PARQUET-668 - Provide option to disable auto crop feature in dump

parquet-tools/README.md

@@ -61,50 +61,13 @@ java jar ./parquet-tools-<VERSION>.jar <command> my_parquet_file.lzo.parquet
 
 ## Commands Usage
 
-To run it on hadoop, you should use "hadoop jar" instead of "java jar"
+To see usage instructions for all commands: 
 
-```sh
-usage: java -jar ./parquet-tools-<VERSION>.jar cat [option...] <input>
-where option is one of:
-       --debug     Disable color output even if supported
-    -h,--help      Show this help string
-       --no-color  Disable color output even if supported
-where <input> is the parquet file to print to stdout
-
-usage: java -jar ./parquet-tools-<VERSION>.jar head [option...] <input>
-where option is one of:
-       --debug          Disable color output even if supported
-    -h,--help           Show this help string
-    -n,--records <arg>  The number of records to show (default: 5)
-       --no-color       Disable color output even if supported
-where <input> is the parquet file to print to stdout
-
-usage: java -jar ./parquet-tools-<VERSION>.jar schema [option...] <input>
-where option is one of:
-    -d,--detailed <arg>  Show detailed information about the schema.
-       --debug           Disable color output even if supported
-    -h,--help            Show this help string
-       --no-color        Disable color output even if supported
-where <input> is the parquet file containing the schema to show
-
-usage: java -jar ./parquet-tools-<VERSION>.jar meta [option...] <input>
-where option is one of:
-       --debug     Disable color output even if supported
-    -h,--help      Show this help string
-       --no-color  Disable color output even if supported
-where <input> is the parquet file to print to stdout
-
-usage: java -jar dump [option...] <input>
-where option is one of:
-    -c,--column <arg>  Dump only the given column, can be specified more than
-                       once
-    -d,--disable-data  Do not dump column data
-       --debug         Disable color output even if supported
-    -h,--help          Show this help string
-    -m,--disable-meta  Do not dump row group and page metadata
-       --no-color      Disable color output even if supported
-where <input> is the parquet file to print to stdout
 ```
+java jar ./parquet-tools-<VERSION>.jar --help
+```
+
+**Note:** To run it on hadoop, you should use `hadoop jar` instead of `java jar`
 
 ## Meta Legend
 

parquet-tools/src/main/java/org/apache/parquet/tools/command/DumpCommand.java

@@ -85,13 +85,18 @@ public class DumpCommand extends ArgsOnlyCommand {
                                  .withDescription("Do not dump column data")
                                  .create('d');
 
+        Option nocrop = OptionBuilder.withLongOpt("disable-crop")
+                                 .withDescription("Do not crop the output based on console width")
+                                 .create('n');
+
         Option cl = OptionBuilder.withLongOpt("column")
                                  .withDescription("Dump only the given column, can be specified more than once")
                                  .hasArgs()
                                  .create('c');
 
         OPTIONS.addOption(md);
         OPTIONS.addOption(dt);
+        OPTIONS.addOption(nocrop);
         OPTIONS.addOption(cl);
     }
 
@@ -122,24 +127,17 @@ public void execute(CommandLine options) throws Exception {
         ParquetMetadata metaData = ParquetFileReader.readFooter(conf, inpath, NO_FILTER);
         MessageType schema = metaData.getFileMetaData().getSchema();
 
-        PrettyPrintWriter out = PrettyPrintWriter.stdoutPrettyPrinter()
-                                                 .withAutoColumn()
-                                                 .withAutoCrop()
-                                                 .withWhitespaceHandler(WhiteSpaceHandler.ELIMINATE_NEWLINES)
-                                                 .withColumnPadding(1)
-                                                 .withMaxBufferedLines(1000000)
-                                                 .withFlushOnTab()
-                                                 .build();
-
         boolean showmd = !options.hasOption('m');
         boolean showdt = !options.hasOption('d');
+        boolean cropoutput = !options.hasOption('n');
 
         Set<String> showColumns = null;
         if (options.hasOption('c')) {
             String[] cols = options.getOptionValues('c');
             showColumns = new HashSet<String>(Arrays.asList(cols));
         }
 
+        PrettyPrintWriter out = prettyPrintWriter(cropoutput);
         dump(out, metaData, schema, inpath, showmd, showdt, showColumns);
     }
 
@@ -346,6 +344,21 @@ public static BigInteger binaryToBigInteger(Binary value) {
         return new BigInteger(data);
     }
 
+    private static PrettyPrintWriter prettyPrintWriter(boolean cropOutput) {
+        PrettyPrintWriter.Builder builder = PrettyPrintWriter.stdoutPrettyPrinter()
+                .withAutoColumn()
+                .withWhitespaceHandler(WhiteSpaceHandler.ELIMINATE_NEWLINES)
+                .withColumnPadding(1)
+                .withMaxBufferedLines(1000000)
+                .withFlushOnTab();
+
+        if (cropOutput) {
+            builder.withAutoCrop();
+        }
+
+        return builder.build();
+    }
+
     private static final class DumpGroupConverter extends GroupConverter {
         @Override public void start() { }
         @Override public void end() { }