Rework date and string encoding, add and fix tests

Author: jonmmease

packages/python/plotly/plotly/io/_json.py

@@ -3,8 +3,7 @@
 from six import string_types
 import json
 import decimal
-import os
-
+import datetime
 
 from plotly.io._utils import validate_coerce_fig_to_dict, validate_coerce_output_type
 from _plotly_utils.optional_imports import get_module
@@ -474,12 +473,19 @@ def clean_to_json_compatible(obj, **kwargs):
     if np is not None:
         if obj is np.ma.core.masked:
             return float("nan")
-        elif (
-            numpy_allowed
-            and isinstance(obj, np.ndarray)
-            and obj.dtype.kind in ("b", "i", "u", "f")
-        ):
-            return np.ascontiguousarray(obj)
+        elif isinstance(obj, np.ndarray):
+            if numpy_allowed and obj.dtype.kind in ("b", "i", "u", "f"):
+                return np.ascontiguousarray(obj)
+            elif obj.dtype.kind == "M":
+                # datetime64 array
+                return np.datetime_as_string(obj).tolist()
+            elif obj.dtype.kind == "U":
+                return obj.tolist()
+            elif obj.dtype.kind == "O":
+                # Treat object array as a lists, continue processing
+                obj = obj.tolist()
+        elif isinstance(obj, np.datetime64):
+            return str(obj)
 
     # pandas
     if pd is not None:
@@ -496,35 +502,29 @@ def clean_to_json_compatible(obj, **kwargs):
 
                 if not datetime_allowed:
                     # Note: We don't need to handle dropping timezones here because
-                    # numpy's datetime64 doesn't support them and pandas's tolist()
-                    # doesn't preserve them.
+                    # numpy's datetime64 doesn't support them and pandas's tz_localize
+                    # above drops them.
                     for i in range(len(dt_values)):
                         dt_values[i] = dt_values[i].isoformat()
 
                 return dt_values
 
     # datetime and date
-    if not datetime_allowed:
-        try:
-            # Need to drop timezone for scalar datetimes
-            return obj.replace(tzinfo=None).isoformat()
-        except (TypeError, AttributeError):
-            pass
+    try:
+        # Need to drop timezone for scalar datetimes. Don't need to convert
+        # to string since engine can do that
+        obj = obj.replace(tzinfo=None)
+        obj = obj.to_pydatetime()
+    except(TypeError, AttributeError):
+        pass
 
-        if np and isinstance(obj, np.datetime64):
-            return str(obj)
-    else:
-        res = None
+    if not datetime_allowed:
         try:
-            # Need to drop timezone for scalar datetimes. Don't need to convert
-            # to string since engine can do that
-            res = obj.replace(tzinfo=None)
-            res = res.to_pydatetime()
+            return obj.isoformat()
         except(TypeError, AttributeError):
             pass
-
-        if res is not None:
-            return res
+    elif isinstance(obj, datetime.datetime):
+        return obj
 
     # Try .tolist() convertible, do not recurse inside
     try:

packages/python/plotly/plotly/tests/test_io/test_to_from_plotly_json.py

@@ -96,6 +96,11 @@ def object_numpy_array(request):
     return np.array(["a", 1, [2, 3]])
 
 
+@pytest.fixture(scope="module")
+def numpy_unicode_array(request):
+    return np.array(["A", "BB", "CCC"], dtype="U")
+
+
 @pytest.fixture(
     scope="module",
     params=[
@@ -118,6 +123,7 @@ def datetime_value(request):
         lambda a: pd.DatetimeIndex(a),  # Pandas DatetimeIndex
         lambda a: pd.Series(pd.DatetimeIndex(a)),  # Pandas Datetime Series
         lambda a: pd.DatetimeIndex(a).values,  # Numpy datetime64 array
+        lambda a: np.array(a, dtype="object"),  # Numpy object array of datetime
     ]
 )
 def datetime_array(request, datetime_value):
@@ -143,6 +149,16 @@ def test_numeric_numpy_encoding(numeric_numpy_array, engine, pretty):
     check_roundtrip(result, engine=engine, pretty=pretty)
 
 
+def test_numpy_unicode_encoding(numpy_unicode_array, engine, pretty):
+    value = build_test_dict(numpy_unicode_array)
+    result = pio.to_json_plotly(value, engine=engine, pretty=pretty)
+
+    array_str = to_json_test(numpy_unicode_array.tolist())
+    expected = build_test_dict_string(array_str)
+    assert result == expected
+    check_roundtrip(result, engine=engine, pretty=pretty)
+
+
 def test_object_numpy_encoding(object_numpy_array, engine, pretty):
     value = build_test_dict(object_numpy_array)
     result = pio.to_json_plotly(value, engine=engine, pretty=pretty)
@@ -191,7 +207,7 @@ def to_str(v):
     elif isinstance(datetime_array, pd.DatetimeIndex):
         dt_values = [to_str(d) for d in datetime_array.to_pydatetime().tolist()]
     else:  # numpy datetime64 array
-        dt_values = datetime_array.tolist()
+        dt_values = [to_str(d) for d in datetime_array]
 
     array_str = to_json_test(dt_values)
     expected = build_test_dict_string(array_str)