feat: provide Mobi files [best effort, not all locales are supported] (…

…#2319)

.github/workflows/auto-updates.yml

@@ -44,6 +44,12 @@ jobs:
       - name: Install requirements
         run: python -m pip install -r requirements.txt
 
+      - name: Install kindlegen
+        run: |
+          mkdir -p ~/.local/bin
+          wget https://raw.githubusercontent.com/BoboTiG/ebook-reader-dict/refs/heads/kindlegen-backup/kindlegen_linux/kindlegen -O ~/.local/bin/kindlegen
+          chmod a+x ~/.local/bin/kindlegen
+
       - name: Download the latest Wiktionary dump
         run: python -Wd -m wikidict ${{ matrix.locale }} --download
 
@@ -66,11 +72,13 @@ jobs:
           tag_name: ${{ matrix.locale }}
           body_path: release.txt
           files: |
-            data/${{ matrix.locale }}/dicthtml-${{ matrix.locale }}-${{ matrix.locale }}*.zip
-            data/${{ matrix.locale }}/dicthtml-${{ matrix.locale }}-${{ matrix.locale }}*.zip.sha256
             data/${{ matrix.locale }}/dict-${{ matrix.locale }}-${{ matrix.locale }}*.df.bz2
             data/${{ matrix.locale }}/dict-${{ matrix.locale }}-${{ matrix.locale }}*.df.bz2.sha256
+            data/${{ matrix.locale }}/dict-${{ matrix.locale }}-${{ matrix.locale }}*.mobi
+            data/${{ matrix.locale }}/dict-${{ matrix.locale }}-${{ matrix.locale }}*.mobi.sha256
             data/${{ matrix.locale }}/dict-${{ matrix.locale }}-${{ matrix.locale }}*.zip
             data/${{ matrix.locale }}/dict-${{ matrix.locale }}-${{ matrix.locale }}*.zip.sha256
+            data/${{ matrix.locale }}/dicthtml-${{ matrix.locale }}-${{ matrix.locale }}*.zip
+            data/${{ matrix.locale }}/dicthtml-${{ matrix.locale }}-${{ matrix.locale }}*.zip.sha256
             data/${{ matrix.locale }}/dictorg-${{ matrix.locale }}-${{ matrix.locale }}*.zip
             data/${{ matrix.locale }}/dictorg-${{ matrix.locale }}-${{ matrix.locale }}*.zip.sha256

.github/workflows/tests.yml

@@ -24,6 +24,12 @@ jobs:
       - name: Quality checks, and linters
         run: ./check.sh
 
+      - name: Install kindlegen
+        run: |
+          mkdir -p ~/.local/bin
+          wget https://raw.githubusercontent.com/BoboTiG/ebook-reader-dict/refs/heads/kindlegen-backup/kindlegen_linux/kindlegen -O ~/.local/bin/kindlegen
+          chmod a+x ~/.local/bin/kindlegen
+
       - name: Unit tests
         run: python -Wd -m pytest tests --doctest-modules wikidict
 

.gitignore

@@ -3,12 +3,13 @@
 *.bz2
 *.df
 *.json
+*.mobi
 *.xml
 *.zip
 dict-data.*
 sections.txt
 templates.txt
-/data
+/data/
 tests/data/*/dict-data.*
 tests/data/*/INSTALL.txt
 tests/data/*/words.*
@@ -20,137 +21,10 @@ apicache-py3
 pywikibot.lwp
 throttle.ctrl
 
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.DS_Store
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-pip-wheel-metadata/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
+# Python stuff
 .coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py,cover
-.hypothesis/
+__pycache__/
+.mypy_cache/
 .pytest_cache/
 .ruff_cache/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-.python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.venv
-env/
-venv*/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-# Intellij IDEA
-.idea
+venv/

tests/test_3_convert.py

@@ -13,16 +13,18 @@
 Export Wiktionnaire : 2020-12-17
 
 Version complète :
-- [Kobo](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dicthtml-fr-fr.zip)
-- [StarDict](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dict-fr-fr.zip)
 - [DictFile](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dict-fr-fr.df.bz2)
 - [DICT.org](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dictorg-fr-fr.zip)
+- [Kindle](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dict-fr-fr.mobi)
+- [Kobo](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dicthtml-fr-fr.zip)
+- [StarDict](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dict-fr-fr.zip)
 
