scitex 2.5.0__py3-none-any.whl → 2.7.3__py3-none-any.whl

scitex/utils/_search.py

@@ -71,17 +71,17 @@ def search(
         # Check for numpy arrays first
         if isinstance(string_or_pattern, np.ndarray):
             return string_or_pattern.tolist()
-        
+
         # Check for pandas types if pandas is available
         if pd is not None:
             if isinstance(string_or_pattern, (pd.Series, pd.Index)):
                 return string_or_pattern.tolist()
-        
+
         # Check for xarray types if xarray is available
         if xr is not None:
             if isinstance(string_or_pattern, xr.DataArray):
                 return string_or_pattern.tolist()
-        
+
         # Check for other iterables
         if isinstance(string_or_pattern, abc.KeysView):
             return list(string_or_pattern)
@@ -106,9 +106,9 @@ def search(
     keys_matched = list(np.array(strings)[indices_matched])
 
     if ensure_one:
-        assert (
-            len(indices_matched) == 1
-        ), "Expected exactly one match, but found {}".format(len(indices_matched))
+        assert len(indices_matched) == 1, (
+            "Expected exactly one match, but found {}".format(len(indices_matched))
+        )
 
     if as_bool:
         bool_matched = np.zeros(len(strings), dtype=bool)

scitex/utils/_verify_scitex_format.py

@@ -5,9 +5,8 @@
 # ----------------------------------------
 from __future__ import annotations
 import os
-__FILE__ = (
-    "./src/scitex/utils/_verify_scitex_format.py"
-)
+
+__FILE__ = "./src/scitex/utils/_verify_scitex_format.py"
 __DIR__ = os.path.dirname(__FILE__)
 # ----------------------------------------
 
@@ -48,6 +47,8 @@ logger = logging.getLogger(__name__)
 
 
 """Functions & Classes"""
+
+
 @dataclass
 class FileInfo:
     """Store file information."""
@@ -104,9 +105,7 @@ class TemplateCompliance:
         return sum(checks) / len(checks)
 
 
-def scan_python_files(
-    paths: list[Path], base_dir: Path = None
-) -> Dict[str, FileInfo]:
+def scan_python_files(paths: list[Path], base_dir: Path = None) -> Dict[str, FileInfo]:
     """Scan Python files from filesystem paths.
 
     Args:
@@ -136,9 +135,7 @@ def scan_python_files(
 
         for py_file in python_files:
             # Skip template.py, __init__.py, and test files
-            if any(
-                skip in py_file.name for skip in ["template.py", "__init__.py"]
-            ):
+            if any(skip in py_file.name for skip in ["template.py", "__init__.py"]):
                 continue
 
             try:
@@ -162,9 +159,7 @@ def check_compliance(content: str) -> TemplateCompliance:
     compliance = TemplateCompliance()
 
     # Check for main function
-    compliance.has_main = bool(
-        re.search(r"^def main\(", content, re.MULTILINE)
-    )
+    compliance.has_main = bool(re.search(r"^def main\(", content, re.MULTILINE))
 
     # Check for parse_args function
     compliance.has_parse_args = bool(
@@ -172,14 +167,10 @@ def check_compliance(content: str) -> TemplateCompliance:
     )
 
     # Check for run_main function
-    compliance.has_run_main = bool(
-        re.search(r"^def run_main\(", content, re.MULTILINE)
-    )
+    compliance.has_run_main = bool(re.search(r"^def run_main\(", content, re.MULTILINE))
 
     # Check for main guard
-    compliance.has_main_guard = bool(
-        re.search(r'if __name__ == "__main__":', content)
-    )
+    compliance.has_main_guard = bool(re.search(r'if __name__ == "__main__":', content))
 
     # Check if run_main follows the exact template format
     compliance.is_run_main_unchanged = _check_run_main_unchanged(content)
@@ -194,9 +185,7 @@ def check_compliance(content: str) -> TemplateCompliance:
     )
 
     # Check for scitex session usage
-    compliance.uses_scitex_session = bool(
-        re.search(r"stx\.session\.start", content)
-    )
+    compliance.uses_scitex_session = bool(re.search(r"stx\.session\.start", content))
 
