amontalenti

#!/usr/bin/env python

#
# simple static Flask fileserving app
# with livereload integration
#
from flask import Flask

STATIC_FOLDER = "."

amontalenti

Lucene Fundamentals

A useful set of Lucene fundamentals that are good for grok'ing Elasticsearch.

Jargon Glossary

• document: a record; the unit of search; the thing returned as search results
• field: a typed slot in a document for storing and indexing values
• index: a collection of documents, typically with the same field mappings or schema
• corpus: the entire set of documents in an index

amontalenti

var httpProxy = require('http-proxy');
var url = require('url');

httpProxy.createServer(function(req, res, proxy) {

  var isHtml = false,
      write = res.write,
      writeHead = res.writeHead,
      params = url.parse(req.url, true).query,
      dest = params.dest || 'localhost',

amontalenti

-- XXX: all of this is a bad idea, but it was a nice idea at the time :)

CREATE TABLE IF NOT EXISTS apikey_changed_urls (
    process_minute timestamp,               -- current minute of processing
    apikey text,                            -- apikey
    url text,                               -- url where data changed
    change_time timestamp,                  -- 5-min period where data changed
    process_hour timestamp,                 -- current hour of processing
    process_day timestamp,                  -- current day of processing 
    PRIMARY KEY (process_minute, apikey, url, change_time)); 

amontalenti

>>> import re
>>> eml = re.compile(r"([^@|\s]+@[^@]+\.[^@|\s]+)")
>>> match = eml.search("some text that has a test@test.com email address")
>>> match.group(1)
"test@test.com"

amontalenti

#!/bin/sh

# on Ubuntu 14.04, set a pm-hibernate resume hook
# which is placed in /etc/pm/sleep.d/00_intel_pstate

# it sets up CPU intel pstate appropriately, which by default
# gets ruined by being scaled down to 50% of max CPU without the
# easy ability to change it back; also sets governor to performance
# for good measure, since apparently default is "powersave"

amontalenti

import os
import requests
from BeautifulSoup import BeautifulSoup
from urlparse import urlparse

sitemap_xml = "http://www.cnn.com/sitemaps/sitemap-specials-2013-11.xml"

sitemap_response = requests.get(sitemap_xml)
soup = BeautifulSoup(sitemap_response.content)

amontalenti

>>> from nltk import word_tokenize
>>> from nltk.collocations import BigramCollocationFinder
>>> text = "obama says that obama says that the war is happening"
>>> finder = BigramCollocationFinder.from_words(word_tokenize(text))
>>> finder.items()[0:5]
[(('obama', 'says'), 2),
 (('says', 'that'), 2),
 (('is', 'happening'), 1),
 (('that', 'obama'), 1),
 (('that', 'the'), 1)]

amontalenti

from itertools import chain, product
from re import match, findall

GRAMMAR = '''
<sentence> ::= <noun phrase=""> <verb phrase="">
<noun> ::= "boy " | "troll " | "moon " | "telescope "
<transitive verb=""> ::= "hits " | "sees "
<intransitive verb=""> ::= "runs " | "sleeps "
<adjective> ::= "big " | "red "
<adverb> ::= "quickly " | "quietly "

amontalenti

export PYTHON_CONFIGURE_OPTS="--enable-ipv6\
                              --enable-unicode=ucs4\
                              --with-dbmliborder=bdb:gdbm\
                              --with-system-expat\
                              --with-system-ffi\
                              --with-fpectl"
pyenv install -f 2.7.14