transforms.conf.example

#   Version 6.5.0
#
# This is an example transforms.conf.  Use this file to create regexes and
# rules for transforms.  Use this file in tandem with props.conf.
#
# To use one or more of these configurations, copy the configuration block
# into transforms.conf in $SPLUNK_HOME/etc/system/local/. You must restart
# Splunk to enable configurations.
#
# To learn more about configuration files (including precedence) please see
# the documentation located at
# http://docs.splunk.com/Documentation/Splunk/latest/Admin/Aboutconfigurationfiles

# Note: These are examples.  Replace the values with your own customizations.


# Indexed field:

[netscreen-error]
REGEX =  device_id=\[w+\](?<err_code>[^:]+)
FORMAT = err_code::$1
WRITE_META = true


# Override host:

[hostoverride]
DEST_KEY = MetaData:Host
REGEX = \s(\w*)$
FORMAT = host::$1


# Extracted fields:

[netscreen-error-field]
REGEX = device_id=\[w+\](?<err_code>[^:]+)
FORMAT = err_code::$1


# Static lookup table

[mylookuptable]
filename = mytable.csv

# one to one lookup
# guarantees that we output a single lookup value for each input value, if
# no match exists, we use the value of "default_match", which by default is
# "NONE"
[mylook]
filename = mytable.csv
max_matches = 1
min_matches = 1
default_match = nothing

# Lookup and filter results
[myfilteredlookup]
filename = mytable.csv
filter = id<500 AND color="red"

# external command lookup table

[myexternaltable]
external_cmd = testadapter.py blah
fields_list = foo bar

# Temporal based static lookup table

[staticwtime]
filename = mytable.csv
time_field = timestamp
time_format = %d/%m/%y %H:%M:%S


# Mask sensitive data:

[session-anonymizer]
REGEX = (?m)^(.*)SessionId=\w+(\w{4}[&"].*)$
FORMAT = $1SessionId=########$2
DEST_KEY = _raw


# Route to an alternate index:

[AppRedirect]
REGEX = Application
DEST_KEY = _MetaData:Index
FORMAT = Verbose


# Extract comma-delimited values into fields:

[extract_csv]
DELIMS = ","
FIELDS = "field1", "field2", "field3"

# This example assigns the extracted values from _raw to field1, field2 and
# field3 (in order of extraction). If more than three values are extracted
# the values without a matching field name are ignored.

[pipe_eq]
DELIMS = "|", "="

# The above example extracts key-value pairs which are separated by '|'
# while the key is delimited from value by '='.


[multiple_delims]
DELIMS = "|;", "=:"


# The above example extracts key-value pairs which are separated by '|' or
# ';', while the key is delimited from value by '=' or ':'.


###### BASIC MODULAR REGULAR EXPRESSIONS DEFINITION START ###########
# When adding a new basic modular regex PLEASE add a comment that lists
# the fields that it extracts (named capturing groups), or whether it
# provides a placeholder for the group name as:
# Extracts: field1, field2....
#

[all_lazy]
REGEX = .*?

[all]
REGEX = .*

[nspaces]
# matches one or more NON space characters
REGEX = \S+

[alphas]
# matches a string containing only letters a-zA-Z
REGEX = [a-zA-Z]+

[alnums]
# matches a string containing letters + digits
REGEX = [a-zA-Z0-9]+

[qstring]
# matches a quoted "string" - extracts an unnamed variable
# name MUST be provided as in [[qstring:name]]
# Extracts: empty-name-group (needs name)
REGEX = "(?<>[^"]*+)"

[sbstring]
# matches a string enclosed in [] - extracts an unnamed variable
# name MUST be provided as in [[sbstring:name]]
# Extracts: empty-name-group (needs name)
REGEX = \[(?<>[^\]]*+)\]

[digits]
REGEX = \d+

[int]
# matches an integer or a hex number
REGEX = 0x[a-fA-F0-9]+|\d+

[float]
# matches a float (or an int)
REGEX = \d*\.\d+|[[int]]

[octet]
# this would match only numbers from 0-255 (one octet in an ip)
REGEX = (?:2(?:5[0-5]|[0-4][0-9])|[0-1][0-9][0-9]|[0-9][0-9]?)

[ipv4]
# matches a valid IPv4 optionally followed by :port_num the octets in the ip
# would also be validated 0-255 range
# Extracts: ip, port
REGEX = (?<ip>[[octet]](?:\.[[octet]]){3})(?::[[int:port]])?

[simple_url]
# matches a url of the form proto://domain.tld/uri
# Extracts: url, domain
REGEX = (?<url>\w++://(?<domain>[a-zA-Z0-9\-.:]++)(?:/[^\s"]*)?)

[url]
# matches a url of the form proto://domain.tld/uri
# Extracts: url, proto, domain, uri
REGEX = (?<url>[[alphas:proto]]://(?<domain>[a-zA-Z0-9\-.:]++)(?<uri>/[^\s"]*)?)

[simple_uri]
# matches a uri of the form /path/to/resource?query
# Extracts: uri, uri_path, uri_query
REGEX = (?<uri>(?<uri_path>[^\s\?"]++)(?:\\?(?<uri_query>[^\s"]+))?)

[uri]
# uri  = path optionally followed by query [/this/path/file.js?query=part&other=var]
# path = root part followed by file        [/root/part/file.part]
# Extracts: uri, uri_path, uri_root, uri_file, uri_query, uri_domain (optional if in proxy mode)
REGEX = (?<uri>(?:\w++://(?<uri_domain>[^/\s]++))?(?<uri_path>(?<uri_root>/+(?:[^\s\?;=/]*+/+)*)(?<uri_file>[^\s\?;=?/]*+))(?:\?(?<uri_query>[^\s"]+))?)

[hide-ip-address]
# Make a clone of an event with the sourcetype masked_ip_address.  The clone
# will be modified; its text changed to mask the ip address.
# The cloned event will be further processed by index-time transforms and
# SEDCMD expressions according to its new sourcetype.
# In most scenarios an additional transform would be used to direct the
# masked_ip_address event to a different index than the original data.
REGEX = ^(.*?)src=\d+\.\d+\.\d+\.\d+(.*)$
FORMAT = $1src=XXXXX$2
DEST_KEY = _raw
CLONE_SOURCETYPE = masked_ip_addresses

###### BASIC MODULAR REGULAR EXPRESSIONS DEFINITION END ###########