     # Check for verbose parameter
     compliance.has_verbose_param = bool(
@@ -250,7 +239,7 @@ def generate_report(results: Dict[str, tuple]) -> str:
     lines.append(f"Total Python files analyzed: {total_files}")
     if total_files > 0:
         lines.append(
-            f"Fully compliant files: {compliant_files} ({compliant_files/total_files*100:.1f}%)"
+            f"Fully compliant files: {compliant_files} ({compliant_files / total_files * 100:.1f}%)"
         )
         lines.append(f"Average compliance score: {avg_score:.1%}")
     else:
@@ -280,9 +269,7 @@ def generate_report(results: Dict[str, tuple]) -> str:
             status = "✗ NON-COMPLIANT"
 
         lines.append(f"{status} [{score:.0%}] {filepath}")
-        lines.append(
-            f"  Lines: {file_info.lines}, Size: {file_info.size} bytes"
-        )
+        lines.append(f"  Lines: {file_info.lines}, Size: {file_info.size} bytes")
 
         # Show missing components
         if not compliance.is_compliant:
@@ -315,9 +302,7 @@ def generate_report(results: Dict[str, tuple]) -> str:
             optional_missing.append("verbose parameter")
 
         if optional_missing:
-            lines.append(
-                f"  ⚠️  OPTIONAL Missing: {', '.join(optional_missing)}"
-            )
+            lines.append(f"  ⚠️  OPTIONAL Missing: {', '.join(optional_missing)}")
 
         lines.append("")
 
@@ -358,11 +343,7 @@ def generate_report(results: Dict[str, tuple]) -> str:
         ),
         (
             "  'Functions & Classes'",
-            sum(
-                1
-                for _, c in results.values()
-                if c.has_functions_classes_section
-            ),
+            sum(1 for _, c in results.values() if c.has_functions_classes_section),
         ),
         (
             "  scitex session",
@@ -411,9 +392,7 @@ def generate_report(results: Dict[str, tuple]) -> str:
             if not compliance.has_main_guard:
                 fixes.append("  - Add if __name__ == '__main__': run_main()")
             if not compliance.is_run_main_unchanged:
-                fixes.append(
-                    "  - Update run_main() to match template format exactly"
-                )
+                fixes.append("  - Update run_main() to match template format exactly")
             for fix in fixes:
                 lines.append(fix)
             lines.append("")
@@ -441,9 +420,7 @@ def main(args):
     else:
         # Default to current directory
         paths = [Path.cwd()]
-        base_dir = (
-            Path(args.base_dir).resolve() if args.base_dir else Path.cwd()
-        )
+        base_dir = Path(args.base_dir).resolve() if args.base_dir else Path.cwd()
 
     logger.info(f"Scanning paths: {[str(p) for p in paths]}")
     logger.info(f"Base directory: {base_dir}")
@@ -479,9 +456,7 @@ def main(args):
         logger.success("All files are compliant!")
         return 0
     else:
-        logger.warning(
-            f"{len(results) - compliant_count} files need attention"
-        )
+        logger.warning(f"{len(results) - compliant_count} files need attention")
         return 0  # Still return 0 to avoid breaking pipelines
 
 

scitex/utils/_verify_scitex_format_v01.py

@@ -5,9 +5,8 @@
 # ----------------------------------------
 from __future__ import annotations
 import os
-__FILE__ = (
-    "./src/scitex/utils/_verify_scitex_format.py"
-)
+
+__FILE__ = "./src/scitex/utils/_verify_scitex_format.py"
 __DIR__ = os.path.dirname(__FILE__)
 # ----------------------------------------
 """Analyze template compliance from document text."""
@@ -94,10 +93,7 @@ def parse_document(doc_text: str) -> Dict[str, FileInfo]:
         content = match.group(5)
 
         # Only process .py files, skip template.py
-        if (
-            relative_path.endswith(".py")
-            and "template.py" not in relative_path
-        ):
+        if relative_path.endswith(".py") and "template.py" not in relative_path:
             files[relative_path] = FileInfo(
                 relative_path=relative_path,
                 content=content,
@@ -113,9 +109,7 @@ def check_compliance(content: str) -> TemplateCompliance:
     compliance = TemplateCompliance()
 
     # Check for main function
-    compliance.has_main = bool(
-        re.search(r"^def main\(", content, re.MULTILINE)
-    )
+    compliance.has_main = bool(re.search(r"^def main\(", content, re.MULTILINE))
 
