add tests

datarobot_batch_scoring/reader.py

@@ -434,25 +434,6 @@ def sniff_dialect(sample, sep, skip_dialect, ui):
     return dialect
 
 
-def get_opener_and_mode(is_gz, text=False):
-    if is_gz:
-        if six.PY2:
-            mode = 'r' if text else 'rb'
-            return (gzip_with_encoding, mode)
-        else:
-            mode = 'rt' if text else 'rb'
-            return (gzip.open, mode)
-    else:
-        if six.PY2:
-            if text:
-                from io import open as io_open
-                return (io_open, 'r')
-            return (open, 'rU')
-        else:
-            mode = 'rt' if text else 'rb'
-            return (open, mode)
-
-
 def investigate_encoding_and_dialect(dataset, sep, ui, fast=False,
                                      encoding=None, skip_dialect=False,
                                      output_delimiter=None):
@@ -465,7 +446,7 @@ def investigate_encoding_and_dialect(dataset, sep, ui, fast=False,
     else:
         sample_size = DETECT_SAMPLE_SIZE_SLOW
     is_gz = dataset.endswith('.gz')
-    opener, mode = get_opener_and_mode(is_gz)
+    opener, mode = _get_opener_and_mode(is_gz)
     with opener(dataset, mode) as dfile:
         sample = dfile.read(sample_size)
 
@@ -479,7 +460,7 @@ def investigate_encoding_and_dialect(dataset, sep, ui, fast=False,
         encoding = encoding.lower()
         sample[:1000].decode(encoding)  # Fail here if the encoding is invalid
 
-    opener, mode = get_opener_and_mode(is_gz, text=True)
+    opener, mode = _get_opener_and_mode(is_gz, text=True)
     with opener(dataset, mode, encoding=encoding) as dfile:
         sample = dfile.read(sample_size)
 
@@ -539,7 +520,7 @@ def auto_sampler(dataset, encoding, ui):
 
     sample_size = AUTO_SAMPLE_SIZE
     is_gz = dataset.endswith('.gz')
-    opener, mode = get_opener_and_mode(is_gz, text=True)
+    opener, mode = _get_opener_and_mode(is_gz, text=True)
     with opener(dataset, mode, encoding=encoding) as dfile:
         sample = dfile.read(sample_size)
 
@@ -612,3 +593,18 @@ def peek_row(dataset, delimiter, ui, fast_mode, encoding):
     except StopIteration:
         raise ValueError('Cannot peek first row from {}'.format(dataset))
     return batch
+
+
+def _get_opener_and_mode(is_gz, text=False):
+    if is_gz:
+        if six.PY2:
+            return (gzip_with_encoding, 'r' if text else 'rb')
+        else:
+            return (gzip.open, 'rt' if text else 'rb')
+    else:
+        mode = 'rt' if text else 'rb'
+        if six.PY2:
+            from io import open as io_open
+            return (io_open, mode)
+        else:
+            return (open, mode)