diff options
| author | Vsevolod Stakhov <vsevolod@rambler-co.ru> | 2009-03-23 14:10:07 +0300 |
|---|---|---|
| committer | Vsevolod Stakhov <vsevolod@rambler-co.ru> | 2009-03-23 14:10:07 +0300 |
| commit | c79b5ccd22cbc1c273479f4f88189a18effda533 (patch) | |
| tree | 1741743779a70146a61cd1767936aa43d671e36b /src/message.c | |
| parent | afdaddc4d0745a5bcefad73dd74fd4c03ae3de15 (diff) | |
| download | rspamd-c79b5ccd22cbc1c273479f4f88189a18effda533.tar.gz rspamd-c79b5ccd22cbc1c273479f4f88189a18effda533.zip | |
* Fix error in expression parser that causes bad errors with expressions that have regexp at the end
* Improve test for fuzzy hashes
* Add new object - TextPart to perl XS library that allows access to stripped parts and fuzzy hashes
* Add documentation for expressions parser and fot Mail::Rspamd::TextPart
* Allways calculate fuzzy hash for text parts
* Store text parts separately from other parts
* Add compare_parts_distance for expressions that calculates difference in 2 parts messages
* Do not try to substitute variables in empty strings
Diffstat (limited to 'src/message.c')
| -rw-r--r-- | src/message.c | 19 |
1 files changed, 17 insertions, 2 deletions
diff --git a/src/message.c b/src/message.c index 76743f7de..807463a82 100644 --- a/src/message.c +++ b/src/message.c @@ -242,6 +242,7 @@ mime_foreach_callback (GMimeObject *part, gpointer user_data) { struct worker_task *task = (struct worker_task *)user_data; struct mime_part *mime_part; + struct mime_text_part *text_part; GMimeContentType *type; GMimeDataWrapper *wrapper; GMimeStream *part_stream; @@ -302,13 +303,27 @@ mime_foreach_callback (GMimeObject *part, gpointer user_data) mime_part->content = part_content; msg_debug ("mime_foreach_callback: found part with content-type: %s/%s", type->type, type->subtype); task->parts = g_list_prepend (task->parts, mime_part); - if (g_mime_content_type_is_type (type, "text", "html")) { + /* Now do special processing for text parts of message */ + if (g_mime_content_type_is_type (type, "text", "html") || g_mime_content_type_is_type (type, "text", "xhtml")) { msg_debug ("mime_foreach_callback: got urls from text/html part"); url_parse_html (task, part_content); + + text_part = memory_pool_alloc (task->task_pool, sizeof (struct mime_text_part)); + text_part->content = strip_html_tags (part_content, NULL); + text_part->is_html = TRUE; + text_part->fuzzy = fuzzy_init_byte_array (text_part->content, task->task_pool); + memory_pool_add_destructor (task->task_pool, (pool_destruct_func)free_byte_array_callback, text_part->content); + task->text_parts = g_list_prepend (task->text_parts, text_part); } else if (g_mime_content_type_is_type (type, "text", "plain")) { - url_parse_text (task, part_content); msg_debug ("mime_foreach_callback: got urls from text/plain part"); + url_parse_text (task, part_content); + + text_part = memory_pool_alloc (task->task_pool, sizeof (struct mime_text_part)); + text_part->content = part_content; + text_part->is_html = FALSE; + text_part->fuzzy = fuzzy_init_byte_array (text_part->content, task->task_pool); + task->text_parts = g_list_prepend (task->text_parts, text_part); } } else { |