Skip to content

Commit e782736

Browse files
committed
update
1 parent a0983cc commit e782736

5 files changed

Lines changed: 9 additions & 28 deletions

File tree

parquet-cli/README.md

Lines changed: 1 addition & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -136,23 +136,15 @@ Usage: parquet [options] [command] [command options]
136136

137137
### Configuration Options
138138

139-
The `convert` and `convert-csv` commands support a generic configuration mechanism:
140-
141139
- `--conf` or `--property`: Set any configuration property in format `key=value`. Can be specified multiple times.
142140

143-
This allows you to configure any Avro or Parquet setting without needing to modify source code or rebuild the project.
144-
145141
Examples:
146142
```bash
147-
# Enable UUID support
148143
parquet convert input.avro -o output.parquet --conf parquet.avro.write-parquet-uuid=true
149144

150-
# Use new 3-level list structure
151145
parquet convert input.avro -o output.parquet --conf parquet.avro.write-old-list-structure=false
152146

153-
# Convert CSV with multiple options
147+
# Multiple options
154148
parquet convert-csv input.csv -o output.parquet --schema schema.avsc --conf parquet.avro.write-parquet-uuid=true --conf parquet.avro.write-old-list-structure=false
155149

156-
# Set any other configuration properties
157-
parquet convert input.avro -o output.parquet --conf parquet.avro.add-list-element-records=false --conf parquet.avro.write.data.supplier=org.apache.parquet.avro.GenericDataSupplier
158150
```

parquet-cli/src/main/java/org/apache/parquet/cli/commands/ConvertCSVCommand.java

Lines changed: 0 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -174,10 +174,8 @@ public int run() throws IOException {
174174
}
175175
}
176176

177-
// Create a configuration and apply custom properties
178177
Configuration conf = new Configuration(getConf());
179178

180-
// Apply custom configuration properties
181179
if (confProperties != null) {
182180
for (String prop : confProperties) {
183181
String[] parts = prop.split("=", 2);

parquet-cli/src/main/java/org/apache/parquet/cli/commands/ConvertCommand.java

Lines changed: 1 addition & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -34,6 +34,7 @@
3434
import java.util.List;
3535
import org.apache.avro.Schema;
3636
import org.apache.avro.generic.GenericData;
37+
import org.apache.hadoop.conf.Configuration;
3738
import org.apache.hadoop.fs.FileSystem;
3839
import org.apache.hadoop.fs.Path;
3940
import org.apache.parquet.avro.AvroParquetWriter;
@@ -43,7 +44,6 @@
4344
import org.apache.parquet.hadoop.ParquetWriter;
4445
import org.apache.parquet.hadoop.metadata.CompressionCodecName;
4546
import org.slf4j.Logger;
46-
import org.apache.hadoop.conf.Configuration;
4747

4848
@Parameters(commandDescription = "Create a Parquet file from a data file")
4949
public class ConvertCommand extends BaseCommand {
@@ -125,10 +125,8 @@ public int run() throws IOException {
125125
outFS.delete(outPath);
126126
}
127127

128-
// Create a configuration and apply custom properties
129128
Configuration conf = new Configuration(getConf());
130129

131-
// Apply custom configuration properties
132130
if (confProperties != null) {
133131
for (String prop : confProperties) {
134132
String[] parts = prop.split("=", 2);

parquet-cli/src/test/java/org/apache/parquet/cli/commands/ConvertCSVCommandTest.java

Lines changed: 2 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -69,10 +69,8 @@ public void testConvertCSVCommandWithGenericConf() throws IOException {
6969
command.targets = Arrays.asList(file.getAbsolutePath());
7070
File output = new File(getTempFolder(), getClass().getSimpleName() + "_with_generic_conf.parquet");
7171
command.outputPath = output.getAbsolutePath();
72-
command.confProperties = Arrays.asList(
73-
"parquet.avro.write-parquet-uuid=true",
74-
"parquet.avro.write-old-list-structure=false"
75-
);
72+
command.confProperties =
73+
Arrays.asList("parquet.avro.write-parquet-uuid=true", "parquet.avro.write-old-list-structure=false");
7674
command.setConf(new Configuration());
7775
Assert.assertEquals(0, command.run());
7876
Assert.assertTrue(output.exists());

parquet-cli/src/test/java/org/apache/parquet/cli/commands/ConvertCommandTest.java

Lines changed: 5 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -48,8 +48,7 @@ public void testConvertCommandWithGenericConf() throws IOException {
4848
command.confProperties = Arrays.asList(
4949
"parquet.avro.write-parquet-uuid=true",
5050
"parquet.avro.write-old-list-structure=false",
51-
"test.property=test.value"
52-
);
51+
"test.property=test.value");
5352
command.setConf(new Configuration());
5453

5554
Assert.assertEquals(0, command.run());
@@ -64,10 +63,8 @@ public void testConvertCommandConfigurationValidation() throws IOException {
6463
File output = new File(getTempFolder(), "converted_with_config_validation.parquet");
6564
command.outputPath = output.getAbsolutePath();
6665

67-
command.confProperties = Arrays.asList(
68-
"parquet.avro.write-parquet-uuid=true",
69-
"parquet.avro.write-old-list-structure=false"
70-
);
66+
command.confProperties =
67+
Arrays.asList("parquet.avro.write-parquet-uuid=true", "parquet.avro.write-old-list-structure=false");
7168

7269
command.setConf(new Configuration());
7370

@@ -76,10 +73,8 @@ public void testConvertCommandConfigurationValidation() throws IOException {
7673

7774
File output2 = new File(getTempFolder(), "converted_with_config_validation2.parquet");
7875
command.outputPath = output2.getAbsolutePath();
79-
command.confProperties = Arrays.asList(
80-
"parquet.avro.write-parquet-uuid=false",
81-
"parquet.avro.write-old-list-structure=true"
82-
);
76+
command.confProperties =
77+
Arrays.asList("parquet.avro.write-parquet-uuid=false", "parquet.avro.write-old-list-structure=true");
8378

8479
Assert.assertEquals(0, command.run());
8580
Assert.assertTrue(output2.exists());

0 commit comments

Comments
 (0)