Merge pull request #251 from openzim/upgrade_deps

benoit74 · web-flow · commit 9b959eb3ade8 · 2025-02-17T09:04:41.000+01:00
Upgrade to wombat 3.8.8 and other Python/JS dependencies
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -8,15 +8,15 @@ repos:
       - id: trailing-whitespace
       - id: end-of-file-fixer
   - repo: https://github.com/psf/black
-    rev: '24.10.0'
+    rev: '25.1.0'
     hooks:
       - id: black
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.9.2
+    rev: v0.9.6
     hooks:
       - id: ruff
   - repo: https://github.com/RobertCraigie/pyright-python
-    rev: v1.1.391
+    rev: v1.1.394
     hooks:
       - id: pyright
         name: pyright (system)
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -7,6 +7,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Changed
+
+- Upgrade to wombat 3.8.8 and other Python/JS dependencies (#249)
+
 ## [5.1.0] - 2025-01-21
 
 ### Changed
diff --git a/javascript/package.json b/javascript/package.json
@@ -5,16 +5,16 @@
   "license": "GPL-3.0-or-later",
   "author": "openZIM",
   "devDependencies": {
-    "@rollup/plugin-commonjs": "28.0.1",
-    "@rollup/plugin-node-resolve": "15.3.0",
+    "@rollup/plugin-commonjs": "28.0.2",
+    "@rollup/plugin-node-resolve": "16.0.0",
     "@rollup/plugin-strip": "^3.0.4",
     "@rollup/plugin-terser": "0.4.4",
-    "ava": "^6.1.3",
+    "ava": "^6.2.0",
     "babel-eslint": "^10.1.0",
-    "eslint": "9.13.0",
-    "eslint-config-prettier": "9.1.0",
-    "prettier": "3.3.3",
-    "rollup": "4.24.0",
+    "eslint": "9.20.1",
+    "eslint-config-prettier": "10.0.1",
+    "prettier": "3.5.1",
+    "rollup": "4.34.7",
     "rollup-plugin-version-injector": "^1.3.3"
   },
   "scripts": {
diff --git a/javascript/yarn.lock b/javascript/yarn.lock
diff --git a/openzim.toml b/openzim.toml
@@ -6,5 +6,5 @@ execute_after=[
 
 [files.assets.actions."wombat.js"]
 action="get_file"
-source="https://cdn.jsdelivr.net/npm/@webrecorder/wombat@3.8.7/dist/wombat.js"
+source="https://cdn.jsdelivr.net/npm/@webrecorder/wombat@3.8.8/dist/wombat.js"
 target_file="wombat.js"
diff --git a/pyproject.toml b/pyproject.toml
@@ -56,30 +56,30 @@ scripts = [
 
 ]
 lint = [
-  "black==24.10.0",
-  "ruff==0.9.2",
+  "black==25.1.0",
+  "ruff==0.9.6",
 ]
 check = [
-  "pyright==1.1.391",
+  "pyright==1.1.394",
   "pytest==8.3.4",
 ]
 test = [
   "pytest==8.3.4",
   "pytest-mock==3.14.0",
-  "coverage==7.6.10",
+  "coverage==7.6.12",
 ]
 docs = [
   "mkdocs==1.6.1",
-  "mkdocstrings[python]==0.27.0",
-  "mkdocs-material==9.5.50",
-  "pymdown-extensions==10.14",
+  "mkdocstrings[python]==0.28.1",
+  "mkdocs-material==9.6.4",
+  "pymdown-extensions==10.14.3",
   "mkdocs-gen-files==0.5.0",
   "mkdocs-literate-nav==0.6.1",
-  "mkdocs-include-markdown-plugin==7.1.2",
+  "mkdocs-include-markdown-plugin==7.1.4",
 ]
 dev = [
-  "ipython==8.31.0",
-  "pre-commit==4.0.1",
+  "ipython==8.32.0",
+  "pre-commit==4.1.0",
   "zimscraperlib[scripts]",
   "zimscraperlib[lint]",
   "zimscraperlib[test]",
diff --git a/src/zimscraperlib/filesystem.py b/src/zimscraperlib/filesystem.py
@@ -1,6 +1,6 @@
-""" Files manipulation tools
+"""Files manipulation tools
 
