<?php
// Benchmarks of: http://stackoverflow.com/q/18359729/1928023


/**
 * Answer 1 using regexes
 *
 * Changed: Do nod read input from disk for performance measuring
 *
 * @autor hek2mgl
 * @link http://stackoverflow.com/a/18406873/1928023
 */
function answer_1($input) {
  $record = array();
  //foreach(file('input.txt') as $line) {
  foreach($input AS $line) {
    if(preg_match('~^(HD|BY|PD|LP|TD) ?(.*)?$~', $line, $matches)) {
      $currentKey = $matches[1];
      $record[$currentKey] = $matches[2];
    } else {
      $record[$currentKey] .= str_replace("\n", ' ', $line);
    }
  }
  return $record;
}


/**
 * Answer 2 not using regexes
 *
 * Changed: Do nod read input from disk for performance measuring
 *
 * @autor Emo Mosley
 * @link http://stackoverflow.com/a/18406908/1928023
 */
function answer_2($lines) {
  $fields = array('HD', 'BY', 'PD', 'LP', 'TD');
   # load file as array of lines
   //$lines = file($filename);
   if($lines === false)
      return(null);
   $sections = array();
   $code = "";
   $str = "";
   # examine each line to build section array
   for($i=0; $i<sizeof($lines); $i++) {
      $line = trim($lines[$i]);
      # check for special field codes
      $left = substr($line, 0, 2);
      if(in_array($left, $fields)) {
         # field code detected; first, finish previous section, if exists
         if($code) {
            # store the previous section
            $sections[$code] = trim($str);
         }
         # begin to process new section
         $code = $left;
         $str = trim(substr($line, 2));
      } else if($code && $line) {
         # keep a running string of section content
         $str .= " ".$line;
      }
   } # for i
   # check for no data
   if(!$code)
      return(null);
   # store the last section and return results
   $sections[$code] = trim($str);
   return($sections);
}


/**
 * Answer 3 using regexes
 *
 * @autor anubhava
 * @link http://stackoverflow.com/a/18407529/1928023
 */
function answer_3($s) {
  $match = array(); // will hold final output
  if (preg_match_all('~(^|[A-Z]{2})\s(.*?)(?=[A-Z]{2}\s|$)~s', $s, $arr)) {
      for ( $i = 0; $i < count($arr[1]); $i++ )
         $match[ trim($arr[1][$i]) ] = str_replace( "\n", "", $arr[2][$i] );
  }
  return $match;
}


/**
 * Answer 4 not using regexes
 *
 * @autor jgb
 * @link http://stackoverflow.com/a/18410733/1928023
 */
function answer_4(array $parts, $str, $eol=PHP_EOL) {
  $ret=array_fill_keys($parts, '');
  $current=null;
  foreach(explode($eol, $str) AS $line) {
    $substr = substr($line, 0, 2);
    if (isset($ret[$substr])) {
      $current = $substr;
      $line = trim(substr($line, 2));
    }
    if ($current) $ret[$current] .= $line;
  }
  return $ret;
}



$str="HD Alcoa Earnings Soar; Outlook Stays Upbeat
BY By James R. Hagerty and Matthew Day
PD 12 July 2011
LP

Alcoa Inc.'s profit more than doubled in the second quarter.
The giant aluminum producer managed to meet analysts' forecasts.

However, profits wereless than expected

TD
Licence this article via our website:

http://example.com";
$array = explode(PHP_EOL, $str);

$iterations=100000;

/*
var_dump(answer_1($array));
var_dump(answer_2($array));
var_dump(answer_3($str));
var_dump(answer_4(array('HD', 'BY', 'PD', 'LP', 'TD'), $str));
exit;
*/

// Start benchmarking
echo "Answer 1 by: hek2mgl     ";
$benchmark_start = microtime(true);
for($i=0;$i<$iterations;$i++) answer_1($array);
echo round(microtime(true) - $benchmark_start, 3) . " seconds (regexp)\n";

echo "Answer 2 by: Emo Mosley  ";
$benchmark_start = microtime(true);
for($i=0;$i<$iterations;$i++) answer_2($array);
echo round(microtime(true) - $benchmark_start, 3) . " seconds\n";

echo "Answer 3 by: anubhava    ";
$benchmark_start = microtime(true);
for($i=0;$i<$iterations;$i++) answer_3($str);
echo round(microtime(true) - $benchmark_start, 3) . " seconds (regexp)\n";

echo "Answer 4 by: jgb         ";
$benchmark_start = microtime(true);
for($i=0;$i<$iterations;$i++) answer_4(array('HD', 'BY', 'PD', 'LP', 'TD'), $str);
echo round(microtime(true) - $benchmark_start, 3) . " seconds\n";