shantanuo

#!/usr/bin/python
# -*- coding: utf-8 -*-
# texts =[u"वाराणसी", u"भौगोलिक", u"उपदर्शन"]
# CREATE TABLE syllabalize (id int(11) DEFAULT NULL, seqn int(11) DEFAULT NULL, akshar varchar(10) DEFAULT NULL) DEFAULT CHARSET=utf8

import codecs
f = codecs.open('testfile.txt', encoding='utf-8')
texts = f.read().split()
signs = [
u'\u0902', u'\u0903', u'\u093e', u'\u093f', u'\u0940', u'\u0941',

bostwick

#!/usr/bin/env python

import sys
import urllib2
import json
from collections import defaultdict

from nltk import word_tokenize

IGNORED_WORDS = ["!", ".", ",", "(", ")", "'s", ":", "?", "...", "$", 

cwholt

module.exports = function(redisClient,prefix) {
  var Autocomplete = {};
  
  Autocomplete.prefix = prefix;
  Autocomplete.terminal = "+";
  
  Autocomplete.add = function(word, next) {
    function add(letters, key, last, x) {
      var letter = last ? Autocomplete.terminal : letters[x];
      var score = last ? 0 : letter.charCodeAt(0);

mvaz

import cx_Oracle
import pandas

connection = cx_Oracle.connect('username/pwd@host:port/dbname')

def read_query(connection, query):
    cursor = connection.cursor()
    try:
        cursor.execute( query )
        names = [ x[0] for x in cursor.description]

davorg

#!/usr/bin/perl

use strict;
use warnings;

use Data::Dumper;
use Text::ParseWords;
use List::Util 'max';

my $file = shift || die "Need a csv file to process\n";

BrockA

/*--- waitForKeyElements():  A utility function, for Greasemonkey scripts,
    that detects and handles AJAXed content.

    Usage example:

        waitForKeyElements (
            "div.comments"
            , commentCallbackFunction
        );

griggheo

import os
import sys
import subprocess
import re
import optparse
import boto

dynamodb_conn = boto.connect_dynamodb(aws_access_key_id='MY_ACCESS_KEY_ID', aws_secret_access_key='MY_SECRET_ACCESS_KEY')
table_name = 'mytable'
dynamodb_table = dynamodb_conn.get_table(table_name)

karussell

Why is there no such DataImportHandler thing in ElasticSearch? Uhm, well ... but because:

1. You should really consider your own scripts 
(be it jvm based, perl, ruby, php, nodejs/javascript) 
to feed ElasticSearch via bulk indexing: 
http://www.elasticsearch.org/guide/reference/java-api/bulk.html

2. There are two projects doing it already:
 * http://code.google.com/p/sql-to-nosql-importer/
 * https://github.com/Aconex/scrutineer (keeps DB in synch with ES or solr!)

mindsocket

#!/usr/bin/env python
# -*- python -*-
#
# Plugin to track account balances on ingdirect.com.au, using selenium gymnastics to log in
#
# E.g.
#    ln -s /usr/share/munin/plugins/ingdirect.py /etc/munin/plugins/ingdirect
#
# Needs (hint: pip install):
#   selenium

Rafe

HANDY ONE-LINE SCRIPTS FOR AWK                               30 April 2008
Compiled by Eric Pement - eric [at] pement.org               version 0.27

Latest version of this file (in English) is usually at:
   http://www.pement.org/awk/awk1line.txt

This file will also be available in other languages:
   Chinese  - http://ximix.org/translation/awk1line_zh-CN.txt   

USAGE: