reader 3.13__tar.gz → 3.14__tar.gz

{reader-3.13 → reader-3.14}/CHANGES.rst

@@ -6,6 +6,41 @@ Changelog
   :noindex:
 
 
+Version 3.14
+------------
+
+Released 2024-07-23
+
+* Add :attr:`~EntryCounts.unimportant` attribute to
+  :class:`EntryCounts` and :class:`EntrySearchCounts`.
+  Thanks to `chenthur`_ for the pull request.
+  (:issue:`283`)
+* Fix bug in the :mod:`~reader.plugins.entry_dedupe` plugin causing entries
+  to flip-flop if there were multiple *new* duplicates of the same issue
+  (on the first update, one entry remains, on the second update, the other);
+  related to the bug fixed in `version 3.2 <Version 3.2_>`_.
+  (:issue:`340`)
+
+* :mod:`~reader._plugins.enclosure_tags` plugin improvements. (:issue:`344`)
+
+  * Set genre to `Podcast` if the feed has any tag containing "podcast".
+  * Rewrite tags on the fly,
+    instead of downloading the entire file before sending it to the user;
+    allows browsers to display accurate download progress.
+  * Prefer feed user title to feed title if available.
+  * Use feed title as artist, instead of author.
+
+* Support Python 3.13. (:issue:`341`)
+* Update vendored `feedparser`_ to the ``develop`` branch as of 2024-06-26.
+  Needed because upstream removed dependency on stdlib module ``cgi``
+  (removed in Python 3.13), but the `version 2.9 <Version 2.9_>`_
+  memory usage reduction was not released upstream yet.
+  (:issue:`341`)
+
+.. _chenthur: https://github.com/chenthur
+.. _feedparser: https://feedparser.readthedocs.io/en/latest/
+
+
 Version 3.13
 ------------
 
@@ -341,7 +376,7 @@ Released 2022-09-14
   became optional.
   (:issue:`96`)
 * Fix bug in :mod:`~reader.plugins.entry_dedupe` causing updates to fail
-  if there were multiple *new* duplicates of the same issue.
+  if there were multiple *new* duplicates of the same entry.
   (:issue:`292`)
 * Fix bug in :mod:`~reader.plugins.readtime`
   and :mod:`~reader.plugins.mark_as_read` causing updates to fail

{reader-3.13/src/reader.egg-info → reader-3.14}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: reader
-Version: 3.13
+Version: 3.14
 Summary: A Python feed reader library.
 Author: lemon24
 License: BSD-3-Clause
@@ -22,6 +22,7 @@ Classifier: Programming Language :: Python :: 3 :: Only
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy
 Classifier: Topic :: Internet
@@ -65,11 +66,11 @@ Requires-Dist: pytest-rerunfailures; extra == "tests"
 Requires-Dist: coverage; extra == "tests"
 Requires-Dist: pytest-cov; extra == "tests"
 Requires-Dist: requests-mock; extra == "tests"
-Requires-Dist: mechanicalsoup; (implementation_name != "pypy" or python_version <= "3.9") and extra == "tests"
+Requires-Dist: mechanicalsoup; (implementation_name != "pypy" and python_version <= "3.12") and extra == "tests"
 Requires-Dist: requests-wsgi-adapter; extra == "tests"
-Requires-Dist: lxml; (implementation_name != "pypy" or python_version <= "3.9") and extra == "tests"
+Requires-Dist: lxml; (implementation_name != "pypy" and python_version <= "3.12") and extra == "tests"
 Requires-Dist: html5lib; extra == "tests"
-Requires-Dist: numpy; (implementation_name != "pypy" and os_name == "posix") and extra == "tests"
+Requires-Dist: numpy; (implementation_name != "pypy" and os_name == "posix" and python_version <= "3.12") and extra == "tests"
 Requires-Dist: mypy; implementation_name != "pypy" and extra == "tests"
 Requires-Dist: types-requests; extra == "tests"
 Requires-Dist: types-beautifulsoup4; extra == "tests"

{reader-3.13 → reader-3.14}/docs/dev.rst

@@ -721,6 +721,8 @@ Duplicate entries
 Duplicate entries are mainly handled by the :mod:`reader.entry_dedupe` plugin.
 
 * Using MinHash to speed up similarity checks (maybe): https://gist.github.com/lemon24/b9af5ade919713406bda9603847d32e5
+* Discussion of unifying "on-line" dedupe (after an entry is added/updated),
+  and "on-demand" dedupe (backfill): :issue:`340`.
 
