Merge remote-tracking branch 'origin/topic/jsiwek/faf-updates'

Nice solution with the ComponentManager/TaggedComponent!

BIT-1049 #Merged Merged into master.

* origin/topic/jsiwek/faf-updates:
  Fix some build errors.
  Minor fix to file/protocol analyzer plugin reference doc.
  Internal refactoring of how plugin components are tagged/managed.
  Factor out the need for a tag field in Files::AnalyzerArgs record.
  Add a distinct tag class for file analyzers.
  Fix various documentation, mostly related to file analysis.

doc/file-analysis.rst

@@ -82,9 +82,9 @@ attached, they start receiving the contents of the file as Bro extracts
 it from an ongoing network connection.  What they do with the file
 contents is up to the particular file analyzer implementation, but
 they'll typically either report further information about the file via
-events (e.g. :bro:see:`FileAnalysis::ANALYZER_MD5` will report the
+events (e.g. :bro:see:`Files::ANALYZER_MD5` will report the
 file's MD5 checksum via :bro:see:`file_hash` once calculated) or they'll
-have some side effect (e.g. :bro:see:`FileAnalysis::ANALYZER_EXTRACT`
+have some side effect (e.g. :bro:see:`Files::ANALYZER_EXTRACT`
 will write the contents of the file out to the local file system).
 
 In the future there may be file analyzers that automatically attach to
@@ -98,7 +98,7 @@ explicit attachment decision:
         {
         print "new file", f$id;
         if ( f?$mime_type && f$mime_type == "text/plain" )
-            FileAnalysis::add_analyzer(f, [$tag=FileAnalysis::ANALYZER_MD5]);
+            Files::add_analyzer(f, Files::ANALYZER_MD5);
         }
 
     event file_hash(f: fa_file, kind: string, hash: string)
@@ -113,26 +113,27 @@ output::
     file_hash, Cx92a0ym5R8, md5, 397168fd09991a0e712254df7bc639ac
 
 Some file analyzers might have tunable parameters that need to be
-specified in the call to :bro:see:`FileAnalysis::add_analyzer`:
+specified in the call to :bro:see:`Files::add_analyzer`:
 
 .. code:: bro
 
     event file_new(f: fa_file)
         {
-        FileAnalysis::add_analyzer(f, [$tag=FileAnalysis::ANALYZER_EXTRACT,
+        Files::add_analyzer(f, Files::ANALYZER_EXTRACT,
-                                       $extract_filename="./myfile"]);
+                            [$extract_filename="myfile"]);
         }
 
 In this case, the file extraction analyzer doesn't generate any further
-events, but does have the side effect of writing out the file contents
+events, but does have the effect of writing out the file contents to the
-to the local file system at the specified location of ``./myfile``.  Of
+local file system at the location resulting from the concatenation of
-course, for a network with more than a single file being transferred,
+the path specified by :bro:see:`FileExtract::prefix` and the string,
-it's probably preferable to specify a different extraction path for each
+``myfile``.  Of course, for a network with more than a single file being
-file, unlike this example.
+transferred, it's probably preferable to specify a different extraction
+path for each file, unlike this example.
 
 Regardless of which file analyzers end up acting on a file, general
 information about the file (e.g. size, time of last data transferred,
-MIME type, etc.) are logged in ``file_analysis.log``.
+MIME type, etc.) are logged in ``files.log``.
 
 Input Framework Integration
 ===========================
@@ -150,7 +151,7 @@ a network interface it's monitoring.  It only requires a call to
     event file_new(f: fa_file)
         {
         print "new file", f$id;
-        FileAnalysis::add_analyzer(f, [$tag=FileAnalysis::ANALYZER_MD5]);
+        Files::add_analyzer(f, Files::ANALYZER_MD5);
         }
 
     event file_state_remove(f: fa_file)

doc/index.rst

@@ -47,6 +47,7 @@ Script Reference
    scripts/index
    scripts/builtins
    scripts/proto-analyzers
+   scripts/file-analyzers
 
 Other Bro Components
 --------------------

doc/scripts/CMakeLists.txt

@@ -124,28 +124,34 @@ endmacro(REST_TARGET)
 # Schedule Bro scripts for which to generate documentation.
 include(DocSourcesList.cmake)
 
-# This reST target is independent of a particular Bro script...
+# Macro for generating reST docs that are independent of any particular Bro
-add_custom_command(OUTPUT proto-analyzers.rst
+# script.
-    # delete any leftover state from previous bro runs
+macro(INDEPENDENT_REST_TARGET reST_file)
-    COMMAND "${CMAKE_COMMAND}"
+    add_custom_command(OUTPUT ${reST_file}
-    ARGS -E remove_directory .state
+        # delete any leftover state from previous bro runs
-    # generate the reST documentation using bro
+        COMMAND "${CMAKE_COMMAND}"
-    COMMAND BROPATH=${BROPATH}:${srcDir} BROMAGIC=${CMAKE_SOURCE_DIR}/magic/database ${CMAKE_BINARY_DIR}/src/bro
+        ARGS -E remove_directory .state
-    ARGS -b -Z base/init-bare.bro || (rm -rf .state *.log *.rst && exit 1)
+        # generate the reST documentation using bro
-    # move generated doc into a new directory tree that
+        COMMAND BROPATH=${BROPATH}:${srcDir} BROMAGIC=${CMAKE_SOURCE_DIR}/magic/database ${CMAKE_BINARY_DIR}/src/bro
-    # defines the final structure of documents
+        ARGS -b -Z base/init-bare.bro || (rm -rf .state *.log *.rst && exit 1)
-    COMMAND "${CMAKE_COMMAND}"
+        # move generated doc into a new directory tree that
-    ARGS -E make_directory ${dstDir}
+        # defines the final structure of documents
-    COMMAND "${CMAKE_COMMAND}"
+        COMMAND "${CMAKE_COMMAND}"
-    ARGS -E copy proto-analyzers.rst ${dstDir}
+        ARGS -E make_directory ${dstDir}
-    # clean up the build directory
+        COMMAND "${CMAKE_COMMAND}"
-    COMMAND rm
+        ARGS -E copy ${reST_file} ${dstDir}
-    ARGS -rf .state *.log *.rst
+        # clean up the build directory
-    DEPENDS bro
+        COMMAND rm
-    WORKING_DIRECTORY ${CMAKE_BINARY_DIR}
+        ARGS -rf .state *.log *.rst
-    COMMENT "[Bro] Generating reST docs for proto-analyzers.rst"
+        DEPENDS bro
-)
+        WORKING_DIRECTORY ${CMAKE_BINARY_DIR}
-list(APPEND ALL_REST_OUTPUTS proto-analyzers.rst)
+        COMMENT "[Bro] Generating reST docs for ${reST_file}"
+    )
+    list(APPEND ALL_REST_OUTPUTS ${reST_file})
+endmacro(INDEPENDENT_REST_TARGET)
+
+independent_rest_target(proto-analyzers.rst)
+independent_rest_target(file-analyzers.rst)
 
 # create temporary list of all docs to include in the master policy/index file
 file(WRITE ${MASTER_POLICY_INDEX} "${MASTER_POLICY_INDEX_TEXT}")

doc/scripts/DocSourcesList.cmake

@@ -141,6 +141,7 @@ rest_target(${psd} base/protocols/dns/consts.bro)
 rest_target(${psd} base/protocols/dns/main.bro)
 rest_target(${psd} base/protocols/ftp/files.bro)
 rest_target(${psd} base/protocols/ftp/gridftp.bro)
+rest_target(${psd} base/protocols/ftp/info.bro)
 rest_target(${psd} base/protocols/ftp/main.bro)
 rest_target(${psd} base/protocols/ftp/utils-commands.bro)
 rest_target(${psd} base/protocols/ftp/utils.bro)

scripts/base/frameworks/files/main.bro

@@ -204,7 +204,7 @@ export {
 	## 
 	## tag: Tag for the protocol analyzer having a callback being registered.
 	##
-	## reg: A :bro:see:`ProtoRegistration` record.
+	## reg: A :bro:see:`Files::ProtoRegistration` record.
 	##
 	## Returns: true if the protocol being registered was not previously registered.
 	global register_protocol: function(tag: Analyzer::Tag, reg: ProtoRegistration): bool;
@@ -228,11 +228,6 @@ redef record fa_file += {
 	info: Info &optional;
 };
 
-redef record AnalyzerArgs += {
-	# This is used interally for the core file analyzer api.
-	tag: Files::Tag &optional;
-};
-
 # Store the callbacks for protocol analyzers that have files.
 global registered_protocols: table[Analyzer::Tag] of ProtoRegistration = table();
 
@@ -275,14 +270,12 @@ function set_timeout_interval(f: fa_file, t: interval): 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[Files::analyzer_name(tag)];
 
 	if ( tag in analyzer_add_callbacks )
 		analyzer_add_callbacks[tag](f, args);
 
-	if ( ! __add_analyzer(f$id, args) )
+	if ( ! __add_analyzer(f$id, tag, args) )
 		{
 		Reporter::warning(fmt("Analyzer %s not added successfully to file %s.", tag, f$id));
 		return F;
@@ -297,8 +290,7 @@ function register_analyzer_add_callback(tag: Files::Tag, callback: function(f: f
 
 function remove_analyzer(f: fa_file, tag: Files::Tag, args: AnalyzerArgs): bool
 	{
-	args$tag = tag;
+	return __remove_analyzer(f$id, tag, args);
-	return __remove_analyzer(f$id, args);
 	}
 
 function stop(f: fa_file): bool

scripts/base/frameworks/packet-filter/main.bro

@@ -109,7 +109,7 @@ export {
 
 	## Enables the old filtering approach of "only watch common ports for
 	## analyzed protocols".
-        ##
+	##
 	## Unless you know what you are doing, leave this set to F.
 	const enable_auto_protocol_capture_filters = F &redef;
 

scripts/base/init-bare.bro

@@ -531,22 +531,19 @@ type record_field_table: table[string] of record_field;
 # dependent on the names remaining as they are now.
 
 ## Set of BPF capture filters to use for capturing, indexed by a user-definable
-## ID (which must be unique). If Bro is *not* configured to examine
+## ID (which must be unique). If Bro is *not* configured with
-## :bro:id:`PacketFilter::all_packets`, all packets matching at least
+## :bro:id:`PacketFilter::enable_auto_protocol_capture_filters`,
-## one of the filters in this table (and all in :bro:id:`restrict_filters`)
+## all packets matching at least one of the filters in this table (and all in
-## will be analyzed.
+## :bro:id:`restrict_filters`) will be analyzed.
 ##
-## .. bro:see:: PacketFilter PacketFilter::all_packets
+## .. bro:see:: PacketFilter PacketFilter::enable_auto_protocol_capture_filters
 ##    PacketFilter::unrestricted_filter restrict_filters
 global capture_filters: table[string] of string &redef;
 
 ## Set of BPF filters to restrict capturing, indexed by a user-definable ID (which
-## must be unique). If Bro is *not* configured to examine
+## must be unique).
-## :bro:id:`PacketFilter::all_packets`, only packets matching *all* of the
-## filters in this table (and any in :bro:id:`capture_filters`) will be
-## analyzed.
 ##
-## .. bro:see:: PacketFilter PacketFilter::all_packets
+## .. bro:see:: PacketFilter PacketFilter::enable_auto_protocol_capture_filters
 ##    PacketFilter::unrestricted_filter capture_filters
 global restrict_filters: table[string] of string &redef;
 

scripts/base/protocols/ftp/__load__.bro

@@ -1,4 +1,5 @@
 @load ./utils-commands
+@load ./info
 @load ./main
 @load ./utils
 @load ./files

scripts/base/protocols/ftp/files.bro

@@ -1,3 +1,4 @@
+@load ./info
 @load ./main
 @load ./utils
 @load base/utils/conn-ids

scripts/base/protocols/ftp/gridftp.bro

@@ -19,6 +19,7 @@
 ##! sizes are not logged, but at the benefit of saving CPU cycles that
 ##! otherwise go to analyzing the large (and likely benign) connections.
 
+@load ./info
 @load ./main
 @load base/protocols/conn
 @load base/protocols/ssl

scripts/base/protocols/ftp/info.bro

@@ -0,0 +1,72 @@
+##! Defines data structures for tracking and logging FTP sessions.
+
+module FTP;
+
+@load ./utils-commands
+
+export {
+
+	## This setting changes if passwords used in FTP sessions are
+	## captured or not.
+	const default_capture_password = F &redef;
+
+	## The expected endpoints of an FTP data channel.
+	type ExpectedDataChannel: record {
+		## Whether PASV mode is toggled for control channel.
+		passive: bool &log;
+		## The host that will be initiating the data connection.
+		orig_h: addr &log;
+		## The host that will be accepting the data connection.
+		resp_h: addr &log;
+		## The port at which the acceptor is listening for the data connection.
+		resp_p: port &log;
+	};
+
+	type Info: record {
+		## Time when the command was sent.
+		ts:               time        &log;
+		## Unique ID for the connection.
+		uid:              string      &log;
+		## The connection's 4-tuple of endpoint addresses/ports.
+		id:               conn_id     &log;
+		## User name for the current FTP session.
+		user:             string      &log &default="<unknown>";
+		## Password for the current FTP session if captured.
+		password:         string      &log &optional;
+		## Command given by the client.
+		command:          string      &log &optional;
+		## Argument for the command if one is given.
+		arg:              string      &log &optional;
+
+		## Libmagic "sniffed" file type if the command indicates a file transfer.
+		mime_type:        string      &log &optional;
+		## Size of the file if the command indicates a file transfer.
+		file_size:        count       &log &optional;
+
+		## Reply code from the server in response to the command.
+		reply_code:       count       &log &optional;
+		## Reply message from the server in response to the command.
+		reply_msg:        string      &log &optional;
+
+		## Expected FTP data channel.
+		data_channel:     ExpectedDataChannel &log &optional;
+
+		## Current working directory that this session is in.  By making
+		## the default value '.', we can indicate that unless something
+		## more concrete is discovered that the existing but unknown
+		## directory is ok to use.
+		cwd:                string  &default=".";
+
+		## Command that is currently waiting for a response.
+		cmdarg:             CmdArg  &optional;
+		## Queue for commands that have been sent but not yet responded to
+		## are tracked here.
+		pending_commands:   PendingCmds;
+
+		## Indicates if the session is in active or passive mode.
+		passive:            bool &default=F;
+
+		## Determines if the password will be captured for this request.
+		capture_password:   bool &default=default_capture_password;
+	};
+}

scripts/base/protocols/ftp/main.bro

@@ -3,6 +3,8 @@
 ##! will take on the full path that the client is at along with the requested
 ##! file name.
 
