Fix some nits

Author: tomchop

dftimewolf/cli/recipes/gcp_turbinia.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 """Process a GCP persistent disk with Turbinia and send output to Timesketch.
 
-This processes a disk that is already in the project where Turbinia exists.  If
+This processes a disk that is already in the project where Turbinia exists. If
 you want to copy the disk from another project, use the gcp_turbinia_import
 recipe.
 """

dftimewolf/cli/recipes/gcp_turbinia_import.py

@@ -2,16 +2,16 @@
 """Imports a remote GCP persistent disk and sends to Turbinia and Timesketch.
 
 This copies a disk from a remote GCP project and sends to Turbinia for
-processing and then sends those results to Timesketch.  It will also start an
-analysis VM with the attached disk.  If you want to process a disk already in
+processing and then sends those results to Timesketch. It will also start an
+analysis VM with the attached disk. If you want to process a disk already in
 the same project as Turbinia you can use the gcp_turbinia recipe.
 """
 
 from __future__ import unicode_literals
 from datetime import datetime
 
-_short_description = ('Imports a remote GCP persistent disk and sends to '
-                      'Turbinia and Timesketch.')
+_short_description = ('Imports a remote GCP persistent disk, processes it with '
+                      'Turbinia and sends results to Timesketch.')
 
 contents = {
     'name': 'gcp_turbinia_import',
@@ -31,7 +31,7 @@
     }, {
         'name': 'TurbiniaProcessor',
         'args': {
-            'disk_name': None,
+            'disk_name': None,  # Taken from GoogleCloudCollector's output
             'project': '@analysis_project_name',
             'zone': '@zone',
         },
@@ -50,7 +50,6 @@
 args = [
     ('remote_project_name',
      'Name of the project containing the instance / disks to copy ', None),
-
     ('--zone', 'The GCP zone the disk to process (and Turbinia workers) are in',
      None),
     ('--incident_id', 'Incident ID (used for Timesketch description)',
@@ -63,6 +62,6 @@
     ('--all_disks', 'Copy all disks in the designated instance. '
                     'Overrides disk_names if specified', False),
     ('--analysis_project_name', 'Name of the project where the analysis VM will'
-                                ' be created', 'turbinia-external-test'),
+                                ' be created', None),
     ('--boot_disk_size', 'The size of the analysis VM boot disk (in GB)', 50.0),
 ]

dftimewolf/lib/collectors/gcloud.py

@@ -112,6 +112,7 @@ def setup(self,
         zone)
 
     try:
+      # TODO: Make creating an analysis VM optional
       self.analysis_vm, _ = libcloudforensics.start_analysis_vm(
           self.analysis_project.project_id, analysis_vm_name, zone,
           boot_disk_size)

dftimewolf/lib/processors/turbinia.py

@@ -2,6 +2,7 @@
 """Processes cloud artifacts using a remote Turbinia instance."""
 from __future__ import unicode_literals
 from __future__ import absolute_import
+from __future__ import print_function
 
 import os
 import tempfile
@@ -17,7 +18,7 @@
 
 
 class TurbiniaProcessor(BaseModule):
-  """Process cloud disks with remote Turbinia instance.
+  """Process cloud disks with a remote Turbinia instance.
 
   Attributes:
     client: A TurbiniaClient object
@@ -52,6 +53,8 @@ def setup(self, disk_name, project, zone):  # pylint: disable=arguments-differ
       project: The project containing the disk to process
       zone: The zone containing the disk to process
     """
+    # TODO: Consider the case when multiple disks are provided by the previous
+    # module or by the CLI.
     if self.state.input and not disk_name:
       _, disk = self.state.input[0]
       disk_name = disk.name
@@ -81,6 +84,7 @@ def setup(self, disk_name, project, zone):  # pylint: disable=arguments-differ
       self.client = turbinia_client.TurbiniaClient()
     except TurbiniaException as e:
       self.state.add_error(e, critical=True)
+      return
 
   def cleanup(self):
     pass
@@ -107,9 +111,9 @@ def process(self):
       task_data = self.client.get_task_data(
           instance=self.instance, project=self.project, region=self.region,
           request_id=request.request_id)
-      print self.client.format_task_status(
+      print(self.client.format_task_status(
           instance=self.instance, project=self.project, region=self.region,
-          request_id=request.request_id, all_fields=True)
+          request_id=request.request_id, all_fields=True))
     except TurbiniaException as e:
       self.state.add_error(e, critical=True)
       return
@@ -138,6 +142,7 @@ def process(self):
 
     # For files remote in GCS we copy each plaso file back from GCS and then add
     # to output paths
+    # TODO: Externalize fetching files from GCS buckets to a different module.
     for path in gs_paths:
       local_path = None
       try: