bpo-25711: Move _ZipImportResourceReader from importlib to zipimport. (GH-9406)

This commit is contained in:
Serhiy Storchaka 2018-09-19 09:28:06 +03:00 committed by GitHub
parent 2a9c3805dd
commit 9da3961f36
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 1067 additions and 952 deletions

View File

@ -257,87 +257,3 @@ def contents(package: Package) -> Iterable[str]:
else:
package_directory = Path(package.__spec__.origin).parent
return os.listdir(package_directory)
# Private implementation of ResourceReader and get_resource_reader() called
# from zipimport.c. Don't use these directly! We're implementing these in
# Python because 1) it's easier, 2) zipimport may get rewritten in Python
# itself at some point, so doing this all in C would difficult and a waste of
# effort.
class _ZipImportResourceReader(resources_abc.ResourceReader):
"""Private class used to support ZipImport.get_resource_reader().
This class is allowed to reference all the innards and private parts of
the zipimporter.
"""
def __init__(self, zipimporter, fullname):
self.zipimporter = zipimporter
self.fullname = fullname
def open_resource(self, resource):
fullname_as_path = self.fullname.replace('.', '/')
path = f'{fullname_as_path}/{resource}'
try:
return BytesIO(self.zipimporter.get_data(path))
except OSError:
raise FileNotFoundError(path)
def resource_path(self, resource):
# All resources are in the zip file, so there is no path to the file.
# Raising FileNotFoundError tells the higher level API to extract the
# binary data and create a temporary file.
raise FileNotFoundError
def is_resource(self, name):
# Maybe we could do better, but if we can get the data, it's a
# resource. Otherwise it isn't.
fullname_as_path = self.fullname.replace('.', '/')
path = f'{fullname_as_path}/{name}'
try:
self.zipimporter.get_data(path)
except OSError:
return False
return True
def contents(self):
# This is a bit convoluted, because fullname will be a module path,
# but _files is a list of file names relative to the top of the
# archive's namespace. We want to compare file paths to find all the
# names of things inside the module represented by fullname. So we
# turn the module path of fullname into a file path relative to the
# top of the archive, and then we iterate through _files looking for
# names inside that "directory".
fullname_path = Path(self.zipimporter.get_filename(self.fullname))
relative_path = fullname_path.relative_to(self.zipimporter.archive)
# Don't forget that fullname names a package, so its path will include
# __init__.py, which we want to ignore.
assert relative_path.name == '__init__.py'
package_path = relative_path.parent
subdirs_seen = set()
for filename in self.zipimporter._files:
try:
relative = Path(filename).relative_to(package_path)
except ValueError:
continue
# If the path of the file (which is relative to the top of the zip
# namespace), relative to the package given when the resource
# reader was created, has a parent, then it's a name in a
# subdirectory and thus we skip it.
parent_name = relative.parent.name
if len(parent_name) == 0:
yield relative.name
elif parent_name not in subdirs_seen:
subdirs_seen.add(parent_name)
yield parent_name
# Called from zipimport.c
def _zipimport_get_resource_reader(zipimporter, fullname):
try:
if not zipimporter.is_package(fullname):
return None
except ZipImportError:
return None
return _ZipImportResourceReader(zipimporter, fullname)

View File

@ -272,8 +272,16 @@ class zipimporter:
If 'fullname' is a package within the zip file, return the
'ResourceReader' object for the package. Otherwise return None.
"""
from importlib import resources
return resources._zipimport_get_resource_reader(self, fullname)
try:
if not self.is_package(fullname):
return None
except ZipImportError:
return None
if not _ZipImportResourceReader._registered:
from importlib.abc import ResourceReader
ResourceReader.register(_ZipImportResourceReader)
_ZipImportResourceReader._registered = True
return _ZipImportResourceReader(self, fullname)
def __repr__(self):
@ -648,3 +656,74 @@ def _get_module_code(self, fullname):
return code, ispackage, modpath
else:
raise ZipImportError(f"can't find module {fullname!r}", name=fullname)
class _ZipImportResourceReader:
"""Private class used to support ZipImport.get_resource_reader().
This class is allowed to reference all the innards and private parts of
the zipimporter.
"""
_registered = False
def __init__(self, zipimporter, fullname):
self.zipimporter = zipimporter
self.fullname = fullname
def open_resource(self, resource):
fullname_as_path = self.fullname.replace('.', '/')
path = f'{fullname_as_path}/{resource}'
from io import BytesIO
try:
return BytesIO(self.zipimporter.get_data(path))
except OSError:
raise FileNotFoundError(path)
def resource_path(self, resource):
# All resources are in the zip file, so there is no path to the file.
# Raising FileNotFoundError tells the higher level API to extract the
# binary data and create a temporary file.
raise FileNotFoundError
def is_resource(self, name):
# Maybe we could do better, but if we can get the data, it's a
# resource. Otherwise it isn't.
fullname_as_path = self.fullname.replace('.', '/')
path = f'{fullname_as_path}/{name}'
try:
self.zipimporter.get_data(path)
except OSError:
return False
return True
def contents(self):
# This is a bit convoluted, because fullname will be a module path,
# but _files is a list of file names relative to the top of the
# archive's namespace. We want to compare file paths to find all the
# names of things inside the module represented by fullname. So we
# turn the module path of fullname into a file path relative to the
# top of the archive, and then we iterate through _files looking for
# names inside that "directory".
from pathlib import Path
fullname_path = Path(self.zipimporter.get_filename(self.fullname))
relative_path = fullname_path.relative_to(self.zipimporter.archive)
# Don't forget that fullname names a package, so its path will include
# __init__.py, which we want to ignore.
assert relative_path.name == '__init__.py'
package_path = relative_path.parent
subdirs_seen = set()
for filename in self.zipimporter._files:
try:
relative = Path(filename).relative_to(package_path)
except ValueError:
continue
# If the path of the file (which is relative to the top of the zip
# namespace), relative to the package given when the resource
# reader was created, has a parent, then it's a name in a
# subdirectory and thus we skip it.
parent_name = relative.parent.name
if len(parent_name) == 0:
yield relative.name
elif parent_name not in subdirs_seen:
subdirs_seen.add(parent_name)
yield parent_name

File diff suppressed because it is too large Load Diff