Merge remote-tracking branch 'origin/master' into topic/seth/file-entropy

# Conflicts:
#	scripts/test-all-policy.bro
#	testing/btest/Baseline/coverage.default-load-baseline/canonified_loaded_scripts.log

.gitmodules

@@ -22,3 +22,6 @@
 [submodule "aux/plugins"]
 	path = aux/plugins
 	url = git://git.bro.org/bro-plugins
+[submodule "aux/broker"]
+	path = aux/broker
+	url = git://git.bro.org/broker

CMakeLists.txt

@@ -61,7 +61,7 @@ if (NOT SED_EXE)
     endif ()
 endif ()
 
-FindRequiredPackage(Perl)
+FindRequiredPackage(PythonInterp)
 FindRequiredPackage(FLEX)
 FindRequiredPackage(BISON)
 FindRequiredPackage(PCAP)
@@ -88,7 +88,7 @@ endif ()
 
 include_directories(BEFORE
                     ${PCAP_INCLUDE_DIR}
-                    ${OpenSSL_INCLUDE_DIR}
+                    ${OPENSSL_INCLUDE_DIR}
                     ${BIND_INCLUDE_DIR}
                     ${BinPAC_INCLUDE_DIR}
                     ${ZLIB_INCLUDE_DIR}
@@ -113,7 +113,7 @@ if (NOT DISABLE_PERFTOOLS)
    find_package(GooglePerftools)
 endif ()
 
-if (GOOGLEPERFTOOLS_FOUND)
+if (GOOGLEPERFTOOLS_FOUND OR TCMALLOC_FOUND)
     set(HAVE_PERFTOOLS true)
     # Non-Linux systems may not be well-supported by gperftools, so
     # require explicit request from user to enable it in that case.
@@ -141,7 +141,7 @@ endif ()
 set(brodeps
     ${BinPAC_LIBRARY}
     ${PCAP_LIBRARY}
-    ${OpenSSL_LIBRARIES}
+    ${OPENSSL_LIBRARIES}
     ${BIND_LIBRARY}
     ${ZLIB_LIBRARY}
     ${JEMALLOC_LIBRARIES}
@@ -165,18 +165,26 @@ include(PCAPTests)
 include(OpenSSLTests)
 include(CheckNameserCompat)
 include(GetArchitecture)
+include(RequireCXX11)
 
 # Tell the plugin code that we're building as part of the main tree.
 set(BRO_PLUGIN_INTERNAL_BUILD true CACHE INTERNAL "" FORCE)
 
-configure_file(${CMAKE_CURRENT_SOURCE_DIR}/config.h.in
+configure_file(${CMAKE_CURRENT_SOURCE_DIR}/bro-config.h.in
-               ${CMAKE_CURRENT_BINARY_DIR}/config.h)
+               ${CMAKE_CURRENT_BINARY_DIR}/bro-config.h)
 
 include_directories(${CMAKE_CURRENT_BINARY_DIR})
 
 ########################################################################
 ## Recurse on sub-directories
 
+if ( ENABLE_BROKER )
+    add_subdirectory(aux/broker)
+    set(brodeps ${brodeps} broker)
+    add_definitions(-DENABLE_BROKER)
+    include_directories(BEFORE ${CMAKE_CURRENT_SOURCE_DIR}/aux/broker)
+endif ()
+
 add_subdirectory(src)
 add_subdirectory(scripts)
 add_subdirectory(doc)
@@ -224,6 +232,8 @@ message(
     "\nCXXFLAGS:          ${CMAKE_CXX_FLAGS} ${CMAKE_CXX_FLAGS_${BuildType}}"
     "\nCPP:               ${CMAKE_CXX_COMPILER}"
     "\n"
+    "\nBroker:            ${ENABLE_BROKER}"
+    "\nBroker Python:     ${BROKER_PYTHON_BINDINGS}"
     "\nBroccoli:          ${INSTALL_BROCCOLI}"
     "\nBroctl:            ${INSTALL_BROCTL}"
     "\nAux. Tools:        ${INSTALL_AUX_TOOLS}"

COPYING

@@ -1,4 +1,4 @@
-Copyright (c) 1995-2013, The Regents of the University of California
+Copyright (c) 1995-2015, The Regents of the University of California
 through the Lawrence Berkeley National Laboratory and the
 International Computer Science Institute. All rights reserved.
 

INSTALL

@@ -1,3 +0,0 @@
-
-See doc/install/install.rst for installation instructions.
-

INSTALL

@@ -0,0 +1 @@
+doc/install/install.rst

Makefile

@@ -51,13 +51,15 @@ distclean:
 	$(MAKE) -C testing $@
 
 test:
-	@( cd testing && make )
+	-@( cd testing && make )
 
-test-all: test
+test-aux:
-	test -d aux/broctl && ( cd aux/broctl && make test-all )
+	-test -d aux/broctl && ( cd aux/broctl && make test-all )
-	test -d aux/btest  && ( cd aux/btest && make test )
+	-test -d aux/btest  && ( cd aux/btest && make test )
-	test -d aux/bro-aux && ( cd aux/bro-aux && make test )
+	-test -d aux/bro-aux && ( cd aux/bro-aux && make test )
-	test -d aux/plugins && ( cd aux/plugins && make test-all )
+	-test -d aux/plugins && ( cd aux/plugins && make test-all )
+
+test-all: test test-aux
 
 configured:
 	@test -d $(BUILD) || ( echo "Error: No build/ directory found. Did you run configure?" && exit 1 )

NEWS

@@ -4,11 +4,100 @@ release. For an exhaustive list of changes, see the ``CHANGES`` file
 (note that submodules, such as BroControl and Broccoli, come with
 their own ``CHANGES``.)
 
-Bro 2.4 (in progress)
+Bro 2.5 (in progress)
 =====================
 
-Dependencies
+New Dependencies
-------------
+----------------
+
+- Bro now requires a compiler with C++11 support for building the
+  source code.
+
+- Bro now requires the C++ Actor Framework, CAF, which must be
+  installed first. See http://actor-framework.org.
+
+- Bro now requires Python instead of Perl to compile the source code.
+
+- The pcap buffer size can set through the new option Pcap::bufsize.
+
+New Functionality
+-----------------
+
+- Bro now includes the NetControl framework. The framework allows for easy
+  interaction of Bro with hard- and software switches, firewalls, etc.
+
+- Bro now supports the Radiotap header for 802.11 frames.
+
+- Bro now tracks VLAN IDs. To record them inside the connection log,
+  load protocols/conn/vlan-logging.bro.
+
+- A new per-packet event raw_packet() provides access to layer 2
+  information. Use with care, generating events per packet is
+  expensive.
+
+- A new built-in function, decode_base64_conn() for Base64 decoding.
+  It works like decode_base64() but receives an additional connection
+  argument that will be used for decoding errors into weird.log
+  (instead of reporter.log).
+
+- Two new built-in functions for handling set[subnet] and table[subnet]:
+
+  - check_subnet(subnet, table) checks if a specific subnet is a member
+    of a set/table. This is different from the "in" operator, which always
+    performs a longest prefix match.
+
+  - matching_subnets(subnet, table) returns all subnets of the set or table
+    that contain the given subnet.
+
+- Several built-in functions for handling IP addresses and subnets were added:
+
+  - is_v4_subnet(subnet) checks whether a subnet specification is IPv4.
+
+  - is_v6_subnet(subnet) checks whether a subnet specification is IPv6.
+
+  - addr_to_subnet(addr) converts an IP address to a /32 subnet.
+
+  - subnet_to_addr(subnet) returns the IP address part of a subnet.
+
+  - subnet_width(subnet) returns the width of a subnet.
+
+- The IRC analyzer now recognizes StartTLS sessions and enable the SSL
+  analyzer for them.
+
+- New Bro plugins in aux/plugins:
+
+    - af_packet: Native AF_PACKET support.
+    - kafka : Log writer interfacing to Kafka.
+    - myricom: Native Myricom SNF v3 support.
+    - pf_ring: Native PF_RING support.
+    - redis: An experimental log writer for Redis.
+    - tcprs: An TCP-level analyzer detecting retransmissions, reordering, and more.
+
+Changed Functionality
+---------------------
+
+- ``SSH::skip_processing_after_detection`` was removed. The functionality was
+  replaced by ``SSH::disable_analyzer_after_detection``.
+
+- Some script-level identifier have changed their names:
+
+      snaplen                  -> Pcap::snaplen
+      precompile_pcap_filter() -> Pcap::precompile_pcap_filter()
+      install_pcap_filter()    -> Pcap::install_pcap_filter()
+      pcap_error()             -> Pcap::pcap_error()
+
+
+Deprecated Functionality
+------------------------
+
+    - The built-in functions decode_base64_custom() and
+      encode_base64_custom() are no longer needed and will be removed
+      in the future. Their functionality is now provided directly by
+      decode_base64() and encode_base64(), which take an optional
+      parameter to change the Base64 alphabet.
+
+Bro 2.4
+=======
 
 New Functionality
 -----------------
@@ -16,20 +105,51 @@ New Functionality
 - Bro now has support for external plugins that can extend its core
   functionality, like protocol/file analysis, via shared libraries.
   Plugins can be developed and distributed externally, and will be
-  pulled in dynamically at startup. Currently, a plugin can provide
+  pulled in dynamically at startup (the environment variables
-  custom protocol analyzers, file analyzers, log writers[TODO], input
+  BRO_PLUGIN_PATH and BRO_PLUGIN_ACTIVATE can be used to specify the
-  readers[TODO], packet sources[TODO], and new built-in functions. A
+  locations and names of plugins to activate). Currently, a plugin
-  plugin can furthermore hook into Bro's processing a number of places
+  can provide custom protocol analyzers, file analyzers, log writers,
-  to add custom logic.
+  input readers, packet sources and dumpers, and new built-in functions.
+  A plugin can furthermore hook into Bro's processing at a number of
+  places to add custom logic.
 
   See https://www.bro.org/sphinx-git/devel/plugins.html for more
   information on writing plugins.
 
-- Bro now has supoprt for the MySQL wire protocol. Activity gets
+- Bro now has support for the MySQL wire protocol. Activity gets
   logged into mysql.log.
 
+- Bro now parses DTLS traffic. Activity gets logged into ssl.log.
+
+- Bro now has support for the Kerberos KRB5 protocol over TCP and
+  UDP. Activity gets logged into kerberos.log.
+
+- Bro now has an RDP analyzer. Activity gets logged into rdp.log.
+
+- Bro now has a file analyzer for Portable Executables. Activity gets
+  logged into pe.log.
+
+- Bro now has support for the SIP protocol over UDP. Activity gets
+  logged into sip.log.
+
+- Bro now features a completely rewritten, enhanced SSH analyzer.  The
+  new analyzer is able to determine if logins failed or succeeded in
+  most circumstances, logs a lot more more information about SSH
+  sessions, supports v1, and introduces the intelligence type
+  ``Intel::PUBKEY_HASH`` and location ``SSH::IN_SERVER_HOST_KEY``. The
+  analayzer also generates a set of additional events
+  (``ssh_auth_successful``, ``ssh_auth_failed``, ``ssh_capabilities``,
+  ``ssh2_server_host_key``, ``ssh1_server_host_key``,
+  ``ssh_encrypted_packet``, ``ssh2_dh_server_params``,
+  ``ssh2_gss_error``, ``ssh2_ecc_key``). See next section for
+  incompatible SSH changes.
+
 - Bro's file analysis now supports reassembly of files that are not
-  transferred/seen sequentially.
+  transferred/seen sequentially.  The default file reassembly buffer
+  size is set with the ``Files::reassembly_buffer_size`` variable.
+
+- Bro's file type identification has been greatly improved (new file types,
+  bug fixes, and performance improvements).
 
 - Bro's scripting language now has a ``while`` statement::
 
@@ -39,6 +159,70 @@ New Functionality
   ``next`` and ``break`` can be used inside the loop's body just like
   with ``for`` loops.
 
+- Bro now integrates Broker, a new communication library. See
+  aux/broker/README for more information on Broker, and
+  doc/frameworks/broker.rst for the corresponding Bro script API.
+
+  With Broker, Bro has the similar capabilities of exchanging events and
+  logs with remote peers (either another Bro process or some other
+  application that uses Broker).  It also includes a key-value store
+  API that can be used to share state between peers and optionally
+  allow data to persist on disk for longer-term storage.
+
+  Broker support is by default off for now; it can be enabled at
+  configure time with --enable-broker. It requires CAF version 0.13+
+  (https://github.com/actor-framework/actor-framework) as well as a
+  C++11 compiler (e.g. GCC 4.8+ or Clang 3.3+).
+
+  Broker will become a mandatory dependency in future Bro versions and
+  replace the current communication and serialization system.
+
+- Add --enable-c++11 configure flag to compile Bro's source code in
+  C++11 mode with a corresponding compiler. Note that 2.4 will be the
+  last version of Bro that compiles without C++11 support.
+
+- The SSL analysis now alerts when encountering SSL connections with
+  old protocol versions or unsafe cipher suites. It also gained
+  extended reporting of weak keys, caching of already validated
+  certificates, and full support for TLS record defragmentation. SSL generally
+  became much more robust and added several fields to ssl.log (while
+  removing some others).
+
+- A new icmp_sent_payload event provides access to ICMP payload.
+
+- The input framework's raw reader now supports seeking by adding an
+  option "offset" to the config map. Positive offsets are interpreted
+  to be from the beginning of the file, negative from the end of the
+  file (-1 is end of file).
+
+- One can now raise events when a connection crosses a given size
+  threshold in terms of packets or bytes. The primary API for that
+  functionality is in base/protocols/conn/thresholds.bro.
+
+- There is a new command-line option -Q/--time that prints Bro's execution
+  time and memory usage to stderr.
+
+- BroControl now has a new command "deploy" which is equivalent to running
+  the "check", "install", "stop", and "start" commands (in that order).
+
+- BroControl now has a new option "StatusCmdShowAll" that controls whether
+  or not the broctl "status" command gathers all of the status information.
+  This option can be used to make the "status" command run significantly
+  faster (in this case, the "Peers" column will not be shown in the output).
+
+- BroControl now has a new option "StatsLogEnable" that controls whether
+  or not broctl will record information to the "stats.log" file.  This option
+  can be used to make the "broctl cron" command run slightly faster (in this
+  case, "broctl cron" will also no longer send email about not seeing any
+  packets on the monitoring interfaces).
+
+- BroControl now has a new option "MailHostUpDown" which controls whether or
+  not the "broctl cron" command will send email when it notices that a host
+  in the cluster is up or down.
+
+- BroControl now has a new option "CommandTimeout" which specifies the number
+  of seconds to wait for a command that broctl ran to return results.
+
 Changed Functionality
 ---------------------
 
@@ -47,9 +231,17 @@ Changed Functionality
 - File analysis
 
     * Removed ``fa_file`` record's ``mime_type`` and ``mime_types``
-      fields.  The events ``file_mime_type`` and ``file_mime_types``
+      fields.  The event ``file_sniff`` has been added which provides
-      have been added which contain the same information.  The
+      the same information.  The ``mime_type`` field of ``Files::Info``
-      ``mime_type`` field of ``Files::Info`` also still has this info.
+      also still has this info.
+
+    * The earliest point that new mime type information is available is
+      in the ``file_sniff`` event which comes after the ``file_new`` and
+      ``file_over_new_connection`` events.  Scripts which inspected mime
+      type info within those events will need to be adapted.  (Note: for
+      users that worked w/ versions of Bro from git, for a while there was
+      also an event called ``file_mime_type`` which is now replaced with
+      the ``file_sniff`` event).
 
     * Removed ``Files::add_analyzers_for_mime_type`` function.
 
@@ -58,15 +250,83 @@ Changed Functionality
       reassembly for non-sequential files, "offset" can be obtained
       with other information already available -- adding together
       ``seen_bytes`` and ``missed_bytes`` fields of the ``fa_file``
-      record gives the how many bytes have been written so far (i.e.
+      record gives how many bytes have been written so far (i.e.
       the "offset").
 
-- has_valid_octets: now uses a string_vec parameter instead of
+- The SSH changes come with a few incompatibilities. The following
+  events have been renamed:
+
+    * ``SSH::heuristic_failed_login`` to ``ssh_auth_failed``
+    * ``SSH::heuristic_successful_login`` to ``ssh_auth_successful``
+
+  The ``SSH::Info`` status field has been removed and replaced with
+  the ``auth_success`` field.  This field has been changed from a
+  string that was previously ``success``, ``failure`` or
+  ``undetermined`` to a boolean. a boolean that is ``T``, ``F``, or
+  unset.
+
+- The has_valid_octets function now uses a string_vec parameter instead of
   string_array.
 
 - conn.log gained a new field local_resp that works like local_orig,
   just for the responder address of the connection.
 
+- GRE tunnels are now identified as ``Tunnel::GRE`` instead of
+  ``Tunnel::IP``.
+
+- The default name for extracted files changed from extract-protocol-id
+  to extract-timestamp-protocol-id.
+
+- The weird named "unmatched_HTTP_reply" has been removed since it can
+  be detected at the script-layer and is handled correctly by the
+  default HTTP scripts.
+
+- When adding a logging filter to a stream, the filter can now inherit
+  a default ``path`` field from the associated ``Log::Stream`` record.
+
+- When adding a logging filter to a stream, the
+  ``Log::default_path_func`` is now only automatically added to the
+  filter if it has neither a ``path`` nor a ``path_func`` already
+  explicitly set.  Before, the default path function would always be set
+  for all filters which didn't specify their own ``path_func``.
+
+- BroControl now establishes only one ssh connection from the manager to
+  each remote host in a cluster configuration (previously, there would be
+  one ssh connection per remote Bro process).
+
+- BroControl now uses SQLite to record state information instead of a
+  plain text file (the file "spool/broctl.dat" is no longer used).
+  On FreeBSD, this means that there is a new dependency on the package
+  "py27-sqlite3".
+
+- BroControl now records the expected running state of each Bro node right
+  before each start or stop.  The "broctl cron" command uses this info to
+  either start or stop Bro nodes as needed so that the actual state matches
+  the expected state (previously, "broctl cron" could only start nodes in
+  the "crashed" state, and could never stop a node).
+
+- BroControl now sends all normal command output (i.e., not error messages)
+  to stdout.  Error messages are still sent to stderr, however.
+
+- The capability of processing NetFlow input has been removed for the
+  time being.  Therefore, the -y/--flowfile and -Y/--netflow command-line
+  options have been removed, and the netflow_v5_header and netflow_v5_record
+  events have been removed.
+
+- The -D/--dfa-size command-line option has been removed.
+
+- The -L/--rule-benchmark command-line option has been removed.
+
+- The -O/--optimize command-line option has been removed.
+
+- The deprecated fields "hot" and "addl" have been removed from the
+  connection record. Likewise, the functions append_addl() and
+  append_addl_marker() have been removed.
+
+- Log files now escape non-printable characters consistently as "\xXX'.
+  Furthermore, backslashes are escaped as "\\", making the
+  representation fully reversible.
+
 Deprecated Functionality
 ------------------------
 
@@ -76,7 +336,7 @@ Deprecated Functionality
   concatenation/extraction functions. Note that the new functions use
   0-based indexing, rather than 1-based.
 
-  The full list of now deprecation functions is:
+  The full list of now deprecated functions is:
 
     * split: use split_string instead.
 

README.rst

@@ -0,0 +1 @@
+README

VERSION

@@ -1 +1 @@
-2.3-451
+2.4-406

aux/binpac

@@ -1 +1 @@
-Subproject commit 33cb1f8e6bf2e33c2773e86b157e1f343ee85dc6
+Subproject commit 424d40c1e8d5888311b50c0e5a9dfc9c5f818b66

aux/bro-aux

@@ -1 +1 @@
-Subproject commit c9d340847c668590a450f1881e6e3d763abe1138
+Subproject commit 105dfe4ad6c4ae4563b21cb0466ee350f0af0d43

aux/broccoli

@@ -1 +1 @@
-Subproject commit 1d55a0a84c5b1d0aa1727829300b388c92f92daa
+Subproject commit 6ded82da498d805def6aa129cd7691d3b7287c37

aux/broctl

@@ -1 +1 @@
-Subproject commit 76f99ea52c3e021cade3d03eda7865d4f4d1793e
+Subproject commit 583f3a3ff1847cf96a87f865d5cf0f36fae9dd67

aux/broker

@@ -0,0 +1 @@
+Subproject commit fe35cde8f07ff7cf6decd2fb761cffc32e763d2d

aux/btest

@@ -1 +1 @@
-Subproject commit 93d4989ed1537e4d143cf09d44077159f869a4b2
+Subproject commit 4bea8fa948be2bc86ff92399137131bc1c029b08

aux/plugins

@@ -1 +1 @@
-Subproject commit 71d820e9d8ca753fea8fb34ea3987993b28d79e4
+Subproject commit ab61be0c4f128c976f72dfa5a09a87cd842f387a

cmake

@@ -1 +1 @@
-Subproject commit ff08be5aa1b8eaadbe2775cbc11b499c5f93349e
+Subproject commit 537e45afe1006a10f73847fab5f13d28ce43fc4d

configure

@@ -41,11 +41,13 @@ Usage: $0 [OPTION]... [VAR=VALUE]...
     --enable-perftools-debug use Google's perftools for debugging
     --enable-jemalloc      link against jemalloc
     --enable-ruby          build ruby bindings for broccoli (deprecated)
+    --disable-broker       disable use of the Broker communication library
     --disable-broccoli     don't build or install the Broccoli library
     --disable-broctl       don't install Broctl
     --disable-auxtools     don't build or install auxiliary tools
     --disable-perftools    don't try to build with Google Perftools
     --disable-python       don't try to build python bindings for broccoli
+    --disable-pybroker     don't try to build python bindings for broker
 
   Required Packages in Non-Standard Locations:
     --with-openssl=PATH    path to OpenSSL install root
@@ -54,19 +56,22 @@ Usage: $0 [OPTION]... [VAR=VALUE]...
     --with-binpac=PATH     path to BinPAC install root
     --with-flex=PATH       path to flex executable
     --with-bison=PATH      path to bison executable
-    --with-perl=PATH       path to perl executable
+    --with-python=PATH     path to Python executable
+    --with-libcaf=PATH     path to C++ Actor Framework installation
+                           (a required Broker dependency)
 
   Optional Packages in Non-Standard Locations:
     --with-geoip=PATH      path to the libGeoIP install root
     --with-perftools=PATH  path to Google Perftools install root
     --with-jemalloc=PATH   path to jemalloc install root
-    --with-python=PATH     path to Python interpreter
     --with-python-lib=PATH path to libpython
     --with-python-inc=PATH path to Python headers
     --with-ruby=PATH       path to ruby interpreter
     --with-ruby-lib=PATH   path to ruby library
     --with-ruby-inc=PATH   path to ruby headers
     --with-swig=PATH       path to SWIG executable
+    --with-rocksdb=PATH    path to RocksDB installation
+                           (an optional Broker dependency)
 
   Packaging Options (for developers):
     --binary-package       toggle special logic for binary packaging
@@ -88,7 +93,7 @@ Usage: $0 [OPTION]... [VAR=VALUE]...
 sourcedir="$( cd "$( dirname "$0" )" && pwd )"
 
 # Function to append a CMake cache entry definition to the
-# CMakeCacheEntries variable
+# CMakeCacheEntries variable.
 #   $1 is the cache entry variable name
 #   $2 is the cache entry variable type
 #   $3 is the cache entry variable value
@@ -96,6 +101,17 @@ append_cache_entry () {
     CMakeCacheEntries="$CMakeCacheEntries -D $1:$2=$3"
 }
 
+# Function to remove a CMake cache entry definition from the
+# CMakeCacheEntries variable
+#   $1 is the cache entry variable name
+remove_cache_entry () {
+    CMakeCacheEntries="$CMakeCacheEntries -U $1"
+
+    # Even with -U, cmake still warns by default if
+    # added previously with -D.
+    CMakeCacheEntries="$CMakeCacheEntries --no-warn-unused-cli"
+}
+
 # set defaults
 builddir=build
 prefix=/usr/local/bro
@@ -105,10 +121,13 @@ append_cache_entry BRO_ROOT_DIR         PATH   $prefix
 append_cache_entry PY_MOD_INSTALL_DIR   PATH   $prefix/lib/broctl
 append_cache_entry BRO_SCRIPT_INSTALL_PATH STRING $prefix/share/bro
 append_cache_entry BRO_ETC_INSTALL_DIR  PATH   $prefix/etc
+append_cache_entry BROKER_PYTHON_HOME   PATH   $prefix
+append_cache_entry BROKER_PYTHON_BINDINGS BOOL false
 append_cache_entry ENABLE_DEBUG         BOOL   false
 append_cache_entry ENABLE_PERFTOOLS     BOOL   false
 append_cache_entry ENABLE_PERFTOOLS_DEBUG BOOL false
-append_cache_entry ENABLE_JEMALLOC      BOOL false
+append_cache_entry ENABLE_JEMALLOC      BOOL   false
+append_cache_entry ENABLE_BROKER        BOOL   true
 append_cache_entry BinPAC_SKIP_INSTALL  BOOL   true
 append_cache_entry BUILD_SHARED_LIBS    BOOL   true
 append_cache_entry INSTALL_AUX_TOOLS    BOOL   true
@@ -142,6 +161,10 @@ while [ $# -ne 0 ]; do
             append_cache_entry CMAKE_INSTALL_PREFIX PATH   $optarg
             append_cache_entry BRO_ROOT_DIR         PATH   $optarg
             append_cache_entry PY_MOD_INSTALL_DIR   PATH   $optarg/lib/broctl
+
+            if [ -z "$user_disabled_broker" ]; then
+                append_cache_entry BROKER_PYTHON_HOME   PATH   $optarg
+            fi
             ;;
         --scriptdir=*)
             append_cache_entry BRO_SCRIPT_INSTALL_PATH STRING $optarg
@@ -176,6 +199,11 @@ while [ $# -ne 0 ]; do
         --enable-jemalloc)
             append_cache_entry ENABLE_JEMALLOC     BOOL   true
             ;;
+        --disable-broker)
+            append_cache_entry ENABLE_BROKER        BOOL   false
+            remove_cache_entry BROKER_PYTHON_HOME
+            user_disabled_broker="true"
+            ;;
         --disable-broccoli)
             append_cache_entry INSTALL_BROCCOLI     BOOL   false
             ;;
@@ -191,11 +219,14 @@ while [ $# -ne 0 ]; do
         --disable-python)
             append_cache_entry DISABLE_PYTHON_BINDINGS     BOOL   true
             ;;
+        --disable-pybroker)
+            append_cache_entry DISABLE_PYBROKER     BOOL   true
+            ;;
         --enable-ruby)
             append_cache_entry DISABLE_RUBY_BINDINGS     BOOL   false
             ;;
         --with-openssl=*)
-            append_cache_entry OpenSSL_ROOT_DIR PATH $optarg
+            append_cache_entry OPENSSL_ROOT_DIR PATH $optarg
             ;;
         --with-bind=*)
             append_cache_entry BIND_ROOT_DIR PATH $optarg
@@ -212,9 +243,6 @@ while [ $# -ne 0 ]; do
         --with-bison=*)
             append_cache_entry BISON_EXECUTABLE PATH $optarg
             ;;
-        --with-perl=*)
-            append_cache_entry PERL_EXECUTABLE PATH $optarg
-            ;;
         --with-geoip=*)
             append_cache_entry LibGeoIP_ROOT_DIR PATH $optarg
             ;;
@@ -248,6 +276,12 @@ while [ $# -ne 0 ]; do
         --with-swig=*)
             append_cache_entry SWIG_EXECUTABLE      PATH    $optarg
             ;;
+        --with-libcaf=*)
+            append_cache_entry LIBCAF_ROOT_DIR      PATH   $optarg
+            ;;
+        --with-rocksdb=*)
+            append_cache_entry ROCKSDB_ROOT_DIR     PATH   $optarg
+            ;;
         --binary-package)
             append_cache_entry BINARY_PACKAGING_MODE BOOL true
             ;;

doc/components/bro-plugins/README.rst

@@ -0,0 +1 @@
+../../../aux/plugins/README

doc/components/bro-plugins/af_packet/README.rst

@@ -0,0 +1 @@
+../../../../aux/plugins/af_packet/README

doc/components/bro-plugins/elasticsearch/README.rst

@@ -0,0 +1 @@
+../../../../aux/plugins/elasticsearch/README

doc/components/bro-plugins/myricom/README.rst

@@ -0,0 +1 @@
+../../../../aux/plugins/myricom/README

doc/components/bro-plugins/netmap/README.rst

@@ -0,0 +1 @@
+../../../../aux/plugins/netmap/README

doc/components/bro-plugins/pf_ring/README.rst

@@ -0,0 +1 @@
+../../../../aux/plugins/pf_ring/README

doc/components/bro-plugins/redis/README.rst

@@ -0,0 +1 @@
+../../../../aux/plugins/redis/README

doc/components/bro-plugins/tcprs/README.rst

@@ -0,0 +1 @@
+../../../../aux/plugins/tcprs/README

doc/components/broker/README.rst

@@ -0,0 +1 @@
+../../../aux/broker/README

doc/components/broker/broker-manual.rst

@@ -0,0 +1 @@
+../../../aux/broker/broker-manual.rst

doc/components/index.rst

@@ -17,8 +17,11 @@ current, independent component releases.
    Broccoli - User Manual <broccoli/broccoli-manual>
    Broccoli Python Bindings <broccoli-python/README>
    Broccoli Ruby Bindings <broccoli-ruby/README>
+   Broker - Bro's (New) Messaging Library (README) <broker/README>
+   Broker - User Manual <broker/broker-manual.rst>
    BroControl - Interactive Bro management shell <broctl/README>
    Bro-Aux - Small auxiliary tools for Bro <bro-aux/README>
+   Bro-Plugins - A collection of plugins for Bro <bro-plugins/README>
    BTest - A unit testing framework <btest/README>
    Capstats - Command-line packet statistic tool <capstats/README>
    PySubnetTree - Python module for CIDR lookups<pysubnettree/README>

doc/conf.py.in

@@ -66,7 +66,7 @@ master_doc = 'index'
 
