feat: initial scaffolding for ckan_geoconnex_bulk_runner

Cargo.toml

@@ -0,0 +1,11 @@
+[package]
+name = "ckan_geoconnex_bulk_runner"
+version = "0.1.0"
+edition = "2024"
+
+[dependencies]
+anyhow = "1.0.102"
+ckanaction = "0.1.4"
+jsonschema = "0.46.4"
+serde_json = "1.0.149"
+tokio = { version = "1.52.1", features = ["full"] }

README.md

@@ -0,0 +1,15 @@
+# ckan_geoconnex_bulk_runner
+
+> Status: This codebase is currently a work in progress and more documentation is planned.
+
+The `ckan_geoconnex_bulk_runner` codebase is meant to run as a container for a bulk integration of a [CKAN](https://ckan.org) instance's relevant datasets and locations (e.g. for water data hubs) to the [Geoconnex](https://geoconnex.us) knowledge graph. The codebase ultimately runs as a program outputting to standard output JSON-LD on a new line for each approved dataset/location which the Geoconnex crawler then uses to update the Geoconnex knowledge graph.
+
+Refer to "The Geoconnex Bulk Namespace" documentation here for more information: https://github.com/internetofwater/geoconnex.us/tree/master/namespaces/bulk
+
+This runner is expected to be implemented for a water data hub with [DataPusher+](https://github.com/dathere/datapusher-plus) enabled. For questions reach out to [datHere](https://dathere.com), [Center for Geospatial Solutions](https://cgsearth.org/), or add an issue/discussion.
+
+## Installation and setup
+
+```bash
+cargo run --release
+```

config.toml

@@ -0,0 +1,2 @@
+ckan_url = "https://data.dathere.com"
+geoconnex_about_field_name = "geoconnex_about"

src/main.rs

@@ -0,0 +1,31 @@
+mod utils;
+
+use anyhow::Result;
+
+#[tokio::main]
+async fn main() -> Result<(), Box<dyn std::error::Error>> {
+    let ckan = ckanaction::CKAN::builder()
+        .url("https://data.dathere.com")
+        .build();
+    // TODO: Paginate through package_list and run package_show for each package
+    // If about exists then construct JSON-LD and validate then output JSON-LD to stdout on a new line
+    let response = ckan.package_show().id("".to_string()).call().await?;
+
+    let result = response
+        .as_object()
+        .unwrap()
+        .get("result")
+        .unwrap()
+        .as_object()
+        .unwrap();
+    if let Some(geoconnex_about) = result.get("geoconnex_about") {
+        // Check if at least one valid reference feature exists in dataset metadata
+    }
+    // TODO: Construct JSON-LD if valid `about`
+    // TODO: Validate constructed JSON-LD against JSON schema
+    // TODO: Print JSON-LD to new line
+
+    println!("{result:#?}");
+
+    Ok(())
+}

src/utils.rs

@@ -0,0 +1,14 @@
+use serde_json::json;
+
+async fn construct_jsonld(metadata: serde_json::Value) -> serde_json::Value {}
+
+async fn get_dataset_schema() -> serde_json::Value {
+    json!({
+        "type": "object",
+        "properties": {
+            "@context": {"type": ["string", "object"]},
+            "@type": {"const": "Dataset"}
+        },
+        "required": []
+    })
+}