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

scitex/vis/utils/{validate.py → _validate.py}

@@ -44,9 +44,7 @@ def validate_json_structure(fig_json: Dict[str, Any]) -> bool:
         raise ValueError(f"width_mm must be positive, got {fig_json['width_mm']}")
 
     if fig_json["height_mm"] <= 0:
-        raise ValueError(
-            f"height_mm must be positive, got {fig_json['height_mm']}"
-        )
+        raise ValueError(f"height_mm must be positive, got {fig_json['height_mm']}")
 
     # Optional fields validation
     if "nrows" in fig_json:
@@ -103,9 +101,7 @@ def validate_plot_data(plot_data: Dict[str, Any]) -> bool:
         y_len = len(data["y"]) if hasattr(data["y"], "__len__") else 1
 
         if x_len != y_len:
-            raise ValueError(
-                f"x and y data must have same length: {x_len} != {y_len}"
-            )
+            raise ValueError(f"x and y data must have same length: {x_len} != {y_len}")
 
     elif plot_type in ["bar", "barh"]:
         if "x" not in data:
@@ -170,9 +166,7 @@ def validate_color(color: str) -> bool:
     return True
 
 
-def validate_axes_layout(
-    nrows: int, ncols: int, num_axes: int
-) -> bool:
+def validate_axes_layout(nrows: int, ncols: int, num_axes: int) -> bool:
     """
     Validate axes layout is consistent.
 

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.

scitex/writer/.legacy/_compile.py

@@ -5,9 +5,8 @@
 # ----------------------------------------
 from __future__ import annotations
 import os
-__FILE__ = (
-    "./src/scitex/writer/_compile.py"
-)
+
+__FILE__ = "./src/scitex/writer/_compile.py"
 __DIR__ = os.path.dirname(__FILE__)
 # ----------------------------------------
 
@@ -58,14 +57,8 @@ def _run_compile(
 
     # Get compile script from scripts/shell/ directory
     script_map = {
-        "manuscript": project_dir
-        / "scripts"
-        / "shell"
-        / "compile_manuscript.sh",
-        "supplementary": project_dir
-        / "scripts"
-        / "shell"
-        / "compile_supplementary.sh",
+        "manuscript": project_dir / "scripts" / "shell" / "compile_manuscript.sh",
+        "supplementary": project_dir / "scripts" / "shell" / "compile_supplementary.sh",
         "revision": project_dir / "scripts" / "shell" / "compile_revision.sh",
     }
 
@@ -92,6 +85,7 @@ def _run_compile(
 
     try:
         import os
+
         cwd_original = Path.cwd()
         os.chdir(project_dir)
 
@@ -103,11 +97,15 @@ def _run_compile(
                 timeout=timeout * 1000,
             )
 
-            result = type('Result', (), {
-                'returncode': result_dict['exit_code'],
-                'stdout': result_dict['stdout'],
-                'stderr': result_dict['stderr']
-            })()
+            result = type(
+                "Result",
+                (),
+                {
+                    "returncode": result_dict["exit_code"],
+                    "stdout": result_dict["stdout"],
+                    "stderr": result_dict["stderr"],
+                },
+            )()
 
             duration = (datetime.now() - start_time).total_seconds()
         finally:
@@ -167,9 +165,7 @@ def _run_compile(
             if output_pdf:
                 logger.info(f"Output PDF: {output_pdf}")
         else:
-            logger.error(
-                f"Compilation failed with exit code {result.returncode}"
-            )
+            logger.error(f"Compilation failed with exit code {result.returncode}")
             if errors:
                 logger.error(f"Found {len(errors)} errors")
 
@@ -187,9 +183,7 @@ def _run_compile(
         )
 
 
-def compile_manuscript(
-    project_dir: Path, timeout: int = 300
-) -> CompilationResult:
+def compile_manuscript(project_dir: Path, timeout: int = 300) -> CompilationResult:
     """
     Compile manuscript document.
 
@@ -211,9 +205,7 @@ def compile_manuscript(
     return _run_compile("manuscript", project_dir, timeout=timeout)
 
 
-def compile_supplementary(
-    project_dir: Path, timeout: int = 300
-) -> CompilationResult:
+def compile_supplementary(project_dir: Path, timeout: int = 300) -> CompilationResult:
     """
     Compile supplementary materials.
 
