Merge pull request #1400 from devin-petersohn/bugs/1379

modin/engines/base/io/text/csv_reader.py

@@ -18,32 +18,14 @@
 import sys
 
 
-def pathlib_or_pypath(filepath_or_buffer):
-    try:
-        import py
-
-        if isinstance(filepath_or_buffer, py.path.local):
-            return True
-    except ImportError:  # pragma: no cover
-        pass
-    try:
-        import pathlib
-
-        if isinstance(filepath_or_buffer, pathlib.Path):
-            return True
-    except ImportError:  # pragma: no cover
-        pass
-    return False
-
-
 class CSVReader(TextFileReader):
     @classmethod
     def read(cls, filepath_or_buffer, **kwargs):
         if isinstance(filepath_or_buffer, str):
             if not cls.file_exists(filepath_or_buffer):
                 return cls.single_worker_read(filepath_or_buffer, **kwargs)
             filepath_or_buffer = cls.get_path(filepath_or_buffer)
-        elif not pathlib_or_pypath(filepath_or_buffer):
+        elif not cls.pathlib_or_pypath(filepath_or_buffer):
             return cls.single_worker_read(filepath_or_buffer, **kwargs)
         compression_type = cls.infer_compression(
             filepath_or_buffer, kwargs.get("compression")

modin/engines/base/io/text/json_reader.py

@@ -21,7 +21,12 @@
 class JSONReader(TextFileReader):
     @classmethod
     def read(cls, path_or_buf, **kwargs):
-        path_or_buf = cls.get_path(path_or_buf)
+        if isinstance(path_or_buf, str):
+            if not cls.file_exists(path_or_buf):
+                return cls.single_worker_read(path_or_buf, **kwargs)
+            path_or_buf = cls.get_path(path_or_buf)
+        elif not cls.pathlib_or_pypath(path_or_buf):
+            return cls.single_worker_read(path_or_buf, **kwargs)
         if not kwargs.get("lines", False):
             return cls.single_worker_read(path_or_buf, **kwargs)
         columns = pandas.read_json(

modin/engines/base/io/text/text_file_reader.py

@@ -52,3 +52,21 @@ def build_partition(cls, partition_ids, row_lengths, column_widths):
                 for i in range(len(partition_ids))
             ]
         )
+
+    @classmethod
+    def pathlib_or_pypath(cls, filepath_or_buffer):
+        try:
+            import py
+
+            if isinstance(filepath_or_buffer, py.path.local):
+                return True
+        except ImportError:  # pragma: no cover
+            pass
+        try:
+            import pathlib
+
+            if isinstance(filepath_or_buffer, pathlib.Path):
+                return True
+        except ImportError:  # pragma: no cover
+            pass
+        return False

modin/pandas/test/test_io.py

@@ -23,7 +23,13 @@
 import shutil
 import sqlalchemy as sa
 
-from .utils import df_equals
+from .utils import (
+    df_equals,
+    json_short_string,
+    json_short_bytes,
+    json_long_string,
+    json_long_bytes,
+)
 
 from modin import __execution_engine__
 
@@ -474,6 +480,18 @@ def test_from_json_lines():
     teardown_json_file()
 
 
+@pytest.mark.parametrize(
+    "data", [json_short_string, json_short_bytes, json_long_string, json_long_bytes],
+)
+def test_read_json_string_bytes(data):
+    with pytest.warns(UserWarning):
+        modin_df = pd.read_json(data)
+    # For I/O objects we need to rewind to reuse the same object.
+    if hasattr(data, "seek"):
+        data.seek(0)
+    df_equals(modin_df, pandas.read_json(data))
+
+
 def test_from_html():
     setup_html_file(SMALL_ROW_SIZE)
 

modin/pandas/test/utils.py

@@ -16,6 +16,7 @@
 from pandas.util.testing import assert_almost_equal, assert_frame_equal
 import modin.pandas as pd
 from modin.pandas.utils import to_pandas
+from io import BytesIO
 
 random_state = np.random.RandomState(seed=42)
 
@@ -300,6 +301,48 @@
 
 # END parametrizations of common kwargs
 
+json_short_string = """[{"project": "modin"}]"""
+json_long_string = """{
+        "quiz": {
+            "sport": {
+                "q1": {
+                    "question": "Which one is correct team name in NBA?",
+                    "options": [
+                        "New York Bulls",
+                        "Los Angeles Kings",
+                        "Golden State Warriros",
+                        "Huston Rocket"
+                    ],
+                    "answer": "Huston Rocket"
+                }
+            },
+            "maths": {
+                "q1": {
+                    "question": "5 + 7 = ?",
+                    "options": [
+                        "10",
+                        "11",
+                        "12",
+                        "13"
+                    ],
+                    "answer": "12"
+                },
+                "q2": {
+                    "question": "12 - 8 = ?",
+                    "options": [
+                        "1",
+                        "2",
+                        "3",
+                        "4"
+                    ],
+                    "answer": "4"
+                }
+            }
+        }
+    }"""
+json_long_bytes = BytesIO(json_long_string.encode(encoding="UTF-8"))
+json_short_bytes = BytesIO(json_short_string.encode(encoding="UTF-8"))
+
 
 def df_equals(df1, df2):
     """Tests if df1 and df2 are equal.