     # Check for parse_args function
     compliance.has_parse_args = bool(
@@ -123,14 +117,10 @@ def check_compliance(content: str) -> TemplateCompliance:
     )
 
     # Check for run_main function
-    compliance.has_run_main = bool(
-        re.search(r"^def run_main\(", content, re.MULTILINE)
-    )
+    compliance.has_run_main = bool(re.search(r"^def run_main\(", content, re.MULTILINE))
 
     # Check for main guard
-    compliance.has_main_guard = bool(
-        re.search(r'if __name__ == "__main__":', content)
-    )
+    compliance.has_main_guard = bool(re.search(r'if __name__ == "__main__":', content))
 
     # Check for module docstring
     compliance.has_docstring = bool(re.search(r'"""[\s\S]*?"""', content))
@@ -142,9 +132,7 @@ def check_compliance(content: str) -> TemplateCompliance:
     )
 
     # Check for scitex session usage
-    compliance.uses_scitex_session = bool(
-        re.search(r"stx\.session\.start", content)
-    )
+    compliance.uses_scitex_session = bool(re.search(r"stx\.session\.start", content))
 
     # Check for verbose parameter
     compliance.has_verbose_param = bool(
@@ -173,7 +161,7 @@ def generate_report(results: Dict[str, tuple]) -> str:
 
     lines.append(f"Total Python files analyzed: {total_files}")
     lines.append(
-        f"Fully compliant files: {compliant_files} ({compliant_files/total_files*100:.1f}%)"
+        f"Fully compliant files: {compliant_files} ({compliant_files / total_files * 100:.1f}%)"
     )
     lines.append(f"Average compliance score: {avg_score:.1%}")
     lines.append("")
@@ -201,9 +189,7 @@ def generate_report(results: Dict[str, tuple]) -> str:
             status = "✗ NON-COMPLIANT"
 
         lines.append(f"{status} [{score:.0%}] {filepath}")
-        lines.append(
-            f"  Lines: {file_info.lines}, Size: {file_info.size} bytes"
-        )
+        lines.append(f"  Lines: {file_info.lines}, Size: {file_info.size} bytes")
 
         # Show missing components
         if not compliance.is_compliant:
@@ -234,9 +220,7 @@ def generate_report(results: Dict[str, tuple]) -> str:
             optional_missing.append("verbose parameter")
 
         if optional_missing:
-            lines.append(
-                f"  ⚠️  OPTIONAL Missing: {', '.join(optional_missing)}"
-            )
+            lines.append(f"  ⚠️  OPTIONAL Missing: {', '.join(optional_missing)}")
 
         lines.append("")
 
@@ -273,11 +257,7 @@ def generate_report(results: Dict[str, tuple]) -> str:
         ),
         (
             "  'Functions & Classes'",
-            sum(
-                1
-                for _, c in results.values()
-                if c.has_functions_classes_section
-            ),
+            sum(1 for _, c in results.values() if c.has_functions_classes_section),
         ),
         (
             "  scitex session",
@@ -337,9 +317,7 @@ def generate_report(results: Dict[str, tuple]) -> str:
 def main():
     """Main function."""
     # Read the document
-    with open(
-        "/mnt/user-data/uploads/document_1.txt", "r", encoding="utf-8"
-    ) as f:
+    with open("/mnt/user-data/uploads/document_1.txt", "r", encoding="utf-8") as f:
         doc_text = f.read()
 
     print("Parsing document...")

scitex/utils/template.py

@@ -5,9 +5,8 @@
 # ----------------------------------------
 from __future__ import annotations
 import os
-__FILE__ = (
-    "./src/scitex/utils/template.py"
-)
+
+__FILE__ = "./src/scitex/utils/template.py"
 __DIR__ = os.path.dirname(__FILE__)
 # ----------------------------------------
 
@@ -55,6 +54,8 @@ logger = logging.getLogger(__name__)
 # CONFIG = stx.io.load_configs()
 