 # General information about the project.
 project = u'Bro'
-copyright = u'2013, The Bro Project'
+copyright = u'2016, The Bro Project'
 
 # The version info for the project you're documenting, acts as replacement for
 # |version| and |release|, also used in various other places throughout the

doc/devel/plugins.rst

@@ -3,7 +3,7 @@
 Writing Bro Plugins
 ===================
 
-Bro internally provides plugin API that enables extending
+Bro internally provides a plugin API that enables extending
 the system dynamically, without modifying the core code base. That way
 custom code remains self-contained and can be maintained, compiled,
 and installed independently. Currently, plugins can add the following
@@ -32,7 +32,7 @@ Quick Start
 ===========
 
 Writing a basic plugin is quite straight-forward as long as one
-follows a few conventions. In the following we walk a simple example
+follows a few conventions. In the following we create a simple example
 plugin that adds a new built-in function (bif) to Bro: we'll add 
 ``rot13(s: string) : string``, a function that rotates every character
 in a string by 13 places.
@@ -81,7 +81,7 @@ The syntax of this file is just like any other ``*.bif`` file; we
 won't go into it here.
 
 Now we can already compile our plugin, we just need to tell the
-configure script that ``init-plugin`` put in place where the Bro
+configure script (that ``init-plugin`` created) where the Bro
 source tree is located (Bro needs to have been built there first)::
 
     # cd rot13-plugin
@@ -99,7 +99,7 @@ option::
     # export BRO_PLUGIN_PATH=/path/to/rot13-plugin/build
     # bro -N
     [...]
-    Plugin: Demo::Rot13 - <Insert brief description of plugin> (dynamic, version 1)
+    Demo::Rot13 - <Insert description> (dynamic, version 0.1)
     [...]
 
 That looks quite good, except for the dummy description that we should
@@ -108,28 +108,30 @@ is about.  We do this by editing the ``config.description`` line in
 ``src/Plugin.cc``, like this::
 
     [...]
-    plugin::Configuration Configure()
+    plugin::Configuration Plugin::Configure()
         {
         plugin::Configuration config;
         config.name = "Demo::Rot13";
         config.description = "Caesar cipher rotating a string's characters by 13 places.";
-        config.version.major = 1;
+        config.version.major = 0;
-        config.version.minor = 0;
+        config.version.minor = 1;
         return config;
         }
     [...]
 
+Now rebuild and verify that the description is visible::
+
     # make
     [...]
     # bro -N | grep Rot13
-    Plugin: Demo::Rot13 - Caesar cipher rotating a string's characters by 13 places. (dynamic, version 1)
+    Demo::Rot13 - Caesar cipher rotating a string's characters by 13 places. (dynamic, version 0.1)
 
-Better. Bro can also show us what exactly the plugin provides with the
+Bro can also show us what exactly the plugin provides with the
 more verbose option ``-NN``::
 
     # bro -NN
     [...]
-    Plugin: Demo::Rot13 - Caesar cipher rotating a string's characters by 13 places. (dynamic, version 1)
+    Demo::Rot13 - Caesar cipher rotating a string's characters by 13 places. (dynamic, version 0.1)
         [Function] Demo::rot13
     [...]
 
@@ -157,10 +159,12 @@ The installed version went into
 ``<bro-install-prefix>/lib/bro/plugins/Demo_Rot13``.
 
 One can distribute the plugin independently of Bro for others to use.
-To distribute in source form, just remove the ``build/`` (``make
+To distribute in source form, just remove the ``build/`` directory
-distclean`` does that) and then tar up the whole ``rot13-plugin/``
+(``make distclean`` does that) and then tar up the whole ``rot13-plugin/``
 directory. Others then follow the same process as above after
-unpacking. To distribute the plugin in binary form, the build process
+unpacking.
+
+To distribute the plugin in binary form, the build process
 conveniently creates a corresponding tarball in ``build/dist/``. In
 this case, it's called ``Demo_Rot13-0.1.tar.gz``, with the version
 number coming out of the ``VERSION`` file that ``init-plugin`` put
@@ -169,14 +173,14 @@ plugin, but no further source files. Optionally, one can include
 further files by specifying them in the plugin's ``CMakeLists.txt``
 through the ``bro_plugin_dist_files`` macro; the skeleton does that
 for ``README``, ``VERSION``, ``CHANGES``, and ``COPYING``. To use the
-plugin through the binary tarball, just unpack it and point
+plugin through the binary tarball, just unpack it into
-``BRO_PLUGIN_PATH`` there; or copy it into
+``<bro-install-prefix>/lib/bro/plugins/``.  Alternatively, if you unpack
-``<bro-install-prefix>/lib/bro/plugins/`` directly.
+it in another location, then you need to point ``BRO_PLUGIN_PATH`` there.
 
 Before distributing your plugin, you should edit some of the meta
 files that ``init-plugin`` puts in place. Edit ``README`` and
 ``VERSION``, and update ``CHANGES`` when you make changes. Also put a
-license file in place as ``COPYING``; if BSD is fine, you find a
+license file in place as ``COPYING``; if BSD is fine, you will find a
 template in ``COPYING.edit-me``.
 
 Plugin Directory Layout
@@ -193,7 +197,7 @@ directory. With the skeleton, ``<base>`` corresponds to ``build/``.
     must exist, and its content must consist of a single line with the
     qualified name of the plugin (e.g., "Demo::Rot13").
 
-``<base>/lib/<plugin-name>-<os>-<arch>.so``
+``<base>/lib/<plugin-name>.<os>-<arch>.so``
     The shared library containing the plugin's compiled code. Bro will
     load this in dynamically at run-time if OS and architecture match
     the current platform.
@@ -205,8 +209,15 @@ directory. With the skeleton, ``<base>`` corresponds to ``build/``.
     "@load"ed.
 
 ``scripts``/__load__.bro
-    A Bro script that will be loaded immediately when the plugin gets
+    A Bro script that will be loaded when the plugin gets activated.
-    activated. See below for more information on activating plugins.
+    When this script executes, any BiF elements that the plugin
+    defines will already be available. See below for more information
+    on activating plugins.
+
+``scripts``/__preload__.bro
+    A Bro script that will be loaded when the plugin gets activated,
+    but before any BiF elements become available. See below for more
+    information on activating plugins.
 
 ``lib/bif/``
     Directory with auto-generated Bro scripts that declare the plugin's
@@ -215,8 +226,8 @@ directory. With the skeleton, ``<base>`` corresponds to ``build/``.
 Any other files in ``<base>`` are ignored by Bro.
 
 By convention, a plugin should put its custom scripts into sub folders
-of ``scripts/``, i.e., ``scripts/<script-namespace>/<script>.bro`` to
+of ``scripts/``, i.e., ``scripts/<plugin-namespace>/<plugin-name>/<script>.bro``
-avoid conflicts. As usual, you can then put a ``__load__.bro`` in
+to avoid conflicts. As usual, you can then put a ``__load__.bro`` in
 there as well so that, e.g., ``@load Demo/Rot13`` could load a whole
 module in the form of multiple individual scripts.
 
@@ -242,16 +253,30 @@ as well as the ``__bro_plugin__`` magic file and any further
 distribution files specified in ``CMakeLists.txt`` (e.g., README,
 VERSION). You can find a full list of files installed in
 ``build/MANIFEST``. Behind the scenes, ``make install`` really just
-copies over the binary tarball in ``build/dist``. 
+unpacks the binary tarball from ``build/dist`` into the destination
+directory.
 
 ``init-plugin`` will never overwrite existing files. If its target
-directory already exists, it will be default decline to do anything.
+directory already exists, it will by default decline to do anything.
 You can run it with ``-u`` instead to update an existing plugin,
 however it will never overwrite any existing files; it will only put
 in place files it doesn't find yet. To revert a file back to what
 ``init-plugin`` created originally, delete it first and then rerun
 with ``-u``.
 
+``init-plugin`` puts a ``configure`` script in place that wraps
+``cmake`` with a more familiar configure-style configuration. By
+default, the script provides two options for specifying paths to the
+Bro source (``--bro-dist``) and to the plugin's installation directory
+(``--install-root``). To extend ``configure`` with plugin-specific
+options (such as search paths for its dependencies) don't edit the
+script directly but instead extend ``configure.plugin``, which
+``configure`` includes. That way you will be able to more easily
+update ``configure`` in the future when the distribution version
+changes. In ``configure.plugin`` you can use the predefined shell
+function ``append_cache_entry`` to seed values into the CMake cache;
+see the installed skeleton version and existing plugins for examples.
+
 Activating a Plugin
 ===================
 
@@ -261,7 +286,9 @@ Activating a plugin will:
     1. Load the dynamic module
     2. Make any bif items available
     3. Add the ``scripts/`` directory to ``BROPATH``
-    4. Load ``scripts/__load__.bro``
+    4. Load ``scripts/__preload__.bro``
+    5. Make BiF elements available to scripts.
+    6. Load ``scripts/__load__.bro``
 
 By default, Bro will automatically activate all dynamic plugins found
 in its search path ``BRO_PLUGIN_PATH``. However, in bare mode (``bro
@@ -356,18 +383,19 @@ Testing Plugins
 ===============
 
 A plugin should come with a test suite to exercise its functionality.
-The ``init-plugin`` script puts in place a basic </btest/README> setup
+The ``init-plugin`` script puts in place a basic
+:doc:`BTest <../../components/btest/README>` setup
 to start with. Initially, it comes with a single test that just checks
 that Bro loads the plugin correctly. It won't have a baseline yet, so
 let's get that in place::
 
     # cd tests
     # btest -d
-    [  0%] plugin.loading ... failed
+    [  0%] rot13.show-plugin ... failed
     % 'btest-diff output' failed unexpectedly (exit code 100)
     % cat .diag
     == File ===============================
-    Demo::Rot13 - Caesar cipher rotating a string's characters by 13 places. (dynamic, version 1.0)
+    Demo::Rot13 - Caesar cipher rotating a string's characters by 13 places. (dynamic, version 0.1)
         [Function] Demo::rot13
 
     == Error ===============================
@@ -400,8 +428,8 @@ correctly::
 
 Check the output::
 
-    # btest -d plugin/rot13.bro
+    # btest -d rot13/bif-rot13.bro
-    [  0%] plugin.rot13 ... failed
+    [  0%] rot13.bif-rot13 ... failed
     % 'btest-diff output' failed unexpectedly (exit code 100)
     % cat .diag
     == File ===============================
@@ -416,7 +444,7 @@ Check the output::
 
 Install the baseline::
 
-    # btest -U plugin/rot13.bro
+    # btest -U rot13/bif-rot13.bro
     all 1 tests successful
 
 Run the test-suite::
@@ -444,7 +472,7 @@ your plugin's debugging output with ``-B plugin-<name>``, where
 ``<name>`` is the name of the plugin as returned by its
 ``Configure()`` method, yet with the namespace-separator ``::``
 replaced with a simple dash. Example: If the plugin is called
-``Bro::Demo``, use ``-B plugin-Bro-Demo``. As usual, the debugging
+``Demo::Rot13``, use ``-B plugin-Demo-Rot13``. As usual, the debugging
 output will be recorded to ``debug.log`` if Bro's compiled in debug
 mode.
 

doc/frameworks/broker.rst

@@ -0,0 +1,200 @@
+
+.. _brokercomm-framework:
+
+======================================
+Broker-Enabled Communication Framework
+======================================
+
+.. rst-class:: opening
+
+    Bro can now use the `Broker Library
+    <../components/broker/README.html>`_ to exchange information with
+    other Bro processes.
+
+.. contents::
+
+Connecting to Peers
+===================
+
+Communication via Broker must first be turned on via
+:bro:see:`BrokerComm::enable`.
+
+Bro can accept incoming connections by calling :bro:see:`BrokerComm::listen`
+and then monitor connection status updates via the
+:bro:see:`BrokerComm::incoming_connection_established` and
+:bro:see:`BrokerComm::incoming_connection_broken` events.
+
+.. btest-include:: ${DOC_ROOT}/frameworks/broker/connecting-listener.bro
+
+Bro can initiate outgoing connections by calling :bro:see:`BrokerComm::connect`
+and then monitor connection status updates via the
+:bro:see:`BrokerComm::outgoing_connection_established`,
+:bro:see:`BrokerComm::outgoing_connection_broken`, and
+:bro:see:`BrokerComm::outgoing_connection_incompatible` events.
+
+.. btest-include:: ${DOC_ROOT}/frameworks/broker/connecting-connector.bro
+
+Remote Printing
+===============
+
+To receive remote print messages, first use the
+:bro:see:`BrokerComm::subscribe_to_prints` function to advertise to peers a
+topic prefix of interest and then create an event handler for
+:bro:see:`BrokerComm::print_handler` to handle any print messages that are
+received.
+
+.. btest-include:: ${DOC_ROOT}/frameworks/broker/printing-listener.bro
+
+To send remote print messages, just call :bro:see:`BrokerComm::print`.
+
+.. btest-include:: ${DOC_ROOT}/frameworks/broker/printing-connector.bro
+
+Notice that the subscriber only used the prefix "bro/print/", but is
+able to receive messages with full topics of "bro/print/hi",
+"bro/print/stuff", and "bro/print/bye".  The model here is that the
+publisher of a message checks for all subscribers who advertised
+interest in a prefix of that message's topic and sends it to them.
+
+Message Format
+--------------
+
+For other applications that want to exchange print messages with Bro,
+the Broker message format is simply:
+
+.. code:: c++
+
+    broker::message{std::string{}};
+
+Remote Events
+=============
+
+Receiving remote events is similar to remote prints.  Just use the
+:bro:see:`BrokerComm::subscribe_to_events` function and possibly define any
+new events along with handlers that peers may want to send.
+
+.. btest-include:: ${DOC_ROOT}/frameworks/broker/events-listener.bro
+
+There are two different ways to send events.  The first is to call the
+:bro:see:`BrokerComm::event` function directly.  The second option is to call
+the :bro:see:`BrokerComm::auto_event` function where you specify a
+particular event that will be automatically sent to peers whenever the
+event is called locally via the normal event invocation syntax.
+
+.. btest-include:: ${DOC_ROOT}/frameworks/broker/events-connector.bro
+
+Again, the subscription model is prefix-based.
+
+Message Format
+--------------
+
+For other applications that want to exchange event messages with Bro,
+the Broker message format is:
+
+.. code:: c++
+
+    broker::message{std::string{}, ...};
+
+The first parameter is the name of the event and the remaining ``...``
+are its arguments, which are any of the supported Broker data types as
+they correspond to the Bro types for the event named in the first
+parameter of the message.
+
+Remote Logging
+==============
+
+.. btest-include:: ${DOC_ROOT}/frameworks/broker/testlog.bro
+
+Use the :bro:see:`BrokerComm::subscribe_to_logs` function to advertise interest
+in logs written by peers.  The topic names that Bro uses are implicitly of the
+form "bro/log/<stream-name>".
+
+.. btest-include:: ${DOC_ROOT}/frameworks/broker/logs-listener.bro
+
+To send remote logs either redef :bro:see:`Log::enable_remote_logging` or
+use the :bro:see:`BrokerComm::enable_remote_logs` function.  The former
+allows any log stream to be sent to peers while the latter enables remote
+logging for particular streams.
+
+.. btest-include:: ${DOC_ROOT}/frameworks/broker/logs-connector.bro
+
+Message Format
+--------------
+
+For other applications that want to exchange log messages with Bro,
+the Broker message format is:
+
+.. code:: c++
+
+    broker::message{broker::enum_value{}, broker::record{}};
+
+The enum value corresponds to the stream's :bro:see:`Log::ID` value, and
+the record corresponds to a single entry of that log's columns record,
+in this case a ``Test::Info`` value.
+
+Tuning Access Control
+=====================
+
+By default, endpoints do not restrict the message topics that it sends
+to peers and do not restrict what message topics and data store
+identifiers get advertised to peers.  These are the default
+:bro:see:`BrokerComm::EndpointFlags` supplied to :bro:see:`BrokerComm::enable`.
+
+If not using the ``auto_publish`` flag, one can use the
+:bro:see:`BrokerComm::publish_topic` and :bro:see:`BrokerComm::unpublish_topic`
+functions to manipulate the set of message topics (must match exactly)
+that are allowed to be sent to peer endpoints.  These settings take
+precedence over the per-message ``peers`` flag supplied to functions
+that take a :bro:see:`BrokerComm::SendFlags` such as :bro:see:`BrokerComm::print`,
+:bro:see:`BrokerComm::event`, :bro:see:`BrokerComm::auto_event` or
+:bro:see:`BrokerComm::enable_remote_logs`.
+
+If not using the ``auto_advertise`` flag, one can use the
+:bro:see:`BrokerComm::advertise_topic` and
+:bro:see:`BrokerComm::unadvertise_topic` functions
+to manipulate the set of topic prefixes that are allowed to be
+advertised to peers.  If an endpoint does not advertise a topic prefix, then
+the only way peers can send messages to it is via the ``unsolicited``
+flag of :bro:see:`BrokerComm::SendFlags` and choosing a topic with a matching
+prefix (i.e. full topic may be longer than receivers prefix, just the
+prefix needs to match).
+
+Distributed Data Stores
+=======================
+
+There are three flavors of key-value data store interfaces: master,
+clone, and frontend.
+
+A frontend is the common interface to query and modify data stores.
+That is, a clone is a specific type of frontend and a master is also a
+specific type of frontend, but a standalone frontend can also exist to
+e.g. query and modify the contents of a remote master store without
+actually "owning" any of the contents itself.
+
+A master data store can be cloned from remote peers which may then
+perform lightweight, local queries against the clone, which
+automatically stays synchronized with the master store.  Clones cannot
+modify their content directly, instead they send modifications to the
+centralized master store which applies them and then broadcasts them to
+all clones.
+
+Master and clone stores get to choose what type of storage backend to
+use.  E.g. In-memory versus SQLite for persistence.  Note that if clones
+are used, then data store sizes must be able to fit within memory
+regardless of the storage backend as a single snapshot of the master
+store is sent in a single chunk to initialize the clone.
+
+Data stores also support expiration on a per-key basis either using an
+absolute point in time or a relative amount of time since the entry's
+last modification time.
+
+.. btest-include:: ${DOC_ROOT}/frameworks/broker/stores-listener.bro
+
+.. btest-include:: ${DOC_ROOT}/frameworks/broker/stores-connector.bro
+
+In the above example, if a local copy of the store contents isn't
+needed, just replace the :bro:see:`BrokerStore::create_clone` call with
+:bro:see:`BrokerStore::create_frontend`.  Queries will then be made against
+the remote master store instead of the local clone.
+
+Note that all data store queries must be made within Bro's asynchronous
+``when`` statements and must specify a timeout block.

doc/frameworks/broker/connecting-connector.bro

@@ -0,0 +1,18 @@
+const broker_port: port = 9999/tcp &redef;
+redef exit_only_after_terminate = T;
+redef BrokerComm::endpoint_name = "connector";
+
+event bro_init()
+	{
+	BrokerComm::enable();
+	BrokerComm::connect("127.0.0.1", broker_port, 1sec);
+	}
+
+event BrokerComm::outgoing_connection_established(peer_address: string,
+                                            peer_port: port,
+                                            peer_name: string)
+	{
+	print "BrokerComm::outgoing_connection_established",
+		  peer_address, peer_port, peer_name;
+	terminate();
+	}

doc/frameworks/broker/connecting-listener.bro

@@ -0,0 +1,20 @@
+const broker_port: port = 9999/tcp &redef;
+redef exit_only_after_terminate = T;
+redef BrokerComm::endpoint_name = "listener";
+
+event bro_init()
+	{
+	BrokerComm::enable();
+	BrokerComm::listen(broker_port, "127.0.0.1");
+	}
+
+event BrokerComm::incoming_connection_established(peer_name: string)
+	{
+	print "BrokerComm::incoming_connection_established", peer_name;
+	}
+
+event BrokerComm::incoming_connection_broken(peer_name: string)
+	{
+	print "BrokerComm::incoming_connection_broken", peer_name;
+	terminate();
+	}

doc/frameworks/broker/events-connector.bro

@@ -0,0 +1,31 @@
+const broker_port: port = 9999/tcp &redef;
+redef exit_only_after_terminate = T;
+redef BrokerComm::endpoint_name = "connector";
+global my_event: event(msg: string, c: count);
+global my_auto_event: event(msg: string, c: count);
+
+event bro_init()
+	{
+	BrokerComm::enable();
+	BrokerComm::connect("127.0.0.1", broker_port, 1sec);
+	BrokerComm::auto_event("bro/event/my_auto_event", my_auto_event);
+	}
+
+event BrokerComm::outgoing_connection_established(peer_address: string,
+                                            peer_port: port,
+                                            peer_name: string)
+	{
+	print "BrokerComm::outgoing_connection_established",
+	      peer_address, peer_port, peer_name;
+	BrokerComm::event("bro/event/my_event", BrokerComm::event_args(my_event, "hi", 0));
+	event my_auto_event("stuff", 88);
+	BrokerComm::event("bro/event/my_event", BrokerComm::event_args(my_event, "...", 1));
+	event my_auto_event("more stuff", 51);
+	BrokerComm::event("bro/event/my_event", BrokerComm::event_args(my_event, "bye", 2));
+	}
+
+event BrokerComm::outgoing_connection_broken(peer_address: string,
+                                       peer_port: port)
+	{
+	terminate();
+	}

doc/frameworks/broker/events-listener.bro

@@ -0,0 +1,36 @@
+const broker_port: port = 9999/tcp &redef;
+redef exit_only_after_terminate = T;
+redef BrokerComm::endpoint_name = "listener";
+global msg_count = 0;
+global my_event: event(msg: string, c: count);
+global my_auto_event: event(msg: string, c: count);
+
+event bro_init()
+	{
+	BrokerComm::enable();
+	BrokerComm::subscribe_to_events("bro/event/");
+	BrokerComm::listen(broker_port, "127.0.0.1");
+	}
+
+event BrokerComm::incoming_connection_established(peer_name: string)
+	{
+	print "BrokerComm::incoming_connection_established", peer_name;
+	}
+
+event my_event(msg: string, c: count)
+	{
+	++msg_count;
+	print "got my_event", msg, c;
+
+	if ( msg_count == 5 )
+		terminate();
+	}
+
+event my_auto_event(msg: string, c: count)
+	{
+	++msg_count;
+	print "got my_auto_event", msg, c;
+
+	if ( msg_count == 5 )
+		terminate();
+	}

doc/frameworks/broker/logs-connector.bro

@@ -0,0 +1,40 @@
+@load ./testlog
+
+const broker_port: port = 9999/tcp &redef;
+redef exit_only_after_terminate = T;
+redef BrokerComm::endpoint_name = "connector";
+redef Log::enable_local_logging = F;
+redef Log::enable_remote_logging = F;
+global n = 0;
+
+event bro_init()
+	{
+	BrokerComm::enable();
+	BrokerComm::enable_remote_logs(Test::LOG);
+	BrokerComm::connect("127.0.0.1", broker_port, 1sec);
+	}
+
+event do_write()
+	{
+	if ( n == 6 )
+		return;
+
+	Log::write(Test::LOG, [$msg = "ping", $num = n]);
+	++n;
+	event do_write();
+	}
+
+event BrokerComm::outgoing_connection_established(peer_address: string,
+                                            peer_port: port,
+                                            peer_name: string)
+	{
+	print "BrokerComm::outgoing_connection_established",
+	      peer_address, peer_port, peer_name;
+	event do_write();
+	}
+
+event BrokerComm::outgoing_connection_broken(peer_address: string,
+                                       peer_port: port)
+	{
+	terminate();
+	}

doc/frameworks/broker/logs-listener.bro

@@ -0,0 +1,25 @@
+@load ./testlog
+
+const broker_port: port = 9999/tcp &redef;
+redef exit_only_after_terminate = T;
+redef BrokerComm::endpoint_name = "listener";
+
+event bro_init()
+	{
+	BrokerComm::enable();
+	BrokerComm::subscribe_to_logs("bro/log/Test::LOG");
+	BrokerComm::listen(broker_port, "127.0.0.1");
+	}
+
+event BrokerComm::incoming_connection_established(peer_name: string)
+	{
+	print "BrokerComm::incoming_connection_established", peer_name;
+	}
+
+event Test::log_test(rec: Test::Info)
+	{
+	print "wrote log", rec;
+
+	if ( rec$num == 5 )
+		terminate();
+	}

