def _user_search_query(graph: GraphTraversalSource,
tag_filter: str) -> List[Dict]:
traversal = graph.V().hasLabel(User.USER_NODE_LABEL)
traversal = traversal.has(User.USER_NODE_FULL_NAME)
if tag_filter:
traversal = traversal.where('published_tag', tag_filter)
traversal = traversal.project('email', 'first_name', 'last_name',
'full_name', 'github_username', 'team_name',
'employee_type', 'manager_email', 'slack_id',
'is_active', 'role_name', 'total_read',
'total_own', 'total_follow')
traversal = traversal.by('email') # email
traversal = traversal.by('first_name') # first_name
traversal = traversal.by('last_name') # last_name
traversal = traversal.by('full_name') # full_name
traversal = traversal.by('github_username') # github_username
traversal = traversal.by('team_name') # team_name
traversal = traversal.by('employee_type') # employee_type
traversal = traversal.by(
__.coalesce(
__.out(User.USER_MANAGER_RELATION_TYPE).values('email'),
__.constant(''))) # manager_email
traversal = traversal.by('slack_id') # slack_id
traversal = traversal.by('is_active') # is_active
traversal = traversal.by('role_name') # role_name
traversal = traversal.by(
__.coalesce(
__.outE(READ_RELATION_TYPE).values('read_count'),
__.constant(0)).sum()) # total_read
traversal = traversal.by(
__.outE(OWNER_OF_OBJECT_RELATION_TYPE).fold().count()) # total_own
traversal = traversal.by(
__.outE('FOLLOWED_BY').fold().count()) # total_follow
traversal = traversal.order().by(__.select('email'), Order.asc)
return traversal.toList()
def _table_search_query(graph: GraphTraversalSource,
tag_filter: str) -> List[Dict]:
traversal = graph.V().hasLabel(TableMetadata.TABLE_NODE_LABEL)
if tag_filter:
traversal = traversal.has('published_tag', tag_filter)
traversal = traversal.project('database', 'cluster', 'schema',
'schema_description', 'name', 'key',
'description', 'last_updated_timestamp',
'column_names', 'column_descriptions',
'total_usage', 'unique_usage', 'tags',
'badges', 'programmatic_descriptions')
traversal = traversal.by(
__.out(TableMetadata.TABLE_SCHEMA_RELATION_TYPE).out(
SCHEMA_REVERSE_RELATION_TYPE).out(
CLUSTER_REVERSE_RELATION_TYPE).values('name')) # database
traversal = traversal.by(
__.out(TableMetadata.TABLE_SCHEMA_RELATION_TYPE).out(
SCHEMA_REVERSE_RELATION_TYPE).values('name')) # cluster
traversal = traversal.by(
__.out(
TableMetadata.TABLE_SCHEMA_RELATION_TYPE).values('name')) # schema
traversal = traversal.by(
__.coalesce(
__.out(TableMetadata.TABLE_SCHEMA_RELATION_TYPE).out(
DescriptionMetadata.DESCRIPTION_RELATION_TYPE).values(
'description'), __.constant(''))) # schema_description
traversal = traversal.by('name') # name
traversal = traversal.by(T.id) # key
traversal = traversal.by(
__.coalesce(
__.out(DescriptionMetadata.DESCRIPTION_RELATION_TYPE).values(
'description'), __.constant(''))) # description
traversal = traversal.by(
__.coalesce(
__.out(LASTUPDATED_RELATION_TYPE).values(TIMESTAMP_PROPERTY),
__.constant(''))) # last_updated_timestamp
traversal = traversal.by(
__.out(TableMetadata.TABLE_COL_RELATION_TYPE).values(
'name').fold()) # column_names
traversal = traversal.by(
__.out(TableMetadata.TABLE_COL_RELATION_TYPE).out(
DescriptionMetadata.DESCRIPTION_RELATION_TYPE).values(
'description').fold()) # column_descriptions
traversal = traversal.by(
__.coalesce(
__.outE(READ_REVERSE_RELATION_TYPE).values('read_count'),
__.constant(0)).sum()) # total_usage
traversal = traversal.by(
__.outE(READ_REVERSE_RELATION_TYPE).count()) # unique_usage
traversal = traversal.by(
__.inE(TableMetadata.TAG_TABLE_RELATION_TYPE).outV().values(
METADATA_KEY_PROPERTY_NAME).fold()) # tags
traversal = traversal.by(
__.out('HAS_BADGE').values('keys').dedup().fold()) # badges
traversal = traversal.by(
__.out(DescriptionMetadata.PROGRAMMATIC_DESCRIPTION_NODE_LABEL).values(
'description').fold()) # programmatic_descriptions
traversal = traversal.order().by(__.select('name'), Order.asc)
