macos-tools/harbor/scripts/batch-cache-images.sh

#!/bin/bash

# 批量镜像缓存脚本
# 根据清单批量缓存项目所需镜像到 Harbor

set -e

HARBOR_REGISTRY="192.168.1.83:8443"
HARBOR_USER="admin"
HARBOR_PASS="admin123"
IMAGES_LIST="./project-images.list"
LOG_FILE="./cache-images.log"

# 颜色输出
RED='\033[0;31m'
GREEN='\033[0;32m'
YELLOW='\033[1;33m'
BLUE='\033[0;34m'
NC='\033[0m' # No Color

# 日志函数
log() {
    echo "$(date '+%Y-%m-%d %H:%M:%S') - $1" | tee -a "$LOG_FILE"
}

error() {
    echo -e "${RED}ERROR: $1${NC}" | tee -a "$LOG_FILE"
}

success() {
    echo -e "${GREEN}SUCCESS: $1${NC}" | tee -a "$LOG_FILE"
}

warning() {
    echo -e "${YELLOW}WARNING: $1${NC}" | tee -a "$LOG_FILE"
}

info() {
    echo -e "${BLUE}INFO: $1${NC}" | tee -a "$LOG_FILE"
}

# 显示帮助信息
show_help() {
    echo "批量镜像缓存工具"
    echo ""
    echo "用法: $0 [选项] [筛选条件]"
    echo ""
    echo "选项:"
    echo "  -f, --file <文件>     指定镜像清单文件 (默认: project-images.list)"
    echo "  -p, --priority <级别> 按优先级筛选 (high/medium/low)"
    echo "  -t, --type <类型>     按类型筛选 (runtime/build/k8s/application/security/tools)"
    echo "  -d, --dry-run         仅显示将要缓存的镜像，不实际执行"
    echo "  -c, --continue        遇到错误时继续执行"
    echo "  -j, --parallel <数量> 并发数量 (默认: 3)"
    echo "  -h, --help            显示帮助信息"
    echo ""
    echo "示例:"
    echo "  $0                    # 缓存所有镜像"
    echo "  $0 -p high            # 只缓存高优先级镜像"
    echo "  $0 -t runtime         # 只缓存运行时镜像"
    echo "  $0 -p high -t runtime  # 缓存高优先级的运行时镜像"
    echo "  $0 -d                 # 预览模式，不实际执行"
}

# 解析命令行参数
DRY_RUN=false
CONTINUE_ON_ERROR=false
PARALLEL_JOBS=3
PRIORITY_FILTER=""
TYPE_FILTER=""

while [[ $# -gt 0 ]]; do
    case $1 in
        -f|--file)
            IMAGES_LIST="$2"
            shift 2
            ;;
        -p|--priority)
            PRIORITY_FILTER="$2"
            shift 2
            ;;
        -t|--type)
            TYPE_FILTER="$2"
            shift 2
            ;;
        -d|--dry-run)
            DRY_RUN=true
            shift
            ;;
        -c|--continue)
            CONTINUE_ON_ERROR=true
            shift
            ;;
        -j|--parallel)
            PARALLEL_JOBS="$2"
            shift 2
            ;;
        -h|--help)
            show_help
            exit 0
            ;;
        *)
            error "未知参数: $1"
            show_help
            exit 1
            ;;
    esac
done

# 检查镜像清单文件
if [ ! -f "$IMAGES_LIST" ]; then
    error "镜像清单文件不存在: $IMAGES_LIST"
    exit 1
fi

# 登录 Harbor
info "登录 Harbor..."
if ! echo "$HARBOR_PASS" | docker login "$HARBOR_REGISTRY" -u "$HARBOR_USER" --password-stdin > /dev/null 2>&1; then
    error "Harbor 登录失败"
    exit 1
fi
success "Harbor 登录成功"

