feat: add CLI option to get the json schema of inventory file.

CHANGELOG.md

@@ -10,6 +10,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 _This paragraph may describe WIP/unreleased features. They are merged to main branch but not tagged._
 
 - [Doc: reference Boavizta methodology paper. · Issue #552 · Boavizta/cloud-scanner](https://github.com/Boavizta/cloud-scanner/issues/552)
+- [Expose the json schema of the inventory format · Issue #558 · Boavizta/cloud-scanner](https://github.com/Boavizta/cloud-scanner/issues/558). Use `cargo run inventory --print-json-schema` with CLI to get the schema on stdout.
 
 ## [3.0.1]-2024-06-19
 

cloud-scanner-cli/src/inventory_exporter.rs

@@ -1,4 +1,5 @@
 use anyhow::Context;
+use schemars::schema_for;
 
 use crate::model::Inventory;
 
@@ -13,3 +14,31 @@ pub async fn print_inventory(inventory: &Inventory) -> anyhow::Result<()> {
     println!("{}", json_inventory);
     Ok(())
 }
+
+/// Returns the json schema of an inventory as String
+pub fn get_inventory_schema() -> anyhow::Result<String> {
+    let schema = schema_for!(Inventory);
+    let st = serde_json::to_string_pretty(&schema)?;
+    Ok(st)
+}
+
+/// Print inventory schema on stdout
+pub fn print_inventory_schema() -> anyhow::Result<()> {
+    let s = get_inventory_schema()?;
+    println!("{}", s);
+    Ok(())
+}
+
+#[cfg(test)]
+mod tests {
+    use crate::inventory_exporter::get_inventory_schema;
+    const INVENTORY_JSON_SCHEMA: &str = include_str!("../test-data/INVENTORY_JSON_SCHEMA.json");
+
+    #[test]
+    pub fn generate_inventory_schema() {
+        let s = get_inventory_schema().unwrap();
+        println!("{}", s);
+
+        assert_eq!(s, INVENTORY_JSON_SCHEMA, "schema do not match");
+    }
+}

cloud-scanner-cli/src/main.rs

@@ -72,6 +72,10 @@ enum SubCommand {
         #[arg(long, short = 'b', action)]
         /// Experimental feature: include block storage in the inventory
         include_block_storage: bool,
+
+        /// Print the json schema of the inventory (instead of performing inventory)
+        #[arg(short = 's', long)]
+        print_json_schema: bool,
     },
     ///  Run as a standalone server.
     /// Access metrics (e.g. http://localhost:8000/metrics?aws_region=eu-west-3), inventory or impacts (see http://localhost:8000/swagger-ui)
@@ -168,12 +172,20 @@ async fn main() -> Result<()> {
         }
         SubCommand::Inventory {
             include_block_storage,
+            print_json_schema,
         } => {
-            info!("Using filter tags {:?}", &args.filter_tags);
-            let inventory =
-                cloud_scanner_cli::get_inventory(&args.filter_tags, &region, include_block_storage)
-                    .await?;
-            print_inventory(&inventory).await?;
+            if print_json_schema {
+                cloud_scanner_cli::inventory_exporter::print_inventory_schema()?;
+            } else {
+                info!("Using filter tags {:?}", &args.filter_tags);
+                let inventory = cloud_scanner_cli::get_inventory(
+                    &args.filter_tags,
+                    &region,
+                    include_block_storage,
+                )
+                .await?;
+                print_inventory(&inventory).await?;
+            }
         }
         SubCommand::Serve {} => cloud_scanner_cli::serve_metrics(&api_url).await?,
     }

cloud-scanner-cli/src/model.rs

@@ -12,7 +12,7 @@ use std::{fmt, fs};
 use crate::impact_provider::CloudResourceWithImpacts;
 use crate::usage_location::UsageLocation;
 
-///  Statistics about program execution
+/// Statistics about program execution
 #[derive(Clone, Debug, Serialize, Deserialize, JsonSchema)]
 #[serde(rename_all = "snake_case")]
 pub struct ExecutionStatistics {
@@ -27,7 +27,7 @@ impl fmt::Display for ExecutionStatistics {
     }
 }
 
-/// Inventory: a list of resources
+/// A list of cloud resources and metadata that describes the inventory itself
 #[derive(Clone, Serialize, Deserialize, JsonSchema)]
 #[serde(rename_all = "snake_case")]
 pub struct Inventory {
@@ -39,10 +39,13 @@ pub struct Inventory {
 #[derive(Clone, Serialize, Deserialize, JsonSchema)]
 #[serde(rename_all = "snake_case")]
 pub struct InventoryMetadata {
+    /// The date when the inventory was generated
     pub inventory_date: Option<DateTime<Utc>>,
+    /// A free text description of the inventory
     pub description: Option<String>,
     /// The version of the cloud scanner that generated the inventory
     pub cloud_scanner_version: Option<String>,
+    /// Statistics about program execution
     pub execution_statistics: Option<ExecutionStatistics>,
 }
 
@@ -67,11 +70,12 @@ pub struct EstimatedInventory {
     pub execution_statistics: Option<ExecutionStatistics>,
 }
 
-///  A cloud resource (could be an instance, function or any other resource)
+///  A cloud resource (could be an instance, block storage or any other resource)
 #[derive(Clone, Debug, Serialize, Deserialize, JsonSchema)]
 pub struct CloudResource {
     pub provider: CloudProvider,
     pub id: String,
+    ///  The location where cloud resources are running.
     pub location: UsageLocation,
     pub resource_details: ResourceDetails,
     pub tags: Vec<CloudResourceTag>,