return traversal.toList()
def handle_youtube_video_added(self, video_id, user_id, name, description, location, preview_image_location,
tags, added_date, timestamp):
# make sure tags are unique (no duplicates)
unique_tags = set(tags)
logging.debug('SuggestedVideosService:handle_youtube_video_added, video ID: ' + str(video_id) +
', user ID: ' + str(user_id) + ', name: ' + name + ', description: ' + description +
', location: ' + location + ', preview_image_location: ' + preview_image_location +
', tags: ' + str(unique_tags) + ', timestamp: ' + str(timestamp))
# Note: building a single traversal, but broken into several steps for readability
# locate user vertex
traversal = self.graph.V().has('user', 'userId', user_id).as_('^user')
# add video vertex
traversal = traversal.addV('video').property('videoId', video_id)\
.property('added_date', added_date) \
.property('description', description) \
.property('name', name) \
.property('preview_image_location', preview_image_location) \
.as_('^video')
# add edge from user to video vertex
traversal = traversal.addE('uploaded').from_('^user').to('^video').property('added_date', added_date)
# find vertices for tags and add edges from video vertex
for tag in unique_tags:
traversal = traversal.addE('taggedWith').from_('^video').to(__.coalesce(
__.V().has('tag', 'name', tag),
__.addV('tag').property('name', tag).property('tagged_date', added_date)))
# execute the traversal
traversal.iterate()
def _dashboard_search_query(graph: GraphTraversalSource,
tag_filter: str) -> List[Dict]:
traversal = graph.V().hasLabel(DashboardMetadata.DASHBOARD_NODE_LABEL)
traversal = traversal.has('name')
if tag_filter:
traversal = traversal.where('published_tag', tag_filter)
traversal = traversal.project('group_name', 'name', 'cluster',
'description', 'group_description',
'group_url', 'url', 'uri',
'last_successful_run_timestamp',
'query_names', 'chart_names', 'total_usage',
'tags', 'badges')
traversal = traversal.by(
__.out(
DashboardMetadata.DASHBOARD_DASHBOARD_GROUP_RELATION_TYPE).values(
'name')) # group_name
traversal = traversal.by('name') # name
traversal = traversal.by(
__.out(DashboardMetadata.DASHBOARD_DASHBOARD_GROUP_RELATION_TYPE).out(
DashboardMetadata.DASHBOARD_GROUP_CLUSTER_RELATION_TYPE).values(
'name')) # cluster
traversal = traversal.by(
__.coalesce(
__.out(
DashboardMetadata.DASHBOARD_DESCRIPTION_RELATION_TYPE).values(
'description'), __.constant(''))) # description
traversal = traversal.by(
__.coalesce(
__.out(
DashboardMetadata.DASHBOARD_DASHBOARD_GROUP_RELATION_TYPE).out(
DashboardMetadata.DASHBOARD_DESCRIPTION_RELATION_TYPE).
values('description'), __.constant(''))) # group_description
traversal = traversal.by(
__.out(
DashboardMetadata.DASHBOARD_DASHBOARD_GROUP_RELATION_TYPE).values(
'dashboard_group_url')) # group_url
traversal = traversal.by('dashboard_url') # dashboard_url
traversal = traversal.by('key') # uri
traversal = traversal.by(
__.coalesce(
__.out('EXECUTED').has(
'key', TextP.endingWith(
'_last_successful_execution')).values('timestamp'),
__.constant(''))) # last_successful_run_timestamp
traversal = traversal.by(
__.out(DashboardQuery.DASHBOARD_QUERY_RELATION_TYPE).values(
'name').dedup().fold()) # query_names
traversal = traversal.by(
__.out(DashboardQuery.DASHBOARD_QUERY_RELATION_TYPE).out(
DashboardChart.CHART_RELATION_TYPE).values(
'name').dedup().fold()) # chart_names
traversal = traversal.by(
__.coalesce(
__.outE(READ_REVERSE_RELATION_TYPE).values(
READ_RELATION_COUNT_PROPERTY),
__.constant(0)).sum()) # total_usage
traversal = traversal.by(
__.out('TAGGED_BY').has(
'tag_type', 'default').values('keys').dedup().fold()) # tags
traversal = traversal.by(
__.out('HAS_BADGE').values('keys').dedup().fold()) # badges
traversal = traversal.order().by(__.select('name'), Order.asc)
dashboards = traversal.toList()
for dashboard in dashboards:
dashboard['product'] = dashboard['uri'].split('_')[0]
return dashboards