 However, it is also possible for a feed to have two entries with the same id
 – yes, even though in most (if not all) formats,

{reader-3.13 → reader-3.14}/docs/internal.rst

@@ -219,9 +219,14 @@ Type aliases
 Recipes
 -------
 
-.. include:: ../examples/parser_only.py
+.. include:: ../examples/custom_headers.py
     :start-after: """
-    :end-before: """  # docstring-end
+    :end-before: """
+.. literalinclude:: ../examples/custom_headers.py
+    :start-at: import
 
+.. include:: ../examples/parser_only.py
+    :start-after: """
+    :end-before: """
 .. literalinclude:: ../examples/parser_only.py
-    :start-after: """  # docstring-end
+    :start-at: import

reader-3.14/examples/custom_headers.py

@@ -0,0 +1,50 @@
+"""
+Adding custom headers when retrieving feeds
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Example of adding custom request headers with :attr:`.SessionFactory.request_hooks`:
+
+.. code-block:: console
+
+    $ python examples/custom_headers.py
+    updating...
+    server: Hello, world!
+    updated!
+
+"""
+
+# fmt: off
+# flake8: noqa
+
+import http.server
+import threading
+from reader import make_reader
+
+# start a background server that logs the received header
+
+class Handler(http.server.BaseHTTPRequestHandler):
+    def log_message(self, *_): pass
+    def do_GET(self):
+        print("server:", self.headers.get('my-header'))
+        self.send_error(304)
+
+server = http.server.HTTPServer(('localhost', 8080), Handler)
+threading.Thread(target=server.handle_request).start()
+
+# create a reader object
+
+reader = make_reader(':memory:')
+reader.add_feed('http://localhost:8080')
+
+# set up a hook that adds the header to each request
+
+def hook(session, request, **kwargs):
+    request.headers.setdefault('my-header', 'Hello, world!')
+
+reader._parser.session_factory.request_hooks.append(hook)
+
+# updating the feed sends the modified request to the server
+
+print("updating...")
+reader.update_feeds()
+print("updated!")

{reader-3.13 → reader-3.14}/examples/parser_only.py

@@ -11,7 +11,7 @@ retrieved asynchronously with `HTTPX <https://www.python-httpx.org/>`_:
     death and gravity
     Has your password been pwned? Or, how I almost failed to search a 37 GB text file in under 1 millisecond (in Python)
 
-"""  # docstring-end
+"""
 
 import asyncio
 import io

{reader-3.13 → reader-3.14}/pyproject.toml

@@ -26,6 +26,7 @@ classifiers = [
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
     "Programming Language :: Python :: Implementation :: CPython",
     "Programming Language :: Python :: Implementation :: PyPy",
     "Topic :: Internet",
@@ -107,14 +108,15 @@ tests = [
     "pytest-cov",
     "requests-mock",
     # mechanicalsoup hard-depends on lxml (see below)
-    'mechanicalsoup; (implementation_name != "pypy" or python_version <= "3.9")',
+    'mechanicalsoup; (implementation_name != "pypy" and python_version <= "3.12")',
     "requests-wsgi-adapter",
     # we want to test search with all known bs4 parsers.
-    # lxml does not have a PyPy 3.10+ wheel.
-    'lxml; (implementation_name != "pypy" or python_version <= "3.9")',
+    # lxml usually does not have recent PyPy wheels.
+    # lxml usually does not have pre-relase CPython wheels.
+    'lxml; (implementation_name != "pypy" and python_version <= "3.12")',
     "html5lib",
     # for bench.py
-    'numpy; (implementation_name != "pypy" and os_name == "posix")',
+    'numpy; (implementation_name != "pypy" and os_name == "posix" and python_version <= "3.12")',
     # mypy does not work on pypy (yet).
     'mypy; implementation_name != "pypy"',
     "types-requests",

{reader-3.13 → reader-3.14}/src/reader/__init__.py

@@ -37,7 +37,7 @@ Print the titles of the unread entries::
 
 """
 
-__version__ = '3.13'
+__version__ = '3.14'
 
