[3.9] gh-136065: Fix quadratic complexity in os.path.expandvars() (GH-134952) (GH-140839)

(cherry picked from commit f029e8db62)

Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
Co-authored-by: Łukasz Langa <lukasz@langa.pl>

Lib/ntpath.py

@@ -335,17 +335,23 @@ def expanduser(path):
 # XXX With COMMAND.COM you can use any characters in a variable name,
 # XXX except '^|<>='.
 
+_varpattern = r"'[^']*'?|%(%|[^%]*%?)|\$(\$|[-\w]+|\{[^}]*\}?)"
+_varsub = None
+_varsubb = None
+
 def expandvars(path):
     """Expand shell variables of the forms $var, ${var} and %var%.
 
     Unknown variables are left unchanged."""
     path = os.fspath(path)
+    global _varsub, _varsubb
     if isinstance(path, bytes):
         if b'$' not in path and b'%' not in path:
             return path
-        import string
-        varchars = bytes(string.ascii_letters + string.digits + '_-', 'ascii')
-        quote = b'\''
+        if not _varsubb:
+            import re
+            _varsubb = re.compile(_varpattern.encode(), re.ASCII).sub
+        sub = _varsubb
         percent = b'%'
         brace = b'{'
         rbrace = b'}'
@@ -354,94 +360,44 @@ def expandvars(path):
     else:
         if '$' not in path and '%' not in path:
             return path
-        import string
-        varchars = string.ascii_letters + string.digits + '_-'
-        quote = '\''
+        if not _varsub:
+            import re
+            _varsub = re.compile(_varpattern, re.ASCII).sub
+        sub = _varsub
         percent = '%'
         brace = '{'
         rbrace = '}'
         dollar = '$'
         environ = os.environ
-    res = path[:0]
-    index = 0
-    pathlen = len(path)
-    while index < pathlen:
-        c = path[index:index+1]
-        if c == quote:   # no expansion within single quotes
-            path = path[index + 1:]
-            pathlen = len(path)
-            try:
-                index = path.index(c)
-                res += c + path[:index + 1]
-            except ValueError:
-                res += c + path
-                index = pathlen - 1
-        elif c == percent:  # variable or '%'
-            if path[index + 1:index + 2] == percent:
-                res += c
-                index += 1
+
+    def repl(m):
+        lastindex = m.lastindex
+        if lastindex is None:
+            return m[0]
+        name = m[lastindex]
+        if lastindex == 1:
+            if name == percent:
+                return name
+            if not name.endswith(percent):
+                return m[0]
+            name = name[:-1]
         else:
-                path = path[index+1:]
-                pathlen = len(path)
-                try:
-                    index = path.index(percent)
-                except ValueError:
-                    res += percent + path
-                    index = pathlen - 1
-                else:
-                    var = path[:index]
+            if name == dollar:
+                return name
+            if name.startswith(brace):
+                if not name.endswith(rbrace):
+                    return m[0]
+                name = name[1:-1]
+
         try:
             if environ is None:
-                            value = os.fsencode(os.environ[os.fsdecode(var)])
+                return os.fsencode(os.environ[os.fsdecode(name)])
             else:
-                            value = environ[var]
+                return environ[name]
         except KeyError:
-                        value = percent + var + percent
-                    res += value
-        elif c == dollar:  # variable or '$$'
-            if path[index + 1:index + 2] == dollar:
-                res += c
-                index += 1
-            elif path[index + 1:index + 2] == brace:
-                path = path[index+2:]
-                pathlen = len(path)
-                try:
-                    index = path.index(rbrace)
-                except ValueError:
-                    res += dollar + brace + path
-                    index = pathlen - 1
-                else:
-                    var = path[:index]
-                    try:
-                        if environ is None:
-                            value = os.fsencode(os.environ[os.fsdecode(var)])
-                        else:
-                            value = environ[var]
-                    except KeyError:
-                        value = dollar + brace + var + rbrace
-                    res += value
-            else:
-                var = path[:0]
-                index += 1
-                c = path[index:index + 1]
-                while c and c in varchars:
-                    var += c
-                    index += 1
-                    c = path[index:index + 1]
-                try:
-                    if environ is None:
-                        value = os.fsencode(os.environ[os.fsdecode(var)])
-                    else:
-                        value = environ[var]
-                except KeyError:
-                    value = dollar + var
-                res += value
-                if c:
-                    index -= 1
-        else:
-            res += c
-        index += 1
-    return res
+            return m[0]
+
+    return sub(repl, path)
 
