'commit'

2026-02-05 16:55:32 +08:00
parent 1ad4605462
commit ff00bf17fa
10 changed files with 522 additions and 150 deletions
--- a/DataX/run_jobs_full_doris.sh
+++ b/DataX/run_jobs_full_doris.sh
@@ -91,8 +91,25 @@ for JOB in "${JOBS[@]}"; do
    # 记录开始时间（用于计算耗时）
    START_TIME=$(date +%s)
    
-    # 执行任务 (添加 -p 参数传递变量)
-    /usr/bin/python "$DATAX_PY" -p "$PARAMS" "$JOB"
+    # 构造 Java 命令 (绕过 datax.py 以避免环境兼容问题)
+    CLASS_PATH="$DATAX_HOME/lib/*:$DATAX_HOME/conf:."
+    
+    # 构造 JVM 参数 (可根据服务器配置调整堆内存)
+    JVM_OPTS="-server -Xms1g -Xmx1g -XX:+HeapDumpOnOutOfMemoryError"
+    
+    # 执行 DataX
+    java $JVM_OPTS -classpath "$CLASS_PATH" \
+        -Dfile.encoding=UTF-8 \
+        -Dlogback.statusListenerClass=ch.qos.logback.core.status.NopStatusListener \
+        -Djava.security.egd=file:///dev/urandom \
+        -Ddatax.home="$DATAX_HOME" \
+        -Dlogback.configurationFile="$DATAX_HOME/conf/logback.xml" \
+        $PARAMS \
+        com.alibaba.datax.core.Engine \
+        -mode standalone \
+        -jobid -1 \
+        -job "$JOB"
+    
    EXIT_CODE=$?
    