+@load ./info
+@load ./utils
 @load ./utils-commands
 @load base/utils/paths
 @load base/utils/numbers
@@ -20,72 +22,9 @@ export {
 		"EPSV"
 	} &redef;
 
-	## This setting changes if passwords used in FTP sessions are captured or not.
-	const default_capture_password = F &redef;
-
 	## User IDs that can be considered "anonymous".
 	const guest_ids = { "anonymous", "ftp", "ftpuser", "guest" } &redef;
 
-	## The expected endpoints of an FTP data channel.
-	type ExpectedDataChannel: record {
-		## Whether PASV mode is toggled for control channel.
-		passive: bool &log;
-		## The host that will be initiating the data connection.
-		orig_h: addr &log;
-		## The host that will be accepting the data connection.
-		resp_h: addr &log;
-		## The port at which the acceptor is listening for the data connection.
-		resp_p: port &log;
-	};
-
-	type Info: record {
-		## Time when the command was sent.
-		ts:               time        &log;
-		## Unique ID for the connection.
-		uid:              string      &log;
-		## The connection's 4-tuple of endpoint addresses/ports.
-		id:               conn_id     &log;
-		## User name for the current FTP session.
-		user:             string      &log &default="<unknown>";
-		## Password for the current FTP session if captured.
-		password:         string      &log &optional;
-		## Command given by the client.
-		command:          string      &log &optional;
-		## Argument for the command if one is given.
-		arg:              string      &log &optional;
-
-		## Libmagic "sniffed" file type if the command indicates a file transfer.
-		mime_type:        string      &log &optional;
-		## Size of the file if the command indicates a file transfer.
-		file_size:        count       &log &optional;
-
-		## Reply code from the server in response to the command.
-		reply_code:       count       &log &optional;
-		## Reply message from the server in response to the command.
-		reply_msg:        string      &log &optional;
-
-		## Expected FTP data channel.
-		data_channel:     ExpectedDataChannel &log &optional;
-
-		## Current working directory that this session is in.  By making
-		## the default value '.', we can indicate that unless something
-		## more concrete is discovered that the existing but unknown
-		## directory is ok to use.
-		cwd:                string  &default=".";
-
-		## Command that is currently waiting for a response.
-		cmdarg:             CmdArg  &optional;
-		## Queue for commands that have been sent but not yet responded to
-		## are tracked here.
-		pending_commands:   PendingCmds;
-
-		## Indicates if the session is in active or passive mode.
-		passive:            bool &default=F;
-
-		## Determines if the password will be captured for this request.
-		capture_password:   bool &default=default_capture_password;
-	};
-
 	## This record is to hold a parsed FTP reply code.  For example, for the
 	## 201 status code, the digits would be parsed as: x->2, y->0, z=>1.
 	type ReplyCode: record {
@@ -102,8 +41,6 @@ export {
 	global log_ftp: event(rec: Info);
 }
 
-@load ./utils
-
 # Add the state tracking information variable to the connection record
 redef record connection += {
 	ftp: Info &optional;

scripts/base/protocols/ftp/utils.bro

@@ -1,7 +1,8 @@
 ##! Utilities specific for FTP processing.
 
-@load ./main
+@load ./info
 @load base/utils/addrs
+@load base/utils/paths
 
 module FTP;
 

scripts/policy/frameworks/packet-filter/shunt.bro

@@ -34,8 +34,8 @@ export {
 	global current_shunted_host_pairs: function(): set[conn_id];
 
 	redef enum Notice::Type += {
-		## Indicative that :bro:id:`max_bpf_shunts` connections are already
+		## Indicative that :bro:id:`PacketFilter::max_bpf_shunts` connections
-		## being shunted with BPF filters and no more are allowed.
+		## are already being shunted with BPF filters and no more are allowed.
 		No_More_Conn_Shunts_Available,
 
 		## Limitations in BPF make shunting some connections with BPF impossible.

scripts/policy/misc/load-balancing.bro

@@ -12,12 +12,12 @@ export {
 		## Apply BPF filters to each worker in a way that causes them to
 		## automatically flow balance traffic between them.
 		AUTO_BPF,
-		## Load balance traffic across the workers by making each one apply
+		# Load balance traffic across the workers by making each one apply
-		## a restrict filter to only listen to a single MAC address.  This
+		# a restrict filter to only listen to a single MAC address.  This
-		## is a somewhat common deployment option for sites doing network
+		# is a somewhat common deployment option for sites doing network
-		## based load balancing with MAC address rewriting and passing the
+		# based load balancing with MAC address rewriting and passing the
-		## traffic to a single interface.  Multiple MAC addresses will show
+		# traffic to a single interface.  Multiple MAC addresses will show
-		## up on the same interface and need filtered to a single address.
+		# up on the same interface and need filtered to a single address.
 		#MAC_ADDR_BPF,
 	};
 

scripts/policy/tuning/defaults/packet-fragments.bro

@@ -1,10 +1,10 @@
-## Capture TCP fragments, but not UDP (or ICMP), since those are a lot more
+# Capture TCP fragments, but not UDP (or ICMP), since those are a lot more
-## common due to high-volume, fragmenting protocols such as NFS :-(.
+# common due to high-volume, fragmenting protocols such as NFS :-(.
 
-## This normally isn't used because of the default open packet filter 
+# This normally isn't used because of the default open packet filter 
-## but we set it anyway in case the user is using a packet filter.
+# but we set it anyway in case the user is using a packet filter.
-## Note: This was removed because the default model now is to have a wide
+# Note: This was removed because the default model now is to have a wide
-##       open packet filter.
+#       open packet filter.
 #redef capture_filters += { ["frag"] = "(ip[6:2] & 0x3fff != 0) and tcp" };
 
 ## Shorten the fragment timeout from never expiring to expiring fragments after

src/BroDoc.cc

@@ -11,6 +11,7 @@
 #include "plugin/Manager.h"
 #include "analyzer/Manager.h"
 #include "analyzer/Component.h"
+#include "file_analysis/Manager.h"
 
 BroDoc::BroDoc(const std::string& rel, const std::string& abs)
 	{
@@ -479,6 +480,17 @@ static void WriteAnalyzerComponent(FILE* f, const analyzer::Component* c)
 	fprintf(f, ":bro:enum:`Analyzer::%s`\n\n", tag.c_str());
 	}
 
+static void WriteAnalyzerComponent(FILE* f, const file_analysis::Component* c)
+	{
+	EnumType* atag = file_mgr->GetTagEnumType();
+	string tag = fmt("ANALYZER_%s", c->CanonicalName());
+
+	if ( atag->Lookup("Files", tag.c_str()) < 0 )
+		reporter->InternalError("missing analyzer tag for %s", tag.c_str());
+
+	fprintf(f, ":bro:enum:`Files::%s`\n\n", tag.c_str());
+	}
+
 static void WritePluginComponents(FILE* f, const plugin::Plugin* p)
 	{
 	plugin::Plugin::component_list components = p->Components();
@@ -494,6 +506,10 @@ static void WritePluginComponents(FILE* f, const plugin::Plugin* p)
 			WriteAnalyzerComponent(f,
 			        dynamic_cast<const analyzer::Component*>(*it));
 			break;
+		case plugin::component::FILE_ANALYZER:
+			WriteAnalyzerComponent(f,
+			        dynamic_cast<const file_analysis::Component*>(*it));
+			break;
 		case plugin::component::READER:
 			reporter->InternalError("docs for READER component unimplemented");
 		case plugin::component::WRITER:
@@ -537,30 +553,35 @@ static void WritePluginBifItems(FILE* f, const plugin::Plugin* p,
 		}
 	}
 
-static void WriteAnalyzerTagDefn(FILE* f, EnumType* e)
+static void WriteAnalyzerTagDefn(FILE* f, EnumType* e, const string& module)
 	{
+	string tag_id= module + "::Tag";
 	e = new CommentedEnumType(e);
-	e->SetTypeID(copy_string("Analyzer::Tag"));
+	e->SetTypeID(copy_string(tag_id.c_str()));
 
-	ID* dummy_id = new ID(copy_string("Analyzer::Tag"), SCOPE_GLOBAL, true);
+	ID* dummy_id = new ID(copy_string(tag_id.c_str()), SCOPE_GLOBAL, true);
 	dummy_id->SetType(e);
 	dummy_id->MakeType();
 
 	list<string>* r = new list<string>();
-	r->push_back("Unique identifiers for protocol analyzers.");
+	r->push_back("Unique identifiers for analyzers.");
 
 	BroDocObj bdo(dummy_id, r, true);
 
 	bdo.WriteReST(f);
 	}
 
-static bool IsAnalyzerPlugin(const plugin::Plugin* p)
+static bool ComponentsMatch(const plugin::Plugin* p, plugin::component::Type t,
+                            bool match_empty = false)
 	{
 	plugin::Plugin::component_list components = p->Components();
 	plugin::Plugin::component_list::const_iterator it;
 
+	if ( components.empty() )
+		return match_empty;
+
 	for ( it = components.begin(); it != components.end(); ++it )
-		if ( (*it)->Type() != plugin::component::ANALYZER )
+		if ( (*it)->Type() != t )
 			return false;
 
 	return true;
@@ -573,14 +594,44 @@ void CreateProtoAnalyzerDoc(const char* filename)
 	fprintf(f, "Protocol Analyzer Reference\n");
 	fprintf(f, "===========================\n\n");
 
-	WriteAnalyzerTagDefn(f, analyzer_mgr->GetTagEnumType());
+	WriteAnalyzerTagDefn(f, analyzer_mgr->GetTagEnumType(), "Analyzer");
 
 	plugin::Manager::plugin_list plugins = plugin_mgr->Plugins();
 	plugin::Manager::plugin_list::const_iterator it;
 
 	for ( it = plugins.begin(); it != plugins.end(); ++it )
 		{
-		if ( ! IsAnalyzerPlugin(*it) )
+		if ( ! ComponentsMatch(*it, plugin::component::ANALYZER, true) )
+			continue;
+
+		WritePluginSectionHeading(f, *it);
+		WritePluginComponents(f, *it);
+		WritePluginBifItems(f, *it, plugin::BifItem::CONSTANT,
+		                    "Options/Constants");
+		WritePluginBifItems(f, *it, plugin::BifItem::GLOBAL, "Globals");
+		WritePluginBifItems(f, *it, plugin::BifItem::TYPE, "Types");
+		WritePluginBifItems(f, *it, plugin::BifItem::EVENT, "Events");
+		WritePluginBifItems(f, *it, plugin::BifItem::FUNCTION, "Functions");
+		}
+
+	fclose(f);
+	}
+
+void CreateFileAnalyzerDoc(const char* filename)
+	{
+	FILE* f = fopen(filename, "w");
+
+	fprintf(f, "File Analyzer Reference\n");
+	fprintf(f, "=======================\n\n");
+
+	WriteAnalyzerTagDefn(f, file_mgr->GetTagEnumType(), "Files");
+
+	plugin::Manager::plugin_list plugins = plugin_mgr->Plugins();
+	plugin::Manager::plugin_list::const_iterator it;
+
+	for ( it = plugins.begin(); it != plugins.end(); ++it )
+		{
+		if ( ! ComponentsMatch(*it, plugin::component::FILE_ANALYZER) )
 			continue;
 
 		WritePluginSectionHeading(f, *it);

src/BroDoc.h

@@ -413,4 +413,10 @@ private:
  */
 void CreateProtoAnalyzerDoc(const char* filename);
 
+/**
+ * Writes out plugin index documentation for all file analyzer plugins.
+ * @param filename the name of the file to write.
+ */
+void CreateFileAnalyzerDoc(const char* filename);
+
 #endif

src/CMakeLists.txt

@@ -319,6 +319,7 @@ set(bro_SRCS
     StateAccess.cc
     Stats.cc
     Stmt.cc
+    Tag.cc
     Timer.cc
     Traverse.cc
     Trigger.cc
@@ -362,6 +363,8 @@ set(bro_SRCS
     3rdparty/sqlite3.c
 
     plugin/Component.cc
+    plugin/ComponentManager.h
+    plugin/TaggedComponent.h
     plugin/Manager.cc
     plugin/Plugin.cc
     plugin/Macros.h

src/DebugLogger.cc

@@ -16,7 +16,8 @@ DebugLogger::Stream DebugLogger::streams[NUM_DBGS] = {
 	{ "notifiers", 0, false },  { "main-loop", 0, false },
 	{ "dpd", 0, false }, { "tm", 0, false },
 	{ "logging", 0, false }, {"input", 0, false }, 
-	{ "threading", 0, false }, { "file_analysis", 0, false }
+	{ "threading", 0, false }, { "file_analysis", 0, false },
+	{ "plugins", 0, false}
 };
 
 DebugLogger::DebugLogger(const char* filename)

src/DebugLogger.h

@@ -27,6 +27,7 @@ enum DebugStream {
 	DBG_INPUT,	// Input streams
 	DBG_THREADING,	// Threading system
 	DBG_FILE_ANALYSIS,	// File analysis
+	DBG_PLUGINS,
 
 	NUM_DBGS // Has to be last
 };

src/RuleAction.cc

@@ -40,7 +40,7 @@ RuleActionAnalyzer::RuleActionAnalyzer(const char* arg_analyzer)
 	string str(arg_analyzer);
 	string::size_type pos = str.find(':');
 	string arg = str.substr(0, pos);
-	analyzer = analyzer_mgr->GetAnalyzerTag(arg.c_str());
+	analyzer = analyzer_mgr->GetComponentTag(arg.c_str());
 
 	if ( ! analyzer )
 		reporter->Warning("unknown analyzer '%s' specified in rule", arg.c_str());
@@ -48,7 +48,7 @@ RuleActionAnalyzer::RuleActionAnalyzer(const char* arg_analyzer)
 	if ( pos != string::npos )
 		{
 		arg = str.substr(pos + 1);
-		child_analyzer = analyzer_mgr->GetAnalyzerTag(arg.c_str());
+		child_analyzer = analyzer_mgr->GetComponentTag(arg.c_str());
 
 		if ( ! child_analyzer )
 			reporter->Warning("unknown analyzer '%s' specified in rule", arg.c_str());
@@ -60,11 +60,11 @@ RuleActionAnalyzer::RuleActionAnalyzer(const char* arg_analyzer)
 void RuleActionAnalyzer::PrintDebug()
 	{
 	if ( ! child_analyzer )
-		fprintf(stderr, "|%s|\n", analyzer_mgr->GetAnalyzerName(analyzer));
+		fprintf(stderr, "|%s|\n", analyzer_mgr->GetComponentName(analyzer));
 	else
 		fprintf(stderr, "|%s:%s|\n",
-			analyzer_mgr->GetAnalyzerName(analyzer),
+			analyzer_mgr->GetComponentName(analyzer),
-			analyzer_mgr->GetAnalyzerName(child_analyzer));
+			analyzer_mgr->GetComponentName(child_analyzer));
 	}
 
