More file analysis updates.

- Recorrected the module name to Files.

  - Added Files::analyzer_name to get a more readable name for a
    file analyzer.

  - Improved and just overall better handled multipart mime
    transfers in HTTP and SMTP.  HTTP now has orig_fuids and resp_fuids
    log fields since multiple "files" can be transferred with
    multipart mime in a single request/response pair.  SMTP has
    an fuids field which has file unique IDs for all parts
    transferred. FTP and IRC have a log field named fuid added
    because only a single file can be transferred per irc and ftp
    log line.
This commit is contained in:
Seth Hall 2013-07-09 11:50:54 -04:00
parent 58d133e764
commit cdf6b7864e
18 changed files with 257 additions and 120 deletions

View file

@ -61,7 +61,7 @@ export {
depth: count &default=0 &log;
## A set of analysis types done during the file analysis.
analyzers: set[Analyzer] &log;
analyzers: set[string] &log;
## A mime type provided by libmagic against the *bof_buffer*, or
## in the cases where no buffering of the beginning of file occurs,
@ -76,11 +76,16 @@ export {
## The duration the file was analyzed for.
duration: interval &log &default=0secs;
## If the source of this file is is a network connection, this field
## If the source of this file is a network connection, this field
## indicates if the data originated from the local network or not as
## determined by the configured bro:see:`Site::local_nets`.
local_orig: bool &log &optional;
## If the source of this file is a network connection, this field
## indicates if the file is being sent by the originator of the connection
## or the responder.
is_orig: bool &log &optional;
## Number of bytes provided to the file analysis engine for the file.
seen_bytes: count &log &default=0;
@ -105,7 +110,7 @@ export {
## A table that can be used to disable file analysis completely for
## any files transferred over given network protocol analyzers.
const disable: table[Analyzer::Tag] of bool = table() &redef;
const disable: table[Files::Tag] of bool = table() &redef;
## The salt concatenated to unique file handle strings generated by
## :bro:see:`get_file_handle` before hashing them in to a file id
@ -139,7 +144,7 @@ export {
## for the *id* isn't currently active or the *args*
## were invalid for the analyzer type.
global add_analyzer: function(f: fa_file,
tag: Files::Analyzer,
tag: Files::Tag,
args: AnalyzerArgs &default=AnalyzerArgs()): bool;
## Removes an analyzer from the analysis of a given file.
@ -150,7 +155,7 @@ export {
##
## Returns: true if the analyzer will be removed, or false if analysis
## for the *id* isn't currently active.
global remove_analyzer: function(f: fa_file, tag: Files::Analyzer, args: AnalyzerArgs): bool;
global remove_analyzer: function(f: fa_file, tag: Files::Tag, args: AnalyzerArgs): bool;
## Stops/ignores any further analysis of a given file.
##
@ -161,6 +166,13 @@ export {
## isn't currently active.
global stop: function(f: fa_file): bool;
## Translates an file analyzer enum value to a string with the analyzer's name.
##
## tag: The analyzer tag.
##
## Returns: The analyzer name corresponding to the tag.
global analyzer_name: function(tag: Files::Tag): string;
## Register callbacks for protocols that work with the Files framework.
## The callbacks must uniquely identify a file and each protocol can
## only have a single callback registered for it.
@ -171,7 +183,7 @@ export {
## defined previously.
##
## Returns: true if the protocol being registered was not previously registered.
global register_protocol: function(tag: AnalyzerTag, callback: function(c: connection, is_orig: bool): string): bool;
global register_protocol: function(tag: Files::Tag, callback: function(c: connection, is_orig: bool): string): bool;
