scitex 2.5.0__py3-none-any.whl → 2.7.0__py3-none-any.whl

scitex/scholar/utils/validation/DOIValidator.py

@@ -5,6 +5,7 @@
 # ----------------------------------------
 from __future__ import annotations
 import os
+
 __FILE__ = "./src/scitex/scholar/utils/validation/DOIValidator.py"
 __DIR__ = os.path.dirname(__FILE__)
 # ----------------------------------------
@@ -80,7 +81,7 @@ class DOIValidator:
                     url,
                     timeout=self.timeout,
                     allow_redirects=True,
-                    headers={'User-Agent': self.user_agent}
+                    headers={"User-Agent": self.user_agent},
                 )
 
                 # DOI service returns 404 for invalid DOIs
@@ -93,14 +94,19 @@ class DOIValidator:
                         url,
                         timeout=self.timeout,
                         allow_redirects=True,
-                        headers={'User-Agent': self.user_agent}
+                        headers={"User-Agent": self.user_agent},
                     )
 
                 # Success codes (200-399, including redirects)
                 if 200 <= response.status_code < 400:
                     resolved_url = response.url
                     if resolved_url != url:
-                        return True, "Valid (resolved)", response.status_code, resolved_url
+                        return (
+                            True,
+                            "Valid (resolved)",
+                            response.status_code,
+                            resolved_url,
+                        )
                     return True, "Valid", response.status_code, resolved_url
 
                 # Other error codes
@@ -108,7 +114,9 @@ class DOIValidator:
 
             except requests.exceptions.Timeout:
                 if self.retry_on_timeout and attempt < self.max_retries:
-                    logger.warning(f"DOI validation timeout (attempt {attempt}/{self.max_retries}), retrying...")
+                    logger.warning(
+                        f"DOI validation timeout (attempt {attempt}/{self.max_retries}), retrying..."
+                    )
                     time.sleep(1)  # Brief delay before retry
                     continue
                 return False, "Timeout", 0, None
@@ -145,7 +153,7 @@ class DOIValidator:
 
         for prefix in prefixes:
             if doi.startswith(prefix):
-                doi = doi[len(prefix):]
+                doi = doi[len(prefix) :]
 
         return doi.strip()
 
@@ -201,7 +209,7 @@ class DOIValidator:
         self,
         dois: list[str],
         delay: float = 0.5,
-        progress_callback: Optional[callable] = None
+        progress_callback: Optional[callable] = None,
     ) -> dict:
         """Validate multiple DOIs with rate limiting.
 
@@ -219,30 +227,25 @@ class DOIValidator:
                 'results': [{'doi': str, 'is_valid': bool, 'message': str, ...}, ...]
             }
         """
-        results = {
-            'total': len(dois),
-            'valid': 0,
-            'invalid': 0,
-            'results': []
-        }
+        results = {"total": len(dois), "valid": 0, "invalid": 0, "results": []}
 
         for i, doi in enumerate(dois, 1):
             is_valid, message, status_code, resolved_url = self.validate_doi(doi)
 
             result_entry = {
-                'doi': doi,
-                'is_valid': is_valid,
-                'message': message,
-                'status_code': status_code,
-                'resolved_url': resolved_url
+                "doi": doi,
+                "is_valid": is_valid,
+                "message": message,
+                "status_code": status_code,
+                "resolved_url": resolved_url,
             }
 
-            results['results'].append(result_entry)
+            results["results"].append(result_entry)
 
             if is_valid:
-                results['valid'] += 1
+                results["valid"] += 1
             else:
-                results['invalid'] += 1
+                results["invalid"] += 1
 
