Stabilize CLI, modularize commands, migrate packaging to uv + pyproject.toml

.github/workflows/tests.yaml

@@ -25,17 +25,13 @@ jobs:
     steps:
       - name: Checkout
         uses: actions/checkout@v3
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
         with:
           python-version: ${{ matrix.python-version }}
       - name: Install packages
-        run: |
-          python -m pip install --upgrade pip
-          pip install pytest
-          if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
-          pip install .
+        run: uv sync --extra dev
       - name: pre-commit
         uses: pre-commit/action@v3.0.0
       - name: Test with pytest
-        run: pytest
+        run: uv run pytest

README.md

@@ -26,40 +26,52 @@ Documentation: [dataherb.github.io/dataherb-python](https://dataherb.github.io/d
 
 > Requires Python 3
 
-The DataHerb cli provides tools to create dataset metadata, validate metadata, search dataset in flora, and download dataset.
+The DataHerb CLI provides tools to create dataset metadata, validate metadata, search datasets in a flora, and download datasets.
+
+### Command status
+
+| Command | Status | Description |
+|---------|--------|-------------|
+| `version` | ✅ Stable | Print the installed version |
+| `configure` | ✅ Stable | Set up or inspect the local configuration |
+| `search` | ✅ Stable | Search datasets by keyword or id |
+| `download` | ✅ Stable | Download a dataset from a flora by id |
+| `create` | ✅ Stable | Create metadata for a local dataset folder |
+| `add` | ✅ Stable | Add a remote dataset to the flora |
+| `remove` | ✅ Stable | Remove a dataset from the flora |
+| `upload` | ⚠️ Experimental | Upload the current folder to a remote (git sync is manual) |
+| `validate` | ✅ Stable | Validate the `dataherb.json` in the current folder |
+| `serve` | ✅ Stable | Launch a local MkDocs site for the flora |
 
 ### Search and Download
 
 Search by keyword
 
 ```
 dataherb search covid19
-# Shows the minimal metadata
+# Shows a rich table summary
 ```
 
 Search by dataherb id
 
 ```
-dataherb search -i covid19_eu_data
-# Shows the full metadata
+dataherb search --id covid19_eu_data
+# Shows the dataset details
 ```
 
 Download dataset by dataherb id
 
 ```
 dataherb download covid19_eu_data
-# Downloads this dataset: http://dataherb.io/flora/covid19_eu_data
+# Downloads this dataset
 ```
 
-
 ### Create Dataset Using Command Line Tool
 
-We provide a template for dataset creation.
-
 Within a dataset folder where the data files are located, use the following command line tool to create the metadata template.
 
 ```bash
-dataherb create
+dataherb create .
 ```
 
 ### Upload dataset to remote
@@ -70,8 +82,16 @@ Within the dataset folder, run
 dataherb upload
 ```
 
-### UI for all the datasets in a flora
+> **Note:** Git-based uploads (`source: git`) currently guide you to push manually.
+> Pass `--experimental` to attempt an automatic git push.
+
+### Validate dataset metadata
 
+```bash
+dataherb validate
+```
+
+### UI for all the datasets in a flora
 
 ```bash
 dataherb serve
@@ -132,8 +152,15 @@ We desigined the following workflow to share and index open datasets.
 
 ## Development
 
-1. Create a conda environment.
-2. Install requirements: `pip install -r requirements.txt`
+1. Install [uv](https://docs.astral.sh/uv/getting-started/installation/).
+2. Install the project and dev dependencies:
+   ```bash
+   uv sync --extra dev
+   ```
+3. Run tests:
+   ```bash
+   uv run pytest
+   ```
 
 ## Documentation
 

dataherb/cmd/configure.py

@@ -0,0 +1,118 @@
+"""
+CLI command for configuring dataherb.
+"""
+import json
+import sys
+from pathlib import Path
+
+import click
+import inquirer
+from loguru import logger
+
+from dataherb.utils.configs import Config
+
+logger.remove()
+logger.add(sys.stderr, level="INFO", enqueue=True)
+
+
+@click.command()
+@click.option(
+    "--show/--no-show", "-s/ ", default=False, help="Show the current configuration"
+)
+@click.option(
+    "--locate/--no-locate",
+    "-l/ ",
+    default=False,
+    help="Locate the folder that contains the configuration",
+)
+def configure(show, locate):
+    """
+    Configure dataherb; inspect, or locate the current configurations.
+
+    :param show: if flag is given, will show the current configuration instead of starting
+        the configuration process.
+    :param locate: if flag is given, will locate the configuration folder
+        and open in filesystem.
+    """
+
+    home = Path.home()
+    config_path = home / ".dataherb" / "config.json"
+
+    if locate:
+        click.launch(config_path.parent)
+    elif not show:
+        if config_path.exists():
+            is_overwite = click.confirm(
+                click.style(
+                    f"Config file ({config_path}) already exists. Overwrite?", fg="red"
+                ),
+                default=False,
+            )
+            if is_overwite:
+                click.echo(click.style("Overwriting config file...", fg="red"))
+            else:
+                click.echo("Skipping...")
+                raise SystemExit(0)
+
+        if not config_path.parent.exists():
+            config_path.parent.mkdir(parents=True)
+
+        ###############
+        # Ask questions
+        ###############
+        questions = [
+            inquirer.Path(
+                "workdir",
+                message="Where should I put all the datasets and flora database? An empty folder is recommended.",
+                # path_type=inquirer.Path.DIRECTORY,
+                normalize_to_absolute_path=True,
+            ),
+            inquirer.Text(
+                "default_flora",
+                message="How would you name the default flora? Please keep the default value if this is not clear to you.",
+                default="flora",
+            ),
+        ]
+
+        answers = inquirer.prompt(questions)
+
+        config = {
+            "workdir": answers.get("workdir"),
+            "default": {
+                "flora": answers.get("default_flora"),
+                "aggregrated": False,  # if false, we will use folders for each herb.
+            },
+        }
+
+        flora_path_workdir = answers.get("workdir", "")
+        if flora_path_workdir.startswith("~"):
+            home = Path.home()
+            flora_path_workdir = str(home / flora_path_workdir[2:])
+
+        flora_path = (
+            Path(flora_path_workdir) / "flora" / f"{answers.get('default_flora')}"
+        )
+        if not flora_path.exists():
+            click.secho(
+                f"{flora_path} doesn't exist. Creating {flora_path}...", fg="red"
+            )
+            flora_path.mkdir(parents=True)
+        else:
+            click.secho(f"{flora_path} exists, using the folder directly.", fg="green")
+
+        logger.debug(f"config: {config}")
+
+        with open(config_path, "w") as f:
+            json.dump(config, f, indent=4)
+
+        click.secho(f"The dataherb config has been saved to {config_path}!", fg="green")
+    else:
+        if not config_path.exists():
+            click.secho(f"Config file ({config_path}) doesn't exist.", fg="red")
+        else:
+            c = Config()
+            click.secho(f"The current config for dataherb is:")
+            click.secho(
+                json.dumps(c.config, indent=2, sort_keys=True, ensure_ascii=False)
+            )
+            click.secho(f"The above config is extracted from {config_path}")