def __init__(self, config: SimpleDatasetTermsConfig, ctx: PipelineContext):
terms = [GlossaryTermAssociationClass(urn=term) for term in config.term_urns]
generic_config = AddDatasetTermsConfig(
get_terms_to_add=lambda _: terms,
)
super().__init__(generic_config, ctx)
def __init__(self, config: PatternDatasetTermsConfig,
ctx: PipelineContext):
term_pattern = config.term_pattern
generic_config = AddDatasetTermsConfig(get_terms_to_add=lambda _: [
GlossaryTermAssociationClass(urn=urn)
for urn in term_pattern.value(_.urn)
], )
super().__init__(generic_config, ctx)
def make_glossary_terms_aspect_from_urn_list(
term_urns: List[str]) -> GlossaryTerms:
for term_urn in term_urns:
assert term_urn.startswith("urn:li:glossaryTerm:")
glossary_terms = GlossaryTerms(
[GlossaryTermAssociationClass(term_urn) for term_urn in term_urns],
AuditStampClass(
time=int(time.time() * 1000),
actor="urn:li:corpuser:datahub",
),
)
return glossary_terms
ChangeTypeClass,
GlossaryTermAssociationClass,
GlossaryTermsClass,
)
log = logging.getLogger(__name__)
logging.basicConfig(level=logging.INFO)
# First we get the current terms
gms_endpoint = "http://localhost:8080"
rest_emitter = DatahubRestEmitter(gms_server=gms_endpoint)
dataset_urn = make_dataset_urn(platform="hive", name="realestate_db.sales", env="PROD")
term_to_add = make_term_urn("Classification.HighlyConfidential")
term_association_to_add = GlossaryTermAssociationClass(urn=term_to_add)
# an audit stamp that basically says we have no idea when these terms were added to this dataset
# change the time value to (time.time() * 1000) if you want to specify the current time of running this code as the time of the application
unknown_audit_stamp = AuditStampClass(time=0, actor="urn:li:corpuser:ingestion")
# create a brand new terms aspect
terms_aspect = GlossaryTermsClass(
terms=[term_association_to_add],
auditStamp=unknown_audit_stamp,
)
event: MetadataChangeProposalWrapper = MetadataChangeProposalWrapper(
entityType="dataset",
changeType=ChangeTypeClass.UPSERT,
entityUrn=dataset_urn,
aspectName="glossaryTerms",
nativeDataType=
"VARCHAR(100)", # use this to provide the type of the field in the source system's vernacular
jsonPath="", # Unused field, can omit
nullable=True,
description=
"This is the zipcode of the address. Specified using extended form and limited to addresses in the United States",
recursive=False, # Unused field, can omit
# It is rare to attach tags to fields as part of the technical schema unless you are purely reflecting state that exists in the source system.
# For an editable (in UI) version of this, use the editableSchemaMetadata aspect
globalTags=GlobalTagsClass(
tags=[TagAssociationClass(tag=make_tag_urn("location"))]),
# It is rare to attach glossary terms to fields as part of the technical schema unless you are purely reflecting state that exists in the source system.
# For an editable (in UI) version of this, use the editableSchemaMetadata aspect
glossaryTerms=GlossaryTermsClass(
terms=[
GlossaryTermAssociationClass(
urn=make_term_urn("Classification.PII"))
],
auditStamp=
AuditStampClass( # represents the time when this term was attached to this field?
time=
0, # time in milliseconds, leave as 0 if no time of association is known
actor=
"urn:li:corpuser:ingestion", # if this is a system provided tag, use a bot user id like ingestion
),
),
)
],
),
)
# Create rest emitter