From c085c2d39136aa19e434d5a26d36152e70940562 Mon Sep 17 00:00:00 2001
From: ghoward <gregory.howard@sword-group.com>
Date: Tue, 25 Apr 2017 17:44:16 +0200
Subject: [PATCH] Adding some unitests

---
 spacy/tests/fr/test_lemmatization.py | 36 ++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)
 create mode 100644 spacy/tests/fr/test_lemmatization.py

diff --git a/spacy/tests/fr/test_lemmatization.py b/spacy/tests/fr/test_lemmatization.py
new file mode 100644
index 000000000..702ab81e3
--- /dev/null
+++ b/spacy/tests/fr/test_lemmatization.py
@@ -0,0 +1,36 @@
+# coding: utf-8
+
+from __future__ import unicode_literals
+
+import pytest
+
+@pytest.mark.xfail
+def test_lemmatizer_(fr_tokenizer):
+    text = "Je suis allé au mois de janv. aux prud’hommes."
+    tokens = fr_tokenizer(text)
+    assert len(tokens) == 10
+    assert tokens[2].lemma_ == "aller"
+
+@pytest.mark.xfail
+def test_tokenizer_handles_exc_in_text_2(fr_tokenizer):
+    text = "Je dois manger ce soir"
+    tokens = fr_tokenizer(text)
+    assert len(tokens) == 11
+    assert tokens[1].lemma_ == "devoir"
+
+
+@pytest.mark.xfail
+def test_tokenizer_handles_exc_in_text_2(fr_tokenizer):
+    text = "Je dois manger ce soir"
+    tokens = fr_tokenizer(text)
+    assert len(tokens) == 11
+    assert tokens[1].lemma_ == "devoir"
+
+@pytest.mark.xfail
+def test_tokenizer_handles_exc_in_text_2(fr_tokenizer):
+    # This one is tricky because notes is a NOUN and can be a VERB
+    text = "Nous validerons vos notes plus tard"
+    tokens = fr_tokenizer(text)
+    assert len(tokens) == 11
+    assert tokens[1].lemma_ == "valider"
+    assert tokens[3].lemma_ == "notes"
\ No newline at end of file