Merge branch 'master' into topic/jsiwek/broxygen

CHANGES

@@ -1,4 +1,34 @@
 
+2.2-beta-114 | 2013-10-18 14:17:57 -0700
+
+  * Moving the SQLite examples into separate Bro files to turn them
+    into sphinx-btest tests. (Robin Sommer)
+
+2.2-beta-112 | 2013-10-18 13:47:13 -0700
+
+  * A larger chunk of documentation fixes and cleanup. (Daniel Thayer)
+    
+    Apart from many smaller improves this includes in particular:
+
+        * Add README files for most Bro frameworks and base/protocols.
+        * Add README files for base/protocols.
+        * Update installation instructions.
+        * Improvements to file analysis docs and conversion to using
+          btest sphinx.
+
+2.2-beta-80 | 2013-10-18 13:18:05 -0700
+
+  * SQLite reader/writer documentation. (Bernhard Amann)
+
+  * Check that the SQLite reader is only used in MANUAL reading mode.
+    (Bernhard Amann)
+
+  * Rename the SQLite writer "dbname" configuration option to
+    "tablename". (Bernhard Amann)
+
+  * Remove the "dbname" configuration option from the SQLite reader as
+    it wasn't used there. (Bernhard Amann)
+
 2.2-beta-73 | 2013-10-14 14:28:25 -0700
 
   * Fix misc. Coverity-reported issues (leaks, potential null pointer

VERSION

@@ -1 +1 @@
-2.2-beta-73
+2.2-beta-114

aux/broctl

@@ -1 +1 @@
-Subproject commit 2ccc76eee5565b7142e10f9b625a05e9932f459f
+Subproject commit e8eda204f418c78cc35102db04602ad2ea94aff8

doc/frameworks/file-analysis.rst

@@ -31,40 +31,13 @@ some information about the file such as which network
 :bro:see:`connection` and protocol are transporting the file, how many
 bytes have been transferred so far, and its MIME type.
 
-.. code:: bro
+Here's a simple example:
 
-    event connection_state_remove(c: connection)
+.. btest-include:: ${DOC_ROOT}/frameworks/file_analysis_01.bro
-        {
-        print "connection_state_remove";
-        print c$uid;
-        print c$id;
-        for ( s in c$service )
-            print s;
-        }
 
-    event file_state_remove(f: fa_file)
+.. btest:: file-analysis-01
-        {
-        print "file_state_remove";
-        print f$id;
-        for ( cid in f$conns )
-            {
-            print f$conns[cid]$uid;
-            print cid;
-            }
-        print f$source;
-        }
 
-might give output like::
+    @TEST-EXEC: btest-rst-cmd bro -r ${TRACES}/http/get.trace ${DOC_ROOT}/frameworks/file_analysis_01.bro
-
-    file_state_remove
-    Cx92a0ym5R8
-    REs2LQfVW2j
-    [orig_h=10.0.0.7, orig_p=59856/tcp, resp_h=192.150.187.43, resp_p=80/tcp]
-    HTTP
-    connection_state_remove
-    REs2LQfVW2j
-    [orig_h=10.0.0.7, orig_p=59856/tcp, resp_h=192.150.187.43, resp_p=80/tcp]
-    HTTP
 
 This doesn't perform any interesting analysis yet, but does highlight
 the similarity between analysis of connections and files.  Connections
@@ -90,27 +63,16 @@ will write the contents of the file out to the local file system).
 In the future there may be file analyzers that automatically attach to
 files based on heuristics, similar to the Dynamic Protocol Detection
 (DPD) framework for connections, but many will always require an
-explicit attachment decision:
+explicit attachment decision.
 
-.. code:: bro
+Here's a simple example of how to use the MD5 file analyzer to
+calculate the MD5 of plain text files:
 
-    event file_new(f: fa_file)
+.. btest-include:: ${DOC_ROOT}/frameworks/file_analysis_02.bro
-        {
-        print "new file", f$id;
-        if ( f?$mime_type && f$mime_type == "text/plain" )
-            Files::add_analyzer(f, Files::ANALYZER_MD5);
-        }
 
-    event file_hash(f: fa_file, kind: string, hash: string)
+.. btest:: file-analysis-02
-        {
-        print "file_hash", f$id, kind, hash;
-        }
 
-this script calculates MD5s for all plain text files and might give
+    @TEST-EXEC: btest-rst-cmd bro -r ${TRACES}/http/get.trace ${DOC_ROOT}/frameworks/file_analysis_02.bro
-output::
-
-    new file, Cx92a0ym5R8
-    file_hash, Cx92a0ym5R8, md5, 397168fd09991a0e712254df7bc639ac
 
 Some file analyzers might have tunable parameters that need to be
 specified in the call to :bro:see:`Files::add_analyzer`:
@@ -144,41 +106,19 @@ in the same way it analyzes files that it sees coming over traffic from
 a network interface it's monitoring.  It only requires a call to
 :bro:see:`Input::add_analysis`:
 
-.. code:: bro
+.. btest-include:: ${DOC_ROOT}/frameworks/file_analysis_03.bro
-
-    redef exit_only_after_terminate = T;
-
-    event file_new(f: fa_file)
-        {
-        print "new file", f$id;
-        Files::add_analyzer(f, Files::ANALYZER_MD5);
-        }
-
-    event file_state_remove(f: fa_file)
-        {
-        Input::remove(f$source);
-        terminate();
-        }
-
-    event file_hash(f: fa_file, kind: string, hash: string)
-        {
-        print "file_hash", f$id, kind, hash;
-        }
-
-    event bro_init()
-        {
-        local source: string = "./myfile";
-        Input::add_analysis([$source=source, $name=source]);
-        }
 
 Note that the "source" field of :bro:see:`fa_file` corresponds to the
 "name" field of :bro:see:`Input::AnalysisDescription` since that is what
 the input framework uses to uniquely identify an input stream.
 
-The output of the above script may be::
+The output of the above script may be (assuming a file called "myfile"
+exists):
 
-    new file, G1fS2xthS4l
+.. btest:: file-analysis-03
-    file_hash, G1fS2xthS4l, md5, 54098b367d2e87b078671fad4afb9dbb
+
+    @TEST-EXEC: echo "Hello world" > myfile
+    @TEST-EXEC: btest-rst-cmd bro ${DOC_ROOT}/frameworks/file_analysis_03.bro
 
 Nothing that special, but it at least verifies the MD5 file analyzer
 saw all the bytes of the input file and calculated the checksum

doc/frameworks/file_analysis_01.bro

@@ -0,0 +1,20 @@
+event connection_state_remove(c: connection)
+    {
+    print "connection_state_remove";
+    print c$uid;
+    print c$id;
+    for ( s in c$service )
+        print s;
+    }
+
+event file_state_remove(f: fa_file)
+    {
+    print "file_state_remove";
+    print f$id;
+    for ( cid in f$conns )
+        {
+        print f$conns[cid]$uid;
+        print cid;
+        }
+    print f$source;
+    }

doc/frameworks/file_analysis_02.bro

@@ -0,0 +1,11 @@
+event file_new(f: fa_file)
+    {
+    print "new file", f$id;
+    if ( f?$mime_type && f$mime_type == "text/plain" )
+        Files::add_analyzer(f, Files::ANALYZER_MD5);
+    }
+
+event file_hash(f: fa_file, kind: string, hash: string)
+    {
+    print "file_hash", f$id, kind, hash;
+    }

doc/frameworks/file_analysis_03.bro

@@ -0,0 +1,25 @@
+redef exit_only_after_terminate = T;
+
+event file_new(f: fa_file)
+    {
+    print "new file", f$id;
+    Files::add_analyzer(f, Files::ANALYZER_MD5);
+    }
+
+event file_state_remove(f: fa_file)
+    {
+    print "file_state_remove";
+    Input::remove(f$source);
+    terminate();
+    }
+
+event file_hash(f: fa_file, kind: string, hash: string)
+    {
+    print "file_hash", f$id, kind, hash;
+    }
+
+event bro_init()
+    {
+    local source: string = "./myfile";
+    Input::add_analysis([$source=source, $name=source]);
+    }

doc/frameworks/geoip.rst

@@ -11,10 +11,41 @@ GeoLocation
     to find the geographic location for an IP address. Bro has support
     for the `GeoIP library <http://www.maxmind.com/app/c>`__ at the
     policy script level beginning with release 1.3 to account for this
-    need.
+    need.  To use this functionality, you need to first install the libGeoIP
+    software, and then install the GeoLite city database before building
+    Bro.
 
 .. contents::
 
+Install libGeoIP
+----------------
+
+* FreeBSD:
+
+  .. console::
+
+      sudo pkg_add -r GeoIP
+
+* RPM/RedHat-based Linux:
+
+  .. console::
+
+      sudo yum install GeoIP-devel
+
+* DEB/Debian-based Linux:
+
+  .. console::
+
+      sudo apt-get install libgeoip-dev
+
+* Mac OS X:
+
+  Vanilla OS X installations don't ship with libGeoIP, but if
+  installed from your preferred package management system (e.g.
+  MacPorts, Fink, or Homebrew), they should be automatically detected
+  and Bro will compile against them.
+
+
 GeoIPLite Database Installation
 ------------------------------------
 
@@ -22,39 +53,23 @@ 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 geolitecity
+`Download <http://www.maxmind.com/app/geolitecity>`__ the GeoLite city
-binary database and follow the directions to install it.
+binary database.
-
-FreeBSD Quick Install
----------------------
 
   .. console::
 
-    pkg_add -r GeoIP
     wget http://geolite.maxmind.com/download/geoip/database/GeoLiteCity.dat.gz
     gunzip GeoLiteCity.dat.gz
-    mv GeoLiteCity.dat /usr/local/share/GeoIP/GeoIPCity.dat
 
-    # Set your environment correctly before running Bro's configure script
+Next, the file needs to be put in the database directory.  This directory
-    export CFLAGS=-I/usr/local/include
+should already exist and will vary depending on which platform and package
-    export LDFLAGS=-L/usr/local/lib
+you are using.  For FreeBSD, use ``/usr/local/share/GeoIP``.  For Linux,
-
+use ``/usr/share/GeoIP`` or ``/var/lib/GeoIP`` (choose whichever one
-
+already exists).
-CentOS Quick Install
---------------------
     
   .. console::
 
-    yum install GeoIP-devel
+    mv GeoLiteCity.dat <path_to_database_dir>/GeoIPCity.dat
-    
-    wget http://geolite.maxmind.com/download/geoip/database/GeoLiteCity.dat.gz
-    gunzip GeoLiteCity.dat.gz
-    mkdir -p /var/lib/GeoIP/
-    mv GeoLiteCity.dat /var/lib/GeoIP/GeoIPCity.dat
-    
-    # Set your environment correctly before running Bro's configure script
-    export CFLAGS=-I/usr/local/include
-    export LDFLAGS=-L/usr/local/lib
 
 
 Usage

doc/frameworks/input.rst

@@ -1,4 +1,6 @@
 
+.. _framework-input:
+
 ===============
 Input Framework
 ===============
@@ -260,8 +262,13 @@ 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.
 
-In the future, the input framework will get support for new data sources
+Currently, Bro supports the following readers in addition to the 
-like, for example, different databases.
+aforementioned ones:
+
+.. toctree::
+   :maxdepth: 1
+
+   logging-input-sqlite
 
 Add_table options
 -----------------

doc/frameworks/logging-elasticsearch.rst

@@ -31,12 +31,12 @@ Once extracted, start ElasticSearch with::
 # ./bin/elasticsearch
 
 For more detailed information, refer to the ElasticSearch installation
-documentation: http://www.elasticsearch.org/guide/reference/setup/installation.html
+documentation: http://www.elasticsearch.org/guide/en/elasticsearch/reference/current/setup.html
 
 Compiling Bro with ElasticSearch Support
 ----------------------------------------
 
-First, ensure that you have libcurl installed the run configure.::
+First, ensure that you have libcurl installed then run configure::
 
     # ./configure
     [...]
@@ -51,9 +51,9 @@ First, ensure that you have libcurl installed the run configure.::
 Activating ElasticSearch
 ------------------------
 
-The easiest way to enable ElasticSearch output is to load the tuning/logs-to-
+The easiest way to enable ElasticSearch output is to load the
-elasticsearch.bro script.  If you are using BroControl, the following line in
+tuning/logs-to-elasticsearch.bro script.  If you are using BroControl,
-local.bro will enable it.
+the following line in local.bro will enable it:
 
 .. console::
 
@@ -76,7 +76,7 @@ A common problem encountered with ElasticSearch is too many files being held
 open.  The ElasticSearch website has some suggestions on how to increase the
 open file limit.
 