 Version sans étymologies :
-- [Kobo](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dicthtml-fr-fr-noetym.zip)
-- [StarDict](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dict-fr-fr-noetym.zip)
 - [DictFile](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dict-fr-fr-noetym.df.bz2)
 - [DICT.org](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dictorg-fr-fr-noetym.zip)
+- [Kindle](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dict-fr-fr-noetym.mobi)
+- [Kobo](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dicthtml-fr-fr-noetym.zip)
+- [StarDict](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dict-fr-fr-noetym.zip)
 
 Mis à jour le"""
 
@@ -82,12 +84,6 @@ def test_simple() -> None:
     assert (output_dir / "dict-fr-fr-noetym.df.bz2").is_file()
     assert (output_dir / f"dict-fr-fr-noetym.df.bz2.{ASSET_CHECKSUM_ALGO}").is_file()
 
-    # StarDict
-    assert (output_dir / "dict-fr-fr.zip").is_file()
-    assert (output_dir / f"dict-fr-fr.zip.{ASSET_CHECKSUM_ALGO}").is_file()
-    assert (output_dir / "dict-fr-fr-noetym.zip").is_file()
-    assert (output_dir / f"dict-fr-fr-noetym.zip.{ASSET_CHECKSUM_ALGO}").is_file()
-
     # DICT.org
     assert (output_dir / "dictorg-fr-fr.zip").is_file()
     assert (output_dir / f"dictorg-fr-fr.zip.{ASSET_CHECKSUM_ALGO}").is_file()
@@ -101,6 +97,18 @@ def test_simple() -> None:
     assert dicthtml.is_file()
     assert (output_dir / f"dicthtml-fr-fr.zip.{ASSET_CHECKSUM_ALGO}").is_file()
 
+    # Mobi
+    assert (output_dir / "dict-fr-fr.mobi").is_file()
+    assert (output_dir / f"dict-fr-fr.mobi.{ASSET_CHECKSUM_ALGO}").is_file()
+    assert (output_dir / "dict-fr-fr-noetym.mobi").is_file()
+    assert (output_dir / f"dict-fr-fr-noetym.mobi.{ASSET_CHECKSUM_ALGO}").is_file()
+
+    # StarDict
+    assert (output_dir / "dict-fr-fr.zip").is_file()
+    assert (output_dir / f"dict-fr-fr.zip.{ASSET_CHECKSUM_ALGO}").is_file()
+    assert (output_dir / "dict-fr-fr-noetym.zip").is_file()
+    assert (output_dir / f"dict-fr-fr-noetym.zip.{ASSET_CHECKSUM_ALGO}").is_file()
+
     # Check the Kobo ZIP content
     with ZipFile(dicthtml) as fh:
         expected = [
@@ -187,12 +195,14 @@ def test_generate_primary_dict(formatter: type[convert.BaseFormat], filename: st
 @pytest.mark.parametrize(
     "formatter, filename, include_etymology",
     [
-        (convert.StarDictFormat, "dict-fr-fr.zip", True),
-        (convert.StarDictFormat, "dict-fr-fr-noetym.zip", False),
         (convert.BZ2DictFileFormat, "dict-fr-fr.df.bz2", True),
         (convert.BZ2DictFileFormat, "dict-fr-fr-noetym.df.bz2", False),
         (convert.DictOrgFormat, "dictorg-fr-fr.zip", True),
         (convert.DictOrgFormat, "dictorg-fr-fr-noetym.zip", False),
+        (convert.MobiFormat, "dict-fr-fr.mobi", True),
+        (convert.MobiFormat, "dict-fr-fr-noetym.mobi", False),
+        (convert.StarDictFormat, "dict-fr-fr.zip", True),
+        (convert.StarDictFormat, "dict-fr-fr-noetym.zip", False),
     ],
 )
 @pytest.mark.dependency(

tests/test_4_release.py

@@ -10,16 +10,18 @@
 Export Wiktionnaire : 2020-02-20
 
 Version complète :
-- [Kobo](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dicthtml-fr-fr.zip) (dicthtml-fr-fr.zip)
-- [StarDict](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dict-fr-fr.zip) (dict-fr-fr.zip)
 - [DictFile](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dict-fr-fr.df.bz2) (dict-fr-fr.df.bz2)
 - [DICT.org](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dictorg-fr-fr.zip) (dictorg-fr-fr.zip)
+- [Kindle](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dict-fr-fr.mobi) (dict-fr-fr.mobi)
+- [Kobo](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dicthtml-fr-fr.zip) (dicthtml-fr-fr.zip)
+- [StarDict](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dict-fr-fr.zip) (dict-fr-fr.zip)
 
