(state->token[0], "multipart")) {
state->curr_ctype = MIME_CTYPE_MULTIPART;
if (tok_count >= 3
&& state->token[1].type == '/'
&& TOKEN_MATCH(state->token[2], "digest")) {
def_ctype = MIME_CTYPE_MESSAGE;
def_stype = MIME_STYPE_RFC822;
} else {
def_ctype = MIME_CTYPE_TEXT;
def_stype = MIME_STYPE_PLAIN;
}
/*
* Yes, this is supposed to capture multiple boundary strings,
* which are illegal and which could be used to hide content in
* an implementation dependent manner. The code below allows us
* to find embedded message headers as long as the sender uses
* only one of these same-level boundary strings.
*
* Yes, this is supposed to ignore the boundary value type.
*/
while ((tok_count = PARSE_CONTENT_TYPE_HEADER(state, &cp)) >= 0) {
if (tok_count >= 3
&& TOKEN_MATCH(state->token[0], "boundary")
&& state->token[1].type == '=') {
if (state->nesting_level > var_mime_maxdepth) {
if (state->static_flags & MIME_OPT_REPORT_NESTING)
REPORT_ERROR(state, MIME_ERR_NESTING,
STR(state->output_buffer));
} else {
mime_state_push(state, def_ctype, def_stype,
state->token[2].u.value);
}
}
}
}
return;
}
/*
* other/whatever.
*/
else {
state->curr_ctype = MIME_CTYPE_OTHER;
return;
}
}
