first commit

venv/Lib/site-packages/pip/_internal/network/__init__.py

@@ -0,0 +1,2 @@
+"""Contains purely network-related utilities.
+"""

venv/Lib/site-packages/pip/_internal/network/cache.py

@@ -0,0 +1,69 @@
+"""HTTP cache implementation.
+"""
+
+import os
+from contextlib import contextmanager
+from typing import Generator, Optional
+
+from pip._vendor.cachecontrol.cache import BaseCache
+from pip._vendor.cachecontrol.caches import FileCache
+from pip._vendor.requests.models import Response
+
+from pip._internal.utils.filesystem import adjacent_tmp_file, replace
+from pip._internal.utils.misc import ensure_dir
+
+
+def is_from_cache(response: Response) -> bool:
+    return getattr(response, "from_cache", False)
+
+
+@contextmanager
+def suppressed_cache_errors() -> Generator[None, None, None]:
+    """If we can't access the cache then we can just skip caching and process
+    requests as if caching wasn't enabled.
+    """
+    try:
+        yield
+    except OSError:
+        pass
+
+
+class SafeFileCache(BaseCache):
+    """
+    A file based cache which is safe to use even when the target directory may
+    not be accessible or writable.
+    """
+
+    def __init__(self, directory: str) -> None:
+        assert directory is not None, "Cache directory must not be None."
+        super().__init__()
+        self.directory = directory
+
+    def _get_cache_path(self, name: str) -> str:
+        # From cachecontrol.caches.file_cache.FileCache._fn, brought into our
+        # class for backwards-compatibility and to avoid using a non-public
+        # method.
+        hashed = FileCache.encode(name)
+        parts = list(hashed[:5]) + [hashed]
+        return os.path.join(self.directory, *parts)
+
+    def get(self, key: str) -> Optional[bytes]:
+        path = self._get_cache_path(key)
+        with suppressed_cache_errors():
+            with open(path, "rb") as f:
+                return f.read()
+
+    def set(self, key: str, value: bytes, expires: Optional[int] = None) -> None:
+        path = self._get_cache_path(key)
+        with suppressed_cache_errors():
+            ensure_dir(os.path.dirname(path))
+
+            with adjacent_tmp_file(path) as f:
+                f.write(value)
+
+            replace(f.name, path)
+
+    def delete(self, key: str) -> None:
+        path = self._get_cache_path(key)
+        with suppressed_cache_errors():
+            os.remove(path)