-  - http://www.elasticsearch.org/tutorials/2011/04/06/too-many-open-files.html
+  - http://www.elasticsearch.org/tutorials/too-many-open-files/
 
 TODO
 ----

doc/frameworks/logging-input-sqlite.rst

@@ -0,0 +1,166 @@
+
+============================================
+Logging To and Reading From SQLite Databases
+============================================
+
+.. rst-class:: opening
+
+   Starting with version 2.2, Bro features a SQLite logging writer
+   as well as a SQLite input reader. SQLite is a simple, file-based,
+   widely used SQL database system. Using SQLite allows Bro to write
+   and access data in a format that is easy to use in interchange with
+   other applications. Due to the transactional nature of SQLite,
+   databases can be used by several applications simultaneously. Hence,
+   they can, for example, be used to make data that changes regularly available
+   to Bro on a continuing basis.
+
+.. contents::
+
+Warning
+=======
+
+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.
+
+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
+configurations.
+
+Sending data from existing logging streams to SQLite is rather straightforward. 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:
+
+.. btest-include:: ${DOC_ROOT}/frameworks/sqlite-conn-filter.bro
+
+.. btest:: sqlite-conn-filter-check
+
+    # 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.
+It will also create a table with the name ``conn`` (if it 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
+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
+that are present in the ASCII log files::
+
+    # sqlite3 /var/db/conn.sqlite
+
+    SQLite version 3.8.0.2 2013-09-03 17:11:13
+    Enter ".help" for instructions
+    Enter SQL statements terminated with a ";"
+    sqlite> .schema
+    CREATE TABLE conn (
+    'ts' double precision,
+    'uid' text,
+    'id.orig_h' text,
+    'id.orig_p' integer,
+    ...
+
+Note that the ASCII ``conn.log`` will still be created. To disable the ASCII writer for a
+log stream, 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
+just the information you want to commit to the database. 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
+with version 2.2.
+
+Just as with the text-based input readers (please refer to the :ref:`framework-input`
+documentation for them and for basic information 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
+the resulting data will be structured. For this example, we expect that we have a SQLite database,
+which contains 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::
+
+    create table machines_to_users (
+    host text unique not null,
+    users text not null);
+
+    insert into machines_to_users values ('192.168.17.1', 'bernhard,matthias,seth');
+    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
+into Bro:
+
+.. btest-include:: ${DOC_ROOT}/frameworks/sqlite-read-table.bro
+
+.. btest:: sqlite-read-table-check
+
+    # 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
+userlist.
+
+Turning Data into Events
+------------------------
+
+The second mode is to use the SQLite reader to output the input data as events. Typically there
+are two reasons to do this. First, when the structure of the input data is too complicated
+for a direct table import. In this case, 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
+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
+could be used to check the sporadically happening downloads against the database.
+
+The SQLite commands to create the schema are as follows::
+
+    create table malware_hashes (
+    hash text unique not null,
+    description text not null);
+
+    insert into malware_hashes values ('86f7e437faa5a7fce15d1ddcb9eaeaea377667b8', 'malware a');
+    insert into malware_hashes values ('e9d71f5ee7c92d6dc9e92ffdad17b8bd49418f98', 'malware b');
+    insert into malware_hashes values ('84a516841ba77a5b4648de2cd0dfcb30ea46dbb4', 'malware c');
+    insert into malware_hashes values ('3c363836cf4e16666669a25da280a1865c2d2874', 'malware d');
+    insert into malware_hashes values ('58e6b3a414a1e090dfc6029add0f3555ccba127f', 'malware e');
+    insert into malware_hashes values ('4a0a19218e082a343a1b17e5333409af9d98f0f5', 'malware f');
+    insert into malware_hashes values ('54fd1711209fb1c0781092374132c66e79e2241b', 'malware g');
+    insert into malware_hashes values ('27d5482eebd075de44389774fce28c69f45c8a75', 'malware h');
+    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
+transmitted over the network. For each hash, a SQL-query 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
+
+.. btest:: sqlite-read-events-check
+
+    # 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
+will get one hit.

doc/frameworks/logging.rst

@@ -387,3 +387,4 @@ Bro supports the following output formats other than ASCII:
 
    logging-dataseries
    logging-elasticsearch
+   logging-input-sqlite

doc/frameworks/sqlite-conn-filter.bro

@@ -0,0 +1,12 @@
+event bro_init()
+    {
+    local filter: Log::Filter =
+        [
+        $name="sqlite",
+        $path="/var/db/conn",
+        $config=table(["tablename"] = "conn"),
+        $writer=Log::WRITER_SQLITE
+        ];
+    
+     Log::add_filter(Conn::LOG, filter);
+    }

doc/frameworks/sqlite-read-events.bro

@@ -0,0 +1,40 @@
+@load frameworks/files/hash-all-files
+
+type Val: record {
+    hash: string;
+    description: string;
+};
+
+event line(description: Input::EventDescription, tpe: Input::Event, r: Val)
+    {
+    print fmt("malware-hit with hash %s, description %s", r$hash, r$description);
+    }
+
+global malware_source = "/var/db/malware";
+
+event file_hash(f: fa_file, kind: string, hash: string)
+    {
+
+    # check all sha1 hashes
+    if ( kind=="sha1" )
+        {
+        Input::add_event(
+            [
+            $source=malware_source,
+            $name=hash,
+            $fields=Val,
+            $ev=line,
+            $want_record=T,
+            $config=table(
+                ["query"] = fmt("select * from malware_hashes where hash='%s';", hash)
+                ),
+            $reader=Input::READER_SQLITE
+            ]);
+        }
+    }
+
+event Input::end_of_data(name: string, source:string)
+    {
+    if ( source == malware_source )
+        Input::remove(name);
+    }

doc/frameworks/sqlite-read-table.bro

@@ -0,0 +1,35 @@
+type Idx: record {
+    host: addr;
+};
+
+type Val: record {
+    users: set[string];
+};
+
+global hostslist: table[addr] of Val = table();
+
+event bro_init()
+    {
+    Input::add_table([$source="/var/db/hosts",
+        $name="hosts",
+        $idx=Idx,
+        $val=Val,
+        $destination=hostslist,
+        $reader=Input::READER_SQLITE,
+        $config=table(["query"] = "select * from machines_to_users;")
+        ]);
+
+    Input::remove("hosts");
+    }
+
+event Input::end_of_data(name: string, source: string)
+    {
+    if ( name != "hosts" )
+        return;
+
+    # now all data is in the table
+    print "Hosts list has been successfully imported";
+
+    # List the users of one host.
+    print hostslist[192.168.17.1]$users;
+    }

doc/install/install.rst

@@ -32,6 +32,7 @@ before you begin:
     * Libmagic 5.04 or greater
     * Libz
     * Bash (for BroControl)
+    * Python (for BroControl)
 
 To build Bro from source, the following additional dependencies are required:
 
@@ -47,7 +48,8 @@ To build Bro from source, the following additional dependencies are required:
     * zlib headers
     * Perl
 
-To install the required dependencies, you can use:
+To install the required dependencies, you can use (when done, make sure
+that ``bash`` and ``python`` are in your ``PATH``):
 
 * RPM/RedHat-based Linux:
 
@@ -68,11 +70,7 @@ To install the required dependencies, you can use:
 
   .. console::
 
-      sudo pkg_add -r bash cmake swig bison python
+      sudo pkg_add -r bash cmake swig bison python perl
-
-  Note that ``bash`` needs to be in ``PATH``, which by default it is
-  not. The FreeBSD package installs the binary into
-  ``/usr/local/bin``.
 
 * Mac OS X:
 
@@ -87,8 +85,8 @@ To install the required dependencies, you can use:
   preferred Mac OS X package management system (e.g. MacPorts_, Fink_,
   or Homebrew_).
 
-  Specifically for MacPorts, the ``swig``, ``swig-ruby``, ``swig-python``
+  Specifically for MacPorts, the ``cmake``, ``swig``, ``swig-ruby``,
-  and ``file`` packages provide the required dependencies.
+  ``swig-python`` and ``file`` packages provide the required dependencies.
 
 
 Optional Dependencies
@@ -98,45 +96,14 @@ Bro can make use of some optional libraries and tools if they are found at
 build time:
 
     * LibGeoIP (for geo-locating IP addresses)
+    * sendmail (enables Bro and BroControl to send mail)
     * gperftools (tcmalloc is used to improve memory and CPU usage)
     * 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 easily installed
+LibGeoIP is probably the most interesting and can be installed
-on most platforms:
+on most platforms by following the instructions for :ref:`installing
-
+libGeoIP and the GeoIP database
-* RedHat Enterprise Linux:
-
-  .. console::
-
-      sudo yum install geoip-devel sendmail
-
-* CentOS Linux:
-
-  .. console::
-  
-      sudo yum install GeoIP-devel sendmail
-
-* DEB/Debian-based Linux:
-
-  .. console::
-
-      sudo apt-get install libgeoip-dev sendmail
-
-* FreeBSD using ports:
-
-  .. console::
-
-      sudo pkg_add -r GeoIP
-
-* Mac OS X:
-
-  Vanilla OS X installations don't ship with libGeoIP, but if
-  installed from your preferred package management system (e.g.
-  MacPorts, Fink, or Homebrew), they should be automatically detected
-  and Bro will compile against them.
-
-Additional steps may be needed to :ref:`get the right GeoIP database
 <geolocation>`.
 
 
@@ -217,7 +184,7 @@ 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 at `FAQ
+OpenBSD users, please see our `FAQ
 <http://www.bro.org/documentation/faq.html>`_ if you are having
 problems installing Bro.
 

doc/scripting/index.rst

@@ -351,7 +351,7 @@ decrypted from HTTP streams is stored in
 excerpt from :doc:`/scripts/base/protocols/http/main` below.
 
 .. btest-include:: ${BRO_SRC_ROOT}/scripts/base/protocols/http/main.bro
-   :lines: 8-10,19,20,118
+   :lines: 8-10,19-21,120
 
 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
@@ -810,7 +810,7 @@ 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: 10-12,16,17,19,21,23,25,28,31,35,37,56,62,68,90,93,97,100,104,108,109,114
+   :lines: 10-12,16-17,19,21,23,25,28,31,35,38,57,63,69,92,95,99,102,106,110-111,116
 
 Looking at the structure of the definition, a new collection of data
 types is being defined as a type called ``Info``.  Since this type

scripts/base/files/extract/main.bro

@@ -8,18 +8,21 @@ export {
 	const prefix = "./extract_files/" &redef;
 
 	## The default max size for extracted files (they won't exceed this
-	## number of bytes), unlimited.
+	## number of bytes). A value of zero means unlimited.
 	const default_limit = 0 &redef;
 
 	redef record Files::Info += {
-		## Local filenames of extracted file.
+		## Local filename of extracted file.
 		extracted: string &optional &log;
 	};
 
 	redef record Files::AnalyzerArgs += {
 		## The local filename to which to write an extracted file.
 		## This field is used in the core by the extraction plugin
-		## to know where to write the file to.  It's also optional
+		## to know where to write the file to.  If not specified, then
+		## a filename in the format "extract-<source>-<id>" is
+		## automatically assigned (using the *source* and *id*
+		## fields of :bro:see:`fa_file`).
 		extract_filename: string &optional;
 		## The maximum allowed file size in bytes of *extract_filename*.
 		## Once reached, a :bro:see:`file_extraction_limit` event is

scripts/base/files/unified2/main.bro

@@ -42,17 +42,17 @@ export {
 		sensor_id:          count    &log;
 		## Sig id for this generator.
 		signature_id:       count    &log;
-		## A string representation of the "signature_id" field if a sid_msg.map file was loaded.
+		## A string representation of the *signature_id* field if a sid_msg.map file was loaded.
 		signature:          string   &log &optional;
 		## Which generator generated the alert?
 		generator_id:       count    &log;
-		## A string representation of the "generator_id" field if a gen_msg.map file was loaded.
+		## A string representation of the *generator_id* field if a gen_msg.map file was loaded.
 		generator:          string   &log &optional;
 		## Sig revision for this id.
 		signature_revision: count    &log;
 		## Event classification.
 		classification_id:  count    &log;
-		## Descriptive classification string,
+		## Descriptive classification string.
 		classification:     string   &log &optional;
 		## Event priority.
 		priority_id:        count    &log;

scripts/base/frameworks/analyzer/README

@@ -0,0 +1,3 @@
+The analyzer framework allows to dynamically enable or disable Bro's
+protocol analyzers, as well as to manage the well-known ports which
+automatically activate a particular analyzer for new connections.

scripts/base/frameworks/analyzer/main.bro

@@ -5,8 +5,8 @@
 ##! particular analyzer for new connections.
 ##!
 ##! Protocol analyzers are identified by unique tags of type
-##! :bro:type:`Analyzer::Tag`, such as :bro:enum:`Analyzer::ANALYZER_HTTP` and
+##! :bro:type:`Analyzer::Tag`, such as :bro:enum:`Analyzer::ANALYZER_HTTP`.
-##! :bro:enum:`Analyzer::ANALYZER_HTTP`. These tags are defined internally by
+##! These tags are defined internally by
 ##! the analyzers themselves, and documented in their analyzer-specific
 ##! description along with the events that they generate.
 
@@ -15,8 +15,8 @@
 module Analyzer;
 
 export {
-	## If true, all available analyzers are initially disabled at startup. One
+	## If true, all available analyzers are initially disabled at startup.
-	## can then selectively enable them with
+	## One can then selectively enable them with
 	## :bro:id:`Analyzer::enable_analyzer`.
 	global disable_all = F &redef;
 
@@ -45,7 +45,7 @@ export {
 	##
 	## ports: The set of well-known ports to associate with the analyzer.
 	##
-	## Returns: True if the ports were sucessfully registered.
+	## Returns: True if the ports were successfully registered.
 	global register_for_ports: function(tag: Analyzer::Tag, ports: set[port]) : bool;
 
 	## Registers an individual well-known port for an analyzer. If a future
@@ -57,7 +57,7 @@ export {
 	##
 	## p: The well-known port to associate with the analyzer.
 	##
-	## Returns: True if the port was sucessfully registered.
+	## Returns: True if the port was successfully registered.
 	global register_for_port: function(tag: Analyzer::Tag, p: port) : bool;
 
 	## Returns a set of all well-known ports currently registered for a
@@ -88,8 +88,8 @@ export {
 	## Returns: The analyzer tag corresponding to the name.
 	global get_tag: function(name: string): Analyzer::Tag;
 
-	## Schedules an analyzer for a future connection originating from a given IP
+	## Schedules an analyzer for a future connection originating from a
-	## address and port.
+	## given IP address and port.
 	##
 	## orig: The IP address originating a connection in the future.
 	##       0.0.0.0 can be used as a wildcard to match any originator address.
@@ -103,7 +103,7 @@ export {
 	## tout: A timeout interval after which the scheduling request will be
 	##       discarded if the connection has not yet been seen.
 	##
-	## Returns: True if succesful.
+	## Returns: True if successful.
 	global schedule_analyzer: function(orig: addr, resp: addr, resp_p: port,
 	                                   analyzer: Analyzer::Tag, tout: interval) : bool;
 

scripts/base/frameworks/cluster/README

@@ -0,0 +1,2 @@
+The cluster framework provides for establishing and controlling a cluster
+of Bro instances.

scripts/base/frameworks/cluster/main.bro

@@ -39,7 +39,8 @@ export {
 		## The node type doing all the actual traffic analysis.
 		WORKER,
 		## A node acting as a traffic recorder using the
-		## `Time Machine <http://tracker.bro.org/time-machine>`_ software.
+		## `Time Machine <http://bro.org/community/time-machine.html>`_
+		## software.
 		TIME_MACHINE,
 	};
 	
@@ -58,7 +59,7 @@ export {
 	## Events raised by workers and handled by a manager.
 	const worker2manager_events = /(TimeMachine::command|Drop::.*)/ &redef;
 	
-	## Events raised by workers and handled by proxies..
+	## Events raised by workers and handled by proxies.
 	const worker2proxy_events = /EMPTY/ &redef;
 	
 	## Events raised by TimeMachine instances and handled by a manager.
@@ -80,7 +81,7 @@ export {
 		## If the *ip* field is a non-global IPv6 address, this field
 		## can specify a particular :rfc:`4007` ``zone_id``.
 		zone_id:      string      &default="";
-		## The port to which the this local node can connect when
+		## The port to which this local node can connect when
 		## establishing communication.
 		p:            port;
 		## Identifier for the interface a worker is sniffing.

