BUG: Fix string formatting (pandas-dev#53855)

* fixed string formatting bug

* updating doc

* add tests

* change whatsnew

* Update doc/source/whatsnew/v2.0.1.rst

Co-authored-by: Matthew Roeschke <[email protected]>

* Update v2.0.1.rst

* Update v2.0.1.rst

* change whatsnew

* Update pandas/tests/io/formats/test_format.py

Co-authored-by: Matthew Roeschke <[email protected]>

* Fix bug with smaller change

---------

Co-authored-by: Rithik Reddy <[email protected]>
Co-authored-by: reddyrg1 <[email protected]>
Co-authored-by: Matthew Roeschke <[email protected]>

Author: 3 people

doc/source/whatsnew/v2.0.3.rst

@@ -14,6 +14,7 @@ including other versions of pandas.
 Fixed regressions
 ~~~~~~~~~~~~~~~~~
 - Fixed performance regression in merging on datetime-like columns (:issue:`53231`)
+- Fixed regression when :meth:`DataFrame.to_string` creates extra space for string dtypes (:issue:`52690`)
 - For external ExtensionArray implementations, restored the default use of ``_values_for_factorize`` for hashing arrays (:issue:`53475`)
 -
 

pandas/io/formats/format.py

@@ -1391,7 +1391,7 @@ def _format(x):
 
         fmt_values = []
         for i, v in enumerate(vals):
-            if not is_float_type[i] and leading_space or self.formatter is not None:
+            if (not is_float_type[i] or self.formatter is not None) and leading_space:
                 fmt_values.append(f" {_format(v)}")
             elif is_float_type[i]:
                 fmt_values.append(float_format(v))

pandas/tests/io/formats/test_format.py

@@ -2206,6 +2206,17 @@ def test_max_rows_fitted(self, length, min_rows, max_rows, expected):
         result = formatter.max_rows_fitted
         assert result == expected
 
+    def test_no_extra_space(self):
+        # GH 52690: Check that no extra space is given
+        col1 = "TEST"
+        col2 = "PANDAS"
+        col3 = "to_string"
+        expected = f"{col1:<6s} {col2:<7s} {col3:<10s}"
+        df = DataFrame([{"col1": "TEST", "col2": "PANDAS", "col3": "to_string"}])
+        d = {"col1": "{:<6s}".format, "col2": "{:<7s}".format, "col3": "{:<10s}".format}
+        result = df.to_string(index=False, header=False, formatters=d)
+        assert result == expected
+
 
 def gen_series_formatting():
     s1 = Series(["a"] * 100)