venv/Lib/site-packages/pip/_internal/network/download.py

@@ -0,0 +1,186 @@
+"""Download files with progress indicators.
+"""
+import email.message
+import logging
+import mimetypes
+import os
+from typing import Iterable, Optional, Tuple
+
+from pip._vendor.requests.models import CONTENT_CHUNK_SIZE, Response
+
+from pip._internal.cli.progress_bars import get_download_progress_renderer
+from pip._internal.exceptions import NetworkConnectionError
+from pip._internal.models.index import PyPI
+from pip._internal.models.link import Link
+from pip._internal.network.cache import is_from_cache
+from pip._internal.network.session import PipSession
+from pip._internal.network.utils import HEADERS, raise_for_status, response_chunks
+from pip._internal.utils.misc import format_size, redact_auth_from_url, splitext
+
+logger = logging.getLogger(__name__)
+
+
+def _get_http_response_size(resp: Response) -> Optional[int]:
+    try:
+        return int(resp.headers["content-length"])
+    except (ValueError, KeyError, TypeError):
+        return None
+
+
+def _prepare_download(
+    resp: Response,
+    link: Link,
+    progress_bar: str,
+) -> Iterable[bytes]:
+    total_length = _get_http_response_size(resp)
+
+    if link.netloc == PyPI.file_storage_domain:
+        url = link.show_url
+    else:
+        url = link.url_without_fragment
+
+    logged_url = redact_auth_from_url(url)
+
+    if total_length:
+        logged_url = "{} ({})".format(logged_url, format_size(total_length))
+
+    if is_from_cache(resp):
+        logger.info("Using cached %s", logged_url)
+    else:
+        logger.info("Downloading %s", logged_url)
+
+    if logger.getEffectiveLevel() > logging.INFO:
+        show_progress = False
+    elif is_from_cache(resp):
+        show_progress = False
+    elif not total_length:
+        show_progress = True
+    elif total_length > (40 * 1000):
+        show_progress = True
+    else:
+        show_progress = False
+
+    chunks = response_chunks(resp, CONTENT_CHUNK_SIZE)
+
+    if not show_progress:
+        return chunks
+
+    renderer = get_download_progress_renderer(bar_type=progress_bar, size=total_length)
+    return renderer(chunks)
+
+
+def sanitize_content_filename(filename: str) -> str:
+    """
+    Sanitize the "filename" value from a Content-Disposition header.
+    """
+    return os.path.basename(filename)
+
+
+def parse_content_disposition(content_disposition: str, default_filename: str) -> str:
+    """
+    Parse the "filename" value from a Content-Disposition header, and
+    return the default filename if the result is empty.
+    """
+    m = email.message.Message()
+    m["content-type"] = content_disposition
+    filename = m.get_param("filename")
+    if filename:
+        # We need to sanitize the filename to prevent directory traversal
+        # in case the filename contains ".." path parts.
+        filename = sanitize_content_filename(str(filename))
+    return filename or default_filename
+
+
+def _get_http_response_filename(resp: Response, link: Link) -> str:
+    """Get an ideal filename from the given HTTP response, falling back to
+    the link filename if not provided.
+    """
+    filename = link.filename  # fallback
+    # Have a look at the Content-Disposition header for a better guess
+    content_disposition = resp.headers.get("content-disposition")
+    if content_disposition:
+        filename = parse_content_disposition(content_disposition, filename)
+    ext: Optional[str] = splitext(filename)[1]
+    if not ext:
+        ext = mimetypes.guess_extension(resp.headers.get("content-type", ""))
+        if ext:
+            filename += ext
+    if not ext and link.url != resp.url:
+        ext = os.path.splitext(resp.url)[1]
+        if ext:
+            filename += ext
+    return filename
+
+
+def _http_get_download(session: PipSession, link: Link) -> Response:
+    target_url = link.url.split("#", 1)[0]
+    resp = session.get(target_url, headers=HEADERS, stream=True)
+    raise_for_status(resp)
+    return resp
+
+
+class Downloader:
+    def __init__(
+        self,
+        session: PipSession,
+        progress_bar: str,
+    ) -> None:
+        self._session = session
+        self._progress_bar = progress_bar
+
+    def __call__(self, link: Link, location: str) -> Tuple[str, str]:
+        """Download the file given by link into location."""
+        try:
+            resp = _http_get_download(self._session, link)
+        except NetworkConnectionError as e:
+            assert e.response is not None
+            logger.critical(
+                "HTTP error %s while getting %s", e.response.status_code, link
+            )
+            raise
+
+        filename = _get_http_response_filename(resp, link)
+        filepath = os.path.join(location, filename)
+
+        chunks = _prepare_download(resp, link, self._progress_bar)
+        with open(filepath, "wb") as content_file:
+            for chunk in chunks:
+                content_file.write(chunk)
+        content_type = resp.headers.get("Content-Type", "")
+        return filepath, content_type
+
+
+class BatchDownloader:
+    def __init__(
+        self,
+        session: PipSession,
+        progress_bar: str,
+    ) -> None:
+        self._session = session
+        self._progress_bar = progress_bar
+
+    def __call__(
+        self, links: Iterable[Link], location: str
+    ) -> Iterable[Tuple[Link, Tuple[str, str]]]:
+        """Download the files given by links into location."""
+        for link in links:
+            try:
+                resp = _http_get_download(self._session, link)
+            except NetworkConnectionError as e:
+                assert e.response is not None
+                logger.critical(
+                    "HTTP error %s while getting %s",
+                    e.response.status_code,
+                    link,
+                )
+                raise
+
+            filename = _get_http_response_filename(resp, link)
+            filepath = os.path.join(location, filename)
+
+            chunks = _prepare_download(resp, link, self._progress_bar)
+            with open(filepath, "wb") as content_file:
+                for chunk in chunks:
+                    content_file.write(chunk)
+            content_type = resp.headers.get("Content-Type", "")
+            yield link, (filepath, content_type)