scripts/base/frameworks/cluster/nodes/worker.bro

@@ -19,6 +19,6 @@ redef Log::default_rotation_postprocessor_cmd = "delete-log";
 ## Record all packets into trace file.
 ##
 ## Note that this only indicates that *if* we are recording packets, we want all
-## of them (rather than just those the core deems sufficiently important). Setting
+## of them (rather than just those the core deems sufficiently important).
-## this does not turn recording on. Use '-w <trace>' for that.
+## Setting this does not turn recording on. Use '-w <trace>' for that.
 redef record_all_packets = T;

scripts/base/frameworks/communication/README

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

scripts/base/frameworks/communication/main.bro

@@ -42,10 +42,11 @@ export {
 	type Info: record {
 		## The network time at which a communication event occurred.
 		ts:                  time   &log;
-		## The peer name (if any) with which a communication event is concerned.
+		## The peer name (if any) with which a communication event is
+		## concerned.
 		peer:                string &log &optional;
-		## Where the communication event message originated from, that is,
+		## Where the communication event message originated from, that
-		## either from the scripting layer or inside the Bro process.
+		## is, either from the scripting layer or inside the Bro process.
 		src_name:            string &log &optional;
 		## .. todo:: currently unused.
 		connected_peer_desc: string &log &optional;
@@ -71,8 +72,8 @@ export {
 		## can specify a particular :rfc:`4007` ``zone_id``.
 		zone_id: string &optional;
 
-		## Port of the remote Bro communication endpoint if we are initiating
+		## Port of the remote Bro communication endpoint if we are
-		## the connection based on the :bro:id:`connect` field.
+		## initiating the connection (based on the *connect* field).
 		p: port &optional;
 
 		## When accepting a connection, the configuration only
@@ -87,7 +88,7 @@ export {
 		events: pattern &optional;
 
 		## Whether we are going to connect (rather than waiting
-		## for the other sie to connect to us).
+		## for the other side to connect to us).
 		connect: bool &default = F;
 
 		## If disconnected, reconnect after this many seconds.
@@ -103,13 +104,14 @@ export {
 		request_logs: bool &default = F;
 
 		## When performing state synchronization, whether we consider
-		## our state to be authoritative.  If so, we will send the peer
+		## our state to be authoritative (only one side can be
-		## our current set when the connection is set up.
+		## authoritative).  If so, we will send the peer our current
-		## (Only one side can be authoritative)
+		## set when the connection is set up.
 		auth: bool &default = F;
 
 		## If not set, no capture filter is sent.
-		## If set to "", the default capture filter is sent.
+		## If set to an empty string, then the default capture filter
+		## is sent.
 		capture_filter: string &optional;
 
 		## Whether to use SSL-based communication.

scripts/base/frameworks/control/README

@@ -0,0 +1,3 @@
+The control framework provides the foundation for providing "commands"
+that can be taken remotely at runtime to modify a running Bro instance
+or collect information from the running instance.

scripts/base/frameworks/control/main.bro

@@ -57,7 +57,8 @@ export {
 	## Returns the current net_stats.
 	global net_stats_response: event(s: string);
 
-	## Inform the remote Bro instance that it's configuration may have been updated.
+	## Inform the remote Bro instance that it's configuration may have been
+	## updated.
 	global configuration_update_request: event();
 	## This event is a wrapper and alias for the
 	## :bro:id:`Control::configuration_update_request` event.

scripts/base/frameworks/dpd/README

@@ -0,0 +1,2 @@
+The DPD (dynamic protocol detection) activates port-independent protocol
+detection and selectively disables analyzers if protocol violations occur.

scripts/base/frameworks/files/README

@@ -0,0 +1,3 @@
+The file analysis framework provides an interface for driving the analysis
+of files, possibly independent of any network protocol over which they're
+transported.

scripts/base/frameworks/files/main.bro

@@ -14,10 +14,11 @@ export {
 		LOG
 	};
 
-	## A structure which represents a desired type of file analysis.
+	## A structure which parameterizes a type of file analysis.
 	type AnalyzerArgs: record {
 		## An event which will be generated for all new file contents,
-		## chunk-wise.  Used when *tag* is
+		## chunk-wise.  Used when *tag* (in the
+		## :bro:see:`Files::add_analyzer` function) is
 		## :bro:see:`Files::ANALYZER_DATA_EVENT`.
 		chunk_event: event(f: fa_file, data: string, off: count) &optional;
 
@@ -47,12 +48,12 @@ export {
 		## the data traveled to.
 		rx_hosts: set[addr] &log;
 
-		## Connection UIDS over which the file was transferred.
+		## Connection UIDs over which the file was transferred.
 		conn_uids: set[string] &log;
 
-		## An identification of the source of the file data.  E.g. it may be
+		## An identification of the source of the file data.  E.g. it
-		## a network protocol over which it was transferred, or a local file
+		## may be a network protocol over which it was transferred, or a
-		## path which was read, or some other input source.
+		## local file path which was read, or some other input source.
 		source: string &log &optional;
 
 		## A value to represent the depth of this file in relation 
@@ -64,9 +65,10 @@ export {
 		## A set of analysis types done during the file analysis.
 		analyzers: set[string] &log;
 
-		## A mime type provided by libmagic against the *bof_buffer*, or
+		## A mime type provided by libmagic against the *bof_buffer*
-		## in the cases where no buffering of the beginning of file occurs,
+		## field of :bro:see:`fa_file`, or in the cases where no
-		## an initial guess of the mime type based on the first data seen.
+		## buffering of the beginning of file occurs, an initial
+		## guess of the mime type based on the first data seen.
 		mime_type: string &log &optional;
 
 		## A filename for the file if one is available from the source
@@ -79,12 +81,12 @@ export {
 
 		## If the source of this file is a network connection, this field
 		## indicates if the data originated from the local network or not as
-		## determined by the configured bro:see:`Site::local_nets`.
+		## determined by the configured :bro:see:`Site::local_nets`.
 		local_orig: bool &log &optional;
 
 		## If the source of this file is a network connection, this field
-		## indicates if the file is being sent by the originator of the connection
+		## indicates if the file is being sent by the originator of the
-		## or the responder.
+		## connection or the responder.
 		is_orig: bool &log &optional;
 
 		## Number of bytes provided to the file analysis engine for the file.
@@ -116,15 +118,15 @@ export {
 	## The salt concatenated to unique file handle strings generated by
 	## :bro:see:`get_file_handle` before hashing them in to a file id
 	## (the *id* field of :bro:see:`fa_file`).
-	## Provided to help mitigate the possiblility of manipulating parts of
+	## Provided to help mitigate the possibility of manipulating parts of
 	## network connections that factor in to the file handle in order to
 	## generate two handles that would hash to the same file id.
 	const salt = "I recommend changing this." &redef;
 
 	## Sets the *timeout_interval* field of :bro:see:`fa_file`, which is
 	## used to determine the length of inactivity that is allowed for a file
-	## before internal state related to it is cleaned up.  When used within a
+	## before internal state related to it is cleaned up.  When used within
-	## :bro:see:`file_timeout` handler, the analysis will delay timing out
+	## a :bro:see:`file_timeout` handler, the analysis will delay timing out
 	## again for the period specified by *t*.
 	##
 	## f: the file.
@@ -132,7 +134,7 @@ export {
 	## t: the amount of time the file can remain inactive before discarding.
 	##
 	## Returns: true if the timeout interval was set, or false if analysis
-	##          for the *id* isn't currently active.
+	##          for the file isn't currently active.
 	global set_timeout_interval: function(f: fa_file, t: interval): bool;
 
 	## Adds an analyzer to the analysis of a given file.
@@ -144,7 +146,7 @@ export {
 	## args: any parameters the analyzer takes.
 	##
 	## Returns: true if the analyzer will be added, or false if analysis
-	##          for the *id* isn't currently active or the *args*
+	##          for the file isn't currently active or the *args*
 	##          were invalid for the analyzer type.
 	global add_analyzer: function(f: fa_file, 
 	                              tag: Files::Tag, 
@@ -154,10 +156,12 @@ export {
 	##
 	## f: the file.
 	##
+	## tag: the analyzer type.
+	##
 	## args: the analyzer (type and args) to remove.
 	##
 	## Returns: true if the analyzer will be removed, or false if analysis
-	##          for the *id* isn't currently active.
+	##          for the file isn't currently active.
 	global remove_analyzer: function(f: fa_file,
 	                                 tag: Files::Tag,
 	                                 args: AnalyzerArgs &default=AnalyzerArgs()): bool;
@@ -167,11 +171,12 @@ export {
 	## f: the file.
 	##
 	## Returns: true if analysis for the given file will be ignored for the
-	##          rest of it's contents, or false if analysis for the *id*
+	##          rest of its contents, or false if analysis for the file
 	##          isn't currently active.
 	global stop: function(f: fa_file): bool;
 
-	## Translates an file analyzer enum value to a string with the analyzer's name.
+	## Translates a file analyzer enum value to a string with the
+	## analyzer's name.
 	##
 	## tag: The analyzer tag.
 	##
@@ -183,7 +188,7 @@ export {
 	##
 	## f: The file to be described.
 	##
-	## Returns a text description regarding metadata of the file.
+	## Returns: a text description regarding metadata of the file.
 	global describe: function(f: fa_file): string;
 
 	type ProtoRegistration: record {
@@ -209,10 +214,10 @@ export {
 	## Returns: true if the protocol being registered was not previously registered.
 	global register_protocol: function(tag: Analyzer::Tag, reg: ProtoRegistration): bool;
 
-	## Register a callback for file analyzers to use if they need to do some manipulation
+	## Register a callback for file analyzers to use if they need to do some
-	## when they are being added to a file before the core code takes over.  This is 
+	## manipulation when they are being added to a file before the core code
-	## unlikely to be interesting for users and should only be called by file analyzer
+	## takes over.  This is unlikely to be interesting for users and should
-	## authors but it *not required*.
+	## only be called by file analyzer authors but is *not required*.
 	## 
 	## tag: Tag for the file analyzer.
 	##

scripts/base/frameworks/input/README

@@ -0,0 +1,2 @@
+The input framework provides a way to read previously stored data either as
+an event stream or into a Bro table.

scripts/base/frameworks/input/main.bro

@@ -33,45 +33,45 @@ export {
 	## that contain types that are not supported (at the moment
 	## file and function). If true, the input framework will
 	## warn in these cases, but continue. If false, it will
-	## abort. Defaults to false (abort)
+	## abort. Defaults to false (abort).
 	const accept_unsupported_types = F &redef;
 
 	## TableFilter description type used for the `table` method.
 	type TableDescription: record {
-		## Common definitions for tables and events
+		# Common definitions for tables and events
 
 		## String that allows the reader to find the source.
 		## For `READER_ASCII`, this is the filename.
 		source: string;
 
-		## Reader to use for this stream
+		## Reader to use for this stream.
 		reader: Reader &default=default_reader;
 
-		## Read mode to use for this stream
+		## Read mode to use for this stream.
 		mode: Mode &default=default_mode;
 
-		## Descriptive name. Used to remove a stream at a later time
+		## Descriptive name. Used to remove a stream at a later time.
 		name: string;
 
 		# Special definitions for tables
 
-		## Table which will receive the data read by the input framework
+		## Table which will receive the data read by the input framework.
 		destination: any;
 
-		## Record that defines the values used as the index of the table
+		## Record that defines the values used as the index of the table.
 		idx: any;
 
-		## Record that defines the values used as the elements of the table
+		## Record that defines the values used as the elements of the table.
-		## If val is undefined, destination has to be a set.
+		## If this is undefined, then *destination* has to be a set.
 		val: any &optional;
 
-		## Defines if the value of the table is a record (default), or a single  value. Val
+		## Defines if the value of the table is a record (default), or a single value.
-		## can only contain one element when this is set to false.
+		## 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
 		## from the table. The event will receive an Input::Event enum as the first
-		## argument, the idx record as the second argument and the value (record) as the
+		## argument, the *idx* record as the second argument and the value (record) as the
 		## third argument.
 		ev: any &optional; # event containing idx, val as values.
 
@@ -88,19 +88,19 @@ export {
 
 	## EventFilter description type used for the `event` method.
 	type EventDescription: record {
-		## Common definitions for tables and events
+		# Common definitions for tables and events
 
 		## String that allows the reader to find the source.
 		## For `READER_ASCII`, this is the filename.
 		source: string;
 
-		## Reader to use for this steam
+		## Reader to use for this stream.
 		reader: Reader &default=default_reader;
 
-		## Read mode to use for this stream
+		## Read mode to use for this stream.
 		mode: Mode &default=default_mode;
 
-		## Descriptive name. Used to remove a stream at a later time
+		## Descriptive name. Used to remove a stream at a later time.
 		name: string;
 
 		# Special definitions for events
@@ -108,8 +108,8 @@ export {
 		## Record describing the fields to be retrieved from the source input.
 		fields: any;
 
-		## If want_record if 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 separate argument.
-		## If it is set to true (default), the event receives all fields in a single record value.
+		## 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.
@@ -122,23 +122,23 @@ export {
 		config: table[string] of string &default=table();
 	};
 
-	## A file analyis input stream type used to forward input data to the
+	## A file analysis input stream type used to forward input data to the
 	## file analysis framework.
 	type AnalysisDescription: record {
 		## String that allows the reader to find the source.
 		## For `READER_ASCII`, this is the filename.
 		source: string;
 
-		## Reader to use for this steam.  Compatible readers must be
+		## Reader to use for this stream.  Compatible readers must be
 		## able to accept a filter of a single string type (i.e.
 		## they read a byte stream).
 		reader: Reader &default=Input::READER_BINARY;
 
-		## Read mode to use for this stream
+		## Read mode to use for this stream.
 		mode: Mode &default=default_mode;
 
 		## Descriptive name that uniquely identifies the input source.
-		## Can be used used to remove a stream at a later time.
+		## Can be used to remove a stream at a later time.
 		## This will also be used for the unique *source* field of
 		## :bro:see:`fa_file`.  Most of the time, the best choice for this
 		## field will be the same value as the *source* field.
@@ -150,38 +150,44 @@ export {
 		config: table[string] of string &default=table();
 	};
 
-	## Create a new table input from a given source. Returns true on success.
+	## Create a new table input 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. Returns true on success.
+	## Create a new event input from a given source.
 	##
-	## description: `TableDescription` record describing the 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
 	## the source is automatically forwarded to the file analysis framework.
 	##
-	## description: A record describing the source
+	## description: A record describing the source.
 	##
-	## Returns: true on sucess.
+	## Returns: true on success.
 	global add_analysis: function(description: Input::AnalysisDescription) : bool;
 