 # isort: off
 

{reader-3.13 → reader-3.14}/src/reader/_app/__init__.py

@@ -8,6 +8,7 @@ from dataclasses import dataclass
 from datetime import datetime
 from datetime import timedelta
 from datetime import timezone
+from functools import lru_cache
 
 import flask.signals
 import humanize
@@ -418,7 +419,7 @@ def add_entry():
 FEED_SORT_NATIVE = {'title', 'added'}
 FEED_SORT_FANCY = {
     'important': lambda counts: counts.important,
-    # TODO: an unread/unimportant property would be nice
+    'unimportant': lambda counts: counts.unimportant,
     'unread': lambda counts: counts.total - counts.read,
     # TODO: if we keep these average intervals, properties for them might be nice too
     'avg1m': lambda counts: counts.averages[0],
@@ -435,7 +436,6 @@ def feeds():
 
     updates_enabled = request.args.get('updates-enabled')
     updates_enabled = {None: None, 'no': False, 'yes': True}[updates_enabled]
-
     sort = request.args.get('sort', 'title')
     assert sort in FEED_SORT_ALL
 
@@ -801,12 +801,28 @@ def delete_entry(data):
     get_reader().delete_entry((feed_url, entry_id))
 
 
+def get_feed_tag_keys(url):
+    assert isinstance(url, str), url
+
+    if not hasattr(g, 'reader_get_feed_tag_keys'):
+
+        @lru_cache(128)
+        def get(url):
+            return list(current_app.reader.get_tag_keys(url))
+
+        g.reader_get_feed_tag_keys = get
+
+    return g.reader_get_feed_tag_keys(url)
+
+
 # for some reason, @blueprint.app_template_global does not work
 @blueprint.app_template_global()
 def additional_enclosure_links(enclosure, entry):
     funcs = getattr(current_app, 'reader_additional_enclosure_links', ())
+    # TODO: this would not be needed if entry.feed could have tags on it
+    feed_tags = get_feed_tag_keys(entry.feed.url)
     for func in funcs:
-        yield from func(enclosure, entry)
+        yield from func(enclosure, entry, feed_tags)
 
 
 @blueprint.app_template_global()

{reader-3.13 → reader-3.14}/src/reader/_parser/_lazy.py

@@ -72,7 +72,7 @@ class Parser:
         self.parsers_by_mime_type: dict[str, list[tuple[float, ParserType[Any]]]] = {}
         self.parsers_by_url: dict[str, ParserType[Any]] = {}
 
-        #: :class:`~reader._requests_utils.SessionFactory`
+        #: :class:`~reader._parser.requests.SessionFactory`
         #: used to create Requests sessions for retrieving feeds.
         #:
         #: Plugins may add request or response hooks to this.
@@ -314,25 +314,25 @@ class Parser:
             ParseError: No parser matches.
 
         """
-        parser = self.get_parser_by_url(url)
-        if not parser:
-            if not mime_type:
-                mime_type, _ = mimetypes.guess_type(url)
-
-            # https://tools.ietf.org/html/rfc7231#section-3.1.1.5
-            #
-            # > If a Content-Type header field is not present, the recipient
-            # > MAY either assume a media type of "application/octet-stream"
-            # > ([RFC2046], Section 4.5.1) or examine the data to determine its type.
-            #
-            if not mime_type:
-                mime_type = 'application/octet-stream'
-
-            parser = self.get_parser_by_mime_type(mime_type)
-            if not parser:
-                raise ParseError(url, message=f"no parser for MIME type {mime_type!r}")
-
-        return parser, mime_type
+        if parser := self.get_parser_by_url(url):
+            return parser, mime_type
+
+        if not mime_type:
+            mime_type, _ = mimetypes.guess_type(url)
+
+        # https://tools.ietf.org/html/rfc7231#section-3.1.1.5
+        #
+        # > If a Content-Type header field is not present, the recipient
+        # > MAY either assume a media type of "application/octet-stream"
+        # > ([RFC2046], Section 4.5.1) or examine the data to determine its type.
+        #
+        if not mime_type:
+            mime_type = 'application/octet-stream'
+
+        if parser := self.get_parser_by_mime_type(mime_type):
+            return parser, mime_type
+
+        raise ParseError(url, message=f"no parser for MIME type {mime_type!r}")
 
     def validate_url(self, url: str) -> None:
         """Check if ``url`` is valid without actually retrieving it.