 

src/Tag.cc

@@ -0,0 +1,82 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
+#include "Tag.h"
+#include "Val.h"
+
+Tag::Tag(EnumType* etype, type_t arg_type, subtype_t arg_subtype)
+	{
+	assert(arg_type > 0);
+
+	type = arg_type;
+	subtype = arg_subtype;
+	int64_t i = (int64)(type) | ((int64)subtype << 31);
+	Ref(etype);
+	val = new EnumVal(i, etype);
+	}
+
+Tag::Tag(EnumVal* arg_val)
+	{
+	assert(arg_val);
+
+	val = arg_val;
+	Ref(val);
+
+	int64 i = val->InternalInt();
+	type = i & 0xffffffff;
+	subtype = (i >> 31) & 0xffffffff;
+	}
+
+Tag::Tag(const Tag& other)
+	{
+	type = other.type;
+	subtype = other.subtype;
+	val = other.val;
+
+	if ( val )
+		Ref(val);
+	}
+
+Tag::Tag()
+	{
+	type = 0;
+	subtype = 0;
+	val = 0;
+	}
+
+Tag::~Tag()
+	{
+	Unref(val);
+	val = 0;
+	}
+
+Tag& Tag::operator=(const Tag& other)
+	{
+	if ( this != &other )
+		{
+		type = other.type;
+		subtype = other.subtype;
+		val = other.val;
+
+		if ( val )
+			Ref(val);
+		}
+
+	return *this;
+	}
+
+EnumVal* Tag::AsEnumVal(EnumType* etype) const
+	{
+	if ( ! val )
+		{
+		assert(type == 0 && subtype == 0);
+		Ref(etype);
+		val = new EnumVal(0, etype);
+		}
+
+	return val;
+	}
+
+std::string Tag::AsString() const
+	{
+	return fmt("%" PRIu32 "/%" PRIu32, type, subtype);
+	}

src/Tag.h

@@ -0,0 +1,138 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
+#ifndef TAG_H
+#define TAG_H
+
+#include "config.h"
+#include "util.h"
+#include "Type.h"
+
+class EnumVal;
+
+/**
+ * Class to identify an analyzer type.
+ *
+ * Each analyzer type gets a tag consisting of a main type and subtype. The
+ * former is an identifier that's unique across all analyzer classes. The latter is
+ * passed through to the analyzer instances for their use, yet not further
+ * interpreted by the analyzer infrastructure; it allows an analyzer to
+ * branch out into a set of sub-analyzers internally. Jointly, main type and
+ * subtype form an analyzer "tag". Each unique tag corresponds to a single
+ * "analyzer" from the user's perspective. At the script layer, these tags
+ * are mapped into enums of type \c Analyzer::Tag or Files::Tag. Internally,
+ * the analyzer::Manager and file_analysis::Manager maintain the mapping of tag
+ * to analyzer (and it also assigns them their main types), and
+ * analyzer::Component and file_analysis::Component create new tag.
+ *
+ * The Tag class supports all operations necessary to act as an index in a
+ * \c std::map.
+ */
+class Tag  {
+public:
+	/**
+	 * Type for the analyzer's main type.
+	 */
+	typedef uint32 type_t;
+
+	/**
+	 * Type for the analyzer's subtype.
+	 */
+	typedef uint32 subtype_t;
+
+	/**
+	 * Returns the tag's main type.
+	 */
+	type_t Type() const 	{ return type; }
+
+	/**
+	 * Returns the tag's subtype.
+	 */
+	subtype_t Subtype() const 	{ return subtype; }
+
+	/**
+	 * Returns the numerical values for main and subtype inside a string
+	 * suitable for printing. This is primarily for debugging.
+	 */
+	std::string AsString() const;
+
+protected:
+	/*
+	 * Copy constructor.
+	 */
+	Tag(const Tag& other);
+
+	/**
+	 * Default constructor. This initializes the tag with an error value
+	 * that will make \c operator \c bool return false.
+	 */
+	Tag();
+
+	/**
+	 * Destructor.
+	 */
+	~Tag();
+
+	/**
+	 * Assignment operator.
+	 */
+	Tag& operator=(const Tag& other);
+
+	/**
+	 * Compares two tags for equality.
+	 */
+	bool operator==(const Tag& other) const
+		{
+		return type == other.type && subtype == other.subtype;
+		}
+
+	/**
+	 * Compares two tags for inequality.
+	 */
+	bool operator!=(const Tag& other) const
+		{
+		return type != other.type || subtype != other.subtype;
+		}
+
+	/**
+	 * Compares two tags for less-than relationship.
+	 */
+	bool operator<(const Tag& other) const
+		{
+		return type != other.type ? type < other.type : (subtype < other.subtype);
+		}
+
+	/**
+	 * Returns the script-layer enum that corresponds to this tag.
+	 * The returned value does not have its ref-count increased.
+	 *
+	 * @param etype the script-layer enum type associated with the tag.
+	 */
+	EnumVal* AsEnumVal(EnumType* etype) const;
+
+	/**
+	 * Constructor.
+	 *
+	 * @param etype the script-layer enum type associated with the tag.
+	 *
+	 * @param type The main type. Note that the manager class manages the
+	 * the value space internally, so noone else should assign main types.
+	 *
+	 * @param subtype The sub type, which is left to an analyzer for
+	 * interpretation. By default it's set to zero.
+	 */
+	Tag(EnumType* etype, type_t type, subtype_t subtype = 0);
+
+	/**
+	 * Constructor.
+	 *
+	 * @param val An enum value of script type \c Analyzer::Tag.
+	 */
+	Tag(EnumVal* val);
+
+private:
+	type_t type;            // Main type.
+	subtype_t subtype;      // Subtype.
+	mutable EnumVal* val;   // Script-layer value.
+};
+
+#endif

src/analyzer/Analyzer.cc

@@ -70,12 +70,12 @@ void AnalyzerTimer::Init(Analyzer* arg_analyzer, analyzer_timer_func arg_timer,
 	Ref(analyzer->Conn());
 	}
 
-analyzer::ID Analyzer::id_counter = 0;;
+analyzer::ID Analyzer::id_counter = 0;
 
 const char* Analyzer::GetAnalyzerName() const
 	{
 	assert(tag);
-	return analyzer_mgr->GetAnalyzerName(tag);
+	return analyzer_mgr->GetComponentName(tag);
 	}
 
 void Analyzer::SetAnalyzerTag(const Tag& arg_tag)
@@ -87,7 +87,7 @@ void Analyzer::SetAnalyzerTag(const Tag& arg_tag)
 bool Analyzer::IsAnalyzer(const char* name)
 	{
 	assert(tag);
-	return strcmp(analyzer_mgr->GetAnalyzerName(tag), name) == 0;
+	return strcmp(analyzer_mgr->GetComponentName(tag), name) == 0;
 	}
 
 // Used in debugging output.
@@ -98,7 +98,7 @@ static string fmt_analyzer(Analyzer* a)
 
 Analyzer::Analyzer(const char* name, Connection* conn)
 	{
-	Tag tag = analyzer_mgr->GetAnalyzerTag(name);
+	Tag tag = analyzer_mgr->GetComponentTag(name);
 
 	if ( ! tag )
 		reporter->InternalError("unknown analyzer name %s; mismatch with tag analyzer::Component?", name);
@@ -494,7 +494,7 @@ Analyzer* Analyzer::FindChild(Tag arg_tag)
 
 Analyzer* Analyzer::FindChild(const char* name)
 	{
-	Tag tag = analyzer_mgr->GetAnalyzerTag(name);
+	Tag tag = analyzer_mgr->GetComponentTag(name);
 	return tag ? FindChild(tag) : 0;
 	}
 

src/analyzer/Component.cc

@@ -8,29 +8,26 @@
 
 using namespace analyzer;
 
-Tag::type_t Component::type_counter = 0;
-
 Component::Component(const char* arg_name, factory_callback arg_factory, Tag::subtype_t arg_subtype, bool arg_enabled, bool arg_partial)
-	: plugin::Component(plugin::component::ANALYZER)
+	: plugin::Component(plugin::component::ANALYZER),
+	  plugin::TaggedComponent<analyzer::Tag>(arg_subtype)
 	{
 	name = copy_string(arg_name);
 	canon_name = canonify_name(arg_name);
 	factory = arg_factory;
 	enabled = arg_enabled;
 	partial = arg_partial;
-
-	tag = analyzer::Tag(++type_counter, arg_subtype);
 	}
 
 Component::Component(const Component& other)
-	: plugin::Component(Type())
+	: plugin::Component(Type()),
+	  plugin::TaggedComponent<analyzer::Tag>(other)
 	{
 	name = copy_string(other.name);
 	canon_name = copy_string(other.canon_name);
 	factory = other.factory;
 	enabled = other.enabled;
 	partial = other.partial;
-	tag = other.tag;
 	}
 
 Component::~Component()
@@ -39,11 +36,6 @@ Component::~Component()
 	delete [] canon_name;
 	}
 
-analyzer::Tag Component::Tag() const
-	{
-	return tag;
-	}
-
 void Component::Describe(ODesc* d) const
 	{
 	plugin::Component::Describe(d);
@@ -63,13 +55,14 @@ void Component::Describe(ODesc* d) const
 
 Component& Component::operator=(const Component& other)
 	{
+	plugin::TaggedComponent<analyzer::Tag>::operator=(other);
+
 	if ( &other != this )
 		{
 		name = copy_string(other.name);
 		factory = other.factory;
 		enabled = other.enabled;
 		partial = other.partial;
-		tag = other.tag;
 		}
 
 	return *this;

src/analyzer/Component.h

@@ -5,6 +5,7 @@
 
 #include "Tag.h"
 #include "plugin/Component.h"
+#include "plugin/TaggedComponent.h"
 
 #include "../config.h"
 #include "../util.h"
@@ -21,7 +22,8 @@ class Analyzer;
  * A plugin can provide a specific protocol analyzer by registering this
  * analyzer component, describing the analyzer.
  */
-class Component : public plugin::Component {
+class Component : public plugin::Component,
+                  public plugin::TaggedComponent<analyzer::Tag> {
 public:
 	typedef Analyzer* (*factory_callback)(Connection* conn);
 
@@ -100,13 +102,6 @@ public:
 	 */
 	bool Enabled() const	{ return enabled; }
 
-	/**
-	 * Returns the analyzer's tag. Note that this is automatically
-	 * generated for each new Components, and hence unique across all of
-	 * them.
-	 */
-	analyzer::Tag Tag() const;
-
 	/**
 	 * Enables or disables this analyzer.
 	 *
@@ -128,11 +123,7 @@ private:
 	const char* canon_name;	// The analyzer's canonical name.
 	factory_callback factory;	// The analyzer's factory callback.
 	bool partial;	// True if the analyzer supports partial connections.
-	analyzer::Tag tag;	// The automatically assigned analyzer tag.
 	bool enabled;	// True if the analyzer is enabled.
-
-	// Global counter used to generate unique tags.
-	static analyzer::Tag::type_t type_counter;
 };
 
 }

src/analyzer/Manager.cc

@@ -60,10 +60,8 @@ bool Manager::ConnIndex::operator<(const ConnIndex& other) const
 	}
 
 Manager::Manager()
+	: plugin::ComponentManager<analyzer::Tag, analyzer::Component>("Analyzer")
 	{
-	tag_enum_type = new EnumType("Analyzer::Tag");
-	::ID* id = install_ID("Tag", "Analyzer", true, true);
-	add_type(id, tag_enum_type, 0, 0);
 	}
 
 Manager::~Manager()
@@ -91,14 +89,14 @@ void Manager::InitPreScript()
 	std::list<Component*> analyzers = plugin_mgr->Components<Component>();
 
 	for ( std::list<Component*>::const_iterator i = analyzers.begin(); i != analyzers.end(); i++ )
-		RegisterAnalyzerComponent(*i);
+		RegisterComponent(*i, "ANALYZER_");
 
 	// Cache these tags.
-	analyzer_backdoor = GetAnalyzerTag("BACKDOOR");
+	analyzer_backdoor = GetComponentTag("BACKDOOR");
-	analyzer_connsize = GetAnalyzerTag("CONNSIZE");
+	analyzer_connsize = GetComponentTag("CONNSIZE");
-	analyzer_interconn = GetAnalyzerTag("INTERCONN");
+	analyzer_interconn = GetComponentTag("INTERCONN");
-	analyzer_stepping = GetAnalyzerTag("STEPPINGSTONE");
+	analyzer_stepping = GetComponentTag("STEPPINGSTONE");
-	analyzer_tcpstats = GetAnalyzerTag("TCPSTATS");
+	analyzer_tcpstats = GetComponentTag("TCPSTATS");
 	}
 
 void Manager::InitPostScript()
@@ -109,8 +107,9 @@ void Manager::DumpDebug()
 	{
 #ifdef DEBUG
 	DBG_LOG(DBG_ANALYZER, "Available analyzers after bro_init():");
-	for ( analyzer_map_by_name::const_iterator i = analyzers_by_name.begin(); i != analyzers_by_name.end(); i++ )
+	list<Component*> all_analyzers = GetComponents();
-		DBG_LOG(DBG_ANALYZER, "    %s (%s)", i->second->Name(), IsEnabled(i->second->Tag()) ? "enabled" : "disabled");
+	for ( list<Component*>::const_iterator i = all_analyzers.begin(); i != all_analyzers.end(); ++i )
+		DBG_LOG(DBG_ANALYZER, "    %s (%s)", (*i)->Name(), IsEnabled((*i)->Tag()) ? "enabled" : "disabled");
 
