Fix linter / type checker issues

contrib/cleanup_log.py

@@ -2,8 +2,9 @@ import re
 import sys
 from pathlib import Path
 
+from zimscraperlib.rewriting.url_rewriting import ZimPath
+
 from warc2zim.constants import logger
-from warc2zim.url_rewriting import ZimPath
 
 
 def notify(_: ZimPath):

contrib/html_convert.py

@@ -1,4 +1,4 @@
-""" html rewrite test utility
+"""html rewrite test utility
 
 This utility takes a given HTML content as input, base64 encoded, its original URL, and
  rewrites its content.
@@ -17,9 +17,10 @@ import logging
 import sys
 from pathlib import Path
 
+from zimscraperlib.rewriting.html import HtmlRewriter
+from zimscraperlib.rewriting.url_rewriting import ArticleUrlRewriter, HttpUrl, ZimPath
+
 from warc2zim.constants import logger
-from warc2zim.content_rewriting.html import HtmlRewriter
-from warc2zim.url_rewriting import ArticleUrlRewriter, HttpUrl, ZimPath
 from warc2zim.utils import to_string
 
 
@@ -37,7 +38,9 @@ def main(path_to_content: str, article_url: str, encoding: str | None = None):
     content = Path(path_to_content)
 
     url_rewriter = ArticleUrlRewriter(
-        HttpUrl(article_url), existing_zim_paths=set(), missing_zim_paths=set()
+        article_url=HttpUrl(article_url),
+        existing_zim_paths=set(),
+        missing_zim_paths=set(),
     )
 
     html_rewriter = HtmlRewriter(url_rewriter, "", None, notify)

contrib/marxists.org.py

@@ -1,4 +1,4 @@
-""" MIA English exclude list
+"""MIA English exclude list
 
 This utility computes the list of all subpages/languages that must be ignored for the
 English ZIM of The Marxists Internet Archive (MIA) at www.marxists.org.
@@ -23,9 +23,9 @@ soup = BeautifulSoup(resp.text, "html.parser")
 subfolders = set()
 REGEX = re.compile(r"\.\.\/(?P<subfolder>.*?)\/")
 for anchor in soup.find_all("a"):
-    if not anchor.has_attr("href"):
+    if not anchor.has_attr("href"):  # pyright: ignore
         continue
-    if match := REGEX.match(anchor["href"]):
+    if match := REGEX.match(anchor["href"]):  # pyright: ignore
         subfolders.add(match.group("subfolder"))
 
 print("|".join(sorted(subfolders)))  # noqa: T201

src/warc2zim/constants.py

@@ -1,4 +1,4 @@
-from zimscraperlib import getLogger
+from zimscraperlib.logging import getLogger
 
 # Shared logger with default log level at this stage
 logger = getLogger("warc2zim")

src/warc2zim/converter.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # vim: ai ts=4 sts=4 et sw=4 nu
 
-""" warc2zim conversion utility
+"""warc2zim conversion utility
 
 This utility provides a conversion from WARC records to ZIM files.
 WARC record are directly stored in a zim file as:
@@ -739,7 +739,7 @@ class Converter:
             lang_elem = soup.find("html", attrs={"lang": True})
             if lang_elem:
                 self.language = parse_language(
-                    lang_elem.attrs[  # pyright: ignore[reportGeneralTypeIssues ,reportAttributeAccessIssue]
+                    lang_elem.attrs[  # pyright: ignore[reportArgumentType, reportAttributeAccessIssue]
                         "lang"
                     ]
                 )
@@ -751,7 +751,7 @@ class Converter:
             )
             if lang_elem:
                 self.language = parse_language(
-                    lang_elem.attrs[  # pyright: ignore[reportGeneralTypeIssues ,reportAttributeAccessIssue]
+                    lang_elem.attrs[  # pyright: ignore[reportArgumentType ,reportAttributeAccessIssue]
                         "content"
                     ]
                 )
@@ -761,7 +761,7 @@ class Converter:
             lang_elem = soup.find("meta", {"name": "language", "content": True})
             if lang_elem:
                 self.language = parse_language(
-                    lang_elem.attrs[  # pyright: ignore[reportGeneralTypeIssues ,reportAttributeAccessIssue]
+                    lang_elem.attrs[  # pyright: ignore[reportArgumentType ,reportAttributeAccessIssue]
                         "content"
                     ]
                 )

src/warc2zim/items.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # vim: ai ts=4 sts=4 et sw=4 nu
 
-""" warc2zim's item classes
+"""warc2zim's item classes
 
 This module contains the differents Item we may want to add to a Zim archive.
 """

src/warc2zim/rewriting.py

@@ -27,7 +27,7 @@ JSONP_CALLBACK_REGEX = re.compile(r"[?].*(?:callback|jsonp)=([^&]+)", re.I)
 
 
 def no_title(
-    function: Callable[..., str | bytes]
+    function: Callable[..., str | bytes],
 ) -> Callable[..., tuple[str, str | bytes]]:
     """Decorator for methods transforming content without extracting a title.
 

tests/test_utils.py

@@ -258,7 +258,7 @@ class CharsetsTestData:
     expected_strings: list[str]
 
 
-def get_testdata() -> Generator[CharsetsTestData, None, None]:
+def get_testdata() -> Generator[CharsetsTestData]:
     data = json.loads(
         (Path(__file__).parent / "encodings" / "definition.json").read_bytes()
     )

tests/test_warc_to_zim.py

@@ -10,8 +10,9 @@ from urllib.parse import unquote
 
 import pytest
 import requests
-from zimscraperlib.image.conversion import convert_image, convert_svg2png, resize_image
+from zimscraperlib.image.conversion import convert_image, convert_svg2png
 from zimscraperlib.image.probing import format_for
+from zimscraperlib.image.transformation import resize_image
 from zimscraperlib.zim import Archive
 
 from warc2zim.__about__ import __version__