 
 # Normalize a path, e.g. A//B, A/./B and A/foo/../B all become A\B.

Lib/posixpath.py

@@ -275,42 +275,41 @@ def expanduser(path):
 # This expands the forms $variable and ${variable} only.
 # Non-existent variables are left unchanged.
 
-_varprog = None
-_varprogb = None
+_varpattern = r'\$(\w+|\{[^}]*\}?)'
+_varsub = None
+_varsubb = None
 
 def expandvars(path):
     """Expand shell variables of form $var and ${var}.  Unknown variables
     are left unchanged."""
     path = os.fspath(path)
-    global _varprog, _varprogb
+    global _varsub, _varsubb
     if isinstance(path, bytes):
         if b'$' not in path:
             return path
-        if not _varprogb:
+        if not _varsubb:
             import re
-            _varprogb = re.compile(br'\$(\w+|\{[^}]*\})', re.ASCII)
-        search = _varprogb.search
+            _varsubb = re.compile(_varpattern.encode(), re.ASCII).sub
+        sub = _varsubb
         start = b'{'
         end = b'}'
         environ = getattr(os, 'environb', None)
     else:
         if '$' not in path:
             return path
-        if not _varprog:
+        if not _varsub:
             import re
-            _varprog = re.compile(r'\$(\w+|\{[^}]*\})', re.ASCII)
-        search = _varprog.search
+            _varsub = re.compile(_varpattern, re.ASCII).sub
+        sub = _varsub
         start = '{'
         end = '}'
         environ = os.environ
-    i = 0
-    while True:
-        m = search(path, i)
-        if not m:
-            break
-        i, j = m.span(0)
-        name = m.group(1)
-        if name.startswith(start) and name.endswith(end):
+
+    def repl(m):
+        name = m[1]
+        if name.startswith(start):
+            if not name.endswith(end):
+                return m[0]
             name = name[1:-1]
         try:
             if environ is None:
@@ -318,13 +317,11 @@ def expandvars(path):
             else:
                 value = environ[name]
         except KeyError:
-            i = j
+            return m[0]
         else:
-            tail = path[j:]
-            path = path[:i] + value
-            i = len(path)
-            path += tail
-    return path
+            return value
+
+    return sub(repl, path)
 
 
 # Normalize a path, e.g. A//B, A/./B and A/foo/../B all become A/B.

Lib/test/test_genericpath.py

@@ -9,7 +9,7 @@
 import warnings
 from test import support
 from test.support.script_helper import assert_python_ok
-from test.support import FakePath
+from test.support import FakePath, EnvironmentVarGuard
 
 
 def create_file(filename, data=b'foo'):
@@ -374,7 +374,7 @@ def test_splitdrive(self):
 
     def test_expandvars(self):
         expandvars = self.pathmodule.expandvars
-        with support.EnvironmentVarGuard() as env:
+        with EnvironmentVarGuard() as env:
             env.clear()
             env["foo"] = "bar"
             env["{foo"] = "baz1"
@@ -408,7 +408,7 @@ def test_expandvars_nonascii(self):
         expandvars = self.pathmodule.expandvars
         def check(value, expected):
             self.assertEqual(expandvars(value), expected)
-        with support.EnvironmentVarGuard() as env:
+        with EnvironmentVarGuard() as env:
             env.clear()
             nonascii = support.FS_NONASCII
             env['spam'] = nonascii
@@ -429,6 +429,19 @@ def check(value, expected):
                   os.fsencode('$bar%s bar' % nonascii))
             check(b'$spam}bar', os.fsencode('%s}bar' % nonascii))
 