 Version sans étymologies :
-- [Kobo](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dicthtml-fr-fr-noetym.zip) (dicthtml-fr-fr-noetym.zip)
-- [StarDict](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dict-fr-fr-noetym.zip) (dict-fr-fr-noetym.zip)
 - [DictFile](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dict-fr-fr-noetym.df.bz2) (dict-fr-fr-noetym.df.bz2)
 - [DICT.org](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dictorg-fr-fr-noetym.zip) (dictorg-fr-fr-noetym.zip)
+- [Kindle](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dict-fr-fr-noetym.mobi) (dict-fr-fr-noetym.mobi)
+- [Kobo](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dicthtml-fr-fr-noetym.zip) (dicthtml-fr-fr-noetym.zip)
+- [StarDict](https://github.com/BoboTiG/ebook-reader-dict/releases/download/fr/dict-fr-fr-noetym.zip) (dict-fr-fr-noetym.zip)
 
 <sub>Mis à jour le """
 

wikidict/__main__.py

@@ -22,9 +22,10 @@
                             --workers=N         Set the number of multiprocessing workers,
                                                 defaults to the number of CPU in the system.
   --convert                 Convert rendered data to working dictionaries into several files:
-                                - "data/$LOCALE/dicthtml-$LOCALE-$LOCALE.zip": Kobo format.
                                 - "data/$LOCALE/dict-$LOCALE-$LOCALE.df.bz2": DictFile format.
+                                - "data/$LOCALE/dict-$LOCALE-$LOCALE.mobi": Kindle format.
                                 - "data/$LOCALE/dict-$LOCALE-$LOCALE.zip": StarDict format.
+                                - "data/$LOCALE/dicthtml-$LOCALE-$LOCALE.zip": Kobo format.
                                 - "data/$LOCALE/dictorg-$LOCALE-$LOCALE.zip": DICT.org format.
   --find-templates          DEBUG: Find all templates in use.
   --check-words             Render words, then compare with the rendering done on the Wiktionary to catch errors.
@@ -37,7 +38,7 @@
   --gen-dict=WORDS          DEBUG: Generate dictionary for specific words. Pass multiple words
                             separated with a comma: WORD1,WORD2,WORD3,...
                             The generated filename can be tweaked via the --output=FILENAME argument.
-                            --format=FORMAT     Format can be "kobo", "stardict", "dictorg" [default: kobo]
+                            --format=FORMAT     Format can be dictorg, kobo, mobi, stardict [default: kobo]
   --release                 DEV: Generate the description of a GitHub release.
 
 If no argument given, --download, --parse, --render, and --convert will be done automatically.

wikidict/constants.py

@@ -13,6 +13,7 @@
 DOWNLOAD_URL_DICTFILE = f"{GH_REPOS}/releases/download/{{0}}/dict-{{0}}-{{0}}{{1}}.df.bz2"
 DOWNLOAD_URL_DICTORGFILE = f"{GH_REPOS}/releases/download/{{0}}/dictorg-{{0}}-{{0}}{{1}}.zip"
 DOWNLOAD_URL_KOBO = f"{GH_REPOS}/releases/download/{{0}}/dicthtml-{{0}}-{{0}}{{1}}.zip"
+DOWNLOAD_URL_MOBI = f"{GH_REPOS}/releases/download/{{0}}/dict-{{0}}-{{0}}{{1}}.mobi"
 DOWNLOAD_URL_STARDICT = f"{GH_REPOS}/releases/download/{{0}}/dict-{{0}}-{{0}}{{1}}.zip"
 ASSET_CHECKSUM_ALGO = "sha256"