[orc] branch main updated: ORC-958: Convert command support overwrite option (#876)

[do...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

dongjoon pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/orc.git


The following commit(s) were added to refs/heads/main by this push:
     new 2dcbd62  ORC-958: Convert command support overwrite option (#876)
2dcbd62 is described below

commit 2dcbd6281e2fbeeaf0ffe46aa3b78cd3df96ed62
Author: guiyanakaung <gu...@gmail.com>
AuthorDate: Sat Aug 21 02:51:39 2021 +0800

    ORC-958: Convert command support overwrite option (#876)
    
    ### What changes were proposed in this pull request?
    
    Make the convert command support the overwrite option.
    
    ### Why are the changes needed?
    
    You can overwrite old files when you convert multiple times.
    
    ```
    $ java -jar java/tools/target/orc-tools-1.8.0-SNAPSHOT-uber.jar convert
    usage: convert
     -e,--escape <arg>            CSV escape character
     -h,--help                    Provide help
     -H,--header <arg>            CSV header lines
     -n,--null <arg>              CSV null string
     -o,--output <arg>            Output filename
     -O,--overwrite               Overwrite an existing file
     -q,--quote <arg>             CSV quote character
     -s,--schema <arg>            The schema to write in to the file
     -S,--separator <arg>         CSV separator character
     -t,--timestampformat <arg>   Timestamp Format
    
    $ java -jar java/tools/target/orc-tools-1.8.0-SNAPSHOT-uber.jar convert -O examples/orc-file-11-format.orc examples/orc-file-11-format.orc
    Merging schema from examples/orc-file-11-format.orc
    Merging schema from examples/orc-file-11-format.orc
    Processing examples/orc-file-11-format.orc
    Processing examples/orc-file-11-format.orc
    
    $ java -jar java/tools/target/orc-tools-1.8.0-SNAPSHOT-uber.jar convert -O examples/orc-file-11-format.orc examples/orc-file-11-format.orc
    Merging schema from examples/orc-file-11-format.orc
    Merging schema from examples/orc-file-11-format.orc
    Processing examples/orc-file-11-format.orc
    Processing examples/orc-file-11-format.orc
    ```
    
    ### How was this patch tested?
    
    Pass the CIs.
---
 .../tools/src/java/org/apache/orc/tools/convert/ConvertTool.java | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/java/tools/src/java/org/apache/orc/tools/convert/ConvertTool.java b/java/tools/src/java/org/apache/orc/tools/convert/ConvertTool.java
index 7bacde8..fbb2337 100644
--- a/java/tools/src/java/org/apache/orc/tools/convert/ConvertTool.java
+++ b/java/tools/src/java/org/apache/orc/tools/convert/ConvertTool.java
@@ -196,8 +196,9 @@ public class ConvertTool {
     this.timestampFormat = opts.getOptionValue("t", DEFAULT_TIMESTAMP_FORMAT);
     String outFilename = opts.hasOption('o')
         ? opts.getOptionValue('o') : "output.orc";
+    boolean overwrite = opts.hasOption('O');
     writer = OrcFile.createWriter(new Path(outFilename),
-        OrcFile.writerOptions(conf).setSchema(schema));
+        OrcFile.writerOptions(conf).setSchema(schema).overwrite(overwrite));
     batch = schema.createRowBatch();
   }
 
@@ -256,8 +257,12 @@ public class ConvertTool {
         Option.builder("H").longOpt("header").desc("CSV header lines")
             .hasArg().build());
     options.addOption(
-            Option.builder("t").longOpt("timestampformat").desc("Timestamp Format")
+        Option.builder("t").longOpt("timestampformat").desc("Timestamp Format")
             .hasArg().build());
+    options.addOption(
+        Option.builder("O").longOpt("overwrite").desc("Overwrite an existing file")
+            .build()
+    );
     CommandLine cli = new DefaultParser().parse(options, args);
     if (cli.hasOption('h') || cli.getArgs().length == 0) {
       HelpFormatter formatter = new HelpFormatter();