RC traffic stats calculation

<?php

define('STATS_MONTH', '06');    // MM
define('STATS_YEAR',  '2015');  // YYYY
define('STATS_LANG',  'de');    // "en", "de", "fr", etc.

$articles = array('4-Hydroxycumarine',
                  [..................]
          'Refraktärmetalle');

// ---------------------------------------------
// obviously, configurable stuff ends here
// ---------------------------------------------

define('CHUNK_SIZE',  50);  // articles
define('CHUNK_SLEEP', 3);   // seconds

set_time_limit(0);
ini_set('memory_limit', 67108864);
ini_set('default_socket_timeout', 90);

// a few small helper functions

function plural_output($value, $unit) {
    return (number_format($value) . " {$unit}" . ((abs($value) != 1) ? 's' : ''));
}

function progress_message($message = '.') {
    static $last_message = null;

    $now     = microtime(true);
    $ret_val = false;

    if (($last_message === null) ||
        (($now - $last_message) > 0.5)) {   // one message every 0.5 seconds
        echo($message);

        $last_message = $now;
        $ret_val      = true;   // the message was printed
    }

    return ($ret_val);
}

// prepare the cURL handles for all articles

echo("\nFetching statistics data: ");

$start_time  = microtime(true);
$handles     = array();
$articles_no = count($articles);
$curr_month  = (STATS_MONTH == @date('m'));

if ($articles_no == 0)      // a small sanity check
    die("no articles specified!\n");

if ($curr_month && (@date('j') == 1))       // only the whole days are accounted
    die("no elapsed days in current month!\n");

for ($id = 0; $id < $articles_no; $id++) {
    $handles[$id] = curl_init();

    curl_setopt($handles[$id], CURLOPT_URL, 'http://stats.grok.se/json/' . STATS_LANG .
                                            '/' . STATS_YEAR . STATS_MONTH .
                                            '/' . str_replace('%2F', '/', rawurlencode($articles[$id])));

    curl_setopt($handles[$id], CURLOPT_HEADER, false);
    curl_setopt($handles[$id], CURLOPT_RETURNTRANSFER, true);

    curl_setopt($handles[$id], CURLOPT_CONNECTTIMEOUT, 20);
    curl_setopt($handles[$id], CURLOPT_TIMEOUT, 60);
    curl_setopt($handles[$id], CURLOPT_DNS_CACHE_TIMEOUT, 3600);

    curl_setopt($handles[$id], CURLOPT_FORBID_REUSE, false);
    curl_setopt($handles[$id], CURLOPT_FRESH_CONNECT, false);
    curl_setopt($handles[$id], CURLOPT_MAXCONNECTS, 10);
}

progress_message();

// run the cURL handles in chunks; otherwise, fetching data for a large number
// of articles at once causes stats.grok.se to start refusing HTTP connections

$handle_all  = curl_multi_init();
$chunks      = ceil(1.0 * $articles_no / CHUNK_SIZE);
$output      = array();
$error_msgs  = array('Parsing JSON data failed' => -1);

$total_views = 0;
$failures    = 0;
$today       = @date('Y-m-d');
$version     = explode('.', phpversion(), 3);

if (($version[0] >= 5) &&   // available since PHP 5.5.0
    ($version[1] >= 5)) {
    curl_multi_setopt($handle_all, CURLMOPT_PIPELINING, true);
    curl_multi_setopt($handle_all, CURLMOPT_MAXCONNECTS, 10);
}

for ($chunk = 0; $chunk < $chunks; $chunk++) {      // fetch one chunk at a time
    $id_limit = min(($chunk + 1) * CHUNK_SIZE, $articles_no);

    for ($id = $chunk * CHUNK_SIZE; $id < $id_limit; $id++)     // all articles in this chunk
        curl_multi_add_handle($handle_all, $handles[$id]);

    do {    // fetch the articles stats data in JSON format...
        $status = curl_multi_exec($handle_all, $running);
        progress_message();
    } while (($status == CURLM_CALL_MULTI_PERFORM) ||
             ($running > 0));

    for ($id = $chunk * CHUNK_SIZE; $id < $id_limit; $id++) {       // ... and process it
        $json = curl_multi_getcontent($handles[$id]);

        if (($json == '') ||    // is the JSON Ok?
            (($json = json_decode($json, true)) === null) ||
            !array_key_exists('daily_views', $json) ||
            !is_array($json['daily_views'])) {

            ++$failures;

            if (($message = curl_error($handles[$id])) != '') {     // for some reason, curl_errno()
                if (!array_key_exists($message, $error_msgs)) {     // always returns zero here
                    $errno = -1 * count($error_msgs) - 1;
                    $error_msgs[$message] = $errno;
                }
                else    // already seen
                    $errno = $error_msgs[$message];
            }
            else    // below -1 are cURL errors
                $errno = -1;

            $output[$id] = $errno;
        }
        else {  // JSON data Ok
            $views = 0;

            foreach ($json['daily_views'] as $key => $value)
                if (!$curr_month || ($key != $today))   // account only the whole days
                    $views += abs($value);              // just in case, should never be negative

            $total_views += $views;
            $output[$id]  = $views;
        }

        curl_multi_remove_handle($handle_all, $handles[$id]);
        curl_close($handles[$id]);

        progress_message();     // done with this chunk
    }

    if ($chunk != ($chunks - 1)) {      // don't sleep after the last chunk
        $message = '#';
        $limit   = CHUNK_SLEEP * 4;

        for ($i = 0; $i <= $limit; $i++) {
            if (progress_message($message) === true)    // only one "marker"
                $message = '.';

            usleep(250000);
        }
    }
}

curl_multi_close($handle_all);
echo(" done.\n\n");

// done fetching all chunks of the stats data, generate and print the output...

arsort($output, SORT_NUMERIC);

$error_msgs = array_flip($error_msgs);
$first_err  = true;

foreach ($output as $id => $views)
    if ($views >= 0)
        echo("- {$articles[$id]}: total " . plural_output($views, 'view') . "\n");
    else {
        if ($first_err === true) {      // display an empty line before
            echo("\n");                 // the first failure message
            $first_err = false;
        }

        echo("> {$articles[$id]}: failure ({$error_msgs[$views]})\n");
    }

// ... and the final summary

$articles_ok  = $articles_no - $failures;
$days         = !$curr_month
                ? cal_days_in_month(CAL_GREGORIAN, STATS_MONTH, STATS_YEAR)
                : (@date('j') - 1);
$month_name   = @date('F', @strtotime(STATS_YEAR . '-' . STATS_MONTH . '-01'));
$daily_views  = intval($total_views / $days);

$elapsed_time = microtime(true) - $start_time;
$elapsed_min  = intval($elapsed_time / 60);
$elapsed_sec  = round($elapsed_time - $elapsed_min * 60);

echo("\nDone, {$month_name} " . STATS_YEAR . ' statistics for ' . plural_output($articles_ok, 'article') .
     ' fetched in ' . (($elapsed_min > 0)
                       ? (plural_output($elapsed_min, 'minute') . ' and ')
                       : '') .
     plural_output($elapsed_sec, 'second') . ".\n" .
     (($failures > 0)
      ? ('Fetching the views statistics failed for ' . plural_output($failures, 'article') . ".\n")
      : '') .
     'Total ' . plural_output($total_views, 'view') . ', averaging in ' .
     plural_output($daily_views, 'view') . ' per day (' .
     plural_output($days, ($curr_month ? 'whole ' : '') . 'day') .
     ' in ' . ($curr_month ? 'current' : 'that') . " month).\n\n");

?>