-	## Remove a input stream. Returns true on success and false if the named stream was
+	## Remove an input stream.
-	## not found.
 	##
-	## id: string value identifying the stream to be removed
+	## id: string value identifying the stream to be removed.
+	##
+	## Returns: true on success and false if the named stream was not found.
 	global remove: function(id: string) : bool;
 
 	## Forces the current input to be checked for changes.
-	## Returns true on success and false if the named stream was not found
 	##
-	## id: string value identifying the stream
+	## id: string value identifying the stream.
+	##
+	## Returns: true on success and false if the named stream was not found.
 	global force_update: function(id: string) : bool;
 
-	## Event that is called, when the end of a data source has been reached, including
+	## Event that is called when the end of a data source has been reached,
-	## after an update.
+	## including after an update.
 	global end_of_data: event(name: string, source:string);
 }
 

scripts/base/frameworks/input/readers/ascii.bro

@@ -6,11 +6,11 @@ module InputAscii;
 
 export {
 	## Separator between fields.
-	## Please note that the separator has to be exactly one character long
+	## Please note that the separator has to be exactly one character long.
 	const separator = Input::separator &redef;
 
 	## Separator between set elements.
-	## Please note that the separator has to be exactly one character long
+	## Please note that the separator has to be exactly one character long.
 	const set_separator = Input::set_separator &redef;
 
 	## String to use for empty fields.

scripts/base/frameworks/input/readers/benchmark.bro

@@ -1,23 +1,23 @@
-##! Interface for the ascii input reader.
+##! Interface for the benchmark input reader.
 
 module InputBenchmark;
 
 export {
-	## multiplication factor for each second
+	## Multiplication factor for each second.
 	const factor = 1.0 &redef;
 
-	## spread factor between lines
+	## Spread factor between lines.
 	const spread = 0 &redef;
 
-	## spreading where usleep = 1000000 / autospread * num_lines
+	## Spreading where usleep = 1000000 / autospread * num_lines
 	const autospread = 0.0 &redef;
 
-	## addition factor for each heartbeat
+	## Addition factor for each heartbeat.
 	const addfactor = 0 &redef;
 
-	## stop spreading at x lines per heartbeat
+	## Stop spreading at x lines per heartbeat.
 	const stopspreadat = 0 &redef;
 
-	## 1 -> enable timed spreading
+	## 1 -> enable timed spreading.
 	const timedspread = 0.0 &redef;
 }

scripts/base/frameworks/input/readers/raw.bro

@@ -4,14 +4,14 @@ module InputRaw;
 
 export {
 	## Separator between input records.
-	## Please note that the separator has to be exactly one character long
+	## Please note that the separator has to be exactly one character long.
 	const record_separator = "\n" &redef;
 
 	## Event that is called when a process created by the raw reader exits.
 	##
-	## name: name of the input stream
+	## name: name of the input stream.
-	## source: source of the input stream
+	## source: source of the input stream.
-	## exit_code: exit code of the program, or number of the signal that forced the program to exit
+	## exit_code: exit code of the program, or number of the signal that forced the program to exit.
-	## signal_exit: false when program exitted normally, true when program was forced to exit by a signal
+	## signal_exit: false when program exited normally, true when program was forced to exit by a signal.
 	global process_finished: event(name: string, source:string, exit_code:count, signal_exit:bool);
 }

scripts/base/frameworks/intel/README

@@ -0,0 +1,3 @@
+The intelligence framework provides a way to store and query intelligence
+data (such as IP addresses or strings). Metadata can also be associated
+with the intelligence.

scripts/base/frameworks/intel/cluster.bro

@@ -1,5 +1,5 @@
-##! Cluster transparency support for the intelligence framework.  This is mostly oriented
+##! Cluster transparency support for the intelligence framework.  This is mostly
-##! toward distributing intelligence information across clusters.
+##! oriented toward distributing intelligence information across clusters.
 
 @load base/frameworks/cluster
 @load ./input

scripts/base/frameworks/intel/input.bro

@@ -4,7 +4,7 @@ module Intel;
 
 export {
 	## Intelligence files that will be read off disk.  The files are
-	## reread everytime they are updated so updates much be atomic with
+	## reread every time they are updated so updates must be atomic with
 	## "mv" instead of writing the file in place.
 	const read_files: set[string] = {} &redef;
 }

scripts/base/frameworks/intel/main.bro

@@ -1,6 +1,6 @@
 ##! The intelligence framework provides a way to store and query IP addresses,
 ##! and strings (with a str_type).  Metadata can
-##! also be associated with the intelligence like for making more informed
+##! also be associated with the intelligence, like for making more informed
 ##! decisions about matching and handling of intelligence.
 
 @load base/frameworks/notice
@@ -14,7 +14,7 @@ export {
 	type Type: enum {
 		## An IP address.
 		ADDR,
-		## A complete URL without the prefix "http://".
+		## A complete URL without the prefix ``"http://"``.
 		URL,
 		## Software name.
 		SOFTWARE,
@@ -24,21 +24,22 @@ export {
 		DOMAIN,
 		## A user name.
 		USER_NAME,
-		## File hash which is non-hash type specific.  It's up to the user to query
+		## File hash which is non-hash type specific.  It's up to the
-		## for any relevant hash types.
+		## user to query for any relevant hash types.
 		FILE_HASH,
-		## File names.  Typically with protocols with definite indications
+		## File name.  Typically with protocols with definite
-		## of a file name.
+		## indications of a file name.
 		FILE_NAME,
 		## Certificate SHA-1 hash.
 		CERT_HASH,
 	};
 	
-	## Data about an :bro:type:`Intel::Item`
+	## Data about an :bro:type:`Intel::Item`.
 	type MetaData: record {
-		## An arbitrary string value representing the data source.  Typically,
+		## An arbitrary string value representing the data source.
-		## the convention for this field will be the source name and feed name
+		## Typically, the convention for this field will be the source
-		## separated by a hyphen.  For example: "source1-c&c".
+		## name and feed name separated by a hyphen.
+		## For example: "source1-c&c".
 		source:      string;
 		## A freeform description for the data.
 		desc:        string      &optional;
@@ -81,7 +82,7 @@ export {
 		where:           Where         &log;
 		
 		## If the data was discovered within a connection, the 
-		## connection record should go into get to give context to the data.
+		## connection record should go here to give context to the data.
 		conn:            connection    &optional;
 
 		## If the data was discovered within a file, the file record
@@ -106,10 +107,12 @@ export {
 		## this is the uid for the file.
 		fuid:           string   &log &optional;
 		## A mime type if the intelligence hit is related to a file.  
-		## If the $f field is provided this will be automatically filled out.
+		## If the $f field is provided this will be automatically filled
+		## out.
 		file_mime_type: string   &log &optional;
 		## Frequently files can be "described" to give a bit more context.
-		## If the $f field is provided this field will be automatically filled out.
+		## If the $f field is provided this field will be automatically
+		## filled out.
 		file_desc:      string   &log &optional;
 
 		## Where the data was seen.
@@ -125,13 +128,13 @@ export {
 	## it against known intelligence for matches.
 	global seen: function(s: Seen);
 
-	## Event to represent a match in the intelligence data from data that was seen.  
+	## Event to represent a match in the intelligence data from data that
-	## On clusters there is no assurance as to where this event will be generated 
+	## was seen.  On clusters there is no assurance as to where this event
-	## so do not assume that arbitrary global state beyond the given data
+	## will be generated so do not assume that arbitrary global state beyond
-	## will be available.
+	## the given data will be available.
 	##
-	## This is the primary mechanism where a user will take actions based on data
+	## This is the primary mechanism where a user will take actions based on
-	## within the intelligence framework.
+	## data within the intelligence framework.
 	global match: event(s: Seen, items: set[Item]);
 
 	global log_intel: event(rec: Info);
@@ -140,7 +143,7 @@ export {
 # Internal handler for matches with no metadata available.
 global match_no_items: event(s: Seen);
 
-# Internal events for cluster data distribution
+# Internal events for cluster data distribution.
 global new_item: event(item: Item);
 global updated_item: event(item: Item);
 

scripts/base/frameworks/logging/README

@@ -0,0 +1 @@
+The logging framework provides a flexible key-value based logging interface.

scripts/base/frameworks/logging/main.bro

@@ -1,6 +1,6 @@
 ##! The Bro logging interface.
 ##!
-##! See :doc:`/frameworks/logging` for a introduction to Bro's
+##! See :doc:`/frameworks/logging` for an introduction to Bro's
 ##! logging framework.
 
 module Log;
@@ -27,7 +27,7 @@ export {
 	const set_separator = "," &redef;
 
 	## String to use for empty fields. This should be different from
-        ## *unset_field* to make the output non-ambigious. 
+        ## *unset_field* to make the output unambiguous. 
 	## Can be overwritten by individual writers.
 	const empty_field = "(empty)" &redef;
 
@@ -41,8 +41,8 @@ export {
 		columns: any;
 
 		## Event that will be raised once for each log entry.
-		## The event receives a single same parameter, an instance of type
+		## The event receives a single same parameter, an instance of
-		## ``columns``.
+		## type ``columns``.
 		ev: any &optional;
 	};
 
@@ -114,7 +114,7 @@ export {
 		##
 		## The specific interpretation of the string is up to
 		## the used writer, and may for example be the destination
-		## file name. Generally, filenames are expected to given
+		## file name. Generally, filenames are expected to be given
 		## without any extensions; writers will add appropiate
 		## extensions automatically.
 		##
@@ -126,34 +126,36 @@ export {
 		path: string &optional;
 
 		## A function returning the output path for recording entries
-		## matching this filter. This is similar to ``path`` yet allows
+		## matching this filter. This is similar to *path* yet allows
 		## to compute the string dynamically. It is ok to return
 		## different strings for separate calls, but be careful: it's
 		## easy to flood the disk by returning a new string for each
-		## connection ...
+		## connection.
 		##
 		## id: The ID associated with the log stream.
 		##
 		## path: A suggested path value, which may be either the filter's
-		##       ``path`` if defined, else a previous result from the function.
+		##       ``path`` if defined, else a previous result from the
-		##       If no ``path`` is defined for the filter, then the first call
+		##       function.  If no ``path`` is defined for the filter,
-		##       to the function will contain an empty string.
+		##       then the first call to the function will contain an
+		##       empty string.
 		##
 		## rec: An instance of the streams's ``columns`` type with its
 		##      fields set to the values to be logged.
 		##
-		## Returns: The path to be used for the filter, which will be subject
+		## Returns: The path to be used for the filter, which will be
-		##          to the same automatic correction rules as the *path*
+		##          subject to the same automatic correction rules as
-		##          field of :bro:type:`Log::Filter` in the case of conflicts
+		##          the *path* field of :bro:type:`Log::Filter` in the
-		##          with other filters trying to use the same writer/path pair.
+		##          case of conflicts with other filters trying to use
+		##          the same writer/path pair.
 		path_func: function(id: ID, path: string, rec: any): string &optional;
 
 		## Subset of column names to record. If not given, all
 		## columns are recorded.
 		include: set[string] &optional;
 
-		## Subset of column names to exclude from recording. If not given,
+		## Subset of column names to exclude from recording. If not
-		## all columns are recorded.
+		## given, all columns are recorded.
 		exclude: set[string] &optional;
 
 		## If true, entries are recorded locally.
@@ -229,7 +231,7 @@ export {
 	##
 	## filter: A record describing the desired logging parameters.
 	##
-	## Returns: True if the filter was sucessfully added, false if
+	## Returns: True if the filter was successfully added, false if
 	##          the filter was not added or the *filter* argument was not
 	##          the correct type.
 	##
@@ -277,7 +279,7 @@ export {
 	##
 	## Returns: True if the stream was found and no error occurred in writing
 	##          to it or if the stream was disabled and nothing was written.
-	##          False if the stream was was not found, or the *columns*
+	##          False if the stream was not found, or the *columns*
 	##          argument did not match what the stream was initially defined
 	##          to handle, or one of the stream's filters has an invalid
 	##          ``path_func``.
@@ -286,8 +288,8 @@ export {
 	global write: function(id: ID, columns: any) : bool;
 
 	## Sets the buffering status for all the writers of a given logging stream.
-	## A given writer implementation may or may not support buffering and if it
+	## A given writer implementation may or may not support buffering and if
-	## doesn't then toggling buffering with this function has no effect.
+	## it doesn't then toggling buffering with this function has no effect.
 	##
 	## id: The ID associated with a logging stream for which to
 	##     enable/disable buffering.
@@ -347,7 +349,7 @@ export {
 	##
 	## npath: The new path of the file (after already being rotated/processed
 	##        by writer-specific postprocessor as defined in
-	##        :bro:id:`Log::default_rotation_postprocessors`.
+	##        :bro:id:`Log::default_rotation_postprocessors`).
 	##
 	## Returns: True when :bro:id:`Log::default_rotation_postprocessor_cmd`
 	##          is empty or the system command given by it has been invoked

scripts/base/frameworks/logging/postprocessors/scp.bro

@@ -16,9 +16,9 @@
 module Log;
 
 export {
-	## Secure-copies the rotated-log to all the remote hosts
+	## Secure-copies the rotated log to all the remote hosts
 	## defined in :bro:id:`Log::scp_destinations` and then deletes
-	## the local copy of the rotated-log.  It's not active when
+	## the local copy of the rotated log.  It's not active when
 	## reading from trace files.
 	##
 	## info: A record holding meta-information about the log file to be
@@ -42,9 +42,9 @@ export {
 	};
 
 	## A table indexed by a particular log writer and filter path, that yields
-	## a set remote destinations.  The :bro:id:`Log::scp_postprocessor`
+	## a set of remote destinations.  The :bro:id:`Log::scp_postprocessor`
 	## function queries this table upon log rotation and performs a secure
-	## copy of the rotated-log to each destination in the set.  This
+	## copy of the rotated log to each destination in the set.  This
 	## table can be modified at run-time.
 	global scp_destinations: table[Writer, string] of set[SCPDestination];
 

scripts/base/frameworks/logging/postprocessors/sftp.bro

@@ -16,9 +16,9 @@
 module Log;
 
 export {
-	## Securely transfers the rotated-log to all the remote hosts
+	## Securely transfers the rotated log to all the remote hosts
 	## defined in :bro:id:`Log::sftp_destinations` and then deletes
-	## the local copy of the rotated-log.  It's not active when
+	## the local copy of the rotated log.  It's not active when
 	## reading from trace files.
 	##
 	## info: A record holding meta-information about the log file to be
@@ -42,9 +42,9 @@ export {
 	};
 
