Merge f7db6ba into 91e1e65

CHANGELOG.rst

@@ -46,7 +46,7 @@ Removed
 Fixed
 -----
 - Fixed Luis emulation output to add start, end position and confidence for each entity.
-
+- Fixed byte encoding issue where training data could not be loaded by URL in python 3.
 
 [0.12.3] - 2018-05-02
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

rasa_nlu/training_data/loading.py

@@ -70,7 +70,8 @@ def load_data_from_url(url, language='en'):
     try:
         response = requests.get(url)
         response.raise_for_status()
-        temp_data_file = utils.create_temporary_file(response.content)
+        temp_data_file = utils.create_temporary_file(response.content,
+                                                     mode="w+b")
         return _load(temp_data_file, language)
     except Exception as e:
         logger.warning("Could not retrieve training data "

rasa_nlu/utils/__init__.py

@@ -331,13 +331,14 @@ def pycloud_pickle(file_name, obj):
         cloudpickle.dump(obj, f)
 
 
-def create_temporary_file(data, suffix=""):
-    """Creates a tempfile.NamedTemporaryFile object for data"""
+def create_temporary_file(data, suffix="", mode="w+"):
+    """Creates a tempfile.NamedTemporaryFile object for data.
+
+    mode defines NamedTemporaryFile's  mode parameter in py3."""
 
     if PY3:
-        f = tempfile.NamedTemporaryFile("w+", suffix=suffix,
-                                        delete=False,
-                                        encoding="utf-8")
+        f = tempfile.NamedTemporaryFile(mode=mode, suffix=suffix,
+                                        delete=False)
         f.write(data)
     else:
         f = tempfile.NamedTemporaryFile("w+", suffix=suffix,

tests/base/test_training_data.py

@@ -332,3 +332,37 @@ def test_training_data_conversion(tmpdir, data_file, gold_standard_file,
     # to dump to the file and diff using git
     # with io.open(gold_standard_file) as f:
     #     f.write(td.as_json(indent=2))
+
+
+def test_url_data_format():
+    data = u"""
+    {
+      "rasa_nlu_data": {
+        "entity_synonyms": [
+          {
+            "value": "nyc",
+            "synonyms": ["New York City", "nyc", "the big apple"]
+          }
+        ],
+        "common_examples" : [
+          {
+            "text": "show me flights to New York City",
+            "intent": "unk",
+            "entities": [
+              {
+                "entity": "destination",
+                "start": 19,
+                "end": 32,
+                "value": "NYC"
+              }
+            ]
+          }
+        ]
+      }
+    }"""
+    fname = utils.create_temporary_file(data.encode("utf-8"),
+                                        suffix="_tmp_training_data.json",
+                                        mode="w+b")
+    data = utils.read_json_file(fname)
+    assert data is not None
+    validate_rasa_nlu_data(data)