Preprocess available time zones on Windows #2673 (#2672)

* Preprocess available time zones on Windows #241

plaso/cli/pinfo_tool.py

@@ -255,7 +255,8 @@ def _PrintAnalysisReportCounter(
     Args:
       analysis_reports_counter (collections.Counter): number of analysis
           reports per analysis plugin.
-      session_identifier (Optional[str]): session identifier.
+      session_identifier (Optional[str]): session identifier, formatted as
+          a UUID.
     """
     if not analysis_reports_counter:
       return
@@ -378,7 +379,8 @@ def _PrintEventLabelsCounter(
     Args:
       event_labels_counter (collections.Counter): number of event tags per
           label.
-      session_identifier (Optional[str]): session identifier.
+      session_identifier (Optional[str]): session identifier, formatted as
+          a UUID.
     """
     if not event_labels_counter:
       return
@@ -410,7 +412,8 @@ def _PrintParsersCounter(self, parsers_counter, session_identifier=None):
     Args:
       parsers_counter (collections.Counter): number of events per parser or
           parser plugin.
-      session_identifier (Optional[str]): session identifier.
+      session_identifier (Optional[str]): session identifier, formatted as
+          a UUID.
     """
     if not parsers_counter:
       self._output_writer.Write('No events stored.\n\n')
@@ -433,24 +436,34 @@ def _PrintParsersCounter(self, parsers_counter, session_identifier=None):
 
     table_view.Write(self._output_writer)
 
-  def _PrintPreprocessingInformation(self, storage_reader, session_number=None):
+  def _PrintPreprocessingInformation(
+      self, storage_reader, session_identifier=None):
     """Prints the details of the preprocessing information.
 
     Args:
       storage_reader (StorageReader): storage reader.
-      session_number (Optional[int]): session number.
+      session_identifier (Optional[str]): session identifier, formatted as
+          a UUID.
     """
     knowledge_base_object = knowledge_base.KnowledgeBase()
 
     storage_reader.ReadPreprocessingInformation(knowledge_base_object)
 
-    # TODO: replace session_number by session_identifier.
+    lookup_identifier = session_identifier
+    if lookup_identifier:
+      # The knowledge base requires the session identifier to be formatted in
+      # hexadecimal representation.
+      lookup_identifier = lookup_identifier.replace('-', '')
+
     system_configuration = knowledge_base_object.GetSystemConfigurationArtifact(
-        session_identifier=session_number)
+        session_identifier=lookup_identifier)
     if not system_configuration:
       return
 
     title = 'System configuration'
+    if session_identifier:
+      title = '{0:s}: {1:s}'.format(title, session_identifier)
+
     table_view = views.ViewsFactory.GetTableView(
         self._views_format_type, title=title)
 
@@ -477,7 +490,23 @@ def _PrintPreprocessingInformation(self, storage_reader, session_number=None):
 
     table_view.Write(self._output_writer)
 
+    title = 'Available time zones'
+    if session_identifier:
+      title = '{0:s}: {1:s}'.format(title, session_identifier)
+
+    table_view = views.ViewsFactory.GetTableView(
+        self._views_format_type,
+        column_names=['Name', ''], title=title)
+
+    for time_zone in system_configuration.available_time_zones:
+      table_view.AddRow([time_zone.name, ''])
+
+    table_view.Write(self._output_writer)
+
     title = 'User accounts'
+    if session_identifier:
+      title = '{0:s}: {1:s}'.format(title, session_identifier)
+
     table_view = views.ViewsFactory.GetTableView(
         self._views_format_type,
         column_names=['Username', 'User directory'], title=title)
@@ -494,7 +523,7 @@ def _PrintSessionsDetails(self, storage_reader):
     Args:
       storage_reader (BaseStore): storage.
     """
-    for session_number, session in enumerate(storage_reader.GetSessions()):
+    for session in storage_reader.GetSessions():
       session_identifier = uuid.UUID(hex=session.identifier)
       session_identifier = '{0!s}'.format(session_identifier)
 
@@ -545,7 +574,8 @@ def _PrintSessionsDetails(self, storage_reader):
       table_view.Write(self._output_writer)
 
       if self._verbose:
-        self._PrintPreprocessingInformation(storage_reader, session_number + 1)
+        self._PrintPreprocessingInformation(
+            storage_reader, session_identifier=session_identifier)
 
         self._PrintParsersCounter(
             session.parsers_counter, session_identifier=session_identifier)

plaso/containers/artifacts.py

@@ -46,8 +46,7 @@ class HostnameArtifact(ArtifactAttributeContainer):
 
