[Auditbeat] Cherry-pick elastic#10101 to 6.6: Rename "metricset" to "…

…dataset" in docs (elastic#10106)

Cherry-pick of PR elastic#10101 to 6.6 branch. Original message: 

Follow up to elastic#10018.

Changes the Auditbeat system module documentation to say `dataset` rather than `metricset` in all places. No Go code changes.

auditbeat/_meta/common.reference.yml

@@ -22,7 +22,7 @@ auditbeat.config.modules:
   # Set to true to enable config reloading
   reload.enabled: false
 
-# Maximum amount of time to randomly delay the start of a metricset. Use 0 to
+# Maximum amount of time to randomly delay the start of a dataset. Use 0 to
 # disable startup delay.
 auditbeat.max_start_delay: 10s
 

auditbeat/auditbeat.reference.yml

@@ -22,7 +22,7 @@ auditbeat.config.modules:
   # Set to true to enable config reloading
   reload.enabled: false
 
-# Maximum amount of time to randomly delay the start of a metricset. Use 0 to
+# Maximum amount of time to randomly delay the start of a dataset. Use 0 to
 # disable startup delay.
 auditbeat.max_start_delay: 10s
 

auditbeat/scripts/docs_collector.py

@@ -3,7 +3,7 @@
 import yaml
 import six
 
-# Collects docs for all modules and metricset
+# Collects docs for all modules and datasets
 
 
 def collect(base_paths):
@@ -60,7 +60,7 @@ def collect(base_paths):
         config_file = beat_path + "/config.yml"
 
         # Add example config file
-        if os.path.isfile(config_file) == True:
+        if os.path.isfile(config_file):
 
             module_file += """
 
@@ -75,7 +75,7 @@ def collect(base_paths):
 ----
 """ + beat_name + ".modules:\n"
 
-            # Load metricset yaml
+            # Load dataset yaml
             with open(config_file) as f:
                 # Add 2 spaces for indentation in front of each line
                 for line in f:
@@ -86,63 +86,63 @@ def collect(base_paths):
         module_links = ""
         module_includes = ""
 
-        # Iterate over all metricsets
-        for metricset in sorted(os.listdir(module_dir)):
+        # Iterate over all datasets
+        for dataset in sorted(os.listdir(module_dir)):
 
-            metricset_docs = os.path.join(module_dir, metricset, "_meta/docs.asciidoc")
+            dataset_docs = os.path.join(module_dir, dataset, "_meta/docs.asciidoc")
 
             # Only check folders where fields.yml exists
-            if os.path.isfile(metricset_docs) == False:
+            if not os.path.isfile(dataset_docs):
                 continue
 
-            link_name = "{beatname_lc}-metricset-" + module + "-" + metricset
-            link = "<<" + link_name + "," + metricset + ">>"
+            link_name = "{beatname_lc}-dataset-" + module + "-" + dataset
+            link = "<<" + link_name + "," + dataset + ">>"
             reference = "[id=\"" + link_name + "\"]"
 
             module_links += "* " + link + "\n\n"
 
-            module_includes += "include::" + module + "/" + metricset + ".asciidoc[]\n\n"
+            module_includes += "include::" + module + "/" + dataset + ".asciidoc[]\n\n"
 
-            metricset_file = generated_note
+            dataset_file = generated_note
 
-            # Add reference to metricset file and include file
-            metricset_file += reference + "\n"
+            # Add reference to dataset file and include file
+            dataset_file += reference + "\n"
 
-            # Create title out of module and metricset set name
-            metricset_file += "=== {} {} metricset\n\n".format(title, metricset)
+            # Create title out of module and dataset set name
+            dataset_file += "=== {} {} dataset\n\n".format(title, dataset)
 
-            metricset_file += 'include::../../../module/' + module + '/' + metricset + '/_meta/docs.asciidoc[]' + "\n"
+            dataset_file += 'include::../../../module/' + module + '/' + dataset + '/_meta/docs.asciidoc[]' + "\n"
 
-            # TODO: This should point directly to the exported fields of the metricset, not the whole module
-            metricset_file += """
+            # TODO: This should point directly to the exported fields of the dataset, not the whole module
+            dataset_file += """
 
 ==== Fields
 
-For a description of each field in the metricset, see the
+For a description of each field in the dataset, see the
 <<exported-fields-""" + module + """,exported fields>> section.
 
