cm-dashboard/agent/src/collectors/backup.rs

use async_trait::async_trait;
use cm_dashboard_shared::{Metric, MetricValue, Status};
use chrono::Utc;
use serde::{Deserialize, Serialize};
use std::collections::HashMap;
use tokio::fs;

use super::{Collector, CollectorError};
use tracing::error;

/// Backup collector that reads TOML status files for borgbackup metrics
#[derive(Debug, Clone)]
pub struct BackupCollector {
    pub backup_status_file: String,
    pub max_age_hours: u64,
}

impl BackupCollector {
    pub fn new(backup_status_file: Option<String>, max_age_hours: u64) -> Self {
        Self {
            backup_status_file: backup_status_file.unwrap_or_else(|| "/var/lib/backup/backup-status.toml".to_string()),
            max_age_hours,
        }
    }

    async fn read_backup_status(&self) -> Result<BackupStatusToml, CollectorError> {
        let content = fs::read_to_string(&self.backup_status_file)
            .await
            .map_err(|e| CollectorError::SystemRead {
                path: self.backup_status_file.clone(),
                error: e.to_string(),
            })?;

        toml::from_str(&content).map_err(|e| CollectorError::Parse {
            value: "backup status TOML".to_string(),
            error: e.to_string(),
        })
    }

    fn calculate_backup_status(&self, backup_status: &BackupStatusToml) -> Status {
        // Parse the start time to check age - handle both RFC3339 and local timestamp formats
        let start_time = match chrono::DateTime::parse_from_rfc3339(&backup_status.start_time) {
            Ok(dt) => dt.with_timezone(&Utc),
            Err(_) => {
                // Try parsing as naive datetime and assume UTC
                match chrono::NaiveDateTime::parse_from_str(&backup_status.start_time, "%Y-%m-%dT%H:%M:%S%.f") {
                    Ok(naive_dt) => naive_dt.and_utc(),
                    Err(_) => {
                        error!("Failed to parse backup timestamp: {}", backup_status.start_time);
                        return Status::Unknown;
                    }
                }
            }
        };

        let hours_since_backup = Utc::now().signed_duration_since(start_time).num_hours();

        // Check overall backup status
        match backup_status.status.as_str() {
            "success" => {
                if hours_since_backup > self.max_age_hours as i64 {
                    Status::Warning // Backup too old
                } else {
                    Status::Ok
                }
            },
            "failed" => Status::Critical,
            "running" => Status::Ok, // Currently running is OK
            _ => Status::Unknown,
        }
    }

    fn calculate_service_status(&self, service: &ServiceStatus) -> Status {
        match service.status.as_str() {
            "completed" => {
                if service.exit_code == 0 {
                    Status::Ok
                } else {
                    Status::Critical
                }
            },
            "failed" => Status::Critical,
            "disabled" => Status::Warning, // Service intentionally disabled
            "running" => Status::Ok,
            _ => Status::Unknown,
        }
    }

    fn bytes_to_gb(bytes: u64) -> f32 {
        bytes as f32 / (1024.0 * 1024.0 * 1024.0)
    }
}

#[async_trait]
impl Collector for BackupCollector {
    fn name(&self) -> &str {
        "backup"
    }

    async fn collect(&self) -> Result<Vec<Metric>, CollectorError> {
        let backup_status = self.read_backup_status().await?;
        let mut metrics = Vec::new();
        let timestamp = chrono::Utc::now().timestamp() as u64;

        // Overall backup status
        let overall_status = self.calculate_backup_status(&backup_status);
        metrics.push(Metric {
            name: "backup_overall_status".to_string(),
            value: MetricValue::String(match overall_status {
                Status::Ok => "ok".to_string(),
                Status::Warning => "warning".to_string(),
                Status::Critical => "critical".to_string(),
                Status::Unknown => "unknown".to_string(),
            }),
            status: overall_status,
            timestamp,
            description: Some(format!("Backup: {} at {}", backup_status.status, backup_status.start_time)),
            unit: None,
        });

        // Backup duration
        metrics.push(Metric {
            name: "backup_duration_seconds".to_string(),
            value: MetricValue::Integer(backup_status.duration_seconds),
            status: Status::Ok,
            timestamp,
            description: Some("Duration of last backup run".to_string()),
            unit: Some("seconds".to_string()),
        });