   Also see:
     https://en.wikipedia.org/wiki/Hostname
-    http://cybox.mitre.org/language/version2.1/xsddocs/objects/
-    Hostname_Object.html
+    Cybox / Stix Hostname Object
 
   Attributes:
     name (str): name of the host according to the naming schema.
@@ -226,6 +225,7 @@ class SystemConfigurationArtifact(ArtifactAttributeContainer):
   system installation e.g. Windows or Linux.
 
   Attributes:
+    available_time_zones (list[TimeZone]): available time zones.
     code_page (str): system code page.
     hostname (HostnameArtifact): hostname.
     keyboard_layout (str): keyboard layout.
@@ -247,6 +247,7 @@ def __init__(self, code_page=None, time_zone=None):
       time_zone (Optional[str]): system time zone.
     """
     super(SystemConfigurationArtifact, self).__init__()
+    self.available_time_zones = []
     self.code_page = code_page
     self.hostname = None
     self.keyboard_layout = None
@@ -257,12 +258,30 @@ def __init__(self, code_page=None, time_zone=None):
     self.user_accounts = []
 
 
+class TimeZoneArtifact(ArtifactAttributeContainer):
+  """Time zone artifact attribute container.
+
+  Attributes:
+    name (str): name describing the time zone e.g. Greenwich Standard Time.
+  """
+  CONTAINER_TYPE = 'time_zone'
+
+  def __init__(self, name=None):
+    """Initializes a time zone artifact.
+
+    Args:
+      name (Optional[str]): name describing the time zone e.g. Greenwich
+          Standard Time.
+    """
+    super(TimeZoneArtifact, self).__init__()
+    self.name = name
+
+
 class UserAccountArtifact(ArtifactAttributeContainer):
   """User account artifact attribute container.
 
   Also see:
-    http://cybox.mitre.org/language/version2.1/xsddocs/objects/
-    User_Account_Object.html
+    Cybox / Stix User Account Object
 
   Attributes:
     full_name (str): name describing the user e.g. full name.
@@ -276,7 +295,7 @@ class UserAccountArtifact(ArtifactAttributeContainer):
   def __init__(
       self, full_name=None, group_identifier=None, identifier=None,
       path_separator='/', user_directory=None, username=None):
-    """Initializes an user artifact.
+    """Initializes a user account artifact.
 
     Args:
       full_name (Optional[str]): name describing the user e.g. full name.
@@ -311,4 +330,4 @@ def GetUserDirectoryPathSegments(self):
 
 manager.AttributeContainersManager.RegisterAttributeContainers([
     EnvironmentVariableArtifact, HostnameArtifact, SystemConfigurationArtifact,
-    UserAccountArtifact])
+    TimeZoneArtifact, UserAccountArtifact])

plaso/engine/knowledge_base.py

@@ -27,13 +27,19 @@ class KnowledgeBase(object):
   def __init__(self):
     """Initializes a knowledge base."""
     super(KnowledgeBase, self).__init__()
+    self._available_time_zones = {}
     self._codepage = 'cp1252'
     self._environment_variables = {}
     self._hostnames = {}
     self._time_zone = pytz.UTC
     self._user_accounts = {}
     self._values = {}
 
+  @property
+  def available_time_zones(self):
+    """list[TimeZone]: available time zones of the current session."""
+    return self._available_time_zones.get(self.CURRENT_SESSION, {}).values()
+
   @property
   def codepage(self):
     """str: codepage of the current session."""
@@ -63,6 +69,26 @@ def year(self):
     """int: year of the current session."""
     return self.GetValue('year', default_value=0)
 
+  def AddAvailableTimeZone(self, time_zone, session_identifier=CURRENT_SESSION):
+    """Adds an available time zone.
+
+    Args:
+      time_zone (TimeZoneArtifact): time zone artifact.
+      session_identifier (Optional[str])): session identifier, where
+          CURRENT_SESSION represents the active session.
+
+    Raises:
+      KeyError: if the time zone already exists.
+    """
+    if session_identifier not in self._available_time_zones:
+      self._available_time_zones[session_identifier] = {}
+
+    available_time_zones = self._available_time_zones[session_identifier]
+    if time_zone.name in available_time_zones:
+      raise KeyError('Time zone: {0:s} already exists.'.format(time_zone.name))
+
+    available_time_zones[time_zone.name] = time_zone
+
   def AddUserAccount(self, user_account, session_identifier=CURRENT_SESSION):
     """Adds an user account.
 