 	## A table indexed by a particular log writer and filter path, that yields
-	## a set remote destinations.  The :bro:id:`Log::sftp_postprocessor`
+	## a set of remote destinations.  The :bro:id:`Log::sftp_postprocessor`
 	## function queries this table upon log rotation and performs a secure
-	## transfer of the rotated-log to each destination in the set.  This
+	## transfer of the rotated log to each destination in the set.  This
 	## table can be modified at run-time.
 	global sftp_destinations: table[Writer, string] of set[SFTPDestination];
 

scripts/base/frameworks/logging/writers/ascii.bro

@@ -2,10 +2,10 @@
 ##! to tweak the output format of ASCII logs.
 ##!
 ##! The ASCII writer supports currently one writer-specific filter option via
-##! ``config``: setting ``tsv`` to the string ``T`` turns the output into into
+##! ``config``: setting ``tsv`` to the string ``T`` turns the output into
-##! "tab-separated-value" mode where only a single header row with the column names
+##! "tab-separated-value" mode where only a single header row with the column
-##! is printed out as meta information, with no "# fields" prepended; no other meta
+##! names is printed out as meta information, with no "# fields" prepended; no
-##! data gets included in that mode.   
+##! other meta data gets included in that mode.   
 ##! 
 ##! Example filter using this::
 ##! 
@@ -19,9 +19,9 @@ export {
 	## into files. This is primarily for debugging purposes.
 	const output_to_stdout = F &redef;
 
-	## If true, include lines with log meta information such as column names with
+	## If true, include lines with log meta information such as column names
-	## types, the values of ASCII logging options that in use, and the time when the
+	## with types, the values of ASCII logging options that are in use, and
-	## file was opened and closes (the latter at the end). 
+	## the time when the file was opened and closed (the latter at the end).
 	const include_meta = T &redef;
 
 	## Prefix for lines with meta information.
@@ -34,7 +34,7 @@ export {
 	const set_separator = Log::set_separator &redef;
 
 	## String to use for empty fields. This should be different from
-        ## *unset_field* to make the output non-ambigious. 
+        ## *unset_field* to make the output unambiguous. 
 	const empty_field = Log::empty_field &redef;
 
 	## String to use for an unset &optional field.

scripts/base/frameworks/logging/writers/dataseries.bro

@@ -6,16 +6,16 @@ export {
 	## Compression to use with the DS output file.  Options are:
 	##
 	## 'none' -- No compression.
-	## 'lzf'  -- LZF compression.   Very quick, but leads to larger output files.
+	## 'lzf'  -- LZF compression (very quick, but leads to larger output files).
-	## 'lzo'  -- LZO compression.   Very fast decompression times.
+	## 'lzo'  -- LZO compression (very fast decompression times).
-	## 'gz'   -- GZIP compression.  Slower than LZF, but also produces smaller output.
+	## 'gz'   -- GZIP compression (slower than LZF, but also produces smaller output).
-	## 'bz2'  -- BZIP2 compression. Slower than GZIP, but also produces smaller output.
+	## 'bz2'  -- BZIP2 compression (slower than GZIP, but also produces smaller output).
 	const compression = "gz" &redef;
 
 	## The extent buffer size.
-	## Larger values here lead to better compression and more efficient writes, but
+	## Larger values here lead to better compression and more efficient writes,
-	## also increase the lag between the time events are received and the time they
+	## but also increase the lag between the time events are received and
-	## are actually written to disk.
+	## the time they are actually written to disk.
 	const extent_size = 65536 &redef;
 
 	## Should we dump the XML schema we use for this DS file to disk?
@@ -43,8 +43,8 @@ export {
 }
 
 # Default function to postprocess a rotated DataSeries log file. It moves the
-# rotated file to a new name that includes a timestamp with the opening time, and
+# rotated file to a new name that includes a timestamp with the opening time,
-# then runs the writer's default postprocessor command on it.
+# and then runs the writer's default postprocessor command on it.
 function default_rotation_postprocessor_func(info: Log::RotationInfo) : bool
 	{
 	# Move file to name including both opening and closing time.

scripts/base/frameworks/logging/writers/elasticsearch.bro

@@ -10,16 +10,16 @@
 module LogElasticSearch;
 
 export {
-	## Name of the ES cluster
+	## Name of the ES cluster.
 	const cluster_name = "elasticsearch" &redef;
 
-	## ES Server
+	## ES server.
 	const server_host = "127.0.0.1" &redef;
 
-	## ES Port
+	## ES port.
 	const server_port = 9200 &redef;
 
-	## Name of the ES index
+	## Name of the ES index.
 	const index_prefix = "bro" &redef;
 
 	## The ES type prefix comes before the name of the related log.
@@ -27,9 +27,9 @@ export {
 	const type_prefix = "" &redef;
 
 	## The time before an ElasticSearch transfer will timeout. Note that
-	## the fractional part of the timeout will be ignored. In particular, time
+	## the fractional part of the timeout will be ignored. In particular,
-	## specifications less than a second result in a timeout value of 0, which
+	## time specifications less than a second result in a timeout value of
-	## means "no timeout."
+	## 0, which means "no timeout."
 	const transfer_timeout = 2secs;
 
 	## The batch size is the number of messages that will be queued up before

scripts/base/frameworks/logging/writers/none.bro

@@ -1,4 +1,4 @@
-##! Interface for the None log writer. Thiis writer is mainly for debugging.
+##! Interface for the None log writer. This writer is mainly for debugging.
 
 module LogNone;
 

scripts/base/frameworks/logging/writers/sqlite.bro

@@ -11,7 +11,7 @@ export {
 	const unset_field = Log::unset_field &redef;
 
 	## String to use for empty fields. This should be different from
-        ## *unset_field* to make the output non-ambigious.
+        ## *unset_field* to make the output unambiguous.
 	const empty_field = Log::empty_field &redef;
 }
 

scripts/base/frameworks/packet-filter/README

@@ -0,0 +1 @@
+The packet filter framework supports how Bro sets its BPF capture filter.

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

@@ -1,4 +1,4 @@
-##! This script supports how Bro sets it's BPF capture filter.  By default
+##! This script supports how Bro sets its BPF capture filter.  By default
 ##! Bro sets a capture filter that allows all traffic.  If a filter
 ##! is set on the command line, that filter takes precedence over the default
 ##! open filter and all filters defined in Bro scripts with the
@@ -19,7 +19,7 @@ export {
 		## This notice is generated if a packet filter cannot be compiled.
 		Compile_Failure,
 
-		## Generated if a packet filter is fails to install.
+		## Generated if a packet filter fails to install.
 		Install_Failure,
 
 		## Generated when a notice takes too long to compile.
@@ -33,8 +33,8 @@ export {
 		ts:     time   &log;
 
 		## This is a string representation of the node that applied this
-		## packet filter.  It's mostly useful in the context of dynamically
+		## packet filter.  It's mostly useful in the context of
-		## changing filters on clusters.
+		## dynamically changing filters on clusters.
 		node:   string &log &optional;
 
 		## The packet filter that is being set.
@@ -48,27 +48,28 @@ export {
 	};
 
 	## The BPF filter that is used by default to define what traffic should
-	## be captured.  Filters defined in :bro:id:`restrict_filters` will still
+	## be captured.  Filters defined in :bro:id:`restrict_filters` will
-	## be applied to reduce the captured traffic.
+	## still be applied to reduce the captured traffic.
 	const default_capture_filter = "ip or not ip" &redef;
 
-	## Filter string which is unconditionally or'ed to the beginning of every
+	## Filter string which is unconditionally or'ed to the beginning of
-	## dynamically built filter.
+	## every dynamically built filter.
 	const unrestricted_filter = "" &redef;
 
-	## Filter string which is unconditionally and'ed to the beginning of every
+	## Filter string which is unconditionally and'ed to the beginning of
-	## dynamically built filter.  This is mostly used when a custom filter is being
+	## every dynamically built filter.  This is mostly used when a custom
-	## used but MPLS or VLAN tags are on the traffic.
+	## filter is being used but MPLS or VLAN tags are on the traffic.
 	const restricted_filter = "" &redef;
 
 	## The maximum amount of time that you'd like to allow for BPF filters to compile.
 	## If this time is exceeded, compensation measures may be taken by the framework
-	## to reduce the filter size.  This threshold being crossed also results in
+	## to reduce the filter size.  This threshold being crossed also results
-	## the :bro:see:`PacketFilter::Too_Long_To_Compile_Filter` notice.
+	## in the :bro:see:`PacketFilter::Too_Long_To_Compile_Filter` notice.
 	const max_filter_compile_time = 100msec &redef;
 
-	## Install a BPF filter to exclude some traffic.  The filter should positively
+	## Install a BPF filter to exclude some traffic.  The filter should
-	## match what is to be excluded, it will be wrapped in a "not".
+	## positively match what is to be excluded, it will be wrapped in
+	## a "not".
 	##
 	## filter_id: An arbitrary string that can be used to identify
 	##            the filter.
@@ -79,9 +80,9 @@ export {
 	##          installed or not.
 	global exclude: function(filter_id: string, filter: string): bool;
 
-	## Install a temporary filter to traffic which should not be passed through
+	## Install a temporary filter to traffic which should not be passed
-	## the BPF filter.  The filter should match the traffic you don't want
+	## through the BPF filter.  The filter should match the traffic you
-	## to see (it will be wrapped in a "not" condition).
+	## don't want to see (it will be wrapped in a "not" condition).
 	##
 	## filter_id: An arbitrary string that can be used to identify
 	##            the filter.
@@ -125,7 +126,7 @@ global dynamic_restrict_filters: table[string] of string = {};
 # install the filter.
 global currently_building = F;
 
-# Internal tracking for if the the filter being built has possibly been changed.
+# Internal tracking for if the filter being built has possibly been changed.
 global filter_changed = F;
 
 global filter_plugins: set[FilterPlugin] = {};

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

@@ -13,7 +13,7 @@ export {
 	##
 	## num_parts: The number of parts the traffic should be split into.
 	##
-	## this_part: The part of the traffic this filter will accept.  0-based.
+	## this_part: The part of the traffic this filter will accept (0-based).
 	global sampling_filter: function(num_parts: count, this_part: count): string;
 
 	## Combines two valid BPF filter strings with a string based operator

scripts/base/frameworks/reporter/main.bro

@@ -7,7 +7,7 @@
 ##! :bro:see:`Reporter::errors_to_stderr`.
 ##!
 ##! Note that this framework deals with the handling of internally generated
-##! reporter messages, for the interface in to actually creating interface
+##! reporter messages, for the interface
 ##! into actually creating reporter messages from the scripting layer, use
 ##! the built-in functions in :doc:`/scripts/base/bif/reporter.bif`.
 

scripts/base/frameworks/software/README

@@ -0,0 +1,4 @@
+The software framework provides infrastructure for maintaining a table
+of software versions seen on the network. The version parsing itself
+is carried out by external protocol-specific scripts that feed into
+this framework.

scripts/base/frameworks/software/main.bro

@@ -1,5 +1,5 @@
 ##! This script provides the framework for software version detection and
-##! parsing but doesn't actually do any detection on it's own.  It relys on
+##! parsing but doesn't actually do any detection on it's own.  It relies on
 ##! other protocol specific scripts to parse out software from the protocols
 ##! that they analyze.  The entry point for providing new software detections
 ##! to this framework is through the :bro:id:`Software::found` function.
@@ -23,15 +23,15 @@ export {
 	
 	## A structure to represent the numeric version of software.
 	type Version: record {
-		## Major version number
+		## Major version number.
 		major:  count  &optional;
-		## Minor version number
+		## Minor version number.
 		minor:  count  &optional;
-		## Minor subversion number
+		## Minor subversion number.
 		minor2: count  &optional;
-		## Minor updates number
+		## Minor updates number.
 		minor3: count  &optional;
-		## Additional version string (e.g. "beta42")
+		## Additional version string (e.g. "beta42").
 		addl:   string &optional;
 	} &log;
 	
@@ -41,7 +41,8 @@ export {
 		ts:               time &log &optional;
 		## The IP address detected running the software.
 		host:             addr &log;
-		## The Port on which the software is running. Only sensible for server software.
+		## The port on which the software is running. Only sensible for
+		## server software.
 		host_p:           port &log &optional;
 		## The type of software detected (e.g. :bro:enum:`HTTP::SERVER`).
 		software_type:    Type &log &default=UNKNOWN;
@@ -49,9 +50,9 @@ export {
 		name:             string &log &optional;
 		## Version of the software.
 		version:          Version &log &optional;
-		## The full unparsed version string found because the version parsing 
+		## The full unparsed version string found because the version
-		## doesn't always work reliably in all cases and this acts as a 
+		## parsing doesn't always work reliably in all cases and this
-		## fallback in the logs.
+		## acts as a fallback in the logs.
 		unparsed_version: string &log &optional;
 		
 		## This can indicate that this software being detected should
@@ -59,13 +60,13 @@ export {
 		## default, only software that is "interesting" due to a change
 		## in version or it being currently unknown is sent to the
 		## logging framework.  This can be set to T to force the record
-		## to be sent to the logging framework if some amount of this tracking
+		## to be sent to the logging framework if some amount of this
-		## needs to happen in a specific way to the software.
+		## tracking needs to happen in a specific way to the software.
 		force_log:        bool &default=F;
 	};
 	
 	## Hosts whose software should be detected and tracked.
-	## Choices are: LOCAL_HOSTS, REMOTE_HOSTS, ALL_HOSTS, NO_HOSTS
+	## Choices are: LOCAL_HOSTS, REMOTE_HOSTS, ALL_HOSTS, NO_HOSTS.
 	const asset_tracking = LOCAL_HOSTS &redef;
 	
 	## Other scripts should call this function when they detect software.
@@ -79,14 +80,14 @@ export {
 	## Compare two version records.
 	## 
 	## Returns:  -1 for v1 < v2, 0 for v1 == v2, 1 for v1 > v2.
-	##           If the numerical version numbers match, the addl string
+	##           If the numerical version numbers match, the *addl* string
 	##           is compared lexicographically.
 	global cmp_versions: function(v1: Version, v2: Version): int;
 	
 	## Type to represent a collection of :bro:type:`Software::Info` records.
 	## It's indexed with the name of a piece of software such as "Firefox" 
-	## and it yields a :bro:type:`Software::Info` record with more information
+	## and it yields a :bro:type:`Software::Info` record with more
-	## about the  software.
+	## information about the software.
 	type SoftwareSet: table[string] of Info;
 	
 	## The set of software associated with an address.  Data expires from

scripts/base/frameworks/sumstats/README

@@ -0,0 +1,2 @@
+The summary statistics framework provides a way to summarize large streams
+of data into simple reduced measurements.

scripts/base/frameworks/sumstats/cluster.bro

@@ -1,6 +1,6 @@
 ##! This implements transparent cluster support for the SumStats framework.
 ##! Do not load this file directly.  It's only meant to be loaded automatically
-##! and will be depending on if the cluster framework has been enabled.
+##! and will be if the cluster framework has been enabled.
 ##! The goal of this script is to make sumstats calculation completely and
 ##! transparently automated when running on a cluster.
 
