Merge pull request RustPython#4077 from youknowone/ntpath

Add nt._path_splitroot and update ntpath

Author: youknowone

Cargo.lock

@@ -9,16 +9,19 @@
 The function translate(PATTERN) returns a regular expression
 corresponding to PATTERN.  (It does not compile it.)
 """
-try:
-    import os
-except ImportError:
-    import _dummy_os as os
+import os
 import posixpath
 import re
 import functools
 
 __all__ = ["filter", "fnmatch", "fnmatchcase", "translate"]
 
+# Build a thread-safe incrementing counter to help create unique regexp group
+# names across calls.
+from itertools import count
+_nextgroupnum = count().__next__
+del count
+
 def fnmatch(name, pat):
     """Test whether FILENAME matches PATTERN.
 
@@ -49,7 +52,7 @@ def _compile_pattern(pat):
     return re.compile(res).match
 
 def filter(names, pat):
-    """Return the subset of the list NAMES that match PAT."""
+    """Construct a list from those elements of the iterable NAMES that match PAT."""
     result = []
     pat = os.path.normcase(pat)
     match = _compile_pattern(pat)
@@ -80,15 +83,19 @@ def translate(pat):
     There is no way to quote meta-characters.
     """
 
+    STAR = object()
+    res = []
+    add = res.append
     i, n = 0, len(pat)
-    res = ''
     while i < n:
         c = pat[i]
         i = i+1
         if c == '*':
-            res = res + '.*'
+            # compress consecutive `*` into one
+            if (not res) or res[-1] is not STAR:
+                add(STAR)
         elif c == '?':
-            res = res + '.'
+            add('.')
         elif c == '[':
             j = i
             if j < n and pat[j] == '!':
@@ -98,10 +105,10 @@ def translate(pat):
             while j < n and pat[j] != ']':
                 j = j+1
             if j >= n:
-                res = res + '\\['
+                add('\\[')
             else:
                 stuff = pat[i:j]
-                if '--' not in stuff:
+                if '-' not in stuff:
                     stuff = stuff.replace('\\', r'\\')
                 else:
                     chunks = []
@@ -113,19 +120,80 @@ def translate(pat):
                         chunks.append(pat[i:k])
                         i = k+1
                         k = k+3
-                    chunks.append(pat[i:j])
+                    chunk = pat[i:j]
+                    if chunk:
+                        chunks.append(chunk)
+                    else:
+                        chunks[-1] += '-'
+                    # Remove empty ranges -- invalid in RE.
+                    for k in range(len(chunks)-1, 0, -1):
+                        if chunks[k-1][-1] > chunks[k][0]:
+                            chunks[k-1] = chunks[k-1][:-1] + chunks[k][1:]
+                            del chunks[k]
                     # Escape backslashes and hyphens for set difference (--).
                     # Hyphens that create ranges shouldn't be escaped.
                     stuff = '-'.join(s.replace('\\', r'\\').replace('-', r'\-')
                                      for s in chunks)
                 # Escape set operations (&&, ~~ and ||).
                 stuff = re.sub(r'([&~|])', r'\\\1', stuff)
                 i = j+1
-                if stuff[0] == '!':
-                    stuff = '^' + stuff[1:]
-                elif stuff[0] in ('^', '['):
-                    stuff = '\\' + stuff
-                res = '%s[%s]' % (res, stuff)
+                if not stuff:
+                    # Empty range: never match.
+                    add('(?!)')
+                elif stuff == '!':
+                    # Negated empty range: match any character.
+                    add('.')
+                else:
+                    if stuff[0] == '!':
+                        stuff = '^' + stuff[1:]
+                    elif stuff[0] in ('^', '['):
+                        stuff = '\\' + stuff
+                    add(f'[{stuff}]')
+        else:
+            add(re.escape(c))
+    assert i == n
+
+    # Deal with STARs.
+    inp = res
+    res = []
+    add = res.append
+    i, n = 0, len(inp)
+    # Fixed pieces at the start?
+    while i < n and inp[i] is not STAR:
+        add(inp[i])
+        i += 1
+    # Now deal with STAR fixed STAR fixed ...
+    # For an interior `STAR fixed` pairing, we want to do a minimal
+    # .*? match followed by `fixed`, with no possibility of backtracking.
+    # We can't spell that directly, but can trick it into working by matching
+    #    .*?fixed
+    # in a lookahead assertion, save the matched part in a group, then
+    # consume that group via a backreference. If the overall match fails,
+    # the lookahead assertion won't try alternatives. So the translation is:
+    #     (?=(?P<name>.*?fixed))(?P=name)
+    # Group names are created as needed: g0, g1, g2, ...
+    # The numbers are obtained from _nextgroupnum() to ensure they're unique
+    # across calls and across threads. This is because people rely on the
+    # undocumented ability to join multiple translate() results together via
+    # "|" to build large regexps matching "one of many" shell patterns.
+    while i < n:
+        assert inp[i] is STAR
+        i += 1
+        if i == n:
+            add(".*")
+            break
+        assert inp[i] is not STAR
+        fixed = []
+        while i < n and inp[i] is not STAR:
+            fixed.append(inp[i])
+            i += 1
+        fixed = "".join(fixed)
+        if i == n:
+            add(".*")
+            add(fixed)
         else:
-            res = res + re.escape(c)
-    return r'(?s:%s)\Z' % res
+            groupnum = _nextgroupnum()
+            add(f"(?=(?P<g{groupnum}>.*?{fixed}))(?P=g{groupnum})")
+    assert i == n
+    res = "".join(res)
+    return fr'(?s:{res})\Z'

