Upgrade nt_path from v3.14.2

RustPython · youknowone · Jan 24, 2026 · Jan 24, 2026 · Jan 24, 2026 · Jan 24, 2026
commit 2ac1b04914acb05fc6f03cff3fc29c558a88e3e2
diff --git a/Lib/ntpath.py b/Lib/ntpath.py
@@ -400,17 +400,23 @@ 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'$' not in path and b'%' not in path:
             return path
-        import string
-        varchars = bytes(string.ascii_letters + string.digits + '_-', 'ascii')
-        quote = b'\''
+        if not _varsubb:
+            import re
+            _varsubb = re.compile(_varpattern.encode(), re.ASCII).sub
+        sub = _varsubb
         percent = b'%'
         brace = b'{'
         rbrace = b'}'
@@ -419,94 +425,44 @@ def expandvars(path):
     else:
         if '$' 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
-            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]
-                    try:
-                        if environ is None:
-                            value = os.fsencode(os.environ[os.fsdecode(var)])
-                        else:
-                            value = environ[var]
-                    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
+
+    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:
-            res += c
-        index += 1
-    return res
+            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:
+                return os.fsencode(os.environ[os.fsdecode(name)])
+            else:
+                return environ[name]
+        except KeyError:
+            return m[0]
+
+    return sub(repl, path)
 
 
 # Normalize a path, e.g. A//B, A/./B and A/foo/../B all become A\B.

diff --git a/Lib/test/test_genericpath.py b/Lib/test/test_genericpath.py
@@ -7,9 +7,9 @@
 import sys
 import unittest
 import warnings
-from test.support import (
-    is_apple, is_emscripten, os_helper, warnings_helper
-)
+from test import support
+from test.support import os_helper
+from test.support import warnings_helper
 from test.support.script_helper import assert_python_ok
 from test.support.os_helper import FakePath
 
@@ -92,8 +92,8 @@ def test_commonprefix(self):
         for s1 in testlist:
             for s2 in testlist:
                 p = commonprefix([s1, s2])
-                self.assertTrue(s1.startswith(p))
-                self.assertTrue(s2.startswith(p))
+                self.assertStartsWith(s1, p)
+                self.assertStartsWith(s2, p)
                 if s1 != s2:
                     n = len(p)
                     self.assertNotEqual(s1[n:n+1], s2[n:n+1])
@@ -161,7 +161,6 @@ def test_exists(self):
         self.assertIs(self.pathmodule.lexists(path=filename), True)
 
     @unittest.skipUnless(hasattr(os, "pipe"), "requires os.pipe()")
-    @unittest.skipIf(is_emscripten, "Emscripten pipe fds have no stat")
     def test_exists_fd(self):
         r, w = os.pipe()
         try:
@@ -171,8 +170,7 @@ def test_exists_fd(self):
             os.close(w)
         self.assertFalse(self.pathmodule.exists(r))
 
-    # TODO: RUSTPYTHON
-    @unittest.expectedFailure
+    @unittest.expectedFailure  # TODO: RUSTPYTHON
     def test_exists_bool(self):
         for fd in False, True:
             with self.assertWarnsRegex(RuntimeWarning,
@@ -352,7 +350,6 @@ def test_invalid_paths(self):
                     with self.assertRaisesRegex(ValueError, 'embedded null'):
                         func(b'/tmp\x00abcds')
 
-
 # Following TestCase is not supposed to be run from test_genericpath.
 # It is inherited by other test modules (ntpath, posixpath).
 
@@ -449,6 +446,19 @@ 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 os_helper.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():
@@ -506,7 +516,7 @@ def test_nonascii_abspath(self):
             # directory (when the bytes name is used).
             and sys.platform not in {
                 "win32", "emscripten", "wasi"
-            } and not is_apple
+            } and not support.is_apple
         ):
             name = os_helper.TESTFN_UNDECODABLE
         elif os_helper.TESTFN_NONASCII:

diff --git a/Lib/test/test_ntpath.py b/Lib/test/test_ntpath.py
@@ -6,10 +6,9 @@
 import sys
 import unittest
 import warnings
-from ntpath import ALLOW_MISSING
 from test import support
-from test.support import cpython_only, os_helper
-from test.support import TestFailed, is_emscripten
+from test.support import os_helper
+from ntpath import ALLOW_MISSING
 from test.support.os_helper import FakePath
 from test import test_genericpath
 from tempfile import TemporaryFile
@@ -59,7 +58,7 @@ def tester(fn, wantResult):
     fn = fn.replace("\\", "\\\\")
     gotResult = eval(fn)
     if wantResult != gotResult and _norm(wantResult) != _norm(gotResult):
-        raise TestFailed("%s should return: %s but returned: %s" \
+        raise support.TestFailed("%s should return: %s but returned: %s" \
               %(str(fn), str(wantResult), str(gotResult)))
 
     # then with bytes
@@ -75,7 +74,7 @@ def tester(fn, wantResult):
         warnings.simplefilter("ignore", DeprecationWarning)
         gotResult = eval(fn)
     if _norm(wantResult) != _norm(gotResult):
-        raise TestFailed("%s should return: %s but returned: %s" \
+        raise support.TestFailed("%s should return: %s but returned: %s" \
               %(str(fn), str(wantResult), repr(gotResult)))
 
 
@@ -1022,6 +1021,19 @@ 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 os_helper.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')
 
@@ -1229,7 +1241,6 @@ def check_error(paths, expected):
         self.assertRaises(TypeError, ntpath.commonpath, ['C:\\Foo', b'Foo\\Baz'])
         self.assertRaises(TypeError, ntpath.commonpath, ['Foo', b'C:\\Foo\\Baz'])
 
-    @unittest.skipIf(is_emscripten, "Emscripten cannot fstat unnamed files.")
     def test_sameopenfile(self):
         with TemporaryFile() as tf1, TemporaryFile() as tf2:
             # Make sure the same file is really the same
@@ -1440,7 +1451,7 @@ def test_con_device(self):
         self.assertTrue(os.path.exists(r"\\.\CON"))
 
     @unittest.skipIf(sys.platform != 'win32', "Fast paths are only for win32")
-    @cpython_only
+    @support.cpython_only
     def test_fast_paths_in_use(self):
         # There are fast paths of these functions implemented in posixmodule.c.
         # Confirm that they are being used, and not the Python fallbacks in