Clarify whitespace behavior in read_fwf documentation (#16772)

Author: Lucas Kushner

doc/source/io.rst

@@ -1258,7 +1258,8 @@ Files with Fixed Width Columns
 
 While ``read_csv`` reads delimited data, the :func:`read_fwf` function works
 with data files that have known and fixed column widths. The function parameters
-to ``read_fwf`` are largely the same as `read_csv` with two extra parameters:
+to ``read_fwf`` are largely the same as `read_csv` with two extra parameters, and
+a different usage of the ``delimiter`` parameter:
 
   - ``colspecs``: A list of pairs (tuples) giving the extents of the
     fixed-width fields of each line as half-open intervals (i.e.,  [from, to[ ).
@@ -1267,6 +1268,9 @@ to ``read_fwf`` are largely the same as `read_csv` with two extra parameters:
     behaviour, if not specified, is to infer.
   - ``widths``: A list of field widths which can be used instead of 'colspecs'
     if the intervals are contiguous.
+  - ``delimiter``: Characters to consider as filler characters in the fixed-width file.
+    Can be used to specify the filler character of the fields
+    if it is not spaces (e.g., '~').
 
 .. ipython:: python
    :suppress:

pandas/io/parsers.py

@@ -63,8 +63,6 @@
     file. For file URLs, a host is expected. For instance, a local file could
     be file ://localhost/path/to/table.csv
 %s
-delimiter : str, default ``None``
-    Alternative argument name for sep.
 delim_whitespace : boolean, default False
     Specifies whether or not whitespace (e.g. ``' '`` or ``'\t'``) will be
     used as the sep. Equivalent to setting ``sep='\s+'``. If this option
@@ -316,7 +314,9 @@
     be used automatically. In addition, separators longer than 1 character and
     different from ``'\s+'`` will be interpreted as regular expressions and
     will also force the use of the Python parsing engine. Note that regex
-    delimiters are prone to ignoring quoted data. Regex example: ``'\r\t'``"""
+    delimiters are prone to ignoring quoted data. Regex example: ``'\r\t'``
+delimiter : str, default ``None``
+    Alternative argument name for sep."""
 
 _read_csv_doc = """
 Read CSV (comma-separated) file into DataFrame
@@ -341,15 +341,16 @@
 widths : list of ints. optional
     A list of field widths which can be used instead of 'colspecs' if
     the intervals are contiguous.
+delimiter : str, default ``'\t' + ' '``
+    Characters to consider as filler characters in the fixed-width file.
+    Can be used to specify the filler character of the fields
+    if it is not spaces (e.g., '~').
 """
 
 _read_fwf_doc = """
 Read a table of fixed-width formatted lines into DataFrame
 
 %s
-
-Also, 'delimiter' is used to specify the filler character of the
-fields if it is not spaces (e.g., '~').
 """ % (_parser_params % (_fwf_widths, ''))
 
 

pandas/tests/io/parser/test_read_fwf.py

@@ -405,3 +405,32 @@ def test_skiprows_inference_empty(self):
 
         with pytest.raises(EmptyDataError):
             read_fwf(StringIO(test), skiprows=3)
+
+    def test_whitespace_preservation(self):
+        # Addresses Issue #16772
+        data_expected = """
+ a ,bbb
+ cc,dd """
+        expected = read_csv(StringIO(data_expected), header=None)
+
+        test_data = """
+ a bbb
+ ccdd """
+        result = read_fwf(StringIO(test_data), widths=[3, 3],
+                          header=None, skiprows=[0], delimiter="\n\t")
+
+        tm.assert_frame_equal(result, expected)
+
+    def test_default_delimiter(self):
+        data_expected = """
+a,bbb
+cc,dd"""
+        expected = read_csv(StringIO(data_expected), header=None)
+
+        test_data = """
+a \tbbb
+cc\tdd """
+        result = read_fwf(StringIO(test_data), widths=[3, 3],
+                          header=None, skiprows=[0])
+
+        tm.assert_frame_equal(result, expected)