fetch_ml/scripts/manage-artifacts.sh

#!/bin/bash

# Artifact Management Script
# Manage local benchmark artifacts

set -e

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
PROJECT_ROOT="$(dirname "$SCRIPT_DIR")"
LOCAL_ARTIFACTS_DIR="$PROJECT_ROOT/.local-artifacts"

# Create artifacts directory if it doesn't exist
mkdir -p "$LOCAL_ARTIFACTS_DIR"

case "${1:-help}" in
    "list")
        echo "=== Benchmark Runs ==="
        if [ -d "$LOCAL_ARTIFACTS_DIR" ]; then
            ls -lt "$LOCAL_ARTIFACTS_DIR"/run_* 2>/dev/null | while read -r line; do
                run_dir=$(echo "$line" | awk '{print $9}')
                if [ -n "$run_dir" ]; then
                    timestamp=$(basename "$run_dir" | sed 's/run_//')
                    echo "Run: $timestamp"
                    echo "  Path: $run_dir"
                    if [ -f "$run_dir/report.html" ]; then
                        echo "  Report: $run_dir/report.html"
                    fi
                    if [ -f "$run_dir/prometheus_metrics.txt" ]; then
                        metrics_count=$(grep -c "benchmark_" "$run_dir/prometheus_metrics.txt" 2>/dev/null || echo "0")
                        echo "  Metrics: $metrics_count benchmarks"
                    fi
                    echo ""
                fi
            done
        else
            echo "No artifacts found"
        fi
        ;;
    
    "clean")
        echo "=== Cleaning Artifacts ==="
        case "${2:-all}" in
            "all")
                echo "Removing all artifacts..."
                rm -rf "$LOCAL_ARTIFACTS_DIR"
                echo "All artifacts removed"
                ;;
            "old")
                keep_count="${3:-10}"
                echo "Keeping last $keep_count runs, removing older ones..."
                cd "$LOCAL_ARTIFACTS_DIR"
                ls -1t run_* 2>/dev/null | tail -n +$((keep_count + 1)) | while read -r run; do
                    echo "Removing: $run"
                    rm -rf "$run"
                done
                ;;
            "run")
                run_id="${3:-}"
                if [ -z "$run_id" ]; then
                    echo "Usage: $0 clean run <run_id>"
                    echo "Available runs:"
                    ls -1 "$LOCAL_ARTIFACTS_DIR"/run_* 2>/dev/null | sed 's/.*run_//' || echo "No runs found"
                    exit 1
                fi
                run_dir="$LOCAL_ARTIFACTS_DIR/run_$run_id"
                if [ -d "$run_dir" ]; then
                    echo "Removing run: $run_id"
                    rm -rf "$run_dir"
                else
                    echo "Run not found: $run_id"
                fi
                ;;
            *)
                echo "Usage: $0 clean [all|old|run <run_id>]"
                exit 1
                ;;
        esac
        ;;
    
    "compare")
        run1="${2:-}"
        run2="${3:-}"
        if [ -z "$run1" ] || [ -z "$run2" ]; then
            echo "Usage: $0 compare <run_id1> <run_id2>"
            echo "Available runs:"
            ls -1 "$LOCAL_ARTIFACTS_DIR"/run_* 2>/dev/null | sed 's/.*run_//' || echo "No runs found"
            exit 1
        fi
        
        echo "=== Comparing Runs ==="
        echo "Run 1: $run1"
        echo "Run 2: $run2"
        echo ""
        
        metrics1="$LOCAL_ARTIFACTS_DIR/run_$run1/prometheus_metrics.txt"
        metrics2="$LOCAL_ARTIFACTS_DIR/run_$run2/prometheus_metrics.txt"
        
        if [ ! -f "$metrics1" ] || [ ! -f "$metrics2" ]; then
            echo "One or both runs not found"
            exit 1
        fi
        
        echo "Benchmark Comparison:"
        printf "%-40s %-15s %-15s %-10s\n" "Benchmark" "Run 1 (ns)" "Run 2 (ns)" "Change"
        printf "%-40s %-15s %-15s %-10s\n" "--------" "----------" "----------" "------"
        
        grep "benchmark_time_per_op" "$metrics1" | while read -r line1; do
            benchmark=$(echo "$line1" | sed 's/.*benchmark="\([^"]*\)".*/\1/')
            value1=$(echo "$line1" | awk '{print $2}')
            
            line2=$(grep "benchmark_time_per_op.*benchmark=\"$benchmark\"" "$metrics2" || true)
            if [ -n "$line2" ]; then
                value2=$(echo "$line2" | awk '{print $2}')
                
