GH-130614: pathlib ABCs: improve support for receiving path metadata (#131259)

In the private pathlib ABCs, replace `_WritablePath._write_info()` with
`_WritablePath._copy_from()`. This provides the target path object with
more control over the copying process, including support for querying and
setting metadata *before* the path is created.

Adjust `_ReadablePath.copy()` so that it forwards its keyword arguments to
`_WritablePath._copy_from()` of the target path object. This allows us to
remove the unimplemented *preserve_metadata* argument in the ABC method,
making it a `Path` exclusive.

diff --git a/Lib/pathlib/__init__.py b/Lib/pathlib/__init__.py
index 338016dbbbe972935697d0f6ff0ea9917cd4f4b2..c272ac4dddd40d87d25fdcfa3f6587dae932851e 100644 (file)
--- a/Lib/pathlib/__init__.py
+++ b/Lib/pathlib/__init__.py
@@ -29,7 +29,7 @@ except ImportError:
 from pathlib._os import (
     PathInfo, DirEntryInfo,
     ensure_different_files, ensure_distinct_paths,
-    copy_file, copy_info,
+    copyfile2, copyfileobj, magic_open, copy_info,
 )
 
 
@@ -810,12 +810,6 @@ class Path(PurePath):
         with self.open(mode='w', encoding=encoding, errors=errors, newline=newline) as f:
             return f.write(data)
 
-    def _write_info(self, info, follow_symlinks=True):
-        """
-        Write the given PathInfo to this path.
-        """
-        copy_info(info, self, follow_symlinks=follow_symlinks)
-
     _remove_leading_dot = operator.itemgetter(slice(2, None))
     _remove_trailing_slash = operator.itemgetter(slice(-1))
 
@@ -1100,18 +1094,21 @@ class Path(PurePath):
             target = self.with_segments(target)
         return target
 
-    def copy(self, target, follow_symlinks=True, preserve_metadata=False):
+    def copy(self, target, **kwargs):
         """
         Recursively copy this file or directory tree to the given destination.
         """
         if not hasattr(target, 'with_segments'):
             target = self.with_segments(target)
         ensure_distinct_paths(self, target)
-        copy_file(self, target, follow_symlinks, preserve_metadata)
+        try:
+            copy_to_target = target._copy_from
+        except AttributeError:
+            raise TypeError(f"Target path is not writable: {target!r}") from None
+        copy_to_target(self, **kwargs)
         return target.joinpath()  # Empty join to ensure fresh metadata.
 
-    def copy_into(self, target_dir, *, follow_symlinks=True,
-                  preserve_metadata=False):
+    def copy_into(self, target_dir, **kwargs):
         """
         Copy this file or directory tree into the given existing directory.
         """
@@ -1122,8 +1119,59 @@ class Path(PurePath):
             target = target_dir / name
         else:
             target = self.with_segments(target_dir, name)
-        return self.copy(target, follow_symlinks=follow_symlinks,
-                         preserve_metadata=preserve_metadata)
+        return self.copy(target, **kwargs)
+
+    def _copy_from(self, source, follow_symlinks=True, preserve_metadata=False):
+        """
+        Recursively copy the given path to this path.
+        """
+        if not follow_symlinks and source.info.is_symlink():
+            self._copy_from_symlink(source, preserve_metadata)
+        elif source.info.is_dir():
+            children = source.iterdir()
+            os.mkdir(self)
+            for child in children:
+                self.joinpath(child.name)._copy_from(
+                    child, follow_symlinks, preserve_metadata)
+            if preserve_metadata:
+                copy_info(source.info, self)
+        else:
+            self._copy_from_file(source, preserve_metadata)
+
+    def _copy_from_file(self, source, preserve_metadata=False):
+        ensure_different_files(source, self)
+        with magic_open(source, 'rb') as source_f:
+            with open(self, 'wb') as target_f:
+                copyfileobj(source_f, target_f)
+        if preserve_metadata:
+            copy_info(source.info, self)
+
+    if copyfile2:
+        # Use fast OS routine for local file copying where available.
+        _copy_from_file_fallback = _copy_from_file
+        def _copy_from_file(self, source, preserve_metadata=False):
+            try:
+                source = os.fspath(source)
+            except TypeError:
+                pass
+            else:
+                copyfile2(source, str(self))
+                return
+            self._copy_from_file_fallback(source, preserve_metadata)
+
+    if os.name == 'nt':
+        # If a directory-symlink is copied *before* its target, then
+        # os.symlink() incorrectly creates a file-symlink on Windows. Avoid
+        # this by passing *target_is_dir* to os.symlink() on Windows.
+        def _copy_from_symlink(self, source, preserve_metadata=False):
+            os.symlink(str(source.readlink()), self, source.info.is_dir())
+            if preserve_metadata:
+                copy_info(source.info, self, follow_symlinks=False)
+    else:
+        def _copy_from_symlink(self, source, preserve_metadata=False):
+            os.symlink(str(source.readlink()), self)
+            if preserve_metadata:
+                copy_info(source.info, self, follow_symlinks=False)
 
     def move(self, target):
         """

diff --git a/Lib/pathlib/_os.py b/Lib/pathlib/_os.py
index 121b6d656a8f5360db82b42e99712aea6cb6cddc..ee8657f427efbd5125883fc6bbd89d6a7be4b164 100644 (file)
--- a/Lib/pathlib/_os.py
+++ b/Lib/pathlib/_os.py
@@ -102,16 +102,16 @@ else:
 
 
 if _winapi and hasattr(_winapi, 'CopyFile2'):
-    def _copyfile2(source, target):
+    def copyfile2(source, target):
         """
         Copy from one file to another using CopyFile2 (Windows only).
         """
         _winapi.CopyFile2(source, target, 0)
 else:
-    _copyfile2 = None
+    copyfile2 = None
 
