read_sas catches own error #24548 (#24554)

Author: benjaminr

doc/source/whatsnew/v0.24.0.rst

@@ -1599,6 +1599,7 @@ Notice how we now instead output ``np.nan`` itself instead of a stringified form
 - :func:`read_sas()` will parse numbers in sas7bdat-files that have width less than 8 bytes correctly. (:issue:`21616`)
 - :func:`read_sas()` will correctly parse sas7bdat files with many columns (:issue:`22628`)
 - :func:`read_sas()` will correctly parse sas7bdat files with data page types having also bit 7 set (so page type is 128 + 256 = 384) (:issue:`16615`)
+- Bug in :func:`read_sas()` in which an incorrect error was raised on an invalid file format. (:issue:`24548`)
 - Bug in :meth:`detect_client_encoding` where potential ``IOError`` goes unhandled when importing in a mod_wsgi process due to restricted access to stdout. (:issue:`21552`)
 - Bug in :func:`to_html()` with ``index=False`` misses truncation indicators (...) on truncated DataFrame (:issue:`15019`, :issue:`22783`)
 - Bug in :func:`to_html()` with ``index=False`` when both columns and row index are ``MultiIndex`` (:issue:`22579`)

pandas/io/sas/sasreader.py

@@ -16,8 +16,8 @@ def read_sas(filepath_or_buffer, format=None, index=None, encoding=None,
     filepath_or_buffer : string or file-like object
         Path to the SAS file.
     format : string {'xport', 'sas7bdat'} or None
-        If None, file format is inferred.  If 'xport' or 'sas7bdat',
-        uses the corresponding format.
+        If None, file format is inferred from file extension. If 'xport' or
+        'sas7bdat', uses the corresponding format.
     index : identifier of index column, defaults to None
         Identifier of column that should be used as index of the DataFrame.
     encoding : string, default is None
@@ -39,16 +39,13 @@ def read_sas(filepath_or_buffer, format=None, index=None, encoding=None,
         filepath_or_buffer = _stringify_path(filepath_or_buffer)
         if not isinstance(filepath_or_buffer, compat.string_types):
             raise ValueError(buffer_error_msg)
-        try:
-            fname = filepath_or_buffer.lower()
-            if fname.endswith(".xpt"):
-                format = "xport"
-            elif fname.endswith(".sas7bdat"):
-                format = "sas7bdat"
-            else:
-                raise ValueError("unable to infer format of SAS file")
-        except ValueError:
-            pass
+        fname = filepath_or_buffer.lower()
+        if fname.endswith(".xpt"):
+            format = "xport"
+        elif fname.endswith(".sas7bdat"):
+            format = "sas7bdat"
+        else:
+            raise ValueError("unable to infer format of SAS file")
 
     if format.lower() == 'xport':
         from pandas.io.sas.sas_xport import XportReader

pandas/tests/io/sas/test_sas.py

@@ -3,6 +3,7 @@
 from pandas.compat import StringIO
 
 from pandas import read_sas
+import pandas.util.testing as tm
 
 
 class TestSas(object):
@@ -15,3 +16,10 @@ def test_sas_buffer_format(self):
                "name, you must specify a format string")
         with pytest.raises(ValueError, match=msg):
             read_sas(b)
+
+    def test_sas_read_no_format_or_extension(self):
+        # see gh-24548
+        msg = ("unable to infer format of SAS file")
+        with tm.ensure_clean('test_file_no_extension') as path:
+            with pytest.raises(ValueError, match=msg):
+                read_sas(path)