<?php
/**
* Example of stemming using NlpTools PorterStemmer
*
* @author Glenn De Backer <*****@*****.**>
*/
include 'vendor/autoload.php';
use NlpTools\Stemmers\PorterStemmer;
// init PorterStemmer
$stemmer = new PorterStemmer();
// stemming variants of upload
printf("%s\n", $stemmer->stem("uploading"));
printf("%s\n", $stemmer->stem("uploaded"));
printf("%s\n", $stemmer->stem("uploads"));
// stemming variants of delete
printf("%s\n", $stemmer->stem("delete"));
printf("%s\n", $stemmer->stem("deleted"));
printf("%s\n", $stemmer->stem("deleting"));
// stemming variants of computer
printf("%s\n", $stemmer->stem("computer"));
printf("%s\n", $stemmer->stem("computers"));
/*
* words.txt and stems.txt are taken from
* http://tartarus.org/~martin/PorterStemmer/
*
* The other porter stemmer implementation is the one mentioned in
* http://tartarus.org/~martin/PorterStemmer/ as a php implementation
* */
include '../../../autoloader.php';
include 'other_php_porter_stemmer.php';
use NlpTools\Stemmers\PorterStemmer as OurPorterStemmer;
$stemmer = new OurPorterStemmer();
$wordlist = file('words.txt', FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
$start = microtime(true);
foreach ($wordlist as $word) {
$stemmer->stem($word);
}
$dur1 = microtime(true) - $start;
$start = microtime(true);
foreach ($wordlist as $word) {
PorterStemmer::Stem($word);
}
$dur2 = microtime(true) - $start;
echo $dur1, PHP_EOL;
echo $dur2, PHP_EOL;
$speedup = $dur1 / $dur2;
if ($speedup > 1) {
printf("NlpTools implementation is %.2f%% slower\n", 100 * (1 - 1 / $speedup));
} else {
printf("NlpTools implementation is %.2f%% faster\n", 100 * (1 - $speedup));
}
<?php
/*
* words.txt and stems.txt are taken from
* http://tartarus.org/~martin/PorterStemmer/
* */
include '../../../autoloader.php';
$words = fopen('words.txt', 'r');
$stems = fopen('stems.txt', 'r');
use NlpTools\Stemmers\PorterStemmer;
$stemmer = new PorterStemmer();
while (!feof($words)) {
$word = substr(fgets($words), 0, -1);
$stem = substr(fgets($stems), 0, -1);
$our_stem = $stemmer->stem($word);
if ($our_stem !== $stem) {
echo $word, ', stem: ', $stem, ' our_stem: ', $our_stem, PHP_EOL;
}
}