    # 计算耗时
@@ -191,3 +208,4 @@ if [ ${#TASK_DURATIONS[@]} -gt 0 ]; then
 fi

 echo "=========================="
+
--- a/DataX/run_jobs_full_mysql.sh
+++ b/DataX/run_jobs_full_mysql.sh
@@ -0,0 +1,180 @@
+#!/bin/bash
+export PATH=$PATH:/usr/local/bin:/usr/bin:/bin:/usr/sbin:/sbin
+[ -f /etc/profile ] && . /etc/profile
+[ -f ~/.bash_profile ] && . ~/.bash_profile
+[ -f ~/.profile ] && . ~/.profile
+
+DATAX_HOME="/usr/local/datax"
+SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )"
+CONF_DIR="$SCRIPT_DIR/json_full"
+BIN_DIR="$DATAX_HOME/bin"
+DATAX_PY="$BIN_DIR/datax.py"
+
+JOBS=(
+    "t_equipment_charge_order.json"
+    "t_equipment_charge_order_detail.json"
+    "t_account_recharge.json"
+    "t_account_water.json"
+    "t_car.json"
+    "t_company.json"
+    "t_company_info_value.json"
+    "t_connector.json"
+    "t_equipment.json"
+    "t_station.json"
+    "t_ext_hurry_quit.json"
+    "t_time_day.json"
+    "t_user.json"
+    "t_user_account.json"
+    "t_user_upload_fault.json"
+)
+
+# 源端保持与现有 DataX 配置一致
+# 目标为 MySQL：10.10.14.210:22066 数据库 ylt 用户 ylt 密码 Ycharge666
+# 同时启用 rewriteBatchedStatements 以获得真正的批量写入性能
+PARAMS="-Dsrc_user=ylt -Dsrc_pwd=Ycharge666 -Dsrc_jdbc=jdbc:mysql://rm-bp1ux6tuk49er80t9xo.mysql.rds.aliyuncs.com:3306/yltcharge -Ddest_mysql_user=ylt -Ddest_mysql_pwd=Ycharge666 -Ddest_mysql_jdbc=jdbc:mysql://10.10.14.210:22066/yltcharge?useUnicode=true&characterEncoding=UTF-8&useSSL=false&rewriteBatchedStatements=true&autoReconnect=true&failOverReadOnly=false"
+
+SCRIPT_START_TIME=$(date '+%Y-%m-%d %H:%M:%S')
+SCRIPT_START_TIMESTAMP=$(date +%s)
+
+echo "DataX MySQL全量同步脚本 (MySQL -> MySQL)"
+echo "====================================="
+echo "DataX路径: $DATAX_PY"
+echo "配置文件目录: $CONF_DIR"
+echo "任务数量: ${#JOBS[@]}"
+echo "脚本开始时间: $SCRIPT_START_TIME"
+echo "策略: 每张表 TRUNCATE 后以 INSERT 批量写入"
+echo "====================================="
+
+cd "$CONF_DIR" || { echo "错误: 无法进入配置文件目录 $CONF_DIR"; exit 1; }
+
+SUCCESS_COUNT=0
+FAIL_COUNT=0
+TOTAL=${#JOBS[@]}
+CURRENT=0
+
+for JOB in "${JOBS[@]}"; do
+    CURRENT=$((CURRENT + 1))
+    echo "任务 [$CURRENT/$TOTAL] $JOB"
+    echo "----------------------------------------"
+
+    if [ ! -f "$JOB" ]; then
+        echo "✗ 错误: 文件不存在 - $JOB"
+        FAIL_COUNT=$((FAIL_COUNT + 1))
+        echo "----------------------------------------"
+        continue
+    fi
+
+    START_TIME=$(date +%s)
+
+    TMP_FILE="/tmp/datax_mysql_full_${JOB}"
+    /usr/bin/python - <<'PY' "$JOB" "$TMP_FILE"
+import json, sys, re
+src_path = sys.argv[1]
+dst_path = sys.argv[2]
+
+with open(src_path, 'r', encoding='utf-8') as f:
+    data = json.load(f)
+
+unit = data['job']['content'][0]
+reader = unit.get('reader', {})
+writer = unit.get('writer', {})
+rp = reader.get('parameter', {})
+wp = writer.get('parameter', {})
+
+# 获取表名：优先从原 writer.connection.table 获取；否则从 reader.connection.table；最后从 querySql 解析
+table_name = None
+try:
+    table_name = wp.get('connection', [{}])[0].get('table', [None])[0]
+except Exception:
+    table_name = None
+if not table_name:
+    try:
+        table_name = rp.get('connection', [{}])[0].get('table', [None])[0]
+    except Exception:
+        table_name = None
+if not table_name:
+    q = rp.get('connection', [{}])[0].get('querySql', [None])[0]
+    if q:
+        m = re.search(r'FROM\\s+`?(\\w+)`?', q, re.IGNORECASE)
+        if m:
+            table_name = m.group(1)
+
+if not table_name:
+    raise RuntimeError("无法确定目标表名，请检查配置: %s" % src_path)
+
+# 列：从原 writer.column 优先获取，否则回退 reader.column
+columns = wp.get('column') or rp.get('column')
+if not columns:
+    raise RuntimeError("无法确定列列表，请检查配置: %s" % src_path)
+
+new_writer = {
+    "name": "mysqlwriter",
+    "parameter": {
+        "connection": [
+            {
+                "jdbcUrl": "${dest_mysql_jdbc}",
+                "table": [table_name]
+            }
+        ],
+        "username": "${dest_mysql_user}",
+        "password": "${dest_mysql_pwd}",
+        "column": columns,
+        "writeMode": "insert",
+        "batchSize": 2000,
+        "preSql": [f"TRUNCATE TABLE `{table_name}`"],
+        "postSql": []
+    }
+}
+
+unit['writer'] = new_writer
+
+with open(dst_path, 'w', encoding='utf-8') as f:
+    json.dump(data, f, ensure_ascii=False, indent=4)
+PY
+
+    if [ $? -ne 0 ]; then
+        echo "✗ 错误: 生成 MySQL Writer 配置失败 - $JOB"
+        FAIL_COUNT=$((FAIL_COUNT + 1))
+        echo "----------------------------------------"
+        continue
+    fi
+
+    # 构造 Java 命令 (绕过 datax.py 以避免环境兼容问题)
+    CLASS_PATH="$DATAX_HOME/lib/*:$DATAX_HOME/conf:."
+    
+    # 构造 JVM 参数 (可根据服务器配置调整堆内存)
+    JVM_OPTS="-server -Xms1g -Xmx1g -XX:+HeapDumpOnOutOfMemoryError"
+    
+    # 执行 DataX
+    java $JVM_OPTS -classpath "$CLASS_PATH" \
+        -Dfile.encoding=UTF-8 \
+        -Dlogback.statusListenerClass=ch.qos.logback.core.status.NopStatusListener \
+        -Djava.security.egd=file:///dev/urandom \
+        -Ddatax.home="$DATAX_HOME" \
+        -Dlogback.configurationFile="$DATAX_HOME/conf/logback.xml" \
+        $PARAMS \
+        com.alibaba.datax.core.Engine \
+        -mode standalone \
+        -jobid -1 \
+        -job "$TMP_FILE"
+    
+    EXIT_CODE=$?
+
+    END_TIME=$(date +%s)
+    DURATION=$((END_TIME - START_TIME))
+
+    if [ $EXIT_CODE -eq 0 ]; then
+        echo "✓ 成功: $JOB 用时 ${DURATION}s"
+        SUCCESS_COUNT=$((SUCCESS_COUNT + 1))
+    else
+        echo "✗ 失败: $JOB 用时 ${DURATION}s (exit=$EXIT_CODE)"
+        FAIL_COUNT=$((FAIL_COUNT + 1))
+    fi
+
+    echo "----------------------------------------"
+done
+
+TOTAL_TIME=$(( $(date +%s) - SCRIPT_START_TIMESTAMP ))
+echo "完成: 成功 $SUCCESS_COUNT, 失败 $FAIL_COUNT, 总耗时 ${TOTAL_TIME}s"
+exit $([ $FAIL_COUNT -eq 0 ] && echo 0 || echo 1)
+
--- a/DataX/run_jobs_inc_doris.sh
+++ b/DataX/run_jobs_inc_doris.sh
@@ -93,8 +93,25 @@ for JOB in "${JOBS[@]}"; do
    # 记录开始时间（用于计算耗时）
    START_TIME=$(date +%s)
    