 """Functions & Classes"""
+
+
 def main(args):
     return 0
 

scitex/web/__init__.py

@@ -15,7 +15,13 @@ from ._search_pubmed import (
     parse_args,
     run_main,
 )
-from ._summarize_url import summarize_url, extract_main_content, crawl_url, crawl_to_json, summarize_all
+from ._summarize_url import (
+    summarize_url,
+    extract_main_content,
+    crawl_url,
+    crawl_to_json,
+    summarize_all,
+)
 from ._scraping import get_urls, download_images, get_image_urls
 
 __all__ = [

scitex/web/_scraping.py

@@ -19,6 +19,7 @@ from tqdm import tqdm
 try:
     from PIL import Image
     from io import BytesIO
+
     PILLOW_AVAILABLE = True
 except ImportError:
     PILLOW_AVAILABLE = False
@@ -30,7 +31,7 @@ logger = getLogger(__name__)
 
 def _get_default_download_dir() -> str:
     """Get default download directory using SCITEX_DIR if available."""
-    scitex_root = os.environ.get('SCITEX_DIR')
+    scitex_root = os.environ.get("SCITEX_DIR")
     if scitex_root is None:
         scitex_root = os.path.expanduser("~/.scitex")
     return os.path.join(scitex_root, "web", "downloads")
@@ -68,7 +69,7 @@ def get_urls(
         logger.error(f"Failed to fetch URL {url}: {e}")
         return []
 
-    soup = BeautifulSoup(response.text, 'html.parser')
+    soup = BeautifulSoup(response.text, "html.parser")
     urls_found: Set[str] = set()
 
     # Parse the base domain
@@ -76,8 +77,8 @@ def get_urls(
     base_domain = f"{parsed_base.scheme}://{parsed_base.netloc}"
 
     # Find all links
-    for link in soup.find_all('a', href=True):
-        href = link['href']
+    for link in soup.find_all("a", href=True):
+        href = link["href"]
 
         # Convert to absolute URL if requested
         if absolute:
@@ -146,7 +147,7 @@ def download_images(
     # Set default output directory
     if output_dir is None:
         # Check SCITEX_WEB_DOWNLOADS_DIR first
-        output_dir = os.environ.get('SCITEX_WEB_DOWNLOADS_DIR')
+        output_dir = os.environ.get("SCITEX_WEB_DOWNLOADS_DIR")
         if output_dir is None:
             # Fall back to SCITEX_DIR/web/downloads
             output_dir = _get_default_download_dir()
@@ -166,21 +167,21 @@ def download_images(
         logger.error(f"Failed to fetch URL {url}: {e}")
         return []
 
-    soup = BeautifulSoup(response.text, 'html.parser')
+    soup = BeautifulSoup(response.text, "html.parser")
     image_urls: Set[str] = set()
 
     # Parse the base domain
     parsed_base = urllib.parse.urlparse(url)
 
     # Find all image tags
-    for img in soup.find_all('img', src=True):
-        img_url = img['src']
+    for img in soup.find_all("img", src=True):
+        img_url = img["src"]
 
         # Convert to absolute URL
         img_url = urllib.parse.urljoin(url, img_url)
 
         # Skip SVG files (vector graphics, not raster images)
-        if img_url.lower().endswith(('.svg', '.svgz')):
+        if img_url.lower().endswith((".svg", ".svgz")):
             continue
 
         # Filter by domain if requested
@@ -220,16 +221,16 @@ def download_images(
             filename = Path(parsed_url.path).name
 
             # If filename is empty or doesn't have extension, generate one
-            if not filename or '.' not in filename:
-                ext = '.jpg'  # default extension
-                if 'content-type' in img_response.headers:
-                    content_type = img_response.headers['content-type']
-                    if 'png' in content_type:
-                        ext = '.png'
-                    elif 'gif' in content_type:
-                        ext = '.gif'
-                    elif 'webp' in content_type:
-                        ext = '.webp'
+            if not filename or "." not in filename:
+                ext = ".jpg"  # default extension
+                if "content-type" in img_response.headers:
+                    content_type = img_response.headers["content-type"]
+                    if "png" in content_type:
+                        ext = ".png"
+                    elif "gif" in content_type:
+                        ext = ".gif"
+                    elif "webp" in content_type:
+                        ext = ".webp"
                 filename = f"image_{hash(img_url)}{ext}"
 
             # Save image
@@ -242,7 +243,7 @@ def download_images(
                 file_path = output_path / f"{original_stem}_{counter}{file_path.suffix}"
                 counter += 1
 
