t3rmin4t0r

import sys
import re
S_RE = re.compile(r'Stripe: offset: ([0-9]*) data: ([0-9]*) rows: ([0-9]*).*')
items = [m.groups() for m in [S_RE.search(l) for l in sys.stdin] if m]
parsed = [(int(a),int(b), int(c)) for (a,b,c) in items]
stripe_size = 256*1024*1024
for (start, len, rows) in parsed:
        if (start / stripe_size) != ((start+len) / stripe_size):
                print start+len, "overflows", start, "block"

t3rmin4t0r

[base-source]
name=CentOS-$releasever - Base Source
baseurl=http://vault.centos.org/centos/$releasever/os/Source/
enabled=0

[updates-source]
name=CentOS-$releasever - Updates Source
baseurl=http://vault.centos.org/centos/$releasever/updates/Source/
enabled=0

t3rmin4t0r

import sys
import re,math,string
from time import sleep
import os.path as path
import urllib2
from json import loads as json_parse
from collections import defaultdict
import getopt
import datetime
import time

t3rmin4t0r

import sys,re,math,os
import curses
from time import sleep 

running=re.compile(r'Status: Running \(application id: (application_[0-9_]*)\)')
tasks=re.compile(r'(Map [0-9]*|Reducer [0-9]*): ([\-0-9]*)(\(.[0-9]*\))?/([\-0-9]*)')

log = open("log", "w")
debug = lambda a: (log.write(str(a)+"\n"),log.flush())

t3rmin4t0r

import sys

for l in sys.stdin:
        l = l.strip()
        name = l[0:l.find("{")]
        cols = [x.strip().split(" ") for x in l[l.find("{")+1:l.find("}")].split(",")]
        print "create table ", name, "(",
        print ",".join(["%s %s" % (b,a) for (a,b) in cols]), ");"
[gopal@cn041-10 comcast]$ 

t3rmin4t0r

import sys
import re

def Counter(name):
	pattern = re.compile("%s=([^,]*)" % name)
	# warning closure
	def get(l):
		m = pattern.search(l)
		if m:
			return m.group(1)

t3rmin4t0r

import sys, re, os, math, os.path

from collections import defaultdict

class JStackTrie(object):
	def __init__(self):
		self.roots = defaultdict(JStackTrie)
		self.count = 0
		self.name = "root"

t3rmin4t0r

import json
import sys

class ATSFile(object):
	def __init__(self, name):
		self.data = json.load(open(name))
		self.name = name
	def dump(self):
		info = self.data["otherinfo"]
		q = json.loads(info["QUERY"])

t3rmin4t0r

import re
import sys, math, os.path
from glob import glob
from itertools import groupby,chain
from collections import defaultdict

import re

def parse(f):
        PAT = re.compile(r'DIR\* completeFile: ([^ ]*) is closed by ([^ ]*)')

t3rmin4t0r

#!/usr/bin/env gawk -f 
BEGIN { id = 0; 
  cmd = "gzip -c -2"; 
  ext = ".gz";
  file = sprintf("%04d%s",id, ext); 
  print "Opening new file " file " at " NR " rows";
  count = 1000000;
}

# Use pipes