fix lint

f

Author: NastyBoget

.github/workflows/docs.yaml

@@ -16,6 +16,11 @@ jobs:
       uses: actions/setup-python@v2
       with:
         python-version: '3.10'
+    - name: Set up JDK
+      uses: actions/setup-java@v6
+      with:
+        distribution: 'temurin'
+        java-version: '25'
 
     - name: Install dependencies
       run: |

dedoc/readers/pdf_reader/pdf_auto_reader/txtlayer_detector.py

@@ -72,9 +72,9 @@ def __classify_all_pages(
         #    by the time the second read would reference them.
         pages_reusable = (
             not reusable
-            and start == 1
-            and get_param_pdf_with_txt_layer(parameters) == "auto_tabby"
-            and not get_param_with_attachments(parameters)
+            and start == 1  # noqa W503
+            and get_param_pdf_with_txt_layer(parameters) == "auto_tabby"  # noqa W503
+            and not get_param_with_attachments(parameters)  # noqa W503
         )
         detected_pages = [] if pages_reusable else None
         if reusable:
@@ -98,8 +98,16 @@ def __classify_all_pages(
         first_page_lines = [line for line in document.lines if line.metadata.page_id == 0]
         first_page_correct = txtlayer_classifier.predict([first_page_lines])[0]
         if first_page_correct:
-            return [TxtLayerResult(correct=True, start=start, end=end, document=reuse_document,
-                                   detected_pages=detected_pages, detected_last_page=detected_last_page)]
+            return [
+                TxtLayerResult(
+                    correct=True,
+                    start=start,
+                    end=end,
+                    document=reuse_document,
+                    detected_pages=detected_pages,
+                    detected_last_page=detected_last_page
+                )
+            ]
         else:
             # the leading pages are not read as one chunk here, so the detection extraction cannot be reused as-is
             return [TxtLayerResult(correct=False, start=start, end=start), TxtLayerResult(correct=True, start=start + 1, end=end)]

dedoc/readers/pdf_reader/pdf_txtlayer_reader/pdf_tabby_reader.py

@@ -416,7 +416,7 @@ def __process_pdf(self,
         import os
 
         self.__run(path=path, start_page=start_page, end_page=end_page, tmp_dir=tmp_dir, remove_frame=remove_frame, gost_json_path=gost_json_path)
-        with open(os.path.join(tmp_dir, "data.json"), "r", encoding="utf-8") as response:  # encoding= : data.json is UTF-8, avoids cp1251 breakage on RU-locale Windows
+        with open(os.path.join(tmp_dir, "data.json"), "r", encoding="utf-8") as response:
             return json.load(response)
 
     def _process_one_page(self,