Skip to content

Fix read option name for change data feed for Delta [databricks] #13532

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.

Sign up for GitHub

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

Merged
jihoonson merged 4 commits into from
Oct 2, 2025
Merged

Fix read option name for change data feed for Delta [databricks] #13532

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
8a08a74
Fix readChangeFeed option name and add asserts for the valid schema
jihoonson Sep 29, 2025
22ce95f
missing option name change
jihoonson Sep 29, 2025
8c79a0c
use read_delta_path_with_cdf
jihoonson Sep 29, 2025
903d3f0
xfail some low shuffle merge tests with cdf on databricks
jihoonson Sep 30, 2025
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
11 changes: 8 additions & 3 deletions integration_tests/src/main/python/delta_lake_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -184,9 +184,14 @@ def read_delta_path(spark, path):
return spark.read.format("delta").load(path)

def read_delta_path_with_cdf(spark, path):
return spark.read.format("delta") \
.option("readChangeDataFeed", "true").option("startingVersion", 0) \
.load(path).drop("_commit_timestamp")
df = spark.read.format("delta") \
.option("readChangeFeed", "true").option("startingVersion", 0) \
.load(path)
assert "_change_type" in df.columns
assert "_commit_version" in df.columns
assert "_commit_timestamp" in df.columns
# Drop the commit timestamp column since it will differ between CPU and GPU
return df.drop("_commit_timestamp")

def schema_to_ddl(spark, schema):
return spark.sparkContext._jvm.org.apache.spark.sql.types.DataType.fromJson(schema.json()).toDDL()
Expand Down
24 changes: 4 additions & 20 deletions integration_tests/src/main/python/delta_lake_write_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -487,23 +487,15 @@ def test_delta_write_round_trip_cdf_write_opt(spark_tmp_path, enable_deletion_ve
gen_df(spark, gen_list).coalesce(1).write.format("delta"), enable_deletion_vectors)
.option("delta.enableChangeDataFeed", "true")
.save(path),
lambda spark, path: spark.read.format("delta")
.option("readChangeDataFeed", "true")
.option("startingVersion", 0)
.load(path)
.drop("_commit_timestamp"),
read_delta_path_with_cdf,
data_path,
conf=confs)
assert_gpu_and_cpu_writes_are_equal_collect(
lambda spark, path: get_writer_with_deletion_vector_property_set(
gen_df(spark, gen_list).coalesce(1).write.format("delta"), enable_deletion_vectors)
.mode("overwrite")
.save(path),
lambda spark, path: spark.read.format("delta")
.option("readChangeDataFeed", "true")
.option("startingVersion", 0)
.load(path)
.drop("_commit_timestamp"),
read_delta_path_with_cdf,
data_path,
conf=confs)

Expand All @@ -528,22 +520,14 @@ def setup_tables(spark):
.mode("append")
.option("delta.enableChangeDataFeed", "true")
.save(path),
lambda spark, path: spark.read.format("delta")
.option("readChangeDataFeed", "true")
.option("startingVersion", 0)
.load(path)
.drop("_commit_timestamp"),
read_delta_path_with_cdf,
data_path,
conf=confs)
assert_gpu_and_cpu_writes_are_equal_collect(
lambda spark, path: gen_df(spark, gen_list).coalesce(1).write.format("delta")
.mode("overwrite")
.save(path),
lambda spark, path: spark.read.format("delta")
.option("readChangeDataFeed", "true")
.option("startingVersion", 0)
.load(path)
.drop("_commit_timestamp"),
read_delta_path_with_cdf,
data_path,
conf=confs)
with_cpu_session(lambda spark: assert_gpu_and_cpu_delta_logs_equivalent(spark, data_path))
Expand Down
Loading