2018-06-06 11:18:51 -04:00

98 lines
3.5 KiB
INI

; diskover config file
; if you make any changes, restart worker bots so they get the new config
[excludes]
; directory names and absolute paths you want to exclude from crawl, case-sensitive, can include wildcard (.* or tmp* or /dir/dirname* etc)
dirs = .*,.snapshot,.Snapshot
; files you want to exclude from crawl, case-sensitive, can include wildcards (.*, *.doc or NULLEXT for files with no extension)
files = .*,Thumbs.db,.DS_Store,._.DS_Store,.localized,desktop.ini
[includes]
; directory names and absolute paths you want to include (whitelist), case-sensitive
;dirs = .recycle
; files you want to include (whitelist), case-sensitive
;files =
[autotag]
; pattern dictionaries for diskover bots to use when auto-tagging, values are case-sensitive, can include wildcard for ext, name or path (tmp* or TMP* or *tmp or *TMP* etc)
;files = [{"name": [], "name_exclude": [], "ext": ["tmp*", "TMP*", "temp*", "TEMP*", "cache*", "CACHE*"], "path": ["*/Application Support/*", "*/Containers/*"], "path_exclude": [], "mtime": 90, "atime": 0, "ctime": 90, "tag": "delete", "tag_custom": "autotag"}]
;dirs = [{"name": ["*tmp*", "*TMP*", "*temp*", "*TEMP*", "*Temp*", "*cache*", "*CACHE*", "*Cache*"], "name_exclude": ["*templates*", "*Templates*"], "path": ["*/Application Support/*", "*/Containers/*"], "path_exclude": [], "mtime": 90, "atime": 0, "ctime": 90, "tag": "delete", "tag_custom": "autotag"}]
[elasticsearch]
; uncomment the below three lines if you are using AWS ES
;aws = False
;host = search-diskover-es-cluster-eg3yztrvzb6qucroyyjk2vokza.ap-northeast-1.es.amazonaws.com
;port = 443
; below two lines are for local ES, comment out if you are using AWS ES
host = {{ES_HOST}}
port = {{ES_PORT}}
; uncomment the below two lines if you installed X-Pack, for http-auth
user = {{ES_USER}}
password = {{ES_PASS}}
; index name for ES, cli arg overwrites this
indexname = diskover-index
; timeout for connection to ES (default is 10)
timeout = 30
; number of connections kept open to ES when crawling (default is 10)
maxsize = 20
; max retries for ES operations (default is 0)
maxretries = 10
; wait for at least yellow status before bulk uploading (default is False), set to True if you want to wait
wait = False
; chunk size for ES bulk operations (default is 500)
chunksize = 1000
; number of shards for index (default is 5)
shards = 5
; number of replicas for index (default is 1)
replicas = 1
[redis]
host = {{REDIS_HOST}}
port = {{REDIS_PORT}}
;password =
; how long directory times lives in Redis (seconds) (default 1 week)
; used for -I index2 when comparing directory times to get metadata from index2 instead of off disk
dirtimesttl = 604800
[workerbot]
; enable bot logs (True or False)
botlogs = False
; log file directory to store worker logs
; log files are named diskover_bot_worker_<workername>_<time>_log
logfiledir = /tmp
[paths]
; used by diskover socket server
; path to diskover.py (default is ./diskover.py)
diskoverpath = ./diskover.py
; path to python executable (default is python)
pythonpath = python
[socketlistener]
; hostname and port (TCP) for diskover socket server for remote commands
host = localhost
port = 9999
[dupescheck]
; read size (bytes) for md5 sum check
readsize = 65536
[crawlbot]
; continuous scanner
; time to sleep (seconds) between checking for directory changes
sleeptime = 0.1
; number of threads for checking directories
threads = 8
[gource]
; should be set to same in diskover-gource.sh
maxfilelag = 0.1
[qumulo]
; Qumulo host
;cluster = 172.16.129.10
; Qumulo api user
;api_user = admin
; Qumulo api password
;api_password = admin