Vijay Sarvepali created HBASE-10385:
---------------------------------------
Summary: ImportTsv to parse date time from typical loader formats
Key: HBASE-10385
URL: https://issues.apache.org/jira/browse/HBASE-10385
Project: HBase
Issue Type: New Feature
Components: mapreduce
Affects Versions: 0.96.1.1
Reporter: Vijay Sarvepali
Priority: Minor
Simple patch to enable parsing of standard date time fields from TSV files into
Hbase.
***************
*** 57,62 ****
--- 57,70 ----
import com.google.common.base.Splitter;
import com.google.common.collect.Lists;
+ //2013-08-19T04:39:07
+ import java.text.DateFormat;
+ import java.util.*;
+ import java.text.SimpleDateFormat;
+ import java.text.ParseException;
+
+
+
/**
* Tool to import data from a TSV file.
*
***************
*** 220,229 ****
getColumnOffset(timestampKeyColumnIndex),
getColumnLength(timestampKeyColumnIndex));
try {
! return Long.parseLong(timeStampStr);
} catch (NumberFormatException nfe) {
// treat this record as bad record
! throw new BadTsvLineException("Invalid timestamp " + timeStampStr);
}
}
--- 228,239 ----
getColumnOffset(timestampKeyColumnIndex),
getColumnLength(timestampKeyColumnIndex));
try {
! return Long.parseLong(timeStampStr);
} catch (NumberFormatException nfe) {
+ // Try this record with string to date in mseconds long
+ return extractTimestampInput(timeStampStr);
// treat this record as bad record
! //throw new BadTsvLineException("Invalid timestamp " +
timeStampStr);
}
}
***************
*** 243,248 ****
--- 253,274 ----
return lineBytes;
}
}
+ public static long extractTimestampInput(String strDate) throws
BadTsvLineException{
+ final List<String> dateFormats = Arrays.asList("yyyy-MM-dd HH:mm:ss.SSS",
"yyyy-MM-dd'T'HH:mm:ss");
+
+ for(String format: dateFormats){
+ SimpleDateFormat sdf = new SimpleDateFormat(format);
+ try{
+ Date d= sdf.parse(strDate);
+ long msecs = d.getTime();
+ return msecs;
+ } catch (ParseException e) {
+ //intentionally empty
+ }
+ }
+ // If we come here we have a problem with converting timestamps for this
row.
+ throw new BadTsvLineException("Invalid timestamp " + strDate);
+ }
public static class BadTsvLineException extends Exception {
public BadTsvLineException(String err) {
--
This message was sent by Atlassian JIRA
(v6.1.5#6160)