venv/Lib/site-packages/pip/_internal/network/lazy_wheel.py

@@ -0,0 +1,210 @@
+"""Lazy ZIP over HTTP"""
+
+__all__ = ["HTTPRangeRequestUnsupported", "dist_from_wheel_url"]
+
+from bisect import bisect_left, bisect_right
+from contextlib import contextmanager
+from tempfile import NamedTemporaryFile
+from typing import Any, Dict, Generator, List, Optional, Tuple
+from zipfile import BadZipFile, ZipFile
+
+from pip._vendor.packaging.utils import canonicalize_name
+from pip._vendor.requests.models import CONTENT_CHUNK_SIZE, Response
+
+from pip._internal.metadata import BaseDistribution, MemoryWheel, get_wheel_distribution
+from pip._internal.network.session import PipSession
+from pip._internal.network.utils import HEADERS, raise_for_status, response_chunks
+
+
+class HTTPRangeRequestUnsupported(Exception):
+    pass
+
+
+def dist_from_wheel_url(name: str, url: str, session: PipSession) -> BaseDistribution:
+    """Return a distribution object from the given wheel URL.
+
+    This uses HTTP range requests to only fetch the portion of the wheel
+    containing metadata, just enough for the object to be constructed.
+    If such requests are not supported, HTTPRangeRequestUnsupported
+    is raised.
+    """
+    with LazyZipOverHTTP(url, session) as zf:
+        # For read-only ZIP files, ZipFile only needs methods read,
+        # seek, seekable and tell, not the whole IO protocol.
+        wheel = MemoryWheel(zf.name, zf)  # type: ignore
+        # After context manager exit, wheel.name
+        # is an invalid file by intention.
+        return get_wheel_distribution(wheel, canonicalize_name(name))
+
+
+class LazyZipOverHTTP:
+    """File-like object mapped to a ZIP file over HTTP.
+
+    This uses HTTP range requests to lazily fetch the file's content,
+    which is supposed to be fed to ZipFile.  If such requests are not
+    supported by the server, raise HTTPRangeRequestUnsupported
+    during initialization.
+    """
+
+    def __init__(
+        self, url: str, session: PipSession, chunk_size: int = CONTENT_CHUNK_SIZE
+    ) -> None:
+        head = session.head(url, headers=HEADERS)
+        raise_for_status(head)
+        assert head.status_code == 200
+        self._session, self._url, self._chunk_size = session, url, chunk_size
+        self._length = int(head.headers["Content-Length"])
+        self._file = NamedTemporaryFile()
+        self.truncate(self._length)
+        self._left: List[int] = []
+        self._right: List[int] = []
+        if "bytes" not in head.headers.get("Accept-Ranges", "none"):
+            raise HTTPRangeRequestUnsupported("range request is not supported")
+        self._check_zip()
+
+    @property
+    def mode(self) -> str:
+        """Opening mode, which is always rb."""
+        return "rb"
+
+    @property
+    def name(self) -> str:
+        """Path to the underlying file."""
+        return self._file.name
+
+    def seekable(self) -> bool:
+        """Return whether random access is supported, which is True."""
+        return True
+
+    def close(self) -> None:
+        """Close the file."""
+        self._file.close()
+
+    @property
+    def closed(self) -> bool:
+        """Whether the file is closed."""
+        return self._file.closed
+
+    def read(self, size: int = -1) -> bytes:
+        """Read up to size bytes from the object and return them.
+
+        As a convenience, if size is unspecified or -1,
+        all bytes until EOF are returned.  Fewer than
+        size bytes may be returned if EOF is reached.
+        """
+        download_size = max(size, self._chunk_size)
+        start, length = self.tell(), self._length
+        stop = length if size < 0 else min(start + download_size, length)
+        start = max(0, stop - download_size)
+        self._download(start, stop - 1)
+        return self._file.read(size)
+
+    def readable(self) -> bool:
+        """Return whether the file is readable, which is True."""