Lib/fnmatch.py

@@ -23,6 +23,7 @@
 import genericpath
 from genericpath import *
 
+
 __all__ = ["normcase","isabs","join","splitdrive","split","splitext",
            "basename","dirname","commonprefix","getsize","getmtime",
            "getatime","getctime", "islink","exists","lexists","isdir","isfile",
@@ -41,14 +42,39 @@ def _get_bothseps(path):
 # Other normalizations (such as optimizing '../' away) are not done
 # (this is done by normpath).
 
-def normcase(s):
-    """Normalize case of pathname.
-
-    Makes all characters lowercase and all slashes into backslashes."""
-    s = os.fspath(s)
-    if isinstance(s, bytes):
-        return s.replace(b'/', b'\\').lower()
-    else:
+try:
+    from _winapi import (
+        LCMapStringEx as _LCMapStringEx,
+        LOCALE_NAME_INVARIANT as _LOCALE_NAME_INVARIANT,
+        LCMAP_LOWERCASE as _LCMAP_LOWERCASE)
+
+    def normcase(s):
+        """Normalize case of pathname.
+
+        Makes all characters lowercase and all slashes into backslashes.
+        """
+        s = os.fspath(s)
+        if not s:
+            return s
+        if isinstance(s, bytes):
+            encoding = sys.getfilesystemencoding()
+            s = s.decode(encoding, 'surrogateescape').replace('/', '\\')
+            s = _LCMapStringEx(_LOCALE_NAME_INVARIANT,
+                               _LCMAP_LOWERCASE, s)
+            return s.encode(encoding, 'surrogateescape')
+        else:
+            return _LCMapStringEx(_LOCALE_NAME_INVARIANT,
+                                  _LCMAP_LOWERCASE,
+                                  s.replace('/', '\\'))
+except ImportError:
+    def normcase(s):
+        """Normalize case of pathname.
+
+        Makes all characters lowercase and all slashes into backslashes.
+        """
+        s = os.fspath(s)
+        if isinstance(s, bytes):
+            return os.fsencode(os.fsdecode(s).replace('/', '\\').lower())
         return s.replace('/', '\\').lower()
 
 
@@ -312,12 +338,25 @@ def expanduser(path):
             drive = ''
         userhome = join(drive, os.environ['HOMEPATH'])
 
+    if i != 1: #~user
+        target_user = path[1:i]
+        if isinstance(target_user, bytes):
+            target_user = os.fsdecode(target_user)
+        current_user = os.environ.get('USERNAME')
+
+        if target_user != current_user:
+            # Try to guess user home directory.  By default all user
+            # profile directories are located in the same place and are
+            # named by corresponding usernames.  If userhome isn't a
+            # normal profile directory, this guess is likely wrong,
+            # so we bail out.
+            if current_user != basename(userhome):
+                return path
+            userhome = join(dirname(userhome), target_user)
+
     if isinstance(path, bytes):
         userhome = os.fsencode(userhome)
 
-    if i != 1: #~user
-        userhome = join(dirname(userhome), path[1:i])
-
     return userhome + path[i:]
 
 
@@ -622,7 +661,7 @@ def _getfinalpathname_nonstrict(path):
                 tail = join(name, tail) if tail else name
         return tail
 
-    def realpath(path):
+    def realpath(path, *, strict=False):
         path = normpath(path)
         if isinstance(path, bytes):
             prefix = b'\\\\?\\'
@@ -647,6 +686,8 @@ def realpath(path):
             path = _getfinalpathname(path)
             initial_winerror = 0
         except OSError as ex:
+            if strict:
+                raise
             initial_winerror = ex.winerror
             path = _getfinalpathname_nonstrict(path)
         # The path returned by _getfinalpathname will always start with \\?\ -