gibrown

function es_api_detect_lang( $text ) {
	$lang = false;

	//if we can't tell the lang with 5000 characters we probably can't tell the language
	$text = mb_substr( $text, 0, 5000 );

	//replace non-breaking spaces so they don't match the \p{L} char class
	$text = preg_replace( '/[\x{00A0}\x{2007}\x{202F}]/u', ' ', $text );

	//replace unicode symbols: see: http://www.utf8-chartable.de/unicode-utf8-table.pl

gibrown

//These are some params I've used elsewhere, may want to try adjusting
$date_scale = '5d';
$date_decay = 0.99999;
$date_origin = date( 'Y-m-d' );
$query = array(
	'query' => array(
		"function_score" => array(
			'query' => array( 'filtered' => array(
				'query' => array( 'multi_match' => array(
					'query' => $query,

gibrown

<?php


class Theme_Support_Index_Builder extends WPES_Abstract_Index_Builder {

	public function get_config( $args ) {
		$defaults = array(
			'lang' => 'en',
		);
		$args = wp_parse_args( $args, $defaults );

gibrown

#/bin/python

import sys
import org_search as org
import pprint
import csv

#Configuration
lang='en_US'
min_count=1000

gibrown

#!/bin/bash

# To prep a file for this script:
# - take a list of docs orig.json with one json doc per line
# - run: split -l 1000 orig.json orig-split


export ESINDEX="$1"    #ES index name
export ESTYPE="$2"     #ES document type name
JSONFILE="$3" #JSON file path name. One doc per line.

gibrown

from __future__ import division
import matplotlib.pyplot as plt
import matplotlib.dates as mdates

from pylab import *
import math
from scipy.stats import beta, norm, uniform
from scipy.special import betaln
from random import random, normalvariate
import numpy as np

gibrown

<?php

// This uses the wpes-lib framework to build the index: https://github.com/automattic/wpes-lib
class WPOrg_Plugins_Index_Builder extends VIP_Index_Builder {

	//override to add support for all analyzers
	public function get_settings( $args ) {
		$defaults = array(
		);
		$args = wp_parse_args( $args, $defaults );