From 3dff40ea1d5797b82c3ef12c749fc8a580004acd Mon Sep 17 00:00:00 2001
From: Maxime COLIN <maxime.colin@elao.com>
Date: Mon, 22 May 2017 23:18:27 +0200
Subject: [PATCH] Add french stopwords (#92)

* Add french stopwords

* Add french stopwords test
---
 .../FeatureExtraction/StopWords/French.php    | 29 +++++++++++++++++++
 .../Phpml/FeatureExtraction/StopWordsTest.php |  8 +++++
 2 files changed, 37 insertions(+)
 create mode 100644 src/Phpml/FeatureExtraction/StopWords/French.php

diff --git a/src/Phpml/FeatureExtraction/StopWords/French.php b/src/Phpml/FeatureExtraction/StopWords/French.php
new file mode 100644
index 0000000..96cc110
--- /dev/null
+++ b/src/Phpml/FeatureExtraction/StopWords/French.php
@@ -0,0 +1,29 @@
+<?php
+
+declare(strict_types=1);
+
+namespace Phpml\FeatureExtraction\StopWords;
+
+use Phpml\FeatureExtraction\StopWords;
+
+final class French extends StopWords
+{
+    /**
+     * @var array
+     */
+    protected $stopWords = [
+        'alors', 'au', 'aucuns', 'aussi', 'autre', 'avant', 'avec', 'avoir', 'bon', 'car', 'ce', 'cela', 'ces', 'ceux', 'chaque', 'ci',
+        'comme', 'comment', 'dans', 'des', 'du', 'dedans', 'dehors', 'depuis', 'devrait', 'doit', 'donc', 'dos', 'début', 'elle', 'elles',
+        'en', 'encore', 'essai', 'est', 'et', 'eu', 'fait', 'faites', 'fois', 'font', 'hors', 'ici', 'il', 'ils', 'je', 'juste', 'la',
+        'le', 'les', 'leur', 'là', 'ma', 'maintenant', 'mais', 'mes', 'mine', 'moins', 'mon', 'mot', 'même', 'ni', 'nommés', 'notre',
+        'nous', 'ou', 'où', 'par', 'parce', 'pas', 'peut', 'peu', 'plupart', 'pour', 'pourquoi', 'quand', 'que', 'quel', 'quelle',
+        'quelles', 'quels', 'qui', 'sa', 'sans', 'ses', 'seulement', 'si', 'sien', 'son', 'sont', 'sous', 'soyez', 'sujet', 'sur', 'ta',
+        'tandis', 'tellement', 'tels', 'tes', 'ton', 'tous', 'tout', 'trop', 'très', 'tu', 'voient', 'vont', 'votre', 'vous', 'vu',
+        'ça', 'étaient', 'état', 'étions', 'été', 'être',
+    ];
+
+    public function __construct()
+    {
+        parent::__construct($this->stopWords);
+    }
+}
diff --git a/tests/Phpml/FeatureExtraction/StopWordsTest.php b/tests/Phpml/FeatureExtraction/StopWordsTest.php
index dd0a185..4979860 100644
--- a/tests/Phpml/FeatureExtraction/StopWordsTest.php
+++ b/tests/Phpml/FeatureExtraction/StopWordsTest.php
@@ -45,4 +45,12 @@ class StopWordsTest extends TestCase
         $this->assertTrue($stopWords->isStopWord('wam'));
         $this->assertFalse($stopWords->isStopWord('transhumanizm'));
     }
+
+    public function testFrenchStopWords()
+    {
+        $stopWords = StopWords::factory('French');
+
+        $this->assertTrue($stopWords->isStopWord('alors'));
+        $this->assertFalse($stopWords->isStopWord('carte'));
+    }
 }