chore: set up initial pre-commit hooks

.github/FUNDING.yml

@@ -1,4 +1,4 @@
 # These are supported funding model platforms
 
-github: chrismattmann 
+github: chrismattmann
 custom: ["https://www.paypal.me/MattmannAI", "https://venmo.com/Chris-Mattmann"]

.github/workflows/ci.yml

@@ -7,6 +7,16 @@ on:
   pull_request:
 
 jobs:
+  lint:
+    runs-on: ubuntu-slim
+    steps:
+    - uses: actions/checkout@v6
+    - uses: actions/setup-python@v6
+      with:
+        python-version: "3.14"
+    # Ref: https://github.com/tox-dev/action-pre-commit-uv
+    - uses: tox-dev/action-pre-commit-uv@246b66536e366bb885f52d61983bf32f7c95e8b1 # 1.0.3
+
   test:
     runs-on: ${{ matrix.os }}
     strategy:

.pre-commit-config.yaml

@@ -0,0 +1,20 @@
+# pre-commit
+# Ref: https://pre-commit.com/#usage
+# ------------------------------------------------------------------------------
+
+default_language_version:
+  python: '3.14'
+
+repos:
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: 3e8a8703264a2f4a69428a0aa4dcb512790b2c8c  # frozen: v6.0.0
+  hooks:
+  - id: check-merge-conflict
+  - id: check-case-conflict
+  - id: check-ast
+  - id: debug-statements
+  - id: check-toml
+  - id: check-yaml
+  - id: end-of-file-fixer
+    exclude_types: [csv]
+  - id: trailing-whitespace

docs/source/readme.rst

@@ -2,4 +2,4 @@ README.md
 ==========
 
 .. include:: ../../README.md
-   :parser: myst_parser.sphinx_
+   :parser: myst_parser.sphinx_

tests/conftest.py

@@ -8,4 +8,3 @@
 @pytest.fixture
 def test_file_path():
     return Path(__file__).parent / "files" / "rwservlet.pdf"
-

tests/test_parser.py

@@ -42,4 +42,3 @@ def test_local_buffer():
 def test_local_path(test_file_path):
     """parse file path"""
     assert parser.from_file(str(test_file_path))
-

tests/test_prep.txt

@@ -1,7 +1,7 @@
 Tika
 Tika supports dozens of document types. Each should be tested when extended
 Client applications manage event streams, so test stream type/doc type combinations
- 
+
 Document types
 pdf - http://www.fns.usda.gov/sites/default/files/snap/2014-SNAP-Retailer-Management-Annual-Report.pdf
 pdf - http://dcra.dc.gov/sites/default/files/dc/sites/dcra/publication/attachments/ai_NuisanceAbatement.pdf

tika/config.py

@@ -25,4 +25,3 @@ def getMimeTypes():
 
 def getDetectors():
     return getConfig('detectors')[1]
-

tika/tika.py

@@ -903,4 +903,3 @@ def main(argv=None):
     else:
         out.write(resp)
     out.write('\n')
-

tika/translate.py

@@ -12,7 +12,7 @@
 # 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.
-# 
+#
 
 from .tika import ServerEndpoint, Translator, callServer, doTranslate1
 
@@ -38,7 +38,7 @@ def from_buffer(string, srcLang, destLang, serverEndpoint=ServerEndpoint, reques
     :param serverEndpoint:
     :return:
     '''
-    status, response = callServer('put', ServerEndpoint, '/translate/all/'+Translator+'/'+srcLang+'/'+destLang, 
+    status, response = callServer('put', ServerEndpoint, '/translate/all/'+Translator+'/'+srcLang+'/'+destLang,
                                   string, {'Accept': 'text/plain'}, False, requestOptions=requestOptions)
     return response
 
@@ -51,7 +51,7 @@ def auto_from_file(filename, destLang, serverEndpoint=ServerEndpoint, requestOpt
     :return:
     '''
     jsonOutput = doTranslate1(destLang, filename, serverEndpoint, requestOptions=requestOptions)
-    return jsonOutput[1]    
+    return jsonOutput[1]
 
 def auto_from_buffer(string, destLang, serverEndpoint=ServerEndpoint, requestOptions={}):
     '''
@@ -61,7 +61,6 @@ def auto_from_buffer(string, destLang, serverEndpoint=ServerEndpoint, requestOpt
     :param serverEndpoint: Tika server end point (Optional)
     :return:
     '''
-    status, response = callServer('put', ServerEndpoint, '/translate/all/'+Translator+'/'+destLang, 
+    status, response = callServer('put', ServerEndpoint, '/translate/all/'+Translator+'/'+destLang,
                                   string, {'Accept': 'text/plain'}, False, requestOptions=requestOptions)
     return response
-