{reader-3.13 → reader-3.14}/src/reader/_parser/_url_utils.py

@@ -93,6 +93,8 @@ def resolve_root(root: str, path: str) -> str:
 
     # we normalize the path **before** symlinks are resolved;
     # i.e. it behaves as realpath -L (logical), not realpath -P (physical).
+    # we could probably use pathlib resolve() here, but it is not pure,
+    # and we can't mock the Windows version on POSIX.
     # https://docs.python.org/3/library/os.path.html#os.path.normpath
     # https://stackoverflow.com/questions/34865153/os-path-normpath-and-symbolic-links
     path = os.path.normcase(os.path.normpath(os.path.join(root, path)))
@@ -112,8 +114,8 @@ def resolve_root(root: str, path: str) -> str:
 def is_abs_path(path: str) -> bool:
     """Return True if path is an absolute pathname.
 
-    Unlike os.path.isabs(), return False on Windows if there's no drive
-    (e.g. "\\path").
+    Unlike os.path.isabs(), return False on Windows
+    if there's no drive (e.g. "\\path").
 
     """
     is_abs = os.path.isabs(path)
@@ -124,10 +126,19 @@ def is_abs_path(path: str) -> bool:
 def is_rel_path(path: str) -> bool:
     """Return True if path is a relative pathname.
 
-    Unlike "not os.path.isabs()", return False on windows if there's a drive
-    (e.g. "C:path").
+    Unlike "not os.path.isabs()", return False on Windows
+    if there's a drive (e.g. "C:path").
 
     """
+    # starting with Python 3.13, os.path.isabs('/a') is False on Windows.
+    # pathlib is_absolute() doesn't need this.
+    path = os.path.normpath(path)
+
     is_abs = os.path.isabs(path)
+
+    # starting with Python 3.13, os.path.isabs('\\a') is False on Windows.
+    if os.name == 'nt' and path.startswith('\\'):
+        is_abs = True
+
     has_drive = os.name == 'nt' and os.path.splitdrive(path)[0]
     return not any([is_abs, has_drive])

{reader-3.13 → reader-3.14}/src/reader/_parser/feedparser.py

@@ -51,7 +51,7 @@ class FeedparserParser:
         # feedparser content sanitization and relative link resolution should be ON.
         # https://github.com/lemon24/reader/issues/125
         # https://github.com/lemon24/reader/issues/157
-        result = feedparser.parse(  # type: ignore[attr-defined]
+        result = feedparser.parse(
             resource,
             resolve_relative_uris=True,
             sanitize_html=True,

