Last active
August 30, 2018 00:58
-
-
Save cbaenziger/6310a53811a6e39962ab412d95115f5f to your computer and use it in GitHub Desktop.
JRuby File Deletion Script
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
include Java | |
import org.apache.hadoop.conf.Configuration | |
import org.apache.hadoop.fs.FileSystem | |
import org.apache.hadoop.fs.Path | |
import java.io.FileNotFoundException.hadoop.fs.Path | |
import java.util.NoSuchElementException | |
# hdfs file system handle | |
fs = FileSystem.newInstance(Configuration.new) | |
list_of_files = '/tmp/file_list.txt' | |
delete_files = false | |
totals = {} | |
totals.default = 0 | |
files = {'seen' => 0, 'found' => 0} | |
File.open(list_of_files) do |f| | |
f.each do |p| | |
path = Path.new(p.strip) | |
puts p | |
files['seen'] += 1 | |
begin | |
if fs.isDirectory(path) | |
status = fs.listFiles(path, true) | |
while ( l = status.has_next()) do | |
l = status.next() | |
begin | |
totals[l.getOwner().to_s] = totals[status.getOwner()] + (l.getLen() * l.getReplication()) | |
rescue java.io.FileNotFoundException => e | |
puts e.message | |
end | |
end | |
else | |
status = fs.listStatus(path)[0] | |
totals[status.getOwner().to_s] = totals[status.getOwner()] + (status.getLen() * status.getReplication()) | |
end | |
rescue java.io.FileNotFoundException => e | |
puts e.message | |
next | |
end | |
files['found'] += 1 | |
if delete_files == true | |
fs.delete(path, true) | |
end | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment