镜像制作

2025-11-24 11:50:15 +08:00
parent 12592c5a24
commit 07bd166257
53 changed files with 3822 additions and 2140 deletions
--- a/schoolNewsServ/.bin/mysql/sql/reInit.sh
+++ b/schoolNewsServ/.bin/mysql/sql/reInit.sh
@@ -14,12 +14,12 @@ YELLOW='\033[1;33m'
 BLUE='\033[0;34m'
 NC='\033[0m' # No Color

-# 数据库配置
-DB_HOST="localhost"
-DB_PORT="3306"
-DB_USER="root"
-DB_PASSWORD="123456"
-DB_NAME="school_news"
+# 数据库配置（优先使用环境变量）
+DB_HOST="${DB_HOST:-localhost}"
+DB_PORT="${DB_PORT:-3306}"
+DB_USER="${DB_USER:-root}"
+DB_PASSWORD="${DB_PASSWORD:-123456}"
+DB_NAME="${DB_NAME:-school_news}"

 # 脚本目录
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
@@ -101,19 +101,6 @@ execute_init_script() {
 import_sensitive_words() {
    print_message $BLUE "开始导入敏感词数据..."
    
-    # 检查conda是否可用
-    if ! command -v conda &> /dev/null; then
-        print_message $YELLOW "conda命令未找到，跳过敏感词导入"
-        return 0
-    fi
-    
-    # 检查schoolNewsCrawler环境是否存在
-    if ! conda env list | grep -q "schoolNewsCrawler"; then
-        print_message $YELLOW "conda环境 'schoolNewsCrawler' 不存在，跳过敏感词导入"
-        print_message $YELLOW "提示: 可以使用以下命令创建环境: conda create -n schoolNewsCrawler python=3.10"
-        return 0
-    fi
-    
    # 切换到敏感词脚本目录
    local sensitive_dir="$SCRIPT_DIR/sensitiveData"
    if [ ! -d "$sensitive_dir" ]; then
@@ -121,25 +108,63 @@ import_sensitive_words() {
        return 0
    fi
    
-    if [ ! -f "$sensitive_dir/writeWord.py" ]; then
-        print_message $YELLOW "敏感词脚本不存在: $sensitive_dir/writeWord.py"
+    # 检查Shell脚本是否存在
+    if [ -f "$sensitive_dir/importSensitiveWords.sh" ]; then
+        print_message $BLUE "使用Shell脚本导入敏感词"
+        cd "$sensitive_dir"
+        
+        # 导出数据库配置环境变量
+        export DB_HOST="$DB_HOST"
+        export DB_PORT="$DB_PORT"
+        export DB_USER="$DB_USER"
+        export DB_PASSWORD="$DB_PASSWORD"
+        export DB_NAME="$DB_NAME"
+        export AUTO_CONFIRM=true
+        
+        bash importSensitiveWords.sh -y
+        
+        if [ $? -eq 0 ]; then
+            print_message $GREEN "敏感词数据导入成功"
+        else
+            print_message $YELLOW "敏感词数据导入失败，但不影响系统运行"
+        fi
+        
+        cd "$SCRIPT_DIR"
        return 0
    fi
    
-    print_message $BLUE "激活conda环境: schoolNewsCrawler"
-    cd "$sensitive_dir"
-    
-    # 使用conda run来在指定环境中执行命令，添加-y参数自动确认
-    conda run -n schoolNewsCrawler python writeWord.py -y
-    
-    if [ $? -eq 0 ]; then
-        print_message $GREEN "敏感词数据导入成功"
-    else
-        print_message $YELLOW "敏感词数据导入失败，但不影响系统运行"
+    # 兼容旧的Python脚本（如果Shell脚本不存在）
+    if [ -f "$sensitive_dir/writeWord.py" ]; then
+        print_message $YELLOW "使用Python脚本导入敏感词（建议使用Shell版本）"
+        
+        # 检查conda是否可用
+        if ! command -v conda &> /dev/null; then
+            print_message $YELLOW "conda命令未找到，跳过敏感词导入"
+            return 0
+        fi
+        
+        # 检查schoolNewsCrawler环境是否存在
+        if ! conda env list | grep -q "schoolNewsCrawler"; then
+            print_message $YELLOW "conda环境 'schoolNewsCrawler' 不存在，跳过敏感词导入"
+            return 0
+        fi
+        
+        cd "$sensitive_dir"
+        conda run -n schoolNewsCrawler python writeWord.py -y
+        
+        if [ $? -eq 0 ]; then
+            print_message $GREEN "敏感词数据导入成功"
+        else
+            print_message $YELLOW "敏感词数据导入失败，但不影响系统运行"
+        fi
+        
+        cd "$SCRIPT_DIR"
+        return 0
    fi
    
-    # 返回脚本目录
-    cd "$SCRIPT_DIR"
+    # 如果两个脚本都不存在
+    print_message $YELLOW "敏感词导入脚本不存在，跳过导入"
+    print_message $YELLOW "提示: 可以使用 importSensitiveWords.sh (推荐) 或 writeWord.py"
 }

 # 验证初始化结果
--- a/schoolNewsServ/.bin/mysql/sql/sensitiveData/importSensitiveWords.sh
+++ b/schoolNewsServ/.bin/mysql/sql/sensitiveData/importSensitiveWords.sh
@@ -0,0 +1,182 @@
+#!/bin/bash
+
+##############################################
+# 敏感词批量导入脚本 (纯Shell实现)
+# 功能：从 sensitive_word_dict.txt 读取敏感词并导入数据库
+# 优势：不需要Python环境，只需要MySQL客户端
+##############################################
+
+set -e
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m'
+
+log_info() {
+    echo -e "${GREEN}[INFO]${NC} $1"
+}
+
+log_warn() {
+    echo -e "${YELLOW}[WARN]${NC} $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+# 数据库配置
+DB_HOST="${DB_HOST:-localhost}"
+DB_PORT="${DB_PORT:-3306}"
+DB_USER="${DB_USER:-root}"
+DB_PASSWORD="${DB_PASSWORD:-123456}"
+DB_NAME="${DB_NAME:-school_news}"
+
+# 脚本目录
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+DICT_FILE="${SCRIPT_DIR}/sensitive_word_dict.txt"
+
+echo "=================================================="
+echo "敏感词批量导入工具 (Shell版本)"
+echo "=================================================="
+log_info "数据库: ${DB_HOST}:${DB_PORT}/${DB_NAME}"
+log_info "敏感词文件: ${DICT_FILE}"
+echo "=================================================="
+echo ""
+
+# 检查敏感词文件
+if [ ! -f "${DICT_FILE}" ]; then
+    log_error "敏感词文件不存在: ${DICT_FILE}"
+    exit 1
+fi
+
+# 统计敏感词数量
+TOTAL_WORDS=$(grep -v '^$' "${DICT_FILE}" | wc -l)
+log_info "检测到 ${TOTAL_WORDS} 个敏感词"
+
+if [ ${TOTAL_WORDS} -eq 0 ]; then
+    log_warn "敏感词文件为空"
+    exit 0
+fi
+
+# 检查MySQL连接
+log_info "检查数据库连接..."
+if ! mysql -h"${DB_HOST}" -P"${DB_PORT}" -u"${DB_USER}" -p"${DB_PASSWORD}" -e "SELECT 1;" &>/dev/null; then
+    log_error "数据库连接失败"
+    exit 1
+fi
+log_info "数据库连接成功"
+echo ""
+
+# 确认导入
+log_warn "准备导入 ${TOTAL_WORDS} 个敏感词到数据库"
+log_warn "这将清除现有的 deny 类型敏感词"
+echo ""
+
+# 检查是否是自动模式（通过 -y 参数或环境变量）
+AUTO_CONFIRM=${AUTO_CONFIRM:-false}
+if [ "$1" = "-y" ] || [ "$1" = "--yes" ] || [ "${AUTO_CONFIRM}" = "true" ]; then
+    log_info "自动确认模式，开始导入..."
+else
+    read -p "是否继续？(y/N): " -n 1 -r
+    echo
+    if [[ ! $REPLY =~ ^[Yy]$ ]]; then
+        log_warn "用户取消导入"
+        exit 0
+    fi
+fi
+echo ""
+
+# 开始导入
+log_info "开始导入敏感词..."
+START_TIME=$(date +%s)
+
+# 创建临时SQL文件
+TEMP_SQL=$(mktemp)
+trap "rm -f ${TEMP_SQL}" EXIT
+
+# 生成SQL语句
+log_info "生成SQL语句..."
+cat > "${TEMP_SQL}" <<EOF
+-- 敏感词批量导入
+USE ${DB_NAME};
+
+-- 设置字符集
+SET NAMES utf8mb4;
+
+-- 清除现有的deny类型敏感词
+DELETE FROM tb_sensitive_word WHERE type = 'deny';
+
+-- 批量插入敏感词
+INSERT INTO tb_sensitive_word (word, type) VALUES
+EOF
+
+# 读取敏感词并生成INSERT语句
+COUNTER=0
+while IFS= read -r word || [ -n "$word" ]; do
+    # 跳过空行
+    [ -z "$word" ] && continue
+    
+    # 转义单引号
+    word=$(echo "$word" | sed "s/'/''/g")
+    
+    COUNTER=$((COUNTER + 1))
+    
+    # 添加到SQL（最后一个不加逗号）
+    if [ $COUNTER -eq ${TOTAL_WORDS} ]; then
+        echo "('${word}', 'deny');" >> "${TEMP_SQL}"
+    else
+        echo "('${word}', 'deny')," >> "${TEMP_SQL}"
+    fi
+    
+    # 进度提示（每1000个）
+    if [ $((COUNTER % 1000)) -eq 0 ]; then
+        log_info "已处理 ${COUNTER}/${TOTAL_WORDS} 个敏感词..."
+    fi
+done < "${DICT_FILE}"
+
+# 添加查询语句
+cat >> "${TEMP_SQL}" <<EOF
+
+-- 验证导入结果
+SELECT COUNT(*) AS '导入数量' FROM tb_sensitive_word WHERE type = 'deny';
+EOF
+
+log_info "SQL语句生成完成（${COUNTER}个敏感词）"
+echo ""
+
+# 执行SQL
+log_info "执行数据库导入..."
+if mysql -h"${DB_HOST}" -P"${DB_PORT}" -u"${DB_USER}" -p"${DB_PASSWORD}" < "${TEMP_SQL}"; then
+    END_TIME=$(date +%s)
+    DURATION=$((END_TIME - START_TIME))
+    
+    echo ""
+    echo "=================================================="
+    log_info "导入完成！"
+    log_info "成功导入: ${COUNTER} 个敏感词"
+    log_info "耗时: ${DURATION} 秒"
+    echo "=================================================="
+else
+    log_error "数据库导入失败"
+    exit 1
+fi
+
+# 验证结果
+log_info "验证导入结果..."
+IMPORTED_COUNT=$(mysql -h"${DB_HOST}" -P"${DB_PORT}" -u"${DB_USER}" -p"${DB_PASSWORD}" -D"${DB_NAME}" -sNe \
+    "SELECT COUNT(*) FROM tb_sensitive_word WHERE type = 'deny';")
+
+echo ""
+log_info "数据库中当前有 ${IMPORTED_COUNT} 个 deny 类型敏感词"
+
+if [ "${IMPORTED_COUNT}" -eq "${COUNTER}" ]; then
+    log_info "✅ 验证通过：导入数量与预期一致"
+else
+    log_warn "⚠️  导入数量不匹配：预期 ${COUNTER}，实际 ${IMPORTED_COUNT}"
+fi
+
+echo ""
+log_info "敏感词导入完成！"