reader-3.14/src/reader/_plugins/enclosure_tags.py

@@ -0,0 +1,166 @@
+"""
+enclosure_tags
+~~~~~~~~~~~~~~
+
+Fix tags for MP3 enclosures (e.g. podcasts).
+
+Adds a "with tags" link to a version of the file with tags set as follows:
+
+* the entry title as title
+* the feed (user) title as album and artist
+* `Podcast` as genre, if the feed has any tag containing "podcast"
+
+This plugin needs additional dependencies, use the ``unstable-plugins`` extra
+to install them:
+
+.. code-block:: bash
+
+    pip install reader[unstable-plugins]
+
+To load::
+
+    READER_APP_PLUGIN='reader._plugins.enclosure_tags:init' \\
+    python -m reader serve
+
+Implemented for :issue:`50`.
+Became a plugin in :issue:`52`.
+Streaming added in :issue:`344`.
+
+"""
+
+import io
+from urllib.parse import urlparse
+
+import mutagen.mp3
+import requests
+from flask import Blueprint
+from flask import request
+from flask import Response
+from flask import stream_with_context
+from flask import url_for
+
+
+blueprint = Blueprint('enclosure_tags', __name__)
+
+
+ALL_TAGS = ('album', 'title', 'artist', 'genre')
+
+
+@blueprint.route('/enclosure-tags', defaults={'filename': None})
+@blueprint.route('/enclosure-tags/<filename>')
+def enclosure_tags(filename):
+    tags = {}
+    for tag in ALL_TAGS:
+        if value := request.args.get(tag):
+            tags[tag] = value
+
+    # TODO: handle raise_for_status() exceptions nicely
+    headers, chunks = update_tags_requests(request.args['url'], tags)
+
+    def iter_chunks():
+        # Send the headers as soon as possible.
+        # Some browsers wait for the headers before showing the "Save As" dialog.
+        yield ''
+        yield from chunks
+
+    return Response(stream_with_context(iter_chunks()), headers=headers)
+
+
+def update_tags_requests(url, tags, *, session=requests):
+    """update_tags_requests(url, ...) -> (headers, iter_chunks())"""
+
+    response = requests.get(url, stream=True)
+    response.raise_for_status()
+
+    headers = {}
+
+    if content_disposition := response.headers.get('content-disposition'):
+        headers['content_disposition'] = content_disposition
+        response.raw.name = content_disposition
+    else:
+        response.raw.name = urlparse(url).path.split('/')[-1]
+
+    old_prefix, new_prefix = update_tags(response.raw, tags)
+
+    try:
+        content_length = int(response.headers.get('content-length', ''))
+    except ValueError:
+        pass
+    else:
+        content_length = content_length - len(old_prefix) + len(new_prefix)
+        headers['content-length'] = str(content_length)
+
+    if content_type := response.headers.get('content-type'):
+        headers['content-type'] = content_type
+
+    def iter_chunks():
+        with response:
+            yield new_prefix
+            yield from response.iter_content(2**18)
+
+    return headers, iter_chunks()
+
+
+def update_tags(file, tags):
+    """update_tags(file, ...) -> (old_prefix, new_prefix)
+
+    Rewrite the prefix of file to update ID3v2 tags.
+
+    """
+    prefix = b''
+    easy = None
+    for size in [2**17, 2**17, 2**18, 2**19, 2**19, 2**19]:
+        chunk = file.read(size)
+        if not chunk:
+            break
+        prefix += chunk
+        try:
+            easy = mutagen.mp3.EasyMP3(io.BytesIO(prefix))
+        except mutagen.MutagenError:
+            # TODO: debug logging
+            pass
+        else:
+            break
+
+    if easy is None:
+        return prefix, prefix
+
+    if easy.info.sketchy:
+        return prefix, prefix
+
+    offset = easy.info.frame_offset
+
+    for tag, value in tags.items():
+        easy[tag] = value
+
+    out = io.BytesIO()
+    easy.save(out)
+
+    return prefix, out.getvalue() + prefix[offset:]
+
+
+def enclosure_tags_filter(enclosure, entry, feed_tags):
+    filename = urlparse(enclosure.href).path.split('/')[-1]
+    if not filename.endswith('.mp3'):
+        return []
+
+    args = {'url': enclosure.href, 'filename': filename}
+    if entry.title:
+        args['title'] = entry.title
+    if album := (entry.feed.user_title or entry.feed.title):
+        args['album'] = album
+        args['artist'] = album
+    elif artist := (entry.author or entry.feed.author):
+        args['artist'] = artist
+
+    for tag in feed_tags:
+        if 'podcast' in tag.lower():
+            args['genre'] = 'Podcast'
+            break
+
+    return [('with tags', url_for('enclosure_tags.enclosure_tags', **args))]
+
+
+def init(app):
+    app.register_blueprint(blueprint)
+    app.reader_additional_enclosure_links.append(enclosure_tags_filter)

{reader-3.13 → reader-3.14}/src/reader/_storage/_entries.py

@@ -62,7 +62,7 @@ class EntriesMixin(StorageBase):
             self.paginated_query,
             partial(get_entries_query, filter, sort),
             row_factory=entry_factory,
-        )  # type: ignore[var-annotated]
+        )
         if sort != 'random':
             last = self.get_entry_last(sort, starting_after) if starting_after else None
             return paginated_query(limit, last)
@@ -101,8 +101,7 @@ class EntriesMixin(StorageBase):
         context.update(new_context)
 
         row = exactly_one(self.get_db().execute(str(query), context))
-
-        return EntryCounts(*row[:4], row[4:7])  # type: ignore[call-arg]
+        return EntryCounts(*row[:5], row[5:8])  # type: ignore[call-arg]
 
     @wrap_exceptions()
     def set_entry_read(
@@ -593,6 +592,7 @@ def get_entry_counts_query(
             'count(*)',
             'coalesce(sum(read == 1), 0)',
             'coalesce(sum(important == 1), 0)',
+            'coalesce(sum(important == 0), 0)',
             """
             coalesce(
                 sum(
@@ -606,7 +606,6 @@ def get_entry_counts_query(
         .FROM("entries_filtered")
         .JOIN("entries USING (id, feed)")
     )
-
     # one CTE / period + HAVING in the CTE is a tiny bit faster than
     # one CTE + WHERE in the SELECT
 