doc/frameworks/broker/printing-connector.bro

@@ -0,0 +1,26 @@
+const broker_port: port = 9999/tcp &redef;
+redef exit_only_after_terminate = T;
+redef BrokerComm::endpoint_name = "connector";
+
+event bro_init()
+	{
+	BrokerComm::enable();
+	BrokerComm::connect("127.0.0.1", broker_port, 1sec);
+	}
+
+event BrokerComm::outgoing_connection_established(peer_address: string,
+                                            peer_port: port,
+                                            peer_name: string)
+	{
+	print "BrokerComm::outgoing_connection_established",
+	      peer_address, peer_port, peer_name;
+	BrokerComm::print("bro/print/hi", "hello");
+	BrokerComm::print("bro/print/stuff", "...");
+	BrokerComm::print("bro/print/bye", "goodbye");
+	}
+
+event BrokerComm::outgoing_connection_broken(peer_address: string,
+                                       peer_port: port)
+	{
+	terminate();
+	}

doc/frameworks/broker/printing-listener.bro

@@ -0,0 +1,25 @@
+const broker_port: port = 9999/tcp &redef;
+redef exit_only_after_terminate = T;
+redef BrokerComm::endpoint_name = "listener";
+global msg_count = 0;
+
+event bro_init()
+	{
+	BrokerComm::enable();
+	BrokerComm::subscribe_to_prints("bro/print/");
+	BrokerComm::listen(broker_port, "127.0.0.1");
+	}
+
+event BrokerComm::incoming_connection_established(peer_name: string)
+	{
+	print "BrokerComm::incoming_connection_established", peer_name;
+	}
+
+event BrokerComm::print_handler(msg: string)
+	{
+	++msg_count;
+	print "got print message", msg;
+
+	if ( msg_count == 3 )
+		terminate();
+	}

doc/frameworks/broker/stores-connector.bro

@@ -0,0 +1,53 @@
+const broker_port: port = 9999/tcp &redef;
+redef exit_only_after_terminate = T;
+
+global h: opaque of BrokerStore::Handle;
+
+function dv(d: BrokerComm::Data): BrokerComm::DataVector
+	{
+	local rval: BrokerComm::DataVector;
+	rval[0] = d;
+	return rval;
+	}
+
+global ready: event();
+
+event BrokerComm::outgoing_connection_broken(peer_address: string,
+                                       peer_port: port)
+	{
+	terminate();
+	}
+
+event BrokerComm::outgoing_connection_established(peer_address: string,
+                                            peer_port: port,
+                                            peer_name: string)
+	{
+	local myset: set[string] = {"a", "b", "c"};
+	local myvec: vector of string = {"alpha", "beta", "gamma"};
+	h = BrokerStore::create_master("mystore");
+	BrokerStore::insert(h, BrokerComm::data("one"), BrokerComm::data(110));
+	BrokerStore::insert(h, BrokerComm::data("two"), BrokerComm::data(223));
+	BrokerStore::insert(h, BrokerComm::data("myset"), BrokerComm::data(myset));
+	BrokerStore::insert(h, BrokerComm::data("myvec"), BrokerComm::data(myvec));
+	BrokerStore::increment(h, BrokerComm::data("one"));
+	BrokerStore::decrement(h, BrokerComm::data("two"));
+	BrokerStore::add_to_set(h, BrokerComm::data("myset"), BrokerComm::data("d"));
+	BrokerStore::remove_from_set(h, BrokerComm::data("myset"), BrokerComm::data("b"));
+	BrokerStore::push_left(h, BrokerComm::data("myvec"), dv(BrokerComm::data("delta")));
+	BrokerStore::push_right(h, BrokerComm::data("myvec"), dv(BrokerComm::data("omega")));
+
+	when ( local res = BrokerStore::size(h) )
+		{
+		print "master size", res;
+		event ready();
+		}
+	timeout 10sec
+		{ print "timeout"; }
+	}
+
+event bro_init()
+	{
+	BrokerComm::enable();
+	BrokerComm::connect("127.0.0.1", broker_port, 1secs);
+	BrokerComm::auto_event("bro/event/ready", ready);
+	}

doc/frameworks/broker/stores-listener.bro

@@ -0,0 +1,43 @@
+const broker_port: port = 9999/tcp &redef;
+redef exit_only_after_terminate = T;
+
+global h: opaque of BrokerStore::Handle;
+global expected_key_count = 4;
+global key_count = 0;
+
+function do_lookup(key: string)
+	{
+	when ( local res = BrokerStore::lookup(h, BrokerComm::data(key)) )
+		{
+		++key_count;
+		print "lookup", key, res;
+
+		if ( key_count == expected_key_count )
+			terminate();
+		}
+	timeout 10sec
+		{ print "timeout", key; }
+	}
+
+event ready()
+	{
+	h = BrokerStore::create_clone("mystore");
+
+	when ( local res = BrokerStore::keys(h) )
+		{
+		print "clone keys", res;
+		do_lookup(BrokerComm::refine_to_string(BrokerComm::vector_lookup(res$result, 0)));
+		do_lookup(BrokerComm::refine_to_string(BrokerComm::vector_lookup(res$result, 1)));
+		do_lookup(BrokerComm::refine_to_string(BrokerComm::vector_lookup(res$result, 2)));
+		do_lookup(BrokerComm::refine_to_string(BrokerComm::vector_lookup(res$result, 3)));
+		}
+	timeout 10sec
+		{ print "timeout"; }
+	}
+
+event bro_init()
+	{
+	BrokerComm::enable();
+	BrokerComm::subscribe_to_events("bro/event/ready");
+	BrokerComm::listen(broker_port, "127.0.0.1");
+	}

doc/frameworks/broker/testlog.bro

@@ -0,0 +1,18 @@
+module Test;
+
+export {
+	redef enum Log::ID += { LOG };
+
+	type Info: record {
+		msg: string &log;
+		num: count &log;
+	};
+
+	global log_test: event(rec: Test::Info);
+}
+
+event bro_init() &priority=5
+	{
+	BrokerComm::enable();
+	Log::create_stream(Test::LOG, [$columns=Test::Info, $ev=log_test, $path="test"]);
+	}

doc/frameworks/file_analysis_02.bro

@@ -1,7 +1,8 @@
-event file_mime_type(f: fa_file, mime_type: string)
+event file_sniff(f: fa_file, meta: fa_metadata)
     {
+	if ( ! meta?$mime_type ) return;
     print "new file", f$id;
-    if ( mime_type == "text/plain" )
+    if ( meta$mime_type == "text/plain" )
         Files::add_analyzer(f, Files::ANALYZER_MD5);
     }
 

doc/frameworks/geoip.rst

@@ -20,11 +20,13 @@ GeoLocation
 Install libGeoIP
 ----------------
 
+Before building Bro, you need to install libGeoIP.
+
 * FreeBSD:
 
   .. console::
 
-      sudo pkg_add -r GeoIP
+      sudo pkg install GeoIP
 
 * RPM/RedHat-based Linux:
 
@@ -40,80 +42,99 @@ Install libGeoIP
 
 * Mac OS X:
 
-  Vanilla OS X installations don't ship with libGeoIP, but if
+  You need to install from your preferred package management system
-  installed from your preferred package management system (e.g.
+  (e.g. MacPorts, Fink, or Homebrew).  The name of the package that you need
-  MacPorts, Fink, or Homebrew), they should be automatically detected
+  may be libgeoip, geoip, or geoip-dev, depending on which package management
-  and Bro will compile against them.
+  system you are using.
 
 
 GeoIPLite Database Installation
-------------------------------------
+-------------------------------
 
 A country database for GeoIPLite is included when you do the C API
 install, but for Bro, we are using the city database which includes
 cities and regions in addition to countries.
 
 `Download <http://www.maxmind.com/app/geolitecity>`__ the GeoLite city
-binary database.
+binary database:
 
-  .. console::
+.. console::
 
     wget http://geolite.maxmind.com/download/geoip/database/GeoLiteCity.dat.gz
     gunzip GeoLiteCity.dat.gz
 
-Next, the file needs to be put in the database directory.  This directory
+Next, the file needs to be renamed and put in the GeoIP database directory.
-should already exist and will vary depending on which platform and package
+This directory should already exist and will vary depending on which platform
-you are using.  For FreeBSD, use ``/usr/local/share/GeoIP``.  For Linux,
+and package you are using.  For FreeBSD, use ``/usr/local/share/GeoIP``.  For
-use ``/usr/share/GeoIP`` or ``/var/lib/GeoIP`` (choose whichever one
+Linux, use ``/usr/share/GeoIP`` or ``/var/lib/GeoIP`` (choose whichever one
 already exists).
     
-  .. console::
+.. console::
 
     mv GeoLiteCity.dat <path_to_database_dir>/GeoIPCity.dat
 
+Note that there is a separate database for IPv6 addresses, which can also
+be installed if you want GeoIP functionality for IPv6.
+
+Testing
+-------
+
+Before using the GeoIP functionality, it is a good idea to verify that
+everything is setup correctly.  After installing libGeoIP and the GeoIP city
+database, and building Bro, you can quickly check if the GeoIP functionality
+works by running a command like this:
+
+.. console::
+
+    bro -e "print lookup_location(8.8.8.8);"
+
+If you see an error message similar to "Failed to open GeoIP City database",
+then you may need to either rename or move your GeoIP city database file (the
+error message should give you the full pathname of the database file that
+Bro is looking for).
+
+If you see an error message similar to "Bro was not configured for GeoIP
+support", then you need to rebuild Bro and make sure it is linked against
+libGeoIP.  Normally, if libGeoIP is installed correctly then it should
+automatically be found when building Bro.  If this doesn't happen, then
+you may need to specify the path to the libGeoIP installation
+(e.g. ``./configure --with-geoip=<path>``).
 
 Usage
 -----
 
-There is a single built in function that provides the GeoIP
+There is a built-in function that provides the GeoIP functionality:
-functionality:
 
 .. code:: bro
 
     function lookup_location(a:addr): geo_location
 
-There is also the :bro:see:`geo_location` data structure that is returned
+The return value of the :bro:see:`lookup_location` function is a record
-from the :bro:see:`lookup_location` function:
+type called :bro:see:`geo_location`, and it consists of several fields
-
+containing the country, region, city, latitude, and longitude of the specified
-.. code:: bro
+IP address.  Since one or more fields in this record will be uninitialized
-
+for some IP addresses (for example, the country and region of an IP address
-    type geo_location: record {
+might be known, but the city could be unknown), a field should be checked
-      country_code: string;
+if it has a value before trying to access the value.
-      region: string;
-      city: string;
-      latitude: double;
-      longitude: double;
-    };
-
 
 Example
 -------
 
-To write a line in a log file for every ftp connection from hosts in
+To show every ftp connection from hosts in Ohio, this is now very easy:
-Ohio, this is now very easy:
 
 .. code:: bro
 
-    global ftp_location_log: file = open_log_file("ftp-location");
-    
     event ftp_reply(c: connection, code: count, msg: string, cont_resp: bool)
     {
       local client = c$id$orig_h;
       local loc = lookup_location(client);
-      if (loc$region == "OH" && loc$country_code == "US")
+
+      if (loc?$region && loc$region == "OH" && loc$country_code == "US")
       {
-        print ftp_location_log, fmt("FTP Connection from:%s (%s,%s,%s)", client, loc$city, loc$region, loc$country_code); 
+        local city = loc?$city ? loc$city : "<unknown>";
+
+        print fmt("FTP Connection from:%s (%s,%s,%s)", client, city,
+          loc$region, loc$country_code);
       }
     }
 
-

doc/frameworks/index.rst

@@ -14,4 +14,4 @@ Frameworks
    notice
    signatures
    sumstats
-
+   broker

doc/frameworks/input.rst

@@ -32,7 +32,8 @@ For this example we assume that we want to import data from a blacklist
 that contains server IP addresses as well as the timestamp and the reason
 for the block.
 
-An example input file could look like this:
+An example input file could look like this (note that all fields must be
+tab-separated):
 
 ::
 
@@ -63,19 +64,23 @@ The two records are defined as:
                 reason: string;
         };
 
-Note that the names of the fields in the record definitions have to correspond
+Note that the names of the fields in the record definitions must correspond
 to the column names listed in the '#fields' line of the log file, in this
-case 'ip', 'timestamp', and 'reason'.
+case 'ip', 'timestamp', and 'reason'.  Also note that the ordering of the
+columns does not matter, because each column is identified by name.
 
-The log file is read into the table with a simple call of the ``add_table``
+The log file is read into the table with a simple call of the
-function:
+:bro:id:`Input::add_table` function:
 
 .. code:: bro
 
         global blacklist: table[addr] of Val = table();
 
-        Input::add_table([$source="blacklist.file", $name="blacklist", $idx=Idx, $val=Val, $destination=blacklist]);
+        event bro_init() {
-        Input::remove("blacklist");
+            Input::add_table([$source="blacklist.file", $name="blacklist",
+                              $idx=Idx, $val=Val, $destination=blacklist]);
+            Input::remove("blacklist");
+        }
 
 With these three lines we first create an empty table that should contain the
 blacklist data and then instruct the input framework to open an input stream
@@ -92,7 +97,7 @@ Because of this, the data is not immediately accessible. Depending on the
 size of the data source it might take from a few milliseconds up to a few
 seconds until all data is present in the table. Please note that this means
 that when Bro is running without an input source or on very short captured
-files, it might terminate before the data is present in the system (because
+files, it might terminate before the data is present in the table (because
 Bro already handled all packets before the import thread finished).
 
 Subsequent calls to an input source are queued until the previous action has
@@ -101,8 +106,8 @@ been completed. Because of this, it is, for example, possible to call
 will remain queued until the first read has been completed.
 
 Once the input framework finishes reading from a data source, it fires
-the ``end_of_data`` event. Once this event has been received all data
+the :bro:id:`Input::end_of_data` event. Once this event has been received all
-from the input file is available in the table.
+data from the input file is available in the table.
 
 .. code:: bro
 
@@ -111,9 +116,9 @@ from the input file is available in the table.
                 print blacklist;
         }
 
-The table can also already be used while the data is still being read - it
+The table can be used while the data is still being read - it
-just might not contain all lines in the input file when the event has not
+just might not contain all lines from the input file before the event has
-yet fired. After it has been populated it can be used like any other Bro
+fired. After the table has been populated it can be used like any other Bro
 table and blacklist entries can easily be tested:
 
 .. code:: bro
@@ -130,10 +135,11 @@ changing. For these cases, the Bro input framework supports several ways to
 deal with changing data files.
 
 The first, very basic method is an explicit refresh of an input stream. When
-an input stream is open, the function ``force_update`` can be called. This
+an input stream is open (this means it has not yet been removed by a call to
-will trigger a complete refresh of the table; any changed elements from the
+:bro:id:`Input::remove`), the function :bro:id:`Input::force_update` can be
-file will be updated.  After the update is finished the ``end_of_data``
+called.  This will trigger a complete refresh of the table; any changed
-event will be raised.
+elements from the file will be updated.  After the update is finished the
+:bro:id:`Input::end_of_data` event will be raised.
 
 In our example the call would look like:
 
@@ -141,30 +147,35 @@ In our example the call would look like:
 
         Input::force_update("blacklist");
 
-The input framework also supports two automatic refresh modes. The first mode
+Alternatively, the input framework can automatically refresh the table
-continually checks if a file has been changed. If the file has been changed, it
+contents when it detects a change to the input file.  To use this feature,
+you need to specify a non-default read mode by setting the ``mode`` option
+of the :bro:id:`Input::add_table` call.  Valid values are ``Input::MANUAL``
+(the default), ``Input::REREAD`` and ``Input::STREAM``.  For example,
+setting the value of the ``mode`` option in the previous example
+would look like this:
+
+.. code:: bro
+
+        Input::add_table([$source="blacklist.file", $name="blacklist",
+                          $idx=Idx, $val=Val, $destination=blacklist,
+                          $mode=Input::REREAD]);
+
+When using the reread mode (i.e., ``$mode=Input::REREAD``), Bro continually
+checks if the input file has been changed. If the file has been changed, it
 is re-read and the data in the Bro table is updated to reflect the current
 state.  Each time a change has been detected and all the new data has been
 read into the table, the ``end_of_data`` event is raised.
 
-The second mode is a streaming mode. This mode assumes that the source data
+When using the streaming mode (i.e., ``$mode=Input::STREAM``), Bro assumes
-file is an append-only file to which new data is continually appended. Bro
+that the source data file is an append-only file to which new data is
-continually checks for new data at the end of the file and will add the new
+continually appended. Bro continually checks for new data at the end of
-data to the table.  If newer lines in the file have the same index as previous
+the file and will add the new data to the table.  If newer lines in the
-lines, they will overwrite the values in the output table.  Because of the
+file have the same index as previous lines, they will overwrite the
-nature of streaming reads (data is continually added to the table),
+values in the output table.  Because of the nature of streaming reads
-the ``end_of_data`` event is never raised when using streaming reads.
+(data is continually added to the table), the ``end_of_data`` event
+is never raised when using streaming reads.
 
-The reading mode can be selected by setting the ``mode`` option of the
-add_table call.  Valid values are ``MANUAL`` (the default), ``REREAD``
-and ``STREAM``.
-
-Hence, when adding ``$mode=Input::REREAD`` to the previous example, the
-blacklist table will always reflect the state of the blacklist input file.
-
-.. code:: bro
-
-        Input::add_table([$source="blacklist.file", $name="blacklist", $idx=Idx, $val=Val, $destination=blacklist, $mode=Input::REREAD]);
 
 Receiving change events
 -----------------------
@@ -173,34 +184,40 @@ When re-reading files, it might be interesting to know exactly which lines in
 the source files have changed.
 
 For this reason, the input framework can raise an event each time when a data
-item is added to, removed from or changed in a table.
+item is added to, removed from, or changed in a table.
 
-The event definition looks like this:
+The event definition looks like this (note that you can change the name of
+this event in your own Bro script):
 
 .. code:: bro
 
-        event entry(description: Input::TableDescription, tpe: Input::Event, left: Idx, right: Val) {
+        event entry(description: Input::TableDescription, tpe: Input::Event,
-                # act on values
+                    left: Idx, right: Val) {
+                # do something here...
+                print fmt("%s = %s", left, right);
         }
 
-The event has to be specified in ``$ev`` in the ``add_table`` call:
+The event must be specified in ``$ev`` in the ``add_table`` call:
 
 .. code:: bro
 
-        Input::add_table([$source="blacklist.file", $name="blacklist", $idx=Idx, $val=Val, $destination=blacklist, $mode=Input::REREAD, $ev=entry]);
+        Input::add_table([$source="blacklist.file", $name="blacklist",
+                          $idx=Idx, $val=Val, $destination=blacklist,
+                          $mode=Input::REREAD, $ev=entry]);
 
-The ``description`` field of the event contains the arguments that were
+The ``description`` argument of the event contains the arguments that were
 originally supplied to the add_table call.  Hence, the name of the stream can,
-for example, be accessed with ``description$name``. ``tpe`` is an enum
+for example, be accessed with ``description$name``. The ``tpe`` argument of the
-containing the type of the change that occurred.
+event is an enum containing the type of the change that occurred.
 
 If a line that was not previously present in the table has been added,
-then ``tpe`` will contain ``Input::EVENT_NEW``. In this case ``left`` contains
+then the value of ``tpe`` will be ``Input::EVENT_NEW``. In this case ``left``
-the index of the added table entry and ``right`` contains the values of the
+contains the index of the added table entry and ``right`` contains the
-added entry.
+values of the added entry.
 
 If a table entry that already was present is altered during the re-reading or
-streaming read of a file, ``tpe`` will contain ``Input::EVENT_CHANGED``. In
+streaming read of a file, then the value of ``tpe`` will be
+``Input::EVENT_CHANGED``. In
 this case ``left`` contains the index of the changed table entry and ``right``
 contains the values of the entry before the change. The reason for this is
 that the table already has been updated when the event is raised. The current
@@ -208,8 +225,9 @@ value in the table can be ascertained by looking up the current table value.
 Hence it is possible to compare the new and the old values of the table.
 
 If a table element is removed because it was no longer present during a
-re-read, then ``tpe`` will contain ``Input::REMOVED``.  In this case ``left``
+re-read, then the value of ``tpe`` will be ``Input::EVENT_REMOVED``.  In this
-contains the index and ``right`` the values of the removed element.
+case ``left`` contains the index and ``right`` the values of the removed
+element.
 
 
 Filtering data during import
@@ -222,24 +240,26 @@ can either accept or veto the change by returning true for an accepted
 change and false for a rejected change. Furthermore, it can alter the data
 before it is written to the table.
 
-The following example filter will reject to add entries to the table when
+The following example filter will reject adding entries to the table when
 they were generated over a month ago. It will accept all changes and all
 removals of values that are already present in the table.
 
 .. code:: bro
 
-        Input::add_table([$source="blacklist.file", $name="blacklist", $idx=Idx, $val=Val, $destination=blacklist, $mode=Input::REREAD,
+        Input::add_table([$source="blacklist.file", $name="blacklist",
-                        $pred(typ: Input::Event, left: Idx, right: Val) = {
+                          $idx=Idx, $val=Val, $destination=blacklist,
-                                if ( typ != Input::EVENT_NEW ) {
+                          $mode=Input::REREAD,
-                                        return T;
+                          $pred(typ: Input::Event, left: Idx, right: Val) = {
-                                }
+                            if ( typ != Input::EVENT_NEW ) {
-                                return ( ( current_time() - right$timestamp ) < (30 day) );
+                                return T;
-                        }]);
+                            }
+                            return (current_time() - right$timestamp) < 30day;
+                          }]);
 
 To change elements while they are being imported, the predicate function can
 manipulate ``left`` and ``right``. Note that predicate functions are called
 before the change is committed to the table. Hence, when a table element is
-changed (``tpe`` is ``INPUT::EVENT_CHANGED``), ``left`` and ``right``
+changed (``typ`` is ``Input::EVENT_CHANGED``), ``left`` and ``right``
 contain the new values, but the destination (``blacklist`` in our example)
 still contains the old values. This allows predicate functions to examine
 the changes between the old and the new version before deciding if they
@@ -250,14 +270,19 @@ Different readers
 
 The input framework supports different kinds of readers for different kinds
 of source data files. At the moment, the default reader reads ASCII files
-formatted in the Bro log file format (tab-separated values). At the moment,
+formatted in the Bro log file format (tab-separated values with a "#fields"
-Bro comes with two other readers. The ``RAW`` reader reads a file that is
+header line).  Several other readers are included in Bro.
-split by a specified record separator (usually newline). The contents are
+
+The raw reader reads a file that is
+split by a specified record separator (newline by default). The contents are
 returned line-by-line as strings; it can, for example, be used to read
 configuration files and the like and is probably
 only useful in the event mode and not for reading data to tables.
 
-Another included reader is the ``BENCHMARK`` reader, which is being used
+The binary reader is intended to be used with file analysis input streams (and
+is the default type of reader for those streams).
+
+The benchmark reader is being used
 to optimize the speed of the input framework. It can generate arbitrary
 amounts of semi-random data in all Bro data types supported by the input
 framework.
@@ -270,75 +295,17 @@ aforementioned ones:
 
    logging-input-sqlite
 
-Add_table options
------------------
-
-This section lists all possible options that can be used for the add_table
-function and gives a short explanation of their use. Most of the options
-already have been discussed in the previous sections.
-
-The possible fields that can be set for a table stream are:
-
-        ``source``
-                A mandatory string identifying the source of the data.
-                For the ASCII reader this is the filename.
-
-        ``name``
-                A mandatory name for the filter that can later be used
-                to manipulate it further.
-
-        ``idx``
-                Record type that defines the index of the table.
-
-        ``val``
-                Record type that defines the values of the table.
-
-        ``reader``
-                The reader used for this stream. Default is ``READER_ASCII``.
-
-        ``mode``
-                The mode in which the stream is opened. Possible values are
-                ``MANUAL``, ``REREAD`` and ``STREAM``.  Default is ``MANUAL``.
-                ``MANUAL`` means that the file is not updated after it has
-                been read. Changes to the file will not be reflected in the
-                data Bro knows.  ``REREAD`` means that the whole file is read
-                again each time a change is found. This should be used for
-                files that are mapped to a table where individual lines can
-                change.  ``STREAM`` means that the data from the file is
-                streamed. Events / table entries will be generated as new
-                data is appended to the file.
-
-        ``destination``
-                The destination table.
-
-        ``ev``
-                Optional event that is raised, when values are added to,
-                changed in, or deleted from the table.  Events are passed an
-                Input::Event description as the first argument, the index
-                record as the second argument and the values as the third
-                argument.
-
-        ``pred``
-                Optional predicate, that can prevent entries from being added
-                to the table and events from being sent.
-
-        ``want_record``
-                Boolean value, that defines if the event wants to receive the
-                fields inside of a single record value, or individually
-                (default).  This can be used if ``val`` is a record
-                containing only one type. In this case, if ``want_record`` is
-                set to false, the table will contain elements of the type
-                contained in ``val``.
 
 Reading Data to Events
 ======================
 
 The second supported mode of the input framework is reading data to Bro
-events instead of reading them to a table using event streams.
+events instead of reading them to a table.
 
 Event streams work very similarly to table streams that were already
 discussed in much detail. To read the blacklist of the previous example
-into an event stream, the following Bro code could be used:
+into an event stream, the :bro:id:`Input::add_event` function is used.
+For example:
 
 .. code:: bro
 
@@ -348,12 +315,15 @@ into an event stream, the following Bro code could be used:
                 reason: string;
         };
 
-        event blacklistentry(description: Input::EventDescription, tpe: Input::Event, ip: addr, timestamp: time, reason: string) {
+        event blacklistentry(description: Input::EventDescription,
-                # work with event data
+                             t: Input::Event, data: Val) {
+                # do something here...
+                print "data:", data;
         }
 
         event bro_init() {
-                Input::add_event([$source="blacklist.file", $name="blacklist", $fields=Val, $ev=blacklistentry]);
+                Input::add_event([$source="blacklist.file", $name="blacklist",
+                                  $fields=Val, $ev=blacklistentry]);
         }
 
 
@@ -364,52 +334,3 @@ data types are provided in a single record definition.
 Apart from this, event streams work exactly the same as table streams and
 support most of the options that are also supported for table streams.
 
