You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Splunk_Deploiement/apps/trackme/bin/trackmemergesplkdhm.py

203 lines
6.6 KiB

#!/usr/bin/env python
# coding=utf-8
__author__ = "TrackMe Limited"
__copyright__ = "Copyright 2022-2026, TrackMe Limited, U.K."
__credits__ = "TrackMe Limited, U.K."
__license__ = "TrackMe Limited, all rights reserved"
__version__ = "0.1.0"
__maintainer__ = "TrackMe Limited, U.K."
__email__ = "support@trackme-solutions.com"
__status__ = "PRODUCTION"
# Standard library imports
import ast
import json
import logging
import os
import sys
import time
from logging.handlers import RotatingFileHandler
# Third-party imports
import urllib3
# Disable insecure request warnings for urllib3
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
# splunk home
splunkhome = os.environ["SPLUNK_HOME"]
# set logging
filehandler = RotatingFileHandler(
"%s/var/log/splunk/trackme_merge_splk_dhm.log" % splunkhome,
mode="a",
maxBytes=10000000,
backupCount=1,
)
formatter = logging.Formatter(
"%(asctime)s %(levelname)s %(filename)s %(funcName)s %(lineno)d %(message)s"
)
logging.Formatter.converter = time.gmtime
filehandler.setFormatter(formatter)
log = logging.getLogger() # root logger - Good to get it only once.
for hdlr in log.handlers[:]: # remove the existing file handlers
if isinstance(hdlr, logging.FileHandler):
log.removeHandler(hdlr)
log.addHandler(filehandler) # set the new handler
# set the log level to INFO, DEBUG as the default is ERROR
log.setLevel(logging.INFO)
# append current directory
sys.path.append(os.path.dirname(os.path.abspath(__file__)))
# import libs
import import_declare_test
# import Splunk libs
from splunklib.searchcommands import (
dispatch,
StreamingCommand,
Configuration,
Option,
validators,
)
# Import trackme libs
from trackme_libs import trackme_reqinfo
@Configuration(distributed=False)
class TrackMeMergeSplkDhm(StreamingCommand):
field_host = Option(
doc="""
**Syntax:** **field_host=****
**Description:** field name containing the host value.""",
require=True,
)
field_current = Option(
doc="""
**Syntax:** **field_current=****
**Description:** field name containing the current object dictionnary.""",
require=True,
)
field_previous = Option(
doc="""
**Syntax:** **field_previous=****
**Description:** field name containing the previous object dictionnary.""",
require=True,
)
# status will be statically defined as imported
def stream(self, records):
# Start performance counter
start = time.time()
# Get request info and set logging level
reqinfo = trackme_reqinfo(
self._metadata.searchinfo.session_key, self._metadata.searchinfo.splunkd_uri
)
log.setLevel(reqinfo["logging_level"])
# Iterate over records
for subrecord in records:
# Extract host field
host = subrecord[self.field_host]
# Get the alias, if any
alias = subrecord.get("alias", host)
# Try to parse the current_dict and previous_dict from the record
current_dict, previous_dict = None, None
# get both
current_dict_str = subrecord.get(self.field_current, None)
previous_dict_str = subrecord.get(self.field_previous, None)
if current_dict_str:
try:
logging.debug(f"Trying to parse: {current_dict_str}")
current_dict = ast.literal_eval(current_dict_str)
logging.debug(
f'current_dict loaded successfully, current_dict="{json.dumps(current_dict, indent=2)}"'
)
except (ValueError, SyntaxError) as e:
logging.warning(
f"Failed to parse current_dict for host '{host}', exception: {e}"
)
if previous_dict_str:
try:
logging.debug(f"Trying to parse: {previous_dict_str}")
previous_dict = ast.literal_eval(previous_dict_str)
logging.debug(
f'previous_dict loaded successfully, previous_dict="{json.dumps(previous_dict, indent=2)}"'
)
except (ValueError, SyntaxError) as e:
logging.info(
f"No previous_dict found for host '{host}', this can be expected for new entities."
)
logging.debug(
f"Failed to parse previous_dict for host '{host}', exception: {e}"
)
# Our new dict
new_dict = {}
# If we have both current_dict and previous_dict
if current_dict and previous_dict:
# Preserve any record from the previous iteration that is not available in the current iteration
for p_id, p_info in previous_dict.items():
if p_id not in current_dict:
current_dict[p_id] = p_info
# If we have only current_dict or both current_dict and previous_dict
if current_dict:
for p_id, p_info in current_dict.items():
new_record = {"hash": p_id}
for field in p_info:
new_field = field
if field in (
"idx",
"st",
"first_time",
"last_time",
"last_ingest_lag",
"last_event_lag",
"time_measure",
"last_ingest",
"last_eventcount",
):
new_field = f"summary_{field}"
new_record[new_field] = p_info[field]
# Add to the dict
new_dict[p_id] = new_record
# Yield result per host
yield {
"_time": time.time(),
"host": str(host),
"alias": str(alias),
"record": json.dumps(new_record, indent=1),
}
else:
yield {
"_time": time.time(),
"host": str(host),
"alias": str(alias),
}
# Log the run time
logging.info(
f"trackmemergesplkdhm has terminated, run_time={round(time.time() - start, 3)}"
)
dispatch(TrackMeMergeSplkDhm, sys.argv, sys.stdin, sys.stdout, __name__)