{reader-3.13 → reader-3.14}/src/reader/_storage/_search.py

@@ -349,7 +349,7 @@ class Search:
                     (change.sequence, *change.resource_id),
                 )
                 if cursor.rowcount:  # pragma: no cover
-                    log.warn(
+                    log.warning(
                         "during insert, found and deleted %d rows for %r",
                         cursor.rowcount,
                         change,
@@ -409,7 +409,7 @@ class Search:
         def pq(
             limit: int | None, last: tuple[Any, ...] | None = None
         ) -> Iterable[EntrySearchResult]:
-            with wrap_exceptions(ENABLED_EXC | QUERY_EXC):
+            with wrap_exceptions(ENABLED_EXC | QUERY_EXC):  # type: ignore[operator]
                 yield from paginated_query(
                     self.get_db(),
                     make_query,
@@ -455,7 +455,7 @@ class Search:
             lambda: EntryNotFoundError(feed_url, entry_id),
         )
 
-    @wrap_exceptions(ENABLED_EXC | QUERY_EXC)
+    @wrap_exceptions(ENABLED_EXC | QUERY_EXC)  # type: ignore[operator]
     def search_entry_counts(
         self,
         query: str,
@@ -486,7 +486,7 @@ class Search:
 
         context = dict(query=query, **query_context)
         row = exactly_one(self.get_db().execute(str(sql_query), context))
-        return EntrySearchCounts(*row[:4], row[4:7])  # type: ignore[call-arg]
+        return EntrySearchCounts(*row[:5], row[5:8])  # type: ignore[call-arg]
 
 
 def make_search_entries_query(

{reader-3.13 → reader-3.14}/src/reader/_storage/_sqlite_utils.py

@@ -14,6 +14,7 @@ import traceback
 import weakref
 from collections.abc import Callable
 from collections.abc import Iterator
+from collections.abc import Mapping
 from collections.abc import Sequence
 from contextlib import closing
 from contextlib import contextmanager
@@ -85,7 +86,7 @@ def ddl_transaction(db: sqlite3.Connection) -> Iterator[sqlite3.Connection]:
 @contextmanager
 def wrap_exceptions(
     exc_type: Callable[[str], Exception],
-    op_exc_types: dict[str, Callable[[str], Exception]] = {},  # noqa: B006
+    op_exc_types: Mapping[str, Callable[[str], Exception]] = {},  # noqa: B006
     message: str = "unexpected error",
 ) -> Iterator[None]:
     """Wrap sqlite3 exceptions in a custom exception.

{reader-3.13 → reader-3.14}/src/reader/_update.py

@@ -444,14 +444,14 @@ class Pipeline:
 
         try:
             # assemble pipeline
-            entry_pairs = self.get_entry_pairs(result)
-
             if result and not isinstance(result, Exception):
+                entry_pairs = self.get_entry_pairs(result)
                 entry_pairs = self.reader._parser.process_entry_pairs(
                     feed.url, result.mime_type, entry_pairs
                 )
                 entry_pairs, get_total_count = count_consumed(entry_pairs)
             else:
+                entry_pairs = ()
                 get_total_count = lambda: 0  # noqa: E731
 
             intents = make_intents(entry_pairs)
@@ -466,10 +466,7 @@ class Pipeline:
 
         return feed.url, UpdatedFeed(feed.url, *counts, total - sum(counts))
 
-    def get_entry_pairs(self, result: ParsedFeed | None | ParseError) -> EntryPairs:
-        if not result or isinstance(result, Exception):
-            return ()
-
+    def get_entry_pairs(self, result: ParsedFeed) -> EntryPairs:
         # give storage a chance to consume entries in a streaming fashion
         entries1, entries2 = tee(result.entries)
         entries_for_update = self.reader._storage.get_entries_for_update(

{reader-3.13 → reader-3.14}/src/reader/_utils.py

@@ -89,8 +89,10 @@ def count_consumed(it: Iterable[_T]) -> tuple[Iterable[_T], Callable[[], int]]:
 MapFunction = Callable[[Callable[[_T], _U], Iterable[_T]], Iterator[_U]]
 MapContextManager = AbstractContextManager[MapFunction[_T, _U]]
 
+# type ignore because of https://github.com/python/mypy/issues/17551
 
-@contextmanager
+
+@contextmanager  # type: ignore[arg-type]
 def make_pool_map(workers: int) -> Iterator[MapFunction[_T, _U]]:
     # We are using concurrent.futures instead of multiprocessing.dummy
     # because the latter doesn't work on some environments (e.g. AWS Lambda).