-The options that can be set when creating an event stream with
-``add_event`` are:
-
-        ``source``
-                A mandatory string identifying the source of the data.
-                For the ASCII reader this is the filename.
-
-        ``name``
-                A mandatory name for the stream that can later be used
-                to remove it.
-
-        ``fields``
-                Name of a record type containing the fields, which should be
-                retrieved from the input stream.
-
-        ``ev``
-                The event which is fired, after a line has been read from the
-                input source.  The first argument that is passed to the event
-                is an Input::Event structure, followed by the data, either
-                inside of a record (if ``want_record is set``) or as
-                individual fields.  The Input::Event structure can contain
-                information, if the received line is ``NEW``, has been
-                ``CHANGED`` or ``DELETED``. Since the ASCII reader cannot
-                track this information for event filters, the value is
-                always ``NEW`` at the moment.
-
-        ``mode``
-                The mode in which the stream is opened. Possible values are
-                ``MANUAL``, ``REREAD`` and ``STREAM``.  Default is ``MANUAL``.
-                ``MANUAL`` means that the file is not updated after it has
-                been read. Changes to the file will not be reflected in the
-                data Bro knows.  ``REREAD`` means that the whole file is read
-                again each time a change is found. This should be used for
-                files that are mapped to a table where individual lines can
-                change.  ``STREAM`` means that the data from the file is
-                streamed. Events / table entries will be generated as new
-                data is appended to the file.
-
-        ``reader``
-                The reader used for this stream. Default is ``READER_ASCII``.
-
-        ``want_record``
-                Boolean value, that defines if the event wants to receive the
-                fields inside of a single record value, or individually
-                (default). If this is set to true, the event will receive a
-                single record of the type provided in ``fields``.
-
-
-

doc/frameworks/logging-input-sqlite.rst

@@ -23,17 +23,18 @@ In contrast to the ASCII reader and writer, the SQLite plugins have not yet
 seen extensive use in production environments. While we are not aware
 of any issues with them, we urge to caution when using them
 in production environments. There could be lingering issues which only occur
-when the plugins are used with high amounts of data or in high-load environments.
+when the plugins are used with high amounts of data or in high-load
+environments.
 
 Logging Data into SQLite Databases
 ==================================
 
 Logging support for SQLite is available in all Bro installations starting with
-version 2.2. There is no need to load any additional scripts or for any compile-time
+version 2.2. There is no need to load any additional scripts or for any
-configurations.
+compile-time configurations.
 
-Sending data from existing logging streams to SQLite is rather straightforward. You
+Sending data from existing logging streams to SQLite is rather straightforward.
-have to define a filter which specifies SQLite as the writer.
+You have to define a filter which specifies SQLite as the writer.
 
 The following example code adds SQLite as a filter for the connection log:
 
@@ -44,15 +45,15 @@ The following example code adds SQLite as a filter for the connection log:
     # Make sure this parses correctly at least.
     @TEST-EXEC: bro ${DOC_ROOT}/frameworks/sqlite-conn-filter.bro
 
-Bro will create the database file ``/var/db/conn.sqlite``, if it does not already exist.
+Bro will create the database file ``/var/db/conn.sqlite``, if it does not
-It will also create a table with the name ``conn`` (if it does not exist) and start
+already exist.  It will also create a table with the name ``conn`` (if it
-appending connection information to the table.
+does not exist) and start appending connection information to the table.
 
-At the moment, SQLite databases are not rotated the same way ASCII log-files are. You
+At the moment, SQLite databases are not rotated the same way ASCII log-files
-have to take care to create them in an adequate location.
+are. You have to take care to create them in an adequate location.
 
-If you examine the resulting SQLite database, the schema will contain the same fields
+If you examine the resulting SQLite database, the schema will contain the
-that are present in the ASCII log files::
+same fields that are present in the ASCII log files::
 
     # sqlite3 /var/db/conn.sqlite
 
@@ -67,35 +68,39 @@ that are present in the ASCII log files::
     'id.orig_p' integer,
     ...
 
-Note that the ASCII ``conn.log`` will still be created. To disable the ASCII writer for a
+Note that the ASCII ``conn.log`` will still be created. To prevent this file
-log stream, you can remove the default filter:
+from being created, you can remove the default filter:
 
 .. code:: bro
 
     Log::remove_filter(Conn::LOG, "default");
 
 
-To create a custom SQLite log file, you have to create a new log stream that contains
+To create a custom SQLite log file, you have to create a new log stream
-just the information you want to commit to the database. Please refer to the
+that contains just the information you want to commit to the database.
-:ref:`framework-logging` documentation on how to create custom log streams.
+Please refer to the :ref:`framework-logging` documentation on how to
+create custom log streams.
 
 Reading Data from SQLite Databases
 ==================================
 
-Like logging support, support for reading data from SQLite databases is built into Bro starting
+Like logging support, support for reading data from SQLite databases is
-with version 2.2.
+built into Bro starting with version 2.2.
 
-Just as with the text-based input readers (please refer to the :ref:`framework-input`
+Just as with the text-based input readers (please refer to the
-documentation for them and for basic information on how to use the input-framework), the SQLite reader
+:ref:`framework-input` documentation for them and for basic information
-can be used to read data - in this case the result of SQL queries - into tables or into events.
+on how to use the input framework), the SQLite reader can be used to
+read data - in this case the result of SQL queries - into tables or into
+events.
 
 Reading Data into Tables
 ------------------------
 
-To read data from a SQLite database, we first have to provide Bro with the information, how
+To read data from a SQLite database, we first have to provide Bro with
-the resulting data will be structured. For this example, we expect that we have a SQLite database,
+the information, how the resulting data will be structured. For this
-which contains host IP addresses and the user accounts that are allowed to log into a specific
+example, we expect that we have a SQLite database, which contains
-machine.
+host IP addresses and the user accounts that are allowed to log into
+a specific machine.
 
 The SQLite commands to create the schema are as follows::
 
@@ -107,8 +112,8 @@ The SQLite commands to create the schema are as follows::
     insert into machines_to_users values ('192.168.17.2', 'bernhard');
     insert into machines_to_users values ('192.168.17.3', 'seth,matthias');
 
-After creating a file called ``hosts.sqlite`` with this content, we can read the resulting table
+After creating a file called ``hosts.sqlite`` with this content, we can
-into Bro:
+read the resulting table into Bro:
 
 .. btest-include:: ${DOC_ROOT}/frameworks/sqlite-read-table.bro
 
@@ -117,22 +122,25 @@ into Bro:
     # Make sure this parses correctly at least.
     @TEST-EXEC: bro ${DOC_ROOT}/frameworks/sqlite-read-table.bro
 
-Afterwards, that table can be used to check logins into hosts against the available
+Afterwards, that table can be used to check logins into hosts against
-userlist.
+the available userlist.
 
 Turning Data into Events
 ------------------------
 
-The second mode is to use the SQLite reader to output the input data as events. Typically there
+The second mode is to use the SQLite reader to output the input data as events.
-are two reasons to do this. First, when the structure of the input data is too complicated
+Typically there are two reasons to do this. First, when the structure of
-for a direct table import. In this case, the data can be read into an event which can then
+the input data is too complicated for a direct table import. In this case,
-create the necessary data structures in Bro in scriptland.
+the data can be read into an event which can then create the necessary
+data structures in Bro in scriptland.
 
-The second reason is, that the dataset is too big to hold it in memory. In this case, the checks
+The second reason is, that the dataset is too big to hold it in memory. In
-can be performed on-demand, when Bro encounters a situation where it needs additional information.
+this case, the checks can be performed on-demand, when Bro encounters a
+situation where it needs additional information.
 
-An example for this would be an internal huge database with malware hashes. Live database queries
+An example for this would be an internal huge database with malware
-could be used to check the sporadically happening downloads against the database.
+hashes. Live database queries could be used to check the sporadically
+happening downloads against the database.
 
 The SQLite commands to create the schema are as follows::
 
@@ -151,9 +159,10 @@ The SQLite commands to create the schema are as follows::
     insert into malware_hashes values ('73f45106968ff8dc51fba105fa91306af1ff6666', 'ftp-trace');
 
 
-The following code uses the file-analysis framework to get the sha1 hashes of files that are
+The following code uses the file-analysis framework to get the sha1 hashes
-transmitted over the network. For each hash, a SQL-query is run against SQLite. If the query
+of files that are transmitted over the network. For each hash, a SQL-query
-returns with a result, we had a hit against our malware-database and output the matching hash.
+is run against SQLite. If the query returns with a result, we had a hit
+against our malware-database and output the matching hash.
 
 .. btest-include:: ${DOC_ROOT}/frameworks/sqlite-read-events.bro
 
@@ -162,5 +171,5 @@ returns with a result, we had a hit against our malware-database and output the
     # Make sure this parses correctly at least.
     @TEST-EXEC: bro ${DOC_ROOT}/frameworks/sqlite-read-events.bro
 
-If you run this script against the trace in ``testing/btest/Traces/ftp/ipv4.trace``, you
+If you run this script against the trace in
-will get one hit.
+``testing/btest/Traces/ftp/ipv4.trace``, you will get one hit.

doc/frameworks/logging.rst

@@ -19,195 +19,144 @@ Terminology
 
 Bro's logging interface is built around three main abstractions:
 
-    Log streams
+    Streams
-        A stream corresponds to a single log. It defines the set of
+        A log stream corresponds to a single log. It defines the set of
-        fields that a log consists of with their names and fields.
+        fields that a log consists of with their names and types.
-        Examples are the ``conn`` for recording connection summaries,
+        Examples are the ``conn`` stream for recording connection summaries,
         and the ``http`` stream for recording HTTP activity.
 
     Filters
         Each stream has a set of filters attached to it that determine
         what information gets written out. By default, each stream has
-        one default filter that just logs everything directly to disk
+        one default filter that just logs everything directly to disk.
-        with an automatically generated file name. However, further
+        However, additional filters can be added to record only a subset
-        filters can be added to record only a subset, split a stream
+        of the log records, write to different outputs, or set a custom
-        into different outputs, or to even duplicate the log to
+        rotation interval.  If all filters are removed from a stream,
-        multiple outputs. If all filters are removed from a stream,
+        then output is disabled for that stream.
-        all output is disabled.
 
     Writers
-        A writer defines the actual output format for the information
+        Each filter has a writer.  A writer defines the actual output
-        being logged. At the moment, Bro comes with only one type of
+        format for the information being logged. The default writer is
-        writer, which produces tab separated ASCII files. In the
+        the ASCII writer, which produces tab-separated ASCII files. Other
-        future we will add further writers, like for binary output and
+        writers are available, like for binary output or direct logging
-        direct logging into a database.
+        into a database.
 
-Basics
+There are several different ways to customize Bro's logging: you can create
-======
+a new log stream, you can extend an existing log with new fields, you
+can apply filters to an existing log stream, or you can customize the output
+format by setting log writer options.  All of these approaches are
+described in this document.
 
-The data fields that a stream records are defined by a record type
+Streams
-specified when it is created. Let's look at the script generating Bro's
+=======
-connection summaries as an example,
-:doc:`/scripts/base/protocols/conn/main.bro`. It defines a record
-:bro:type:`Conn::Info` that lists all the fields that go into
-``conn.log``, each marked with a ``&log`` attribute indicating that it
-is part of the information written out. To write a log record, the
-script then passes an instance of :bro:type:`Conn::Info` to the logging
-framework's :bro:id:`Log::write` function.
 
-By default, each stream automatically gets a filter named ``default``
+In order to log data to a new log stream, all of the following needs to be
-that generates the normal output by recording all record fields into a
+done:
-single output file.
 
-In the following, we summarize ways in which the logging can be
+- A :bro:type:`record` type must be defined which consists of all the
-customized. We continue using the connection summaries as our example
+  fields that will be logged (by convention, the name of this record type is
-to work with.
+  usually "Info").
+- A log stream ID (an :bro:type:`enum` with type name "Log::ID") must be
+  defined that uniquely identifies the new log stream.
+- A log stream must be created using the :bro:id:`Log::create_stream` function.
+- When the data to be logged becomes available, the :bro:id:`Log::write`
+  function must be called.
 
-Filtering
+In the following example, we create a new module "Foo" which creates
----------
+a new log stream.
-
-To create a new output file for an existing stream, you can add a
-new filter. A filter can, e.g., restrict the set of fields being
-logged:
 
 .. code:: bro
 
-    event bro_init()
+    module Foo;
+
+    export {
+        # Create an ID for our new stream. By convention, this is
+        # called "LOG".
+        redef enum Log::ID += { LOG };
+
+        # Define the record type that will contain the data to log.
+        type Info: record {
+            ts: time        &log;
+            id: conn_id     &log;
+            service: string &log &optional;
+            missed_bytes: count &log &default=0;
+        };
+    }
+
+    # Optionally, we can add a new field to the connection record so that
+    # the data we are logging (our "Info" record) will be easily
+    # accessible in a variety of event handlers.
+    redef record connection += {
+        # By convention, the name of this new field is the lowercase name
+        # of the module.
+        foo: Info &optional;
+    };
+
+    # This event is handled at a priority higher than zero so that if
+    # users modify this stream in another script, they can do so at the
+    # default priority of zero.
+    event bro_init() &priority=5
         {
-        # Add a new filter to the Conn::LOG stream that logs only
+        # Create the stream. This adds a default filter automatically.
-        # timestamp and originator address.
+        Log::create_stream(Foo::LOG, [$columns=Info, $path="foo"]);
-        local filter: Log::Filter = [$name="orig-only", $path="origs", $include=set("ts", "id.orig_h")];
-        Log::add_filter(Conn::LOG, filter);
         }
 
-Note the fields that are set for the filter:
+In the definition of the "Info" record above, notice that each field has the
+:bro:attr:`&log` attribute.  Without this attribute, a field will not appear in
+the log output. Also notice one field has the :bro:attr:`&optional` attribute.
+This indicates that the field might not be assigned any value before the
+log record is written.  Finally, a field with the :bro:attr:`&default`
+attribute has a default value assigned to it automatically.
 
-    ``name``
+At this point, the only thing missing is a call to the :bro:id:`Log::write`
-        A mandatory name for the filter that can later be used
+function to send data to the logging framework.  The actual event handler
-        to manipulate it further.
+where this should take place will depend on where your data becomes available.
-
+In this example, the :bro:id:`connection_established` event provides our data,
-    ``path``
+and we also store a copy of the data being logged into the
-        The filename for the output file, without any extension (which
+:bro:type:`connection` record:
-        may be automatically added by the writer). Default path values
-        are generated by taking the stream's ID and munging it slightly.
-        :bro:enum:`Conn::LOG` is converted into ``conn``,
-        :bro:enum:`PacketFilter::LOG` is converted into
-        ``packet_filter``, and :bro:enum:`Known::CERTS_LOG` is
-        converted into ``known_certs``.
-
-    ``include``
-        A set limiting the fields to the ones given. The names
-        correspond to those in the :bro:type:`Conn::Info` record, with
-        sub-records unrolled by concatenating fields (separated with
-        dots).
-
-Using the code above, you will now get a new log file ``origs.log``
-that looks like this::
-
-    #separator \x09
-    #path   origs
-    #fields ts      id.orig_h
-    #types  time    addr
-    1128727430.350788       141.42.64.125
-    1128727435.450898       141.42.64.125
-
-If you want to make this the only log file for the stream, you can
-remove the default filter (which, conveniently, has the name
-``default``):
 
 .. code:: bro
 
-    event bro_init()
+    event connection_established(c: connection)
         {
-        # Remove the filter called "default".
+        local rec: Foo::Info = [$ts=network_time(), $id=c$id];
-        Log::remove_filter(Conn::LOG, "default");
+
+        # Store a copy of the data in the connection record so other
+        # event handlers can access it.
+        c$foo = rec;
+
+        Log::write(Foo::LOG, rec);
         }
 
-An alternate approach to "turning off" a log is to completely disable
+If you run Bro with this script, a new log file ``foo.log`` will be created.
-the stream:
+Although we only specified four fields in the "Info" record above, the
+log output will actually contain seven fields because one of the fields
+(the one named "id") is itself a record type.  Since a :bro:type:`conn_id`
+record has four fields, then each of these fields is a separate column in
+the log output.  Note that the way that such fields are named in the log
+output differs slightly from the way we would refer to the same field
+in a Bro script (each dollar sign is replaced with a period).  For example,
+to access the first field of a ``conn_id`` in a Bro script we would use
+the notation ``id$orig_h``, but that field is named ``id.orig_h``
+in the log output.
 
-.. code:: bro
+When you are developing scripts that add data to the :bro:type:`connection`
+record, care must be given to when and how long data is stored.
+Normally data saved to the connection record will remain there for the
+duration of the connection and from a practical perspective it's not
+uncommon to need to delete that data before the end of the connection.
 
-    event bro_init()
-        {
-        Log::disable_stream(Conn::LOG);
-        }
 
-If you want to skip only some fields but keep the rest, there is a
+Add Fields to a Log
-corresponding ``exclude`` filter attribute that you can use instead of
+-------------------
-``include`` to list only the ones you are not interested in.
 
-A filter can also determine output paths *dynamically* based on the
+You can add additional fields to a log by extending the record
-record being logged. That allows, e.g., to record local and remote
+type that defines its content, and setting a value for the new fields
-connections into separate files. To do this, you define a function
+before each log record is written.
-that returns the desired path:
 
-.. code:: bro
+Let's say we want to add a boolean field ``is_private`` to
-
+:bro:type:`Conn::Info` that indicates whether the originator IP address
-    function split_log(id: Log::ID, path: string, rec: Conn::Info) : string
+is part of the :rfc:`1918` space:
-        {
-        # Return "conn-local" if originator is a local IP, otherwise "conn-remote".
-        local lr = Site::is_local_addr(rec$id$orig_h) ? "local" : "remote";
-        return fmt("%s-%s", path, lr);
-        }
-
-    event bro_init()
-        {
-        local filter: Log::Filter = [$name="conn-split", $path_func=split_log, $include=set("ts", "id.orig_h")];
-        Log::add_filter(Conn::LOG, filter);
-        }
-
-Running this will now produce two files, ``local.log`` and
-``remote.log``, with the corresponding entries. One could extend this
-further for example to log information by subnets or even by IP
-address. Be careful, however, as it is easy to create many files very
-quickly ...
-
-.. sidebar:: A More Generic Path Function
-
-    The ``split_log`` method has one draw-back: it can be used
-    only with the :bro:enum:`Conn::LOG` stream as the record type is hardcoded
-    into its argument list. However, Bro allows to do a more generic
-    variant:
-
-    .. code:: bro
-
-        function split_log(id: Log::ID, path: string, rec: record { id: conn_id; } ) : string
-            {
-            return Site::is_local_addr(rec$id$orig_h) ? "local" : "remote";
-            }
-
-    This function can be used with all log streams that have records
-    containing an ``id: conn_id`` field.
-
-While so far we have seen how to customize the columns being logged,
-you can also control which records are written out by providing a
-predicate that will be called for each log record:
-
-.. code:: bro
-
-    function http_only(rec: Conn::Info) : bool
-        {
-        # Record only connections with successfully analyzed HTTP traffic
-        return rec$service == "http";
-        }
-
-    event bro_init()
-        {
-        local filter: Log::Filter = [$name="http-only", $path="conn-http", $pred=http_only];
-        Log::add_filter(Conn::LOG, filter);
-        }
-
-This will result in a log file ``conn-http.log`` that contains only
-traffic detected and analyzed as HTTP traffic.
-
-Extending
----------
-
-You can add further fields to a log stream by extending the record
-type that defines its content. Let's say we want to add a boolean
-field ``is_private`` to :bro:type:`Conn::Info` that indicates whether the
-originator IP address is part of the :rfc:`1918` space:
 
 .. code:: bro
 
@@ -218,9 +167,21 @@ originator IP address is part of the :rfc:`1918` space:
         is_private: bool &default=F &log;
     };
 
+As this example shows, when extending a log stream's "Info" record, each
+new field must always be declared either with a ``&default`` value or
+as ``&optional``.  Furthermore, you need to add the ``&log`` attribute
+or otherwise the field won't appear in the log file.
 
-Now we need to set the field. A connection's summary is generated at
+Now we need to set the field.  Although the details vary depending on which
-the time its state is removed from memory. We can add another handler
+log is being extended, in general it is important to choose a suitable event
+in which to set the additional fields because we need to make sure that
+the fields are set before the log record is written.  Sometimes the right
+choice is the same event which writes the log record, but at a higher
+priority (in order to ensure that the event handler that sets the additional
+fields is executed before the event handler that writes the log record).
+
+In this example, since a connection's summary is generated at
+the time its state is removed from memory, we can add another handler
 at that time that sets our field correctly:
 
 .. code:: bro
@@ -232,31 +193,58 @@ at that time that sets our field correctly:
         }
 
 Now ``conn.log`` will show a new field ``is_private`` of type
-``bool``.
+``bool``.  If you look at the Bro script which defines the connection
+log stream :doc:`/scripts/base/protocols/conn/main.bro`, you will see
+that ``Log::write`` gets called in an event handler for the
+same event as used in this example to set the additional fields, but at a
+lower priority than the one used in this example (i.e., the log record gets
+written after we assign the ``is_private`` field).
 
-Notes:
+For extending logs this way, one needs a bit of knowledge about how
+the script that creates the log stream is organizing its state
+keeping. Most of the standard Bro scripts attach their log state to
+the :bro:type:`connection` record where it can then be accessed, just
+like ``c$conn`` above. For example, the HTTP analysis adds a field
+``http`` of type :bro:type:`HTTP::Info` to the :bro:type:`connection`
+record.
 
-- For extending logs this way, one needs a bit of knowledge about how
-  the script that creates the log stream is organizing its state
-  keeping. Most of the standard Bro scripts attach their log state to
-  the :bro:type:`connection` record where it can then be accessed, just
-  as the ``c$conn`` above. For example, the HTTP analysis adds a field
-  ``http`` of type :bro:type:`HTTP::Info` to the :bro:type:`connection`
-  record. See the script reference for more information.
 
-- When extending records as shown above, the new fields must always be
+Define a Logging Event
-  declared either with a ``&default`` value or as ``&optional``.
+----------------------
-  Furthermore, you need to add the ``&log`` attribute or otherwise the
-  field won't appear in the output.
-
-Hooking into the Logging
-------------------------
 
 Sometimes it is helpful to do additional analysis of the information
 being logged. For these cases, a stream can specify an event that will
-be generated every time a log record is written to it. All of Bro's
+be generated every time a log record is written to it.  To do this, we
-default log streams define such an event. For example, the connection
+need to modify the example module shown above to look something like this:
-log stream raises the event :bro:id:`Conn::log_conn`. You
+
+.. code:: bro
+
+    module Foo;
+
+    export {
+        redef enum Log::ID += { LOG };
+
+        type Info: record {
+            ts: time     &log;
+            id: conn_id  &log;
+            service: string &log &optional;
+            missed_bytes: count &log &default=0;
+        };
+
+        # Define a logging event. By convention, this is called
+        # "log_<stream>".
+        global log_foo: event(rec: Info);
+    }
+
+    event bro_init() &priority=5
+        {
+        # Specify the "log_foo" event here in order for Bro to raise it.
+        Log::create_stream(Foo::LOG, [$columns=Info, $ev=log_foo,
+                           $path="foo"]);
+        }
+
+All of Bro's default log streams define such an event. For example, the
+connection log stream raises the event :bro:id:`Conn::log_conn`. You
 could use that for example for flagging when a connection to a
 specific destination exceeds a certain duration:
 
@@ -270,7 +258,7 @@ specific destination exceeds a certain duration:
 
     event Conn::log_conn(rec: Conn::Info)
         {
-        if ( rec$duration > 5mins )
+        if ( rec?$duration && rec$duration > 5mins )
             NOTICE([$note=Long_Conn_Found,
                     $msg=fmt("unusually long conn to %s", rec$id$resp_h),
                     $id=rec$id]);
@@ -281,15 +269,196 @@ externally with Perl scripts. Much of what such an external script
 would do later offline, one may instead do directly inside of Bro in
 real-time.
 
-Rotation
+Disable a Stream
---------
+----------------
 
-By default, no log rotation occurs, but it's globally controllable for all
+One way to "turn off" a log is to completely disable the stream.  For
-filters by redefining the :bro:id:`Log::default_rotation_interval` option:
+example, the following example will prevent the conn.log from being written:
 
 .. code:: bro
 
-    redef Log::default_rotation_interval = 1 hr;
+    event bro_init()
+        {
+        Log::disable_stream(Conn::LOG);
+        }
+
+Note that this must run after the stream is created, so the priority
+of this event handler must be lower than the priority of the event handler
+where the stream was created.
+
+
+Filters
+=======
+
+A stream has one or more filters attached to it (a stream without any filters
+will not produce any log output).  When a stream is created, it automatically
+gets a default filter attached to it.  This default filter can be removed
+or replaced, or other filters can be added to the stream.  This is accomplished
+by using either the :bro:id:`Log::add_filter` or :bro:id:`Log::remove_filter`
+function.  This section shows how to use filters to do such tasks as
+rename a log file, split the output into multiple files, control which
+records are written, and set a custom rotation interval.
+
+Rename Log File
+---------------
+
+Normally, the log filename for a given log stream is determined when the
+stream is created, unless you explicitly specify a different one by adding
+a filter.
+
+The easiest way to change a log filename is to simply replace the
+default log filter with a new filter that specifies a value for the "path"
+field.  In this example, "conn.log" will be changed to "myconn.log":
+
+.. code:: bro
+
+    event bro_init()
+        {
+        # Replace default filter for the Conn::LOG stream in order to
+        # change the log filename.
+
+        local f = Log::get_filter(Conn::LOG, "default");
+        f$path = "myconn";
+        Log::add_filter(Conn::LOG, f);
+        }
+
+Keep in mind that the "path" field of a log filter never contains the
+filename extension.  The extension will be determined later by the log writer.
+
+Add a New Log File
+------------------
+
+Normally, a log stream writes to only one log file.  However, you can
+add filters so that the stream writes to multiple files.  This is useful
+if you want to restrict the set of fields being logged to the new file.
+
+In this example, a new filter is added to the Conn::LOG stream that writes
+two fields to a new log file:
+
+.. code:: bro
+
+    event bro_init()
+        {
+        # Add a new filter to the Conn::LOG stream that logs only
+        # timestamp and originator address.
+
+        local filter: Log::Filter = [$name="orig-only", $path="origs",
+                                     $include=set("ts", "id.orig_h")];
+        Log::add_filter(Conn::LOG, filter);
+        }
+
+
+Notice how the "include" filter attribute specifies a set that limits the
+fields to the ones given. The names correspond to those in the
+:bro:type:`Conn::Info` record (however, because the "id" field is itself a
+record, we can specify an individual field of "id" by the dot notation
+shown in the example).
+
+Using the code above, in addition to the regular ``conn.log``, you will
+now also get a new log file ``origs.log`` that looks like the regular
+``conn.log``, but will have only the fields specified in the "include"
+filter attribute.
+
+If you want to skip only some fields but keep the rest, there is a
+corresponding ``exclude`` filter attribute that you can use instead of
+``include`` to list only the ones you are not interested in.
+
+If you want to make this the only log file for the stream, you can
+remove the default filter:
+
+.. code:: bro
+
+    event bro_init()
+        {
+        # Remove the filter called "default".
+        Log::remove_filter(Conn::LOG, "default");
+        }
+
+Determine Log Path Dynamically
+------------------------------
+
+Instead of using the "path" filter attribute, a filter can determine
+output paths *dynamically* based on the record being logged. That
+allows, e.g., to record local and remote connections into separate
+files. To do this, you define a function that returns the desired path,
+and use the "path_func" filter attribute:
+
+.. code:: bro
+
+    # Note: if using BroControl then you don't need to redef local_nets.
+    redef Site::local_nets = { 192.168.0.0/16 };
+
+    function myfunc(id: Log::ID, path: string, rec: Conn::Info) : string
+        {
+        # Return "conn-local" if originator is a local IP, otherwise
+        # return "conn-remote".
+        local r = Site::is_local_addr(rec$id$orig_h) ? "local" : "remote";
+        return fmt("%s-%s", path, r);
+        }
+
+    event bro_init()
+        {
+        local filter: Log::Filter = [$name="conn-split",
+                 $path_func=myfunc, $include=set("ts", "id.orig_h")];
+        Log::add_filter(Conn::LOG, filter);
+        }
+
+Running this will now produce two new files, ``conn-local.log`` and
+``conn-remote.log``, with the corresponding entries (for this example to work,
+the ``Site::local_nets`` must specify your local network). One could extend
+this further for example to log information by subnets or even by IP
+address. Be careful, however, as it is easy to create many files very
+quickly.
+
+The ``myfunc`` function has one drawback: it can be used
+only with the :bro:enum:`Conn::LOG` stream as the record type is hardcoded
+into its argument list. However, Bro allows to do a more generic
+variant:
+
+.. code:: bro
+
+    function myfunc(id: Log::ID, path: string,
+                    rec: record { id: conn_id; } ) : string
+        {
+        local r = Site::is_local_addr(rec$id$orig_h) ? "local" : "remote";
+        return fmt("%s-%s", path, r);
+        }
+
+This function can be used with all log streams that have records
+containing an ``id: conn_id`` field.
+
+Filter Log Records
+------------------
+
+We have seen how to customize the columns being logged, but
+you can also control which records are written out by providing a
+predicate that will be called for each log record:
+
+.. code:: bro
+
+    function http_only(rec: Conn::Info) : bool
+        {
+        # Record only connections with successfully analyzed HTTP traffic
+        return rec?$service && rec$service == "http";
+        }
+
+    event bro_init()
+        {
+        local filter: Log::Filter = [$name="http-only", $path="conn-http",
+                                     $pred=http_only];
+        Log::add_filter(Conn::LOG, filter);
+        }
+
+This will result in a new log file ``conn-http.log`` that contains only
+the log records from ``conn.log`` that are analyzed as HTTP traffic.
+
+Rotation
+--------
+
+The log rotation interval is globally controllable for all
+filters by redefining the :bro:id:`Log::default_rotation_interval` option
+(note that when using BroControl, this option is set automatically via
+the BroControl configuration).
 
