You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@iceberg.apache.org by hu...@apache.org on 2026/03/12 20:54:39 UTC
(iceberg) branch main updated: Spark: Delegate temp file deletion to JUnit in TestParquetVectorizedReads (#15557)
This is an automated email from the ASF dual-hosted git repository.
huaxingao pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/iceberg.git
The following commit(s) were added to refs/heads/main by this push:
new bd54026d73 Spark: Delegate temp file deletion to JUnit in TestParquetVectorizedReads (#15557)
bd54026d73 is described below
commit bd54026d732a1eac49d0a6852036d1cd113ea65d
Author: Noritaka Sekiyama <mo...@gmail.com>
AuthorDate: Fri Mar 13 04:54:33 2026 +0800
Spark: Delegate temp file deletion to JUnit in TestParquetVectorizedReads (#15557)
* Delegate temp file deletion to JUnit in TestParquetVectorizedReads (#13506)
Replace the manual File.createTempFile + delete pattern with
temp.resolve(...).toFile() so JUnit's @TempDir handles cleanup
automatically. Applied to Spark v3.5, v4.0, and v4.1 modules.
Co-Authored-By: Claude Sonnet 4.6 <no...@anthropic.com>
* Rename junit.parquet to data.parquet per review feedback
Co-authored-by: Isaac
---------
Co-authored-by: Claude Sonnet 4.6 <no...@anthropic.com>
---
.../vectorized/parquet/TestParquetVectorizedReads.java | 15 +++++----------
.../vectorized/parquet/TestParquetVectorizedReads.java | 15 +++++----------
.../vectorized/parquet/TestParquetVectorizedReads.java | 15 +++++----------
3 files changed, 15 insertions(+), 30 deletions(-)
diff --git a/spark/v3.5/spark/src/test/java/org/apache/iceberg/spark/data/vectorized/parquet/TestParquetVectorizedReads.java b/spark/v3.5/spark/src/test/java/org/apache/iceberg/spark/data/vectorized/parquet/TestParquetVectorizedReads.java
index 2885563863..24a3603dc7 100644
--- a/spark/v3.5/spark/src/test/java/org/apache/iceberg/spark/data/vectorized/parquet/TestParquetVectorizedReads.java
+++ b/spark/v3.5/spark/src/test/java/org/apache/iceberg/spark/data/vectorized/parquet/TestParquetVectorizedReads.java
@@ -213,8 +213,7 @@ public class TestParquetVectorizedReads extends AvroDataTestBase {
Map<Integer, Object> idToConstant)
throws IOException {
// write a test parquet file using iceberg writer
- File testFile = File.createTempFile("junit", null, temp.toFile());
- assertThat(testFile.delete()).as("Delete should succeed").isTrue();
+ File testFile = temp.resolve("data.parquet").toFile();
try (FileAppender<Record> writer = getParquetWriter(writeSchema, testFile)) {
writer.addAll(expected);
@@ -390,8 +389,7 @@ public class TestParquetVectorizedReads extends AvroDataTestBase {
optional(102, "float_data", Types.FloatType.get()),
optional(103, "decimal_data", Types.DecimalType.of(10, 5)));
- File dataFile = File.createTempFile("junit", null, temp.toFile());
- assertThat(dataFile.delete()).as("Delete should succeed").isTrue();
+ File dataFile = temp.resolve("data.parquet").toFile();
Iterable<Record> data =
generateData(writeSchema, 30000, 0L, RandomData.DEFAULT_NULL_PERCENTAGE, IDENTITY);
try (FileAppender<Record> writer = getParquetWriter(writeSchema, dataFile)) {
@@ -423,8 +421,7 @@ public class TestParquetVectorizedReads extends AvroDataTestBase {
optional(107, "string_data", Types.StringType.get()),
optional(108, "binary_data", Types.BinaryType.get()));
- File dataFile = File.createTempFile("junit", null, temp.toFile());
- assertThat(dataFile.delete()).as("Delete should succeed").isTrue();
+ File dataFile = temp.resolve("data.parquet").toFile();
Iterable<Record> data =
generateData(schema, 30000, 0L, RandomData.DEFAULT_NULL_PERCENTAGE, IDENTITY);
try (FileAppender<Record> writer = getParquetV2Writer(schema, dataFile)) {
@@ -437,8 +434,7 @@ public class TestParquetVectorizedReads extends AvroDataTestBase {
public void testUnsupportedReadsForParquetV2() throws Exception {