        // Last backup timestamp - use last_updated (when backup finished) instead of start_time
        let last_updated_dt_result = chrono::DateTime::parse_from_rfc3339(&backup_status.last_updated)
            .map(|dt| dt.with_timezone(&Utc))
            .or_else(|_| {
                // Try parsing as naive datetime and assume UTC
                chrono::NaiveDateTime::parse_from_str(&backup_status.last_updated, "%Y-%m-%dT%H:%M:%S%.f")
                    .map(|naive_dt| naive_dt.and_utc())
            });
            
        if let Ok(last_updated_dt) = last_updated_dt_result {
            metrics.push(Metric {
                name: "backup_last_run_timestamp".to_string(),
                value: MetricValue::Integer(last_updated_dt.timestamp()),
                status: Status::Ok,
                timestamp,
                description: Some("Timestamp of last backup completion".to_string()),
                unit: Some("unix_timestamp".to_string()),
            });
        } else {
            error!("Failed to parse backup timestamp for last_run_timestamp: {}", backup_status.last_updated);
        }

        // Individual service metrics
        for (service_name, service) in &backup_status.services {
            let service_status = self.calculate_service_status(service);
            
            // Service status
            metrics.push(Metric {
                name: format!("backup_service_{}_status", service_name),
                value: MetricValue::String(match service_status {
                    Status::Ok => "ok".to_string(),
                    Status::Warning => "warning".to_string(),
                    Status::Critical => "critical".to_string(),
                    Status::Unknown => "unknown".to_string(),
                }),
                status: service_status,
                timestamp,
                description: Some(format!("Backup service {} status: {}", service_name, service.status)),
                unit: None,
            });

            // Service exit code
            metrics.push(Metric {
                name: format!("backup_service_{}_exit_code", service_name),
                value: MetricValue::Integer(service.exit_code),
                status: if service.exit_code == 0 { Status::Ok } else { Status::Critical },
                timestamp,
                description: Some(format!("Exit code for backup service {}", service_name)),
                unit: None,
            });

            // Repository archive count
            metrics.push(Metric {
                name: format!("backup_service_{}_archive_count", service_name),
                value: MetricValue::Integer(service.archive_count),
                status: Status::Ok,
                timestamp,
                description: Some(format!("Number of archives in {} repository", service_name)),
                unit: Some("archives".to_string()),
            });

            // Repository size in GB
            let repo_size_gb = Self::bytes_to_gb(service.repo_size_bytes);
            metrics.push(Metric {
                name: format!("backup_service_{}_repo_size_gb", service_name),
                value: MetricValue::Float(repo_size_gb),
                status: Status::Ok,
                timestamp,
                description: Some(format!("Repository size for {} in GB", service_name)),
                unit: Some("GB".to_string()),
            });

            // Repository path for reference
            metrics.push(Metric {
                name: format!("backup_service_{}_repo_path", service_name),
                value: MetricValue::String(service.repo_path.clone()),
                status: Status::Ok,
                timestamp,
                description: Some(format!("Repository path for {}", service_name)),
                unit: None,
            });
        }

        // Total number of services
        metrics.push(Metric {
            name: "backup_total_services".to_string(),
            value: MetricValue::Integer(backup_status.services.len() as i64),
            status: Status::Ok,
            timestamp,
            description: Some("Total number of backup services".to_string()),
            unit: Some("services".to_string()),
        });

        // Calculate total repository size
        let total_size_bytes: u64 = backup_status.services.values()
            .map(|s| s.repo_size_bytes)
            .sum();
        let total_size_gb = Self::bytes_to_gb(total_size_bytes);
        metrics.push(Metric {
            name: "backup_total_repo_size_gb".to_string(),
            value: MetricValue::Float(total_size_gb),
            status: Status::Ok,
            timestamp,
            description: Some("Total size of all backup repositories".to_string()),
            unit: Some("GB".to_string()),
        });