             # Call progress callback if provided
             if progress_callback:
@@ -262,15 +265,15 @@ if __name__ == "__main__":
     # Test cases
     test_dois = [
         "10.1038/s41598-023-12345-6",  # Invalid (example)
-        "10.1186/1751-0473-8-7",       # Valid (Git reproducibility paper)
-        "10.1371/journal.pcbi.1007128", # Valid (Manubot paper)
-        "",                             # Empty
-        "invalid-doi",                  # Invalid format
+        "10.1186/1751-0473-8-7",  # Valid (Git reproducibility paper)
+        "10.1371/journal.pcbi.1007128",  # Valid (Manubot paper)
+        "",  # Empty
+        "invalid-doi",  # Invalid format
     ]
 
-    print("="*80)
+    print("=" * 80)
     print("DOI Validator Demo")
-    print("="*80)
+    print("=" * 80)
 
     for doi in test_dois:
         print(f"\nTesting: {doi or '(empty)'}")
@@ -282,8 +285,8 @@ if __name__ == "__main__":
         if resolved_url:
             print(f"  Resolved URL: {resolved_url[:80]}...")
 
-    print("\n" + "="*80)
+    print("\n" + "=" * 80)
     print("Demo complete")
-    print("="*80)
+    print("=" * 80)
 
 # EOF

scitex/scholar/utils/validation/validate_library_dois.py

@@ -57,42 +57,44 @@ def validate_library_dois(
     validator = DOIValidator()
 
     results = {
-        'total_papers': 0,
-        'papers_with_doi': 0,
-        'valid_dois': 0,
-        'invalid_dois': 0,
-        'empty_dois': 0,
-        'invalid_details': []
+        "total_papers": 0,
+        "papers_with_doi": 0,
+        "valid_dois": 0,
+        "invalid_dois": 0,
+        "empty_dois": 0,
+        "invalid_details": [],
     }
 
     # Find all metadata.json files
     metadata_files = sorted(library_path.glob("*/metadata.json"))
-    results['total_papers'] = len(metadata_files)
+    results["total_papers"] = len(metadata_files)
 
     logger.info(f"Found {len(metadata_files)} papers to validate")
 
-    print("\n" + "="*80)
+    print("\n" + "=" * 80)
     print("DOI VALIDATION REPORT")
-    print("="*80)
+    print("=" * 80)
     print(f"Library: {library_path}")
     print(f"Papers: {len(metadata_files)}")
-    print("="*80)
+    print("=" * 80)
 
     for i, metadata_file in enumerate(metadata_files, 1):
         paper_id = metadata_file.parent.name
 
         # Load metadata
-        with open(metadata_file, 'r') as f:
+        with open(metadata_file, "r") as f:
             metadata = json.load(f)
 
-        doi = metadata.get('metadata', {}).get('id', {}).get('doi', '')
-        title = metadata.get('metadata', {}).get('basic', {}).get('title', 'No title')[:60]
+        doi = metadata.get("metadata", {}).get("id", {}).get("doi", "")
+        title = (
+            metadata.get("metadata", {}).get("basic", {}).get("title", "No title")[:60]
+        )
 
         if not doi:
-            results['empty_dois'] += 1
+            results["empty_dois"] += 1
             continue
 
-        results['papers_with_doi'] += 1
+        results["papers_with_doi"] += 1
 
         print(f"\n[{i}/{len(metadata_files)}] {title}...")
         print(f"  Paper ID: {paper_id}")
@@ -102,32 +104,34 @@ def validate_library_dois(
         is_valid, message, status_code, resolved_url = validator.validate_doi(doi)
 
         if is_valid:
-            results['valid_dois'] += 1
+            results["valid_dois"] += 1
             logger.success(f"  ✓ {message}")
             if resolved_url:
                 print(f"  Resolved to: {resolved_url[:70]}...")
         else:
-            results['invalid_dois'] += 1
+            results["invalid_dois"] += 1
             logger.error(f"  ✗ {message}")
 
-            results['invalid_details'].append({
-                'paper_id': paper_id,
-                'title': title,
-                'doi': doi,
-                'reason': message,
-                'status_code': status_code,
-                'metadata_file': str(metadata_file)
-            })
+            results["invalid_details"].append(
+                {
+                    "paper_id": paper_id,
+                    "title": title,
+                    "doi": doi,
+                    "reason": message,
+                    "status_code": status_code,
+                    "metadata_file": str(metadata_file),
+                }
+            )
 