# 解析镜像清单
parse_images_list() {
    local images_to_cache=()

    while IFS= read -r line; do
        # 跳过注释和空行
        [[ "$line" =~ ^[[:space:]]*# ]] && continue
        [[ "$line" =~ ^[[:space:]]*$ ]] && continue

        # 解析行: 镜像:标签 项目 描述 优先级
        if [[ "$line" =~ ^([^[:space:]]+)[[:space:]]+([^[:space:]]+)[[:space:]]+([^[:space:]]+)[[:space:]]+([^[:space:]]+)$ ]]; then
            image_full="${BASH_REMATCH[1]}"
            target_project="${BASH_REMATCH[2]}"
            description="${BASH_REMATCH[3]}"
            priority="${BASH_REMATCH[4]}"

            # 应用筛选条件
            if [ -n "$PRIORITY_FILTER" ] && [ "$priority" != "$PRIORITY_FILTER" ]; then
                continue
            fi

            if [ -n "$TYPE_FILTER" ] && [ "$target_project" != "$TYPE_FILTER" ]; then
                continue
            fi

            images_to_cache+=("$image_full|$target_project|$description|$priority")
        fi
    done < "$IMAGES_LIST"

    echo "${images_to_cache[@]}"
}

# 缓存单个镜像
cache_single_image() {
    local image_info="$1"
    local image_full=$(echo "$image_info" | cut -d'|' -f1)
    local target_project=$(echo "$image_info" | cut -d'|' -f2)
    local description=$(echo "$image_info" | cut -d'|' -f3)
    local priority=$(echo "$image_info" | cut -d'|' -f4)

    local image_name=$(echo "$image_full" | cut -d':' -f1)
    local image_tag=$(echo "$image_full" | cut -d':' -f2)

    # 构建 Harbor 镜像名
    local harbor_image="${HARBOR_REGISTRY}/${target_project}/${image_name}:${image_tag}"

    info "缓存镜像: $image_full -> $target_project ($description)"

    if [ "$DRY_RUN" = true ]; then
        echo "[DRY-RUN] 将缓存: $harbor_image"
        return 0
    fi

    # 检查镜像是否已存在
    if docker pull "$harbor_image" > /dev/null 2>&1; then
        success "镜像已存在: $harbor_image"
        return 0
    fi

    # 拉取原始镜像
    info "  拉取原始镜像: $image_full"
    if ! docker pull "$image_full" > /dev/null 2>&1; then
        error "  拉取失败: $image_full"
        [ "$CONTINUE_ON_ERROR" = true ] && return 1 || exit 1
    fi

    # 标记并推送到 Harbor
    info "  推送到 Harbor: $harbor_image"
    if ! docker tag "$image_full" "$harbor_image" > /dev/null 2>&1; then
        error "  标记失败: $harbor_image"
        [ "$CONTINUE_ON_ERROR" = true ] && return 1 || exit 1
    fi

    if ! docker push "$harbor_image" > /dev/null 2>&1; then
        error "  推送失败: $harbor_image"
        [ "$CONTINUE_ON_ERROR" = true ] && return 1 || exit 1
    fi

    success "  缓存成功: $harbor_image"

    # 清理本地镜像（可选）
    # docker rmi "$harbor_image" > /dev/null 2>&1 || true

    return 0
}

# 并发缓存函数
cache_images_parallel() {
    local images_array=("$@")
    local total=${#images_array[@]}
    local pids=()
    local active=0
    local completed=0

    info "开始缓存 $total 个镜像 (并发数: $PARALLEL_JOBS)"

    for image_info in "${images_array[@]}"; do
        # 等待有可用的并发槽位
        while [ $active -ge $PARALLEL_JOBS ]; do
            for pid in "${pids[@]}"; do
                if ! kill -0 "$pid" 2>/dev/null; then
                    wait "$pid"
                    ((completed++))
                    ((active--))
                    # 从 pids 数组中移除已完成的 pid
                    pids=("${pids[@]/$pid/}")
                    break
                fi
            done
            [ $active -ge $PARALLEL_JOBS ] && sleep 1
        done

