containerio 2.1.0__tar.gz → 2.2.0__tar.gz

{containerio-2.1.0 → containerio-2.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: containerio
-Version: 2.1.0
+Version: 2.2.0
 Summary: Azure Blob Storage handler with unified local/cloud interface
 Author: Alliance SwissPass
 Requires-Dist: polars>=1.30.0
@@ -406,6 +406,7 @@ StorageHandler(
 | `read_parquet_blob(blob_name)` | Read parquet file, returns `(DataFrame, metadata)` |
 | `read_csv_blob(blob_name, **kwargs)` | Read CSV file into DataFrame |
 | `read_excel_blob(blob_name, **kwargs)` | Read Excel file into DataFrame |
+| `read_json_blob(blob_name, **kwargs)` | Read JSON file into DataFrame |
 | `scan_parquet_blob(blob_name)` | Lazy scan parquet, returns `(LazyFrame, metadata)` |
 | `scan_csv_blob(blob_name, **kwargs)` | Lazy scan CSV file |
 
@@ -416,6 +417,7 @@ StorageHandler(
 | `write_parquet_blob(blob_name, df)` | Write DataFrame to parquet |
 | `write_csv_blob(blob_name, df, **kwargs)` | Write DataFrame to CSV |
 | `write_excel_blob(blob_name, df, **kwargs)` | Write DataFrame to Excel |
+| `write_json_blob(blob_name, df, **kwargs)` | Write DataFrame to JSON |
 | `sink_parquet_blob(blob_name, lf)` | Stream LazyFrame to parquet |
 
 #### Utility Methods
@@ -620,8 +622,12 @@ The CI pipeline will automatically:
 
 The repository includes a Crow CI pipeline that automatically builds, tests, and publishes the package when a git tag is pushed:
 
-2. Commit and push your changes
-3. Create and push a git tag (e.g., `git tag v1.0.0 && git push --tags`)
+1. Merge all branches you want to have part of a new release into main
+1. Check tag for upcoming semantic release version with `git sv rn`
+1. If not already added, add your private key (whose public key is associated with your Codefloe Git user) to the SSH agent.
+   `ssh-add ~/.ssh/<your-private-key>`
+1. Generate tag with version based on git commit messages with `git sv tag`
+1. Create and push a git tag (e.g., `git push --tags`)
 
 The pipeline will:
 - Run linting and tests

{containerio-2.1.0 → containerio-2.2.0}/README.md

@@ -392,6 +392,7 @@ StorageHandler(
 | `read_parquet_blob(blob_name)` | Read parquet file, returns `(DataFrame, metadata)` |
 | `read_csv_blob(blob_name, **kwargs)` | Read CSV file into DataFrame |
 | `read_excel_blob(blob_name, **kwargs)` | Read Excel file into DataFrame |
+| `read_json_blob(blob_name, **kwargs)` | Read JSON file into DataFrame |
 | `scan_parquet_blob(blob_name)` | Lazy scan parquet, returns `(LazyFrame, metadata)` |
 | `scan_csv_blob(blob_name, **kwargs)` | Lazy scan CSV file |
 
@@ -402,6 +403,7 @@ StorageHandler(
 | `write_parquet_blob(blob_name, df)` | Write DataFrame to parquet |
 | `write_csv_blob(blob_name, df, **kwargs)` | Write DataFrame to CSV |
 | `write_excel_blob(blob_name, df, **kwargs)` | Write DataFrame to Excel |
+| `write_json_blob(blob_name, df, **kwargs)` | Write DataFrame to JSON |
 | `sink_parquet_blob(blob_name, lf)` | Stream LazyFrame to parquet |
 
 #### Utility Methods
@@ -606,8 +608,12 @@ The CI pipeline will automatically:
 
 The repository includes a Crow CI pipeline that automatically builds, tests, and publishes the package when a git tag is pushed:
 
-2. Commit and push your changes
-3. Create and push a git tag (e.g., `git tag v1.0.0 && git push --tags`)
+1. Merge all branches you want to have part of a new release into main
+1. Check tag for upcoming semantic release version with `git sv rn`
+1. If not already added, add your private key (whose public key is associated with your Codefloe Git user) to the SSH agent.
+   `ssh-add ~/.ssh/<your-private-key>`
+1. Generate tag with version based on git commit messages with `git sv tag`
+1. Create and push a git tag (e.g., `git push --tags`)
 