             # Fix invalid DOI if requested
             if fix_invalid:
                 logger.warning(f"  Removing invalid DOI from {metadata_file}")
-                metadata['metadata']['id']['doi'] = ''
-                metadata['metadata']['id']['doi_engines'] = []
-                metadata['metadata']['url']['doi'] = None
-                metadata['metadata']['url']['doi_engines'] = []
+                metadata["metadata"]["id"]["doi"] = ""
+                metadata["metadata"]["id"]["doi_engines"] = []
+                metadata["metadata"]["url"]["doi"] = None
+                metadata["metadata"]["url"]["doi_engines"] = []
 
-                with open(metadata_file, 'w') as f:
+                with open(metadata_file, "w") as f:
                     json.dump(metadata, f, indent=2, ensure_ascii=False)
 
                 logger.info(f"  ✓ Removed invalid DOI from metadata")
@@ -137,22 +141,26 @@ def validate_library_dois(
             time.sleep(delay_between_requests)
 
     # Summary
-    print("\n" + "="*80)
+    print("\n" + "=" * 80)
     print("VALIDATION SUMMARY")
-    print("="*80)
+    print("=" * 80)
     print(f"Total papers: {results['total_papers']}")
     print(f"Papers with DOI: {results['papers_with_doi']}")
-    if results['papers_with_doi'] > 0:
-        print(f"  ✓ Valid DOIs: {results['valid_dois']} ({results['valid_dois']*100/results['papers_with_doi']:.1f}%)")
-        print(f"  ✗ Invalid DOIs: {results['invalid_dois']} ({results['invalid_dois']*100/results['papers_with_doi']:.1f}%)")
+    if results["papers_with_doi"] > 0:
+        print(
+            f"  ✓ Valid DOIs: {results['valid_dois']} ({results['valid_dois'] * 100 / results['papers_with_doi']:.1f}%)"
+        )
+        print(
+            f"  ✗ Invalid DOIs: {results['invalid_dois']} ({results['invalid_dois'] * 100 / results['papers_with_doi']:.1f}%)"
+        )
     print(f"Papers without DOI: {results['empty_dois']}")
 
     # Invalid DOI details
-    if results['invalid_details']:
-        print("\n" + "="*80)
+    if results["invalid_details"]:
+        print("\n" + "=" * 80)
         print(f"INVALID DOI DETAILS ({len(results['invalid_details'])} papers)")
-        print("="*80)
-        for item in results['invalid_details']:
+        print("=" * 80)
+        for item in results["invalid_details"]:
             print(f"\nTitle: {item['title']}")
             print(f"  Paper ID: {item['paper_id']}")
             print(f"  DOI: {item['doi']}")
@@ -161,7 +169,7 @@ def validate_library_dois(
 
     # Save results to file if requested
     if output_file:
-        with open(output_file, 'w') as f:
+        with open(output_file, "w") as f:
             json.dump(results, f, indent=2, ensure_ascii=False)
         logger.success(f"\n✓ Validation results saved to: {output_file}")
 
@@ -171,32 +179,28 @@ def validate_library_dois(
 if __name__ == "__main__":
     import argparse
 
