figpack 0.2.36__tar.gz → 0.2.38__tar.gz

{figpack-0.2.36/figpack.egg-info → figpack-0.2.38}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: figpack
-Version: 0.2.36
+Version: 0.2.38
 Summary: A Python package for creating shareable, interactive visualizations in the browser
 Author-email: Jeremy Magland <jmagland@flatironinstitute.org>
 License: Apache-2.0
@@ -133,7 +133,7 @@ If you use figpack in your research, please cite it:
 
 Or in APA format:
 
-> Magland, J. (2025). figpack (Version 0.2.36) [Computer software]. Zenodo. https://doi.org/10.5281/zenodo.17419621
+> Magland, J. (2025). figpack (Version 0.2.38) [Computer software]. Zenodo. https://doi.org/10.5281/zenodo.17419621
 
 ## Contributing
 

{figpack-0.2.36 → figpack-0.2.38}/README.md

@@ -57,7 +57,7 @@ If you use figpack in your research, please cite it:
 
 Or in APA format:
 
-> Magland, J. (2025). figpack (Version 0.2.36) [Computer software]. Zenodo. https://doi.org/10.5281/zenodo.17419621
+> Magland, J. (2025). figpack (Version 0.2.38) [Computer software]. Zenodo. https://doi.org/10.5281/zenodo.17419621
 
 ## Contributing
 

{figpack-0.2.36 → figpack-0.2.38}/figpack/__init__.py

@@ -2,7 +2,7 @@
 figpack - A Python package for creating shareable, interactive visualizations in the browser
 """
 
-__version__ = "0.2.36"
+__version__ = "0.2.38"
 
 from .cli import view_figure
 from .core import FigpackView, FigpackExtension, ExtensionView

{figpack-0.2.36 → figpack-0.2.38}/figpack/cli.py

@@ -18,6 +18,7 @@ import requests
 from . import __version__
 from .core._server_manager import CORSRequestHandler
 from .core._view_figure import serve_files, view_figure
+from .core._upload_bundle import _upload_bundle, get_figure_by_source_url
 from .extensions import ExtensionManager
 
 MAX_WORKERS_FOR_DOWNLOAD = 16
@@ -249,6 +250,130 @@ def handle_extensions_command(args):
         print("Use 'figpack extensions <command> --help' for more information.")
 
 
+def handle_upload_from_source_url(args) -> None:
+    """
+    Handle the upload-from-source-url command
+
+    Downloads a tar.gz/tgz file from a URL, extracts it, and uploads it as a new figure
+    with the source URL set.
+    """
+    import os
+
+    source_url = args.source_url
+    title = args.title if hasattr(args, "title") else None
+
+    # Get API key from environment variable
+    api_key = os.environ.get("FIGPACK_API_KEY")
+    if not api_key:
+        print(
+            "Error: FIGPACK_API_KEY environment variable must be set to upload figures."
+        )
+        sys.exit(1)
+
+    # Validate URL format
+    if not (source_url.endswith(".tar.gz") or source_url.endswith(".tgz")):
+        print(f"Error: Source URL must point to a .tar.gz or .tgz file: {source_url}")
+        sys.exit(1)
+
+    print(f"Downloading archive from: {source_url}")
+
+    try:
+        # Download the archive
+        response = requests.get(source_url, timeout=120, stream=True)
+        response.raise_for_status()
+
+        # Create temporary file for the archive
+        with tempfile.NamedTemporaryFile(
+            suffix=".tar.gz", delete=False
+        ) as temp_archive:
+            archive_path = temp_archive.name
+
+            # Download with progress indication
+            total_size = int(response.headers.get("content-length", 0))
+            downloaded_size = 0
+
+            for chunk in response.iter_content(chunk_size=8192):
+                if chunk:
+                    temp_archive.write(chunk)
+                    downloaded_size += len(chunk)
+                    if total_size > 0:
+                        progress = (downloaded_size / total_size) * 100
+                        print(
+                            f"Downloaded: {downloaded_size / (1024*1024):.2f} MB ({progress:.1f}%)",
+                            end="\r",
+                        )
+
+            if total_size > 0:
+                print()  # New line after progress
+            print(f"Download complete: {downloaded_size / (1024*1024):.2f} MB")
+
+        # Extract archive to temporary directory
+        print("Extracting archive...")
+        with tempfile.TemporaryDirectory() as extract_dir:
+            extract_path = pathlib.Path(extract_dir)
+
+            try:
+                with tarfile.open(archive_path, "r:gz") as tar:
+                    tar.extractall(path=extract_path)
+                print(f"Extracted to temporary directory")
+            except Exception as e:
+                print(f"Error: Failed to extract archive: {e}")
+                sys.exit(1)
+            finally:
+                # Clean up downloaded archive
+                import os
+
+                try:
+                    os.unlink(archive_path)
+                except Exception:
+                    pass
+
+            # Upload the extracted files
+            print(f"Uploading figure with source URL: {source_url}")
+            try:
+                figure_url = _upload_bundle(
+                    str(extract_path),
+                    api_key=api_key,
+                    title=title,
+                    source_url=source_url,
+                )
+                print(f"\nFigure uploaded successfully!")
+                print(f"Figure URL: {figure_url}")
+            except Exception as e:
+                print(f"Error: Failed to upload figure: {e}")
+                sys.exit(1)
+
+    except requests.exceptions.RequestException as e:
+        print(f"Error: Failed to download archive from {source_url}: {e}")
+        sys.exit(1)
+    except Exception as e:
+        print(f"Error: {e}")
+        sys.exit(1)
+
+
+def handle_find_by_source_url(args) -> None:
+    """
+    Handle the find-by-source-url command
+
+    Queries the API for a figure URL by its source URL.
+    """
+    source_url = args.source_url
+
+    print(f"Querying for figure with source URL: {source_url}")
+
+    try:
+        figure_url = get_figure_by_source_url(source_url)
+
+        if figure_url:
+            print(f"Figure found: {figure_url}")
+        else:
+            print(f"No figure found with source URL: {source_url}")
+            sys.exit(1)
+    except Exception as e:
+        print(f"Error: {e}")
+        sys.exit(1)
+
+
 def download_and_view_archive(url: str, port: int = None) -> None:
     """
     Download a tar.gz/tgz archive from a URL and view it
@@ -370,6 +495,27 @@ def main():
         "extensions", nargs="+", help="Extension package names to uninstall"
     )
 
