Pytest for korean parallel corpus (#96)

ko-nlp · Oct 4, 2020 · 111a26f · 111a26f
1 parent e2d3204
commit 111a26f
Showing 1 changed file with 14 additions and 0 deletions.
diff --git a/tests/test_korean_parallel.py b/tests/test_korean_parallel.py
@@ -0,0 +1,14 @@
+from Korpora import Korpora, KoreanParallelKOENNewsKorpus
+
+
+def test_usage():
+    koen_news = Korpora.load('korean_parallel_koen_news')
+    koen_news_ = KoreanParallelKOENNewsKorpus()
+    assert len(koen_news.train) == len(koen_news_.train) == 94123
+    assert len(koen_news.dev) == 1000
+    assert len(koen_news.test) == 2000
+    print(f'str(korpus)\n{str(koen_news)}')
+    print(f'str(korpus.train)\n{str(koen_news.train)}')
+    for data in [koen_news.train, koen_news.dev, koen_news.test]:
+        for _ in data:
+            continue