 """
 
-            data_file = os.path.join(module_dir, metricset, "_meta/data.json")
+            data_file = os.path.join(module_dir, dataset, "_meta/data.json")
 
             # Add data.json example json document
-            if os.path.isfile(data_file) == True:
-                metricset_file += "Here is an example document generated by this metricset:"
-                metricset_file += "\n\n"
+            if os.path.isfile(data_file):
+                dataset_file += "Here is an example document generated by this dataset:"
+                dataset_file += "\n\n"
 
-                metricset_file += "[source,json]\n"
-                metricset_file += "----\n"
-                metricset_file += "include::../../../module/" + module + "/" + metricset + "/_meta/data.json[]\n"
-                metricset_file += "----\n"
+                dataset_file += "[source,json]\n"
+                dataset_file += "----\n"
+                dataset_file += "include::../../../module/" + module + "/" + dataset + "/_meta/data.json[]\n"
+                dataset_file += "----\n"
 
-            # Write metricset docs
-            with open(os.path.join(module_docs_path(module_dir), "modules", module, metricset + ".asciidoc"), 'w') as f:
-                f.write(metricset_file)
+            # Write dataset docs
+            with open(os.path.join(module_docs_path(module_dir), "modules", module, dataset + ".asciidoc"), 'w') as f:
+                f.write(dataset_file)
 
         if len(module_links) > 0:
             module_file += "[float]\n"
-            module_file += "=== Metricsets\n\n"
-            module_file += "The following metricsets are available:\n\n"
+            module_file += "=== Datasets\n\n"
+            module_file += "The following datasets are available:\n\n"
 
             module_file += module_links
             module_file += module_includes

x-pack/auditbeat/auditbeat.reference.yml

@@ -22,7 +22,7 @@ auditbeat.config.modules:
   # Set to true to enable config reloading
   reload.enabled: false
 
-# Maximum amount of time to randomly delay the start of a metricset. Use 0 to
+# Maximum amount of time to randomly delay the start of a dataset. Use 0 to
 # disable startup delay.
 auditbeat.max_start_delay: 10s
 

x-pack/auditbeat/docs/modules/system.asciidoc

@@ -10,30 +10,30 @@ This file is generated! See scripts/docs_collector.py
 experimental[]
 
 The `system` module collects various security related information about
-a system. All metricsets send both periodic state information (e.g. all currently
+a system. All datasets send both periodic state information (e.g. all currently
 running processes) and real-time changes (e.g. when a new process starts
 or stops).
 
-The module is fully implemented for Linux. Some metricsets are also available
+The module is fully implemented for Linux. Some datasets are also available
 for macOS (Darwin) and Windows.
 
 [float]
 === How it works
 
-Each metricset sends two kinds of information: state and events.
+Each dataset sends two kinds of information: state and events.
 
-State information is sent periodically and on startup (for some metricsets).
+State information is sent periodically and (for some datasets) on startup.
 A state update will consist of one event per object that is currently
 active on the system (e.g. a process). All events belonging to the same state
 update will share the same UUID in `event.id`.
 
-The frequency of state updates can be controlled for all metricsets using the
-`state.period` configuration option. Overrides are available per metricset.
+The frequency of state updates can be controlled for all datasets using the
+`state.period` configuration option. Overrides are available per dataset.
 The default is `12h`.
 
 Event information is sent as the events occur (e.g. a process starts or stops).
-All metricsets are currently using a poll model to retrieve their data.
-The frequency of these polls is controlled using the `period` configuration
+All datasets are currently using a poll model to retrieve their data.
+The frequency of these polls is controlled by the `period` configuration
 parameter.
 
 [float]
@@ -43,13 +43,13 @@ This module has some configuration options for controlling its behavior. The
 following example shows all configuration options with their default values for
 Linux.
 
-NOTE: It is recommended to configure some metricsets separately. See below for a
+NOTE: It is recommended to configure some datasets separately. See below for a
 sample suggested configuration.
 
 [source,yaml]
 ----
 - module: system
-  metricsets:
+  datasets:
     - host
     - process
     - socket
@@ -59,13 +59,13 @@ sample suggested configuration.
   user.detect_password_changes: true
 ----
 
-*`period`*:: The frequency at which the metricsets check for changes. For most
-metricsets - esp. `process` and `socket` - a shorter period is recommended.
+*`period`*:: The frequency at which the datasets check for changes. For most
+datasets - esp. `process` and `socket` - a shorter period is recommended.
 
