Adding a new directory monitor input plugin.

docs/LICENSE_OF_DEPENDENCIES.md

@@ -164,6 +164,7 @@ following works:
 - google.golang.org/genproto [Apache License 2.0](https://github.com/google/go-genproto/blob/master/LICENSE)
 - google.golang.org/grpc [Apache License 2.0](https://github.com/grpc/grpc-go/blob/master/LICENSE)
 - gopkg.in/asn1-ber.v1 [MIT License](https://github.com/go-asn1-ber/asn1-ber/blob/v1.3/LICENSE)
+- gopkg.in/djherbis/times.v1 [MIT License](https://github.com/djherbis/times/blob/master/LICENSE)
 - gopkg.in/fatih/pool.v2 [MIT License](https://github.com/fatih/pool/blob/v2.0.0/LICENSE)
 - gopkg.in/fsnotify.v1 [BSD 3-Clause "New" or "Revised" License](https://github.com/fsnotify/fsnotify/blob/v1.4.7/LICENSE)
 - gopkg.in/gorethink/gorethink.v3 [Apache License 2.0](https://github.com/rethinkdb/rethinkdb-go/blob/v3.0.5/LICENSE)

go.mod

@@ -148,6 +148,7 @@ require (
 	google.golang.org/api v0.20.0
 	google.golang.org/genproto v0.0.0-20200513103714-09dca8ec2884
 	google.golang.org/grpc v1.33.1
+	gopkg.in/djherbis/times.v1 v1.2.0
 	gopkg.in/fatih/pool.v2 v2.0.0 // indirect
 	gopkg.in/gorethink/gorethink.v3 v3.0.5
 	gopkg.in/ldap.v3 v3.1.0

go.sum

@@ -893,6 +893,8 @@ gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15 h1:YR8cESwS4TdDjEe65xsg0ogR
 gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20200902074654-038fdea0a05b h1:QRR6H1YWRnHb4Y/HeNFCTJLFVxaq6wH4YuVdsUOr75U=
 gopkg.in/check.v1 v1.0.0-20200902074654-038fdea0a05b/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/djherbis/times.v1 v1.2.0 h1:UCvDKl1L/fmBygl2Y7hubXCnY7t4Yj46ZrBFNUipFbM=
+gopkg.in/djherbis/times.v1 v1.2.0/go.mod h1:AQlg6unIsrsCEdQYhTzERy542dz6SFdQFZFv6mUY0P8=
 gopkg.in/errgo.v2 v2.1.0/go.mod h1:hNsd1EY+bozCKY1Ytp96fpM3vjJbqLJn88ws8XvfDNI=
 gopkg.in/fatih/pool.v2 v2.0.0 h1:xIFeWtxifuQJGk/IEPKsTduEKcKvPmhoiVDGpC40nKg=
 gopkg.in/fatih/pool.v2 v2.0.0/go.mod h1:8xVGeu1/2jr2wm5V9SPuMht2H5AEmf5aFMGSQixtjTY=

plugins/inputs/all/all.go

@@ -29,6 +29,7 @@ import (
 	_ "github.com/influxdata/telegraf/plugins/inputs/couchdb"
 	_ "github.com/influxdata/telegraf/plugins/inputs/cpu"
 	_ "github.com/influxdata/telegraf/plugins/inputs/dcos"
+	_ "github.com/influxdata/telegraf/plugins/inputs/directory_monitor"
 	_ "github.com/influxdata/telegraf/plugins/inputs/disk"
 	_ "github.com/influxdata/telegraf/plugins/inputs/diskio"
 	_ "github.com/influxdata/telegraf/plugins/inputs/disque"

plugins/inputs/directory_monitor/README.md

@@ -0,0 +1,48 @@
+# Directory Monitor Input Plugin
+
+This plugin monitors a single directory (without looking at sub-directories), and takes in each file placed in the directory.
+The plugin will gather all files in the directory at a configurable interval (`monitor_interval`), and parse the ones that haven't been picked up yet.
+
+This plugin is intended to read files that are moved or copied to the monitored directory, and thus files should also not be used by another process or else they may fail to be gathered. Please be advised that this plugin pulls files directly after they've been in the directory for the length of the configurable `directory_duration_threshold`, and thus files should not be written 'live' to the monitored directory. If you absolutely must write files directly, they must be guaranteed to finish writing before the `directory_duration_threshold`.
+
+### Configuration:
+
+```toml
+[[inputs.directory_monitor]]
+  ## The directory to monitor and read files from.
+  directory = ""
+  #
+  ## The directory to move finished files to.
+  finished_directory = ""
+  #
+  ## The directory to move files to upon file error.
+  ## If not provided, erroring files will stay in the monitored directory.
+  # error_directory = ""
+  #
+  ## The amount of time a file is allowed to sit in the directory before it is picked up.
+  ## This time can generally be low but if you choose to have a very large file written to the directory and it's potentially slow,
+  ## set this higher so that the plugin will wait until the file is fully copied to the directory.
+  # directory_duration_threshold = "50ms" 
+  #
+  ## A list of the only file names to monitor, if necessary. Supports regex. If left blank, all files are ingested.
+  # files_to_monitor = ["^.*\.csv"]
+  #
+  ## A list of files to ignore, if necessary. Supports regex.
+  # files_to_ignore = [".DS_Store"]
+  #
+  ## Maximum lines of the file to process that have not yet be written by the
+  ## output. For best throughput set to the size of the output's metric_buffer_limit.
+  ## Warning: setting this number higher than the output's metric_buffer_limit can cause dropped metrics.
+  # max_buffered_metrics = 10000
+  #
+  ## The maximum amount of file paths to queue up for processing at once, before waiting until files are processed to find more files.
+  ## Lowering this value will result in *slightly* less memory use, with a potential sacrifice in speed efficiency, if absolutely necessary.
+  #	file_queue_size = 100000
+  #
+  ## The dataformat to be read from the files.
+  ## Each data format has its own unique set of configuration options, read
+  ## more about them here:
+  ## https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_INPUT.md
+  ## NOTE: We currently only support parsing newline-delimited JSON. See the format here: https://github.com/ndjson/ndjson-spec
+  data_format = "influx"
+```