+    @support.requires_resource('cpu')
+    def test_expandvars_large(self):
+        expandvars = self.pathmodule.expandvars
+        with EnvironmentVarGuard() as env:
+            env.clear()
+            env["A"] = "B"
+            n = 100_000
+            self.assertEqual(expandvars('$A'*n), 'B'*n)
+            self.assertEqual(expandvars('${A}'*n), 'B'*n)
+            self.assertEqual(expandvars('$A!'*n), 'B!'*n)
+            self.assertEqual(expandvars('${A}A'*n), 'BA'*n)
+            self.assertEqual(expandvars('${'*10*n), '${'*10*n)
+
     def test_abspath(self):
         self.assertIn("foo", self.pathmodule.abspath("foo"))
         with warnings.catch_warnings():

Lib/test/test_ntpath.py

@@ -1,11 +1,10 @@
 import ntpath
 import os
-import subprocess
 import sys
 import unittest
 import warnings
 from ntpath import ALLOW_MISSING
-from test.support import TestFailed, FakePath
+from test.support import TestFailed, FakePath, EnvironmentVarGuard
 from test import support, test_genericpath
 from tempfile import TemporaryFile
 
@@ -642,7 +641,7 @@ def test_realpath_cwd(self):
                         ntpath.realpath("file.txt", **kwargs))
 
     def test_expandvars(self):
-        with support.EnvironmentVarGuard() as env:
+        with EnvironmentVarGuard() as env:
             env.clear()
             env["foo"] = "bar"
             env["{foo"] = "baz1"
@@ -671,7 +670,7 @@ def test_expandvars(self):
     def test_expandvars_nonascii(self):
         def check(value, expected):
             tester('ntpath.expandvars(%r)' % value, expected)
-        with support.EnvironmentVarGuard() as env:
+        with EnvironmentVarGuard() as env:
             env.clear()
             nonascii = support.FS_NONASCII
             env['spam'] = nonascii
@@ -687,10 +686,23 @@ def check(value, expected):
             check('%spam%bar', '%sbar' % nonascii)
             check('%{}%bar'.format(nonascii), 'ham%sbar' % nonascii)
 
+    @support.requires_resource('cpu')
+    def test_expandvars_large(self):
+        expandvars = ntpath.expandvars
+        with EnvironmentVarGuard() as env:
+            env.clear()
+            env["A"] = "B"
+            n = 100_000
+            self.assertEqual(expandvars('%A%'*n), 'B'*n)
+            self.assertEqual(expandvars('%A%A'*n), 'BA'*n)
+            self.assertEqual(expandvars("''"*n + '%%'), "''"*n + '%')
+            self.assertEqual(expandvars("%%"*n), "%"*n)
+            self.assertEqual(expandvars("$$"*n), "$"*n)
+
     def test_expanduser(self):
         tester('ntpath.expanduser("test")', 'test')
 
-        with support.EnvironmentVarGuard() as env:
+        with EnvironmentVarGuard() as env:
             env.clear()
             tester('ntpath.expanduser("~test")', '~test')
 
@@ -908,6 +920,7 @@ def test_nt_helpers(self):
             self.assertIsInstance(b_final_path, bytes)
             self.assertGreater(len(b_final_path), 0)
 
+
 class NtCommonTest(test_genericpath.CommonTest, unittest.TestCase):
     pathmodule = ntpath
     attributes = ['relpath']

Misc/NEWS.d/next/Security/2025-05-30-22-33-27.gh-issue-136065.bu337o.rst

@@ -0,0 +1 @@
+Fix quadratic complexity in :func:`os.path.expandvars`.