-            with open(file_path, 'wb') as f:
+            with open(file_path, "wb") as f:
                 f.write(img_response.content)
 
             return str(file_path)
@@ -253,12 +254,15 @@ def download_images(
 
     # Download images concurrently
     with ThreadPoolExecutor(max_workers=max_workers) as executor:
-        future_to_url = {executor.submit(download_image, img_url): img_url
-                         for img_url in image_urls}
-
-        for future in tqdm(as_completed(future_to_url),
-                          total=len(image_urls),
-                          desc="Downloading images"):
+        future_to_url = {
+            executor.submit(download_image, img_url): img_url for img_url in image_urls
+        }
+
+        for future in tqdm(
+            as_completed(future_to_url),
+            total=len(image_urls),
+            desc="Downloading images",
+        ):
             result = future.result()
             if result:
                 downloaded_paths.append(result)
@@ -298,21 +302,21 @@ def get_image_urls(
         logger.error(f"Failed to fetch URL {url}: {e}")
         return []
 
-    soup = BeautifulSoup(response.text, 'html.parser')
+    soup = BeautifulSoup(response.text, "html.parser")
     image_urls: Set[str] = set()
 
     # Parse the base domain
     parsed_base = urllib.parse.urlparse(url)
 
     # Find all image tags
-    for img in soup.find_all('img', src=True):
-        img_url = img['src']
+    for img in soup.find_all("img", src=True):
+        img_url = img["src"]
 
         # Convert to absolute URL
         img_url = urllib.parse.urljoin(url, img_url)
 
         # Skip SVG files (vector graphics, not raster images)
-        if img_url.lower().endswith(('.svg', '.svgz')):
+        if img_url.lower().endswith((".svg", ".svgz")):
             continue
 
         # Filter by domain if requested
@@ -338,13 +342,23 @@ if __name__ == "__main__":
 
     parser = argparse.ArgumentParser(description="Web scraping utilities")
     parser.add_argument("url", type=str, help="URL to scrape")
-    parser.add_argument("--mode", "-m", choices=["urls", "images", "image_urls"],
-                       default="urls", help="Scraping mode")
+    parser.add_argument(
+        "--mode",
+        "-m",
+        choices=["urls", "images", "image_urls"],
+        default="urls",
+        help="Scraping mode",
+    )
     parser.add_argument("--output", "-o", type=str, help="Output directory for images")
-    parser.add_argument("--pattern", "-p", type=str, help="Regex pattern to filter URLs")
-    parser.add_argument("--same-domain", action="store_true",
-                       help="Only include URLs from same domain")
-    parser.add_argument("--min-size", type=str, help="Minimum image size as WIDTHxHEIGHT")
+    parser.add_argument(
+        "--pattern", "-p", type=str, help="Regex pattern to filter URLs"
+    )
+    parser.add_argument(
+        "--same-domain", action="store_true", help="Only include URLs from same domain"
+    )
+    parser.add_argument(
+        "--min-size", type=str, help="Minimum image size as WIDTHxHEIGHT"
+    )
 
     args = parser.parse_args()
 
@@ -355,7 +369,7 @@ if __name__ == "__main__":
     elif args.mode == "images":
         min_size = None
         if args.min_size:
-            width, height = map(int, args.min_size.split('x'))
+            width, height = map(int, args.min_size.split("x"))
             min_size = (width, height)
 
         paths = download_images(
@@ -368,6 +382,8 @@ if __name__ == "__main__":
         for path in paths:
             print(path)
     elif args.mode == "image_urls":
-        img_urls = get_image_urls(args.url, pattern=args.pattern, same_domain=args.same_domain)
+        img_urls = get_image_urls(
+            args.url, pattern=args.pattern, same_domain=args.same_domain
+        )
         for img_url in img_urls:
             print(img_url)

scitex/web/_search_pubmed.py

@@ -170,23 +170,31 @@ def _get_citation(pmid: str) -> str:
     return response.text if response.ok else ""
 
