prepare version 1.0.0 (#131)

* prepare version 1.0.0

* make sure tests can be reproduced

* fix mypy version

* update readme

* fix history

* update included files

HISTORY.rst

@@ -2,6 +2,31 @@
 History
 =======
 
+1.0.0
+-----
+
+Extensive refactoring by @juanjoDiaz:
+- Series of modular classes
+- Different lemmatization strategies available
+- Customization of dictionary loading and handling (`DictionaryFactory`)
+- `LanguageDetector` class with extended options
+- See readme and [detailed documentation](https://adbar.github.io/simplemma/)
+
+Breaking changes:
+- The `extensive` argument is now `greedy`
+- The `langdetect` submodule is now `language_detector`
+`from simplemma.langdetect import ...` → `from simplemma.language_detector import ...`
+
+Fixes and improvements:
+- `is_known()` function now restored to its state in v0.9.0 (full dictionary)
+- More languages and better rules (with @juanjoDiaz)
+- Use binary strings in dictionaries to save memory
+- Dictionary sort before compression by @1over137
+
+Documentation:
+- Classes and general doc pages by @juanjoDiaz 
+- Section on classes in the readme by @osma
+
 
 0.9.1
 -----

MANIFEST.in

@@ -1,17 +1,20 @@
-#include AUTHORS.rst
-#include CONTRIBUTING.rst
 include CITATION.cff
 include HISTORY.rst
 include LICENSE
-include README.rst
+include README.md
 include licenses/
 include simplemma/py.typed
-graft simplemma/data/
+graft simplemma/strategies/
 
 recursive-exclude * __pycache__
 recursive-exclude * *.py[co]
 include tests/__init__.py tests/test_*.py
 graft tests/data/
+graft tests/strategies/
 
-recursive-include conf.py Makefile make.bat *.jpg *.png *.gif
-# recursive-include docs *.rst
+graft licenses/
+
+include training/*.py training/*.rst training/*.txt
+
+# recursive-include docs *.md
+# include requirements-*.txt

README.md

@@ -219,10 +219,6 @@ a lesser accuracy.
 
 ### Advanced usage via classes
 
-*The following classes will be made available in the next version. To
-start using them, install the latest version from the git repository.
-The full docs are available [here](https://adbar.github.io/simplemma/)*
-
 The above described functions are suitable for simple usage, but it is
 possible to have more control by instantiating Simplemma classes and
 calling their methods instead. Lemmatization is handled by the
@@ -260,6 +256,9 @@ LANG_CACHE_SIZE = 5  # How many language dictionaries to keep in memory at once
 0.5
 ```
 
+For more information see the
+[extended documentation](https://adbar.github.io/simplemma/).
+
 
 ## Supported languages
 

requirements-dev.txt

@@ -1,6 +1,6 @@
-black==24.4.1
+black==24.4.2
 flake8==7.0.0
 mypy==1.10.0
-pytest==8.1.1
+pytest==8.2.1
 pytest-cov==5.0.0
-types-requests==2.31.0.20240406
+types-requests==2.32.0.20240523

setup.py

@@ -1,5 +1,3 @@
-#!/usr/bin/env python
-
 """The setup script."""
 
 import re
@@ -30,7 +28,7 @@ def get_version(package):
     author_email="[email protected]",
     python_requires=">=3.6",
     classifiers=[  # https://pypi.org/classifiers/
-        "Development Status :: 3 - Alpha",
+        "Development Status :: 4 - Beta",
         "Intended Audience :: Developers",
         "Intended Audience :: Education",
         "Intended Audience :: Information Technology",
@@ -80,6 +78,7 @@ def get_version(package):
         "Programming Language :: Python :: 3.10",
         "Programming Language :: Python :: 3.11",
         "Programming Language :: Python :: 3.12",
+        "Programming Language :: Python :: 3.13",
         "Topic :: Scientific/Engineering :: Information Analysis",
         "Topic :: Software Development :: Internationalization",
         "Topic :: Software Development :: Localization",
@@ -105,8 +104,8 @@ def get_version(package):
     packages=find_packages(include=["simplemma", "simplemma.*"]),
     project_urls={
         "Source": "https://github.com/adbar/simplemma",
-        "Docs": "https://adbar.github.io/simplemma",
-        "Blog": "https://adrien.barbaresi.eu/blog/",  # tag/simplemma
+        "Docs": "https://adbar.github.io/simplemma/",
+        # "Blog": "https://adrien.barbaresi.eu/blog/",  # tag/simplemma
     },
     setup_requires=setup_requirements,
     test_suite="tests",

simplemma/__init__.py

@@ -14,7 +14,7 @@
 __author__ = "Adrien Barbaresi, Juanjo Diaz and contributors"
 __email__ = "[email protected]"
 __license__ = "MIT"
-__version__ = "0.9.1"
+__version__ = "1.0.0"
 
 
 from .language_detector import LanguageDetector, in_target_language, langdetect