compliance-scanner-agent/compliance-agent/src/database.rs

use mongodb::bson::doc;
use mongodb::options::IndexOptions;
use mongodb::{Client, Collection, IndexModel};

use compliance_core::models::*;

use crate::error::AgentError;

#[derive(Clone, Debug)]
pub struct Database {
    inner: mongodb::Database,
}

impl Database {
    pub async fn connect(uri: &str, db_name: &str) -> Result<Self, AgentError> {
        let client = Client::with_uri_str(uri).await?;
        let db = client.database(db_name);
        db.run_command(doc! { "ping": 1 }).await?;
        tracing::info!("Connected to MongoDB database '{db_name}'");
        Ok(Self { inner: db })
    }

    pub async fn ensure_indexes(&self) -> Result<(), AgentError> {
        // repositories: unique git_url
        self.repositories()
            .create_index(
                IndexModel::builder()
                    .keys(doc! { "git_url": 1 })
                    .options(IndexOptions::builder().unique(true).build())
                    .build(),
            )
            .await?;

        // findings: unique fingerprint
        self.findings()
            .create_index(
                IndexModel::builder()
                    .keys(doc! { "fingerprint": 1 })
                    .options(IndexOptions::builder().unique(true).build())
                    .build(),
            )
            .await?;

        // findings: repo_id + severity compound
        self.findings()
            .create_index(
                IndexModel::builder()
                    .keys(doc! { "repo_id": 1, "severity": 1 })
                    .build(),
            )
            .await?;

        // scan_runs: repo_id + started_at descending
        self.scan_runs()
            .create_index(
                IndexModel::builder()
                    .keys(doc! { "repo_id": 1, "started_at": -1 })
                    .build(),
            )
            .await?;

        // sbom_entries: compound
        self.sbom_entries()
            .create_index(
                IndexModel::builder()
                    .keys(doc! { "repo_id": 1, "name": 1, "version": 1 })
                    .build(),
            )
            .await?;

        // cve_alerts: unique cve_id + repo_id
        self.cve_alerts()
            .create_index(
                IndexModel::builder()
                    .keys(doc! { "cve_id": 1, "repo_id": 1 })
                    .options(IndexOptions::builder().unique(true).build())
                    .build(),
            )
            .await?;

        // tracker_issues: unique finding_id
        self.tracker_issues()
            .create_index(
                IndexModel::builder()
                    .keys(doc! { "finding_id": 1 })
                    .options(IndexOptions::builder().unique(true).build())
                    .build(),
            )
            .await?;

        // graph_nodes: compound (repo_id, graph_build_id)
        self.graph_nodes()
            .create_index(
                IndexModel::builder()
                    .keys(doc! { "repo_id": 1, "graph_build_id": 1 })
                    .build(),
            )
            .await?;

        // graph_edges: compound (repo_id, graph_build_id)
        self.graph_edges()
            .create_index(
                IndexModel::builder()
                    .keys(doc! { "repo_id": 1, "graph_build_id": 1 })
                    .build(),
            )
            .await?;

        // graph_builds: compound (repo_id, started_at DESC)
        self.graph_builds()
            .create_index(
                IndexModel::builder()
                    .keys(doc! { "repo_id": 1, "started_at": -1 })
                    .build(),
            )
            .await?;

        // impact_analyses: unique (repo_id, finding_id)
        self.impact_analyses()
            .create_index(
                IndexModel::builder()
                    .keys(doc! { "repo_id": 1, "finding_id": 1 })
                    .options(IndexOptions::builder().unique(true).build())
                    .build(),
            )
            .await?;

        // dast_targets: index on repo_id
        self.dast_targets()
            .create_index(IndexModel::builder().keys(doc! { "repo_id": 1 }).build())
            .await?;

        // dast_scan_runs: compound (target_id, started_at DESC)
        self.dast_scan_runs()
            .create_index(
                IndexModel::builder()
                    .keys(doc! { "target_id": 1, "started_at": -1 })
                    .build(),
            )
            .await?;

        // dast_findings: compound (scan_run_id, vuln_type)
        self.dast_findings()
            .create_index(
                IndexModel::builder()
                    .keys(doc! { "scan_run_id": 1, "vuln_type": 1 })
                    .build(),
            )
            .await?;

        // code_embeddings: compound (repo_id, graph_build_id)
        self.code_embeddings()
            .create_index(
                IndexModel::builder()
                    .keys(doc! { "repo_id": 1, "graph_build_id": 1 })
                    .build(),
            )
            .await?;

        // embedding_builds: compound (repo_id, started_at DESC)
        self.embedding_builds()
            .create_index(
                IndexModel::builder()
                    .keys(doc! { "repo_id": 1, "started_at": -1 })
                    .build(),
            )
            .await?;

        tracing::info!("Database indexes ensured");
        Ok(())
    }

    pub fn repositories(&self) -> Collection<TrackedRepository> {
        self.inner.collection("repositories")
    }

    pub fn findings(&self) -> Collection<Finding> {
        self.inner.collection("findings")
    }

    pub fn scan_runs(&self) -> Collection<ScanRun> {
        self.inner.collection("scan_runs")
    }

    pub fn sbom_entries(&self) -> Collection<SbomEntry> {
        self.inner.collection("sbom_entries")
    }

    pub fn cve_alerts(&self) -> Collection<CveAlert> {
        self.inner.collection("cve_alerts")
    }

    pub fn tracker_issues(&self) -> Collection<TrackerIssue> {
        self.inner.collection("tracker_issues")
    }

    // Graph collections
    pub fn graph_nodes(&self) -> Collection<compliance_core::models::graph::CodeNode> {
        self.inner.collection("graph_nodes")
    }

    pub fn graph_edges(&self) -> Collection<compliance_core::models::graph::CodeEdge> {
        self.inner.collection("graph_edges")
    }

    pub fn graph_builds(&self) -> Collection<compliance_core::models::graph::GraphBuildRun> {
        self.inner.collection("graph_builds")
    }

    pub fn impact_analyses(&self) -> Collection<compliance_core::models::graph::ImpactAnalysis> {
        self.inner.collection("impact_analyses")
    }

    // DAST collections
    pub fn dast_targets(&self) -> Collection<DastTarget> {
        self.inner.collection("dast_targets")
    }

    pub fn dast_scan_runs(&self) -> Collection<DastScanRun> {
        self.inner.collection("dast_scan_runs")
    }

    pub fn dast_findings(&self) -> Collection<DastFinding> {
        self.inner.collection("dast_findings")
    }

    // Embedding collections
    pub fn code_embeddings(&self) -> Collection<compliance_core::models::embedding::CodeEmbedding> {
        self.inner.collection("code_embeddings")
    }

    pub fn embedding_builds(
        &self,
    ) -> Collection<compliance_core::models::embedding::EmbeddingBuildRun> {
        self.inner.collection("embedding_builds")
    }

    #[allow(dead_code)]
    pub fn raw_collection(&self, name: &str) -> Collection<mongodb::bson::Document> {
        self.inner.collection(name)
    }

    /// Get the raw MongoDB database handle (for graph persistence)
    pub fn inner(&self) -> &mongodb::Database {
        &self.inner
    }
}