@@ -285,9 +277,7 @@ def main(args):
         result = compile_supplementary(project_dir, timeout=args.timeout)
     elif args.document == "revision":
         result = compile_revision(
-            project_dir,
-            track_changes=args.track_changes,
-            timeout=args.timeout
+            project_dir, track_changes=args.track_changes, timeout=args.timeout
         )
 
     if result.success:

scitex/writer/Writer.py

@@ -5,9 +5,8 @@
 # ----------------------------------------
 from __future__ import annotations
 import os
-__FILE__ = (
-    "./src/scitex/writer/_Writer.py"
-)
+
+__FILE__ = "./src/scitex/writer/_Writer.py"
 __DIR__ = os.path.dirname(__FILE__)
 # ----------------------------------------
 
@@ -96,9 +95,7 @@ class Writer:
         self.git_root = init_git_repo(self.project_dir, self.git_strategy)
 
         # Document accessors (pass git_root for efficiency)
-        self.shared = SharedTree(
-            self.project_dir / "00_shared", git_root=self.git_root
-        )
+        self.shared = SharedTree(self.project_dir / "00_shared", git_root=self.git_root)
         self.manuscript = ManuscriptTree(
             self.project_dir / "01_manuscript", git_root=self.git_root
         )
@@ -108,13 +105,9 @@ class Writer:
         self.revision = RevisionTree(
             self.project_dir / "03_revision", git_root=self.git_root
         )
-        self.scripts = ScriptsTree(
-            self.project_dir / "scripts", git_root=self.git_root
-        )
+        self.scripts = ScriptsTree(self.project_dir / "scripts", git_root=self.git_root)
 
-        logger.success(
-            f"Writer: Initialization complete for {self.project_name}"
-        )
+        logger.success(f"Writer: Initialization complete for {self.project_name}")
 
     def _attach_or_create_project(self, name: Optional[str] = None) -> Path:
         """
@@ -159,21 +152,15 @@ class Writer:
 
         # Verify target directory exists
         if not target_dir.exists():
-            logger.error(
-                f"Writer: Target directory {target_dir} does not exist"
-            )
-            raise RuntimeError(
-                f"Target directory {target_dir} was not created"
-            )
+            logger.error(f"Writer: Target directory {target_dir} does not exist")
+            raise RuntimeError(f"Target directory {target_dir} was not created")
 
         # Verify project directory was created
         if not self.project_dir.exists():
             logger.error(
                 f"Writer: Project directory {self.project_dir} was not created"
             )
-            raise RuntimeError(
-                f"Project directory {self.project_dir} was not created"
-            )
+            raise RuntimeError(f"Project directory {self.project_dir} was not created")
 
         logger.success(
             f"Writer: Successfully created project at {self.project_dir.absolute()}"

scitex/writer/__init__.py

@@ -52,17 +52,17 @@ from ._compile_async import (
 __version__ = "0.1.0"
 
 __all__ = [
-    'Writer',
-    'CompilationResult',
-    'WriterConfig',
-    'LaTeXIssue',
-    'compile_manuscript',
-    'compile_supplementary',
-    'compile_revision',
-    'compile_manuscript_async',
-    'compile_supplementary_async',
-    'compile_revision_async',
-    'compile_all_async',
+    "Writer",
+    "CompilationResult",
+    "WriterConfig",
+    "LaTeXIssue",
+    "compile_manuscript",
+    "compile_supplementary",
+    "compile_revision",
+    "compile_manuscript_async",
+    "compile_supplementary_async",
+    "compile_revision_async",
+    "compile_all_async",
 ]
 
 # EOF

scitex/writer/_clone_writer_project.py

@@ -56,9 +56,7 @@ def clone_writer_project(
     from scitex.template import clone_writer_directory
 
     try:
-        result = clone_writer_directory(
-            project_dir, git_strategy, branch, tag
-        )
+        result = clone_writer_directory(project_dir, git_strategy, branch, tag)
         return result
     except Exception as e:
         logger.error(f"Failed to initialize writer directory: {e}")
@@ -114,9 +112,7 @@ def main(args):
 def parse_args():
     import argparse
 
-    parser = argparse.ArgumentParser(
-        description="Clone scitex writer project template"
-    )
+    parser = argparse.ArgumentParser(description="Clone scitex writer project template")
     parser.add_argument(
         "project_dir",
         type=str,

scitex/writer/_compile/__init__.py

@@ -5,6 +5,7 @@
 # ----------------------------------------
 from __future__ import annotations
 import os
+
 __FILE__ = "./src/scitex/writer/_compile/__init__.py"
 __DIR__ = os.path.dirname(__FILE__)
 # ----------------------------------------

scitex/writer/_compile/_parser.py

@@ -5,6 +5,7 @@
 # ----------------------------------------
 from __future__ import annotations
 import os
+
 __FILE__ = "./src/scitex/writer/_compile/_parser.py"
 __DIR__ = os.path.dirname(__FILE__)
 # ----------------------------------------