<?php
/**
* SeekQuarry/Yioop --
* Open Source Pure PHP Search Engine, Crawler, and Indexer
*
* Copyright (C) 2009 - 2026 Chris Pollett chris@pollett.org
*
* LICENSE:
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <https://www.gnu.org/licenses/>.
*
* @author Chris Pollett chris@pollett.org
* @license https://www.gnu.org/licenses/ GPL3
* @link https://www.seekquarry.com/
* @copyright 2009 - 2026
* @filesource
*/
namespace seekquarry\yioop\locale\ko\resources;
use seekquarry\yioop\models\LocaleModel;
/**
* Korean specific tokenization code. Typically, tokenizer.php
* either contains a stemmer for the language in question or
* it specifies how many characters in a char gram
*
* @author Chris Pollett
*/
class Tokenizer
{
/**
* A list of frequently occurring terms for this locale which should
* be excluded from certain kinds of queries. This is also used
* for language detection
* @var array
*/
public static $stop_words = ['λ‘', 'λλ', 'κ·Έμ', 'κ·Έ', 'κ·Έ', 'νλ€',
'μ λν', 'μ', 'μλ₯΄', 'μ', 'κ·Έλ€', 'μλ€', 'μ', 'μΌ', 'μ΄', 'μ΄',
'λΆν°', 'μ μν΄', 'λ¨κ±°μ΄', 'λ¨μ΄', 'νμ§λ§', '무μ', 'λ€μ', 'μ΄λ€', 'κ·Έ',
'λΉμ ', 'λλ', 'νλ€', 'μ', 'μ', 'μ', 'κ³Ό', 'μ΄', 'μ', 'μ°λ¦¬', 'μ',
'μμ', 'λ€λ₯Έ', 'νλ€', 'νλ', 'ν ', 'μμ μ', 'μκ°', 'λ©΄', 'κ²', 'λ°©λ²',
'λ§νλ€', 'μ΄', 'κ°', 'μ΄μΌκΈ°', 'νμ§', 'μΈνΈ', 'μΈ', 'νμ', '곡기', 'μ',
'λν', 'μ¬μ', 'μμ', 'λ', 'λ£μ΄', 'ν', 'μ½κΈ°', 'μ', 'ν¬νΈ', 'ν°',
'μ² μ', 'μΆκ°', 'λ', 'λ
', 'μ¬κΈ°', 'ν΄μΌ', 'ν°', 'λμ', 'μ΄λ¬ν', 'λ°λΌ',
'νμ', 'μ΄μ ', 'λ¬Έμ', 'λ¨μ', 'λ³κ²½', 'κ°λ€', 'λΉ', 'μ’
λ₯', 'μ€ν',
'νμκ°μλ€', 'μ§', 'μ¬μ§', 'μν', 'μ°λ¦¬', 'λ€μ', 'λλ¬Ό', 'ν¬μΈνΈ',
'μ΄λ¨Έλ', 'μΈκ³', 'κ°κΉμ΄', 'ꡬμΆ', 'μκΈ°', 'μ§κ΅¬', 'μλ²μ§'];
/**
* How many characters in a char gram for this locale
* @var int
*/
public static $char_gram_len = 3;
/**
* Removes the stop words from the page (used for Word Cloud generation
* and language detection)
*
* @param mixed $data either a string or an array of string to remove
* stop words from
* @return mixed $data with no stop words
*/
public static function stopwordsRemover($data)
{
static $pattern = "";
if (empty($pattern)) {
$pattern = '/(' . implode('|', self::$stop_words) . ')/u';
}
$data = preg_replace($pattern, '', $data);
return $data;
}
}