Merge branch 'develop' into modularize

Author: janvanrijn

openml/_api_calls.py

@@ -95,7 +95,7 @@ def _read_url_files(url, data=None, file_dictionary=None, file_elements=None):
     # 'gzip,deflate'
     response = requests.post(url, data=data, files=file_elements)
     if response.status_code != 200:
-        raise _parse_server_exception(response)
+        raise _parse_server_exception(response, url=url)
     if 'Content-Encoding' not in response.headers or \
             response.headers['Content-Encoding'] != 'gzip':
         warnings.warn('Received uncompressed content from OpenML for %s.' % url)
@@ -117,14 +117,14 @@ def _read_url(url, data=None):
         response = requests.post(url, data=data)
 
     if response.status_code != 200:
-        raise _parse_server_exception(response)
+        raise _parse_server_exception(response, url=url)
     if 'Content-Encoding' not in response.headers or \
             response.headers['Content-Encoding'] != 'gzip':
         warnings.warn('Received uncompressed content from OpenML for %s.' % url)
     return response.text
 
 
-def _parse_server_exception(response):
+def _parse_server_exception(response, url=None):
     # OpenML has a sopisticated error system
     # where information about failures is provided. try to parse this
     try:
@@ -143,4 +143,9 @@ def _parse_server_exception(response):
         # 512 for runs, 370 for datasets (should be 372), 500 for flows
         # 482 for tasks
         return OpenMLServerNoResult(code, message, additional)
-    return OpenMLServerException(code, message, additional)
+    return OpenMLServerException(
+        code=code,
+        message=message,
+        additional=additional,
+        url=url
+    )

openml/datasets/functions.py

@@ -1,4 +1,5 @@
 from collections import OrderedDict
+import hashlib
 import io
 import os
 import re
@@ -365,6 +366,8 @@ def _get_dataset_arff(did_cache_dir, description):
         Location of arff file.
     """
     output_file_path = os.path.join(did_cache_dir, "dataset.arff")
+    md5_checksum_fixture = description.get("oml:md5_checksum")
+    did = description.get("oml:id")
 
     # This means the file is still there; whether it is useful is up to
     # the user and not checked by the program.
@@ -377,6 +380,14 @@ def _get_dataset_arff(did_cache_dir, description):
 
     url = description['oml:url']
     arff_string = _read_url(url)
+    md5 = hashlib.md5()
+    md5.update(arff_string.encode('utf8'))
+    md5_checksum = md5.hexdigest()
+    if md5_checksum != md5_checksum_fixture:
+        raise ValueError(
+            'Checksum %s of downloaded dataset %d is unequal to the checksum '
+            '%s sent by the server.' % (md5_checksum, did, md5_checksum_fixture)
+        )
 
     with io.open(output_file_path, "w", encoding='utf8') as fh:
         fh.write(arff_string)

openml/exceptions.py

@@ -16,9 +16,13 @@ class OpenMLServerException(OpenMLServerError):
     """exception for when the result of the server was
        not 200 (e.g., listing call w/o results). """
 
-    def __init__(self, code, message, additional=None):
+    # Code needs to be optional to allow the exceptino to be picklable:
+    # https://stackoverflow.com/questions/16244923/how-to-make-a-custom-exception-class-with-multiple-init-args-pickleable
+    def __init__(self, message, code=None, additional=None, url=None):
+        self.message = message
         self.code = code
         self.additional = additional
+        self.url = url
         super(OpenMLServerException, self).__init__(message)
 
 

tests/test_datasets/test_dataset_functions.py

@@ -200,6 +200,20 @@ def test__getarff_path_dataset_arff(self):
         self.assertIsInstance(arff_path, str)
         self.assertTrue(os.path.exists(arff_path))
 
+    def test__getarff_md5_issue(self):
+        description = {
+            'oml:id': 5,
+            'oml:md5_checksum': 'abc',
+            'oml:url': 'https://www.openml.org/data/download/61',
+        }
+        self.assertRaisesRegexp(
+            ValueError,
+            'Checksum ad484452702105cbf3d30f8deaba39a9 of downloaded dataset 5 '
+            'is unequal to the checksum abc sent by the server.',
+            _get_dataset_arff,
+            self.workdir, description,
+        )
+
     def test__get_dataset_features(self):
         features = _get_dataset_features(self.workdir, 2)
         self.assertIsInstance(features, dict)