-    parser = argparse.ArgumentParser(description='Validate DOIs in scitex.scholar library')
-    parser.add_argument(
-        '--library-path',
-        type=Path,
-        help='Path to MASTER library directory (default: from config)'
+    parser = argparse.ArgumentParser(
+        description="Validate DOIs in scitex.scholar library"
     )
     parser.add_argument(
-        '--project',
-        type=str,
-        help='Validate specific project only'
+        "--library-path",
+        type=Path,
+        help="Path to MASTER library directory (default: from config)",
     )
+    parser.add_argument("--project", type=str, help="Validate specific project only")
     parser.add_argument(
-        '--delay',
+        "--delay",
         type=float,
         default=0.5,
-        help='Delay between DOI checks in seconds (default: 0.5)'
+        help="Delay between DOI checks in seconds (default: 0.5)",
     )
     parser.add_argument(
-        '--fix',
-        action='store_true',
-        help='Remove invalid DOIs from metadata.json files'
+        "--fix",
+        action="store_true",
+        help="Remove invalid DOIs from metadata.json files",
     )
     parser.add_argument(
-        '--output',
-        type=Path,
-        help='Save validation report to JSON file'
+        "--output", type=Path, help="Save validation report to JSON file"
     )
 
     args = parser.parse_args()
@@ -213,7 +217,7 @@ if __name__ == "__main__":
     logger.success("\n✓ DOI validation complete!")
 
     # Exit with error code if invalid DOIs found
-    if results['invalid_dois'] > 0:
+    if results["invalid_dois"] > 0:
         exit(1)
     else:
         exit(0)

scitex/scholar/zotero/__init__.py

@@ -19,7 +19,7 @@ warnings.warn(
     "Importing from scitex.scholar.zotero is deprecated. "
     "Please use: from scitex.scholar.integration.zotero import ...",
     DeprecationWarning,
-    stacklevel=2
+    stacklevel=2,
 )
 
 # Import from new location for backward compatibility

scitex/security/cli.py

@@ -42,8 +42,7 @@ def check_command(
 
         # Count open alerts
         total = sum(
-            len([a for a in alerts[key] if a.get("state") == "open"])
-            for key in alerts
+            len([a for a in alerts[key] if a.get("state") == "open"]) for key in alerts
         )
 
         if save:
@@ -96,33 +95,21 @@ def main():
     subparsers = parser.add_subparsers(dest="command", help="Commands")
 
     # Check command
-    check_parser = subparsers.add_parser(
-        "check",
-        help="Check GitHub security alerts"
-    )
-    check_parser.add_argument(
-        "--repo",
-        help="Repository in format 'owner/repo' (default: current repo)"
-    )
+    check_parser = subparsers.add_parser("check", help="Check GitHub security alerts")
     check_parser.add_argument(
-        "--save",
-        action="store_true",
-        help="Save report to file"
+        "--repo", help="Repository in format 'owner/repo' (default: current repo)"
     )
+    check_parser.add_argument("--save", action="store_true", help="Save report to file")
     check_parser.add_argument(
-        "--output-dir",
-        help="Output directory (default: ./logs/security)"
+        "--output-dir", help="Output directory (default: ./logs/security)"
     )
 
     # Latest command
-    latest_parser = subparsers.add_parser(
-        "latest",
-        help="Show latest security alerts"
-    )
+    latest_parser = subparsers.add_parser("latest", help="Show latest security alerts")
     latest_parser.add_argument(
         "--dir",
         dest="security_dir",
-        help="Security directory (default: ./logs/security)"
+        help="Security directory (default: ./logs/security)",
     )
 
     args = parser.parse_args()

scitex/security/github.py

@@ -17,6 +17,7 @@ from typing import Dict, List, Optional
 
 class GitHubSecurityError(Exception):
     """Raised when GitHub security operations fail."""
+
     pass
 
 
@@ -68,15 +69,19 @@ def get_secret_alerts(repo: Optional[str] = None) -> List[Dict]:
             owner, repo_name = repo.split("/")
             api_path = f"/repos/{owner}/{repo_name}/secret-scanning/alerts"
 
