Upgrade script from ReAD commit f5bd3f4 to ad87e7b. See https://github.com/doersino/ReAD.

read_computeerts.php

<?php

error_reporting(E_ALL);

require_once "deps/meekrodb.2.3.class.php";
require_once "TextExtractor.class.php";

$allArticles = DB::query("SELECT * FROM `read` ORDER BY `time_added` ASC");
$N = count($allArticles);

echo "\tid\twordcount\n";
echo "-------------------------\n";

foreach ($allArticles as $n => $article) {
    $id = $article["id"];

    // get source
    $source = DB::queryFirstField("SELECT `source` FROM `read_sources` WHERE `id` = '$id'");

    // extract text and compute word count
    $text = TextExtractor::extractText($source);
    $wordcount = TextExtractor::countWords($text);

    // print progress
    echo round(10000 * ($n / $N)) / 100 . "%\t";
    echo "$id\t";
    echo "$wordcount\n";

    // save to database
    DB::query("INSERT INTO `read_texts` ( `id`, `text` ) VALUES (%s, %s)", $id, $text);
    DB::query("UPDATE `read` SET `wordcount` = %i WHERE `id` = %i", $wordcount, $id);
}