Fix import sorting with isort

- Fix import order in pygetpapers.py
- Fix import order in hocr_builder.py
- Fix import order in repository_config.py
- Fix import order in rxiv.py
- Fix import order in debug_api.py

All files now pass isort checks.

Author: petermr

pygetpapers/core/hocr_builder.py

@@ -10,13 +10,14 @@
 PURPOSE: Create unified hOCR output format for PDF and image processing
 """
 
-import logging
 import html
+import logging
 import re
-from pathlib import Path
-from typing import Dict, List, Optional, Tuple, Any, Union
 from dataclasses import dataclass, field
 from datetime import datetime
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Tuple, Union
+
 import lxml.etree as ET
 
 logger = logging.getLogger(__name__)

pygetpapers/core/repository_config.py

@@ -10,7 +10,6 @@
 from typing import Any, Dict, List, Optional
 
 import yaml
-
 from src.pygetpapers.abstract_repository import AbstractRepository
 
 logger = logging.getLogger(__name__)

pygetpapers/pygetpapers.py

@@ -563,13 +563,13 @@ def _create_datatables(self, query_namespace):
         """Create datatables HTML files for the corpus."""
         try:
             import os
+
             from pygetpapers.tools.datatables_integration import PygetpapersDatatables
 
             # Debug logging (can be removed in production)
             # logging.info(f"Query namespace output: {query_namespace.get('output')}")
             # logging.info(f"Query namespace datatables: {query_namespace.get('datatables')}")
             # logging.info(f"Self default path: {self.default_path}")
-
             # Initialize datatables
             dt = PygetpapersDatatables()
 
@@ -1057,10 +1057,10 @@ def run_pygetpapers(command_string):
         >>> result = run_pygetpapers(cmd)
         >>> print(result)
     """
+    import contextlib
     import shlex
     import sys
     from io import StringIO
-    import contextlib
 
     # Parse the command string
     if command_string.startswith("pygetpapers"):

pygetpapers/repositories/biorxiv/rxiv.py

@@ -9,11 +9,11 @@
 from pygetpapers.core.download_tools import DownloadTools
 from pygetpapers.core.pgexceptions import PygetpapersError
 from pygetpapers.core.repositoryinterface import (
+    BIORXIV,
     COLLECTION,
     DOI,
     RXIV_RESULT,
     RepositoryInterface,
-    BIORXIV,
 )
 
 TOTAL_HITS = "total_hits"
@@ -319,12 +319,14 @@ def noexecute(self, query_namespace):
         if self._is_text_query(query):
             logging.info(f"Using {source} web scraper for text query (noexecute mode)")
             try:
+                from urllib.parse import quote_plus
+
+                import requests
+                from bs4 import BeautifulSoup
+
                 from pygetpapers.repositories.biorxiv.biorxiv_advanced_scraper import (
                     BioRxivAdvancedScraper,
                 )
-                import requests
-                from bs4 import BeautifulSoup
-                from urllib.parse import quote_plus
 
                 # Use the correct base URL based on the source
                 if source == "medrxiv":

pygetpapers/repositories/upspace/debug_api.py

@@ -4,9 +4,10 @@
 """
 
 import json
-import requests
 from pathlib import Path
 
+import requests
+
 from pygetpapers.repositories.upspace.upspace import UPSpace