 	DBG_LOG(DBG_ANALYZER, "");
 	DBG_LOG(DBG_ANALYZER, "Analyzers by port:");
@@ -120,7 +119,7 @@ void Manager::DumpDebug()
 		string s;
 
 		for ( tag_set::const_iterator j = i->second->begin(); j != i->second->end(); j++ )
-			s += string(GetAnalyzerName(*j)) + " ";
+			s += string(GetComponentName(*j)) + " ";
 
 		DBG_LOG(DBG_ANALYZER, "    %d/tcp: %s", i->first, s.c_str());
 		}
@@ -130,7 +129,7 @@ void Manager::DumpDebug()
 		string s;
 
 		for ( tag_set::const_iterator j = i->second->begin(); j != i->second->end(); j++ )
-			s += string(GetAnalyzerName(*j)) + " ";
+			s += string(GetComponentName(*j)) + " ";
 
 		DBG_LOG(DBG_ANALYZER, "    %d/udp: %s", i->first, s.c_str());
 		}
@@ -142,25 +141,6 @@ void Manager::Done()
 	{
 	}
 
-void Manager::RegisterAnalyzerComponent(Component* component)
-	{
-	const char* cname = component->CanonicalName();
-
-	if ( Lookup(cname) )
-		reporter->FatalError("Analyzer %s defined more than once", cname);
-
-	DBG_LOG(DBG_ANALYZER, "Registering analyzer %s (tag %s)",
-		component->Name(), component->Tag().AsString().c_str());
-
-	analyzers_by_name.insert(std::make_pair(cname, component));
-	analyzers_by_tag.insert(std::make_pair(component->Tag(), component));
-	analyzers_by_val.insert(std::make_pair(component->Tag().AsEnumVal()->InternalInt(), component));
-
-	// Install enum "Analyzer::ANALYZER_*"
-	string id = fmt("ANALYZER_%s", cname);
-	tag_enum_type->AddName("Analyzer", id.c_str(), component->Tag().AsEnumVal()->InternalInt(), true);
-	}
-
 bool Manager::EnableAnalyzer(Tag tag)
 	{
 	Component* p = Lookup(tag);
@@ -217,8 +197,9 @@ void Manager::DisableAllAnalyzers()
 	{
 	DBG_LOG(DBG_ANALYZER, "Disabling all analyzers");
 
-	for ( analyzer_map_by_tag::const_iterator i = analyzers_by_tag.begin(); i != analyzers_by_tag.end(); i++ )
+	list<Component*> all_analyzers = GetComponents();
-		i->second->SetEnabled(false);
+	for ( list<Component*>::const_iterator i = all_analyzers.begin(); i != all_analyzers.end(); ++i )
+		(*i)->SetEnabled(false);
 	}
 
 bool Manager::IsEnabled(Tag tag)
@@ -270,7 +251,7 @@ bool Manager::RegisterAnalyzerForPort(Tag tag, TransportProto proto, uint32 port
 	tag_set* l = LookupPort(proto, port, true);
 
 #ifdef DEBUG
-	const char* name = GetAnalyzerName(tag);
+	const char* name = GetComponentName(tag);
 	DBG_LOG(DBG_ANALYZER, "Registering analyzer %s for port %" PRIu32 "/%d", name, port, proto);
 #endif
 
@@ -283,7 +264,7 @@ bool Manager::UnregisterAnalyzerForPort(Tag tag, TransportProto proto, uint32 po
 	tag_set* l = LookupPort(proto, port, true);
 
 #ifdef DEBUG
-	const char* name = GetAnalyzerName(tag);
+	const char* name = GetComponentName(tag);
 	DBG_LOG(DBG_ANALYZER, "Unregistering analyzer %s for port %" PRIu32 "/%d", name, port, proto);
 #endif
 
@@ -302,7 +283,7 @@ Analyzer* Manager::InstantiateAnalyzer(Tag tag, Connection* conn)
 		return 0;
 
 	if ( ! c->Factory() )
-		reporter->InternalError("analyzer %s cannot be instantiated dynamically", GetAnalyzerName(tag));
+		reporter->InternalError("analyzer %s cannot be instantiated dynamically", GetComponentName(tag));
 
 	Analyzer* a = c->Factory()(conn);
 
@@ -316,59 +297,10 @@ Analyzer* Manager::InstantiateAnalyzer(Tag tag, Connection* conn)
 
 Analyzer* Manager::InstantiateAnalyzer(const char* name, Connection* conn)
 	{
-	Tag tag = GetAnalyzerTag(name);
+	Tag tag = GetComponentTag(name);
 	return tag ? InstantiateAnalyzer(tag, conn) : 0;
 	}
 
-const char* Manager::GetAnalyzerName(Tag tag)
-	{
-	static const char* error = "<error>";
-
-	if ( ! tag )
-		return error;
-
-	Component* c = Lookup(tag);
-
-	if ( ! c )
-		reporter->InternalError("request for name of unknown analyzer tag %s", tag.AsString().c_str());
-
-	return c->CanonicalName();
-	}
-
-const char* Manager::GetAnalyzerName(Val* val)
-	{
-	return GetAnalyzerName(Tag(val->AsEnumVal()));
-	}
-
-Tag Manager::GetAnalyzerTag(const char* name)
-	{
-	Component* c = Lookup(name);
-	return c ? c->Tag() : Tag();
-	}
-
-EnumType* Manager::GetTagEnumType()
-	{
-	return tag_enum_type;
-	}
-
-Component* Manager::Lookup(const char* name)
-	{
-	analyzer_map_by_name::const_iterator i = analyzers_by_name.find(to_upper(name));
-	return i != analyzers_by_name.end() ? i->second : 0;
-	}
-
-Component* Manager::Lookup(const Tag& tag)
-	{
-	analyzer_map_by_tag::const_iterator i = analyzers_by_tag.find(tag);
-	return i != analyzers_by_tag.end() ? i->second : 0;
-	}
-
-Component* Manager::Lookup(EnumVal* val)
-	{
-	analyzer_map_by_val::const_iterator i = analyzers_by_val.find(val->InternalInt());
-	return i != analyzers_by_val.end() ? i->second : 0;
-	}
-
 Manager::tag_set* Manager::LookupPort(TransportProto proto, uint32 port, bool add_if_not_found)
 	{
 	analyzer_map_by_port* m = 0;
@@ -461,7 +393,7 @@ bool Manager::BuildInitialAnalyzerTree(Connection* conn)
 			root->AddChildAnalyzer(analyzer, false);
 
 			DBG_ANALYZER_ARGS(conn, "activated %s analyzer as scheduled",
-				     analyzer_mgr->GetAnalyzerName(*i));
+					  analyzer_mgr->GetComponentName(*i));
 			}
 
 		}
@@ -487,7 +419,7 @@ bool Manager::BuildInitialAnalyzerTree(Connection* conn)
 
 					root->AddChildAnalyzer(analyzer, false);
 					DBG_ANALYZER_ARGS(conn, "activated %s analyzer due to port %d",
-						     analyzer_mgr->GetAnalyzerName(*j), resp_port);
+							  analyzer_mgr->GetComponentName(*j), resp_port);
 					}
 				}
 			}
@@ -613,7 +545,7 @@ void Manager::ExpireScheduledAnalyzers()
 			conns.erase(i);
 
 			DBG_LOG(DBG_ANALYZER, "Expiring expected analyzer %s for connection %s",
-				analyzer_mgr->GetAnalyzerName(a->analyzer),
+				analyzer_mgr->GetComponentName(a->analyzer),
 				fmt_conn_id(a->conn.orig, 0, a->conn.resp, a->conn.resp_p));
 
 			delete a;
@@ -655,7 +587,7 @@ void Manager::ScheduleAnalyzer(const IPAddr& orig, const IPAddr& resp,
 			TransportProto proto, const char* analyzer,
 			double timeout)
 	{
-	Tag tag = GetAnalyzerTag(analyzer);
+	Tag tag = GetComponentTag(analyzer);
 
 	if ( tag != Tag() )
 		ScheduleAnalyzer(orig, resp, resp_p, proto, tag, timeout);

src/analyzer/Manager.h

@@ -26,6 +26,7 @@
 #include "Analyzer.h"
 #include "Component.h"
 #include "Tag.h"
+#include "plugin/ComponentManager.h"
 
 #include "../Dict.h"
 #include "../net_util.h"
@@ -49,7 +50,7 @@ namespace analyzer {
  * classes. This allows to external analyzer code to potentially use a
  * different C++ standard library.
  */
-class Manager {
+class Manager : public plugin::ComponentManager<Tag, Component> {
 public:
 	/**
 	 * Constructor.
@@ -231,42 +232,6 @@ public:
 	 */
 	Analyzer* InstantiateAnalyzer(const char* name, Connection* c);
 
-	/**
-	 * Translates an analyzer tag into corresponding analyzer name.
-	 *
-	 * @param tag The analyzer tag.
-	 *
-	 * @return The name, or an empty string if the tag is invalid.
-	 */
-	const char* GetAnalyzerName(Tag tag);
-
-	/**
-	 * Translates an script-level analyzer tag into corresponding
-	 * analyzer name.
-	 *
-	 * @param val The analyzer tag as an script-level enum value of type
-	 * \c Analyzer::Tag.
-	 *
-	 * @return The name, or an empty string if the tag is invalid.
-	 */
-	const char* GetAnalyzerName(Val* val);
-
-	/**
-	 * Translates an analyzer name into the corresponding tag.
-	 *
-	 * @param name The name.
-	 *
-	 * @return The tag. If the name does not correspond to a valid
-	 * analyzer, the returned tag will evaluate to false.
-	 */
-	Tag GetAnalyzerTag(const char* name);
-
-	/**
-	 * Returns the enum type that corresponds to the script-level type \c
-	 * Analyzer::Tag.
-	 */
-	EnumType* GetTagEnumType();
-
 	/**
 	 * Given the first packet of a connection, builds its initial
 	 * analyzer tree.
@@ -350,18 +315,8 @@ public:
 
 private:
 	typedef set<Tag> tag_set;
-	typedef map<string, Component*> analyzer_map_by_name;
-	typedef map<Tag, Component*>  analyzer_map_by_tag;
-	typedef map<int, Component*>  analyzer_map_by_val;
 	typedef map<uint32, tag_set*> analyzer_map_by_port;
 
-	void RegisterAnalyzerComponent(Component* component); // Takes ownership.
-
-	Component* Lookup(const string& name);
-	Component* Lookup(const char* name);
-	Component* Lookup(const Tag& tag);
-	Component* Lookup(EnumVal* val);
-
 	tag_set* LookupPort(PortVal* val, bool add_if_not_found);
 	tag_set* LookupPort(TransportProto proto, uint32 port, bool add_if_not_found);
 
@@ -370,9 +325,6 @@ private:
 
 	analyzer_map_by_port analyzers_by_port_tcp;
 	analyzer_map_by_port analyzers_by_port_udp;
-	analyzer_map_by_name analyzers_by_name;
-	analyzer_map_by_tag  analyzers_by_tag;
-	analyzer_map_by_val  analyzers_by_val;
 
 	Tag analyzer_backdoor;
 	Tag analyzer_connsize;
@@ -380,8 +332,6 @@ private:
 	Tag analyzer_stepping;
 	Tag analyzer_tcpstats;
 
-	EnumType* tag_enum_type;
-
 	//// Data structures to track analyzed scheduled for future connections.
 
 	// The index for a scheduled connection.

src/analyzer/Tag.cc

@@ -3,90 +3,20 @@
 #include "Tag.h"
 #include "Manager.h"
 
-#include "../NetVar.h"
+analyzer::Tag analyzer::Tag::Error;
 
-using namespace analyzer;
+analyzer::Tag::Tag(type_t type, subtype_t subtype)
-
+	: ::Tag(analyzer_mgr->GetTagEnumType(), type, subtype)
-Tag Tag::Error;
-
-Tag::Tag(type_t arg_type, subtype_t arg_subtype)
 	{
-	assert(arg_type > 0);
-
-	type = arg_type;
-	subtype = arg_subtype;
-	int64_t i = (int64)(type) | ((int64)subtype << 31);
-
-	EnumType* etype = analyzer_mgr->GetTagEnumType();
-	Ref(etype);
-	val = new EnumVal(i, etype);
 	}
 
-Tag::Tag(EnumVal* arg_val)
+analyzer::Tag& analyzer::Tag::operator=(const analyzer::Tag& other)
 	{
-	assert(arg_val);
+	::Tag::operator=(other);
-
-	val = arg_val;
-	Ref(val);
-
-	int64 i = val->InternalInt();
-	type = i & 0xffffffff;
-	subtype = (i >> 31) & 0xffffffff;
-	}
-
-Tag::Tag(const Tag& other)
-	{
-	type = other.type;
-	subtype = other.subtype;
-	val = other.val;
-
-	if ( val )
-		Ref(val);
-	}
-
-Tag::Tag()
-	{
-	type = 0;
-	subtype = 0;
-	val = 0;
-	}
-
-Tag::~Tag()
-	{
-	Unref(val);
-	val = 0;
-	}
-
-Tag& Tag::operator=(const Tag& other)
-	{
-	if ( this != &other )
-		{
-		type = other.type;
-		subtype = other.subtype;
-		val = other.val;
-
-		if ( val )
-			Ref(val);
-		}
-
 	return *this;
 	}
 
-EnumVal* Tag::AsEnumVal() const
+EnumVal* analyzer::Tag::AsEnumVal() const
 	{
-	if ( ! val )
+	return ::Tag::AsEnumVal(analyzer_mgr->GetTagEnumType());
-		{
-		assert(analyzer_mgr);
-		assert(type == 0 && subtype == 0);
-		EnumType* etype = analyzer_mgr->GetTagEnumType();
-		Ref(etype);
-		val = new EnumVal(0, etype);
-		}
-
-	return val;
-	}
-
-std::string Tag::AsString() const
-	{
-	return fmt("%" PRIu32 "/%" PRIu32, type, subtype);
 	}

src/analyzer/Tag.h

@@ -5,90 +5,46 @@
 
 #include "config.h"
 #include "util.h"
+#include "../Tag.h"
+#include "plugin/TaggedComponent.h"
+#include "plugin/ComponentManager.h"
 
 class EnumVal;
 
-namespace file_analysis {
-class Manager;
-class Component;
-}
-
 namespace analyzer {
 
 class Manager;
 class Component;
 
