1
0

[HUDI-508] Standardizing on "Table" instead of "Dataset" across code (#1197)

- Docs were talking about storage types before, cWiki moved to "Table"
 - Most of code already has HoodieTable, HoodieTableMetaClient - correct naming
 - Replacing renaming use of dataset across code/comments
 - Few usages in comments and use of Spark SQL DataSet remain unscathed
This commit is contained in:
vinoth chandar
2020-01-07 12:52:32 -08:00
committed by GitHub
parent 8306f749a2
commit 9706f659db
73 changed files with 298 additions and 298 deletions

View File

@@ -45,7 +45,7 @@ public class InputFormatTestUtil {
private static String TEST_WRITE_TOKEN = "1-0-1";
public static File prepareDataset(TemporaryFolder basePath, int numberOfFiles, String commitNumber)
public static File prepareTable(TemporaryFolder basePath, int numberOfFiles, String commitNumber)
throws IOException {
basePath.create();
HoodieTestUtils.init(HoodieTestUtils.getDefaultHadoopConf(), basePath.getRoot().toString());
@@ -105,7 +105,7 @@ public class InputFormatTestUtil {
return new Schema.Parser().parse(InputFormatTestUtil.class.getResourceAsStream(location));
}
public static File prepareParquetDataset(TemporaryFolder basePath, Schema schema, int numberOfFiles,
public static File prepareParquetTable(TemporaryFolder basePath, Schema schema, int numberOfFiles,
int numberOfRecords, String commitNumber) throws IOException {
basePath.create();
HoodieTestUtils.init(HoodieTestUtils.getDefaultHadoopConf(), basePath.getRoot().toString());
@@ -114,7 +114,7 @@ public class InputFormatTestUtil {
return partitionPath;
}
public static File prepareSimpleParquetDataset(TemporaryFolder basePath, Schema schema, int numberOfFiles,
public static File prepareSimpleParquetTable(TemporaryFolder basePath, Schema schema, int numberOfFiles,
int numberOfRecords, String commitNumber) throws Exception {
basePath.create();
HoodieTestUtils.init(HoodieTestUtils.getDefaultHadoopConf(), basePath.getRoot().toString());
@@ -123,7 +123,7 @@ public class InputFormatTestUtil {
return partitionPath;
}
public static File prepareNonPartitionedParquetDataset(TemporaryFolder baseDir, Schema schema, int numberOfFiles,
public static File prepareNonPartitionedParquetTable(TemporaryFolder baseDir, Schema schema, int numberOfFiles,
int numberOfRecords, String commitNumber) throws IOException {
baseDir.create();
HoodieTestUtils.init(HoodieTestUtils.getDefaultHadoopConf(), baseDir.getRoot().toString());

View File

@@ -56,7 +56,7 @@ public class TestHoodieInputFormat {
@Test
public void testInputFormatLoad() throws IOException {
// initial commit
File partitionDir = InputFormatTestUtil.prepareDataset(basePath, 10, "100");
File partitionDir = InputFormatTestUtil.prepareTable(basePath, 10, "100");
InputFormatTestUtil.commit(basePath, "100");
// Add the paths
@@ -72,7 +72,7 @@ public class TestHoodieInputFormat {
@Test
public void testInputFormatUpdates() throws IOException {
// initial commit
File partitionDir = InputFormatTestUtil.prepareDataset(basePath, 10, "100");
File partitionDir = InputFormatTestUtil.prepareTable(basePath, 10, "100");
InputFormatTestUtil.commit(basePath, "100");
// Add the paths
@@ -99,7 +99,7 @@ public class TestHoodieInputFormat {
@Test
public void testIncrementalSimple() throws IOException {
// initial commit
File partitionDir = InputFormatTestUtil.prepareDataset(basePath, 10, "100");
File partitionDir = InputFormatTestUtil.prepareTable(basePath, 10, "100");
InputFormatTestUtil.commit(basePath, "100");
// Add the paths
@@ -115,7 +115,7 @@ public class TestHoodieInputFormat {
@Test
public void testIncrementalWithMultipleCommits() throws IOException {
// initial commit
File partitionDir = InputFormatTestUtil.prepareDataset(basePath, 10, "100");
File partitionDir = InputFormatTestUtil.prepareTable(basePath, 10, "100");
InputFormatTestUtil.commit(basePath, "100");
// Add the paths
FileInputFormat.setInputPaths(jobConf, partitionDir.getPath());
@@ -166,7 +166,7 @@ public class TestHoodieInputFormat {
// initial commit
Schema schema = InputFormatTestUtil.readSchema("/sample1.avsc");
String commit1 = "20160628071126";
File partitionDir = InputFormatTestUtil.prepareParquetDataset(basePath, schema, 1, 10, commit1);
File partitionDir = InputFormatTestUtil.prepareParquetTable(basePath, schema, 1, 10, commit1);
InputFormatTestUtil.commit(basePath, commit1);
// Add the paths
FileInputFormat.setInputPaths(jobConf, partitionDir.getPath());