-        output = _run_gh_command([
-            "api", api_path, "--paginate",
-            "--jq",
-            ".[] | {state, secretType: .secret_type_display_name, "
-            "url: .html_url, "
-            "createdAt: .created_at, "
-            "path: .first_location_detected.path, "
-            "line: .first_location_detected.start_line}"
-        ])
+        output = _run_gh_command(
+            [
+                "api",
+                api_path,
+                "--paginate",
+                "--jq",
+                ".[] | {state, secretType: .secret_type_display_name, "
+                "url: .html_url, "
+                "createdAt: .created_at, "
+                "path: .first_location_detected.path, "
+                "line: .first_location_detected.start_line}",
+            ]
+        )
 
         if not output.strip():
             return []
@@ -108,16 +113,20 @@ def get_dependabot_alerts(repo: Optional[str] = None) -> List[Dict]:
             owner, repo_name = repo.split("/")
             api_path = f"/repos/{owner}/{repo_name}/dependabot/alerts"
 
-        output = _run_gh_command([
-            "api", api_path, "--paginate",
-            "--jq",
-            ".[] | {state, severity: .security_advisory.severity, "
-            "summary: .security_advisory.summary, "
-            "package: .dependency.package.name, "
-            "cve: .security_advisory.cve_id, "
-            "url: .html_url, "
-            "created_at: .created_at}"
-        ])
+        output = _run_gh_command(
+            [
+                "api",
+                api_path,
+                "--paginate",
+                "--jq",
+                ".[] | {state, severity: .security_advisory.severity, "
+                "summary: .security_advisory.summary, "
+                "package: .dependency.package.name, "
+                "cve: .security_advisory.cve_id, "
+                "url: .html_url, "
+                "created_at: .created_at}",
+            ]
+        )
 
         if not output.strip():
             return []
@@ -149,16 +158,20 @@ def get_code_scanning_alerts(repo: Optional[str] = None) -> List[Dict]:
             owner, repo_name = repo.split("/")
             api_path = f"/repos/{owner}/{repo_name}/code-scanning/alerts"
 
-        output = _run_gh_command([
-            "api", api_path, "--paginate",
-            "--jq",
-            ".[] | {state, severity: .rule.severity, "
-            "description: .rule.description, "
-            "location: .most_recent_instance.location.path, "
-            "line: .most_recent_instance.location.start_line, "
-            "url: .html_url, "
-            "created_at: .created_at}"
-        ])
+        output = _run_gh_command(
+            [
+                "api",
+                api_path,
+                "--paginate",
+                "--jq",
+                ".[] | {state, severity: .rule.severity, "
+                "description: .rule.description, "
+                "location: .most_recent_instance.location.path, "
+                "line: .most_recent_instance.location.start_line, "
+                "url: .html_url, "
+                "created_at: .created_at}",
+            ]
+        )
 
         if not output.strip():
             return []
@@ -222,9 +235,9 @@ def format_alerts_report(alerts: Dict[str, List[Dict]]) -> str:
     if secrets:
         for alert in secrets:
             lines.append(f"- [{alert['state']}] {alert['secretType']}")
-            path = alert.get('path', 'N/A')
-            line_num = alert.get('line', '')
-            if path != 'N/A' and line_num:
+            path = alert.get("path", "N/A")
+            line_num = alert.get("line", "")
+            if path != "N/A" and line_num:
                 lines.append(f"  Location: {path}:{line_num}")
             lines.append(f"  Created: {alert.get('createdAt', 'N/A')}")
             lines.append(f"  URL: {alert['url']}")

scitex/session/__init__.py

@@ -5,6 +5,7 @@
 # ----------------------------------------
 from __future__ import annotations
 import os
+
 __FILE__ = __file__
 __DIR__ = os.path.dirname(__FILE__)
 # ----------------------------------------
@@ -41,16 +42,14 @@ from ._decorator import session, run
 # Export public API
 __all__ = [
     # Session lifecycle (main functions)
-    'start',
-    'close',
-    'running2finished',
-
+    "start",
+    "close",
+    "running2finished",
     # Session decorator (new simplified API)
-    'session',
-    'run',
-
+    "session",
+    "run",
     # Advanced session management
-    'SessionManager',
+    "SessionManager",
 ]
 
-# EOF
+# EOF