-    Shortcuts to retrieve mime type using magic"""
+Shortcuts to retrieve mime type using magic"""
 
 import pathlib
 from contextlib import contextmanager
diff --git a/src/zimscraperlib/fix_ogvjs_dist.py b/src/zimscraperlib/fix_ogvjs_dist.py
@@ -1,4 +1,4 @@
-""" quick script to fix videojs-ogvjs so that it triggers on webm mimetype """
+"""quick script to fix videojs-ogvjs so that it triggers on webm mimetype"""
 
 import logging
 import pathlib
diff --git a/src/zimscraperlib/html.py b/src/zimscraperlib/html.py
@@ -1,4 +1,4 @@
-""" Tools to work with HTML contents """
+"""Tools to work with HTML contents"""
 
 import pathlib
 from typing import BinaryIO, TextIO
@@ -43,11 +43,13 @@ def find_language_in(content: str | BinaryIO | TextIO, mime_type: str) -> str:
                     continue
                 if (
                     nodename == "meta"
-                    and not node.attrs.get("http-equiv", "").lower()
+                    and not node.attrs.get(
+                        "http-equiv", ""
+                    ).lower()  # pyright:ignore[reportUnknownMemberType, reportAttributeAccessIssue]
                     == "content-language"
                 ):
                     continue
-                return node.attrs[key]
+                return node.attrs[key]  # pyright:ignore[reportReturnType]
     return ""
 
 
diff --git a/src/zimscraperlib/image/optimization.py b/src/zimscraperlib/image/optimization.py
@@ -1,22 +1,22 @@
-""" An image optimization module to optimize the following image formats:
+"""An image optimization module to optimize the following image formats:
 
-    - JPEG (using optimize-images)
-    - PNG (using optimize-images)
-    - GIF (using gifsicle with lossy optimization)
-    - WebP (using Pillow)
+- JPEG (using optimize-images)
+- PNG (using optimize-images)
+- GIF (using gifsicle with lossy optimization)
+- WebP (using Pillow)
 
-    Some important notes:
-    - This makes use of the --lossy option from gifsicle which is present
-     only in versions above 1.92.
-      If the package manager has a lower version, you can build gifsicle
-      from source and install or
-      do not use the lossiness option.
+Some important notes:
+- This makes use of the --lossy option from gifsicle which is present
+ only in versions above 1.92.
+  If the package manager has a lower version, you can build gifsicle
+  from source and install or
+  do not use the lossiness option.
 
-    - Presets for the optimizer are available in zimscraperlib.image.presets.
+- Presets for the optimizer are available in zimscraperlib.image.presets.
 
-    - If no options for an image optimization is passed, the optimizer
-    can still run on default settings which give
-      a bit less size than the original images but maintain a high quality. """
+- If no options for an image optimization is passed, the optimizer
+can still run on default settings which give
+  a bit less size than the original images but maintain a high quality."""
 
 import io
 import os
diff --git a/src/zimscraperlib/misc.py b/src/zimscraperlib/misc.py
@@ -1,4 +1,4 @@
-""" Miscelaneous utils"""
+"""Miscelaneous utils"""
 
 from typing import TypeVar
 
diff --git a/src/zimscraperlib/rewriting/css.py b/src/zimscraperlib/rewriting/css.py
@@ -1,4 +1,4 @@
-""" CSS Rewriting
+"""CSS Rewriting
 
 This modules contains tools to rewrite CSS retrieved from an online source so that it
 can safely operate within a ZIM, linking only to ZIM entries everytime a URL is used.
diff --git a/src/zimscraperlib/rewriting/html.py b/src/zimscraperlib/rewriting/html.py
@@ -1,4 +1,4 @@
-""" HTML Rewriting
+"""HTML Rewriting
 
 This modules contains tools to rewrite HTML retrieved from an online source so that it
 can safely operate within a ZIM.
@@ -101,8 +101,12 @@ def extract_base_href(content: str) -> str | None:
     if not soup.head:
         return None
     for base in soup.head.find_all("base"):
-        if base.has_attr("href"):
-            return base["href"]
+        if base.has_attr(  # pyright:ignore[reportUnknownMemberType, reportAttributeAccessIssue]
+            "href"
+        ):
+            return base[  # pyright:ignore[reportIndexIssue, reportUnknownVariableType, reportArgumentType, reportReturnType]
+                "href"
+            ]
     return None
 
 
diff --git a/src/zimscraperlib/rewriting/js.py b/src/zimscraperlib/rewriting/js.py
@@ -1,4 +1,4 @@
-""" JS Rewriting
+"""JS Rewriting
 