+        return True
+
+    def seek(self, offset: int, whence: int = 0) -> int:
+        """Change stream position and return the new absolute position.
+
+        Seek to offset relative position indicated by whence:
+        * 0: Start of stream (the default).  pos should be >= 0;
+        * 1: Current position - pos may be negative;
+        * 2: End of stream - pos usually negative.
+        """
+        return self._file.seek(offset, whence)
+
+    def tell(self) -> int:
+        """Return the current position."""
+        return self._file.tell()
+
+    def truncate(self, size: Optional[int] = None) -> int:
+        """Resize the stream to the given size in bytes.
+
+        If size is unspecified resize to the current position.
+        The current stream position isn't changed.
+
+        Return the new file size.
+        """
+        return self._file.truncate(size)
+
+    def writable(self) -> bool:
+        """Return False."""
+        return False
+
+    def __enter__(self) -> "LazyZipOverHTTP":
+        self._file.__enter__()
+        return self
+
+    def __exit__(self, *exc: Any) -> None:
+        self._file.__exit__(*exc)
+
+    @contextmanager
+    def _stay(self) -> Generator[None, None, None]:
+        """Return a context manager keeping the position.
+
+        At the end of the block, seek back to original position.
+        """
+        pos = self.tell()
+        try:
+            yield
+        finally:
+            self.seek(pos)
+
+    def _check_zip(self) -> None:
+        """Check and download until the file is a valid ZIP."""
+        end = self._length - 1
+        for start in reversed(range(0, end, self._chunk_size)):
+            self._download(start, end)
+            with self._stay():
+                try:
+                    # For read-only ZIP files, ZipFile only needs
+                    # methods read, seek, seekable and tell.
+                    ZipFile(self)  # type: ignore
+                except BadZipFile:
+                    pass
+                else:
+                    break
+
+    def _stream_response(
+        self, start: int, end: int, base_headers: Dict[str, str] = HEADERS
+    ) -> Response:
+        """Return HTTP response to a range request from start to end."""
+        headers = base_headers.copy()
+        headers["Range"] = f"bytes={start}-{end}"
+        # TODO: Get range requests to be correctly cached
+        headers["Cache-Control"] = "no-cache"
+        return self._session.get(self._url, headers=headers, stream=True)
+
+    def _merge(
+        self, start: int, end: int, left: int, right: int
+    ) -> Generator[Tuple[int, int], None, None]:
+        """Return a generator of intervals to be fetched.
+
+        Args:
+            start (int): Start of needed interval
+            end (int): End of needed interval
+            left (int): Index of first overlapping downloaded data
+            right (int): Index after last overlapping downloaded data
+        """
+        lslice, rslice = self._left[left:right], self._right[left:right]
+        i = start = min([start] + lslice[:1])
+        end = max([end] + rslice[-1:])
+        for j, k in zip(lslice, rslice):
+            if j > i:
+                yield i, j - 1
+            i = k + 1
+        if i <= end:
+            yield i, end
+        self._left[left:right], self._right[left:right] = [start], [end]
+
+    def _download(self, start: int, end: int) -> None:
+        """Download bytes from start to end inclusively."""
+        with self._stay():
+            left = bisect_left(self._right, start)
+            right = bisect_right(self._left, end)
+            for start, end in self._merge(start, end, left, right):
+                response = self._stream_response(start, end)
+                response.raise_for_status()
+                self.seek(start)
+                for chunk in response_chunks(response, self._chunk_size):
+                    self._file.write(chunk)