@@ -187,6 +213,13 @@ def GetSystemConfigurationArtifact(self, session_identifier=CURRENT_SESSION):
 
     system_configuration.time_zone = time_zone
 
+    available_time_zones = self._available_time_zones.get(
+        session_identifier, {})
+    # In Python 3 dict.values() returns a type dict_values, which will cause
+    # the JSON serializer to raise a TypeError.
+    system_configuration.available_time_zones = list(
+        available_time_zones.values())
+
     user_accounts = self._user_accounts.get(session_identifier, {})
     # In Python 3 dict.values() returns a type dict_values, which will cause
     # the JSON serializer to raise a TypeError.
@@ -306,8 +339,12 @@ def ReadSystemConfigurationArtifact(
             'Unsupported time zone: {0:s}, defaulting to {1:s}'.format(
                 system_configuration.time_zone, self.timezone.zone))
 
+    self._available_time_zones[session_identifier] = {
+        time_zone.name: time_zone
+        for time_zone in system_configuration.available_time_zones}
+
     self._user_accounts[session_identifier] = {
-        user_account.username: user_account
+        user_account.identifier: user_account
         for user_account in system_configuration.user_accounts}
 
   def SetCodepage(self, codepage):

plaso/preprocessors/windows.py

@@ -184,6 +184,32 @@ def Collect(self, knowledge_base):
           pass
 
 
+class WindowsAvailableTimeZonesPlugin(
+    interface.WindowsRegistryKeyArtifactPreprocessorPlugin):
+  """The Windows available time zones plugin."""
+
+  ARTIFACT_DEFINITION_NAME = 'WindowsAvailableTimeZones'
+
+  def _ParseKey(self, knowledge_base, registry_key, value_name):
+    """Parses a Windows Registry key for a preprocessing attribute.
+
+    Args:
+      knowledge_base (KnowledgeBase): to fill with preprocessing information.
+      registry_key (dfwinreg.WinRegistryKey): Windows Registry key.
+      value_name (str): name of the Windows Registry value.
+
+    Raises:
+      errors.PreProcessFail: if the preprocessing fails.
+    """
+    time_zone_artifact = artifacts.TimeZoneArtifact(name=registry_key.name)
+
+    try:
+      knowledge_base.AddAvailableTimeZone(time_zone_artifact)
+    except KeyError:
+      # TODO: add and store preprocessing errors.
+      pass
+
+
 class WindowsCodepagePlugin(
     interface.WindowsRegistryValueArtifactPreprocessorPlugin):
   """The Windows codepage plugin."""
@@ -479,6 +505,7 @@ class WindowsWinDirEnvironmentVariablePlugin(
     WindowsAllUsersAppDataKnowledgeBasePlugin,
     WindowsAllUsersProfileEnvironmentVariablePlugin,
     WindowsAllUsersAppProfileKnowledgeBasePlugin,
+    WindowsAvailableTimeZonesPlugin,
     WindowsCodepagePlugin, WindowsHostnamePlugin,
     WindowsProgramDataEnvironmentVariablePlugin,
     WindowsProgramDataKnowledgeBasePlugin,

plaso/storage/sqlite/sqlite_file.py

@@ -1085,9 +1085,10 @@ def ReadPreprocessingInformation(self, knowledge_base):
     generator = self._GetAttributeContainers(
         self._CONTAINER_TYPE_SYSTEM_CONFIGURATION)
     for stream_number, system_configuration in enumerate(generator):
-      # TODO: replace stream_number by session_identifier.
+      session_start = self._GetAttributeContainerByIndex(
+          self._CONTAINER_TYPE_SESSION_START, stream_number)
       knowledge_base.ReadSystemConfigurationArtifact(
-          system_configuration, session_identifier=stream_number)
+          system_configuration, session_identifier=session_start.identifier)
 
   def WritePreprocessingInformation(self, knowledge_base):
     """Writes preprocessing information.