 Or specifically for certain :bro:type:`Log::Filter` instances by setting
 their ``interv`` field.  Here's an example of changing just the
@@ -301,90 +470,72 @@ their ``interv`` field.  Here's an example of changing just the
         {
         local f = Log::get_filter(Conn::LOG, "default");
         f$interv = 1 min;
-        Log::remove_filter(Conn::LOG, "default");
         Log::add_filter(Conn::LOG, f);
         }
 
-ASCII Writer Configuration
+Writers
---------------------------
+=======
 
-The ASCII writer has a number of options for customizing the format of
+Each filter has a writer.  If you do not specify a writer when adding a
-its output, see :doc:`/scripts/base/frameworks/logging/writers/ascii.bro`.
+filter to a stream, then the ASCII writer is the default.
 
-Adding Streams
+There are two ways to specify a non-default writer.  To change the default
-==============
+writer for all log filters, just redefine the :bro:id:`Log::default_writer`
+option.  Alternatively, you can specify the writer to use on a per-filter
+basis by setting a value for the filter's "writer" field.  Consult the
+documentation of the writer to use to see if there are other options that are
+needed.
 
-It's easy to create a new log stream for custom scripts. Here's an
+ASCII Writer
-example for the ``Foo`` module:
+------------
+
+By default, the ASCII writer outputs log files that begin with several
+lines of metadata, followed by the actual log output.  The metadata
+describes the format of the log file, the "path" of the log (i.e., the log
+filename without file extension), and also specifies the time that the log
+was created and the time when Bro finished writing to it.
+The ASCII writer has a number of options for customizing the format of its
+output, see :doc:`/scripts/base/frameworks/logging/writers/ascii.bro`.
+If you change the output format options, then be careful to check whether
+your postprocessing scripts can still recognize your log files.
+
+Some writer options are global (i.e., they affect all log filters using
+that log writer).  For example, to change the output format of all ASCII
+logs to JSON format:
 
 .. code:: bro
 
-    module Foo;
+    redef LogAscii::use_json = T;
 
-    export {
+Some writer options are filter-specific (i.e., they affect only the filters
-        # Create an ID for our new stream. By convention, this is
+that explicitly specify the option).  For example, to change the output
-        # called "LOG".
+format of the ``conn.log`` only:
-        redef enum Log::ID += { LOG };
 
-        # Define the fields. By convention, the type is called "Info".
+.. code:: bro
-        type Info: record {
-            ts: time     &log;
-            id: conn_id  &log;
-        };
 
-        # Define a hook event. By convention, this is called
+    event bro_init()
-        # "log_<stream>".
-        global log_foo: event(rec: Info);
-
-    }
-
-    # This event should be handled at a higher priority so that when
-    # users modify your stream later and they do it at priority 0,
-    # their code runs after this.
-    event bro_init() &priority=5
         {
-        # Create the stream. This also adds a default filter automatically.
+        local f = Log::get_filter(Conn::LOG, "default");
-        Log::create_stream(Foo::LOG, [$columns=Info, $ev=log_foo]);
+        # Use tab-separated-value mode
+        f$config = table(["tsv"] = "T");
+        Log::add_filter(Conn::LOG, f);
         }
 
-You can also add the state to the :bro:type:`connection` record to make
-it easily accessible across event handlers:
-
-.. code:: bro
-
-    redef record connection += {
-        foo: Info &optional;
-        }
-
-Now you can use the :bro:id:`Log::write` method to output log records and
-save the logged ``Foo::Info`` record into the connection record:
-
-.. code:: bro
-
-    event connection_established(c: connection)
-        {
-        local rec: Foo::Info = [$ts=network_time(), $id=c$id];
-        c$foo = rec;
-        Log::write(Foo::LOG, rec);
-        }
-
-See the existing scripts for how to work with such a new connection
-field. A simple example is :doc:`/scripts/base/protocols/syslog/main.bro`.
-
-When you are developing scripts that add data to the :bro:type:`connection`
-record, care must be given to when and how long data is stored.
-Normally data saved to the connection record will remain there for the
-duration of the connection and from a practical perspective it's not
-uncommon to need to delete that data before the end of the connection.
 
 Other Writers
 -------------
 
-Bro supports the following built-in output formats other than ASCII:
+Bro supports the following additional built-in output formats:
 
 .. toctree::
    :maxdepth: 1
 
    logging-input-sqlite
 
-Further formats are available as external plugins.
+Additional writers are available as external plugins:
+
+.. toctree::
+   :maxdepth: 1
+
+   ../components/bro-plugins/README
+

doc/frameworks/notice.rst

@@ -88,15 +88,15 @@ directly make modifications to the :bro:see:`Notice::Info` record
 given as the argument to the hook.
 
 Here's a simple example which tells Bro to send an email for all notices of
-type :bro:see:`SSH::Password_Guessing` if the server is 10.0.0.1:
+type :bro:see:`SSH::Password_Guessing` if the guesser attempted to log in to
+the server at 192.168.56.103:
 
-.. code:: bro
+.. btest-include:: ${DOC_ROOT}/frameworks/notice_ssh_guesser.bro
 
-    hook Notice::policy(n: Notice::Info)
+.. btest:: notice_ssh_guesser.bro
-      {
+
-      if ( n$note == SSH::Password_Guessing && n$id$resp_h == 10.0.0.1 )
+    @TEST-EXEC: btest-rst-cmd bro -C -r ${TRACES}/ssh/sshguess.pcap ${DOC_ROOT}/frameworks/notice_ssh_guesser.bro
-        add n$actions[Notice::ACTION_EMAIL];
+    @TEST-EXEC: btest-rst-cmd cat notice.log
-      }
 
 .. note::
 
@@ -111,10 +111,9 @@ a hook body to run before default hook bodies might look like this:
 .. code:: bro
 
     hook Notice::policy(n: Notice::Info) &priority=5
-      {
+        {
-      if ( n$note == SSH::Password_Guessing && n$id$resp_h == 10.0.0.1 )
+        # Insert your code here.
-        add n$actions[Notice::ACTION_EMAIL];
+        }
-      }
 
 Hooks can also abort later hook bodies with the ``break`` keyword. This
 is primarily useful if one wants to completely preempt processing by

doc/frameworks/notice_ssh_guesser.bro

@@ -0,0 +1,10 @@
+
+@load protocols/ssh/detect-bruteforcing
+
+redef SSH::password_guesses_limit=10;
+
+hook Notice::policy(n: Notice::Info)
+	{
+	if ( n$note == SSH::Password_Guessing && /192\.168\.56\.103/ in n$sub )
+		add n$actions[Notice::ACTION_EMAIL];
+	}

doc/httpmonitor/file_extraction.bro

@@ -7,15 +7,18 @@ global mime_to_ext: table[string] of string = {
 	["text/html"] = "html",
 };
 
-event file_mime_type(f: fa_file, mime_type: string)
+event file_sniff(f: fa_file, meta: fa_metadata)
 	{
 	if ( f$source != "HTTP" )
 		return;
 
-	if ( mime_type !in mime_to_ext )
+	if ( ! meta?$mime_type )
 		return;
 
-	local fname = fmt("%s-%s.%s", f$source, f$id, mime_to_ext[mime_type]);
+	if ( meta$mime_type !in mime_to_ext )
+		return;
+
+	local fname = fmt("%s-%s.%s", f$source, f$id, mime_to_ext[meta$mime_type]);
 	print fmt("Extracting file %s", fname);
 	Files::add_analyzer(f, Files::ANALYZER_EXTRACT, [$extract_filename=fname]);
 	}

doc/install/guidelines.rst

@@ -8,10 +8,12 @@ How to Upgrade
 If you're doing an upgrade install (rather than a fresh install),
 there's two suggested approaches: either install Bro using the same
 installation prefix directory as before, or pick a new prefix and copy
-local customizations over.  Regardless of which approach you choose,
+local customizations over.
-if you are using BroControl, then after upgrading Bro you will need to
+
-run "broctl check" (to verify that your new configuration is OK)
+Regardless of which approach you choose, if you are using BroControl, then
-and "broctl install" to complete the upgrade process.
+before doing the upgrade you should stop all running Bro processes with the
+"broctl stop" command.  After the upgrade is complete then you will need
+to run "broctl deploy".
 
 In the following we summarize general guidelines for upgrading, see
 the :ref:`release-notes` for version-specific information.
@@ -44,4 +46,4 @@ where Bro was originally installed).  Review the files for differences
 before copying and make adjustments as necessary (use the new version for
 differences that aren't a result of a local change).  Of particular note,
 the copied version of ``$prefix/etc/broctl.cfg`` is likely to need changes
-to the ``SpoolDir`` and ``LogDir`` settings.
+to any settings that specify a pathname.

doc/install/install.rst

@@ -4,7 +4,7 @@
 .. _MacPorts: http://www.macports.org
 .. _Fink: http://www.finkproject.org
 .. _Homebrew: http://brew.sh
-.. _bro downloads page: http://bro.org/download/index.html
+.. _bro downloads page: https://www.bro.org/download/index.html
 
 .. _installing-bro:
 
@@ -32,22 +32,24 @@ before you begin:
     * Libz
     * Bash (for BroControl)
     * Python (for BroControl)
+    * C++ Actor Framework (CAF) version 0.14 (http://actor-framework.org)
 
 To build Bro from source, the following additional dependencies are required:
 
     * CMake 2.8 or greater              (http://www.cmake.org)
     * Make
-    * C/C++ compiler
+    * C/C++ compiler with C++11 support (GCC 4.8+ or Clang 3.3+)
     * SWIG                              (http://www.swig.org)
     * Bison (GNU Parser Generator)
     * Flex  (Fast Lexical Analyzer)
     * Libpcap headers                   (http://www.tcpdump.org)
     * OpenSSL headers                   (http://www.openssl.org)
     * zlib headers
-    * Perl
+    * Python
 
-To install the required dependencies, you can use (when done, make sure
+To install CAF, first download the source code of the required version from: https://github.com/actor-framework/actor-framework/releases
-that ``bash`` and ``python`` are in your ``PATH``):
+
+To install the required dependencies, you can use:
 
 * RPM/RedHat-based Linux:
 
@@ -68,19 +70,41 @@ that ``bash`` and ``python`` are in your ``PATH``):
 
   .. console::
 
-      sudo pkg_add -r bash cmake swig bison python perl
+      sudo pkg install bash cmake swig bison python py27-sqlite3
+
+  Note that in older versions of FreeBSD, you might have to use the
+  "pkg_add -r" command instead of "pkg install".
+
+  For older versions of FreeBSD (especially FreeBSD 9.x), the system compiler
+  is not new enough to compile Bro. For these systems, you will have to install
+  a newer compiler using pkg; the ``clang34`` package should work.
+
+  You will also have to define several environment variables on these older
+  systems to use the new compiler and headers similar to this before calling
+  configure:
+
+  .. console::
+
+     export CC=clang34
+     export CXX=clang++34
+     export CXXFLAGS="-stdlib=libc++ -I${LOCALBASE}/include/c++/v1 -L${LOCALBASE}/lib"
+     export LDFLAGS="-pthread"
 
 * Mac OS X:
 
-  Compiling source code on Macs requires first downloading Xcode_,
+  Compiling source code on Macs requires first installing Xcode_ (in older
-  then going through its "Preferences..." -> "Downloads" menus to
+  versions of Xcode, you would then need to go through its
-  install the "Command Line Tools" component.
+  "Preferences..." -> "Downloads" menus to install the "Command Line Tools"
+  component).
 
-  OS X comes with all required dependencies except for CMake_ and SWIG_.
+  OS X comes with all required dependencies except for CMake_, SWIG_,
-  Distributions of these dependencies can likely be obtained from your
+  OpenSSL, and CAF. (OpenSSL used to be part of OS X versions 10.10
-  preferred Mac OS X package management system (e.g. MacPorts_, Fink_,
+  and older, for which it does not need to be installed manually. It
-  or Homebrew_).  Specifically for MacPorts, the ``cmake``, ``swig``,
+  was removed in OS X 10.11). Distributions of these dependencies can
-  and ``swig-python`` packages provide the required dependencies.
+  likely be obtained from your preferred Mac OS X package management
+  system (e.g. Homebrew_, MacPorts_, or Fink_). Specifically for
+  Homebrew, the ``cmake``, ``swig``, ``openssl`` and ``caf`` packages
+  provide the required dependencies.
 
 
 Optional Dependencies
@@ -93,8 +117,9 @@ build time:
     * sendmail (enables Bro and BroControl to send mail)
     * curl (used by a Bro script that implements active HTTP)
     * gperftools (tcmalloc is used to improve memory and CPU usage)
+    * jemalloc (http://www.canonware.com/jemalloc/)
+    * PF_RING (Linux only, see :doc:`Cluster Configuration <../configuration/index>`)
     * ipsumdump (for trace-summary; http://www.cs.ucla.edu/~kohler/ipsumdump)
-    * Ruby executable, library, and headers (for Broccoli Ruby bindings)
 
 LibGeoIP is probably the most interesting and can be installed
 on most platforms by following the instructions for :ref:`installing
@@ -110,40 +135,30 @@ code forms.
 
 
 Using Pre-Built Binary Release Packages
-=======================================
+---------------------------------------
 
 See the `bro downloads page`_ for currently supported/targeted
-platforms for binary releases.
+platforms for binary releases and for installation instructions.
 
-* RPM
+* Linux Packages
 
-  .. console::
+  Linux based binary installations are usually performed by adding
-
+  information about the Bro packages to the respective system packaging
-      sudo yum localinstall Bro-*.rpm
+  tool. Then the usual system utilities such as ``apt``, ``dnf``, ``yum``,
-
+  or ``zypper`` are used to perform the installation.
-* DEB
-
-  .. console::
-
-      sudo gdebi Bro-*.deb
-
-* MacOS Disk Image with Installer
-
-  Just open the ``Bro-*.dmg`` and then run the ``.pkg`` installer.
-  Everything installed by the package will go into ``/opt/bro``.
 
 The primary install prefix for binary packages is ``/opt/bro``.
-Non-MacOS packages that include BroControl also put variable/runtime
-data (e.g. Bro logs) in ``/var/opt/bro``.
 
 Installing from Source
-==========================
+----------------------
 
 Bro releases are bundled into source packages for convenience and are
-available on the `bro downloads page`_. Alternatively, the latest
+available on the `bro downloads page`_.
-Bro development version can be obtained through git repositories
+
+Alternatively, the latest Bro development version
+can be obtained through git repositories
 hosted at ``git.bro.org``.  See our `git development documentation
-<http://bro.org/development/howtos/process.html>`_ for comprehensive
+<https://www.bro.org/development/howtos/process.html>`_ for comprehensive
 information on Bro's use of git revision control, but the short story
 for downloading the full source code experience for Bro via git is:
 
@@ -164,13 +179,23 @@ run ``./configure --help``):
     make
     make install
 
+If the ``configure`` script fails, then it is most likely because it either
+couldn't find a required dependency or it couldn't find a sufficiently new
+version of a dependency.  Assuming that you already installed all required
+dependencies, then you may need to use one of the ``--with-*`` options
+that can be given to the ``configure`` script to help it locate a dependency.
+
 The default installation path is ``/usr/local/bro``, which would typically
 require root privileges when doing the ``make install``.  A different
-installation path can be chosen by specifying the ``--prefix`` option.
+installation path can be chosen by specifying the ``configure`` script
-Note that ``/usr`` and ``/opt/bro`` are the
+``--prefix`` option.  Note that ``/usr`` and ``/opt/bro`` are the
 standard prefixes for binary Bro packages to be installed, so those are
 typically not good choices unless you are creating such a package.
 
+OpenBSD users, please see our `FAQ
+<https://www.bro.org/documentation/faq.html>`_ if you are having
+problems installing Bro.
+
 Depending on the Bro package you downloaded, there may be auxiliary
 tools and libraries available in the ``aux/`` directory. Some of them
 will be automatically built and installed along with Bro. There are
@@ -179,10 +204,6 @@ turn off unwanted auxiliary projects that would otherwise be installed
 automatically.  Finally, use ``make install-aux`` to install some of
 the other programs that are in the ``aux/bro-aux`` directory.
 
-OpenBSD users, please see our `FAQ
-<//www.bro.org/documentation/faq.html>`_ if you are having
-problems installing Bro.
-
 Finally, if you want to build the Bro documentation (not required, because
 all of the documentation for the latest Bro release is available on the
 Bro web site), there are instructions in ``doc/README`` in the source
@@ -191,7 +212,7 @@ distribution.
 Configure the Run-Time Environment
 ==================================
 
-Just remember that you may need to adjust your ``PATH`` environment variable
+You may want to adjust your ``PATH`` environment variable
 according to the platform/shell/package you're using.  For example:
 
 Bourne-Shell Syntax:

doc/mimestats/mimestats.bro

@@ -30,7 +30,7 @@ export {
 
 event bro_init() &priority=3
 	{
-	Log::create_stream(MimeMetrics::LOG, [$columns=Info]);
+	Log::create_stream(MimeMetrics::LOG, [$columns=Info, $path="mime_metrics"]);
 	local r1: SumStats::Reducer = [$stream="mime.bytes",
 	                               $apply=set(SumStats::SUM)];
 	local r2: SumStats::Reducer = [$stream="mime.hits", 

doc/quickstart/conditional-notice.bro

@@ -0,0 +1,24 @@
+@load protocols/ssl/expiring-certs
+
+const watched_servers: set[addr] = {
+	87.98.220.10,
+} &redef;
+
+# Site::local_nets usually isn't something you need to modify if
+# BroControl automatically sets it up from networks.cfg.  It's
+# shown here for completeness.
+redef Site::local_nets += {
+	87.98.0.0/16,
+};
+
+hook Notice::policy(n: Notice::Info)
+	{
+	if ( n$note != SSL::Certificate_Expired )
+		return;
+
+	if ( n$id$resp_h !in watched_servers )
+		return;
+
+	add n$actions[Notice::ACTION_EMAIL];
+	}
+

doc/quickstart/index.rst

@@ -24,9 +24,10 @@ Managing Bro with BroControl
 BroControl is an interactive shell for easily operating/managing Bro
 installations on a single system or even across multiple systems in a
 traffic-monitoring cluster.  This section explains how to use BroControl
-to manage a stand-alone Bro installation.  For instructions on how to
+to manage a stand-alone Bro installation.  For a complete reference on
-configure a Bro cluster, see the :doc:`Cluster Configuration
+BroControl, see the :doc:`BroControl <../components/broctl/README>`
-<../configuration/index>` documentation.
+documentation.  For instructions on how to configure a Bro cluster,
+see the :doc:`Cluster Configuration <../configuration/index>` documentation.
 
 A Minimal Starting Configuration
 --------------------------------
@@ -156,9 +157,11 @@ changes we want to make:
    notice that means an SSL connection was established and the server's
    certificate couldn't be validated using Bro's default trust roots, but
    we want to ignore it.
-2) ``SSH::Login`` is a notice type that is triggered when an SSH connection
+2) ``SSL::Certificate_Expired`` is a notice type that is triggered when
-   attempt looks like it may have been successful, and we want email when
+   an SSL connection was established using an expired certificate.  We
-   that happens, but only for certain servers.
+   want email when that happens, but only for certain servers on the
+   local network (Bro can also proactively monitor for certs that will
+   soon expire, but this is just for demonstration purposes).
 
 We've defined *what* we want to do, but need to know *where* to do it.
 The answer is to use a script written in the Bro programming language, so
@@ -203,7 +206,7 @@ the variable's value may not change at run-time, but whose initial value can be
 modified via the ``redef`` operator at parse-time.
 
 Let's continue on our path to modify the behavior for the two SSL
-and SSH notices.  Looking at :doc:`/scripts/base/frameworks/notice/main.bro`,
+notices.  Looking at :doc:`/scripts/base/frameworks/notice/main.bro`,
 we see that it advertises:
 
 .. code:: bro
@@ -216,7 +219,7 @@ we see that it advertises:
         const ignored_types: set[Notice::Type] = {} &redef;
     }
 
-That's exactly what we want to do for the SSL notice.  Add to ``local.bro``:
+That's exactly what we want to do for the first notice.  Add to ``local.bro``:
 
 .. code:: bro
 
@@ -248,38 +251,30 @@ is valid before installing it and then restarting the Bro instance:
    stopping bro ...
    starting bro ...
 
-Now that the SSL notice is ignored, let's look at how to send an email on
+Now that the SSL notice is ignored, let's look at how to send an email
-the SSH notice.  The notice framework has a similar option called
+on the other notice.  The notice framework has a similar option called
-``emailed_types``, but using that would generate email for all SSH servers and
+``emailed_types``, but using that would generate email for all SSL
-we only want email for logins to certain ones.  There is a ``policy`` hook
+servers with expired certificates and we only want email for connections
-that is actually what is used to implement the simple functionality of
+to certain ones.  There is a ``policy`` hook that is actually what is
-``ignored_types`` and
+used to implement the simple functionality of ``ignored_types`` and
-``emailed_types``, but it's extensible such that the condition and action taken
+``emailed_types``, but it's extensible such that the condition and
-on notices can be user-defined.
+action taken on notices can be user-defined.
 
-In ``local.bro``, let's define a new ``policy`` hook handler body
+In ``local.bro``, let's define a new ``policy`` hook handler body:
-that takes the email action for SSH logins only for a defined set of servers:
 
-.. code:: bro
+.. btest-include:: ${DOC_ROOT}/quickstart/conditional-notice.bro
 
-    const watched_servers: set[addr] = {
+.. btest:: conditional-notice
-        192.168.1.100,
-        192.168.1.101,
-        192.168.1.102,
-    } &redef;
 
-   hook Notice::policy(n: Notice::Info)
+    @TEST-EXEC: btest-rst-cmd bro -r ${TRACES}/tls/tls-expired-cert.trace ${DOC_ROOT}/quickstart/conditional-notice.bro
-       {
+    @TEST-EXEC: btest-rst-cmd cat notice.log
-       if ( n$note == SSH::SUCCESSFUL_LOGIN && n$id$resp_h in watched_servers )
-            add n$actions[Notice::ACTION_EMAIL];
-       }
 
 You'll just have to trust the syntax for now, but what we've done is
 first declare our own variable to hold a set of watched addresses,
-``watched_servers``; then added a hook handler body to the policy that will
+``watched_servers``; then added a hook handler body to the policy that
-generate an email whenever the notice type is an SSH login and the responding
+will generate an email whenever the notice type is an SSL expired
-host stored
+certificate and the responding host stored inside the ``Info`` record's
-inside the ``Info`` record's connection field is in the set of watched servers.
+connection field is in the set of watched servers.
 
 .. note:: Record field member access is done with the '$' character
    instead of a '.' as might be expected from other languages, in

doc/script-reference/attributes.rst

@@ -43,8 +43,6 @@ The Bro scripting language supports the following attributes.
 +-----------------------------+-----------------------------------------------+
 | :bro:attr:`&mergeable`      |Prefer set union for synchronized state.       |
 +-----------------------------+-----------------------------------------------+
-| :bro:attr:`&group`          |Group event handlers to activate/deactivate.   |
-+-----------------------------+-----------------------------------------------+
 | :bro:attr:`&error_handler`  |Used internally for reporter framework events. |
 +-----------------------------+-----------------------------------------------+
 | :bro:attr:`&type_column`    |Used by input framework for "port" type.       |
@@ -56,13 +54,16 @@ Here is a more detailed explanation of each attribute:
 
 .. bro:attr:: &redef
 
-    Allows for redefinition of initial values of global objects declared as
+    Allows use of a :bro:keyword:`redef` to redefine initial values of
-    constant.
+    global variables (i.e., variables declared either :bro:keyword:`global`
-
+    or :bro:keyword:`const`).  Example::
-    In this example, the constant (assuming it is global) can be redefined
-    with a :bro:keyword:`redef` at some later point::
 
         const clever = T &redef;
+        global cache_size = 256 &redef;
+
+    Note that a variable declared "global" can also have its value changed
+    with assignment statements (doesn't matter if it has the "&redef"
+    attribute or not).
 
 .. bro:attr:: &priority
 
@@ -175,14 +176,20 @@ Here is a more detailed explanation of each attribute:
 
     Rotates a file after a specified interval.
 
+    Note: This attribute is deprecated and will be removed in a future release.
+
 .. bro:attr:: &rotate_size
 
     Rotates a file after it has reached a given size in bytes.
 
+    Note: This attribute is deprecated and will be removed in a future release.
+
 .. bro:attr:: &encrypt
 
     Encrypts files right before writing them to disk.
 
+    Note: This attribute is deprecated and will be removed in a future release.
+
 .. bro:attr:: &raw_output
 
     Opens a file in raw mode, i.e., non-ASCII characters are not
@@ -198,11 +205,6 @@ Here is a more detailed explanation of each attribute:
     inconsistencies and can be avoided by unifying the two sets, rather
     than merely overwriting the old value.
 
