add validation for strings in datasets

openml/datasets/dataset.py

@@ -1,4 +1,5 @@
 from collections import OrderedDict
+import re
 import gzip
 import io
 import logging
@@ -108,7 +109,17 @@ def __init__(self, name, description, format=None,
                  paper_url=None, update_comment=None,
                  md5_checksum=None, data_file=None, features=None,
                  qualities=None, dataset=None):
-
+        if description and not re.match("^[\x00-\x7F]*$", description):
+            # not basiclatin (XSD complains)
+            raise ValueError("Invalid symbols in description: {}".format(
+                description))
+        if citation and not re.match("^[\x00-\x7F]*$", citation):
+            # not basiclatin (XSD complains)
+            raise ValueError("Invalid symbols in citation: {}".format(
+                citation))
+        if not re.match("^[a-zA-Z0-9_\\-\\.\\(\\),]+$", name):
+            # regex given by server in error message
+            raise ValueError("Invalid symbols in name: {}".format(name))
         # TODO add function to check if the name is casual_string128
         # Attributes received by querying the RESTful API
         self.dataset_id = int(dataset_id) if dataset_id is not None else None

tests/test_datasets/test_dataset.py

@@ -31,10 +31,24 @@ def setUp(self):
     def test_repr(self):
         # create a bare-bones dataset as would be returned by
         # create_dataset
-        data = openml.datasets.OpenMLDataset(name="some name",
+        data = openml.datasets.OpenMLDataset(name="somename",
                                              description="a description")
         str(data)
 
+    def test_init_string_validation(self):
+        with pytest.raises(ValueError, match="Invalid symbols in name"):
+            openml.datasets.OpenMLDataset(name="some name",
+                                          description="a description")
+
+        with pytest.raises(ValueError, match="Invalid symbols in description"):
+            openml.datasets.OpenMLDataset(name="somename",
+                                          description="a descriptïon")
+
+        with pytest.raises(ValueError, match="Invalid symbols in citation"):
+            openml.datasets.OpenMLDataset(name="somename",
+                                          description="a description",
+                                          citation="Something by Müller")
+
     def test_get_data_array(self):
         # Basic usage
         rval, _, categorical, attribute_names = self.dataset.get_data(dataset_format='array')