 This modules contains tools to rewrite JS retrieved from an online source so that it
 can safely operate within a ZIM. It is based on the assumption that wombat.js will be
diff --git a/src/zimscraperlib/rewriting/url_rewriting.py b/src/zimscraperlib/rewriting/url_rewriting.py
@@ -1,4 +1,4 @@
-""" URL rewriting tools
+"""URL rewriting tools
 
 This module is about url and entry path rewriting.
 
diff --git a/src/zimscraperlib/types.py b/src/zimscraperlib/types.py
@@ -1,16 +1,16 @@
-""" File extensions to MIME-Type  mapping
+"""File extensions to MIME-Type  mapping
 
-    All libzim *articles* contains the mime-type of their content, for the libzim
-    reader to properly return it.
+All libzim *articles* contains the mime-type of their content, for the libzim
+reader to properly return it.
 
-    Providing accurate mime-type for ZIM Article is important to prevent broken features
-    upon reading.
-    Ex.: youtube scraper uses Web Assembly files (.wasm) for the WebM codecs.
-    Without the proper mime-type, wasm files are returned as octet-stream and thus
-    not loaded efficiently.
+Providing accurate mime-type for ZIM Article is important to prevent broken features
+upon reading.
+Ex.: youtube scraper uses Web Assembly files (.wasm) for the WebM codecs.
+Without the proper mime-type, wasm files are returned as octet-stream and thus
+not loaded efficiently.
 
-    Should your scraper need additional mapping, use mimetypes.add_type() and it will
-    be automatically used. """
+Should your scraper need additional mapping, use mimetypes.add_type() and it will
+be automatically used."""
 
 import mimetypes
 import pathlib
diff --git a/src/zimscraperlib/uri.py b/src/zimscraperlib/uri.py
@@ -1,4 +1,4 @@
-""" URI handling module"""
+"""URI handling module"""
 
 import urllib.parse
 
diff --git a/src/zimscraperlib/zim/__init__.py b/src/zimscraperlib/zim/__init__.py
@@ -1,10 +1,10 @@
-""" ZIM file creation tools
+"""ZIM file creation tools
 
-    zim.creator: create files by manually adding each article
-    zim.filesystem: zimwriterfs-like creation from a build folder
-    zim.providers: contentProvider for serving libzim with data
-    zim.items: item to add to creator
-    zim.archive: read ZIM files, accessing or searching its content"""
+zim.creator: create files by manually adding each article
+zim.filesystem: zimwriterfs-like creation from a build folder
+zim.providers: contentProvider for serving libzim with data
+zim.items: item to add to creator
+zim.archive: read ZIM files, accessing or searching its content"""
 
 from libzim.writer import Blob  # pyright: ignore[reportMissingModuleSource]
 
diff --git a/src/zimscraperlib/zim/_libkiwix.py b/src/zimscraperlib/zim/_libkiwix.py
@@ -1,4 +1,4 @@
-r""" [INTERNAL] libkiwix's internal features copies
+r"""[INTERNAL] libkiwix's internal features copies
 
 CAUTION: this is __not__ part of zimscraperlib's API. Don't use outside scraperlib!
 
diff --git a/src/zimscraperlib/zim/archive.py b/src/zimscraperlib/zim/archive.py
@@ -1,10 +1,10 @@
-""" ZIM Archive helper
+"""ZIM Archive helper
 
-    Convenient subclass of libzim.reader.Archive with:
-    - direct access to Item from path
-    - direct access to suggestions and suggestions count
-    - direct access to search results and number of results
-    - public Entry access by Id"""
+Convenient subclass of libzim.reader.Archive with:
+- direct access to Item from path
+- direct access to suggestions and suggestions count
+- direct access to search results and number of results
+- public Entry access by Id"""
 
 from collections.abc import Iterable
 from types import TracebackType
diff --git a/src/zimscraperlib/zim/creator.py b/src/zimscraperlib/zim/creator.py
@@ -1,18 +1,18 @@
-""" ZIM Creator helper
-
-    Convenient subclass of libzim.writer.Creator with:
-    - easier configuration of commonly set props during init
-    - start/stop methods to bypass the contextmanager
-    - method to create an entry directly from args
-    - direct method to add redirects without title
-    - prevent exeption on double call to close()
-
-    Convenient subclasses of libzim.writer.Item with:
-    - metadata set on initialization
-    - metadata stored on object
-    Sister subclass StaticItem (inheriting from it) with:
-    - content stored on object
-    - can be used to store a filepath and content read from it (not stored) """
+"""ZIM Creator helper
+
+Convenient subclass of libzim.writer.Creator with:
+- easier configuration of commonly set props during init
+- start/stop methods to bypass the contextmanager
+- method to create an entry directly from args
+- direct method to add redirects without title
+- prevent exeption on double call to close()
+
+Convenient subclasses of libzim.writer.Item with:
+- metadata set on initialization
+- metadata stored on object
+Sister subclass StaticItem (inheriting from it) with:
+- content stored on object
+- can be used to store a filepath and content read from it (not stored)"""
 