## Register a callback for file analyzers to use if they need to do some manipulation
## when they are being added to a file before the core code takes over. This is
@ -181,7 +193,7 @@ export {
## tag: Tag for the file analyzer.
##
## callback: Function to execute when the given file analyzer is being added.
global register_analyzer_add_callback: function(tag: Files::Analyzer, callback: function(f: fa_file, args: AnalyzerArgs));
global register_analyzer_add_callback: function(tag: Files::Tag, callback: function(f: fa_file, args: AnalyzerArgs));
## Event that can be handled to access the Info record as it is sent on
## to the logging framework.
@ -194,14 +206,14 @@ redef record fa_file += {
redef record AnalyzerArgs += {
# This is used interally for the core file analyzer api.
tag: Files::Analyzer &optional;
tag: Files::Tag &optional;
};
# Store the callbacks for protocol analyzers that have files.
global registered_protocols: table[AnalyzerTag] of function(c: connection, is_orig: bool): string = table()
global registered_protocols: table[Files::Tag] of function(c: connection, is_orig: bool): string = table()
&default=function(c: connection, is_orig: bool): string { return cat(c$uid, is_orig); };
global analyzer_add_callbacks: table[Files::Analyzer] of function(f: fa_file, args: AnalyzerArgs) = table();
global analyzer_add_callbacks: table[Files::Tag] of function(f: fa_file, args: AnalyzerArgs) = table();
event bro_init() &priority=5
{
@ -227,6 +239,8 @@ function set_info(f: fa_file)
f$info$total_bytes = f$total_bytes;
f$info$missing_bytes = f$missing_bytes;
f$info$overflow_bytes = f$overflow_bytes;
if ( f?$is_orig )
f$info$is_orig = f$is_orig;
if ( f?$mime_type )
f$info$mime_type = f$mime_type;
}
@ -236,11 +250,11 @@ function set_timeout_interval(f: fa_file, t: interval): bool
return __set_timeout_interval(f$id, t);
}
function add_analyzer(f: fa_file, tag: Analyzer, args: AnalyzerArgs): bool
function add_analyzer(f: fa_file, tag: Files::Tag, args: AnalyzerArgs): bool
{
# This is to construct the correct args for the core API.
args$tag = tag;
add f$info$analyzers[tag];
add f$info$analyzers[Files::analyzer_name(tag)];
if ( tag in analyzer_add_callbacks )
analyzer_add_callbacks[tag](f, args);
@ -253,12 +267,12 @@ function add_analyzer(f: fa_file, tag: Analyzer, args: AnalyzerArgs): bool
return T;
}
function register_analyzer_add_callback(tag: Files::Analyzer, callback: function(f: fa_file, args: AnalyzerArgs))
function register_analyzer_add_callback(tag: Files::Tag, callback: function(f: fa_file, args: AnalyzerArgs))
{
analyzer_add_callbacks[tag] = callback;
}
function remove_analyzer(f: fa_file, tag: Files::Analyzer, args: AnalyzerArgs): bool
function remove_analyzer(f: fa_file, tag: Files::Tag, args: AnalyzerArgs): bool
{
args$tag = tag;
return __remove_analyzer(f$id, args);
@ -269,6 +283,11 @@ function stop(f: fa_file): bool
return __stop(f$id);
}
function analyzer_name(tag: Files::Tag): string
{
return __analyzer_name(tag);
}
event file_new(f: fa_file) &priority=10
{
set_info(f);
@ -302,14 +321,14 @@ event file_state_remove(f: fa_file) &priority=-10
Log::write(Files::LOG, f$info);
}
function register_protocol(tag: AnalyzerTag, callback: function(c: connection, is_orig: bool): string): bool
function register_protocol(tag: Files::Tag, callback: function(c: connection, is_orig: bool): string): bool
{
local result = (tag !in registered_protocols);
registered_protocols[tag] = callback;
return result;
}
event get_file_handle(tag: AnalyzerTag, c: connection, is_orig: bool) &priority=5
event get_file_handle(tag: Files::Tag, c: connection, is_orig: bool) &priority=5
{
local handler = registered_protocols[tag];
set_file_handle(handler(c, is_orig));