View File

@@ -34,7 +34,7 @@ public class TestRecordReaderValueIterator {
@Test
public void testValueIterator() {
String[] values = new String[] {"hoodie", "efficient", "new project", "realtime", "spark", "dataset",};
String[] values = new String[] {"hoodie", "efficient", "new project", "realtime", "spark", "table",};
List<Pair<Integer, String>> entries =
IntStream.range(0, values.length).boxed().map(idx -> Pair.of(idx, values[idx])).collect(Collectors.toList());
TestRecordReader reader = new TestRecordReader(entries);

View File

@@ -185,8 +185,8 @@ public class TestHoodieRealtimeRecordReader {
Schema schema = HoodieAvroUtils.addMetadataFields(SchemaTestUtil.getEvolvedSchema());
HoodieTestUtils.init(hadoopConf, basePath.getRoot().getAbsolutePath(), HoodieTableType.MERGE_ON_READ);
String baseInstant = "100";
File partitionDir = partitioned ? InputFormatTestUtil.prepareParquetDataset(basePath, schema, 1, 100, baseInstant)
: InputFormatTestUtil.prepareNonPartitionedParquetDataset(basePath, schema, 1, 100, baseInstant);
File partitionDir = partitioned ? InputFormatTestUtil.prepareParquetTable(basePath, schema, 1, 100, baseInstant)
: InputFormatTestUtil.prepareNonPartitionedParquetTable(basePath, schema, 1, 100, baseInstant);
InputFormatTestUtil.commit(basePath, baseInstant);
// Add the paths
FileInputFormat.setInputPaths(jobConf, partitionDir.getPath());
@@ -269,7 +269,7 @@ public class TestHoodieRealtimeRecordReader {
final int numRecords = 1000;
final int firstBatchLastRecordKey = numRecords - 1;
final int secondBatchLastRecordKey = 2 * numRecords - 1;
File partitionDir = InputFormatTestUtil.prepareParquetDataset(basePath, schema, 1, numRecords, commitTime);
File partitionDir = InputFormatTestUtil.prepareParquetTable(basePath, schema, 1, numRecords, commitTime);
InputFormatTestUtil.commit(basePath, commitTime);
// Add the paths
FileInputFormat.setInputPaths(jobConf, partitionDir.getPath());
@@ -343,7 +343,7 @@ public class TestHoodieRealtimeRecordReader {
String commitTime = "100";
int numberOfRecords = 100;
int numberOfLogRecords = numberOfRecords / 2;
File partitionDir = InputFormatTestUtil.prepareParquetDataset(basePath, schema, 1, numberOfRecords, commitTime);
File partitionDir = InputFormatTestUtil.prepareParquetTable(basePath, schema, 1, numberOfRecords, commitTime);
InputFormatTestUtil.commit(basePath, commitTime);
// Add the paths
FileInputFormat.setInputPaths(jobConf, partitionDir.getPath());
@@ -470,7 +470,7 @@ public class TestHoodieRealtimeRecordReader {
int numberOfRecords = 100;
int numberOfLogRecords = numberOfRecords / 2;
File partitionDir =
InputFormatTestUtil.prepareSimpleParquetDataset(basePath, schema, 1, numberOfRecords, commitTime);
InputFormatTestUtil.prepareSimpleParquetTable(basePath, schema, 1, numberOfRecords, commitTime);
InputFormatTestUtil.commit(basePath, commitTime);
// Add the paths
FileInputFormat.setInputPaths(jobConf, partitionDir.getPath());