Refactoring

.flake8

@@ -0,0 +1,6 @@
+[flake8]
+max-line-length = 80
+extend-select = B950
+extend-ignore = E203,E501,E701
+per-file-ignores =
+    quaxa/__init__.py:F401

.github/workflows/test.yml

@@ -0,0 +1,25 @@
+name: Python application
+
+on: [push]
+
+jobs:
+  build:
+    strategy:
+      matrix:
+        platform: [windows-latest, macos-latest, ubuntu-latest]
+
+    runs-on: ${{ matrix.platform }}
+
+    steps:
+    - uses: actions/checkout@v4
+    - uses: actions/setup-python@v5
+      with:
+        python-version: "3.x"
+    - name: Install dependencies
+      run: |
+        pip install -U pip
+        pip install -r requirements-dev.txt
+        pip install .
+    - name: Run unit tests
+      run: |
+        python -m unittest

.gitignore

@@ -108,3 +108,4 @@ venv.bak/
 .vscode
 profile/data*
 .theia
+*.temp

.pre-commit-config.yaml

@@ -0,0 +1,27 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+repos:
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v3.2.0
+  hooks:
+  - id: trailing-whitespace
+  - id: end-of-file-fixer
+  - id: check-yaml
+  - id: check-added-large-files
+- repo: https://github.com/psf/black
+  rev: 22.10.0
+  hooks:
+    - id: black
+- repo: https://github.com/PyCQA/flake8
+  rev: 7.0.0
+  hooks:
+    - id: flake8
+      additional_dependencies: [flake8-bugbear]
+- repo: https://github.com/pycqa/isort
+  rev: 5.12.0
+  hooks:
+    - id: isort
+- repo: https://github.com/pre-commit/mirrors-mypy
+  rev: v1.8.0
+  hooks:
+    - id: mypy

.zenodo.json

@@ -18,4 +18,4 @@
     "good example extractor",
     "German"
   ]
-}
+}

LICENSE

@@ -198,4 +198,4 @@
    distributed under the License is distributed on an "AS IS" BASIS,
    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    See the License for the specific language governing permissions and
-   limitations under the License.
+   limitations under the License.

README.md

@@ -25,7 +25,7 @@ Wenn 1 Knock-out Kriterium identifiziert wird, dann wird direkt der Score direkt
 | `has_blacklist_words` | bool | Satzbeleg enthält Wörter, sodass in keinem Fall der Satzbeleg als Wörterbuchbeispiel in Betracht gezogen wird; ausgenommen das Blacklist-Wort ist selbt der Wörterbucheintrag. (dt. Blacklist ist voreingestellt) | [1] GDEX blacklist |
 
 ### Diskontierungsfakoren
-Je Kriterium wird ein Faktor berechnet, und alle Faktoren miteinander multipliziert. 
+Je Kriterium wird ein Faktor berechnet, und alle Faktoren miteinander multipliziert.
 Wenn bspw. ein Faktor eine Penality von 0.1 bekommt, dann ist der Faktor 0.9.
 Für den Gesamtscore wird der Gesamtfaktor mit 0.5 multipliziert.
 
@@ -79,11 +79,11 @@ pip install -r requirements-dev.txt --no-cache-dir
 Publish
 
 ```sh
-python setup.py sdist 
+python setup.py sdist
 twine upload -r pypi dist/*
 ```
 