 import io
 import logging
diff --git a/src/zimscraperlib/zim/filesystem.py b/src/zimscraperlib/zim/filesystem.py
@@ -1,27 +1,27 @@
-""" zimwriterfs-like tools to convert a build folder into a ZIM
+"""zimwriterfs-like tools to convert a build folder into a ZIM
 
-    make_zim_file behaves in a similar way to zimwriterfs and expects the same options:
+make_zim_file behaves in a similar way to zimwriterfs and expects the same options:
 
-    - Guesses file mime-type from filenames
-    - Add all files to respective namespaces based on mime type
-    - Add redirects from a zimwriterfs-compatible redirects TSV
-    - Adds common metadata
+- Guesses file mime-type from filenames
+- Add all files to respective namespaces based on mime type
+- Add redirects from a zimwriterfs-compatible redirects TSV
+- Adds common metadata
 
-    Also included:
-    - Add redirect from a list of (source, destination, title) strings
+Also included:
+- Add redirect from a list of (source, destination, title) strings
 
-    Note: due to the lack of a cancel() method in the libzim itself, it is not possible
-    to stop a zim creation process. Should an error occur in your code, a Zim file
-    with up-to-that-moment content will be created at destination.
+Note: due to the lack of a cancel() method in the libzim itself, it is not possible
+to stop a zim creation process. Should an error occur in your code, a Zim file
+with up-to-that-moment content will be created at destination.
 
-    To prevent this (creating an unwanted Zim file) from happening,
-    a workaround is in place. It prevents the libzim from finishing its process.
-    While it results in no Zim file being created, it results in the zim temp folder
-    to be left on disk and very frequently leads to a segmentation fault at garbage
-    collection (on exit mostly).
+To prevent this (creating an unwanted Zim file) from happening,
+a workaround is in place. It prevents the libzim from finishing its process.
+While it results in no Zim file being created, it results in the zim temp folder
+to be left on disk and very frequently leads to a segmentation fault at garbage
+collection (on exit mostly).
 
-    Meaning you should exit right after an exception in your code (during zim creation)
-    Use workaround_nocancel=False to disable the workaround. """
+Meaning you should exit right after an exception in your code (during zim creation)
+Use workaround_nocancel=False to disable the workaround."""
 
 import datetime
 import pathlib
diff --git a/src/zimscraperlib/zim/indexing.py b/src/zimscraperlib/zim/indexing.py
@@ -1,4 +1,4 @@
-""" Special item with customized index data and helper classes """
+"""Special item with customized index data and helper classes"""
 
 import io
 import pathlib
diff --git a/src/zimscraperlib/zim/items.py b/src/zimscraperlib/zim/items.py
@@ -1,4 +1,4 @@
-""" libzim Item helpers """
+"""libzim Item helpers"""
 
 import io
 import pathlib
diff --git a/src/zimscraperlib/zim/providers.py b/src/zimscraperlib/zim/providers.py
diff --git a/tests/rewriting/test_js_rewriting.py b/tests/rewriting/test_js_rewriting.py
diff --git a/tests/zim/test_metadata.py b/tests/zim/test_metadata.py

-Original file line number
+Diff line change
 [files.assets.actions."wombat.js"]
 action="get_file"
 -source="https://cdn.jsdelivr.net/npm/@webrecorder/[email protected].7/dist/wombat.js"
 +source="https://cdn.jsdelivr.net/npm/@webrecorder/[email protected].8/dist/wombat.js"
 target_file="wombat.js"
Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,4 @@`
`1`		`-""" quick script to fix videojs-ogvjs so that it triggers on webm mimetype """`
	`1`	`+"""quick script to fix videojs-ogvjs so that it triggers on webm mimetype"""`
`2`	`2`
`3`	`3`	`import logging`
`4`	`4`	`import pathlib`