Optimise textwrap.dedent()

Co-authored-by: Marius Juston <[email protected]>

Author: AA-Turner

Lib/test/test_textwrap.py

@@ -791,7 +791,7 @@ def test_dedent_only_whitespace(self):
 
         # ASCII whitespace.
         text = "\f\n\r\t\v "
-        expect = "\f\n\r\t\v "
+        expect = "\n"
         self.assertEqual(expect, dedent(text))
 
         # One newline.
@@ -801,7 +801,7 @@ def test_dedent_only_whitespace(self):
 
         # Windows-style newlines.
         text = "\r\n"
-        expect = "\r\n"
+        expect = "\n"
         self.assertEqual(expect, dedent(text))
 
         # Whitespace mixture.

Lib/textwrap.py

@@ -413,9 +413,6 @@ def shorten(text, width, **kwargs):
 
 # -- Loosely related functionality -------------------------------------
 
-_whitespace_only_re = re.compile('^[ \t]+$', re.MULTILINE)
-_leading_whitespace_re = re.compile('(^[ \t]*)(?:[^ \t\n])', re.MULTILINE)
-
 def dedent(text):
     """Remove any common leading whitespace from every line in `text`.
 
@@ -429,42 +426,26 @@ def dedent(text):
 
     Entirely blank lines are normalized to a newline character.
     """
-    # Look for the longest leading string of spaces and tabs common to
-    # all lines.
-    margin = None
-    text = _whitespace_only_re.sub('', text)
-    indents = _leading_whitespace_re.findall(text)
-    for indent in indents:
-        if margin is None:
-            margin = indent
-
-        # Current line more deeply indented than previous winner:
-        # no change (previous winner is still on top).
-        elif indent.startswith(margin):
-            pass
-
-        # Current line consistent with and no deeper than previous winner:
-        # it's the new winner.
-        elif margin.startswith(indent):
-            margin = indent
-
-        # Find the largest common whitespace between current line and previous
-        # winner.
-        else:
-            for i, (x, y) in enumerate(zip(margin, indent)):
-                if x != y:
-                    margin = margin[:i]
-                    break
+    if not text:
+        return text
+
+    lines = text.split('\n')
+
+    non_blank_lines = [l for l in lines if l and not l.isspace()]
+    if not non_blank_lines:
+        return '\n'.join([l if l and not l.isspace() else '' for l in lines])
 
-    # sanity check (testing/debugging only)
-    if 0 and margin:
-        for line in text.split("\n"):
-            assert not line or line.startswith(margin), \
-                   "line = %r, margin = %r" % (line, margin)
+    # Get length of leading whitespace, inspired by ``os.path.commonprefix()``
+    l1 = min(non_blank_lines)
+    l2 = max(non_blank_lines)
+    margin = 0
+    for i, c in enumerate(l1):
+        if c != l2[i] or c not in ' \t':
+            break
+        margin += 1
 
-    if margin:
-        text = re.sub(r'(?m)^' + margin, '', text)
-    return text
+    return '\n'.join([l[margin:] if l and not l.isspace() else ''
+                      for l in lines])
 
 
 def indent(text, prefix, predicate=None):

Misc/NEWS.d/next/Library/2025-03-30-19-55-10.gh-issue-131792.NNjzFA.rst

@@ -0,0 +1,2 @@
+Improved performance of :func: `textwrap.dedent` by ~2.4x.
+Patch by Adam Turner and Marius Juston.