Github user kumarvishal09 commented on a diff in the pull request:
https://github.com/apache/carbondata/pull/2830#discussion_r226991227
--- Diff:
tools/cli/src/main/java/org/apache/carbondata/tool/DataSummary.java ---
@@ -226,25 +282,46 @@ private int getColumnIndex(String columnName) {
private boolean collected = false;
private void printColumnStats(String columnName) throws IOException,
MemoryException {
- out.println();
- out.println("## Column Statistics for '" + columnName + "'");
+ outPuts.add("");
+ outPuts.add("## Column Statistics for '" + columnName + "'");
collectStats(columnName);
int columnIndex = getColumnIndex(columnName);
String[] header = new String[]{"BLK", "BLKLT", "Meta Size", "Data
Size",
- "LocalDict", "DictEntries", "DictSize", "AvgPageSize", "Min%",
"Max%"};
+ "LocalDict", "DictEntries", "DictSize", "AvgPageSize", "Min%",
"Max%", "Min", "Max"};
- ShardPrinter printer = new ShardPrinter(header);
+ ShardPrinter printer = new ShardPrinter(header, outPuts);
for (Map.Entry<String, DataFile> entry : dataFiles.entrySet()) {
DataFile file = entry.getValue();
for (DataFile.Blocklet blocklet : file.getAllBlocklets()) {
- String min, max;
+ String min, max, minPercent, maxPercent;
--- End diff --
Now min max will not be present if size is more for example varchar string
this case is not handled please check
---