 
-def get_crossref_metrics(doi: str, api_key: Optional[str] = None, email: Optional[str] = None) -> Dict[str, Any]:
+def get_crossref_metrics(
+    doi: str, api_key: Optional[str] = None, email: Optional[str] = None
+) -> Dict[str, Any]:
     """Get article metrics from CrossRef using DOI."""
     import os
+
     base_url = "https://api.crossref.org/works/"
-    
+
     # Use provided email or fallback to environment variables
     if not email:
-        email = os.getenv("SCITEX_CROSSREF_EMAIL", os.getenv("SCITEX_PUBMED_EMAIL", "research@example.com"))
+        email = os.getenv(
+            "SCITEX_CROSSREF_EMAIL",
+            os.getenv("SCITEX_PUBMED_EMAIL", "research@example.com"),
+        )
     headers = {"User-Agent": f"SciTeX/1.0 (mailto:{email})"}
-    
+
     # Add API key as query parameter if provided
     params = {}
     if api_key:
-        params['key'] = api_key
+        params["key"] = api_key
 
     try:
-        response = requests.get(f"{base_url}{doi}", headers=headers, params=params, timeout=10)
+        response = requests.get(
+            f"{base_url}{doi}", headers=headers, params=params, timeout=10
+        )
         if response.ok:
             data = response.json()["message"]
             return {
@@ -201,24 +209,32 @@ def get_crossref_metrics(doi: str, api_key: Optional[str] = None, email: Optiona
     return {}
 
 
-async def get_crossref_metrics_async(doi: str, api_key: Optional[str] = None, email: Optional[str] = None) -> Dict[str, Any]:
+async def get_crossref_metrics_async(
+    doi: str, api_key: Optional[str] = None, email: Optional[str] = None
+) -> Dict[str, Any]:
     """Get article metrics from CrossRef using DOI (async version)."""
     import os
+
     base_url = "https://api.crossref.org/works/"
-    
+
     # Use provided email or fallback to environment variables
     if not email:
-        email = os.getenv("SCITEX_CROSSREF_EMAIL", os.getenv("SCITEX_PUBMED_EMAIL", "research@example.com"))
+        email = os.getenv(
+            "SCITEX_CROSSREF_EMAIL",
+            os.getenv("SCITEX_PUBMED_EMAIL", "research@example.com"),
+        )
     headers = {"User-Agent": f"SciTeX/1.0 (mailto:{email})"}
-    
+
     # Add API key as query parameter if provided
     params = {}
     if api_key:
-        params['key'] = api_key
+        params["key"] = api_key
 
     try:
         async with aiohttp.ClientSession() as session:
-            async with session.get(f"{base_url}{doi}", headers=headers, params=params, timeout=10) as response:
+            async with session.get(
+                f"{base_url}{doi}", headers=headers, params=params, timeout=10
+            ) as response:
                 if response.ok:
                     data = await response.json()
                     message = data["message"]
@@ -304,8 +320,8 @@ def format_bibtex(paper: Dict[str, Any], pmid: str, abstract_data: tuple) -> str
     year = {{{year}}},
     pmid = {{{pmid}}},
     doi = {{{doi}}},
-    publisher = {{{crossref_metrics.get('publisher', '')}}},
-    references = {{{crossref_metrics.get('references', 0)}}},
+    publisher = {{{crossref_metrics.get("publisher", "")}}},
+    references = {{{crossref_metrics.get("references", 0)}}},
     keywords = {{{", ".join(keywords)}}},
     abstract = {{{abstract}}}
 }}

scitex/writer/.legacy/Writer_v01-refactored.py

@@ -5,6 +5,7 @@
 # ----------------------------------------
 from __future__ import annotations
 import os
+
 __FILE__ = "./src/scitex/writer/Writer.py"
 __DIR__ = os.path.dirname(__FILE__)
 # ----------------------------------------
@@ -81,13 +82,12 @@ class Writer:
         self.git_root = initialize_git(self.project_dir, self.git_strategy)
 
         # Create document trees
-        self.manuscript, self.supplementary, self.revision, self.scripts = \
+        self.manuscript, self.supplementary, self.revision, self.scripts = (
             create_document_trees(self.project_dir, self.git_root)
-
-        logger.success(
-            f"Writer: Initialization complete for {self.project_name}"
         )
 
+        logger.success(f"Writer: Initialization complete for {self.project_name}")
+
     def compile_manuscript(self, timeout: int = 300) -> CompilationResult:
         """
         Compile manuscript to PDF.