        // Disk space metrics for backup directory
        if let Some(ref disk_space) = backup_status.disk_space {
            metrics.push(Metric {
                name: "backup_disk_total_gb".to_string(),
                value: MetricValue::Float(disk_space.total_gb as f32),
                status: Status::Ok,
                timestamp,
                description: Some("Total disk space available for backups".to_string()),
                unit: Some("GB".to_string()),
            });

            metrics.push(Metric {
                name: "backup_disk_used_gb".to_string(),
                value: MetricValue::Float(disk_space.used_gb as f32),
                status: Status::Ok,
                timestamp,
                description: Some("Used disk space on backup drive".to_string()),
                unit: Some("GB".to_string()),
            });

            metrics.push(Metric {
                name: "backup_disk_available_gb".to_string(),
                value: MetricValue::Float(disk_space.available_gb as f32),
                status: Status::Ok,
                timestamp,
                description: Some("Available disk space on backup drive".to_string()),
                unit: Some("GB".to_string()),
            });

            metrics.push(Metric {
                name: "backup_disk_usage_percent".to_string(),
                value: MetricValue::Float(disk_space.usage_percent as f32),
                status: if disk_space.usage_percent >= 95.0 {
                    Status::Critical
                } else if disk_space.usage_percent >= 85.0 {
                    Status::Warning
                } else {
                    Status::Ok
                },
                timestamp,
                description: Some("Backup disk usage percentage".to_string()),
                unit: Some("percent".to_string()),
            });

            // Add disk identification metrics if available from disk_space
            if let Some(ref product_name) = disk_space.product_name {
                metrics.push(Metric {
                    name: "backup_disk_product_name".to_string(),
                    value: MetricValue::String(product_name.clone()),
                    status: Status::Ok,
                    timestamp,
                    description: Some("Backup disk product name from SMART data".to_string()),
                    unit: None,
                });
            }

            if let Some(ref serial_number) = disk_space.serial_number {
                metrics.push(Metric {
                    name: "backup_disk_serial_number".to_string(),
                    value: MetricValue::String(serial_number.clone()),
                    status: Status::Ok,
                    timestamp,
                    description: Some("Backup disk serial number from SMART data".to_string()),
                    unit: None,
                });
            }

        }

        // Add standalone disk identification metrics from TOML fields
        if let Some(ref product_name) = backup_status.disk_product_name {
            metrics.push(Metric {
                name: "backup_disk_product_name".to_string(),
                value: MetricValue::String(product_name.clone()),
                status: Status::Ok,
                timestamp,
                description: Some("Backup disk product name from SMART data".to_string()),
                unit: None,
            });
        }

        if let Some(ref serial_number) = backup_status.disk_serial_number {
            metrics.push(Metric {
                name: "backup_disk_serial_number".to_string(),
                value: MetricValue::String(serial_number.clone()),
                status: Status::Ok,
                timestamp,
                description: Some("Backup disk serial number from SMART data".to_string()),
                unit: None,
            });
        }

        // Count services by status
        let mut status_counts = HashMap::new();
        for service in backup_status.services.values() {
            *status_counts.entry(service.status.clone()).or_insert(0) += 1;
        }

        for (status_name, count) in status_counts {
            metrics.push(Metric {
                name: format!("backup_services_{}_count", status_name),
                value: MetricValue::Integer(count),
                status: Status::Ok,
                timestamp,
                description: Some(format!("Number of services with status: {}", status_name)),
                unit: Some("services".to_string()),
            });
        }

        Ok(metrics)
    }
}

/// TOML structure for backup status file
#[derive(Debug, Clone, Deserialize, Serialize)]
pub struct BackupStatusToml {
    pub backup_name: String,
    pub start_time: String,
    pub current_time: String,
    pub duration_seconds: i64,
    pub status: String,
    pub last_updated: String,
    pub disk_space: Option<DiskSpace>,
    pub disk_product_name: Option<String>,
    pub disk_serial_number: Option<String>,
    pub services: HashMap<String, ServiceStatus>,
}

#[derive(Debug, Clone, Deserialize, Serialize)]
pub struct DiskSpace {
    pub total_bytes: u64,
    pub used_bytes: u64,
    pub available_bytes: u64,
    pub total_gb: f64,
    pub used_gb: f64,
    pub available_gb: f64,
    pub usage_percent: f64,
    // Optional disk identification fields  
    pub product_name: Option<String>,
    pub serial_number: Option<String>,
}

#[derive(Debug, Clone, Deserialize, Serialize)]
pub struct ServiceStatus {
    pub status: String,
    pub exit_code: i64,
    pub repo_path: String,
    pub archive_count: i64,
    pub repo_size_bytes: u64,
}