venv/Lib/site-packages/pip/_internal/network/utils.py

@@ -0,0 +1,96 @@
+from typing import Dict, Generator
+
+from pip._vendor.requests.models import CONTENT_CHUNK_SIZE, Response
+
+from pip._internal.exceptions import NetworkConnectionError
+
+# The following comments and HTTP headers were originally added by
+# Donald Stufft in git commit 22c562429a61bb77172039e480873fb239dd8c03.
+#
+# We use Accept-Encoding: identity here because requests defaults to
+# accepting compressed responses. This breaks in a variety of ways
+# depending on how the server is configured.
+# - Some servers will notice that the file isn't a compressible file
+#   and will leave the file alone and with an empty Content-Encoding
+# - Some servers will notice that the file is already compressed and
+#   will leave the file alone, adding a Content-Encoding: gzip header
+# - Some servers won't notice anything at all and will take a file
+#   that's already been compressed and compress it again, and set
+#   the Content-Encoding: gzip header
+# By setting this to request only the identity encoding we're hoping
+# to eliminate the third case.  Hopefully there does not exist a server
+# which when given a file will notice it is already compressed and that
+# you're not asking for a compressed file and will then decompress it
+# before sending because if that's the case I don't think it'll ever be
+# possible to make this work.
+HEADERS: Dict[str, str] = {"Accept-Encoding": "identity"}
+
+
+def raise_for_status(resp: Response) -> None:
+    http_error_msg = ""
+    if isinstance(resp.reason, bytes):
+        # We attempt to decode utf-8 first because some servers
+        # choose to localize their reason strings. If the string
+        # isn't utf-8, we fall back to iso-8859-1 for all other
+        # encodings.
+        try:
+            reason = resp.reason.decode("utf-8")
+        except UnicodeDecodeError:
+            reason = resp.reason.decode("iso-8859-1")
+    else:
+        reason = resp.reason
+
+    if 400 <= resp.status_code < 500:
+        http_error_msg = (
+            f"{resp.status_code} Client Error: {reason} for url: {resp.url}"
+        )
+
+    elif 500 <= resp.status_code < 600:
+        http_error_msg = (
+            f"{resp.status_code} Server Error: {reason} for url: {resp.url}"
+        )
+
+    if http_error_msg:
+        raise NetworkConnectionError(http_error_msg, response=resp)
+
+
+def response_chunks(
+    response: Response, chunk_size: int = CONTENT_CHUNK_SIZE
+) -> Generator[bytes, None, None]:
+    """Given a requests Response, provide the data chunks."""
+    try:
+        # Special case for urllib3.
+        for chunk in response.raw.stream(
+            chunk_size,
+            # We use decode_content=False here because we don't
+            # want urllib3 to mess with the raw bytes we get
+            # from the server. If we decompress inside of
+            # urllib3 then we cannot verify the checksum
+            # because the checksum will be of the compressed
+            # file. This breakage will only occur if the
+            # server adds a Content-Encoding header, which
+            # depends on how the server was configured:
+            # - Some servers will notice that the file isn't a
+            #   compressible file and will leave the file alone
+            #   and with an empty Content-Encoding
+            # - Some servers will notice that the file is
+            #   already compressed and will leave the file
+            #   alone and will add a Content-Encoding: gzip
+            #   header
+            # - Some servers won't notice anything at all and
+            #   will take a file that's already been compressed
+            #   and compress it again and set the
+            #   Content-Encoding: gzip header
+            #
+            # By setting this not to decode automatically we
+            # hope to eliminate problems with the second case.
+            decode_content=False,
+        ):
+            yield chunk
+    except AttributeError:
+        # Standard file-like object.
+        while True:
+            chunk = response.raw.read(chunk_size)
+            if not chunk:
+                break
+            yield chunk

venv/Lib/site-packages/pip/_internal/network/xmlrpc.py

@@ -0,0 +1,60 @@
+"""xmlrpclib.Transport implementation
+"""
+
+import logging
+import urllib.parse
+import xmlrpc.client
+from typing import TYPE_CHECKING, Tuple
+
+from pip._internal.exceptions import NetworkConnectionError
+from pip._internal.network.session import PipSession
+from pip._internal.network.utils import raise_for_status
+
+if TYPE_CHECKING:
+    from xmlrpc.client import _HostType, _Marshallable
+
+logger = logging.getLogger(__name__)
+
+
+class PipXmlrpcTransport(xmlrpc.client.Transport):
+    """Provide a `xmlrpclib.Transport` implementation via a `PipSession`
+    object.
+    """
+
+    def __init__(
+        self, index_url: str, session: PipSession, use_datetime: bool = False
+    ) -> None:
+        super().__init__(use_datetime)
+        index_parts = urllib.parse.urlparse(index_url)
+        self._scheme = index_parts.scheme
+        self._session = session
+
+    def request(
+        self,
+        host: "_HostType",
+        handler: str,
+        request_body: bytes,
+        verbose: bool = False,
+    ) -> Tuple["_Marshallable", ...]:
+        assert isinstance(host, str)
+        parts = (self._scheme, host, handler, None, None, None)
+        url = urllib.parse.urlunparse(parts)
+        try:
+            headers = {"Content-Type": "text/xml"}
+            response = self._session.post(
+                url,
+                data=request_body,
+                headers=headers,
+                stream=True,
+            )
+            raise_for_status(response)
+            self.verbose = verbose
+            return self.parse_response(response.raw)
+        except NetworkConnectionError as exc:
+            assert exc.response
+            logger.critical(
+                "HTTP error %s while getting %s",
+                exc.response.status_code,
+                url,
+            )
+            raise