 /**
- * Class to identify an analyzer type.
+ * Class to identify a protocol analyzer type.
  *
- * Each analyzer type gets a tag consisting of a main type and subtype. The
+ * The script-layer analogue is Analyzer::Tag.
- * former is an identifier that's unique all analyzer classes. The latter is
- * passed through to the analyzer instances for their use, yet not further
- * interpreted by the analyzer infrastructure; it allows an analyzer to
- * branch out into a set of sub-analyzers internally. Jointly, main type and
- * subtype form an analyzer "tag". Each unique tag corresponds to a single
- * "analyzer" from the user's perspective. At the script layer, these tags
- * are mapped into enums of type \c Analyzer::Tag. Internally, the
- * analyzer::Manager maintains the mapping of tag to analyzer (and it also
- * assigns them their main types), and analyzer::Component creates new
- * tags.
- *
- * The Tag class supports all operations necessary to act as an index in a
- * \c std::map.
  */
-class Tag  {
+class Tag : public ::Tag  {
 public:
-	/**
-	 * Type for the analyzer's main type.
-	 */
-	typedef uint32 type_t;
-
-	/**
-	 * Type for the analyzer's subtype.
-	 */
-	typedef uint32 subtype_t;
-
 	/*
 	 * Copy constructor.
 	 */
-	Tag(const Tag& other);
+	Tag(const Tag& other) : ::Tag(other) {}
 
 	/**
 	 * Default constructor. This initializes the tag with an error value
 	 * that will make \c operator \c bool return false.
 	 */
-	Tag();
+	Tag() : ::Tag() {}
 
 	/**
 	 * Destructor.
 	 */
-	~Tag();
+	~Tag() {}
-
-	/**
-	 * Returns the tag's main type.
-	 */
-	type_t Type() const 	{ return type; }
-
-	/**
-	 * Returns the tag's subtype.
-	 */
-	subtype_t Subtype() const 	{ return subtype; }
-
-	/**
-	 * Returns the \c Analyzer::Tag enum that corresponds to this tag.
-	 * The returned value is \a does not have its ref-count increased.
-	 */
-	EnumVal* AsEnumVal() const;
-
-	/**
-	 * Returns the numerical values for main and subtype inside a string
-	 * suitable for printing. This is primarily for debugging.
-	 */
-	std::string AsString() const;
 
 	/**
 	 * Returns false if the tag represents an error value rather than a
 	 * legal analyzer type.
+	 * TODO: make this conversion operator "explicit" (C++11) or use a
+	 *       "safe bool" idiom (not necessary if "explicit" is available),
+	 *       otherwise this may allow nonsense/undesired comparison operations.
 	 */
 	operator bool() const	{ return *this != Tag(); }
 
@@ -102,7 +58,7 @@ public:
 	 */
 	bool operator==(const Tag& other) const
 		{
-		return type == other.type && subtype == other.subtype;
+		return ::Tag::operator==(other);
 		}
 
 	/**
@@ -110,7 +66,7 @@ public:
 	 */
 	bool operator!=(const Tag& other) const
 		{
-		return type != other.type || subtype != other.subtype;
+		return ::Tag::operator!=(other);
 		}
 
 	/**
@@ -118,23 +74,30 @@ public:
 	 */
 	bool operator<(const Tag& other) const
 		{
-		return type != other.type ? type < other.type : (subtype < other.subtype);
+		return ::Tag::operator<(other);
 		}
 
+	/**
+	 * Returns the \c Analyzer::Tag enum that corresponds to this tag.
+	 * The returned value does not have its ref-count increased.
+	 *
+	 * @param etype the script-layer enum type associated with the tag.
+	 */
+	EnumVal* AsEnumVal() const;
+
 	static Tag Error;
 
 protected:
 	friend class analyzer::Manager;
-	friend class analyzer::Component;
+	friend class plugin::ComponentManager<Tag, Component>;
-	friend class file_analysis::Manager;
+	friend class plugin::TaggedComponent<Tag>;
-	friend class file_analysis::Component;
 
 	/**
 	 * Constructor.
 	 *
 	 * @param type The main type. Note that the \a analyzer::Manager
 	 * manages the value space internally, so noone else should assign
-	 * any main tyoes.
+	 * any main types.
 	 *
 	 * @param subtype The sub type, which is left to an analyzer for
 	 * interpretation. By default it's set to zero.
@@ -144,14 +107,9 @@ protected:
 	/**
 	 * Constructor.
 	 *
-	 * @param val An enuam value of script type \c Analyzer::Tag.
+	 * @param val An enum value of script type \c Analyzer::Tag.
 	 */
-	Tag(EnumVal* val);
+	Tag(EnumVal* val) : ::Tag(val) {}
-
-private:
-	type_t type;		// Main type.
-	subtype_t subtype;	// Subtype.
-	mutable EnumVal* val;	// Analyzer::Tag value.
 };
 
 }

src/analyzer/analyzer.bif

@@ -41,11 +41,11 @@ function Analyzer::__schedule_analyzer%(orig: addr, resp: addr, resp_p: port,
 
 function __name%(atype: Analyzer::Tag%) : string
 	%{
-	return new StringVal(analyzer_mgr->GetAnalyzerName(atype));
+	return new StringVal(analyzer_mgr->GetComponentName(atype));
 	%}
 
 function __tag%(name: string%) : Analyzer::Tag
 	%{
-	analyzer::Tag t = analyzer_mgr->GetAnalyzerTag(name->CheckString());
+	analyzer::Tag t = analyzer_mgr->GetComponentTag(name->CheckString());
 	return t.AsEnumVal()->Ref();
 	%}

src/file_analysis/Analyzer.cc

@@ -0,0 +1,11 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
+#include "Analyzer.h"
+#include "Manager.h"
+
+file_analysis::Analyzer::~Analyzer()
+	{
+	DBG_LOG(DBG_FILE_ANALYSIS, "Destroy file analyzer %s",
+	        file_mgr->GetComponentName(tag));
+	Unref(args);
+	}

src/file_analysis/Analyzer.h

@@ -5,14 +5,12 @@
 
 #include "Val.h"
 #include "NetVar.h"
-#include "analyzer/Tag.h"
+#include "Tag.h"
 
 #include "file_analysis/file_analysis.bif.h"
 
 namespace file_analysis {
 
-typedef int FA_Tag;
-
 class File;
 
 /**
@@ -25,11 +23,7 @@ public:
 	 * Destructor.  Nothing special about it. Virtual since we definitely expect
 	 * to delete instances of derived classes via pointers to this class.
 	 */
-	virtual ~Analyzer()
+	virtual ~Analyzer();
-		{
-		DBG_LOG(DBG_FILE_ANALYSIS, "Destroy file analyzer %d", tag);
-		Unref(args);
-		}
 
 	/**
 	 * Subclasses may override this metod to receive file data non-sequentially.
@@ -76,7 +70,7 @@ public:
 	/**
 	 * @return the analyzer type enum value.
 	 */
-	FA_Tag Tag() const { return tag; }
+	file_analysis::Tag Tag() const { return tag; }
 
 	/**
 	 * @return the AnalyzerArgs associated with the analyzer.
@@ -88,18 +82,6 @@ public:
 	 */
 	File* GetFile() const { return file; }
 
-	/**
-	 * Retrieves an analyzer tag field from full analyzer argument record.
-	 * @param args an \c AnalyzerArgs (script-layer type) value.
-	 * @return the analyzer tag equivalent of the 'tag' field from the
-	 *         \c AnalyzerArgs value \a args.
-	 */
-	static FA_Tag ArgsTag(const RecordVal* args)
-		{
-		using BifType::Record::Files::AnalyzerArgs;
-		return args->Lookup(AnalyzerArgs->FieldOffset("tag"))->AsEnum();
-		}
-
 protected:
 
 	/**
@@ -108,15 +90,15 @@ protected:
 	 *        tunable options, if any, related to a particular analyzer type.
 	 * @param arg_file the file to which the the analyzer is being attached.
 	 */
-	Analyzer(RecordVal* arg_args, File* arg_file)
+	Analyzer(file_analysis::Tag arg_tag, RecordVal* arg_args, File* arg_file)
-	    : tag(file_analysis::Analyzer::ArgsTag(arg_args)),
+	    : tag(arg_tag),
 	      args(arg_args->Ref()->AsRecordVal()),
 	      file(arg_file)
 		{}
 
 private:
 
-	FA_Tag tag;	/**< The particular analyzer type of the analyzer instance. */
+	file_analysis::Tag tag;	/**< The particular type of the analyzer instance. */
 	RecordVal* args;	/**< \c AnalyzerArgs val gives tunable analyzer params. */
 	File* file;	/**< The file to which the analyzer is attached. */
 };

src/file_analysis/AnalyzerSet.cc

@@ -15,6 +15,7 @@ static void analyzer_del_func(void* v)
 AnalyzerSet::AnalyzerSet(File* arg_file) : file(arg_file)
 	{
 	TypeList* t = new TypeList();
+	t->Append(file_mgr->GetTagEnumType());
 	t->Append(BifType::Record::Files::AnalyzerArgs->Ref());
 	analyzer_hash = new CompositeHash(t);
 	Unref(t);
@@ -34,20 +35,20 @@ AnalyzerSet::~AnalyzerSet()
 	delete analyzer_hash;
 	}
 
-bool AnalyzerSet::Add(RecordVal* args)
+bool AnalyzerSet::Add(file_analysis::Tag tag, RecordVal* args)
 	{
-	HashKey* key = GetKey(args);
+	HashKey* key = GetKey(tag, args);
 
 	if ( analyzer_map.Lookup(key) )
 		{
-		DBG_LOG(DBG_FILE_ANALYSIS, "Instantiate analyzer %d skipped for file id"
+		DBG_LOG(DBG_FILE_ANALYSIS, "Instantiate analyzer %s skipped for file id"
-		        " %s: already exists", file_analysis::Analyzer::ArgsTag(args),
+		        " %s: already exists", file_mgr->GetComponentName(tag),
 		        file->GetID().c_str());
 		delete key;
 		return true;
 		}
 
-	file_analysis::Analyzer* a = InstantiateAnalyzer(args);
+	file_analysis::Analyzer* a = InstantiateAnalyzer(tag, args);
 
 	if ( ! a )
 		{
@@ -60,10 +61,10 @@ bool AnalyzerSet::Add(RecordVal* args)
 	return true;
 	}
 
-bool AnalyzerSet::QueueAdd(RecordVal* args)
+bool AnalyzerSet::QueueAdd(file_analysis::Tag tag, RecordVal* args)
 	{
-	HashKey* key = GetKey(args);
+	HashKey* key = GetKey(tag, args);
-	file_analysis::Analyzer* a = InstantiateAnalyzer(args);
+	file_analysis::Analyzer* a = InstantiateAnalyzer(tag, args);
 
 	if ( ! a )
 		{
@@ -80,8 +81,9 @@ bool AnalyzerSet::AddMod::Perform(AnalyzerSet* set)
 	{
 	if ( set->analyzer_map.Lookup(key) )
 		{
-		DBG_LOG(DBG_FILE_ANALYSIS, "Add analyzer %d skipped for file id"
+		DBG_LOG(DBG_FILE_ANALYSIS, "Add analyzer %s skipped for file id"
-		        " %s: already exists", a->Tag(), a->GetFile()->GetID().c_str());
+		        " %s: already exists", file_mgr->GetComponentName(a->Tag()),
+		        a->GetFile()->GetID().c_str());
 
 		Abort();
 		return true;
@@ -91,12 +93,12 @@ bool AnalyzerSet::AddMod::Perform(AnalyzerSet* set)
 	return true;
 	}
 
-bool AnalyzerSet::Remove(const RecordVal* args)
+bool AnalyzerSet::Remove(file_analysis::Tag tag, RecordVal* args)
 	{
-	return Remove(file_analysis::Analyzer::ArgsTag(args), GetKey(args));
+	return Remove(tag, GetKey(tag, args));
 	}
 
-bool AnalyzerSet::Remove(FA_Tag tag, HashKey* key)
+bool AnalyzerSet::Remove(file_analysis::Tag tag, HashKey* key)
 	{
 	file_analysis::Analyzer* a =
 	    (file_analysis::Analyzer*) analyzer_map.Remove(key);
@@ -105,22 +107,22 @@ bool AnalyzerSet::Remove(FA_Tag tag, HashKey* key)
 
 	if ( ! a )
 		{
-		DBG_LOG(DBG_FILE_ANALYSIS, "Skip remove analyzer %d for file id %s",
+		DBG_LOG(DBG_FILE_ANALYSIS, "Skip remove analyzer %s for file id %s",
-		        tag, file->GetID().c_str());
+		        file_mgr->GetComponentName(tag), file->GetID().c_str());
 		return false;
 		}
 
-	DBG_LOG(DBG_FILE_ANALYSIS, "Remove analyzer %d for file id %s", a->Tag(),
+	DBG_LOG(DBG_FILE_ANALYSIS, "Remove analyzer %s for file id %s",
+	        file_mgr->GetComponentName(tag),
 	        file->GetID().c_str());
 
 	delete a;
 	return true;
 	}
 
-bool AnalyzerSet::QueueRemove(const RecordVal* args)
+bool AnalyzerSet::QueueRemove(file_analysis::Tag tag, RecordVal* args)
 	{
-	HashKey* key = GetKey(args);
+	HashKey* key = GetKey(tag, args);
-	FA_Tag tag = file_analysis::Analyzer::ArgsTag(args);
 
 	mod_queue.push(new RemoveMod(tag, key));
 
@@ -132,24 +134,28 @@ bool AnalyzerSet::RemoveMod::Perform(AnalyzerSet* set)
 	return set->Remove(tag, key);
 	}
 
-HashKey* AnalyzerSet::GetKey(const RecordVal* args) const
+HashKey* AnalyzerSet::GetKey(file_analysis::Tag t, RecordVal* args) const
 	{
-	HashKey* key = analyzer_hash->ComputeHash(args, 1);
+	ListVal* lv = new ListVal(TYPE_ANY);
+	lv->Append(t.AsEnumVal()->Ref());
+	lv->Append(args->Ref());
+	HashKey* key = analyzer_hash->ComputeHash(lv, 1);
+	Unref(lv);
 	if ( ! key )
 		reporter->InternalError("AnalyzerArgs type mismatch");
 
 	return key;
 	}
 
-file_analysis::Analyzer* AnalyzerSet::InstantiateAnalyzer(RecordVal* args) const
+file_analysis::Analyzer* AnalyzerSet::InstantiateAnalyzer(Tag tag,
+                                                          RecordVal* args) const
 	{
-	FA_Tag tag = file_analysis::Analyzer::ArgsTag(args);
 	file_analysis::Analyzer* a = file_mgr->InstantiateAnalyzer(tag, args, file);
 
 	if ( ! a )
 		{
 		reporter->Error("Failed file analyzer %s instantiation for file id %s",
-		                file_mgr->GetAnalyzerName(tag), file->GetID().c_str());
+		                file_mgr->GetComponentName(tag), file->GetID().c_str());
 		return 0;
 		}
 
@@ -158,8 +164,8 @@ file_analysis::Analyzer* AnalyzerSet::InstantiateAnalyzer(RecordVal* args) const
 
 void AnalyzerSet::Insert(file_analysis::Analyzer* a, HashKey* key)
 	{
-	DBG_LOG(DBG_FILE_ANALYSIS, "Add analyzer %d for file id %s", a->Tag(),
+	DBG_LOG(DBG_FILE_ANALYSIS, "Add analyzer %s for file id %s",
-	        file->GetID().c_str());
+	        file_mgr->GetComponentName(a->Tag()), file->GetID().c_str());
 	analyzer_map.Insert(key, a);
 	delete key;
 	}

src/file_analysis/AnalyzerSet.h

@@ -9,6 +9,7 @@
 #include "Dict.h"
 #include "CompHash.h"
 #include "Val.h"
+#include "Tag.h"
 
 namespace file_analysis {
 
@@ -38,31 +39,35 @@ public:
 
 	/**
 	 * Attach an analyzer to #file immediately.
+	 * @param tag the analyzer tag of the file analyzer to add.
 	 * @param args an \c AnalyzerArgs value which specifies an analyzer.
 	 * @return true if analyzer was instantiated/attached, else false.
 	 */
-	bool Add(RecordVal* args);
+	bool Add(file_analysis::Tag tag, RecordVal* args);
 
 	/**
 	 * Queue the attachment of an analyzer to #file.
+	 * @param tag the analyzer tag of the file analyzer to add.
 	 * @param args an \c AnalyzerArgs value which specifies an analyzer.
 	 * @return true if analyzer was able to be instantiated, else false.
 	 */
-	bool QueueAdd(RecordVal* args);
+	bool QueueAdd(file_analysis::Tag tag, RecordVal* args);
 
 	/**
 	 * Remove an analyzer from #file immediately.
+	 * @param tag the analyzer tag of the file analyzer to remove.
 	 * @param args an \c AnalyzerArgs value which specifies an analyzer.
 	 * @return false if analyzer didn't exist and so wasn't removed, else true.
 	 */
-	bool Remove(const RecordVal* args);
+	bool Remove(file_analysis::Tag tag, RecordVal* args);
 
 	/**
 	 * Queue the removal of an analyzer from #file.
+	 * @param tag the analyzer tag of the file analyzer to remove.
 	 * @param args an \c AnalyzerArgs value which specifies an analyzer.
 	 * @return true if analyzer exists at time of call, else false;
 	 */
-	bool QueueRemove(const RecordVal* args);
+	bool QueueRemove(file_analysis::Tag tag, RecordVal* args);
 
 	/**
 	 * Perform all queued modifications to the current analyzer set.
@@ -91,17 +96,20 @@ protected:
 
 	/**
 	 * Get a hash key which represents an analyzer instance.
+	 * @param tag the file analyzer tag.
 	 * @param args an \c AnalyzerArgs value which specifies an analyzer.
 	 * @return the hash key calculated from \a args
 	 */
-	HashKey* GetKey(const RecordVal* args) const;
+	HashKey* GetKey(file_analysis::Tag tag, RecordVal* args) const;
 
 	/**
 	 * Create an instance of a file analyzer.
+	 * @param tag the tag of a file analyzer.
 	 * @param args an \c AnalyzerArgs value which specifies an analyzer.
 	 * @return a new file analyzer instance.
 	 */
-	file_analysis::Analyzer* InstantiateAnalyzer(RecordVal* args) const;
+	file_analysis::Analyzer* InstantiateAnalyzer(file_analysis::Tag tag,
+	                                             RecordVal* args) const;
 
 	/**
 	 * Insert an analyzer instance in to the set.
@@ -116,7 +124,7 @@ protected:
 	 *        just used for debugging messages.
 	 * @param key the hash key which represents the analyzer's \c AnalyzerArgs.
 	 */
-	bool Remove(FA_Tag tag, HashKey* key);
+	bool Remove(file_analysis::Tag tag, HashKey* key);
 
 private:
 
@@ -175,14 +183,14 @@ private:
 		 * @param arg_a an analyzer instance to add to an analyzer set.
 		 * @param arg_key hash key representing the analyzer's \c AnalyzerArgs.
 		 */
-		RemoveMod(FA_Tag arg_tag, HashKey* arg_key)
+		RemoveMod(file_analysis::Tag arg_tag, HashKey* arg_key)
 			: Modification(), tag(arg_tag), key(arg_key) {}
 		virtual ~RemoveMod() {}
 		virtual bool Perform(AnalyzerSet* set);
 		virtual void Abort() { delete key; }
 
 	protected:
-		FA_Tag tag;
+		file_analysis::Tag tag;
 		HashKey* key;
 	};
 

src/file_analysis/CMakeLists.txt

@@ -11,9 +11,10 @@ set(file_analysis_SRCS
     Manager.cc
     File.cc
     FileTimer.cc
-    Analyzer.h
+    Analyzer.cc
     AnalyzerSet.cc
     Component.cc
+    Tag.cc
 )
 
 bif_target(file_analysis.bif)

src/file_analysis/Component.cc

@@ -8,26 +8,22 @@
 
 using namespace file_analysis;
 
-analyzer::Tag::type_t Component::type_counter = 0;
+Component::Component(const char* arg_name, factory_callback arg_factory)
-
+	: plugin::Component(plugin::component::FILE_ANALYZER),
-Component::Component(const char* arg_name, factory_callback arg_factory,
+	  plugin::TaggedComponent<file_analysis::Tag>()
-                     analyzer::Tag::subtype_t arg_subtype)
-	: plugin::Component(plugin::component::FILE_ANALYZER)
 	{
 	name = copy_string(arg_name);
 	canon_name = canonify_name(arg_name);
 	factory = arg_factory;
-
-	tag = analyzer::Tag(++type_counter, arg_subtype);
 	}
 
 Component::Component(const Component& other)
-	: plugin::Component(Type())
+	: plugin::Component(Type()),
+	  plugin::TaggedComponent<file_analysis::Tag>(other)
 	{
 	name = copy_string(other.name);
 	canon_name = copy_string(other.canon_name);
 	factory = other.factory;
-	tag = other.tag;
 	}
 
 Component::~Component()
@@ -36,11 +32,6 @@ Component::~Component()
 	delete [] canon_name;
 	}
 
-analyzer::Tag Component::Tag() const
-	{
-	return tag;
-	}
-
 void Component::Describe(ODesc* d) const
 	{
 	plugin::Component::Describe(d);
@@ -58,11 +49,12 @@ void Component::Describe(ODesc* d) const
 
 Component& Component::operator=(const Component& other)
 	{
+	plugin::TaggedComponent<file_analysis::Tag>::operator=(other);
+
 	if ( &other != this )
 		{
 		name = copy_string(other.name);
 		factory = other.factory;
-		tag = other.tag;
 		}
 
 	return *this;

src/file_analysis/Component.h

@@ -3,8 +3,9 @@
 #ifndef FILE_ANALYZER_PLUGIN_COMPONENT_H
 #define FILE_ANALYZER_PLUGIN_COMPONENT_H
 
-#include "analyzer/Tag.h"
+#include "Tag.h"
 #include "plugin/Component.h"
+#include "plugin/TaggedComponent.h"
 
 #include "Val.h"
 
@@ -22,7 +23,8 @@ class Analyzer;
  * A plugin can provide a specific file analyzer by registering this
  * analyzer component, describing the analyzer.
  */
-class Component : public plugin::Component {
+class Component : public plugin::Component,
+                  public plugin::TaggedComponent<file_analysis::Tag> {
 public:
 	typedef Analyzer* (*factory_callback)(RecordVal* args, File* file);
 
@@ -38,15 +40,8 @@ public:
 	 * from file_analysis::Analyzer. This is typically a static \c
 	 * Instatiate() method inside the class that just allocates and
 	 * returns a new instance.
-	 *
-	 * @param subtype A subtype associated with this component that
-	 * further distinguishes it. The subtype will be integrated into
-	 * the analyzer::Tag that the manager associates with this analyzer,
-	 * and analyzer instances can accordingly access it via analyzer::Tag().
-	 * If not used, leave at zero.
 	 */
-	Component(const char* name, factory_callback factory,
+	Component(const char* name, factory_callback factory);
-	          analyzer::Tag::subtype_t subtype = 0);
 
 	/**
 	 * Copy constructor.
@@ -79,13 +74,6 @@ public:
 	 */
 	factory_callback Factory() const	{ return factory; }
 
-	/**
-	 * Returns the analyzer's tag. Note that this is automatically
-	 * generated for each new Components, and hence unique across all of
-	 * them.
-	 */
-	analyzer::Tag Tag() const;
-
 	/**
 	 * Generates a human-readable description of the component's main
 	 * parameters. This goes into the output of \c "bro -NN".
@@ -98,10 +86,6 @@ private:
 	const char* name;	// The analyzer's name.
 	const char* canon_name;	// The analyzer's canonical name.
 	factory_callback factory;	// The analyzer's factory callback.
-	analyzer::Tag tag;	// The automatically assigned analyzer tag.
-
-	// Global counter used to generate unique tags.
-	static analyzer::Tag::type_t type_counter;
 };
 
 }

src/file_analysis/File.cc

@@ -88,7 +88,7 @@ File::File(const string& file_id, Connection* conn, analyzer::Tag tag,
 	if ( conn )
 		{
 		// add source, connection, is_orig fields
-		SetSource(analyzer_mgr->GetAnalyzerName(tag));
+		SetSource(analyzer_mgr->GetComponentName(tag));
 		val->Assign(is_orig_idx, new Val(is_orig, TYPE_BOOL));
 		UpdateConnectionFields(conn, is_orig);
 		}
@@ -231,14 +231,14 @@ void File::ScheduleInactivityTimer() const
 	timer_mgr->Add(new FileTimer(network_time, id, GetTimeoutInterval()));
 	}
 
-bool File::AddAnalyzer(RecordVal* args)
+bool File::AddAnalyzer(file_analysis::Tag tag, RecordVal* args)
 	{
-	return done ? false : analyzers.QueueAdd(args);
+	return done ? false : analyzers.QueueAdd(tag, args);
 	}
 
-bool File::RemoveAnalyzer(const RecordVal* args)
+bool File::RemoveAnalyzer(file_analysis::Tag tag, RecordVal* args)
 	{
-	return done ? false : analyzers.QueueRemove(args);
+	return done ? false : analyzers.QueueRemove(tag, args);
 	}
 
 bool File::BufferBOF(const u_char* data, uint64 len)
@@ -321,7 +321,7 @@ void File::DataIn(const u_char* data, uint64 len, uint64 offset)
 	while ( (a = analyzers.NextEntry(c)) )
 		{
 		if ( ! a->DeliverChunk(data, len, offset) )
-			analyzers.QueueRemove(a->Args());
+			analyzers.QueueRemove(a->Tag(), a->Args());
 		}
 
 	analyzers.DrainModifications();
@@ -356,7 +356,7 @@ void File::DataIn(const u_char* data, uint64 len)
 		{
 		if ( ! a->DeliverStream(data, len) )
 			{
-			analyzers.QueueRemove(a->Args());
+			analyzers.QueueRemove(a->Tag(), a->Args());
 			continue;
 			}
 
@@ -364,7 +364,7 @@ void File::DataIn(const u_char* data, uint64 len)
 		                LookupFieldDefaultCount(missing_bytes_idx);
 
 		if ( ! a->DeliverChunk(data, len, offset) )
-			analyzers.QueueRemove(a->Args());
+			analyzers.QueueRemove(a->Tag(), a->Args());
 		}
 
 	analyzers.DrainModifications();
@@ -389,7 +389,7 @@ void File::EndOfFile()
 	while ( (a = analyzers.NextEntry(c)) )
 		{
 		if ( ! a->EndOfFile() )
-			analyzers.QueueRemove(a->Args());
+			analyzers.QueueRemove(a->Tag(), a->Args());
 		}
 
 	FileEvent(file_state_remove);
@@ -411,7 +411,7 @@ void File::Gap(uint64 offset, uint64 len)
 	while ( (a = analyzers.NextEntry(c)) )
 		{
 		if ( ! a->Undelivered(offset, len) )
-			analyzers.QueueRemove(a->Args());
+			analyzers.QueueRemove(a->Tag(), a->Args());
 		}
 
 	if ( FileEventAvailable(file_gap) )

src/file_analysis/File.h

@@ -10,6 +10,7 @@
 
 #include "Conn.h"
 #include "Val.h"
+#include "Tag.h"
 #include "AnalyzerSet.h"
 #include "BroString.h"
 
@@ -94,17 +95,19 @@ public:
 	/**
 	 * Queues attaching an analyzer.  Only one analyzer per type can be attached
 	 * at a time unless the arguments differ.
+	 * @param tag the analyzer tag of the file analyzer to add.
 	 * @param args an \c AnalyzerArgs value representing a file analyzer.
 	 * @return false if analyzer can't be instantiated, else true.
 	 */
-	bool AddAnalyzer(RecordVal* args);
+	bool AddAnalyzer(file_analysis::Tag tag, RecordVal* args);
 
 	/**
 	 * Queues removal of an analyzer.
+	 * @param tag the analyzer tag of the file analyzer to remove.
 	 * @param args an \c AnalyzerArgs value representing a file analyzer.
 	 * @return true if analyzer was active at time of call, else false.
 	 */
-	bool RemoveAnalyzer(const RecordVal* args);
+	bool RemoveAnalyzer(file_analysis::Tag tag, RecordVal* args);
 
 	/**
 	 * Pass in non-sequential data and deliver to attached analyzers.

src/file_analysis/FileTimer.cc

@@ -14,7 +14,7 @@ FileTimer::FileTimer(double t, const string& id, double interval)
 
 void FileTimer::Dispatch(double t, int is_expire)
 	{
-	File* file = file_mgr->Lookup(file_id);
+	File* file = file_mgr->LookupFile(file_id);
 
 	if ( ! file )
 		return;

src/file_analysis/Manager.cc

@@ -18,10 +18,9 @@ TableVal* Manager::disabled = 0;
 string Manager::salt;
 
