Fix circle ci flaky fail of wmt example (#3485)

* force bleu

* fix wrong file name

* rename file

* different filenames for each example test

* test files should clean up after themselves

* test files should clean up after themselves

* do not force bleu

* correct typo

* fix isort

examples/summarization/bart/test_bart_examples.py

 import logging
+import os
 import sys
 import tempfile
 import unittest
@@ -8,6 +9,8 @@ from unittest.mock import patch
 from .evaluate_cnn import _run_generate
 
 
+output_file_name = "output_bart_sum.txt"
+
 articles = [" New York (CNN)When Liana Barrientos was 23 years old, she got married in Westchester County."]
 
 logging.basicConfig(level=logging.DEBUG)
@@ -19,10 +22,11 @@ class TestBartExamples(unittest.TestCase):
     def test_bart_cnn_cli(self):
         stream_handler = logging.StreamHandler(sys.stdout)
         logger.addHandler(stream_handler)
-        tmp = Path(tempfile.gettempdir()) / "utest_generations.hypo"
+        tmp = Path(tempfile.gettempdir()) / "utest_generations_bart_sum.hypo"
         with tmp.open("w") as f:
             f.write("\n".join(articles))
-        testargs = ["evaluate_cnn.py", str(tmp), "output.txt"]
+        testargs = ["evaluate_cnn.py", str(tmp), output_file_name]
         with patch.object(sys, "argv", testargs):
             _run_generate()
-            self.assertTrue(Path("output.txt").exists())
+            self.assertTrue(Path(output_file_name).exists())
+            os.remove(Path(output_file_name))

examples/summarization/t5/test_t5_examples.py

 import logging
+import os
 import sys
 import tempfile
 import unittest
@@ -8,6 +9,9 @@ from unittest.mock import patch
 from .evaluate_cnn import run_generate
 
 
+output_file_name = "output_t5_sum.txt"
+score_file_name = "score_t5_sum.txt"
+
 articles = ["New York (CNN)When Liana Barrientos was 23 years old, she got married in Westchester County."]
 
 logging.basicConfig(level=logging.DEBUG)
@@ -19,11 +23,13 @@ class TestT5Examples(unittest.TestCase):
     def test_t5_cli(self):
         stream_handler = logging.StreamHandler(sys.stdout)
         logger.addHandler(stream_handler)
-        tmp = Path(tempfile.gettempdir()) / "utest_generations.hypo"
+        tmp = Path(tempfile.gettempdir()) / "utest_generations_t5_sum.hypo"
         with tmp.open("w") as f:
             f.write("\n".join(articles))
-        testargs = ["evaluate_cnn.py", "t5-small", str(tmp), "output.txt", str(tmp), "score.txt"]
+        testargs = ["evaluate_cnn.py", "t5-small", str(tmp), output_file_name, str(tmp), score_file_name]
         with patch.object(sys, "argv", testargs):
             run_generate()
-            self.assertTrue(Path("output.txt").exists())
-            self.assertTrue(Path("score.txt").exists())
+            self.assertTrue(Path(output_file_name).exists())
+            self.assertTrue(Path(score_file_name).exists())
+            os.remove(Path(output_file_name))
+            os.remove(Path(score_file_name))

examples/translation/t5/test_t5_examples.py

 import logging
+import os
 import sys
 import tempfile
 import unittest
@@ -8,7 +9,11 @@ from unittest.mock import patch
 from .evaluate_wmt import run_generate
 
 
-text = [" New York (CNN)When Liana Barrientos was 23 years old, she got married in Westchester County."]
+text = ["When Liana Barrientos was 23 years old, she got married in Westchester County."]
+translation = ["Als Liana Barrientos 23 Jahre alt war, heiratete sie in Westchester County."]
+
+output_file_name = "output_t5_trans.txt"
+score_file_name = "score_t5_trans.txt"
 
 logging.basicConfig(level=logging.DEBUG)
 
@@ -19,10 +24,20 @@ class TestT5Examples(unittest.TestCase):
     def test_t5_cli(self):
         stream_handler = logging.StreamHandler(sys.stdout)
         logger.addHandler(stream_handler)
-        tmp = Path(tempfile.gettempdir()) / "utest_generations.hypo"
-        with tmp.open("w") as f:
+
+        tmp_source = Path(tempfile.gettempdir()) / "utest_generations_t5_trans.hypo"
+        with tmp_source.open("w") as f:
             f.write("\n".join(text))
-        testargs = ["evaluate_cnn.py", str(tmp), "output.txt", str(tmp), "score.txt"]
+
+        tmp_target = Path(tempfile.gettempdir()) / "utest_generations_t5_trans.target"
+        with tmp_target.open("w") as f:
+            f.write("\n".join(translation))
+
+        testargs = ["evaluate_wmt.py", str(tmp_source), output_file_name, str(tmp_target), score_file_name]
+
         with patch.object(sys, "argv", testargs):
             run_generate()
-            self.assertTrue(Path("output.txt").exists())
+            self.assertTrue(Path(output_file_name).exists())
+            self.assertTrue(Path(score_file_name).exists())
+            os.remove(Path(output_file_name))
+            os.remove(Path(score_file_name))