-.. bro:attr:: &group
-
-    Groups event handlers such that those in the same group can be
-    jointly activated or deactivated.
-
 .. bro:attr:: &error_handler
 
     Internally set on the events that are associated with the reporter
@@ -236,5 +238,4 @@ Here is a more detailed explanation of each attribute:
 
     The associated identifier is marked as deprecated and will be
     removed in a future version of Bro.  Look in the NEWS file for more
-    explanation and/or instructions to migrate code that uses deprecated
+    instructions to migrate code that uses deprecated functionality.
-    functionality.

doc/script-reference/directives.rst

@@ -58,6 +58,23 @@ executed.  Directives are evaluated before script execution begins.
     for that script are ignored).
 
 
+.. bro:keyword:: @load-plugin
+
+    Activate a dynamic plugin with the specified plugin name.  The specified
+    plugin must be located in Bro's plugin search path.  Example::
+
+        @load-plugin Demo::Rot13
+
+    By default, Bro will automatically activate all dynamic plugins found
+    in the plugin search path (the search path can be changed by setting
+    the environment variable BRO_PLUGIN_PATH to a colon-separated list of
+    directories). However, in bare mode ("bro -b"), dynamic plugins can be
+    activated only by using "@load-plugin", or by specifying the full
+    plugin name on the Bro command-line (e.g., "bro Demo::Rot13"), or by
+    setting the environment variable BRO_PLUGIN_ACTIVATE to a
+    comma-separated list of plugin names.
+
+
 .. bro:keyword:: @load-sigs
 
     This works similarly to "@load", except that in this case the filename

doc/script-reference/log-files.rst

@@ -26,13 +26,21 @@ Network Protocols
 +----------------------------+---------------------------------------+---------------------------------+
 | irc.log                    | IRC commands and responses            | :bro:type:`IRC::Info`           |
 +----------------------------+---------------------------------------+---------------------------------+
+| kerberos.log               | Kerberos                              | :bro:type:`KRB::Info`           |
++----------------------------+---------------------------------------+---------------------------------+
 | modbus.log                 | Modbus commands and responses         | :bro:type:`Modbus::Info`        |
 +----------------------------+---------------------------------------+---------------------------------+
 | modbus_register_change.log | Tracks changes to Modbus holding      | :bro:type:`Modbus::MemmapInfo`  |
 |                            | registers                             |                                 |
 +----------------------------+---------------------------------------+---------------------------------+
+| mysql.log                  | MySQL                                 | :bro:type:`MySQL::Info`         |
++----------------------------+---------------------------------------+---------------------------------+
 | radius.log                 | RADIUS authentication attempts        | :bro:type:`RADIUS::Info`        |
 +----------------------------+---------------------------------------+---------------------------------+
+| rdp.log                    | RDP                                   | :bro:type:`RDP::Info`           |
++----------------------------+---------------------------------------+---------------------------------+
+| sip.log                    | SIP                                   | :bro:type:`SIP::Info`           |
++----------------------------+---------------------------------------+---------------------------------+
 | smtp.log                   | SMTP transactions                     | :bro:type:`SMTP::Info`          |
 +----------------------------+---------------------------------------+---------------------------------+
 | snmp.log                   | SNMP messages                         | :bro:type:`SNMP::Info`          |
@@ -56,6 +64,8 @@ Files
 +============================+=======================================+=================================+
 | files.log                  | File analysis results                 | :bro:type:`Files::Info`         |
 +----------------------------+---------------------------------------+---------------------------------+
+| pe.log                     | Portable Executable (PE)              | :bro:type:`PE::Info`            |
++----------------------------+---------------------------------------+---------------------------------+
 | x509.log                   | X.509 certificate info                | :bro:type:`X509::Info`          |
 +----------------------------+---------------------------------------+---------------------------------+
 

doc/script-reference/statements.rst

@@ -71,9 +71,11 @@ Statements
 Declarations
 ------------
 
-The following global declarations cannot occur within a function, hook, or
+Declarations cannot occur within a function, hook, or event handler.
-event handler.  Also, these declarations cannot appear after any statements
+
-that are outside of a function, hook, or event handler.
+Declarations must appear before any statements (except those statements
+that are in a function, hook, or event handler) in the concatenation of
+all loaded Bro scripts.
 
 .. bro:keyword:: module
 
@@ -126,9 +128,12 @@ that are outside of a function, hook, or event handler.
 .. bro:keyword:: global
 
     Variables declared with the "global" keyword will be global.
+
     If a type is not specified, then an initializer is required so that
     the type can be inferred.  Likewise, if an initializer is not supplied,
-    then the type must be specified.  Example::
+    then the type must be specified.  In some cases, when the type cannot
+    be correctly inferred, the type must be specified even when an
+    initializer is present.  Example::
 
         global pi = 3.14;
         global hosts: set[addr];
@@ -136,10 +141,11 @@ that are outside of a function, hook, or event handler.
 
     Variable declarations outside of any function, hook, or event handler are
     required to use this keyword (unless they are declared with the
-    :bro:keyword:`const` keyword).  Definitions of functions, hooks, and
+    :bro:keyword:`const` keyword instead).
-    event handlers are not allowed to use the "global"
+
-    keyword (they already have global scope), except function declarations
+    Definitions of functions, hooks, and event handlers are not allowed
-    where no function body is supplied use the "global" keyword.
+    to use the "global" keyword.  However, function declarations (i.e., no
+    function body is provided) can use the "global" keyword.
 
     The scope of a global variable begins where the declaration is located,
     and extends through all remaining Bro scripts that are loaded (however,
@@ -150,18 +156,22 @@ that are outside of a function, hook, or event handler.
 .. bro:keyword:: const
 
     A variable declared with the "const" keyword will be constant.
+
     Variables declared as constant are required to be initialized at the
-    time of declaration.  Example::
+    time of declaration.  Normally, the type is inferred from the initializer,
+    but the type can be explicitly specified.  Example::
 
         const pi = 3.14;
         const ssh_port: port = 22/tcp;
 
-    The value of a constant cannot be changed later (the only
+    The value of a constant cannot be changed.  The only exception is if the
-    exception is if the variable is global and has the :bro:attr:`&redef`
+    variable is a global constant and has the :bro:attr:`&redef`
-    attribute, then its value can be changed only with a :bro:keyword:`redef`).
+    attribute, but even then its value can be changed only with a
+    :bro:keyword:`redef`.
 
     The scope of a constant is local if the declaration is in a
     function, hook, or event handler, and global otherwise.
+
     Note that the "const" keyword cannot be used with either the "local"
     or "global" keywords (i.e., "const" replaces "local" and "global").
 
@@ -184,7 +194,8 @@ that are outside of a function, hook, or event handler.
 .. bro:keyword:: redef
 
     There are three ways that "redef" can be used:  to change the value of
-    a global variable, to extend a record type or enum type, or to specify
+    a global variable (but only if it has the :bro:attr:`&redef` attribute),
+    to extend a record type or enum type, or to specify
     a new event handler body that replaces all those that were previously
     defined.
 
@@ -237,13 +248,14 @@ that are outside of a function, hook, or event handler.
 Statements
 ----------
 
+Statements (except those contained within a function, hook, or event
+handler) can appear only after all global declarations in the concatenation
+of all loaded Bro scripts.
+
 Each statement in a Bro script must be terminated with a semicolon (with a
 few exceptions noted below).  An individual statement can span multiple
 lines.
 
-All statements (except those contained within a function, hook, or event
-handler) must appear after all global declarations.
-
 Here are the statements that the Bro scripting language supports.
 
 .. bro:keyword:: add
@@ -258,8 +270,8 @@ Here are the statements that the Bro scripting language supports.
 
 .. bro:keyword:: break
 
-    The "break" statement is used to break out of a :bro:keyword:`switch` or
+    The "break" statement is used to break out of a :bro:keyword:`switch`,
-    :bro:keyword:`for` statement.
+    :bro:keyword:`for`, or :bro:keyword:`while` statement.
 
 
 .. bro:keyword:: delete
@@ -294,7 +306,10 @@ Here are the statements that the Bro scripting language supports.
 .. bro:keyword:: for
 
     A "for" loop iterates over each element in a string, set, vector, or
-    table and executes a statement for each iteration.
+    table and executes a statement for each iteration.  Currently,
+    modifying a container's membership while iterating over it may
+    result in undefined behavior, so avoid adding or removing elements
+    inside the loop.
 
     For each iteration of the loop, a loop variable will be assigned to an
     element if the expression evaluates to a string or set, or an index if
@@ -376,10 +391,10 @@ Here are the statements that the Bro scripting language supports.
 
 .. bro:keyword:: next
 
-    The "next" statement can only appear within a :bro:keyword:`for` loop.
+    The "next" statement can only appear within a :bro:keyword:`for` or
-    It causes execution to skip to the next iteration.
+    :bro:keyword:`while` loop.  It causes execution to skip to the next
+    iteration.
 
-    For an example, see the :bro:keyword:`for` statement.
 
 .. bro:keyword:: print
 
@@ -568,7 +583,7 @@ Here are the statements that the Bro scripting language supports.
 
 .. bro:keyword:: while
 
-    A "while" loop iterates over a body statement as long a given
+    A "while" loop iterates over a body statement as long as a given
     condition remains true.
 
     A :bro:keyword:`break` statement can be used at any time to immediately
@@ -606,8 +621,8 @@ Here are the statements that the Bro scripting language supports.
     (outside of the braces) of a compound statement.
 
     A compound statement is required in order to execute more than one
-    statement in the body of a :bro:keyword:`for`, :bro:keyword:`if`, or
+    statement in the body of a :bro:keyword:`for`, :bro:keyword:`while`,
-    :bro:keyword:`when` statement.
+    :bro:keyword:`if`, or :bro:keyword:`when` statement.
 
     Example::
 

doc/script-reference/types.rst

@@ -340,15 +340,18 @@ Here is a more detailed description of each type:
 
         table [ type^+ ] of type
 
-    where *type^+* is one or more types, separated by commas.
+    where *type^+* is one or more types, separated by commas.  The
-    For example:
+    index type cannot be any of the following types:  pattern, table, set,
+    vector, file, opaque, any.
+
+    Here is an example of declaring a table indexed by "count" values
+    and yielding "string" values:
 
     .. code:: bro
 
         global a: table[count] of string;
 
-    declares a table indexed by "count" values and yielding
+    The yield type can also be more complex:
-    "string" values.  The yield type can also be more complex:
 
     .. code:: bro
 
@@ -441,7 +444,9 @@ Here is a more detailed description of each type:
 
         set [ type^+ ]
 
-    where *type^+* is one or more types separated by commas.
+    where *type^+* is one or more types separated by commas.  The
+    index type cannot be any of the following types:  pattern, table, set,
+    vector, file, opaque, any.
 
     Sets can be initialized by listing elements enclosed by curly braces:
 

doc/scripting/data_struct_record_01.bro

@@ -4,7 +4,7 @@ type Service: record {
     rfc: count;
 };
 
-function print_service(serv: Service): string
+function print_service(serv: Service)
     {
     print fmt("Service: %s(RFC%d)",serv$name, serv$rfc);
     

doc/scripting/data_struct_record_02.bro

@@ -9,7 +9,7 @@ type System: record {
     services: set[Service];
     };
 
-function print_service(serv: Service): string
+function print_service(serv: Service)
     {
     print fmt("  Service: %s(RFC%d)",serv$name, serv$rfc);
     
@@ -17,7 +17,7 @@ function print_service(serv: Service): string
         print fmt("    port: %s", p);
     }
 
-function print_system(sys: System): string
+function print_system(sys: System)
     {
     print fmt("System: %s", sys$name);
     

doc/scripting/framework_logging_factorial_02.bro

@@ -23,7 +23,7 @@ function factorial(n: count): count
 event bro_init()
     {
     # Create the logging stream.
-    Log::create_stream(LOG, [$columns=Info]);
+    Log::create_stream(LOG, [$columns=Info, $path="factor"]);
     }
 
 event bro_done()

doc/scripting/framework_logging_factorial_03.bro

@@ -37,7 +37,7 @@ function mod5(id: Log::ID, path: string, rec: Factor::Info) : string
 
 event bro_init()
     {
-    Log::create_stream(LOG, [$columns=Info]);
+    Log::create_stream(LOG, [$columns=Info, $path="factor"]);
     
     local filter: Log::Filter = [$name="split-mod5s", $path_func=mod5];
     Log::add_filter(Factor::LOG, filter);

doc/scripting/framework_logging_factorial_04.bro

@@ -22,7 +22,7 @@ function factorial(n: count): count
 
 event bro_init()
     {
-    Log::create_stream(LOG, [$columns=Info, $ev=log_factor]);
+    Log::create_stream(LOG, [$columns=Info, $ev=log_factor, $path="factor"]);
     }
 
 event bro_done()

doc/scripting/index.rst

@@ -363,7 +363,7 @@ decrypted from HTTP streams is stored in
 excerpt from :doc:`/scripts/base/protocols/http/main.bro` below.
 
 .. btest-include:: ${BRO_SRC_ROOT}/scripts/base/protocols/http/main.bro
-   :lines: 9-11,20-22,121
+   :lines: 9-11,20-22,125
 
 Because the constant was declared with the ``&redef`` attribute, if we
 needed to turn this option on globally, we could do so by adding the
@@ -826,7 +826,7 @@ example of the ``record`` data type in the earlier sections, the
 ``conn.log``, is shown by the excerpt below.
 
 .. btest-include:: ${BRO_SRC_ROOT}/scripts/base/protocols/conn/main.bro
-   :lines: 10-12,16-17,19,21,23,25,28,31,35,38,57,63,69,92,95,99,102,106,110-111,116
+   :lines: 10-12,16-17,19,21,23,25,28,31,35,38,57,63,69,75,98,101,105,108,112,116-117,122
 
 Looking at the structure of the definition, a new collection of data
 types is being defined as a type called ``Info``.  Since this type

man/bro.8

@@ -51,12 +51,6 @@ add given prefix to policy file resolution
 \fB\-r\fR,\ \-\-readfile <readfile>
 read from given tcpdump file
 .TP
-\fB\-y\fR,\ \-\-flowfile <file>[=<ident>]
-read from given flow file
-.TP
-\fB\-Y\fR,\ \-\-netflow <ip>:<prt>[=<id>]
-read flow from socket
-.TP
 \fB\-s\fR,\ \-\-rulefile <rulefile>
 read rules from given file
 .TP
@@ -78,27 +72,21 @@ run the specified policy file analysis
 \fB\-C\fR,\ \-\-no\-checksums
 ignore checksums
 .TP
-\fB\-D\fR,\ \-\-dfa\-size <size>
-DFA state cache size
-.TP
 \fB\-F\fR,\ \-\-force\-dns
 force DNS
 .TP
 \fB\-I\fR,\ \-\-print\-id <ID name>
 print out given ID
 .TP
+\fB\-J\fR,\ \-\-set\-seed <seed>
+set the random number seed
+.TP
 \fB\-K\fR,\ \-\-md5\-hashkey <hashkey>
 set key for MD5\-keyed hashing
 .TP
-\fB\-L\fR,\ \-\-rule\-benchmark
-benchmark for rules
-.TP
 \fB\-N\fR,\ \-\-print\-plugins
 print available plugins and exit (\fB\-NN\fR for verbose)
 .TP
-\fB\-O\fR,\ \-\-optimize
-optimize policy script
-.TP
 \fB\-P\fR,\ \-\-prime\-dns
 prime DNS
 .TP
@@ -120,7 +108,7 @@ Record process status in file
 \fB\-W\fR,\ \-\-watchdog
 activate watchdog timer
 .TP
-\fB\-X\fR,\ \-\-broxygen
+\fB\-X\fR,\ \-\-broxygen <cfgfile>
 generate documentation based on config file
 .TP
 \fB\-\-pseudo\-realtime[=\fR<speedup>]
@@ -131,6 +119,19 @@ load seeds from given file
 .TP
 \fB\-\-save\-seeds\fR <file>
 save seeds to given file
+.TP
+The following option is available only when Bro is built with the \-\-enable\-debug configure option:
+.TP
+\fB\-B\fR,\ \-\-debug <dbgstreams>
+Enable debugging output for selected streams ('-B help' for help)
+.TP
+The following options are available only when Bro is built with gperftools support (use the \-\-enable\-perftools and \-\-enable\-perftools\-debug configure options):
+.TP
+\fB\-m\fR,\ \-\-mem-leaks
+show leaks
+.TP
+\fB\-M\fR,\ \-\-mem-profile
+record heap
 .SH ENVIRONMENT
 .TP
 .B BROPATH

pkg/check-cmake

@@ -1,14 +0,0 @@
-#!/bin/sh
-
-# CMake/CPack versions before 2.8.3 have bugs that can create bad packages
-# Since packages will be built on several different systems, a single
-# version of CMake is required to obtain consistency, but can be increased
-# as new versions of CMake come out that also produce working packages.
-
-CMAKE_PACK_REQ="cmake version 2.8.6"
-CMAKE_VER=`cmake -version`
-
-if [ "${CMAKE_VER}" != "${CMAKE_PACK_REQ}" ]; then
-    echo "Package creation requires ${CMAKE_PACK_REQ}" >&2
-    exit 1
-fi

pkg/make-deb-packages

@@ -3,8 +3,6 @@
 # This script generates binary DEB packages.
 # They can be found in ../build/ after running.
 
-./check-cmake || { exit 1; }
-
 # The DEB CPack generator depends on `dpkg-shlibdeps` to automatically
 # determine what dependencies to set for the packages
 type dpkg-shlibdeps > /dev/null 2>&1 || {

pkg/make-mac-packages

@@ -3,14 +3,6 @@
 # This script creates binary packages for Mac OS X.
 # They can be found in ../build/ after running.
 
-cmake -P /dev/stdin << "EOF"
-if ( ${CMAKE_VERSION} VERSION_LESS 2.8.9 )
-    message(FATAL_ERROR "CMake >= 2.8.9 required to build package")
-endif ()
-EOF
-
-[ $? -ne 0 ] && exit 1;
-
 type sw_vers > /dev/null 2>&1 || {
     echo "Unable to get Mac OS X version" >&2;
     exit 1;

pkg/make-rpm-packages

@@ -3,8 +3,6 @@
 # This script generates binary RPM packages.
 # They can be found in ../build/ after running.
 
-./check-cmake || { exit 1; }
-
 # The RPM CPack generator depends on `rpmbuild` to create packages
 type rpmbuild > /dev/null 2>&1 || {
     echo "\

scripts/base/files/extract/main.bro

@@ -53,7 +53,8 @@ function set_limit(f: fa_file, args: Files::AnalyzerArgs, n: count): bool
 function on_add(f: fa_file, args: Files::AnalyzerArgs)
 	{
 	if ( ! args?$extract_filename )
-		args$extract_filename = cat("extract-", f$source, "-", f$id);
+		args$extract_filename = cat("extract-", f$last_active, "-", f$source,
+		                            "-", f$id);
 
 	f$info$extracted = args$extract_filename;
 	args$extract_filename = build_path_compressed(prefix, args$extract_filename);

scripts/base/files/pe/README

@@ -0,0 +1 @@
+Support for Portable Executable (PE) file analysis.

scripts/base/files/pe/__load__.bro

@@ -0,0 +1,2 @@
+@load ./consts
+@load ./main

scripts/base/files/pe/consts.bro

@@ -0,0 +1,184 @@
+
+module PE;
+
+export {
+	const machine_types: table[count] of string = {
+		[0x00]   = "UNKNOWN",
+		[0x1d3]  = "AM33",
+		[0x8664] = "AMD64",
+		[0x1c0]  = "ARM",
+		[0x1c4]  = "ARMNT",
+		[0xaa64] = "ARM64",
+		[0xebc]  = "EBC",
+		[0x14c]  = "I386",
+		[0x200]  = "IA64",
+		[0x9041] = "M32R",
+		[0x266]  = "MIPS16",
+		[0x366]  = "MIPSFPU",
+		[0x466]  = "MIPSFPU16",
+		[0x1f0]  = "POWERPC",
+		[0x1f1]  = "POWERPCFP",
+		[0x166]  = "R4000",
+		[0x1a2]  = "SH3",
+		[0x1a3]  = "SH3DSP",
+		[0x1a6]  = "SH4",
+		[0x1a8]  = "SH5",
+		[0x1c2]  = "THUMB",
+		[0x169]  = "WCEMIPSV2"
+	} &default=function(i: count):string { return fmt("unknown-%d", i); };
+
+	const file_characteristics: table[count] of string = {
+		[0x1]    = "RELOCS_STRIPPED",
+		[0x2]    = "EXECUTABLE_IMAGE",
+		[0x4]    = "LINE_NUMS_STRIPPED",
+		[0x8]    = "LOCAL_SYMS_STRIPPED",
+		[0x10]   = "AGGRESSIVE_WS_TRIM",
+		[0x20]   = "LARGE_ADDRESS_AWARE",
+		[0x80]   = "BYTES_REVERSED_LO",
+		[0x100]  = "32BIT_MACHINE",
+		[0x200]  = "DEBUG_STRIPPED",
+		[0x400]  = "REMOVABLE_RUN_FROM_SWAP",
+		[0x800]  = "NET_RUN_FROM_SWAP",
+		[0x1000] = "SYSTEM",
+		[0x2000] = "DLL",
+		[0x4000] = "UP_SYSTEM_ONLY",
+		[0x8000] = "BYTES_REVERSED_HI"
+	} &default=function(i: count):string { return fmt("unknown-%d", i); };
+
+	const dll_characteristics: table[count] of string = {
+		[0x40]   = "DYNAMIC_BASE",
+		[0x80]   = "FORCE_INTEGRITY",
+		[0x100]  = "NX_COMPAT",
+		[0x200]  = "NO_ISOLATION",
+		[0x400]  = "NO_SEH",
+		[0x800]  = "NO_BIND",
+		[0x2000] = "WDM_DRIVER",
+		[0x8000] = "TERMINAL_SERVER_AWARE"
+	} &default=function(i: count):string { return fmt("unknown-%d", i); };
+
+	const windows_subsystems: table[count] of string = {
+		[0]  = "UNKNOWN",
+		[1]  = "NATIVE",
+		[2]  = "WINDOWS_GUI",
+		[3]  = "WINDOWS_CUI",
+		[7]  = "POSIX_CUI",
+		[9]  = "WINDOWS_CE_GUI",
+		[10] = "EFI_APPLICATION",
+		[11] = "EFI_BOOT_SERVICE_DRIVER",
+		[12] = "EFI_RUNTIME_
DRIVER",
+		[13] = "EFI_ROM",
+		[14] = "XBOX"
+	} &default=function(i: count):string { return fmt("unknown-%d", i); };
+
+	const directories: table[count] of string = {
+		[0]  = "Export Table",
+		[1]  = "Import Table",
+		[2]  = "Resource Table",
+		[3]  = "Exception Table",
+		[4]  = "Certificate Table",
+		[5]  = "Base Relocation Table",
+		[6]  = "Debug",
+		[7]  = "Architecture",
+		[8]  = "Global Ptr",
+		[9]  = "TLS Table",
+		[10] = "Load Config Table",
+		[11] = "Bound Import",
+		[12] = "IAT",
+		[13] = "Delay Import Descriptor",
+		[14] = "CLR Runtime Header",
+		[15] = "Reserved"
+	} &default=function(i: count):string { return fmt("unknown-%d", i); };
+
+	const section_characteristics: table[count] of string = {
+		[0x8]        = "TYPE_NO_PAD",
+		[0x20]       = "CNT_CODE",
+		[0x40]       = "CNT_INITIALIZED_DATA",
+		[0x80]       = "CNT_UNINITIALIZED_DATA",
+		[0x100]      = "LNK_OTHER",
+		[0x200]      = "LNK_INFO",
+		[0x800]      = "LNK_REMOVE",
+		[0x1000]     = "LNK_COMDAT",
+		[0x8000]     = "GPREL",
+		[0x20000]    = "MEM_16BIT",
+		[0x40000]    = "MEM_LOCKED",
+		[0x80000]    = "MEM_PRELOAD",
+		[0x100000]   = "ALIGN_1BYTES",
+		[0x200000]   = "ALIGN_2BYTES",
+		[0x300000]   = "ALIGN_4BYTES",
+		[0x400000]   = "ALIGN_8BYTES",
+		[0x500000]   = "ALIGN_16BYTES",
+		[0x600000]   = "ALIGN_32BYTES",
+		[0x700000]   = "ALIGN_64BYTES",
+		[0x800000]   = "ALIGN_128BYTES",
+		[0x900000]   = "ALIGN_256BYTES",
+		[0xa00000]   = "ALIGN_512BYTES",
+		[0xb00000]   = "ALIGN_1024BYTES",
+		[0xc00000]   = "ALIGN_2048BYTES",
+		[0xd00000]   = "ALIGN_4096BYTES",
+		[0xe00000]   = "ALIGN_8192BYTES",
+		[0x1000000]  = "LNK_NRELOC_OVFL",
+		[0x2000000]  = "MEM_DISCARDABLE",
+		[0x4000000]  = "MEM_NOT_CACHED",
+		[0x8000000]  = "MEM_NOT_PAGED",
+		[0x10000000] = "MEM_SHARED",
+		[0x20000000] = "MEM_EXECUTE",
+		[0x40000000] = "MEM_READ",
+		[0x80000000] = "MEM_WRITE"
+	} &default=function(i: count):string { return fmt("unknown-%d", i); };
+
+	const os_versions: table[count, count] of string = {
+		[10,0] = "Windows 10",
+		[6,4]  = "Windows 10 Technical Preview",
+		[6,3]  = "Windows 8.1 or Server 2012 R2",
+		[6,2]  = "Windows 8 or Server 2012",
+		[6,1]  = "Windows 7 or Server 2008 R2",
+		[6,0]  = "Windows Vista or Server 2008",
+		[5,2]  = "Windows XP x64 or Server 2003",
+		[5,1]  = "Windows XP",
+		[5,0]  = "Windows 2000",
+		[4,90] = "Windows Me",
+		[4,10] = "Windows 98",
+		[4,0]  = "Windows 95 or NT 4.0",
+		[3,51] = "Windows NT 3.51",
+		[3,50] = "Windows NT 3.5",
+		[3,2]  = "Windows 3.2",
+		[3,11] = "Windows for Workgroups 3.11",
+		[3,10] = "Windows 3.1 or NT 3.1",
+		[3,0]  = "Windows 3.0",
+		[2,11] = "Windows 2.11",
+		[2,10] = "Windows 2.10",
+		[2,0] = "Windows 2.0",
+		[1,4] = "Windows 1.04",
+		[1,3] = "Windows 1.03",
+		[1,1] = "Windows 1.01",
+		[1,0] = "Windows 1.0",
+	} &default=function(i: count, j: count):string { return fmt("unknown-%d.%d", i, j); };
+
+	const section_descs: table[string] of string = {
+		[".bss"]      = "Uninitialized data",
+		[".cormeta"]  = "CLR metadata that indicates that the object file contains managed code",
+		[".data"]     = "Initialized data",
+		[".debug$F"]  = "Generated FPO debug information",
+		[".debug$P"]  = "Precompiled debug types",
+		[".debug$S"]  = "Debug symbols",
+		[".debug$T"]  = "Debug types",
+		[".drective"] = "Linker options",
+		[".edata"]    = "Export tables",
+		[".idata"]    = "Import tables",
+		[".idlsym"]   = "Includes registered SEH to support IDL attributes",
+		[".pdata"]    = "Exception information",
+		[".rdata"]    = "Read-only initialized data",
+		[".reloc"]    = "Image relocations",
+		[".rsrc"]     = "Resource directory",
+		[".sbss"]     = "GP-relative uninitialized data",
+		[".sdata"]    = "GP-relative initialized data",
+		[".srdata"]   = "GP-relative read-only data",
+		[".sxdata"]   = "Registered exception handler data",
+		[".text"]     = "Executable code",
+		[".tls"]      = "Thread-local storage",
+		[".tls$"]     = "Thread-local storage",
+		[".vsdata"]   = "GP-relative initialized data",
+		[".xdata"]    = "Exception information",
+	} &default=function(i: string):string { return fmt("unknown-%s", i); };
+
+}