 Manager::Manager()
+	: plugin::ComponentManager<file_analysis::Tag,
+	                           file_analysis::Component>("Files")
 	{
-	tag_enum_type = new EnumType("Files::Tag");
-	::ID* id = install_ID("Tag", "Files", true, true);
-	add_type(id, tag_enum_type, 0, 0);
 	}
 
 Manager::~Manager()
@@ -35,27 +34,7 @@ void Manager::InitPreScript()
 
 	for ( std::list<Component*>::const_iterator i = analyzers.begin();
 	      i != analyzers.end(); ++i )
-	      RegisterAnalyzerComponent(*i);
+	      RegisterComponent(*i, "ANALYZER_");
-	}
-
-void Manager::RegisterAnalyzerComponent(Component* component)
-	{
-	const char* cname = component->CanonicalName();
-
-	if ( tag_enum_type->Lookup("Files", cname) != -1 )
-		reporter->FatalError("File Analyzer %s defined more than once", cname);
-
-	DBG_LOG(DBG_FILE_ANALYSIS, "Registering analyzer %s (tag %s)",
-			component->Name(), component->Tag().AsString().c_str());
-
-	analyzers_by_name.insert(std::make_pair(cname, component));
-	analyzers_by_tag.insert(std::make_pair(component->Tag(), component));
-	analyzers_by_val.insert(std::make_pair(
-	        component->Tag().AsEnumVal()->InternalInt(), component));
-
-	string id = fmt("ANALYZER_%s", cname);
-	tag_enum_type->AddName("Files", id.c_str(),
-						   component->Tag().AsEnumVal()->InternalInt(), true);
 	}
 
 void Manager::InitPostScript()
@@ -193,7 +172,7 @@ void Manager::SetSize(uint64 size, analyzer::Tag tag, Connection* conn,
 
 bool Manager::SetTimeoutInterval(const string& file_id, double interval) const
 	{
-	File* file = Lookup(file_id);
+	File* file = LookupFile(file_id);
 
 	if ( ! file )
 		return false;
@@ -205,24 +184,26 @@ bool Manager::SetTimeoutInterval(const string& file_id, double interval) const
 	return true;
 	}
 
-bool Manager::AddAnalyzer(const string& file_id, RecordVal* args) const
+bool Manager::AddAnalyzer(const string& file_id, file_analysis::Tag tag,
+                          RecordVal* args) const
 	{
-	File* file = Lookup(file_id);
+	File* file = LookupFile(file_id);
 
 	if ( ! file )
 		return false;
 
-	return file->AddAnalyzer(args);
+	return file->AddAnalyzer(tag, args);
 	}
 
-bool Manager::RemoveAnalyzer(const string& file_id, const RecordVal* args) const
+bool Manager::RemoveAnalyzer(const string& file_id, file_analysis::Tag tag,
+                             RecordVal* args) const
 	{
-	File* file = Lookup(file_id);
+	File* file = LookupFile(file_id);
 
 	if ( ! file )
 		return false;
 
-	return file->RemoveAnalyzer(args);
+	return file->RemoveAnalyzer(tag, args);
 	}
 
 File* Manager::GetFile(const string& file_id, Connection* conn,
@@ -255,7 +236,7 @@ File* Manager::GetFile(const string& file_id, Connection* conn,
 	return rval;
 	}
 
-File* Manager::Lookup(const string& file_id) const
+File* Manager::LookupFile(const string& file_id) const
 	{
 	IDMap::const_iterator it = id_map.find(file_id);
 
@@ -267,7 +248,7 @@ File* Manager::Lookup(const string& file_id) const
 
 void Manager::Timeout(const string& file_id, bool is_terminating)
 	{
-	File* file = Lookup(file_id);
+	File* file = LookupFile(file_id);
 
 	if ( ! file )
 		return;
@@ -366,15 +347,13 @@ bool Manager::IsDisabled(analyzer::Tag tag)
 	return rval;
 	}
 
-Analyzer* Manager::InstantiateAnalyzer(int tag, RecordVal* args, File* f) const
+Analyzer* Manager::InstantiateAnalyzer(Tag tag, RecordVal* args, File* f) const
 	{
-	analyzer_map_by_val::const_iterator it = analyzers_by_val.find(tag);
+	Component* c = Lookup(tag);
 
-	if ( it == analyzers_by_val.end() )
+	if ( ! c )
-		reporter->InternalError("cannot instantiate unknown file analyzer: %d",
+		reporter->InternalError("cannot instantiate unknown file analyzer: %s",
-		                        tag);
+		                        tag.AsString().c_str());
-
-	Component* c = it->second;
 
 	if ( ! c->Factory() )
 		reporter->InternalError("file analyzer %s cannot be instantiated "
@@ -382,14 +361,3 @@ Analyzer* Manager::InstantiateAnalyzer(int tag, RecordVal* args, File* f) const
 
 	return c->Factory()(args, f);
 	}
-
-const char* Manager::GetAnalyzerName(int tag) const
-	{
-	analyzer_map_by_val::const_iterator it = analyzers_by_val.find(tag);
-
-	if ( it == analyzers_by_val.end() )
-		reporter->InternalError("cannot get name of unknown file analyzer: %d",
-		                        tag);
-
-	return it->second->CanonicalName();
-	}

src/file_analysis/Manager.h

@@ -18,7 +18,8 @@
 #include "File.h"
 #include "FileTimer.h"
 #include "Component.h"
-
+#include "Tag.h"
+#include "plugin/ComponentManager.h"
 #include "analyzer/Tag.h"
 
 #include "file_analysis/file_analysis.bif.h"
@@ -28,7 +29,7 @@ namespace file_analysis {
 /**
  * Main entry point for interacting with file analysis.
  */
-class Manager {
+class Manager : public plugin::ComponentManager<Tag, Component> {
 public:
 
 	/**
@@ -177,18 +178,22 @@ public:
 	 * analyzers of a given type can be attached per file identifier at a time
 	 * as long as the arguments differ.
 	 * @param file_id the file identifier/hash.
+	 * @param tag the analyzer tag of the file analyzer to add.
 	 * @param args a \c AnalyzerArgs value which describes a file analyzer.
 	 * @return false if the analyzer failed to be instantiated, else true.
 	 */
-	bool AddAnalyzer(const string& file_id, RecordVal* args) const;
+	bool AddAnalyzer(const string& file_id, file_analysis::Tag tag,
+	                 RecordVal* args) const;
 
 	/**
 	 * Queue removal of an analyzer for a given file identifier.
 	 * @param file_id the file identifier/hash.
+	 * @param tag the analyzer tag of the file analyzer to remove.
 	 * @param args a \c AnalyzerArgs value which describes a file analyzer.
 	 * @return true if the analyzer is active at the time of call, else false.
 	 */
-	bool RemoveAnalyzer(const string& file_id, const RecordVal* args) const;
+	bool RemoveAnalyzer(const string& file_id, file_analysis::Tag tag,
+	                    RecordVal* args) const;
 
 	/**
 	 * Tells whether analysis for a file is active or ignored.
@@ -204,15 +209,7 @@ public:
 	 * @param f The file analzer is to be associated with.
 	 * @return The new analyzer instance or null if tag is invalid.
 	 */
-	Analyzer* InstantiateAnalyzer(int tag, RecordVal* args, File* f) const;
+	Analyzer* InstantiateAnalyzer(Tag tag, RecordVal* args, File* f) const;
-
-	/**
-	 * Translates a script-level file analyzer tag in to corresponding file
-	 * analyzer name.
-	 * @param tag The enum val of a file analyzer.
-	 * @return The human-readable name of the file analyzer.
-	 */
-	const char* GetAnalyzerName(int tag) const;
 
 protected:
 	friend class FileTimer;
@@ -247,7 +244,7 @@ protected:
 	 * @return the File object mapped to \a file_id, or a null pointer if no
 	 *         mapping exists.
 	 */
-	File* Lookup(const string& file_id) const;
+	File* LookupFile(const string& file_id) const;
 
 	/**
 	 * Evaluate timeout policy for a file and remove the File object mapped to
@@ -287,20 +284,10 @@ protected:
 	static bool IsDisabled(analyzer::Tag tag);
 
 private:
-	typedef map<string, Component*> analyzer_map_by_name;
-	typedef map<analyzer::Tag, Component*> analyzer_map_by_tag;
-	typedef map<int, Component*> analyzer_map_by_val;
-
-	void RegisterAnalyzerComponent(Component* component);
 
 	IDMap id_map;	/**< Map file ID to file_analysis::File records. */
 	IDSet ignored;	/**< Ignored files.  Will be finally removed on EOF. */
 	string current_file_id;	/**< Hash of what get_file_handle event sets. */
-	EnumType* tag_enum_type;	/**< File analyzer tag type. */
-
-	analyzer_map_by_name analyzers_by_name;
-	analyzer_map_by_tag analyzers_by_tag;
-	analyzer_map_by_val analyzers_by_val;
 
 	static TableVal* disabled;	/**< Table of disabled analyzers. */
 	static string salt; /**< A salt added to file handles before hashing. */

src/file_analysis/Tag.cc

@@ -0,0 +1,24 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
+#include "Tag.h"
+#include "Manager.h"
+
+using namespace file_analysis;
+
+file_analysis::Tag file_analysis::Tag::Error;
+
+file_analysis::Tag::Tag(type_t type, subtype_t subtype)
+	: ::Tag(file_mgr->GetTagEnumType(), type, subtype)
+	{
+	}
+
+file_analysis::Tag& file_analysis::Tag::operator=(const file_analysis::Tag& other)
+	{
+	::Tag::operator=(other);
+	return *this;
+	}
+
+EnumVal* file_analysis::Tag::AsEnumVal() const
+	{
+	return ::Tag::AsEnumVal(file_mgr->GetTagEnumType());
+	}

src/file_analysis/Tag.h

@@ -0,0 +1,116 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
+#ifndef FILE_ANALYZER_TAG_H
+#define FILE_ANALYZER_TAG_H
+
+#include "config.h"
+#include "util.h"
+#include "../Tag.h"
+#include "plugin/TaggedComponent.h"
+#include "plugin/ComponentManager.h"
+
+class EnumVal;
+
+namespace file_analysis {
+
+class Component;
+
+/**
+ * Class to identify a file analyzer type.
+ *
+ * The script-layer analogue is Files::Tag.
+ */
+class Tag : public ::Tag {
+public:
+	/*
+	 * Copy constructor.
+	 */
+	Tag(const Tag& other) : ::Tag(other) {}
+
+	/**
+	 * Default constructor. This initializes the tag with an error value
+	 * that will make \c operator \c bool return false.
+	 */
+	Tag() : ::Tag() {}
+
+	/**
+	 * Destructor.
+	 */
+	~Tag() {}
+
+	/**
+	 * Returns false if the tag represents an error value rather than a
+	 * legal analyzer type.
+	 * TODO: make this conversion operator "explicit" (C++11) or use a
+	 *       "safe bool" idiom (not necessary if "explicit" is available),
+	 *       otherwise this may allow nonsense/undesired comparison operations.
+	 *
+	 */
+	operator bool() const	{ return *this != Tag(); }
+
+	/**
+	 * Assignment operator.
+	 */
+	Tag& operator=(const Tag& other);
+
+	/**
+	 * Compares two tags for equality.
+	 */
+	bool operator==(const Tag& other) const
+		{
+		return ::Tag::operator==(other);
+		}
+
+	/**
+	 * Compares two tags for inequality.
+	 */
+	bool operator!=(const Tag& other) const
+		{
+		return ::Tag::operator!=(other);
+		}
+
+	/**
+	 * Compares two tags for less-than relationship.
+	 */
+	bool operator<(const Tag& other) const
+		{
+		return ::Tag::operator<(other);
+		}
+
+	/**
+	 * Returns the \c Files::Tag enum that corresponds to this tag.
+	 * The returned value does not have its ref-count increased.
+	 *
+	 * @param etype the script-layer enum type associated with the tag.
+	 */
+	EnumVal* AsEnumVal() const;
+
+	static Tag Error;
+
+protected:
+	friend class plugin::ComponentManager<Tag, Component>;
+	friend class plugin::TaggedComponent<Tag>;
+
+	/**
+	 * Constructor.
+	 *
+	 * @param type The main type. Note that the \a file_analysis::Manager
+	 * manages the value space internally, so noone else should assign
+	 * main types.
+	 *
+	 * @param subtype The sub type, which is left to an analyzer for
+	 * interpretation. By default it's set to zero.
+	 */
+	Tag(type_t type, subtype_t subtype = 0);
+
+	/**
+	 * Constructor.
+	 *
+	 * @param val An enum value of script type \c Files::Tag.
+	 */
+	Tag(EnumVal* val) : ::Tag(val) {}
+};
+
+}
+
+#endif

src/file_analysis/analyzer/data_event/CMakeLists.txt

@@ -4,5 +4,5 @@ include_directories(BEFORE ${CMAKE_CURRENT_SOURCE_DIR}
                            ${CMAKE_CURRENT_BINARY_DIR})
 
 bro_plugin_begin(Bro FileDataEvent)
-bro_plugin_cc(DataEvent.cc Plugin.cc)
+bro_plugin_cc(DataEvent.cc Plugin.cc ../../Analyzer.cc)
 bro_plugin_end()

src/file_analysis/analyzer/data_event/DataEvent.cc

@@ -6,12 +6,15 @@
 #include "EventRegistry.h"
 #include "Event.h"
 #include "util.h"
+#include "file_analysis/Manager.h"
 
 using namespace file_analysis;
 
 DataEvent::DataEvent(RecordVal* args, File* file,
                      EventHandlerPtr ce, EventHandlerPtr se)
-    : file_analysis::Analyzer(args, file), chunk_event(ce), stream_event(se)
+    : file_analysis::Analyzer(file_mgr->GetComponentTag("DATA_EVENT"),
+	                          args, file),
+	chunk_event(ce), stream_event(se)
 	{
 	}
 

src/file_analysis/analyzer/extract/CMakeLists.txt

@@ -4,5 +4,5 @@ include_directories(BEFORE ${CMAKE_CURRENT_SOURCE_DIR}
                            ${CMAKE_CURRENT_BINARY_DIR})
 
 bro_plugin_begin(Bro FileExtract)
-bro_plugin_cc(Extract.cc Plugin.cc)
+bro_plugin_cc(Extract.cc Plugin.cc ../../Analyzer.cc)
 bro_plugin_end()

src/file_analysis/analyzer/extract/Extract.cc

@@ -4,11 +4,13 @@
 
 #include "Extract.h"
 #include "util.h"
+#include "file_analysis/Manager.h"
 
 using namespace file_analysis;
 