@@ -10,31 +10,32 @@
 module SumStats;
 
 export {
-	## The percent of the full threshold value that needs to be met on a single worker
+	## The percent of the full threshold value that needs to be met on a
-	## for that worker to send the value to its manager in order for it to request a
+	## single worker for that worker to send the value to its manager in
-	## global view for that value.  There is no requirement that the manager requests
+	## order for it to request a global view for that value.  There is no
-	## a global view for the key since it may opt not to if it requested a global view
+	## requirement that the manager requests a global view for the key since
-	## for the key recently.
+	## it may opt not to if it requested a global view for the key recently.
 	const cluster_request_global_view_percent = 0.2 &redef;
 
-	## This is to deal with intermediate update overload.  A manager will only allow
+	## This is to deal with intermediate update overload.  A manager will
-	## this many intermediate update requests to the workers to be inflight at any
+	## only allow this many intermediate update requests to the workers to
-	## given time.  Requested intermediate updates are currently thrown out and not
+	## be inflight at any given time.  Requested intermediate updates are
-	## performed.  In practice this should hopefully have a minimal effect.
+	## currently thrown out and not performed.  In practice this should
+	## hopefully have a minimal effect.
 	const max_outstanding_global_views = 10 &redef;
 
-	## Event sent by the manager in a cluster to initiate the collection of values for
+	## Event sent by the manager in a cluster to initiate the collection of
-	## a sumstat.
+	## values for a sumstat.
 	global cluster_ss_request: event(uid: string, ss_name: string, cleanup: bool);
 
-	## Event sent by nodes that are collecting sumstats after receiving a request for
+	## Event sent by nodes that are collecting sumstats after receiving a
-	## the sumstat from the manager.
+	## request for the sumstat from the manager.
 	#global cluster_ss_response: event(uid: string, ss_name: string, data: ResultTable, done: bool, cleanup: bool);
 
-	## This event is sent by the manager in a cluster to initiate the collection of
+	## This event is sent by the manager in a cluster to initiate the
-	## a single key value from a sumstat.  It's typically used to get intermediate
+	## collection of a single key value from a sumstat.  It's typically used
-	## updates before the break interval triggers to speed detection of a value
+	## to get intermediate updates before the break interval triggers to
-	## crossing a threshold.
+	## speed detection of a value crossing a threshold.
 	global cluster_get_result: event(uid: string, ss_name: string, key: Key, cleanup: bool);
 
 	## This event is sent by nodes in response to a
@@ -43,7 +44,7 @@ export {
 
 	## This is sent by workers to indicate that they crossed the percent
 	## of the current threshold by the percentage defined globally in
-	## :bro:id:`SumStats::cluster_request_global_view_percent`
+	## :bro:id:`SumStats::cluster_request_global_view_percent`.
 	global cluster_key_intermediate_response: event(ss_name: string, key: SumStats::Key);
 
 	## This event is scheduled internally on workers to send result chunks.

scripts/base/frameworks/sumstats/main.bro

@@ -51,8 +51,8 @@ export {
 		## would like to accept the data being inserted.
 		pred:           function(key: SumStats::Key, obs: SumStats::Observation): bool &optional;
 
-		## A function to normalize the key.  This can be used to aggregate or
+		## A function to normalize the key.  This can be used to
-		## normalize the entire key.
+		## aggregate or normalize the entire key.
 		normalize_key:  function(key: SumStats::Key): Key &optional;
 	};
 
@@ -91,28 +91,28 @@ export {
 		name:               string;
 		
 		## The interval at which this filter should be "broken"
-		## and the '$epoch_result' callback called.  The
+		## and the *epoch_result* callback called.  The
 		## results are also reset at this time so any threshold
 		## based detection needs to be set to a
 		## value that should be expected to happen within
 		## this epoch.
 		epoch:              interval;
 
-		## The reducers for the SumStat
+		## The reducers for the SumStat.
 		reducers:           set[Reducer];
 
 		## Provide a function to calculate a value from the
 		## :bro:see:`SumStats::Result` structure which will be used
 		## for thresholding.
-		## This is required if a $threshold value is given.
+		## This is required if a *threshold* value is given.
 		threshold_val:      function(key: SumStats::Key, result: SumStats::Result): double &optional;
 
 		## The threshold value for calling the
-		## $threshold_crossed callback.
+		## *threshold_crossed* callback.
 		threshold:          double            &optional;
 
 		## A series of thresholds for calling the
-		## $threshold_crossed callback.
+		## *threshold_crossed* callback.
 		threshold_series:   vector of double  &optional;
 
 		## A callback that is called when a threshold is crossed.
@@ -124,7 +124,7 @@ export {
 		epoch_result:       function(ts: time, key: SumStats::Key, result: SumStats::Result) &optional;
 	
 		## A callback that will be called when a single collection 
-		## interval is completed.  The ts value will be the time of 
+		## interval is completed.  The *ts* value will be the time of 
 		## when the collection started.
 		epoch_finished:     function(ts:time) &optional;
 	};

scripts/base/frameworks/sumstats/plugins/last.bro

@@ -5,12 +5,12 @@ module SumStats;
 
 export {
 	redef enum Calculation += {
-		## Keep last X observations in a queue
+		## Keep last X observations in a queue.
 		LAST
 	};
 
 	redef record Reducer += {
-		## number of elements to keep.
+		## Number of elements to keep.
 		num_last_elements: count &default=0;
 	};
 

scripts/base/frameworks/sumstats/plugins/sample.bro

@@ -4,7 +4,8 @@ module SumStats;
 
 export {
 	redef enum Calculation += {
-		## Get uniquely distributed random samples from the observation stream.
+		## Get uniquely distributed random samples from the observation
+		## stream.
 		SAMPLE
 	};
 
@@ -24,8 +25,8 @@ export {
 
 redef record ResultVal += {
 	# Internal use only.  This is not meant to be publically available
-	# and just a copy of num_samples from the Reducer. Needed for availability
+	# and just a copy of num_samples from the Reducer. Needed for
-	# in the compose hook.
+	# availability in the compose hook.
 	num_samples: count &default=0;
 };
 

scripts/base/frameworks/sumstats/plugins/topk.bro

@@ -4,7 +4,7 @@ module SumStats;
 
 export {
 	redef record Reducer += {
-		## number of elements to keep in the top-k list
+		## Number of elements to keep in the top-k list.
 		topk_size: count &default=500;
 	};
 

scripts/base/frameworks/sumstats/plugins/unique.bro

@@ -28,7 +28,7 @@ redef record ResultVal += {
 
 	# Internal use only.  This is not meant to be publically available
 	# because we don't want to trust that we can inspect the values
-	# since we will like move to a probalistic data structure in the future.
+	# since we will likely move to a probabilistic data structure in the future.
 	# TODO: in the future this will optionally be a hyperloglog structure
 	unique_vals: set[Observation] &optional;
 };

scripts/base/frameworks/tunnels/README

@@ -0,0 +1,2 @@
+The tunnels framework handles the tracking/logging of tunnels (e.g. Teredo,
+AYIYA, or IP-in-IP such as 6to4 where "IP" is either IPv4 or IPv6).

scripts/base/frameworks/tunnels/main.bro

@@ -29,8 +29,8 @@ export {
 		## The unique identifier for the tunnel, which may correspond
 		## to a :bro:type:`connection`'s *uid* field for non-IP-in-IP tunnels.
 		## This is optional because there could be numerous connections
-		## for payload proxies like SOCKS but we should treat it as a single
+		## for payload proxies like SOCKS but we should treat it as a
-		## tunnel.
+		## single tunnel.
 		uid:         string       &log &optional;
 		## The tunnel "connection" 4-tuple of endpoint addresses/ports.
 		## For an IP tunnel, the ports will be 0.
@@ -76,8 +76,8 @@ export {
 	## connections before it is considered inactive/expired.
 	const expiration_interval = 1hrs &redef;
 
-	## Currently active tunnels.  That is, tunnels for which new, encapsulated
+	## Currently active tunnels.  That is, tunnels for which new,
-	## connections have been seen in the interval indicated by
+	## encapsulated connections have been seen in the interval indicated by
 	## :bro:see:`Tunnel::expiration_interval`.
 	global active: table[conn_id] of Info = table() &read_expire=expiration_interval &expire_func=expire;
 }

scripts/base/init-bare.bro

@@ -888,13 +888,13 @@ const tcp_excessive_data_without_further_acks = 10 * 1024 * 1024 &redef;
 ## For services without an a handler, these sets define originator-side ports that
 ## still trigger reassembly.
 ##
-## .. :bro:see:: tcp_reassembler_ports_resp
+## .. bro:see:: tcp_reassembler_ports_resp
 const tcp_reassembler_ports_orig: set[port] = {} &redef;
 
 ## For services without an a handler, these sets define responder-side ports that
 ## still trigger reassembly.
 ##
-## .. :bro:see:: tcp_reassembler_ports_orig
+## .. bro:see:: tcp_reassembler_ports_orig
 const tcp_reassembler_ports_resp: set[port] = {} &redef;
 
 ## Defines destination TCP ports for which the contents of the originator stream
@@ -987,7 +987,7 @@ const table_incremental_step = 5000 &redef;
 ## When expiring table entries, wait this amount of time before checking the next
 ## chunk of entries.
 ##
-## .. :bro:see:: table_expire_interval table_incremental_step
+## .. bro:see:: table_expire_interval table_incremental_step
 const table_expire_delay = 0.01 secs &redef;
 
 ## Time to wait before timing out a DNS request.
@@ -1676,7 +1676,7 @@ global secondary_filters: table[string] of event(filter: string, pkt: pkt_hdr)
 
 ## Maximum length of payload passed to discarder functions.
 ##
-## .. :bro:see:: discarder_check_tcp discarder_check_udp discarder_check_icmp
+## .. bro:see:: discarder_check_tcp discarder_check_udp discarder_check_icmp
 ##    discarder_check_ip
 global discarder_maxlen = 128 &redef;
 
@@ -1689,7 +1689,7 @@ global discarder_maxlen = 128 &redef;
 ##
 ## Returns: True if the packet should not be analyzed any further.
 ##
-## .. :bro:see:: discarder_check_tcp discarder_check_udp discarder_check_icmp
+## .. bro:see:: discarder_check_tcp discarder_check_udp discarder_check_icmp
 ##    discarder_maxlen
 ##
 ## .. note:: This is very low-level functionality and potentially expensive.
@@ -1707,7 +1707,7 @@ global discarder_check_ip: function(p: pkt_hdr): bool;
 ##
 ## Returns: True if the packet should not be analyzed any further.
 ##
-## .. :bro:see:: discarder_check_ip discarder_check_udp discarder_check_icmp
+## .. bro:see:: discarder_check_ip discarder_check_udp discarder_check_icmp
 ##    discarder_maxlen
 ##
 ## .. note:: This is very low-level functionality and potentially expensive.
@@ -1725,7 +1725,7 @@ global discarder_check_tcp: function(p: pkt_hdr, d: string): bool;
 ##
 ## Returns: True if the packet should not be analyzed any further.
 ##
-## .. :bro:see:: discarder_check_ip discarder_check_tcp discarder_check_icmp
+## .. bro:see:: discarder_check_ip discarder_check_tcp discarder_check_icmp
 ##    discarder_maxlen
 ##
 ## .. note:: This is very low-level functionality and potentially expensive.
@@ -1741,7 +1741,7 @@ global discarder_check_udp: function(p: pkt_hdr, d: string): bool;
 ##
 ## Returns: True if the packet should not be analyzed any further.
 ##
-## .. :bro:see:: discarder_check_ip discarder_check_tcp discarder_check_udp
+## .. bro:see:: discarder_check_ip discarder_check_tcp discarder_check_udp
 ##    discarder_maxlen
 ##
 ## .. note:: This is very low-level functionality and potentially expensive.
@@ -1935,11 +1935,11 @@ export {
 	## .. .. bro:see:: return_data_max return_data_first_only
 	const return_data = F &redef;
 
-	## If bro:id:`NFS3::return_data` is true, how much data should be returned at
+	## If :bro:id:`NFS3::return_data` is true, how much data should be returned at
 	## most.
 	const return_data_max = 512 &redef;
 
-	## If bro:id:`NFS3::return_data` is true, whether to *only* return data if the read
+	## If :bro:id:`NFS3::return_data` is true, whether to *only* return data if the read
 	## or write offset is 0, i.e., only return data for the beginning of the file.
 	const return_data_first_only = T &redef;
 
@@ -2827,7 +2827,7 @@ const report_gaps_for_partial = F &redef;
 ## Flag to prevent Bro from exiting automatically when input is exhausted.
 ## Normally Bro terminates when all packets sources have gone dry
 ## and  communication isn't enabled. If this flag is set, Bro's main loop will
-## instead keep idleing until :bro:see::`terminate` is explicitly called.
+## instead keep idleing until :bro:see:`terminate` is explicitly called.
 ##
 ## This is mainly for testing purposes when termination behaviour needs to be
 ## controlled for reproducing results.

scripts/base/protocols/conn/README

@@ -0,0 +1 @@
+Support for connection (TCP, UDP, or ICMP) analysis.

scripts/base/protocols/conn/contents.bro

@@ -16,12 +16,12 @@
 module Conn;
 
 export {
-	## The prefix given to files containing extracted connections as they are
+	## The prefix given to files containing extracted connections as they
-	## opened on disk.
+	## are opened on disk.
 	const extraction_prefix = "contents" &redef;
 	
-	## If this variable is set to ``T``, then all contents of all connections
+	## If this variable is set to ``T``, then all contents of all
-	## will be  extracted.
+	## connections will be extracted.
 	const default_extract = F &redef;
 }
 

scripts/base/protocols/conn/main.bro

@@ -1,7 +1,7 @@
 ##! This script manages the tracking/logging of general information regarding
 ##! TCP, UDP, and ICMP traffic.  For UDP and ICMP, "connections" are to
 ##! be interpreted using flow semantics (sequence of packets from a source
-##! host/post to a destination host/port).  Further, ICMP "ports" are to
+##! host/port to a destination host/port).  Further, ICMP "ports" are to
 ##! be interpreted as the source port meaning the ICMP message type and
 ##! the destination port being the ICMP message code.
 
