[Ready for review] Icechunk CLI Initial Implementation

.gitignore

@@ -12,3 +12,4 @@
 /devel
 
 .ipynb_checkpoints
+.vscode

docs/docs/icechunk-python/parallel.md

@@ -76,7 +76,7 @@ xr.testing.assert_identical(ds, ondisk)
 
 Any task execution framework (e.g. `ProcessPoolExecutor`, Joblib, Lithops, Dask Distributed, Ray, etc.)
 can be used instead of the `ThreadPoolExecutor`. However such workloads should account for
-Icehunk being a "stateful" store that records changes executed in a write session.
+Icechunk being a "stateful" store that records changes executed in a write session.
 
 There are three key points to keep in mind:
 1. The `write_task` function *must* return the `Session`. It contains a record of the changes executed by this task.

icechunk-python/Cargo.toml

@@ -38,6 +38,8 @@ async-trait = "0.1.85"
 typetag = "0.2.19"
 serde = { version = "1.0.217", features = ["derive", "rc"] }
 miette = { version = "7.5.0", features = ["fancy"] }
+clap = { version = "4.5", features = ["derive"] }
+anyhow = "1.0.95"
 
 [lints]
 workspace = true

icechunk-python/pyproject.toml

@@ -128,3 +128,7 @@ known-first-party = ["dask", "distributed", "icechunk", "xarray", "zarr"]
 [tool.ruff.lint.flake8-tidy-imports]
 # Disallow all relative imports.
 ban-relative-imports = "all"
+
+
+[project.scripts]
+icechunk = "icechunk._icechunk_python:cli_entrypoint"

icechunk-python/src/lib.rs

@@ -8,6 +8,8 @@ mod streams;
 
 use std::env;
 
+use clap::error::ErrorKind;
+use clap::Parser;
 use config::{
     PyAzureCredentials, PyAzureStaticCredentials, PyCachingConfig,
     PyCompressionAlgorithm, PyCompressionConfig, PyCredentials, PyGcsBearerCredential,
@@ -31,6 +33,37 @@ use repository::{PyDiff, PyGCSummary, PyRepository, PySnapshotInfo};
 use session::PySession;
 use store::PyStore;
 
+use icechunk::cli::interface::{run_cli, IcechunkCLI};
+use pyo3::wrap_pyfunction;
+
+#[pyfunction]
+fn cli_entrypoint(py: Python) -> PyResult<()> {
+    let sys = py.import("sys")?;
+    let args: Vec<String> = sys.getattr("argv")?.extract()?;
+    match IcechunkCLI::try_parse_from(args.to_vec()) {
+        Ok(cli_args) => pyo3_async_runtimes::tokio::get_runtime().block_on(async move {
+            run_cli(cli_args).await.map_err(|e| {
+                PyErr::new::<pyo3::exceptions::PyRuntimeError, _>(e.to_string())
+            })?;
+            Ok(())
+        }),
+        // TODO (Daniel): Improve error handling & printout
+        Err(e) => match e.kind() {
+            ErrorKind::DisplayHelpOnMissingArgumentOrSubcommand
+            | ErrorKind::MissingRequiredArgument => {
+                print!("{}", e);
+                return Ok(());
+            }
+            _ => {
+                println!("{:?}", e.kind());
+                return Err(PyErr::new::<pyo3::exceptions::PyValueError, _>(
+                    e.to_string(),
+                ));
+            }
+        },
+    }
+}
+
 #[pyfunction]
 fn initialize_logs() -> PyResult<()> {
     if env::var("ICECHUNK_NO_LOGS").is_err() {
@@ -84,6 +117,7 @@ fn _icechunk_python(py: Python<'_>, m: &Bound<'_, PyModule>) -> PyResult<()> {
     m.add_class::<PyDiff>()?;
     m.add_function(wrap_pyfunction!(initialize_logs, m)?)?;
     m.add_function(wrap_pyfunction!(spec_version, m)?)?;
+    m.add_function(wrap_pyfunction!(cli_entrypoint, m)?)?;
 
     // Exceptions
     m.add("IcechunkError", py.get_type::<IcechunkError>())?;

icechunk/Cargo.toml

@@ -55,6 +55,8 @@ tracing-subscriber = { version = "0.3.19", features = [
 tracing = "0.1.41"
 err-into = "1.0.1"
 serde_yaml_ng = "0.10.0"
+clap = { version = "4.5", features = ["derive"] }
+anyhow = "1.0.95"
 
 [dev-dependencies]
 pretty_assertions = "1.4.1"

icechunk/default.yaml

@@ -0,0 +1,31 @@
+repos:
+  localrepo: !LocalFileSystem
+    path: testfolder
+    config:
+      inline_chunk_threshold_bytes: null
+      unsafe_overwrite_refs: null
+      get_partial_values_concurrency: null
+      compression: null
+      caching: null
+      storage: null
+      virtual_chunk_containers: null
+      manifest: null
+  s3repo: !S3
+    location:
+      bucket: testbucket
+      prefix: testfolder
+    object_store_config:
+      region: eu-west-1
+      endpoint_url: null
+      anonymous: false
+      allow_http: false
+    credentials: FromEnv
+    config:
+      inline_chunk_threshold_bytes: null
+      unsafe_overwrite_refs: null
+      get_partial_values_concurrency: null
+      compression: null
+      caching: null
+      storage: null
+      virtual_chunk_containers: null
+      manifest: null

icechunk/src/bin/icechunk/main.rs

@@ -0,0 +1,8 @@
+use clap::Parser;
+use icechunk::cli::interface::{run_cli, IcechunkCLI};
+
+#[tokio::main]
+async fn main() {
+    let cli = IcechunkCLI::parse();
+    let _ = run_cli(cli).await;
+}