+    # Upload from URL command
+    upload_from_source_url_parser = subparsers.add_parser(
+        "upload-from-source-url",
+        help="Download a tar.gz/tgz file and upload it as a new figure",
+    )
+    upload_from_source_url_parser.add_argument(
+        "source_url",
+        help="URL to the tar.gz or tgz file (will be set as the figure's source URL)",
+    )
+    upload_from_source_url_parser.add_argument(
+        "--title", help="Optional title for the figure"
+    )
+
+    # Find by source URL command
+    find_by_source_url_parser = subparsers.add_parser(
+        "find-by-source-url", help="Get the figure URL for a given source URL"
+    )
+    find_by_source_url_parser.add_argument(
+        "source_url", help="The source URL to search for"
+    )
+
     args = parser.parse_args()
 
     if args.command == "download":
@@ -382,6 +528,10 @@ def main():
             view_figure(args.archive, port=args.port)
     elif args.command == "extensions":
         handle_extensions_command(args)
+    elif args.command == "upload-from-source-url":
+        handle_upload_from_source_url(args)
+    elif args.command == "find-by-source-url":
+        handle_find_by_source_url(args)
     else:
         parser.print_help()
 

{figpack-0.2.36 → figpack-0.2.38}/figpack/core/_upload_bundle.py

@@ -122,56 +122,24 @@ def _upload_single_file_with_signed_url(
 MAX_WORKERS_FOR_UPLOAD = 16
 
 
-def _compute_deterministic_figure_hash(tmpdir_path: pathlib.Path) -> str:
-    """
-    Compute a deterministic figure ID based on SHA1 hashes of all files
-
-    Returns:
-        str: 40-character SHA1 hash representing the content of all files
-    """
-    file_hashes = []
-
-    # Collect all files and their hashes
-    for file_path in sorted(tmpdir_path.rglob("*")):
-        if file_path.is_file():
-            relative_path = file_path.relative_to(tmpdir_path)
-
-            # Compute SHA1 hash of file content
-            sha1_hash = hashlib.sha1()
-            with open(file_path, "rb") as f:
-                for chunk in iter(lambda: f.read(4096), b""):
-                    sha1_hash.update(chunk)
-
-            # Include both the relative path and content hash to ensure uniqueness
-            file_info = f"{relative_path}:{sha1_hash.hexdigest()}"
-            file_hashes.append(file_info)
-
-    # Create final hash from all file hashes
-    combined_hash = hashlib.sha1()
-    for file_hash in file_hashes:
-        combined_hash.update(file_hash.encode("utf-8"))
-
-    return combined_hash.hexdigest()
-
-
 def _create_or_get_figure(
-    figure_hash: str,
     api_key: Optional[str],
     total_files: Optional[int] = None,
     total_size: Optional[int] = None,
     title: Optional[str] = None,
     ephemeral: bool = False,
+    source_url: Optional[str] = None,
 ) -> dict:
     """
     Create a new figure or get existing figure information
 