-### Clean up 
+### Clean up
 
 ```sh
 find . -type f -name "*.pyc" | xargs rm
@@ -106,4 +106,4 @@ The "Evidence" project was funded by the Deutsche Forschungsgemeinschaft (DFG, G
 
 ### Maintenance
 - till 31.Aug.2023 (v0.1.0) the code repository was maintained within the DFG project [433249742](https://gepris.dfg.de/gepris/projekt/433249742)
-- since 01.Sep.2023 (v0.1.0) the code repository is maintained by Ulf Hamster.
+- since 01.Sep.2023 (v0.1.0) the code repository is maintained by Ulf Hamster.

VERSION

@@ -0,0 +1 @@
+0.1.1

demo/demo_quaxa.py

@@ -1,5 +1,7 @@
-import conllu
 import random
+
+import conllu
+
 import quaxa
 import quaxa.reader
 
@@ -8,21 +10,19 @@
 
 def demo():
     # read conllu file
-    corpus = conllu.parse(open('demo.conllu', 'r').read())
+    corpus = conllu.parse(open("demo.conllu", "r").read())
     # compute scores for example sentences
     for annot in corpus:
         lemmas_content = [
-            tok.get('lemma') for tok in annot 
-            if tok.get('upos') in {'NOUN', 'VERB', 'ADJ'}
+            tok.get("lemma")
+            for tok in annot
+            if tok.get("upos") in {"NOUN", "VERB", "ADJ"}
         ]
-        sent = annot.metadata['text']
+        sent = annot.metadata["text"]
         for headword in lemmas_content:
-            factor = quaxa.total_score(
-                headword=headword, txt=sent, annotation=annot)
-            print((
-                "total_score:"
-                f"{factor: 7.4f}  | {headword} | {sent[:50]} ..."))
+            factor = quaxa.total_score(headword=headword, txt=sent, annotation=annot)
+            print(("total_score:" f"{factor: 7.4f}  | {headword} | {sent[:50]} ..."))
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     demo()

pyproject.toml

@@ -0,0 +1,34 @@
+[build-system]
+requires = ["setuptools"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "quaxa"
+description = "QUAlity of sentence eXAmples scoring"
+authors = [{name = "Ulf Hamster", email = "[email protected]"}]
+classifiers = [
+    "Development Status :: 1 - Planning",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: Apache Software License",
+    "Topic :: Education",
+    "Topic :: Scientific/Engineering",
+    "Topic :: Text Processing :: Linguistic"
+]
+requires-python = ">=3.7"
+dynamic = ["dependencies", "version", "readme"]
+
+[project.urls]
+Homepage = "https://github.com/ulf1/quaxa"
+
+[tool.isort]
+profile = "black"
+
+[tool.setuptools.dynamic]
+dependencies = {file = ["requirements.txt"]}
+version = {file = ["VERSION"]}
+readme = {file = ["README.md"], content-type = "text/markdown"}
+
+[tool.setuptools.packages.find]
+include = ["quaxa*"]
+exclude = ["test*"]

quaxa/__init__.py

@@ -1,19 +1,28 @@
-__version__ = '0.1.1'
+from pathlib import Path
+
+__version__ = (Path(__file__) / ".." / ".." / "VERSION").resolve().read_text().strip()
 
 from .quaxa import (
-    total_score,
-    isa_knockout_criteria,
+    BLACKLIST_WORDS_DE,
+    DEFAULT_SPACE_DEIXIS_TERMS,
+    DEFAULT_TIME_DEIXIS_TERMS,
+    ORD_RARE_CHARS_DE,
+    ORDS_QWERTZ_DE,
+    QWERTZ_DE,
+    RARE_CHARS_DE,
+    deixis_person,
+    deixis_space,
+    deixis_time,
     factor_gradual_criteria,
-    has_finite_verb_and_subject,
-    is_misparsed,
-    has_illegal_chars,
-    has_blacklist_words, BLACKLIST_WORDS_DE,
-    factor_rarechars, RARE_CHARS_DE, ORD_RARE_CHARS_DE,
-    factor_notkeyboardchar, QWERTZ_DE, ORDS_QWERTZ_DE,
     factor_graylist_words,
     factor_named_entity,
-    deixis_space, DEFAULT_SPACE_DEIXIS_TERMS,
-    deixis_time, DEFAULT_TIME_DEIXIS_TERMS,
-    deixis_person,
-    optimal_interval
+    factor_notkeyboardchar,
+    factor_rarechars,
+    has_blacklist_words,
+    has_finite_verb_and_subject,
+    has_illegal_chars,
+    is_misparsed,
+    isa_knockout_criteria,
+    optimal_interval,
+    total_score,
 )