scripts/base/files/pe/main.bro

@@ -0,0 +1,137 @@
+module PE;
+
+@load ./consts.bro
+
+export {
+	redef enum Log::ID += { LOG };
+
+	type Info: record {
+		## Current timestamp.
+		ts:                  time              &log;
+		## File id of this portable executable file.
+		id:                  string            &log;
+		## The target machine that the file was compiled for.
+		machine:             string            &log &optional;
+		## The time that the file was created at.
+		compile_ts:          time              &log &optional;
+		## The required operating system.
+		os:                  string            &log &optional;
+		## The subsystem that is required to run this file.
+		subsystem:           string            &log &optional;
+		## Is the file an executable, or just an object file?
+		is_exe:              bool              &log &default=T;
+		## Is the file a 64-bit executable?
+		is_64bit:            bool              &log &default=T;
+		## Does the file support Address Space Layout Randomization?
+		uses_aslr:           bool              &log &default=F;
+		## Does the file support Data Execution Prevention?
+		uses_dep:            bool              &log &default=F;
+		## Does the file enforce code integrity checks?
+		uses_code_integrity: bool              &log &default=F;
+		## Does the file use structured exception handing?
+		uses_seh:            bool              &log &default=T;
+		## Does the file have an import table?
+		has_import_table:    bool              &log &optional;
+		## Does the file have an export table?
+		has_export_table:    bool              &log &optional;
+		## Does the file have an attribute certificate table?
+		has_cert_table:      bool              &log &optional;
+		## Does the file have a debug table?
+		has_debug_data:      bool              &log &optional;
+		## The names of the sections, in order.
+		section_names:       vector of string  &log &optional;
+	};
+
+	## Event for accessing logged records.
+	global log_pe: event(rec: Info);
+
+	## A hook that gets called when we first see a PE file.
+	global set_file: hook(f: fa_file);
+}
+
+redef record fa_file += {
+	pe: Info &optional;
+};
+
+const pe_mime_types = { "application/x-dosexec" };
+
+event bro_init() &priority=5
+	{
+	Files::register_for_mime_types(Files::ANALYZER_PE, pe_mime_types);
+	Log::create_stream(LOG, [$columns=Info, $ev=log_pe, $path="pe"]);
+	}
+
+hook set_file(f: fa_file) &priority=5
+	{
+	if ( ! f?$pe )
+		f$pe = [$ts=network_time(), $id=f$id];
+	}
+
+event pe_dos_header(f: fa_file, h: PE::DOSHeader) &priority=5
+	{
+	hook set_file(f);
+	}
+
+event pe_file_header(f: fa_file, h: PE::FileHeader) &priority=5
+	{
+	hook set_file(f);
+
+	f$pe$machine    = machine_types[h$machine];
+	f$pe$compile_ts = h$ts;
+	f$pe$is_exe     = ( h$optional_header_size > 0 );
+
+	for ( c in h$characteristics )
+		{
+		if ( file_characteristics[c] == "32BIT_MACHINE" )
+			f$pe$is_64bit = F;
+		}
+	}
+
+event pe_optional_header(f: fa_file, h: PE::OptionalHeader) &priority=5
+	{
+	hook set_file(f);
+
+	# Only EXEs have optional headers
+	if ( ! f$pe$is_exe )
+		return;
+
+	f$pe$os        = os_versions[h$os_version_major, h$os_version_minor];
+	f$pe$subsystem = windows_subsystems[h$subsystem];
+
+	for ( c in h$dll_characteristics )
+		{
+		if ( dll_characteristics[c] == "DYNAMIC_BASE" )
+			f$pe$uses_aslr = T;
+		if ( dll_characteristics[c] == "FORCE_INTEGRITY" )
+			f$pe$uses_code_integrity = T;
+		if ( dll_characteristics[c] == "NX_COMPAT" )
+			f$pe$uses_dep = T;
+		if ( dll_characteristics[c] == "NO_SEH" )
+			f$pe$uses_seh = F;
+		}
+
+	f$pe$has_export_table = (|h$table_sizes| > 0 && h$table_sizes[0] > 0);
+	f$pe$has_import_table = (|h$table_sizes| > 1 && h$table_sizes[1] > 0);
+	f$pe$has_cert_table   = (|h$table_sizes| > 4 && h$table_sizes[4] > 0);
+	f$pe$has_debug_data   = (|h$table_sizes| > 6 && h$table_sizes[6] > 0);
+	}
+
+event pe_section_header(f: fa_file, h: PE::SectionHeader) &priority=5
+	{
+	hook set_file(f);
+
+	# Only EXEs have section headers
+	if ( ! f$pe$is_exe )
+		return;
+
+	if ( ! f$pe?$section_names )
+		f$pe$section_names = vector();
+	f$pe$section_names[|f$pe$section_names|] = h$name;
+	}
+
+event file_state_remove(f: fa_file) &priority=-5
+	{
+	if ( f?$pe && f$pe?$machine )
+		Log::write(LOG, f$pe);
+	}
+

scripts/base/files/unified2/main.bro

@@ -195,7 +195,7 @@ event Input::end_of_data(name: string, source: string)
 
 event bro_init() &priority=5
 	{
-	Log::create_stream(Unified2::LOG, [$columns=Info, $ev=log_unified2]);
+	Log::create_stream(Unified2::LOG, [$columns=Info, $ev=log_unified2, $path="unified2"]);
 
 	if ( sid_msg == "" )
 		{

scripts/base/files/x509/main.bro

@@ -36,7 +36,7 @@ export {
 
 event bro_init() &priority=5
 	{
-	Log::create_stream(X509::LOG, [$columns=Info, $ev=log_x509]);
+	Log::create_stream(X509::LOG, [$columns=Info, $ev=log_x509, $path="x509"]);
 	}
 
 redef record Files::Info += {
@@ -47,6 +47,9 @@ redef record Files::Info += {
 
 event x509_certificate(f: fa_file, cert_ref: opaque of x509, cert: X509::Certificate) &priority=5
 	{
+	if ( ! f$info?$mime_type )
+		f$info$mime_type = "application/pkix-cert";
+
 	f$info$x509 = [$ts=f$info$ts, $id=f$id, $certificate=cert, $handle=cert_ref];
 	}
 

scripts/base/frameworks/broker/README

@@ -0,0 +1,2 @@
+The Broker communication framework facilitates connecting to remote Bro
+instances to share state and transfer events.

scripts/base/frameworks/broker/__load__.bro

@@ -0,0 +1 @@
+@load ./main

scripts/base/frameworks/broker/main.bro

@@ -0,0 +1,103 @@
+##! Various data structure definitions for use with Bro's communication system.
+
+module BrokerComm;
+
+export {
+
+	## A name used to identify this endpoint to peers.
+	## .. bro:see:: BrokerComm::connect BrokerComm::listen
+	const endpoint_name = "" &redef;
+
+	## Change communication behavior.
+	type EndpointFlags: record {
+		## Whether to restrict message topics that can be published to peers.
+		auto_publish: bool &default = T;
+		## Whether to restrict what message topics or data store identifiers
+		## the local endpoint advertises to peers (e.g. subscribing to
+		## events or making a master data store available).
+		auto_advertise: bool &default = T;
+	};
+
+	## Fine-grained tuning of communication behavior for a particular message.
+	type SendFlags: record {
+		## Send the message to the local endpoint.
+		self: bool &default = F;
+		## Send the message to peer endpoints that advertise interest in
+		## the topic associated with the message.
+		peers: bool &default = T;
+		## Send the message to peer endpoints even if they don't advertise
+		## interest in the topic associated with the message.
+		unsolicited: bool &default = F;
+	};
+
+	## Opaque communication data.
+	type Data: record {
+		d: opaque of BrokerComm::Data &optional;
+	};
+
+	## Opaque communication data.
+	type DataVector: vector of BrokerComm::Data;
+
+	## Opaque event communication data.
+	type EventArgs: record {
+		## The name of the event.  Not set if invalid event or arguments.
+		name: string &optional;
+		## The arguments to the event.
+		args: DataVector;
+	};
+
+	## Opaque communication data used as a convenient way to wrap key-value
+	## pairs that comprise table entries.
+	type TableItem : record {
+		key: BrokerComm::Data;
+		val: BrokerComm::Data;
+	};
+}
+
+module BrokerStore;
+
+export {
+
+	## Whether a data store query could be completed or not.
+	type QueryStatus: enum {
+		SUCCESS,
+		FAILURE,
+	};
+
+	## An expiry time for a key-value pair inserted in to a data store.
+	type ExpiryTime: record {
+		## Absolute point in time at which to expire the entry.
+		absolute: time &optional;
+		## A point in time relative to the last modification time at which
+		## to expire the entry.  New modifications will delay the expiration.
+		since_last_modification: interval &optional;
+	};
+
+	## The result of a data store query.
+	type QueryResult: record {
+		## Whether the query completed or not.
+		status: BrokerStore::QueryStatus;
+		## The result of the query.  Certain queries may use a particular
+		## data type (e.g. querying store size always returns a count, but
+		## a lookup may return various data types).
+		result: BrokerComm::Data;
+	};
+
+	## Options to tune the SQLite storage backend.
+	type SQLiteOptions: record {
+		## File system path of the database.
+		path: string &default = "store.sqlite";
+	};
+
+	## Options to tune the RocksDB storage backend.
+	type RocksDBOptions: record {
+		## File system path of the database.
+		path: string &default = "store.rocksdb";
+	};
+
+	## Options to tune the particular storage backends.
+	type BackendOptions: record {
+		sqlite: SQLiteOptions &default = SQLiteOptions();
+		rocksdb: RocksDBOptions &default = RocksDBOptions();
+	};
+}

scripts/base/frameworks/cluster/main.bro

@@ -126,6 +126,9 @@ export {
 	## This is usually supplied on the command line for each instance
 	## of the cluster that is started up.
 	const node = getenv("CLUSTER_NODE") &redef;
+
+	## Interval for retrying failed connections between cluster nodes.
+	const retry_interval = 1min &redef;
 }
 
 function is_enabled(): bool
@@ -159,5 +162,5 @@ event bro_init() &priority=5
 		terminate();
 		}
 
-	Log::create_stream(Cluster::LOG, [$columns=Info]);
+	Log::create_stream(Cluster::LOG, [$columns=Info, $path="cluster"]);
 	}

scripts/base/frameworks/cluster/setup-connections.bro

@@ -39,7 +39,7 @@ event bro_init() &priority=9
 				Communication::nodes["time-machine"] = [$host=nodes[i]$ip,
 				                                        $zone_id=nodes[i]$zone_id,
 				                                        $p=nodes[i]$p,
-				                                        $connect=T, $retry=1min,
+				                                        $connect=T, $retry=retry_interval,
 				                                        $events=tm2manager_events];
 			}
 
@@ -58,7 +58,7 @@ event bro_init() &priority=9
 				if ( n?$proxy )
 					Communication::nodes[i]
 					     = [$host=n$ip, $zone_id=n$zone_id, $p=n$p,
-					        $connect=T, $auth=F, $sync=T, $retry=1mins];
+					        $connect=T, $auth=F, $sync=T, $retry=retry_interval];
 				else if ( me?$proxy && me$proxy == i )
 					Communication::nodes[me$proxy]
 					     = [$host=nodes[i]$ip, $zone_id=nodes[i]$zone_id,
@@ -70,7 +70,7 @@ event bro_init() &priority=9
 				Communication::nodes["manager"] = [$host=nodes[i]$ip,
 				                                   $zone_id=nodes[i]$zone_id,
 				                                   $p=nodes[i]$p,
-				                                   $connect=T, $retry=1mins, 
+				                                   $connect=T, $retry=retry_interval,
 				                                   $class=node,
 				                                   $events=manager2proxy_events];
 			}
@@ -80,7 +80,7 @@ event bro_init() &priority=9
 				Communication::nodes["manager"] = [$host=nodes[i]$ip,
 				                                   $zone_id=nodes[i]$zone_id,
 				                                   $p=nodes[i]$p,
-				                                   $connect=T, $retry=1mins, 
+				                                   $connect=T, $retry=retry_interval,
 				                                   $class=node,
 				                                   $events=manager2worker_events];
 
@@ -88,7 +88,7 @@ event bro_init() &priority=9
 				Communication::nodes["proxy"] = [$host=nodes[i]$ip,
 				                                 $zone_id=nodes[i]$zone_id,
 				                                 $p=nodes[i]$p,
-				                                 $connect=T, $retry=1mins, 
+				                                 $connect=T, $retry=retry_interval,
 				                                 $sync=T, $class=node,
 				                                 $events=proxy2worker_events];
 
@@ -98,7 +98,7 @@ event bro_init() &priority=9
 				                                        $zone_id=nodes[i]$zone_id,
 				                                        $p=nodes[i]$p,
 				                                        $connect=T,
-				                                        $retry=1min,
+				                                        $retry=retry_interval,
 				                                        $events=tm2worker_events];
 
 			}

scripts/base/frameworks/communication/main.bro

@@ -164,7 +164,7 @@ const src_names = {
 
 event bro_init() &priority=5
 	{
-	Log::create_stream(Communication::LOG, [$columns=Info]);
+	Log::create_stream(Communication::LOG, [$columns=Info, $path="communication"]);
 	}
 
 function do_script_log_common(level: count, src: count, msg: string)

scripts/base/frameworks/dpd/main.bro

@@ -38,7 +38,7 @@ redef record connection += {
 
 event bro_init() &priority=5
 	{
-	Log::create_stream(DPD::LOG, [$columns=Info]);
+	Log::create_stream(DPD::LOG, [$columns=Info, $path="dpd"]);
 	}
 
 event protocol_confirmation(c: connection, atype: Analyzer::Tag, aid: count) &priority=10

scripts/base/frameworks/files/magic/__load__.bro

@@ -1,3 +1,9 @@
+@load-sigs ./archive
+@load-sigs ./audio
+@load-sigs ./font
 @load-sigs ./general
+@load-sigs ./image
 @load-sigs ./msoffice
+@load-sigs ./video
+
 @load-sigs ./libmagic

scripts/base/frameworks/files/magic/archive.sig

@@ -0,0 +1,176 @@
+
+signature file-tar {
+    file-magic /^[[:print:]\x00]{100}([[:digit:]\x20]{7}\x00){3}([[:digit:]\x20]{11}\x00){2}([[:digit:]\x00\x20]{7}[\x20\x00])[0-7\x00]/
+    file-mime "application/x-tar", 100
+}
+
+# This is low priority so that files using zip as a
+# container will be identified correctly.
+signature file-zip {
+	file-mime "application/zip", 10
+	file-magic /^PK\x03\x04.{2}/
+}
+
+# Multivolume Zip archive
+signature file-multi-zip {
+	file-mime "application/zip", 10
+	file-magic /^PK\x07\x08PK\x03\x04/
+}
+
+# RAR
+signature file-rar {
+	file-mime "application/x-rar", 70
+	file-magic /^Rar!/
+}
+
+# GZIP
+signature file-gzip {
+	file-mime "application/x-gzip", 100
+	file-magic /\x1f\x8b/
+}
+
+# Microsoft Cabinet
+signature file-ms-cab {
+	file-mime "application/vnd.ms-cab-compressed", 110
+	file-magic /^MSCF\x00\x00\x00\x00/
+}
+
+# Mac OS X DMG files
+signature file-dmg {
+	file-magic /^(\x78\x01\x73\x0D\x62\x62\x60|\x78\xDA\x63\x60\x18\x05|\x78\x01\x63\x60\x18\x05|\x78\xDA\x73\x0D|\x78[\x01\xDA]\xED[\xD0-\xD9])/
+	file-mime "application/x-dmg", 100
+}
+
+# XAR (eXtensible ARchive) format.
+# Mac OS X uses this for the .pkg format.
+signature file-xar {
+	file-magic /^xar\!/
+	file-mime "application/x-xar", 100
+}
+
+# RPM
+signature file-magic-auto352 {
+	file-mime "application/x-rpm", 70
+	file-magic /^(drpm|\xed\xab\xee\xdb)/
+}
+
+# StuffIt
+signature file-stuffit {
+	file-mime "application/x-stuffit", 70
+	file-magic /^(SIT\x21|StuffIt)/
+}
+
+# Archived data
+signature file-x-archive {
+	file-mime "application/x-archive", 70
+	file-magic /^!?<ar(ch)?>/
+}
+
+# ARC archive data
+signature file-arc {
+	file-mime "application/x-arc", 70
+	file-magic /^[\x00-\x7f]{2}[\x02-\x0a\x14\x48]\x1a/
+}
+
+# EET archive
+signature file-eet {
+	file-mime "application/x-eet", 70
+	file-magic /^\x1e\xe7\xff\x00/
+}
+
+# Zoo archive
+signature file-zoo {
+	file-mime "application/x-zoo", 70
+	file-magic /^.{20}\xdc\xa7\xc4\xfd/
+}
+
+# LZ4 compressed data (legacy format)
+signature file-lz4-legacy {
+	file-mime "application/x-lz4", 70
+	file-magic /(\x02\x21\x4c\x18)/
+}
+
+# LZ4 compressed data
+signature file-lz4 {
+	file-mime "application/x-lz4", 70
+	file-magic /^\x04\x22\x4d\x18/
+}
+
+# LRZIP compressed data
+signature file-lrzip {
+	file-mime "application/x-lrzip", 1
+	file-magic /^LRZI/
+}
+
+# LZIP compressed data
+signature file-lzip {
+	file-mime "application/x-lzip", 70
+	file-magic /^LZIP/
+}
+
+# Self-extracting PKZIP archive
+signature file-magic-auto434 {
+	file-mime "application/zip", 340
+	file-magic /^MZ.{28}(Copyright 1989\x2d1990 PKWARE Inc|PKLITE Copr)\x2e/
+}
+
+# LHA archive (LZH)
+signature file-lzh {
+	file-mime "application/x-lzh", 80
+	file-magic /^.{2}-(lh[ abcdex0-9]|lz[s2-8]|lz[s2-8]|pm[s012]|pc1)-/
+}
+
+# WARC Archive
+signature file-warc {
+	file-mime "application/warc", 50
+	file-magic /^WARC\x2f/
+}
+
+# 7-zip archive data
+signature file-7zip {
+	file-mime "application/x-7z-compressed", 50
+	file-magic /^7z\xbc\xaf\x27\x1c/
+}
+
+# XZ compressed data
+signature file-xz {
+	file-mime "application/x-xz", 90
+	file-magic /^\xfd7zXZ\x00/
+}
+
+# LHa self-extracting archive
+signature file-magic-auto436 {
+	file-mime "application/x-lha", 120
+	file-magic /^MZ.{34}LH[aA]\x27s SFX/
+}
+
+# ARJ archive data
+signature file-arj {
+	file-mime "application/x-arj", 50
+	file-magic /^\x60\xea/
+}
+
+# Byte-swapped cpio archive
+signature file-bs-cpio {
+	file-mime "application/x-cpio", 50
+	file-magic /(\x71\xc7|\xc7\x71)/
+}
+
+# CPIO archive
+signature file-cpio {
+	file-mime "application/x-cpio", 50
+	file-magic /^(\xc7\x71|\x71\xc7)/
+}
+
+# Compress'd data
+signature file-compress {
+	file-mime "application/x-compress", 50
+	file-magic /^\x1f\x9d/
+}
+
+# LZMA compressed data
+signature file-lzma {
+	file-mime "application/x-lzma", 71
+	file-magic /^\x5d\x00\x00/
+}
+

scripts/base/frameworks/files/magic/audio.sig

@@ -0,0 +1,13 @@
+
+# MPEG v3 audio
+signature file-mpeg-audio {
+	file-mime "audio/mpeg", 20
+	file-magic /^\xff[\xe2\xe3\xf2\xf3\xf6\xf7\xfa\xfb\xfc\xfd]/
+}
+
+# MPEG v4 audio
+signature file-m4a {
+	file-mime "audio/m4a", 70
+	file-magic /^....ftyp(m4a)/
+}
+

scripts/base/frameworks/files/magic/font.sig

@@ -0,0 +1,41 @@
+
+# Web Open Font Format
+signature file-woff {
+	file-magic /^wOFF/
+	file-mime "application/font-woff", 70
+}
+
+# TrueType font
+signature file-ttf {
+	file-mime "application/x-font-ttf", 80
+	file-magic /^\x00\x01\x00\x00\x00/
+}
+
+signature file-embedded-opentype {
+	file-mime "application/vnd.ms-fontobject", 50
+	file-magic /^.{34}LP/
+}
+
+# X11 SNF font
+signature file-snf {
+	file-mime "application/x-font-sfn", 70
+	file-magic /^(\x04\x00\x00\x00|\x00\x00\x00\x04).{100}(\x04\x00\x00\x00|\x00\x00\x00\x04)/
+}
+
+# OpenType font
+signature file-opentype {
+	file-mime "application/vnd.ms-opentype", 70
+	file-magic /^OTTO/
+}
+
+# FrameMaker Font file
+signature file-maker-screen-font {
+	file-mime "application/x-mif", 190
+	file-magic /^\x3cMakerScreenFont/
+}
+
+# >0  string,=SplineFontDB: (len=13), ["Spline Font Database "], swap_endian=0
+signature file-spline-font-db {
+	file-mime "application/vnd.font-fontforge-sfd", 160
+	file-magic /^SplineFontDB\x3a/
+}

scripts/base/frameworks/files/magic/general.sig

@@ -1,18 +1,93 @@
 # General purpose file magic signatures.
 
+# Plaintext
+# (Including BOMs for UTF-8, 16, and 32)
 signature file-plaintext {
-    file-magic /^([[:print:][:space:]]{10})/
+	file-mime "text/plain", -20
-    file-mime "text/plain", -20
+	file-magic /^(\xef\xbb\xbf|(\x00\x00)?\xfe\xff|\xff\xfe(\x00\x00)?)?[[:space:]\x20-\x7E]{10}/
 }
 
-signature file-tar {
+signature file-json {
-    file-magic /^[[:print:]\x00]{100}([[:digit:]\x20]{7}\x00){3}([[:digit:]\x20]{11}\x00){2}([[:digit:]\x00\x20]{7}[\x20\x00])[0-7\x00]/
+	file-mime "text/json", 1
-    file-mime "application/x-tar", 100
+	file-magic /^(\xef\xbb\xbf)?[\x0d\x0a[:blank:]]*\{[\x0d\x0a[:blank:]]*(["][^"]{1,}["]|[a-zA-Z][a-zA-Z0-9\\_]*)[\x0d\x0a[:blank:]]*:[\x0d\x0a[:blank:]]*(["]|\[|\{|[0-9]|true|false)/
 }
 
-signature file-zip {
+signature file-json2 {
-	file-mime "application/zip", 10
+	file-mime "text/json", 1
-	file-magic /^PK\x03\x04.{2}/
+	file-magic /^(\xef\xbb\xbf)?[\x0d\x0a[:blank:]]*\[[\x0d\x0a[:blank:]]*(((["][^"]{1,}["]|[0-9]{1,}(\.[0-9]{1,})?|true|false)[\x0d\x0a[:blank:]]*,)|\{|\[)[\x0d\x0a[:blank:]]*/
+}
+
+# Match empty JSON documents.
+signature file-json3 {
+	file-mime "text/json", 0
+	file-magic /^(\xef\xbb\xbf)?[\x0d\x0a[:blank:]]*(\[\]|\{\})[\x0d\x0a[:blank:]]*$/
+}
+
+signature file-xml {
+	file-mime "application/xml", 10
+	file-magic /^(\xef\xbb\xbf)?([\x0d\x0a[:blank:]]*(<!--.*-->)?[\x0d\x0a[:blank:]]*)*<\?xml /
+}
+
+signature file-xhtml {
+	file-mime "text/html", 100
+	file-magic /^(\xef\xbb\xbf)?([\x0d\x0a[:blank:]]*(<!--.*-->)?[\x0d\x0a[:blank:]]*)*(<\?xml .*\?>)?([\x0d\x0a[:blank:]]*(<!--.*-->)?[\x0d\x0a[:blank:]]*)*<(![dD][oO][cC][tT][yY][pP][eE] {1,}[hH][tT][mM][lL]|[hH][tT][mM][lL]|[mM][eE][tT][aA] {1,}[hH][tT][tT][pP]-[eE][qQ][uU][iI][vV])/
+}
+
+signature file-html {
+	file-mime "text/html", 49
+	file-magic /^(\xef\xbb\xbf)?([\x0d\x0a[:blank:]]*(<!--.*-->)?[\x0d\x0a[:blank:]]*)*(<\?xml .*\?>)?([\x0d\x0a[:blank:]]*(<!--.*-->)?[\x0d\x0a[:blank:]]*)*<![dD][oO][cC][tT][yY][pP][eE] {1,}[hH][tT][mM][lL]/
+}
+
+signature file-html2 {
+	file-mime "text/html", 20
+	file-magic /^(\xef\xbb\xbf)?([\x0d\x0a[:blank:]]*(<!--.*-->)?[\x0d\x0a[:blank:]]*)*(<\?xml .*\?>)?([\x0d\x0a[:blank:]]*(<!--.*-->)?[\x0d\x0a[:blank:]]*)*<([hH][eE][aA][dD]|[hH][tT][mM][lL]|[tT][iI][tT][lL][eE]|[bB][oO][dD][yY])/
+}
+
+signature file-rss {
+	file-mime "text/rss", 90
+	file-magic /^(\xef\xbb\xbf)?([\x0d\x0a[:blank:]]*(<!--.*-->)?[\x0d\x0a[:blank:]]*)*(<\?xml .*\?>)?([\x0d\x0a[:blank:]]*(<!--.*-->)?[\x0d\x0a[:blank:]]*)*<[rR][sS][sS]/
+}
+
+signature file-atom {
+	file-mime "text/atom", 100
+	file-magic /^(\xef\xbb\xbf)?([\x0d\x0a[:blank:]]*(<!--.*-->)?[\x0d\x0a[:blank:]]*)*(<\?xml .*\?>)?([\x0d\x0a[:blank:]]*(<!--.*-->)?[\x0d\x0a[:blank:]]*)*<([rR][sS][sS][^>]*xmlns:atom|[fF][eE][eE][dD][^>]*xmlns=["']?http:\/\/www.w3.org\/2005\/Atom["']?)/
+}
+
+signature file-soap {
+	file-mime "application/soap+xml", 49
+	file-magic /^(\xef\xbb\xbf)?([\x0d\x0a[:blank:]]*(<!--.*-->)?[\x0d\x0a[:blank:]]*)*(<\?xml .*\?>)?([\x0d\x0a[:blank:]]*(<!--.*-->)?[\x0d\x0a[:blank:]]*)*<[sS][oO][aA][pP](-[eE][nN][vV])?:[eE][nN][vV][eE][lL][oO][pP][eE]/
+}
+
+signature file-cross-domain-policy {
+	file-mime "text/x-cross-domain-policy", 49
+	file-magic /^([\x0d\x0a[:blank:]]*(<!--.*-->)?[\x0d\x0a[:blank:]]*)*(<\?xml .*\?>)?([\x0d\x0a[:blank:]]*(<!--.*-->)?[\x0d\x0a[:blank:]]*)*<![dD][oO][cC][tT][yY][pP][eE] {1,}[cC][rR][oO][sS][sS]-[dD][oO][mM][aA][iI][nN]-[pP][oO][lL][iI][cC][yY]/
+}
+
+signature file-cross-domain-policy2 {
+	file-mime "text/x-cross-domain-policy", 49
+	file-magic /^([\x0d\x0a[:blank:]]*(<!--.*-->)?[\x0d\x0a[:blank:]]*)*(<\?xml .*\?>)?([\x0d\x0a[:blank:]]*(<!--.*-->)?[\x0d\x0a[:blank:]]*)*<[cC][rR][oO][sS][sS]-[dD][oO][mM][aA][iI][nN]-[pP][oO][lL][iI][cC][yY]/
+}
+
+signature file-xmlrpc {
+	file-mime "application/xml-rpc", 49
+	file-magic /^(\xef\xbb\xbf)?([\x0d\x0a[:blank:]]*(<!--.*-->)?[\x0d\x0a[:blank:]]*)*(<\?xml .*\?>)?([\x0d\x0a[:blank:]]*(<!--.*-->)?[\x0d\x0a[:blank:]]*)*<[mM][eE][tT][hH][oO][dD][rR][eE][sS][pP][oO][nN][sS][eE]>/
+}
+
+signature file-coldfusion {
+	file-mime "magnus-internal/cold-fusion", 20
+	file-magic /^([\x0d\x0a[:blank:]]*(<!--.*-->)?)*<(CFPARAM|CFSET|CFIF)/
+}
+
+# Adobe Flash Media Manifest
+signature file-f4m {
+	file-mime "application/f4m", 49
+	file-magic /^(\xef\xbb\xbf)?([\x0d\x0a[:blank:]]*(<!--.*-->)?[\x0d\x0a[:blank:]]*)*(<\?xml .*\?>)?([\x0d\x0a[:blank:]]*(<!--.*-->)?[\x0d\x0a[:blank:]]*)*<[mM][aA][nN][iI][fF][eE][sS][tT][\x0d\x0a[:blank:]]{1,}xmlns=\"http:\/\/ns\.adobe\.com\/f4m\//
+}
+
+# Microsoft LNK files
+signature file-lnk {
+	file-mime "application/x-ms-shortcut", 49
+	file-magic /^\x4C\x00\x00\x00\x01\x14\x02\x00\x00\x00\x00\x00\xC0\x00\x00\x00\x00\x10\x00\x00\x00\x46/
 }
 
 signature file-jar {
@@ -21,8 +96,20 @@ signature file-jar {
 }
 
 signature file-java-applet {
-	file-magic /^\xca\xfe\xba\xbe...[\x2e-\x34]/
 	file-mime "application/x-java-applet", 71
+	file-magic /^\xca\xfe\xba\xbe...[\x2d-\x34]/
+}
+
+# OCSP requests over HTTP.
+signature file-ocsp-request {
+	file-magic /^.{11,19}\x06\x05\x2b\x0e\x03\x02\x1a/
+	file-mime "application/ocsp-request", 71
+}
+
+# OCSP responses over HTTP.
+signature file-ocsp-response {
+	file-magic /^.{11,19}\x06\x09\x2B\x06\x01\x05\x05\x07\x30\x01\x01/
+	file-mime "application/ocsp-response", 71
 }
 
 # Shockwave flash
@@ -37,12 +124,6 @@ signature file-tnef {
 	file-mime "application/vnd.ms-tnef", 100
 }
 
-# Mac OS X DMG files
-signature file-dmg {
-	file-magic /^(\x78\x01\x73\x0D\x62\x62\x60|\x78\xDA\x63\x60\x18\x05|\x78\x01\x63\x60\x18\x05|\x78\xDA\x73\x0D|\x78[\x01\xDA]\xED[\xD0-\xD9])/
-	file-mime "application/x-dmg", 100
-}
-
 # Mac OS X Mach-O executable
 signature file-mach-o {
 	file-magic /^[\xce\xcf]\xfa\xed\xfe/
@@ -55,13 +136,6 @@ signature file-mach-o-universal {
 	file-mime "application/x-mach-o-executable", 100
 }
 
-# XAR (eXtensible ARchive) format. 
-# Mac OS X uses this for the .pkg format.
-signature file-xar {
-	file-magic /^xar\!/
-	file-mime "application/x-xar", 100
-}
-
 signature file-pkcs7 {
 	file-magic /^MIME-Version:.*protocol=\"application\/pkcs7-signature\"/
 	file-mime "application/pkcs7-signature", 100
@@ -79,16 +153,6 @@ signature file-jnlp {
 	file-mime "application/x-java-jnlp-file", 100
 }
 
-signature file-ico {
-	file-magic /^\x00\x00\x01\x00/
-	file-mime "image/x-icon", 70
-}
-
-signature file-cur {
-	file-magic /^\x00\x00\x02\x00/
-	file-mime "image/x-cursor", 70
-}
-
 signature file-pcap {
 	file-magic /^(\xa1\xb2\xc3\xd4|\xd4\xc3\xb2\xa1)/
 	file-mime "application/vnd.tcpdump.pcap", 70
@@ -119,7 +183,58 @@ signature file-python {
 	file-mime "text/x-python", 60
 }
 
+signature file-awk {
+	file-mime "text/x-awk", 60
+	file-magic /^\x23\x21[^\n]{1,15}bin\/(env[[:space:]]+)?(g|n)?awk/
+}
+
+signature file-tcl {
+	file-mime "text/x-tcl", 60
+	file-magic /^\x23\x21[^\n]{1,15}bin\/(env[[:space:]]+)?(wish|tcl)/
+}
+
+signature file-lua {
+	file-mime "text/x-lua", 49
+	file-magic /^\x23\x21[^\n]{1,15}bin\/(env[[:space:]]+)?lua/
+}
+
+signature file-javascript {
+	file-mime "application/javascript", 60
+	file-magic /^\x23\x21[^\n]{1,15}bin\/(env[[:space:]]+)?node(js)?/
+}
+
+signature file-javascript2 {
+	file-mime "application/javascript", 60
+	file-magic /^[\x0d\x0a[:blank:]]*<[sS][cC][rR][iI][pP][tT][[:blank:]]+([tT][yY][pP][eE]|[lL][aA][nN][gG][uU][aA][gG][eE])=['"]?([tT][eE][xX][tT]\/)?[jJ][aA][vV][aA][sS][cC][rR][iI][pP][tT]/
+}
+
+signature file-javascript3 {
+	file-mime "application/javascript", 60
+	# This seems to be a somewhat common idiom in javascript.
+	file-magic /^[\x0d\x0a[:blank:]]*for \(;;\);/
+}
+
+signature file-javascript4 {
+	file-mime "application/javascript", 60
+	file-magic /^[\x0d\x0a[:blank:]]*document\.write(ln)?[:blank:]?\(/
+}
+
+signature file-javascript5 {
+	file-mime "application/javascript", 60
+	file-magic /^\(function\(\)[[:blank:]\n]*\{/
+}
+
+signature file-javascript6 {
+	file-mime "application/javascript", 60
+	file-magic /^[\x0d\x0a[:blank:]]*<script>[\x0d\x0a[:blank:]]*(var|function) /
+}
+
 signature file-php {
+	file-mime "text/x-php", 60
+	file-magic /^\x23\x21[^\n]{1,15}bin\/(env[[:space:]]+)?php/
+}
+
+signature file-php2 {
 	file-magic /^.*<\?php/
 	file-mime "text/x-php", 40
 }
@@ -135,3 +250,23 @@ signature file-skp {
 	file-magic /^\xFF\xFE\xFF\x0E\x53\x00\x6B\x00\x65\x00\x74\x00\x63\x00\x68\x00\x55\x00\x70\x00\x20\x00\x4D\x00\x6F\x00\x64\x00\x65\x00\x6C\x00/
 	file-mime "application/skp", 100
 }
+
+signature file-elf-object {
+	file-mime "application/x-object", 50
+	file-magic /\x7fELF[\x01\x02](\x01.{10}\x01\x00|\x02.{10}\x00\x01)/
+}
+
+signature file-elf {
+	file-mime "application/x-executable", 50
+	file-magic /\x7fELF[\x01\x02](\x01.{10}\x02\x00|\x02.{10}\x00\x02)/
+}
+
+signature file-elf-sharedlib {
+	file-mime "application/x-sharedlib", 50
+	file-magic /\x7fELF[\x01\x02](\x01.{10}\x03\x00|\x02.{10}\x00\x03)/
+}
+
+signature file-elf-coredump {
+	file-mime "application/x-coredump", 50
+	file-magic /\x7fELF[\x01\x02](\x01.{10}\x04\x00|\x02.{10}\x00\x04)/
+}

scripts/base/frameworks/files/magic/image.sig

@@ -0,0 +1,166 @@
+
+signature file-tiff {
+	file-mime "image/tiff", 70
+	file-magic /^(MM\x00[\x2a\x2b]|II[\x2a\x2b]\x00)/
+}
+
+signature file-gif {
+	file-mime "image/gif", 70
+	file-magic /^GIF8/
+}
+
+# JPEG image
+signature file-jpeg {
+	file-mime "image/jpeg", 52
+	file-magic /^\xff\xd8/
+}
+
+signature file-bmp {
+	file-mime "image/x-ms-bmp", 50
+	file-magic /BM.{12}[\x0c\x28\x40\x6c\x7c\x80]\x00/
+}
+
+signature file-ico {
+	file-magic /^\x00\x00\x01\x00/
+	file-mime "image/x-icon", 70
+}
+
+signature file-cur {
+	file-magic /^\x00\x00\x02\x00/
+	file-mime "image/x-cursor", 70
+}
+
+signature file-magic-auto289 {
+	file-mime "image/vnd.adobe.photoshop", 70
+	file-magic /^8BPS/
+}
+
+signature file-png {
+	file-mime "image/png", 110
+	file-magic /^\x89PNG/
+}
+
+# JPEG 2000
+signature file-jp2 {
+	file-mime "image/jp2", 60
+	file-magic /.{4}ftypjp2/
+}
+
+# JPEG 2000
+signature file-jp22 {
+	file-mime "image/jp2", 70
+	file-magic /\x00\x00\x00\x0cjP  \x0d\x0a\x87\x0a.{8}jp2 /
+}
+
+# JPEG 2000
+signature file-jpx {
+	file-mime "image/jpx", 70
+	file-magic /\x00\x00\x00\x0cjP  \x0d\x0a\x87\x0a.{8}jpx /
+}
+
+# JPEG 2000
+signature file-jpm {
+	file-mime "image/jpm", 70
+	file-magic /\x00\x00\x00\x0cjP  \x0d\x0a\x87\x0a.{8}jpm /
+}
+
+# Xcursor image
+signature file-x-cursor {
+	file-mime "image/x-xcursor", 70
+	file-magic /^Xcur/
+}
+
+# NIFF image
+signature file-niff {
+	file-mime "image/x-niff", 70
+	file-magic /^IIN1/
+}
+
+# OpenEXR image
+signature file-openexr {
+	file-mime "image/x-exr", 70
+	file-magic /^\x76\x2f\x31\x01/
+}
+
+# DPX image
+signature file-dpx {
+	file-mime "image/x-dpx", 70
+	file-magic /^SDPX/
+}
+
+# Cartesian Perceptual Compression image
+signature file-cpi {
+	file-mime "image/x-cpi", 70
+	file-magic /(CPC\xb2)/
+}
+
+signature file-orf {
+	file-mime "image/x-olympus-orf", 70
+	file-magic /IIR[OS]|MMOR/
+}
+
+# Foveon X3F raw image
+signature file-x3r {
+	file-mime "image/x-x3f", 70
+	file-magic /^FOVb/
+}
+
+# Paint.NET image
+signature file-paint-net {
+	file-mime "image/x-paintnet", 70
+	file-magic /^PDN3/
+}
+
+# Corel Draw Picture
+signature file-coreldraw {
+	file-mime "image/x-coreldraw", 70
+	file-magic /^RIFF....CDR[A6]/
+}
+
+# Netpbm PAM image
+signature file-netbpm{
+	file-mime "image/x-portable-pixmap", 50
+	file-magic /^P7/
+}
+
+# JPEG 2000 image
+signature file-jpeg-2000 {
+	file-mime "image/jp2", 50
+	file-magic /^....jP/
+}
+
+# DjVU Images
+signature file-djvu {
+	file-mime "image/vnd.djvu", 70
+	file-magic /AT\x26TFORM.{4}(DJV[MUI]|THUM)/
+}
+
+# DWG AutoDesk AutoCAD
+signature file-dwg {
+	file-mime "image/vnd.dwg", 90
+	file-magic /^(AC[12]\.|AC10)/
+}
+
+# GIMP XCF image
+signature file-gimp-xcf {
+	file-mime "image/x-xcf", 110
+	file-magic /^gimp xcf/
+}
+
+# Polar Monitor Bitmap text
+signature file-polar-monitor-bitmap {
+	file-mime "image/x-polar-monitor-bitmap", 160
+	file-magic /^\x5bBitmapInfo2\x5d/
+}
+
+# Award BIOS bitmap
+signature file-award-bitmap {
+	file-mime "image/x-award-bmp", 20
+	file-magic /^AWBM/
+}
+
+# Award BIOS Logo, 136 x 84
+signature file-award-bios-logo {
+	file-mime "image/x-award-bioslogo", 50
+	file-magic /^\x11[\x06\x09]/
+}

scripts/base/frameworks/files/magic/msoffice.sig

@@ -26,3 +26,9 @@ signature file-pptx {
 	file-magic /^PK\x03\x04.{26}(\[Content_Types\]\.xml|_rels\x2f\.rels|ppt\x2f).*PK\x03\x04.{26}ppt\x2f/
 	file-mime "application/vnd.openxmlformats-officedocument.presentationml.presentation", 80
 }
+
+signature file-msaccess {
+	file-mime "application/x-msaccess", 180
+	file-magic /.{4}Standard (Jet|ACE) DB\x00/
+}
+

scripts/base/frameworks/files/magic/video.sig

@@ -0,0 +1,105 @@
+
+# Macromedia Flash Video
+signature file-flv {
+	file-mime "video/x-flv", 60
+	file-magic /^FLV/
+}
+
+# FLI animation
+signature file-fli {
+	file-mime "video/x-fli", 50
+	file-magic /^.{4}\x11\xaf/
+}
+
+# FLC animation
+signature file-flc {
+	file-mime "video/x-flc", 50
+	file-magic /^.{4}\x12\xaf/
+}
+
+# Motion JPEG 2000
+signature file-mj2 {
+	file-mime "video/mj2", 70
+	file-magic /\x00\x00\x00\x0cjP  \x0d\x0a\x87\x0a.{8}mjp2/
+}
+
+# MNG video
+signature file-mng {
+	file-mime "video/x-mng", 70
+	file-magic /^\x8aMNG/
+}
+
+# JNG video
+signature file-jng {
+	file-mime "video/x-jng", 70
+	file-magic /^\x8bJNG/
+}
+
+# Generic MPEG container
+signature file-mpeg {
+	file-mime "video/mpeg", 50
+	file-magic /(\x00\x00\x01[\xb0-\xbb])/
+}
+
+# MPV
+signature file-mpv {
+	file-mime "video/mpv", 71
+	file-magic /(\x00\x00\x01\xb3)/
+}
+
+# H.264
+signature file-h264 {
+	file-mime "video/h264", 41
+	file-magic /(\x00\x00\x00\x01)([\x07\x27\x47\x67\x87\xa7\xc7\xe7])/
+}
+
+# WebM video
+signature file-webm {
+	file-mime "video/webm", 70
+	file-magic /(\x1a\x45\xdf\xa3)(.*)(B\x82)(.{1})(webm)/
+}
+
+# Matroska video
+signature file-matroska {
+	file-mime "video/x-matroska", 110
+	file-magic /(\x1a\x45\xdf\xa3)(.*)(B\x82)(.{1})(matroska)/
+}
+
+# MP2P
+signature file-mp2p {
+	file-mime "video/mp2p", 21
+	file-magic /\x00\x00\x01\xba([\x40-\x7f\xc0-\xff])/
+}
+
+# MPEG transport stream data. These files typically have the extension "ts".
+# Note: The 0x47 repeats every 188 bytes. Using four as the number of
+# occurrences for the test here is arbitrary.
+signature file-mp2t {
+	file-mime "video/mp2t", 40
+	file-magic /^(\x47.{187}){4}/
+}
+
+# Silicon Graphics video
+signature file-sgi-movie {
+	file-mime "video/x-sgi-movie", 70
+	file-magic /^MOVI/
+}
+
+# Apple QuickTime movie
+signature file-quicktime {
+	file-mime "video/quicktime", 70
+	file-magic /^....(mdat|moov)/
+}
+
+# MPEG v4 video
+signature file-mp4 {
+	file-mime "video/mp4", 70
+	file-magic /^....ftyp(isom|mp4[12])/
+}
+
+# 3GPP Video
+signature file-3gpp {
+	file-mime "video/3gpp", 60
+	file-magic /^....ftyp(3g[egps2]|avc1|mmp4)/
+}
+

scripts/base/frameworks/files/main.bro

@@ -129,12 +129,11 @@ export {
 	## files based on the detected mime type of the file.
 	const analyze_by_mime_type_automatically = T &redef;
 
-	## The default setting for if the file reassembler is enabled for 
+	## The default setting for file reassembly.
-	## each file.
 	const enable_reassembler = T &redef;
 
 	## The default per-file reassembly buffer size.
-	const reassembly_buffer_size = 1048576 &redef;
+	const reassembly_buffer_size = 524288 &redef;
 
 	## Allows the file reassembler to be used if it's necessary because the
 	## file is transferred out of order.
@@ -313,7 +312,7 @@ global analyzer_add_callbacks: table[Files::Tag] of function(f: fa_file, args: A
 
 event bro_init() &priority=5
 	{
-	Log::create_stream(Files::LOG, [$columns=Info, $ev=log_files]);
+	Log::create_stream(Files::LOG, [$columns=Info, $ev=log_files, $path="files"]);
 	}
 
 function set_info(f: fa_file)
@@ -484,16 +483,19 @@ event file_over_new_connection(f: fa_file, c: connection, is_orig: bool) &priori
 	add f$info$rx_hosts[f$is_orig ? cid$resp_h : cid$orig_h];
 	}
 
-event file_mime_type(f: fa_file, mime_type: string) &priority=10
+event file_sniff(f: fa_file, meta: fa_metadata) &priority=10
 	{
 	set_info(f);
 
-	f$info$mime_type = mime_type;
+	if ( ! meta?$mime_type )
+		return;
+
+	f$info$mime_type = meta$mime_type;
 
 	if ( analyze_by_mime_type_automatically &&
-	     mime_type in mime_type_to_analyzers )
+	     meta$mime_type in mime_type_to_analyzers )
 		{
-		local analyzers = mime_type_to_analyzers[mime_type];
+		local analyzers = mime_type_to_analyzers[meta$mime_type];
 		for ( a in analyzers )
 			{
 			add f$info$analyzers[Files::analyzer_name(a)];

scripts/base/frameworks/input/main.bro

@@ -1,18 +1,25 @@
 ##! The input framework provides a way to read previously stored data either
-##! as an event stream or into a bro table.
+##! as an event stream or into a Bro table.
 
 module Input;
 
 export {
 	type Event: enum {
+		## New data has been imported.
 		EVENT_NEW = 0,
+		## Existing data has been changed.
 		EVENT_CHANGED = 1,
+		## Previously existing data has been removed.
 		EVENT_REMOVED = 2,
 	};
 
+	## Type that defines the input stream read mode.
 	type Mode: enum {
+		## Do not automatically reread the file after it has been read.
 		MANUAL = 0,
+		## Reread the entire file each time a change is found.
 		REREAD = 1,
+		## Read data from end of file each time new data is appended.
 		STREAM = 2
 	};
 
@@ -24,20 +31,20 @@ export {
 
 	## Separator between fields.
 	## Please note that the separator has to be exactly one character long.
-	## Can be overwritten by individual writers.
+	## Individual readers can use a different value.
 	const separator = "\t" &redef;
 
 	## Separator between set elements.
 	## Please note that the separator has to be exactly one character long.
-	## Can be overwritten by individual writers.
+	## Individual readers can use a different value.
 	const set_separator = "," &redef;
 
 	## String to use for empty fields.
-	## Can be overwritten by individual writers.
+	## Individual readers can use a different value.
 	const empty_field = "(empty)" &redef;
 
 	## String to use for an unset &optional field.
-	## Can be overwritten by individual writers.
+	## Individual readers can use a different value.
 	const unset_field = "-" &redef;
 
 	## Flag that controls if the input framework accepts records
@@ -47,11 +54,11 @@ export {
 	## abort. Defaults to false (abort).
 	const accept_unsupported_types = F &redef;
 
-	## TableFilter description type used for the `table` method.
+	## A table input stream type used to send data to a Bro table.
 	type TableDescription: record {
 		# Common definitions for tables and events
 
-		## String that allows the reader to find the source.
+		## String that allows the reader to find the source of the data.
 		## For `READER_ASCII`, this is the filename.
 		source: string;
 
@@ -61,7 +68,8 @@ export {
 		## Read mode to use for this stream.
 		mode: Mode &default=default_mode;
 
-		## Descriptive name. Used to remove a stream at a later time.
+		## Name of the input stream.  This is used by some functions to
+		## manipulate the stream.
 		name: string;
 
 		# Special definitions for tables
@@ -73,31 +81,35 @@ export {
 		idx: any;
 
 		## Record that defines the values used as the elements of the table.
-		## If this is undefined, then *destination* has to be a set.
+		## If this is undefined, then *destination* must be a set.
 		val: any &optional;
 
-		## Defines if the value of the table is a record (default), or a single value.
+		## Defines if the value of the table is a record (default), or a single
-		## When this is set to false, then *val* can only contain one element.
+		## value. When this is set to false, then *val* can only contain one
+		## element.
 		want_record: bool &default=T;
 
-		## The event that is raised each time a value is added to, changed in or removed
+		## The event that is raised each time a value is added to, changed in,
-		## from the table. The event will receive an Input::Event enum as the first
+		## or removed from the table. The event will receive an
-		## argument, the *idx* record as the second argument and the value (record) as the
+		## Input::TableDescription as the first argument, an Input::Event
-		## third argument.
+		## enum as the second argument, the *idx* record as the third argument
-		ev: any &optional; # event containing idx, val as values.
+		## and the value (record) as the fourth argument.
+		ev: any &optional;
 
-		## Predicate function that can decide if an insertion, update or removal should
+		## Predicate function that can decide if an insertion, update or removal
-		## really be executed. Parameters are the same as for the event. If true is
+		## should really be executed. Parameters have same meaning as for the
-		## returned, the update is performed. If false is returned, it is skipped.
+		## event.
+		## If true is returned, the update is performed. If false is returned,
+		## it is skipped.
 		pred: function(typ: Input::Event, left: any, right: any): bool &optional;
 
-		## A key/value table that will be passed on the reader.
+		## A key/value table that will be passed to the reader.
-		## Interpretation of the values is left to the writer, but
+		## Interpretation of the values is left to the reader, but
 		## usually they will be used for configuration purposes.
-                config: table[string] of string &default=table();
+		config: table[string] of string &default=table();
 	};
 
-	## EventFilter description type used for the `event` method.
+	## An event input stream type used to send input data to a Bro event.
 	type EventDescription: record {
 		# Common definitions for tables and events
 
@@ -116,19 +128,26 @@ export {
 
 		# Special definitions for events
 
-		## Record describing the fields to be retrieved from the source input.
+		## Record type describing the fields to be retrieved from the input
+		## source.
 		fields: any;
 
-		## If this is false, the event receives each value in fields as a separate argument.
+		## If this is false, the event receives each value in *fields* as a
-		## If this is set to true (default), the event receives all fields in a single record value.
+		## separate argument.
+		## If this is set to true (default), the event receives all fields in
+		## a single record value.
 		want_record: bool &default=T;
 
-		## The event that is raised each time a new line is received from the reader.
+		## The event that is raised each time a new line is received from the
-		## The event will receive an Input::Event enum as the first element, and the fields as the following arguments.
+		## reader. The event will receive an Input::EventDescription record
+		## as the first argument, an Input::Event enum as the second
+		## argument, and the fields (as specified in *fields*) as the following
+		## arguments (this will either be a single record value containing
+		## all fields, or each field value as a separate argument).
 		ev: any;
 
-		## A key/value table that will be passed on the reader.
+		## A key/value table that will be passed to the reader.
-		## Interpretation of the values is left to the writer, but
+		## Interpretation of the values is left to the reader, but
 		## usually they will be used for configuration purposes.
 		config: table[string] of string &default=table();
 	};
@@ -155,28 +174,29 @@ export {
 		## field will be the same value as the *source* field.
 		name: string;
 
-		## A key/value table that will be passed on the reader.
+		## A key/value table that will be passed to the reader.
-		## Interpretation of the values is left to the writer, but
+		## Interpretation of the values is left to the reader, but
 		## usually they will be used for configuration purposes.
 		config: table[string] of string &default=table();
 	};
 
-	## Create a new table input from a given source.
+	## Create a new table input stream from a given source.
 	##
 	## description: `TableDescription` record describing the source.
 	##
 	## Returns: true on success.
 	global add_table: function(description: Input::TableDescription) : bool;
 
-	## Create a new event input from a given source.
+	## Create a new event input stream from a given source.
 	##
 	## description: `EventDescription` record describing the source.
 	##
 	## Returns: true on success.
 	global add_event: function(description: Input::EventDescription) : bool;
 
-	## Create a new file analysis input from a given source.  Data read from
+	## Create a new file analysis input stream from a given source.  Data read
-	## the source is automatically forwarded to the file analysis framework.
+	## from the source is automatically forwarded to the file analysis
+	## framework.
 	##
 	## description: A record describing the source.
 	##
@@ -199,7 +219,11 @@ export {
 
 	## Event that is called when the end of a data source has been reached,
 	## including after an update.
-	global end_of_data: event(name: string, source:string);
+	##
+	## name: Name of the input stream.
+	##
+	## source: String that identifies the data source (such as the filename).
+	global end_of_data: event(name: string, source: string);
 }
 
 @load base/bif/input.bif