     Args:
-        figure_hash: The hash of the figure
         api_key: The API key for authentication (required for non-ephemeral)
         total_files: Optional total number of files
         total_size: Optional total size of files
         title: Optional title for the figure
         ephemeral: Whether to create an ephemeral figure
+        source_url: Optional source URL for the figure (must be unique)
 
     Returns:
         dict: Figure information from the API
@@ -181,7 +149,6 @@ def _create_or_get_figure(
         raise ValueError("API key is required for non-ephemeral figures")
 
     payload: dict[str, Union[str, int]] = {
-        "figureHash": figure_hash,
         "figpackVersion": __version__,
         "bucket": FIGPACK_BUCKET,
     }
@@ -198,6 +165,8 @@ def _create_or_get_figure(
         payload["title"] = title
     if ephemeral:
         payload["ephemeral"] = True
+    if source_url is not None:
+        payload["sourceUrl"] = source_url
 
     # Use the same endpoint for both regular and ephemeral figures
     response = requests.post(f"{FIGPACK_API_BASE_URL}/api/figures/create", json=payload)
@@ -208,12 +177,12 @@ def _create_or_get_figure(
             error_msg = error_data.get("message", "Unknown error")
         except:
             error_msg = f"HTTP {response.status_code}"
-        raise Exception(f"Failed to create figure {figure_hash}: {error_msg}")
+        raise Exception(f"Failed to create figure: {error_msg}")
 
     response_data = response.json()
     if not response_data.get("success"):
         raise Exception(
-            f"Failed to create figure {figure_hash}: {response_data.get('message', 'Unknown error')}"
+            f"Failed to create figure: {response_data.get('message', 'Unknown error')}"
         )
 
     return response_data
@@ -258,6 +227,7 @@ def _upload_bundle(
     title: Optional[str] = None,
     ephemeral: bool = False,
     use_consolidated_metadata_only: bool = False,
+    source_url: Optional[str] = None,
 ) -> str:
     """
     Upload the prepared bundle to the cloud using the new database-driven approach
@@ -269,12 +239,10 @@ def _upload_bundle(
         ephemeral: Whether to create an ephemeral figure
         use_consolidated_metadata_only: If True, excludes individual zarr metadata files
             (.zgroup, .zarray, .zattrs) since they are included in .zmetadata
+        source_url: Optional source URL for the figure (must be unique)
     """
     tmpdir_path = pathlib.Path(tmpdir)
 
-    # Compute deterministic figure ID based on file contents
-    figure_hash = _compute_deterministic_figure_hash(tmpdir_path)
-
     # Collect all files to upload
     all_files = []
     for file_path in tmpdir_path.rglob("*"):
@@ -295,7 +263,12 @@ def _upload_bundle(
 
     # Find available figure ID and create/get figure in database with metadata
     result = _create_or_get_figure(
-        figure_hash, api_key, total_files, total_size, title=title, ephemeral=ephemeral
+        api_key,
+        total_files,
+        total_size,
+        title=title,
+        ephemeral=ephemeral,
+        source_url=source_url,
     )
     figure_info = result.get("figure", {})
     figure_url = figure_info.get("figureUrl")
@@ -430,6 +403,39 @@ def _upload_bundle(
     return figure_url
 
 
+def get_figure_by_source_url(source_url: str) -> Optional[str]:
+    """
+    Query the API for a figure URL by its source URL
+
+    Args:
+        source_url: The source URL to search for
+
+    Returns:
+        Optional[str]: The figure URL if found, None otherwise
+    """
+    payload = {"sourceUrl": source_url}
+
+    response = requests.post(
+        f"{FIGPACK_API_BASE_URL}/api/figures/find-by-source-url", json=payload
+    )
+
+    if not response.ok:
+        if response.status_code == 404:
+            return None
+        try:
+            error_data = response.json()
+            error_msg = error_data.get("message", "Unknown error")
+        except:
+            error_msg = f"HTTP {response.status_code}"
+        raise Exception(f"Failed to query figure by source URL: {error_msg}")
+
+    response_data = response.json()
+    if not response_data.get("success"):
+        return None
+
+    return response_data.get("figureUrl")
+
+
 def _determine_content_type(file_path: str) -> str:
     """
     Determine content type for upload based on file extension