CI-119: Add cli option to download only certain files

README.md

@@ -37,6 +37,7 @@ Usage: cirro download [OPTIONS]
 Options:
   --project TEXT         Name or ID of the project
   --dataset TEXT         ID of the dataset
+  --file... TEXT         Name and relative path of the file (optional)
   --data-directory TEXT  Directory to store the files
   -i, --interactive      Gather arguments interactively
   --help                 Show this message and exit.
@@ -91,7 +92,7 @@ $ cirro upload --interactive
 See the following set of Jupyter notebooks that contain examples on the following topics:
 
 | Jupyter Notebook                                                   | Topic                                |
-|--------------------------------------------------------------------|--------------------------------------|
+| ------------------------------------------------------------------ | ------------------------------------ |
 | [Introduction](samples/Getting_started.ipynb)                      | Installing and authenticating        |
 | [Uploading a dataset](samples/Uploading_a_dataset.ipynb)           | Uploading data                       |
 | [Downloading a dataset](samples/Downloading_a_dataset.ipynb)       | Downloading data                     |
@@ -103,7 +104,7 @@ See the following set of Jupyter notebooks that contain examples on the followin
 ## R Usage
 
 | Jupyter Notebook                                    | Topic               |
-|-----------------------------------------------------|---------------------|
+| --------------------------------------------------- | ------------------- |
 | [Downloading a dataset in R](samples/Using-R.ipynb) | Reading data with R |
 
 ## Advanced Usage
@@ -113,7 +114,7 @@ View the API documentation for this library [here](https://cirrobio.github.io/Ci
 ### Supported environment variables
 
 | Name           | Description                   | Default  |
-|----------------|-------------------------------|----------|
+| -------------- | ----------------------------- | -------- |
 | CIRRO_HOME     | Local configuration directory | ~/.cirro |
 | CIRRO_BASE_URL | Base URL of the data portal   |          |
 

cirro/cli/cli.py

@@ -36,6 +36,10 @@ def list_datasets(**kwargs):
               help='Name or ID of the project')
 @click.option('--dataset',
               help='ID of the dataset')
+@click.option('--file',
+              help='Name and relative path of the file (optional)',
+              default=[],
+              multiple=True)
 @click.option('--data-directory',
               help='Directory to store the files')
 @click.option('-i', '--interactive',

cirro/cli/controller.py

@@ -1,4 +1,5 @@
 import logging
+import os
 import sys
 
 import pandas as pd
@@ -142,6 +143,19 @@ def run_download(input_params: DownloadArguments, interactive=False):
         datasets = cirro.datasets.list(project_id)
         dataset_id = get_id_from_name(datasets, input_params['dataset'])
 
+        if input_params['file']:
+            all_files = cirro.datasets.get_file_listing(project_id, dataset_id)
+            files_to_download = []
+
+            for filepath in input_params['file']:
+                if not filepath.startswith('data/'):
+                    filepath = os.path.join('data/', filepath)
+                file = next((f for f in all_files if f.relative_path == filepath), None)
+                if not file:
+                    logger.warning(f"Could not find file {filepath}. Skipping.")
+                    continue
+                files_to_download.append(file)
+
     logger.info("Downloading files")
     if cirro.configuration.enable_additional_checksum:
         checksum_method = "SHA256"

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "cirro"
-version = "1.2.8"
+version = "1.2.9"
 description = "CLI tool and SDK for interacting with the Cirro platform"
 authors = ["Cirro Bio <[email protected]>"]
 license = "MIT"