// Some types use delta encoding and which are not supported for vectorized reads
Schema schema = new Schema(SUPPORTED_PRIMITIVES.fields());
- File dataFile = File.createTempFile("junit", null, temp.toFile());
- assertThat(dataFile.delete()).as("Delete should succeed").isTrue();
+ File dataFile = temp.resolve("data.parquet").toFile();
Iterable<Record> data =
generateData(schema, 30000, 0L, RandomData.DEFAULT_NULL_PERCENTAGE, IDENTITY);
try (FileAppender<Record> writer = getParquetV2Writer(schema, dataFile)) {
@@ -456,8 +452,7 @@ public class TestParquetVectorizedReads extends AvroDataTestBase {
int numRows = 1;
Schema schema = new Schema(optional(100, "uuid", Types.UUIDType.get()));
- File dataFile = File.createTempFile("junit", null, temp.toFile());
- assertThat(dataFile.delete()).as("Delete should succeed").isTrue();
+ File dataFile = temp.resolve("data.parquet").toFile();
Iterable<Record> data = generateData(schema, numRows, 0L, 0, IDENTITY);
try (FileAppender<Record> writer = getParquetV2Writer(schema, dataFile)) {
writer.addAll(data);
diff --git a/spark/v4.0/spark/src/test/java/org/apache/iceberg/spark/data/vectorized/parquet/TestParquetVectorizedReads.java b/spark/v4.0/spark/src/test/java/org/apache/iceberg/spark/data/vectorized/parquet/TestParquetVectorizedReads.java
index 4eabac7ab8..6011c6dad7 100644
--- a/spark/v4.0/spark/src/test/java/org/apache/iceberg/spark/data/vectorized/parquet/TestParquetVectorizedReads.java
+++ b/spark/v4.0/spark/src/test/java/org/apache/iceberg/spark/data/vectorized/parquet/TestParquetVectorizedReads.java
@@ -213,8 +213,7 @@ public class TestParquetVectorizedReads extends AvroDataTestBase {
Map<Integer, Object> idToConstant)
throws IOException {
// write a test parquet file using iceberg writer
- File testFile = File.createTempFile("junit", null, temp.toFile());
- assertThat(testFile.delete()).as("Delete should succeed").isTrue();
+ File testFile = temp.resolve("data.parquet").toFile();
try (FileAppender<Record> writer = getParquetWriter(writeSchema, testFile)) {
writer.addAll(expected);
@@ -390,8 +389,7 @@ public class TestParquetVectorizedReads extends AvroDataTestBase {
optional(102, "float_data", Types.FloatType.get()),
optional(103, "decimal_data", Types.DecimalType.of(10, 5)));
- File dataFile = File.createTempFile("junit", null, temp.toFile());
- assertThat(dataFile.delete()).as("Delete should succeed").isTrue();
+ File dataFile = temp.resolve("data.parquet").toFile();
Iterable<Record> data =
generateData(writeSchema, 30000, 0L, RandomData.DEFAULT_NULL_PERCENTAGE, IDENTITY);
try (FileAppender<Record> writer = getParquetWriter(writeSchema, dataFile)) {
@@ -423,8 +421,7 @@ public class TestParquetVectorizedReads extends AvroDataTestBase {
optional(107, "string_data", Types.StringType.get()),
optional(108, "binary_data", Types.BinaryType.get()));
- File dataFile = File.createTempFile("junit", null, temp.toFile());
- assertThat(dataFile.delete()).as("Delete should succeed").isTrue();
+ File dataFile = temp.resolve("data.parquet").toFile();
Iterable<Record> data =
generateData(schema, 30000, 0L, RandomData.DEFAULT_NULL_PERCENTAGE, IDENTITY);
try (FileAppender<Record> writer = getParquetV2Writer(schema, dataFile)) {
@@ -437,8 +434,7 @@ public class TestParquetVectorizedReads extends AvroDataTestBase {
public void testUnsupportedReadsForParquetV2() throws Exception {
// Some types use delta encoding and which are not supported for vectorized reads
Schema schema = new Schema(SUPPORTED_PRIMITIVES.fields());
- File dataFile = File.createTempFile("junit", null, temp.toFile());
- assertThat(dataFile.delete()).as("Delete should succeed").isTrue();
+ File dataFile = temp.resolve("data.parquet").toFile();
Iterable<Record> data =
generateData(schema, 30000, 0L, RandomData.DEFAULT_NULL_PERCENTAGE, IDENTITY);
try (FileAppender<Record> writer = getParquetV2Writer(schema, dataFile)) {