 Extract::Extract(RecordVal* args, File* file, const string& arg_filename)
-    : file_analysis::Analyzer(args, file), filename(arg_filename)
+    : file_analysis::Analyzer(file_mgr->GetComponentTag("EXTRACT"), args, file),
+	  filename(arg_filename)
 	{
 	fd = open(filename.c_str(), O_WRONLY | O_CREAT | O_TRUNC, 0666);
 

src/file_analysis/analyzer/hash/CMakeLists.txt

@@ -4,6 +4,6 @@ include_directories(BEFORE ${CMAKE_CURRENT_SOURCE_DIR}
                            ${CMAKE_CURRENT_BINARY_DIR})
 
 bro_plugin_begin(Bro FileHash)
-bro_plugin_cc(Hash.cc Plugin.cc)
+bro_plugin_cc(Hash.cc Plugin.cc ../../Analyzer.cc)
 bro_plugin_bif(events.bif)
 bro_plugin_end()

src/file_analysis/analyzer/hash/Hash.cc

@@ -5,11 +5,12 @@
 #include "Hash.h"
 #include "util.h"
 #include "Event.h"
+#include "file_analysis/Manager.h"
 
 using namespace file_analysis;
 
 Hash::Hash(RecordVal* args, File* file, HashVal* hv, const char* arg_kind)
-	: file_analysis::Analyzer(args, file), hash(hv), fed(false), kind(arg_kind)
+	: file_analysis::Analyzer(file_mgr->GetComponentTag(to_upper(arg_kind).c_str()), args, file), hash(hv), fed(false), kind(arg_kind)
 	{
 	hash->Init();
 	}

src/file_analysis/file_analysis.bif

@@ -16,21 +16,23 @@ function Files::__set_timeout_interval%(file_id: string, t: interval%): bool
 	%}
 
 ## :bro:see:`Files::add_analyzer`.
-function Files::__add_analyzer%(file_id: string, args: any%): bool
+function Files::__add_analyzer%(file_id: string, tag: Files::Tag, args: any%): bool
 	%{
 	using BifType::Record::Files::AnalyzerArgs;
 	RecordVal* rv = args->AsRecordVal()->CoerceTo(AnalyzerArgs);
-	bool result = file_mgr->AddAnalyzer(file_id->CheckString(), rv);
+	bool result = file_mgr->AddAnalyzer(file_id->CheckString(),
+	                                    file_mgr->GetComponentTag(tag), rv);
 	Unref(rv);
 	return new Val(result, TYPE_BOOL);
 	%}
 
 ## :bro:see:`Files::remove_analyzer`.
-function Files::__remove_analyzer%(file_id: string, args: any%): bool
+function Files::__remove_analyzer%(file_id: string, tag: Files::Tag, args: any%): bool
 	%{
 	using BifType::Record::Files::AnalyzerArgs;
 	RecordVal* rv = args->AsRecordVal()->CoerceTo(AnalyzerArgs);
-	bool result = file_mgr->RemoveAnalyzer(file_id->CheckString(), rv);
+	bool result = file_mgr->RemoveAnalyzer(file_id->CheckString(),
+	                                       file_mgr->GetComponentTag(tag) , rv);
 	Unref(rv);
 	return new Val(result, TYPE_BOOL);
 	%}
@@ -45,7 +47,7 @@ function Files::__stop%(file_id: string%): bool
 ## :bro:see:`Files::analyzer_name`.
 function Files::__analyzer_name%(tag: Files::Tag%) : string
 	%{
-	return new StringVal(file_mgr->GetAnalyzerName(tag->InternalInt()));
+	return new StringVal(file_mgr->GetComponentName(tag));
 	%}
 
 module GLOBAL;

src/main.cc

@@ -872,6 +872,7 @@ int main(int argc, char** argv)
 	if ( generate_documentation )
 		{
 		CreateProtoAnalyzerDoc("proto-analyzers.rst");
+		CreateFileAnalyzerDoc("file-analyzers.rst");
 
 		std::list<BroDoc*>::iterator it;
 

src/plugin/ComponentManager.h

@@ -0,0 +1,248 @@
+#ifndef PLUGIN_COMPONENT_MANAGER_H
+#define PLUGIN_COMPONENT_MANAGER_H
+
+#include <map>
+#include <list>
+#include <string>
+
+#include "Type.h"
+#include "ID.h"
+#include "Var.h"
+#include "Val.h"
+#include "Reporter.h"
+
+namespace plugin {
+
+/**
+ * A class that manages tracking of plugin components (e.g. analyzers) and
+ * installs identifiers in the script-layer to identify them by a unique tag,
+ * (a script-layer enum value).
+ *
+ * @tparam T A ::Tag type or derivative.
+ * @tparam C A plugin::TaggedComponent type derivative.
+ */
+template <class T, class C>
+class ComponentManager {
+public:
+
+	/**
+	 * Constructor creates a new enum type called a "Tag" to associate with
+	 * a component.
+	 *
+	 * @param module The script-layer module in which to install the "Tag" ID
+	 * representing an enum type.
+	 */
+	ComponentManager(const string& module);
+
+	/**
+	 * @return The script-layer module in which the component's "Tag" ID lives.
+	 */
+	const char* GetModule() const;
+
+	/**
+	 * @return A list of all registered components.
+	 */
+	list<C*> GetComponents() const;
+
+	/**
+	 * @return The enum type associated with the script-layer "Tag".
+	 */
+	EnumType* GetTagEnumType() const;
+
+	/**
+	 * Get a component name from its tag.
+	 *
+	 * @param tag A component's tag.
+	 * @return The canonical component name.
+	 */
+	const char* GetComponentName(T tag) const;
+
+	/**
+	 * Get a component name from it's enum value.
+	 *
+	 * @param val A component's enum value.
+	 * @return The canonical component name.
+	 */
+	const char* GetComponentName(Val* val) const;
+
+	/**
+	 * Get a component tag from its name.
+	 *
+	 * @param name A component's canonical name.
+	 * @return The component's tag, or a tag representing an error if
+	 * no such component assoicated with the name exists.
+	 */
+	T GetComponentTag(const string& name) const;
+
+	/**
+	 * Get a component tag from its enum value.
+	 *
+	 * @param v A component's enum value.
+	 * @return The component's tag, or a tag representing an error if
+	 * no such component assoicated with the value exists.
+	 */
+	T GetComponentTag(Val* v) const;
+
+protected:
+
+	/**
+	 * Add a component the internal maps used to keep track of it and create
+	 * a script-layer ID for the component's enum value.
+	 *
+	 * @param component A component to track.
+	 * @param prefix The script-layer ID associated with the component's enum
+	 * value will be a concatenation of this prefix and the component's
+	 * canonical name.
+	 */
+	void RegisterComponent(C* component, const string& prefix = "");
+
+	/**
+	 * @param name The canonical name of a component.
+	 * @return The component associated with the name or a null pointer if no
+	 * such component exists.
+	 */
+	C* Lookup(const string& name) const;
+
+	/**
+	 * @param name A component tag.
+	 * @return The component associated with the tag or a null pointer if no
+	 * such component exists.
+	 */
+	C* Lookup(const T& tag) const;
+
+	/**
+	 * @param name A component's enum value.
+	 * @return The component associated with the value or a null pointer if no
+	 * such component exists.
+	 */
+	C* Lookup(EnumVal* val) const;
+
+private:
+
+	string module; /**< Script layer module in which component tags live. */
+	EnumType* tag_enum_type; /**< Enum type of component tags. */
+	map<string, C*> components_by_name;
+	map<T, C*> components_by_tag;
+	map<int, C*> components_by_val;
+};
+
+template <class T, class C>
+ComponentManager<T, C>::ComponentManager(const string& arg_module)
+	: module(arg_module)
+	{
+	tag_enum_type = new EnumType(module + "::Tag");
+	::ID* id = install_ID("Tag", module.c_str(), true, true);
+	add_type(id, tag_enum_type, 0, 0);
+	}
+
+template <class T, class C>
+const char* ComponentManager<T, C>::GetModule() const
+	{
+	return module.c_str();
+	}
+
+template <class T, class C>
+list<C*> ComponentManager<T, C>::GetComponents() const
+	{
+	list<C*> rval;
+	typename map<T, C*>::const_iterator i;
+
+	for ( i = components_by_tag.begin(); i != components_by_tag.end(); ++i )
+	      rval.push_back(i->second);
+
+	return rval;
+	}
+
+template <class T, class C>
+EnumType* ComponentManager<T, C>::GetTagEnumType() const
+	{
+	return tag_enum_type;
+	}
+
+template <class T, class C>
+const char* ComponentManager<T, C>::GetComponentName(T tag) const
+	{
+	static const char* error = "<error>";
+
+	if ( ! tag )
+		return error;
+
+	C* c = Lookup(tag);
+
+	if ( ! c )
+		reporter->InternalError("request for name of unknown component tag %s",
+		                        tag.AsString().c_str());
+
+	return c->CanonicalName();
+	}
+
+template <class T, class C>
+const char* ComponentManager<T, C>::GetComponentName(Val* val) const
+	{
+	return GetComponentName(T(val->AsEnumVal()));
+	}
+
+template <class T, class C>
+T ComponentManager<T, C>::GetComponentTag(const string& name) const
+	{
+	C* c = Lookup(name);
+	return c ? c->Tag() : T();
+	}
+
+template <class T, class C>
+T ComponentManager<T, C>::GetComponentTag(Val* v) const
+	{
+	C* c = Lookup(v->AsEnumVal());
+	return c ? c->Tag() : T();
+	}
+
+template <class T, class C>
+C* ComponentManager<T, C>::Lookup(const string& name) const
+	{
+	typename map<string, C*>::const_iterator i =
+	        components_by_name.find(to_upper(name));
+	return i != components_by_name.end() ? i->second : 0;
+	}
+
+template <class T, class C>
+C* ComponentManager<T, C>::Lookup(const T& tag) const
+	{
+	typename map<T, C*>::const_iterator i = components_by_tag.find(tag);
+	return i != components_by_tag.end() ? i->second : 0;
+	}
+
+template <class T, class C>
+C* ComponentManager<T, C>::Lookup(EnumVal* val) const
+	{
+	typename map<int, C*>::const_iterator i =
+	        components_by_val.find(val->InternalInt());
+	return i != components_by_val.end() ? i->second : 0;
+	}
+
+template <class T, class C>
+void ComponentManager<T, C>::RegisterComponent(C* component,
+                                               const string& prefix)
+	{
+	const char* cname = component->CanonicalName();
+
+	if ( Lookup(cname) )
+		reporter->FatalError("Component '%s::%s' defined more than once",
+		                     module.c_str(), cname);
+
+	DBG_LOG(DBG_PLUGINS, "Registering component %s (tag %s)",
+	        component->Name(), component->Tag().AsString().c_str());
+
+	components_by_name.insert(std::make_pair(cname, component));
+	components_by_tag.insert(std::make_pair(component->Tag(), component));
+	components_by_val.insert(std::make_pair(
+	        component->Tag().AsEnumVal()->InternalInt(), component));
+
+	// Install an identfier for enum value
+	string id = fmt("%s%s", prefix.c_str(), cname);
+	tag_enum_type->AddName(module, id.c_str(),
+	                       component->Tag().AsEnumVal()->InternalInt(), true);
+	}
+
+} // namespace plugin
+
+#endif

src/plugin/TaggedComponent.h

@@ -0,0 +1,85 @@
+#ifndef PLUGIN_TAGGED_COMPONENT_H
+#define PLUGIN_TAGGED_COMPONENT_H
+
+namespace plugin {
+
+/**
+ * A class which has a tag of a given type associated with it.
+ *
+ * @tparam T A ::Tag type or derivative.
+ */
+template <class T>
+class TaggedComponent {
+public:
+
+	/**
+	 * Constructor creates a unique tag value for this component.
+	 *
+	 * @param subtype A subtype associated with this component that
+	 * further distinguishes it. The subtype will be integrated into
+	 * the Tag that the manager associates with this component,
+	 * and component instances can accordingly access it via Tag().
+	 * If not used, leave at zero.
+	 */
+	TaggedComponent(typename T::subtype_t subtype = 0);
+
+	/**
+	 * Copy constructor.
+	 *
+	 * @param other Another component from which to copy its tag value.
+	 */
+	TaggedComponent(const TaggedComponent& other);
+
+	/**
+	 * Assignment operator.
+	 *
+	 * @param other A component to assign.
+	 * @return The assigned object.
+	 */
+	TaggedComponent& operator=(const TaggedComponent& other);
+
+	/**
+	 * @return The component's tag.
+	 */
+	T Tag() const;
+
+private:
+
+	T tag; /**< The automatically assigned analyzer tag. */
+	static typename T::type_t type_counter; /**< Used to generate globally
+	                                             unique tags. */
+};
+
+template <class T>
+TaggedComponent<T>::TaggedComponent(typename T::subtype_t subtype)
+	{
+	tag = T(++type_counter, subtype);
+	}
+
+template <class T>
+TaggedComponent<T>::TaggedComponent(const TaggedComponent<T>& other)
+	{
+	tag = other.tag;
+	}
+
+template <class T>
+TaggedComponent<T>&
+TaggedComponent<T>::operator =(const TaggedComponent<T>& other)
+	{
+	if ( &other != this )
+		tag = other.tag;
+
+	return *this;
+	}
+
+template <class T>
+T TaggedComponent<T>::Tag() const
+	{
+	return tag;
+	}
+
+template <class T> typename T::type_t TaggedComponent<T>::type_counter(0);
+
+} // namespace plugin
+
+#endif

testing/btest/Baseline/coverage.default-load-baseline/canonified_loaded_scripts.log

@@ -161,6 +161,7 @@ scripts/base/init-default.bro
     scripts/base/protocols/dns/main.bro
   scripts/base/protocols/ftp/__load__.bro
     scripts/base/protocols/ftp/utils-commands.bro
+    scripts/base/protocols/ftp/info.bro
     scripts/base/protocols/ftp/main.bro
       scripts/base/protocols/ftp/utils.bro
     scripts/base/protocols/ftp/files.bro