        # 启动新的缓存任务
        {
            cache_single_image "$image_info"
        } &

        pids+=("$!")
        ((active++))

        # 显示进度
        local progress=$((completed + active))
        info "进度: $progress/$total ($(( progress * 100 / total ))%)"
    done

    # 等待所有任务完成
    for pid in "${pids[@]}"; do
        wait "$pid"
        ((completed++))
    done

    success "所有镜像缓存完成! 总计: $total 个"
}

# 显示统计信息
show_statistics() {
    info "生成缓存统计报告..."

    echo ""
    echo "📊 缓存统计报告"
    echo "=================="

    local total_images=0
    declare -A project_counts
    declare -A priority_counts

    while IFS= read -r line; do
        [[ "$line" =~ ^[[:space:]]*# ]] && continue
        [[ "$line" =~ ^[[:space:]]*$ ]] && continue

        if [[ "$line" =~ ^([^[:space:]]+)[[:space:]]+([^[:space:]]+)[[:space:]]+([^[:space:]]+)[[:space:]]+([^[:space:]]+)$ ]]; then
            target_project="${BASH_REMATCH[2]}"
            priority="${BASH_REMATCH[4]}"

            ((total_images++))
            ((project_counts["$target_project"]++))
            ((priority_counts["$priority"]++))
        fi
    done < "$IMAGES_LIST"

    echo "总镜像数量: $total_images"
    echo ""
    echo "按项目分类:"
    for project in "${!project_counts[@]}"; do
        echo "  $project: ${project_counts[$project]} 个"
    done
    echo ""
    echo "按优先级分类:"
    for priority in "${!priority_counts[@]}"; do
        echo "  $priority: ${priority_counts[$priority]} 个"
    done

    if [ -n "$PRIORITY_FILTER" ] || [ -n "$TYPE_FILTER" ]; then
        echo ""
        echo "筛选条件:"
        [ -n "$PRIORITY_FILTER" ] && echo "  优先级: $PRIORITY_FILTER"
        [ -n "$TYPE_FILTER" ] && echo "  类型: $TYPE_FILTER"
    fi
}

# 主函数
main() {
    info "开始批量镜像缓存任务..."
    info "镜像清单: $IMAGES_LIST"
    [ -n "$PRIORITY_FILTER" ] && info "优先级筛选: $PRIORITY_FILTER"
    [ -n "$TYPE_FILTER" ] && info "类型筛选: $TYPE_FILTER"
    [ "$DRY_RUN" = true ] && info "模式: 预览 (不实际执行)"

    echo ""

    # 解析镜像清单
    local images_to_cache
    IFS=$'\n' read -r -d '' -a images_to_cache < <(parse_images_list && printf '\0')

    if [ ${#images_to_cache[@]} -eq 0 ]; then
        warning "没有找到符合条件的镜像"
        exit 0
    fi

    # 显示统计信息
    show_statistics

    echo ""
    info "准备缓存 ${#images_to_cache[@]} 个镜像"

    if [ "$DRY_RUN" = false ]; then
        # 并发缓存镜像
        cache_images_parallel "${images_to_cache[@]}"
    else
        echo ""
        echo "预览模式 - 将要缓存的镜像:"
        for image_info in "${images_to_cache[@]}"; do
            local image_full=$(echo "$image_info" | cut -d'|' -f1)
            local target_project=$(echo "$image_info" | cut -d'|' -f2)
            local description=$(echo "$image_info" | cut -d'|' -f3)
            echo "  $image_full -> $target_project ($description)"
        done
    fi

    echo ""
    success "批量镜像缓存任务完成!"
    echo ""
    echo "📝 日志文件: $LOG_FILE"
    echo "🔗 Harbor Web: https://192.168.1.83:8443"
    echo "👤 登录信息: admin / admin123"
}

# 执行主函数
main "$@"