@@ -456,8 +452,7 @@ public class TestParquetVectorizedReads extends AvroDataTestBase {
int numRows = 1;
Schema schema = new Schema(optional(100, "uuid", Types.UUIDType.get()));
- File dataFile = File.createTempFile("junit", null, temp.toFile());
- assertThat(dataFile.delete()).as("Delete should succeed").isTrue();
+ File dataFile = temp.resolve("data.parquet").toFile();
Iterable<Record> data = generateData(schema, numRows, 0L, 0, IDENTITY);
try (FileAppender<Record> writer = getParquetV2Writer(schema, dataFile)) {
writer.addAll(data);
diff --git a/spark/v4.1/spark/src/test/java/org/apache/iceberg/spark/data/vectorized/parquet/TestParquetVectorizedReads.java b/spark/v4.1/spark/src/test/java/org/apache/iceberg/spark/data/vectorized/parquet/TestParquetVectorizedReads.java
index 4eabac7ab8..6011c6dad7 100644
--- a/spark/v4.1/spark/src/test/java/org/apache/iceberg/spark/data/vectorized/parquet/TestParquetVectorizedReads.java
+++ b/spark/v4.1/spark/src/test/java/org/apache/iceberg/spark/data/vectorized/parquet/TestParquetVectorizedReads.java
@@ -213,8 +213,7 @@ public class TestParquetVectorizedReads extends AvroDataTestBase {
Map<Integer, Object> idToConstant)
throws IOException {
// write a test parquet file using iceberg writer
- File testFile = File.createTempFile("junit", null, temp.toFile());
- assertThat(testFile.delete()).as("Delete should succeed").isTrue();
+ File testFile = temp.resolve("data.parquet").toFile();
try (FileAppender<Record> writer = getParquetWriter(writeSchema, testFile)) {
writer.addAll(expected);
@@ -390,8 +389,7 @@ public class TestParquetVectorizedReads extends AvroDataTestBase {
optional(102, "float_data", Types.FloatType.get()),
optional(103, "decimal_data", Types.DecimalType.of(10, 5)));
- File dataFile = File.createTempFile("junit", null, temp.toFile());
- assertThat(dataFile.delete()).as("Delete should succeed").isTrue();
+ File dataFile = temp.resolve("data.parquet").toFile();
Iterable<Record> data =
generateData(writeSchema, 30000, 0L, RandomData.DEFAULT_NULL_PERCENTAGE, IDENTITY);
try (FileAppender<Record> writer = getParquetWriter(writeSchema, dataFile)) {
@@ -423,8 +421,7 @@ public class TestParquetVectorizedReads extends AvroDataTestBase {
optional(107, "string_data", Types.StringType.get()),
optional(108, "binary_data", Types.BinaryType.get()));
- File dataFile = File.createTempFile("junit", null, temp.toFile());
- assertThat(dataFile.delete()).as("Delete should succeed").isTrue();
+ File dataFile = temp.resolve("data.parquet").toFile();
Iterable<Record> data =
generateData(schema, 30000, 0L, RandomData.DEFAULT_NULL_PERCENTAGE, IDENTITY);
try (FileAppender<Record> writer = getParquetV2Writer(schema, dataFile)) {
@@ -437,8 +434,7 @@ public class TestParquetVectorizedReads extends AvroDataTestBase {
public void testUnsupportedReadsForParquetV2() throws Exception {
// Some types use delta encoding and which are not supported for vectorized reads
Schema schema = new Schema(SUPPORTED_PRIMITIVES.fields());
- File dataFile = File.createTempFile("junit", null, temp.toFile());
- assertThat(dataFile.delete()).as("Delete should succeed").isTrue();
+ File dataFile = temp.resolve("data.parquet").toFile();
Iterable<Record> data =
generateData(schema, 30000, 0L, RandomData.DEFAULT_NULL_PERCENTAGE, IDENTITY);
try (FileAppender<Record> writer = getParquetV2Writer(schema, dataFile)) {
@@ -456,8 +452,7 @@ public class TestParquetVectorizedReads extends AvroDataTestBase {
int numRows = 1;
Schema schema = new Schema(optional(100, "uuid", Types.UUIDType.get()));
- File dataFile = File.createTempFile("junit", null, temp.toFile());
- assertThat(dataFile.delete()).as("Delete should succeed").isTrue();
+ File dataFile = temp.resolve("data.parquet").toFile();
Iterable<Record> data = generateData(schema, numRows, 0L, 0, IDENTITY);
try (FileAppender<Record> writer = getParquetV2Writer(schema, dataFile)) {
writer.addAll(data);