bpo-39667: Sync zipp 3.0 (GH-18540)

* bpo-39667: Improve pathlib.Path compatibility on zipfile.Path and correct performance degradation as found in zipp 3.0

* 📜🤖 Added by blurb_it.

* Update docs for new zipfile.Path.open

* Rely on dict, faster than OrderedDict.

* Syntax edits on docs

Co-authored-by: blurb-it[bot] <43283697+blurb-it[bot]@users.noreply.github.com>
(cherry picked from commit 0aeab5c)

Co-authored-by: Jason R. Coombs <[email protected]>

Author: jaraco

Doc/library/zipfile.rst

@@ -489,10 +489,20 @@ Path objects are traversable using the ``/`` operator.
 
    The final path component.
 
-.. method:: Path.open(*, **)
-
-   Invoke :meth:`ZipFile.open` on the current path. Accepts
-   the same arguments as :meth:`ZipFile.open`.
+.. method:: Path.open(mode='r', *, pwd, **)
+
+   Invoke :meth:`ZipFile.open` on the current path.
+   Allows opening for read or write, text or binary
+   through supported modes: 'r', 'w', 'rb', 'wb'.
+   Positional and keyword arguments are passed through to
+   :class:`io.TextIOWrapper` when opened as text and
+   ignored otherwise.
+   ``pwd`` is the ``pwd`` parameter to
+   :meth:`ZipFile.open`.
+
+   .. versionchanged:: 3.9
+      Added support for text and binary modes for open. Default
+      mode is now text.
 
 .. method:: Path.iterdir()
 

Lib/test/test_zipfile.py

@@ -5,6 +5,7 @@
 import os
 import pathlib
 import posixpath
+import string
 import struct
 import subprocess
 import sys
@@ -2839,7 +2840,7 @@ def test_open(self):
             a, b, g = root.iterdir()
             with a.open() as strm:
                 data = strm.read()
-            assert data == b"content of a"
+            assert data == "content of a"
 
     def test_read(self):
         for alpharep in self.zipfile_alpharep():
@@ -2933,6 +2934,11 @@ def test_joinpath_constant_time(self):
         # Check the file iterated all items
         assert entries.count == self.HUGE_ZIPFILE_NUM_ENTRIES
 
+    # @func_timeout.func_set_timeout(3)
+    def test_implied_dirs_performance(self):
+        data = ['/'.join(string.ascii_lowercase + str(n)) for n in range(10000)]
+        zipfile.CompleteDirs._implied_dirs(data)
+
 
 if __name__ == "__main__":
     unittest.main()

Lib/zipfile.py

@@ -17,7 +17,6 @@
 import threading
 import time
 import contextlib
-from collections import OrderedDict
 
 try:
     import zlib # We may need its compression method
@@ -2125,24 +2124,6 @@ def _compile(file, optimize=-1):
         return (fname, archivename)
 
 
-def _unique_everseen(iterable, key=None):
-    "List unique elements, preserving order. Remember all elements ever seen."
-    # unique_everseen('AAAABBBCCDAABBB') --> A B C D
-    # unique_everseen('ABBCcAD', str.lower) --> A B C D
-    seen = set()
-    seen_add = seen.add
-    if key is None:
-        for element in itertools.filterfalse(seen.__contains__, iterable):
-            seen_add(element)
-            yield element
-    else:
-        for element in iterable:
-            k = key(element)
-            if k not in seen:
-                seen_add(k)
-                yield element
-
-
 def _parents(path):
     """
     Given a path with elements separated by
@@ -2184,6 +2165,18 @@ def _ancestry(path):
         path, tail = posixpath.split(path)
 
 
+_dedupe = dict.fromkeys
+"""Deduplicate an iterable in original order"""
+
+
+def _difference(minuend, subtrahend):
+    """
+    Return items in minuend not in subtrahend, retaining order
+    with O(1) lookup.
+    """
+    return itertools.filterfalse(set(subtrahend).__contains__, minuend)
+
+
 class CompleteDirs(ZipFile):
     """
     A ZipFile subclass that ensures that implied directories
@@ -2193,13 +2186,8 @@ class CompleteDirs(ZipFile):
     @staticmethod
     def _implied_dirs(names):
         parents = itertools.chain.from_iterable(map(_parents, names))
-        # Deduplicate entries in original order
-        implied_dirs = OrderedDict.fromkeys(
-            p + posixpath.sep for p in parents
-            # Cast names to a set for O(1) lookups
-            if p + posixpath.sep not in set(names)
-        )
-        return implied_dirs
+        as_dirs = (p + posixpath.sep for p in parents)
+        return _dedupe(_difference(as_dirs, names))
 
     def namelist(self):
         names = super(CompleteDirs, self).namelist()
@@ -2328,20 +2316,31 @@ def __init__(self, root, at=""):
         self.root = FastLookup.make(root)
         self.at = at
 
-    @property
-    def open(self):
-        return functools.partial(self.root.open, self.at)
+    def open(self, mode='r', *args, **kwargs):
+        """
+        Open this entry as text or binary following the semantics
+        of ``pathlib.Path.open()`` by passing arguments through
+        to io.TextIOWrapper().
+        """
+        pwd = kwargs.pop('pwd', None)
+        zip_mode = mode[0]
+        stream = self.root.open(self.at, zip_mode, pwd=pwd)
+        if 'b' in mode:
+            if args or kwargs:
+                raise ValueError("encoding args invalid for binary operation")
+            return stream
+        return io.TextIOWrapper(stream, *args, **kwargs)
 
     @property
     def name(self):
         return posixpath.basename(self.at.rstrip("/"))
 
     def read_text(self, *args, **kwargs):
-        with self.open() as strm:
-            return io.TextIOWrapper(strm, *args, **kwargs).read()
+        with self.open('r', *args, **kwargs) as strm:
+            return strm.read()
 
     def read_bytes(self):
-        with self.open() as strm:
+        with self.open('rb') as strm:
             return strm.read()
 
     def _is_child(self, path):

Misc/NEWS.d/next/Library/2020-02-17-22-38-15.bpo-39667.QuzEHH.rst

@@ -0,0 +1 @@
+Improve pathlib.Path compatibility on zipfile.Path and correct performance degradation as found in zipp 3.0.