 The pipeline will:
 - Run linting and tests

{containerio-2.1.0 → containerio-2.2.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "containerio"
-version = "2.1.0"
+version = "2.2.0"
 description = "Azure Blob Storage handler with unified local/cloud interface"
 readme = "README.md"
 requires-python = ">=3.11"

{containerio-2.1.0 → containerio-2.2.0}/src/containerio/handler.py

@@ -537,11 +537,32 @@ class StorageHandler:
         for path in deleted:
             self.logger.debug(f"Deleted device code cache: {path}")
 
+    @staticmethod
+    def _is_hns_directory(metadata: Optional[dict]) -> bool:
+        """Return `True` if blob metadata marks an ADLS Gen2 directory.
+
+        Hierarchical-namespace (ADLS Gen2) accounts return directory
+        placeholders from `list_blobs` as zero-byte entries tagged with
+        `hdi_isfolder`. Flat-namespace accounts never set it.
+
+        Args:
+            metadata (Optional[dict]): The blob's metadata mapping, or
+                `None` when metadata was not requested.
+
+        Returns:
+            bool: `True` for a directory placeholder, `False` otherwise.
+        """
+        return bool((metadata or {}).get("hdi_isfolder"))
+
     def list_blobs(self) -> List:
         """Lists all blobs in the container with metadata.
 
         Collects file metadata (name, size, last modified timestamp)
-        from either local filesystem or Azure Blob Storage.
+        from either local filesystem or Azure Blob Storage. On
+        hierarchical-namespace (ADLS Gen2) accounts, directory
+        placeholder entries (marked `hdi_isfolder`) are skipped so the
+        result contains only files, matching the flat-namespace and
+        local behaviour.
 
         Returns:
             List: List of blob metadata objects.
@@ -562,7 +583,9 @@ class StorageHandler:
                             )
                         )
         else:
-            for blob in self.container_client.list_blobs():
+            for blob in self.container_client.list_blobs(include=["metadata"]):
+                if self._is_hns_directory(blob.metadata):
+                    continue
                 blobs.append(
                     BlobInfo(
                         name=blob.name,
@@ -632,6 +655,25 @@ class StorageHandler:
         console = Console()
         console.print(tree)
 
+    def read_json_blob(self, blob_name: str, **kwargs: Dict) -> pl.DataFrame:
+        """Reads a JSON file from storage into a Polars DataFrame.
+
+        Args:
+            blob_name (str): The path/name of the file to read.
+            **kwargs: Additional keyword arguments passed to
+                `polars.read_json`.
+
+        Returns:
+            pl.DataFrame: The content of the JSON file as a Polars
+            DataFrame.
+        """
+        if self.local:
+            file_path = self.base_path / blob_name
+            return pl.read_json(source=file_path, **kwargs)
+        else:
+            data = self._read_blob_as_bytes(blob_name)
+            return pl.read_json(source=BytesIO(data), **kwargs)
+
     def read_csv_blob(self, blob_name: str, **kwargs: Dict) -> pl.DataFrame:
         """Reads a CSV file from storage into a Polars DataFrame.
 
@@ -815,6 +857,30 @@ class StorageHandler:
         except Exception as e:
             raise RuntimeError(f"Failed to write blob '{blob_name}': {e}") from e
 
+    def write_json_blob(self, blob_name: str, df: pl.DataFrame, **kwargs: Dict) -> None:
+        """Writes a Polars DataFrame to a JSON file in storage.
+
+        Args:
+            blob_name (str): The path/name of the file to write to.
+            df (pl.DataFrame): The DataFrame to write.
+            **kwargs: Additional keyword arguments passed to
+                `DataFrame.write_json`.
+
+        Returns:
+            None
+        """
+        if self.local:
+            file_path = self.base_path / blob_name
+            file_path.parent.mkdir(parents=True, exist_ok=True)
+            df.write_json(file=file_path, **kwargs)
+        else:
+            # Write the DataFrame to an in-memory stream
+            buffer = BytesIO()
+            df.write_json(file=buffer, **kwargs)
+            buffer.seek(0)
+            # Upload the bytes to Azure Blob Storage
+            self._write_blob_as_bytes(blob_name, buffer.getvalue())
+
     def write_csv_blob(self, blob_name: str, df: pl.DataFrame, **kwargs: Dict) -> None:
         """Writes a Polars DataFrame to a CSV file in storage.