Prep for 3.4.3 release

Author: sveinbjornt

.github/workflows/python-package.yml

@@ -16,7 +16,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest]
-        python-version: [ "3.7", "3.8", "3.9", "3.10", "3.11", "pypy-3.7", "pypy-3.8", "pypy-3.9"]
+        python-version: [ "3.8", "3.9", "3.10", "3.11", "pypy-3.9", "pypy-3.10"]
 
     steps:
     - uses: actions/checkout@v3
@@ -28,10 +28,10 @@ jobs:
       run: |
         python -m pip install --upgrade pip wheel setuptools
         python -m pip install -e .
-    - name: Type check with mypy (only on Python 3.7)
+    - name: Type check with mypy (only on Python 3.8)
       run: |
-        if [ "${{ matrix.python-version }}" == "3.7" ]; then python -m pip install mypy; fi
-        if [ "${{ matrix.python-version }}" == "3.7" ]; then mypy --python-version=3.7 src/tokenizer; fi
+        if [ "${{ matrix.python-version }}" == "3.8" ]; then python -m pip install mypy; fi
+        if [ "${{ matrix.python-version }}" == "3.8" ]; then mypy --python-version=3.8 src/tokenizer; fi
     - name: Test with pytest
       run: |
         python -m pip install pytest

README.rst

@@ -12,7 +12,7 @@ Tokenization is a necessary first step in many natural language processing
 tasks, such as word counting, parsing, spell checking, corpus generation, and
 statistical analysis of text.
 
-**Tokenizer** is a compact pure-Python (>= 3.7) executable
+**Tokenizer** is a compact pure-Python (>= 3.8) executable
 program and module for tokenizing Icelandic text. It converts input text to
 streams of *tokens*, where each token is a separate word, punctuation sign,
 number/amount, date, e-mail, URL/URI, etc. It also segments the token stream
@@ -809,6 +809,7 @@ can be found in the file ``test/toktest_normal_gold_expected.txt``.
 Changelog
 ---------
 
+* Version 3.4.3: Various minor fixes. Now requires Python 3.8 or later.
 * Version 3.4.2: Abbreviations and phrases added, ``META_BEGIN`` token added.
 * Version 3.4.1: Improved performance on long input chunks.
 * Version 3.4.0: Improved handling and normalization of punctuation.

setup.py

@@ -83,7 +83,6 @@ def read(*names: str, **kwargs: Any) -> str:
         "Natural Language :: Icelandic",
         "Programming Language :: Python",
         "Programming Language :: Python :: 3",
-        "Programming Language :: Python :: 3.7",
         "Programming Language :: Python :: 3.8",
         "Programming Language :: Python :: 3.9",
         "Programming Language :: Python :: 3.10",

src/tokenizer/version.py

@@ -1 +1 @@
-__version__ = "3.4.2"
+__version__ = "3.4.3"