-*`state.period`*:: The frequency at which the metricsets send full state information.
-This option can be overridden per metricset using `{metricset}.state.period`.
+*`state.period`*:: The frequency at which the datasets send full state information.
+This option can be overridden per dataset using `{dataset}.state.period`.
 
-*`user.detect_password_changes`*:: If the `user` metricset is configured and
+*`user.detect_password_changes`*:: If the `user` dataset is configured and
 this option is set to `true`, Auditbeat will read password information in `/etc/passwd`
 and `/etc/shadow` to detect password changes. A hash will be kept locally in
 the `beat.db` file to detect changes between Auditbeat restarts. The `beat.db` file
@@ -84,13 +84,14 @@ so a longer polling interval can be used.
 [source,yaml]
 ----
 - module: system
-  metricsets:
+  datasets:
     - host
     - user
   period: 1m
   user.detect_password_changes: true
 
 - module: system
+  datasets:
     - process
     - socket
   period: 1s
@@ -126,17 +127,17 @@ auditbeat.modules:
 ----
 
 [float]
-=== Metricsets
+=== Datasets
 
-The following metricsets are available:
+The following datasets are available:
 
-* <<{beatname_lc}-metricset-system-host,host>>
+* <<{beatname_lc}-dataset-system-host,host>>
 
-* <<{beatname_lc}-metricset-system-process,process>>
+* <<{beatname_lc}-dataset-system-process,process>>
 
-* <<{beatname_lc}-metricset-system-socket,socket>>
+* <<{beatname_lc}-dataset-system-socket,socket>>
 
-* <<{beatname_lc}-metricset-system-user,user>>
+* <<{beatname_lc}-dataset-system-user,user>>
 
 include::system/host.asciidoc[]
 

x-pack/auditbeat/docs/modules/system/host.asciidoc

@@ -2,18 +2,18 @@
 This file is generated! See scripts/docs_collector.py
 ////
 
-[id="{beatname_lc}-metricset-system-host"]
-=== System host metricset
+[id="{beatname_lc}-dataset-system-host"]
+=== System host dataset
 
 include::../../../module/system/host/_meta/docs.asciidoc[]
 
 
 ==== Fields
 
-For a description of each field in the metricset, see the
+For a description of each field in the dataset, see the
 <<exported-fields-system,exported fields>> section.
 
-Here is an example document generated by this metricset:
+Here is an example document generated by this dataset:
 
 [source,json]
 ----

x-pack/auditbeat/docs/modules/system/process.asciidoc

@@ -2,18 +2,18 @@
 This file is generated! See scripts/docs_collector.py
 ////
 
-[id="{beatname_lc}-metricset-system-process"]
-=== System process metricset
+[id="{beatname_lc}-dataset-system-process"]
+=== System process dataset
 
 include::../../../module/system/process/_meta/docs.asciidoc[]
 
 
 ==== Fields
 
-For a description of each field in the metricset, see the
+For a description of each field in the dataset, see the
 <<exported-fields-system,exported fields>> section.
 
-Here is an example document generated by this metricset:
+Here is an example document generated by this dataset:
 
 [source,json]
 ----

x-pack/auditbeat/docs/modules/system/socket.asciidoc

@@ -2,18 +2,18 @@
 This file is generated! See scripts/docs_collector.py
 ////
 
-[id="{beatname_lc}-metricset-system-socket"]
-=== System socket metricset
+[id="{beatname_lc}-dataset-system-socket"]
+=== System socket dataset
 
 include::../../../module/system/socket/_meta/docs.asciidoc[]
 
 
 ==== Fields
 
-For a description of each field in the metricset, see the
+For a description of each field in the dataset, see the
 <<exported-fields-system,exported fields>> section.
 
-Here is an example document generated by this metricset:
+Here is an example document generated by this dataset:
 
 [source,json]
 ----

x-pack/auditbeat/docs/modules/system/user.asciidoc

@@ -2,18 +2,18 @@
 This file is generated! See scripts/docs_collector.py
 ////
 
-[id="{beatname_lc}-metricset-system-user"]
-=== System user metricset
+[id="{beatname_lc}-dataset-system-user"]
+=== System user dataset
 
 include::../../../module/system/user/_meta/docs.asciidoc[]
 
 
 ==== Fields
 
-For a description of each field in the metricset, see the
+For a description of each field in the dataset, see the
 <<exported-fields-system,exported fields>> section.
 
-Here is an example document generated by this metricset:
+Here is an example document generated by this dataset:
 
 [source,json]
 ----