Skip to content

Instantly share code, notes, and snippets.

{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Unicode and Strings in Python 2\n",
"\n",
"When dealing with strings and unicode in most languages there are few rules to live by. This is no different in python, regardless of whether you are talking about 2 or 3.\n",
"\n",
<!DOCTYPE html>
<html>
<head><meta charset="utf-8" />
<title>Python 2</title>
<script src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.1.10/require.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.0.3/jquery.min.js"></script>
<style type="text/css">
/*!
# -*- coding: utf-8 -*-
"""
>>> root = etree.Element('foo')
>>> el = get_path('bar/baz', root).text = 'foobaz'
>>> etree.tostring(root)
'<foo><bar><baz>foobaz</baz></bar></foo>'
>>> get_path('bar/gaz', root).text = 'foogaz'
>>> etree.tostring(root)
'<foo><bar><baz>foobaz</baz><gaz>foogaz</gaz></bar></foo>'
"""
#!/usr/bin/env bash
####
# ./dedup FROM TO
#
# move duplicate emails from FROM to TO
####
duplicates=$(grep --no-filename -rE "^To:\s[[:alpha:]]+" $1 | sort | uniq -c | \
<?xml version="1.0" encoding="UTF-8"?>
<config>
<luceneMatchVersion>4.5</luceneMatchVersion>
<dataDir>${solr.data.dir:}</dataDir>
<directoryFactory name="DirectoryFactory"
class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}" />
@gravesm
gravesm / load.py
Last active December 28, 2015 10:58
#!/usr/bin/env python
from __future__ import print_function
import fileinput
import json
from datetime import datetime
import time
from pymongo import MongoClient
def get_collection(conn=None):
#!/usr/bin/env python
from __future__ import print_function
import json
import sys
from datetime import timedelta, datetime
from random import randint, choice
countries = ('US', 'GB', 'FR', 'DE',)
dlc = ('CSAIL', 'DUSP', 'Lincoln Lab',)
#!/usr/bin/env python
from __future__ import print_function
import fileinput
import sys
import json
import apachelog
parser = apachelog.parser(apachelog.formats['extended'])
@gravesm
gravesm / marc2solr.py
Created September 11, 2013 18:40
MarcXML record to Solr add doc
#!/usr/bin/env python
########################
#
# @TODO: Location field in current Solr index has both libRecord and mapRecord -
# should there be both or just libRecord?
#
########################
from lxml import etree
import sys
@gravesm
gravesm / stubit.js
Last active February 11, 2024 22:24
Jasmine+AMD test stub module injection
/**
* This module allows you to inject test stubs into the module loading process
* during jasmine unit testing.
*/
define(["underscore"], function(_) {
var uid = 0;
function defineMock(mockid, mock) {
define(mockid, function() {