@@ -23,7 +23,7 @@ export {
 		id:           conn_id         &log;
 		## The transport layer protocol of the connection.
 		proto:        transport_proto &log;
-		## An identification of an application protocol being sent over the
+		## An identification of an application protocol being sent over
 		## the connection.
 		service:      string          &log &optional;
 		## How long the connection lasted.  For 3-way or 4-way connection
@@ -31,9 +31,10 @@ export {
 		duration:     interval        &log &optional;
 		## The number of payload bytes the originator sent. For TCP
 		## this is taken from sequence numbers and might be inaccurate
-		## (e.g., due to large connections)
+		## (e.g., due to large connections).
 		orig_bytes:   count           &log &optional;
-		## The number of payload bytes the responder sent. See ``orig_bytes``.
+		## The number of payload bytes the responder sent. See
+		## *orig_bytes*.
 		resp_bytes:   count           &log &optional;
 
 		## ==========   ===============================================
@@ -55,20 +56,20 @@ export {
 		## ==========   ===============================================
 		conn_state:   string          &log &optional;
 
-		## If the connection is originated locally, this value will be T.  If
+		## If the connection is originated locally, this value will be T.
-		## it was originated remotely it will be F.  In the case that the
+		## If it was originated remotely it will be F.  In the case that
-		## :bro:id:`Site::local_nets` variable is undefined, this field will
+		## the :bro:id:`Site::local_nets` variable is undefined, this
-		## be left empty at all times.
+		## field will be left empty at all times.
 		local_orig:   bool            &log &optional;
 
-		## Indicates the number of bytes missed in content gaps, which is
+		## Indicates the number of bytes missed in content gaps, which
-		## representative of packet loss.  A value other than zero will
+		## is representative of packet loss.  A value other than zero
-		## normally cause protocol analysis to fail but some analysis may
+		## will normally cause protocol analysis to fail but some
-		## have been completed prior to the packet loss.
+		## analysis may have been completed prior to the packet loss.
 		missed_bytes: count           &log &default=0;
 
-		## Records the state history of connections as a string of letters.
+		## Records the state history of connections as a string of
-		## The meaning of those letters is:
+		## letters.  The meaning of those letters is:
 		##
 		## ======  ====================================================
 		## Letter  Meaning
@@ -83,24 +84,25 @@ export {
 		## i       inconsistent packet (e.g. SYN+RST bits both set)
 		## ======  ====================================================
 		##
-		## If the event comes from the originator, the letter is in upper-case; if it comes
+		## If the event comes from the originator, the letter is in
-		## from the responder, it's in lower-case. Multiple packets of the same type will
+		## upper-case; if it comes from the responder, it's in
-		## only be noted once (e.g. we only record one "d" in each direction, regardless of
+		## lower-case. Multiple packets of the same type will only be
-		## how many data packets were seen.)
+		## noted once (e.g. we only record one "d" in each direction,
+		## regardless of how many data packets were seen.)
 		history:      string          &log &optional;
 		## Number of packets that the originator sent.
-		## Only set if :bro:id:`use_conn_size_analyzer` = T
+		## Only set if :bro:id:`use_conn_size_analyzer` = T.
 		orig_pkts:     count      &log &optional;
-		## Number of IP level bytes that the originator sent (as seen on the wire,
+		## Number of IP level bytes that the originator sent (as seen on
-		## taken from IP total_length header field).
+		## the wire, taken from the IP total_length header field).
-		## Only set if :bro:id:`use_conn_size_analyzer` = T
+		## Only set if :bro:id:`use_conn_size_analyzer` = T.
 		orig_ip_bytes: count      &log &optional;
 		## Number of packets that the responder sent.
-		## Only set if :bro:id:`use_conn_size_analyzer` = T
+		## Only set if :bro:id:`use_conn_size_analyzer` = T.
 		resp_pkts:     count      &log &optional;
-		## Number og IP level bytes that the responder sent (as seen on the wire,
+		## Number of IP level bytes that the responder sent (as seen on
-		## taken from IP total_length header field).
+		## the wire, taken from the IP total_length header field).
-		## Only set if :bro:id:`use_conn_size_analyzer` = T
+		## Only set if :bro:id:`use_conn_size_analyzer` = T.
 		resp_ip_bytes: count      &log &optional;
 		## If this connection was over a tunnel, indicate the
 		## *uid* values for any encapsulating parent connections

scripts/base/protocols/conn/polling.bro

@@ -11,10 +11,11 @@ export {
 	## c: The connection to watch.
 	##
 	## callback: A callback function that takes as arguments the monitored
-	##           *connection*, and counter *cnt* that increments each time the
+	##           *connection*, and counter *cnt* that increments each time
-	##           callback is called.  It returns an interval indicating how long
+	##           the callback is called.  It returns an interval indicating
-	##           in the future to schedule an event which will call the
+	##           how long in the future to schedule an event which will call
-	##           callback.  A negative return interval causes polling to stop.
+	##           the callback.  A negative return interval causes polling
+	##           to stop.
 	##
 	## cnt: The initial value of a counter which gets passed to *callback*.
 	##

scripts/base/protocols/dhcp/README

@@ -0,0 +1 @@
+Support for Dynamic Host Configuration Protocol (DHCP) analysis.

scripts/base/protocols/dhcp/consts.bro

@@ -5,7 +5,7 @@ module DHCP;
 
 export {
 
-	## Types of DHCP messages. See RFC 1533.
+	## Types of DHCP messages. See :rfc:`1533`.
 	const message_types = {
 		[1] = "DHCP_DISCOVER",
 		[2] = "DHCP_OFFER",

scripts/base/protocols/dhcp/main.bro

@@ -3,7 +3,8 @@
 ##! noisy on most networks, and focuses on the end-result: assigned leases.
 ##!
 ##! If you'd like to track known DHCP devices and to log the hostname
-##! supplied by the client, see policy/protocols/dhcp/known-devices.bro
+##! supplied by the client, see
+##! :doc:`/scripts/policy/protocols/dhcp/known-devices-and-hostnames`.
 
 @load ./utils.bro
 
@@ -18,7 +19,7 @@ export {
 		## associated connection is observed.
 		ts:		time		&log;
 		## A unique identifier of the connection over which DHCP is
-		## occuring.
+		## occurring.
 		uid:		string		&log;
 		## The connection's 4-tuple of endpoint addresses/ports.
 		id:		conn_id		&log;
@@ -28,7 +29,7 @@ export {
 		assigned_ip:	addr		&log &optional;
 		## IP address lease interval.
 		lease_time:	interval	&log &optional;
-		## A random number choosen by the client for this transaction.
+		## A random number chosen by the client for this transaction.
 		trans_id:	count		&log;
 	};
 
@@ -37,7 +38,7 @@ export {
 	global log_dhcp: event(rec: Info);
 }
 
-# Add the dhcp info to the connection record
+# Add the dhcp info to the connection record.
 redef record connection += {
 	dhcp: Info &optional;
 };

scripts/base/protocols/dhcp/utils.bro

@@ -3,11 +3,11 @@
 module DHCP;
 
 export {
-	## Reverse the octets of an IPv4 IP.
+	## Reverse the octets of an IPv4 address.
 	##
-	## ip: An :bro:type:`addr` IPv4 address.
+	## ip: An IPv4 address.
 	##
-	## Returns: A reversed addr.
+	## Returns: A reversed IPv4 address.
 	global reverse_ip: function(ip: addr): addr;
 }
 

scripts/base/protocols/dnp3/README

@@ -0,0 +1 @@
+Support for Distributed Network Protocol (DNP3) analysis.

scripts/base/protocols/dnp3/main.bro

@@ -10,7 +10,7 @@ export {
 	type Info: record {
 		## Time of the request.
 		ts:         time           &log;
-		## Unique identifier for the connnection.
+		## Unique identifier for the connection.
 		uid:        string         &log;
 		## Identifier for the connection.
 		id:         conn_id        &log;

scripts/base/protocols/dns/README

@@ -0,0 +1 @@
+Support for Domain Name System (DNS) protocol analysis.

scripts/base/protocols/dns/consts.bro

@@ -8,7 +8,8 @@ export {
 	const EDNS = 41; ##< An OPT RR TYPE value described by EDNS.
 	const ANY = 255; ##< A QTYPE value describing a request for all records.
 
-	## Mapping of DNS query type codes to human readable string representation.
+	## Mapping of DNS query type codes to human readable string
+	## representation.
 	const query_types = {
 		[1] = "A", [2] = "NS", [3] = "MD", [4] = "MF",
 		[5] = "CNAME", [6] = "SOA", [7] = "MB", [8] = "MG",
@@ -64,8 +65,8 @@ export {
 		[32768] = "DNS_SEC_OK", # accepts DNS Sec RRs
 	} &default="?";
 
-	## Possible values of the CLASS field in resource records or QCLASS field
+	## Possible values of the CLASS field in resource records or QCLASS
-	## in query messages.
+	## field in query messages.
 	const classes = {
 		[1]   = "C_INTERNET",
 		[2]   = "C_CSNET",

scripts/base/protocols/dns/main.bro

@@ -22,8 +22,8 @@ export {
 		id:            conn_id            &log;
 		## The transport layer protocol of the connection.
 		proto:         transport_proto    &log;
-		## A 16 bit identifier assigned by the program that generated the
+		## A 16-bit identifier assigned by the program that generated
-		## DNS query.  Also used in responses to match up replies to
+		## the DNS query.  Also used in responses to match up replies to
 		## outstanding queries.
 		trans_id:      count              &log &optional;
 		## The domain name that is the subject of the DNS query.
@@ -40,17 +40,17 @@ export {
 		rcode:         count              &log &optional;
 		## A descriptive name for the response code value.
 		rcode_name:    string             &log &optional;
-		## The Authoritative Answer bit for response messages specifies that
+		## The Authoritative Answer bit for response messages specifies
-		## the responding name server is an authority for the domain name
+		## that the responding name server is an authority for the
-		## in the question section.
+		## domain name in the question section.
 		AA:            bool               &log &default=F;
 		## The Truncation bit specifies that the message was truncated.
 		TC:            bool               &log &default=F;
 		## The Recursion Desired bit in a request message indicates that
 		## the client wants recursive service for this query.
 		RD:            bool               &log &default=F;
-		## The Recursion Available bit in a response message indicates that
+		## The Recursion Available bit in a response message indicates
-		## the name server supports recursive queries.
+		## that the name server supports recursive queries.
 		RA:            bool               &log &default=F;
 		## A reserved field that is currently supposed to be zero in all
 		## queries and responses.
@@ -58,19 +58,19 @@ export {
 		## The set of resource descriptions in the query answer.
 		answers:       vector of string   &log &optional;
 		## The caching intervals of the associated RRs described by the
-		## ``answers`` field.
+		## *answers* field.
 		TTLs:          vector of interval &log &optional;
 		## The DNS query was rejected by the server.
 		rejected:      bool               &log &default=F;
 
-		## This value indicates if this request/response pair is ready to be
+		## This value indicates if this request/response pair is ready
-		## logged.
+		## to be logged.
 		ready:         bool            &default=F;
-		## The total number of resource records in a reply message's answer
+		## The total number of resource records in a reply message's
-		## section.
+		## answer section.
 		total_answers: count           &optional;
-		## The total number of resource records in a reply message's answer,
+		## The total number of resource records in a reply message's
-		## authority, and additional sections.
+		## answer, authority, and additional sections.
 		total_replies: count           &optional;
 	};
 
@@ -78,9 +78,10 @@ export {
 	## record as it is sent to the logging framework.
 	global log_dns: event(rec: Info);
 
-	## This is called by the specific dns_*_reply events with a "reply" which
+	## This is called by the specific dns_*_reply events with a "reply"
-	## may not represent the full data available from the resource record, but
+	## which may not represent the full data available from the resource
-	## it's generally considered a summarization of the response(s).
+	## record, but it's generally considered a summarization of the
+	## responses.
 	##
 	## c: The connection record for which to fill in DNS reply data.
 	##
@@ -95,7 +96,7 @@ export {
 	## This can be used if additional initialization logic needs to happen
 	## when creating a new session value.
 	##
-	## c: The connection involved in the new session
+	## c: The connection involved in the new session.
 	## 
 	## msg: The DNS message header information.
 	##
@@ -109,9 +110,9 @@ export {
 		## query/response which haven't completed yet.
 		pending: table[count] of Queue::Queue;
 
-		## This is the list of DNS responses that have completed based on the
+		## This is the list of DNS responses that have completed based
-		## number of responses declared and the number received.  The contents
+		## on the number of responses declared and the number received.
-		## of the set are transaction IDs.
+		## The contents of the set are transaction IDs.
 		finished_answers: set[count];
 	};
 }

scripts/base/protocols/ftp/README

@@ -0,0 +1 @@
+Support for File Transfer Protocol (FTP) analysis.

scripts/base/protocols/ftp/gridftp.bro

@@ -4,20 +4,20 @@
 ##! that successfully negotiate the GSSAPI method of an AUTH request
 ##! and for which the exchange involved an encoded TLS/SSL handshake,
 ##! indicating the GSI mechanism for GSSAPI was used.  This analysis
-##! is all supported internally, this script simple adds the "gridftp"
+##! is all supported internally, this script simply adds the "gridftp"
 ##! label to the *service* field of the control channel's
 ##! :bro:type:`connection` record.
 ##!
 ##! GridFTP data channels are identified by a heuristic that relies on
 ##! the fact that default settings for GridFTP clients typically
-##! mutally authenticate the data channel with TLS/SSL and negotiate a
+##! mutually authenticate the data channel with TLS/SSL and negotiate a
 ##! NULL bulk cipher (no encryption).  Connections with those
 ##! attributes are then polled for two minutes with decreasing frequency
 ##! to check if the transfer sizes are large enough to indicate a
-##! GridFTP data channel that would be undesireable to analyze further
+##! GridFTP data channel that would be undesirable to analyze further
 ##! (e.g. stop TCP reassembly).  A side effect is that true connection
 ##! sizes are not logged, but at the benefit of saving CPU cycles that
-##! otherwise go to analyzing the large (and likely benign) connections.
+##! would otherwise go to analyzing the large (and likely benign) connections.
 
