| from pyspark.context import SparkContext | |
| from pyspark.serializers import BatchedSerializer, PickleSerializer | |
| from pyspark.rdd import RDD | |
| from py4j.java_gateway import java_import | |
| class CassandraSparkContext(SparkContext): | |
| def _do_init(self, *args, **kwargs): |
| /* | |
| * Licensed to the Apache Software Foundation (ASF) under one or more | |
| * contributor license agreements. See the NOTICE file distributed with | |
| * this work for additional information regarding copyright ownership. | |
| * The ASF licenses this file to You under the Apache License, Version 2.0 | |
| * (the "License"); you may not use this file except in compliance with | |
| * the License. You may obtain a copy of the License at | |
| * | |
| * http://www.apache.org/licenses/LICENSE-2.0 | |
| * |
| import re | |
| class InvalidVersionException(Exception): pass | |
| class StormVersion(object): | |
| VERSION_RE = re.compile(r"(?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)" | |
| "(?P<older_patch>\.\d+)?(?P<other>.*)") | |
| RC_RE = re.compile(r"-rc(?P<release_candidate>\d+)", re.IGNORECASE) |
| import logging | |
| from streamparse.bolt import Bolt | |
| log = logging.getLogger("custom_code_bolt") | |
| class CustomCodeBolt(Bolt): |
| <!DOCTYPE html> | |
| <html lang="en"> | |
| <head> | |
| <title>TODO</title> | |
| <!-- CSS --> | |
| <link rel="stylesheet" href="http://maxcdn.bootstrapcdn.com/bootstrap/3.2.0/css/bootstrap.min.css"> | |
| <link rel="stylesheet" href="http://maxcdn.bootstrapcdn.com/bootstrap/3.2.0/css/bootstrap-theme.min.css"> | |
| <style> | |
| .done { | |
| text-decoration: line-through; |
Python 2.7 contains a bug when dealing with percent-encoded Unicode strings such as:
>>> import urlparse
>>> url = u"http%3A%2F%2F%C5%A1%C4%BC%C5%AB%C4%8D.org%2F"
>>> print "{!r}".format(urlparse.unquote(url))
u'http://\xc5\xa1\xc4\xbc\xc5\xab\xc4\x8d.org/'
>>> print urlparse.unquote(url)
http://šļū�.org/
| import urlparse | |
| import urllib | |
| import urllib2 | |
| def patch_unquote(): | |
| urllib.unquote = unquote | |
| urllib2.unquote = unquote | |
| urlparse.unquote = unquote |
| { | |
| "metadata": { | |
| "name": "", | |
| "signature": "sha256:d0e242ec0ee3bf0798a38aba54eda99ab710de1890ddab0f0b6fd91939170314" | |
| }, | |
| "nbformat": 3, | |
| "nbformat_minor": 0, | |
| "worksheets": [ | |
| { | |
| "cells": [ |
| # ported from https://github.com/jvirkki/libbloom | |
| from cpython cimport bool | |
| from libc.stdlib cimport malloc, calloc, free | |
| from libc.string cimport memset | |
| from libc.stdio cimport printf | |
| from libc.math cimport log, ceil | |
| from cpython.mem cimport PyMem_Malloc, PyMem_Free | |
| DEF LN2_SQUARED = 0.480453013918201 # ln(2)^2 |
| from functools import wraps | |
| import csv | |
| import os.path | |
| def save_dict_list(filename, **kwargs): | |
| """Decorator to take the results of a function call (assumed to be a | |
| ``list`` of ``dicts``) and cache them in a local file via | |
| csv.DictWriter and serialize them with csv.DictReader""" | |
| def decorator(f): |