                # Calculate percentage change
                if [ "$value1" != "0" ]; then
                    change=$(echo "scale=2; (($value2 - $value1) / $value1) * 100" | bc 2>/dev/null || echo "N/A")
                    printf "%-40s %-15s %-15s %-10s\n" "$benchmark" "$value1" "$value2" "${change}%"
                else
                    printf "%-40s %-15s %-15s %-10s\n" "$benchmark" "$value1" "$value2" "N/A"
                fi
            fi
        done
        ;;
    
    "export")
        run_id="${2:-}"
        format="${3:-json}"
        if [ -z "$run_id" ]; then
            echo "Usage: $0 export <run_id> [json|csv]"
            echo "Available runs:"
            ls -1 "$LOCAL_ARTIFACTS_DIR"/run_* 2>/dev/null | sed 's/.*run_//' || echo "No runs found"
            exit 1
        fi
        
        run_dir="$LOCAL_ARTIFACTS_DIR/run_$run_id"
        if [ ! -d "$run_dir" ]; then
            echo "Run not found: $run_id"
            exit 1
        fi
        
        output_file="$LOCAL_ARTIFACTS_DIR/export_${run_id}.$format"
        
        case "$format" in
            "json")
                echo "Exporting run $run_id to JSON..."
                python3 -c "
import json
import sys

metrics = []
with open('$run_dir/prometheus_metrics.txt', 'r') as f:
    for line in f:
        if line.startswith('benchmark_time_per_op'):
            parts = line.strip().split()
            benchmark = parts[0].split('benchmark=\"')[1].rstrip('\"')
            value = parts[1]
            metrics.append({
                'benchmark': benchmark,
                'time_per_op_ns': int(value),
                'run_id': '$run_id'
            })

export_data = {
    'run_id': '$run_id',
    'timestamp': '$run_id',
    'metrics': metrics
}

with open('$output_file', 'w') as f:
    json.dump(export_data, f, indent=2)
"
                ;;
            "csv")
                echo "Exporting run $run_id to CSV..."
                echo "benchmark,time_per_op_ns,run_id" > "$output_file"
                grep "benchmark_time_per_op" "$run_dir/prometheus_metrics.txt" | while read -r line; do
                    benchmark=$(echo "$line" | sed 's/.*benchmark="\([^"]*\)".*/\1/')
                    value=$(echo "$line" | awk '{print $2}')
                    echo "$benchmark,$value,$run_id" >> "$output_file"
                done
                ;;
            *)
                echo "Unsupported format: $format"
                exit 1
                ;;
        esac
        
        echo "Exported to: $output_file"
        ;;
    
    "help"|*)
        echo "Artifact Management Tool"
        echo ""
        echo "Usage: $0 <command> [args]"
        echo ""
        echo "Commands:"
        echo "  list                    List all benchmark runs"
        echo "  clean [all|old|run]    Clean artifacts"
        echo "    all                   Remove all artifacts"
        echo "    old [count]           Keep last N runs (default: 10)"
        echo "    run <run_id>          Remove specific run"
        echo "  compare <run1> <run2>   Compare two benchmark runs"
        echo "  export <run_id> [format] Export run data (json|csv)"
        echo "  help                    Show this help"
        echo ""
        echo "Examples:"
        echo "  $0 list"
        echo "  $0 clean old 5"
        echo "  $0 compare 20241204_220000 20241204_230000"
        echo "  $0 export 20241204_220000 json"
        ;;
esac