Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix(ingest/snowflake): use fast query fingerprint for lineage #12275

Merged
merged 2 commits into from
Jan 6, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,7 @@
ColumnRef,
DownstreamColumnRef,
)
from datahub.sql_parsing.sqlglot_utils import get_query_fingerprint
from datahub.utilities.perf_timer import PerfTimer
from datahub.utilities.time import ts_millis_to_datetime

Expand Down Expand Up @@ -239,6 +240,9 @@ def get_known_query_lineage(
downstream_table_urn = self.identifiers.gen_dataset_urn(dataset_name)

known_lineage = KnownQueryLineageInfo(
query_id=get_query_fingerprint(
query.query_text, self.identifiers.platform, fast=True
),
query_text=query.query_text,
downstream=downstream_table_urn,
upstreams=self.map_query_result_upstreams(
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -165,6 +165,7 @@ class KnownQueryLineageInfo:
timestamp: Optional[datetime] = None
session_id: Optional[str] = None
query_type: QueryType = QueryType.UNKNOWN
query_id: Optional[str] = None


@dataclasses.dataclass
Expand Down Expand Up @@ -618,11 +619,13 @@ def add_known_query_lineage(
self.report.num_known_query_lineage += 1

# Generate a fingerprint for the query.
with self.report.sql_fingerprinting_timer:
query_fingerprint = get_query_fingerprint(
known_query_lineage.query_text,
platform=self.platform.platform_name,
)
query_fingerprint = known_query_lineage.query_id
if not query_fingerprint:
with self.report.sql_fingerprinting_timer:
query_fingerprint = get_query_fingerprint(
known_query_lineage.query_text,
platform=self.platform.platform_name,
)
formatted_query = self._maybe_format_query(known_query_lineage.query_text)

# Register the query.
Expand Down
Loading