 @load ./info
 @load ./main
@@ -59,8 +59,8 @@ export {
 	## been exceeded.  This is called in a :bro:see:`ssl_established` event
 	## handler and by default looks for both a client and server certificate
 	## and for a NULL bulk cipher.  One way in which this function could be
-	## redefined is to make it also consider client/server certificate issuer
+	## redefined is to make it also consider client/server certificate
-	## subjects.
+	## issuer subjects.
 	##
 	## c: The connection which may possibly be a GridFTP data channel.
 	##

scripts/base/protocols/ftp/info.bro

@@ -18,7 +18,8 @@ export {
 		orig_h: addr &log;
 		## The host that will be accepting the data connection.
 		resp_h: addr &log;
-		## The port at which the acceptor is listening for the data connection.
+		## The port at which the acceptor is listening for the data
+		## connection.
 		resp_p: port &log;
 	};
 
@@ -38,7 +39,8 @@ export {
 		## Argument for the command if one is given.
 		arg:              string      &log &optional;
 
-		## Libmagic "sniffed" file type if the command indicates a file transfer.
+		## Libmagic "sniffed" file type if the command indicates a file
+		## transfer.
 		mime_type:        string      &log &optional;
 		## Size of the file if the command indicates a file transfer.
 		file_size:        count       &log &optional;
@@ -59,8 +61,8 @@ export {
 
 		## Command that is currently waiting for a response.
 		cmdarg:             CmdArg  &optional;
-		## Queue for commands that have been sent but not yet responded to
+		## Queue for commands that have been sent but not yet responded
-		## are tracked here.
+		## to are tracked here.
 		pending_commands:   PendingCmds;
 
 		## Indicates if the session is in active or passive mode.

scripts/base/protocols/ftp/main.bro

@@ -26,7 +26,7 @@ export {
 	const guest_ids = { "anonymous", "ftp", "ftpuser", "guest" } &redef;
 
 	## This record is to hold a parsed FTP reply code.  For example, for the
-	## 201 status code, the digits would be parsed as: x->2, y->0, z=>1.
+	## 201 status code, the digits would be parsed as: x->2, y->0, z->1.
 	type ReplyCode: record {
 		x: count;
 		y: count;

scripts/base/protocols/ftp/utils.bro

@@ -11,14 +11,14 @@ export {
 	##
 	## rec: An :bro:type:`FTP::Info` record.
 	##
-	## Returns: A URL, not prefixed by "ftp://".
+	## Returns: A URL, not prefixed by ``"ftp://"``.
 	global build_url: function(rec: Info): string;
 
 	## Creates a URL from an :bro:type:`FTP::Info` record.
 	##
 	## rec: An :bro:type:`FTP::Info` record.
 	##
-	## Returns: A URL prefixed with "ftp://".
+	## Returns: A URL prefixed with ``"ftp://"``.
 	global build_url_ftp: function(rec: Info): string;
 
 	## Create an extremely shortened representation of a log line.

scripts/base/protocols/http/README

@@ -0,0 +1 @@
+Support for Hypertext Transfer Protocol (HTTP) analysis.

scripts/base/protocols/http/entities.bro

@@ -28,9 +28,11 @@ export {
 
 		## The current entity.
 		current_entity:  Entity           &optional;
-		## Current number of MIME entities in the HTTP request message body.
+		## Current number of MIME entities in the HTTP request message
+		## body.
 		orig_mime_depth: count            &default=0;
-		## Current number of MIME entities in the HTTP response message body.
+		## Current number of MIME entities in the HTTP response message
+		## body.
 		resp_mime_depth: count            &default=0;
 	};
 }

scripts/base/protocols/http/main.bro

@@ -16,7 +16,8 @@ export {
 		EMPTY
 	};
 
-	## This setting changes if passwords used in Basic-Auth are captured or not.
+	## This setting changes if passwords used in Basic-Auth are captured or
+	## not.
 	const default_capture_password = F &redef;
 
 	type Info: record {
@@ -36,8 +37,8 @@ export {
 		## URI used in the request.
 		uri:                     string    &log &optional;
 		## Value of the "referer" header.  The comment is deliberately
-		## misspelled like the standard declares, but the name used here is
+		## misspelled like the standard declares, but the name used here
-		## "referrer" spelled correctly.
+		## is "referrer" spelled correctly.
 		referrer:                string    &log &optional;
 		## Value of the User-Agent header from the client.
 		user_agent:              string    &log &optional;
@@ -55,7 +56,8 @@ export {
 		info_code:               count     &log &optional;
 		## Last seen 1xx informational reply message returned by the server.
 		info_msg:                string    &log &optional;
-		## Filename given in the Content-Disposition header sent by the server.
+		## Filename given in the Content-Disposition header sent by the
+		## server.
 		filename:                string    &log &optional;
 		## A set of indicators of various attributes discovered and
 		## related to a particular request/response pair.

scripts/base/protocols/http/utils.bro

@@ -6,8 +6,8 @@
 module HTTP;
 
 export {
-	## Given a string containing a series of key-value pairs separated by "=",
+	## Given a string containing a series of key-value pairs separated
-	## this function can be used to parse out all of the key names.
+	## by "=", this function can be used to parse out all of the key names.
 	##
 	## data: The raw data, such as a URL or cookie value.
 	##
@@ -17,20 +17,20 @@ export {
 	## Returns: A vector of strings containing the keys.
 	global extract_keys: function(data: string, kv_splitter: pattern): string_vec;
 	
-	## Creates a URL from an :bro:type:`HTTP::Info` record.  This should handle
+	## Creates a URL from an :bro:type:`HTTP::Info` record.  This should
-	## edge cases such as proxied requests appropriately.
+	## handle edge cases such as proxied requests appropriately.
 	##
 	## rec: An :bro:type:`HTTP::Info` record.
 	##
-	## Returns: A URL, not prefixed by "http://".
+	## Returns: A URL, not prefixed by ``"http://"``.
 	global build_url: function(rec: Info): string;
 	
-	## Creates a URL from an :bro:type:`HTTP::Info` record.  This should handle
+	## Creates a URL from an :bro:type:`HTTP::Info` record.  This should
-	## edge cases such as proxied requests appropriately.
+	## handle edge cases such as proxied requests appropriately.
 	##
 	## rec: An :bro:type:`HTTP::Info` record.
 	##
-	## Returns: A URL prefixed with "http://".
+	## Returns: A URL prefixed with ``"http://"``.
 	global build_url_http: function(rec: Info): string;
 
 	## Create an extremely shortened representation of a log line.

scripts/base/protocols/irc/README

@@ -0,0 +1 @@
+Support for Internet Relay Chat (IRC) protocol analysis.

scripts/base/protocols/modbus/README

@@ -0,0 +1 @@
+Support for Modbus protocol analysis.

scripts/base/protocols/modbus/main.bro

@@ -10,7 +10,7 @@ export {
 	type Info: record {
 		## Time of the request.
 		ts:        time           &log;
-		## Unique identifier for the connnection.
+		## Unique identifier for the connection.
 		uid:       string         &log;
 		## Identifier for the connection.
 		id:        conn_id        &log;
@@ -20,8 +20,8 @@ export {
 		exception: string         &log &optional;
 	};
 
-	## Event that can be handled to access the Modbus record as it is sent on
+	## Event that can be handled to access the Modbus record as it is sent
-	## to the logging framework.
+	## on to the logging framework.
 	global log_modbus: event(rec: Info);
 }
 

scripts/base/protocols/pop3/README

@@ -0,0 +1 @@
+Support for POP3 (Post Office Protocol) protocol analysis.

scripts/base/protocols/smtp/README

@@ -0,0 +1 @@
+Support for Simple Mail Transfer Protocol (SMTP) analysis.

scripts/base/protocols/smtp/main.bro

@@ -14,8 +14,8 @@ export {
 		uid:               string          &log;
 		## The connection's 4-tuple of endpoint addresses/ports.
 		id:                conn_id         &log;
-		## A count to represent the depth of this message transaction in a single 
+		## A count to represent the depth of this message transaction in
-		## connection where multiple messages were transferred.
+		## a single connection where multiple messages were transferred.
 		trans_depth:       count           &log;
 		## Contents of the Helo header.
 		helo:              string          &log &optional;
@@ -37,7 +37,7 @@ export {
 		in_reply_to:       string          &log &optional;
 		## Contents of the Subject header.
 		subject:           string          &log &optional;
-		## Contents of the X-Origininating-IP header.
+		## Contents of the X-Originating-IP header.
 		x_originating_ip:  addr            &log &optional;
 		## Contents of the first Received header.
 		first_received:    string          &log &optional;
@@ -50,7 +50,8 @@ export {
 		## Value of the User-Agent header from the client.
 		user_agent:        string          &log &optional;
 		
-		## Indicates if the "Received: from" headers should still be processed.
+		## Indicates if the "Received: from" headers should still be
+		## processed.
 		process_received_from: bool        &default=T;
 		## Indicates if client activity has been seen, but not yet logged.
 		has_client_activity:  bool            &default=F;
@@ -58,9 +59,9 @@ export {
 	
 	type State: record {
 		helo:                     string    &optional;
-		## Count the number of individual messages transmitted during this 
+		## Count the number of individual messages transmitted during
-		## SMTP session.  Note, this is not the number of recipients, but the
+		## this SMTP session.  Note, this is not the number of
-		## number of message bodies transferred.
+		## recipients, but the number of message bodies transferred.
 		messages_transferred:     count     &default=0;
 		
 		pending_messages:         set[Info] &optional;

scripts/base/protocols/socks/README

@@ -0,0 +1 @@
+Support for Socket Secure (SOCKS) protocol analysis.

scripts/base/protocols/socks/main.bro

@@ -9,17 +9,19 @@ export {
 	type Info: record {
 		## Time when the proxy connection was first detected.
 		ts:          time            &log;
-		## Unique ID for the tunnel - may correspond to connection uid or be non-existent.
+		## Unique ID for the tunnel - may correspond to connection uid
+		## or be non-existent.
 		uid:         string          &log;
 		## The connection's 4-tuple of endpoint addresses/ports.
 		id:          conn_id         &log;
 		## Protocol version of SOCKS.
 		version:     count           &log;
-		## Username for the proxy if extracted from the network..
+		## Username for the proxy if extracted from the network.
 		user:        string          &log &optional;
 		## Server status for the attempt at using the proxy.
 		status:      string          &log &optional;
-		## Client requested SOCKS address. Could be an address, a name or both.
+		## Client requested SOCKS address. Could be an address, a name
+		## or both.
 		request:     SOCKS::Address  &log &optional;
 		## Client requested port.
 		request_p:   port            &log &optional;

scripts/base/protocols/ssh/README

@@ -0,0 +1 @@
+Support for Secure Shell (SSH) protocol analysis.

scripts/base/protocols/ssh/main.bro

@@ -25,8 +25,8 @@ export {
 		uid:             string       &log;
 		## The connection's 4-tuple of endpoint addresses/ports.
 		id:              conn_id      &log;
-		## Indicates if the login was heuristically guessed to be "success",
+		## Indicates if the login was heuristically guessed to be
-		## "failure", or "undetermined".
+		## "success", "failure", or "undetermined".
 		status:          string       &log &default="undetermined";
 		## Direction of the connection.  If the client was a local host
 		## logging into an external host, this would be OUTBOUND. INBOUND
@@ -39,8 +39,8 @@ export {
 		server:          string       &log &optional;
 		## Amount of data returned from the server. This is currently
 		## the only measure of the success heuristic and it is logged to
-		## assist analysts looking at the logs to make their own determination
+		## assist analysts looking at the logs to make their own
-		## about the success on a case-by-case basis.
+		## determination about the success on a case-by-case basis.
 		resp_size:       count        &log &default=0;
 
 		## Indicate if the SSH session is done being watched.

scripts/base/protocols/ssl/README

@@ -0,0 +1 @@
+Support for Secure Sockets Layer (SSL) protocol analysis.

scripts/base/protocols/ssl/consts.bro

@@ -23,7 +23,7 @@ export {
 	} &default=function(i: count):string { return fmt("unknown-%d", i); };
 	
 	## Mapping between numeric codes and human readable strings for alert 
-	## descriptions..
+	## descriptions.
 	const alert_descriptions: table[count] of string = {
 		[0] = "close_notify",
 		[10] = "unexpected_message",
@@ -453,8 +453,8 @@ export {
 	const TLS_EMPTY_RENEGOTIATION_INFO_SCSV = 0x00FF;
 	
 	## This is a table of all known cipher specs.  It can be used for 
-	## detecting unknown ciphers and for converting the cipher spec constants 
+	## detecting unknown ciphers and for converting the cipher spec
-	## into a human readable format.
+	## constants into a human readable format.
 	const cipher_desc: table[count] of string = {
 		[SSLv20_CK_RC4_128_EXPORT40_WITH_MD5] =
 			"SSLv20_CK_RC4_128_EXPORT40_WITH_MD5",

scripts/base/protocols/ssl/main.bro

@@ -26,7 +26,8 @@ export {
 		session_id:       string           &log &optional;
 		## Subject of the X.509 certificate offered by the server.
 		subject:          string           &log &optional;
-		## Subject of the signer of the X.509 certificate offered by the server.
+		## Subject of the signer of the X.509 certificate offered by the
+		## server.
 		issuer_subject:   string           &log &optional;
 		## NotValidBefore field value from the server certificate.
 		not_valid_before: time             &log &optional;
@@ -37,7 +38,8 @@ export {
 
 		## Subject of the X.509 certificate offered by the client.
 		client_subject:          string           &log &optional;
-		## Subject of the signer of the X.509 certificate offered by the client.
+		## Subject of the signer of the X.509 certificate offered by the
+		## client.
 		client_issuer_subject:   string           &log &optional;
 
 		## Full binary server certificate stored in DER format.
@@ -58,8 +60,8 @@ export {
 		analyzer_id:      count            &optional;
 	};
 
-	## The default root CA bundle.  By loading the
+	## The default root CA bundle.  By default, the mozilla-ca-list.bro
-	## mozilla-ca-list.bro script it will be set to Mozilla's root CA list.
+	## script sets this to Mozilla's root CA list.
 	const root_certs: table[string] of string = {} &redef;
 
 	## If true, detach the SSL analyzer from the connection to prevent
@@ -67,8 +69,8 @@ export {
 	## (especially with large file transfers).
 	const disable_analyzer_after_detection = T &redef;
 
-	## Delays an SSL record for a specific token: the record will not be logged
+	## Delays an SSL record for a specific token: the record will not be
-	## as longs the token exists or until 15 seconds elapses.
+	## logged as long as the token exists or until 15 seconds elapses.
 	global delay_log: function(info: Info, token: string);
 
 	## Undelays an SSL record for a previously inserted token, allowing the