Skip to content

PARQUET-386: Printing out the statistics of metadata in parquet-tools #279

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
onursoyer wants to merge 1 commit into from
Closed

PARQUET-386: Printing out the statistics of metadata in parquet-tools #279

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
64 changes: 61 additions & 3 deletions parquet-tools/src/main/java/org/apache/parquet/tools/util/MetadataUtils.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,9 +19,6 @@
package org.apache.parquet.tools.util;

import java.util.ArrayList;
import java.util.Arrays;

import java.util.HashMap;
import java.util.LinkedHashMap;
import java.util.List;
import java.util.Map;
Expand All @@ -30,6 +27,7 @@
import com.google.common.base.Strings;

import org.apache.parquet.column.ColumnDescriptor;
import org.apache.parquet.column.statistics.*;
import org.apache.parquet.hadoop.metadata.BlockMetaData;
import org.apache.parquet.hadoop.metadata.ColumnChunkMetaData;
import org.apache.parquet.hadoop.metadata.FileMetaData;
Expand All @@ -42,6 +40,9 @@
import org.apache.parquet.schema.Type;
import org.apache.parquet.schema.Type.Repetition;

import static org.apache.parquet.tools.command.DumpCommand.binaryToBigInteger;
import static org.apache.parquet.tools.command.DumpCommand.binaryToString;

public class MetadataUtils {
public static final double BAD_COMPRESSION_RATIO_CUTOFF = 0.97;
public static final double GOOD_COMPRESSION_RATIO_CUTOFF = 1.2;
Expand Down Expand Up @@ -149,6 +150,63 @@ private static void showDetails(PrettyPrintWriter out, ColumnChunkMetaData meta,
out.format(" FPO:%d", foff);
out.format(" SZ:%d/%d/%.2f", tsize, usize, ratio);
out.format(" VC:%d", count);

if (!meta.getStatistics().isEmpty()) {
Statistics statistics = meta.getStatistics();

if (statistics.hasNonNullValue()) {
String maxValue = null;
String minValue = null;
switch (meta.getType()) {
case BINARY:
BinaryStatistics binaryStatistics = (BinaryStatistics) statistics;
minValue = String.format("%s", binaryToString(binaryStatistics.genericGetMin()));
maxValue = String.format("%s", binaryToString(binaryStatistics.genericGetMax()));
break;
case BOOLEAN:
BooleanStatistics booleanStatistics = (BooleanStatistics) statistics;
minValue = String.format("%s", booleanStatistics.genericGetMin());
maxValue = String.format("%s", booleanStatistics.genericGetMax());
break;
case DOUBLE:
DoubleStatistics doubleStatistics = (DoubleStatistics) statistics;
minValue = String.format("%s", doubleStatistics.genericGetMin());
maxValue = String.format("%s", doubleStatistics.genericGetMax());
break;
case FLOAT:
FloatStatistics floatStatistics = (FloatStatistics) statistics;
minValue = String.format("%s", floatStatistics.genericGetMin());
maxValue = String.format("%s", floatStatistics.genericGetMax());
break;
case INT32:
IntStatistics int32Statistics = (IntStatistics) statistics;
minValue = String.format("%s", int32Statistics.genericGetMin());
maxValue = String.format("%s", int32Statistics.genericGetMax());
break;
case INT64:
LongStatistics int64Statistics = (LongStatistics) statistics;
minValue = String.format("%s", int64Statistics.genericGetMin());
maxValue = String.format("%s", int64Statistics.genericGetMax());
break;
case INT96:
BinaryStatistics int96Statistics = (BinaryStatistics) statistics;
minValue = String.format("%s", binaryToBigInteger(int96Statistics.genericGetMin()));
maxValue = String.format("%s", binaryToBigInteger(int96Statistics.genericGetMax()));
break;
case FIXED_LEN_BYTE_ARRAY:
BinaryStatistics fixLenByteArrStatistics = (BinaryStatistics) statistics;
minValue = String.format("%s", binaryToString(fixLenByteArrStatistics.genericGetMin()));
maxValue = String.format("%s", binaryToString(fixLenByteArrStatistics.genericGetMax()));
break;
}

out.format(" MIN:%s", minValue);
out.format(" MAX:%s", maxValue);
}

out.format(" NN:%d", meta.getStatistics().getNumNulls());
}

if (!encodings.isEmpty()) out.format(" ENC:%s", encodings);
out.println();
}
Expand Down