Correct pylint for translate datasets.

tensorflow_datasets/translate/flores.py

@@ -13,12 +13,8 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-# Lint as: python3
 """Facebook Low Resource (FLoRes) machine translation benchmark dataset."""
 
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
 
 import collections
 
@@ -78,8 +74,12 @@ def __init__(self,
         name=name,
         description=description,
         version=tfds.core.Version(
-            "1.1.0",
+            "1.0.0",
             "New split API (https://tensorflow.org/datasets/splits)"),
+        supported_versions=[
+            tfds.core.Version(
+                "0.0.3", experiments={tfds.core.Experiment.S3: False}),
+        ],
         **kwargs)
     self.text_encoder_config = (
         text_encoder_config or tfds.features.text.TextEncoderConfig())
@@ -126,6 +126,7 @@ def _vocab_text_gen(self, files, language):
       yield ex[language]
 
   def _split_generators(self, dl_manager):
+    """Generate Splits"""
     dl_dir = dl_manager.download_and_extract(_DATA_URL)
 
     source, target = self.builder_config.language_pair

tensorflow_datasets/translate/wmt.py

@@ -13,13 +13,8 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-# Lint as: python3
 """WMT: Translate dataset."""
 
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-
 import codecs
 import functools
 import gzip
@@ -60,7 +55,7 @@
 ]
 
 
-class SubDataset(object):
+class SubDataset(object):  # pylint: disable=R0205
   """Class to keep track of information on a sub-dataset of WMT."""
 
   def __init__(self, name, target, sources, url, path, manual_dl_files=None):
@@ -102,12 +97,11 @@ def _inject_language(self, src, strings):
     def _format_string(s):
       if "{0}" in s and "{1}" and "{src}" in s:
         return s.format(*sorted([src, self.target]), src=src)
-      elif "{0}" in s and "{1}" in s:
+      if "{0}" in s and "{1}" in s:
         return s.format(*sorted([src, self.target]))
-      elif "{src}" in s:
+      if "{src}" in s:
         return s.format(src=src)
-      else:
-        return s
+      return s
     return [_format_string(s) for s in strings]
 
   def get_url(self, src):
@@ -675,6 +669,7 @@ def _vocab_text_gen(self, split_subsets, extraction_map, language):
       yield ex[language]
 
   def _split_generators(self, dl_manager):
+    """Generate Splits"""
     source, _ = self.builder_config.language_pair
 
     def _check_manual_files(ds):
@@ -939,7 +934,7 @@ def _parse_czeng(*paths, **kwargs):
     re_block = re.compile(r"^[^-]+-b(\d+)-\d\d[tde]")
     with tf.io.gfile.GFile(filter_path) as f:
       bad_blocks = {
-          blk for blk in re.search(
+          blk for blk in re.search(  # pylint: disable=R1721
               r"qw{([\s\d]*)}", f.read()).groups()[0].split()
       }
     logging.info(

tensorflow_datasets/translate/wmt19_test.py

@@ -16,15 +16,13 @@
 # Lint as: python3
 """Tests for WMT translate dataset module."""
 
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
 
 from tensorflow_datasets import testing
 from tensorflow_datasets.translate import wmt19
 
 
 class TranslateDeEnWmt19Test(testing.DatasetBuilderTestCase):
+  """Create testing.DatasetBuilderTestCase for de-en test"""
   DATASET_CLASS = wmt19.Wmt19Translate
   BUILDER_CONFIG_NAMES_TO_TEST = ["de-en"]
   OVERLAPPING_SPLITS = ["validation"]
@@ -46,6 +44,7 @@ class TranslateDeEnWmt19Test(testing.DatasetBuilderTestCase):
 
 
 class TranslateCsEnWmt19Test(testing.DatasetBuilderTestCase):
+  """Create testing.DatasetBuilderTestCase for cs-en test"""
   DATASET_CLASS = wmt19.Wmt19Translate
   BUILDER_CONFIG_NAMES_TO_TEST = ["cs-en"]
   OVERLAPPING_SPLITS = ["validation"]
@@ -65,5 +64,6 @@ class TranslateCsEnWmt19Test(testing.DatasetBuilderTestCase):
       "validation": 2,
   }
 
+
 if __name__ == "__main__":
   testing.test_main()

tensorflow_datasets/translate/wmt_test.py

@@ -29,10 +29,11 @@
 
 
 class TranslateWmtCustomConfigTest(testing.DatasetBuilderTestCase):
-
+  """Create testing.DatasetBuilderTestCase for de-en test"""
   @classmethod
-  def setUpClass(cls):
-    super(TranslateWmtCustomConfigTest, cls).setUpClass()
+  def setup_class(cls):
+    """Create configs """
+    super(TranslateWmtCustomConfigTest, cls).setup_class()
 
     config = wmt.WmtConfig(
         name="small",
@@ -47,8 +48,8 @@ def setUpClass(cls):
     wmt.WmtTranslate.BUILDER_CONFIGS = [config]
 
   @classmethod
-  def tearDownClass(cls):
-    super(TranslateWmtCustomConfigTest, cls).tearDownClass()
+  def teardown_class(cls):
+    super(TranslateWmtCustomConfigTest, cls).teardown_class()
     wmt.WmtTranslate.BUILDER_CONFIGS.pop()
 
   DATASET_CLASS = wmt.WmtTranslate
@@ -81,8 +82,9 @@ def tearDownClass(cls):
   }
 
   def test_gzip_reading(self):
+    """Testing gzip Reading"""
     results = [
-        x for _, x in wmt._parse_parallel_sentences(
+        x for _, x in wmt._parse_parallel_sentences(  # pylint: disable=protected-access
             os.path.join(self.example_dir, "first.cs.gz"),
             os.path.join(self.example_dir, "second.en.txt"))
     ]