 
-def _copyfileobj(source_f, target_f):
+def copyfileobj(source_f, target_f):
     """
     Copy data from file-like object source_f to file-like object target_f.
     """
@@ -242,42 +242,6 @@ def ensure_different_files(source, target):
     raise err
 
 
-def copy_file(source, target, follow_symlinks=True, preserve_metadata=False):
-    """
-    Recursively copy the given source ReadablePath to the given target WritablePath.
-    """
-    info = source.info
-    if not follow_symlinks and info.is_symlink():
-        target.symlink_to(str(source.readlink()), info.is_dir())
-        if preserve_metadata:
-            target._write_info(info, follow_symlinks=False)
-    elif info.is_dir():
-        children = source.iterdir()
-        target.mkdir()
-        for src in children:
-            dst = target.joinpath(src.name)
-            copy_file(src, dst, follow_symlinks, preserve_metadata)
-        if preserve_metadata:
-            target._write_info(info)
-    else:
-        if _copyfile2:
-            # Use fast OS routine for local file copying where available.
-            try:
-                source_p = os.fspath(source)
-                target_p = os.fspath(target)
-            except TypeError:
-                pass
-            else:
-                _copyfile2(source_p, target_p)
-                return
-        ensure_different_files(source, target)
-        with magic_open(source, 'rb') as source_f:
-            with magic_open(target, 'wb') as target_f:
-                _copyfileobj(source_f, target_f)
-        if preserve_metadata:
-            target._write_info(info)
-
-
 def copy_info(info, target, follow_symlinks=True):
     """Copy metadata from the given PathInfo to the given local path."""
     copy_times_ns = (

diff --git a/Lib/pathlib/types.py b/Lib/pathlib/types.py
index 9852bd4ff1e997d35987648ee1cb2199799e4704..85dd9e5b2d6b9a9ee10dcd942258716141072a40 100644 (file)
--- a/Lib/pathlib/types.py
+++ b/Lib/pathlib/types.py
@@ -12,8 +12,8 @@ Protocols for supporting classes in pathlib.
 
 from abc import ABC, abstractmethod
 from glob import _PathGlobber
+from pathlib._os import magic_open, ensure_distinct_paths, ensure_different_files, copyfileobj
 from pathlib import PurePath, Path
-from pathlib._os import magic_open, ensure_distinct_paths, copy_file
 from typing import Optional, Protocol, runtime_checkable
 
 
@@ -332,18 +332,21 @@ class _ReadablePath(_JoinablePath):
         """
         raise NotImplementedError
 
-    def copy(self, target, follow_symlinks=True, preserve_metadata=False):
+    def copy(self, target, **kwargs):
         """
         Recursively copy this file or directory tree to the given destination.
         """
         if not hasattr(target, 'with_segments'):
             target = self.with_segments(target)
         ensure_distinct_paths(self, target)
-        copy_file(self, target, follow_symlinks, preserve_metadata)
+        try:
+            copy_to_target = target._copy_from
+        except AttributeError:
+            raise TypeError(f"Target path is not writable: {target!r}") from None
+        copy_to_target(self, **kwargs)
         return target.joinpath()  # Empty join to ensure fresh metadata.
 
-    def copy_into(self, target_dir, *, follow_symlinks=True,
-                  preserve_metadata=False):
+    def copy_into(self, target_dir, **kwargs):
         """
         Copy this file or directory tree into the given existing directory.
         """
@@ -354,8 +357,7 @@ class _ReadablePath(_JoinablePath):
             target = target_dir / name
         else:
             target = self.with_segments(target_dir, name)
-        return self.copy(target, follow_symlinks=follow_symlinks,
-                         preserve_metadata=preserve_metadata)
+        return self.copy(target, **kwargs)
 
 
 class _WritablePath(_JoinablePath):
@@ -409,11 +411,25 @@ class _WritablePath(_JoinablePath):
         with magic_open(self, mode='w', encoding=encoding, errors=errors, newline=newline) as f:
             return f.write(data)
 
-    def _write_info(self, info, follow_symlinks=True):
-        """
-        Write the given PathInfo to this path.
-        """
-        pass
+    def _copy_from(self, source, follow_symlinks=True):
+        """
+        Recursively copy the given path to this path.
+        """
+        stack = [(source, self)]
+        while stack:
+            src, dst = stack.pop()
+            if not follow_symlinks and src.info.is_symlink():
+                dst.symlink_to(str(src.readlink()), src.info.is_dir())
+            elif src.info.is_dir():
+                children = src.iterdir()
+                dst.mkdir()
+                for child in children:
+                    stack.append((child, dst.joinpath(child.name)))
+            else:
+                ensure_different_files(src, dst)
+                with magic_open(src, 'rb') as source_f:
+                    with magic_open(dst, 'wb') as target_f:
+                        copyfileobj(source_f, target_f)
 
 
 _JoinablePath.register(PurePath)