-    # 执行任务 (添加 -p 参数传递变量)
-    /usr/bin/python "$DATAX_PY" -p "$PARAMS" "$JOB"
+    # 构造 Java 命令 (绕过 datax.py 以避免环境兼容问题)
+    CLASS_PATH="$DATAX_HOME/lib/*:$DATAX_HOME/conf:."
+    
+    # 构造 JVM 参数 (可根据服务器配置调整堆内存)
+    JVM_OPTS="-server -Xms1g -Xmx1g -XX:+HeapDumpOnOutOfMemoryError"
+    
+    # 执行 DataX
+    java $JVM_OPTS -classpath "$CLASS_PATH" \
+        -Dfile.encoding=UTF-8 \
+        -Dlogback.statusListenerClass=ch.qos.logback.core.status.NopStatusListener \
+        -Djava.security.egd=file:///dev/urandom \
+        -Ddatax.home="$DATAX_HOME" \
+        -Dlogback.configurationFile="$DATAX_HOME/conf/logback.xml" \
+        $PARAMS \
+        com.alibaba.datax.core.Engine \
+        -mode standalone \
+        -jobid -1 \
+        -job "$JOB"
+    
    EXIT_CODE=$?
    
    # 计算耗时
@@ -182,3 +199,4 @@ if [ ${#TASK_DURATIONS[@]} -gt 0 ]; then
 fi

 echo "=========================="
+
--- a/DataX/run_jobs_inc_mysql.sh
+++ b/DataX/run_jobs_inc_mysql.sh
@@ -0,0 +1,178 @@
+#!/bin/bash
+export PATH=$PATH:/usr/local/bin:/usr/bin:/bin:/usr/sbin:/sbin
+[ -f /etc/profile ] && . /etc/profile
+[ -f ~/.bash_profile ] && . ~/.bash_profile
+[ -f ~/.profile ] && . ~/.profile
+
+DATAX_HOME="/usr/local/datax"
+SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )"
+CONF_DIR="$SCRIPT_DIR/json_inc"
+BIN_DIR="$DATAX_HOME/bin"
+DATAX_PY="$BIN_DIR/datax.py"
+
+JOBS=(
+    "t_equipment_charge_order.json"
+    "t_equipment_charge_order_detail.json"
+    "t_account_recharge.json"
+    "t_account_water.json"
+    "t_car.json"
+    "t_company.json"
+    "t_company_info_value.json"
+    "t_connector.json"
+    "t_equipment.json"
+    "t_station.json"
+    "t_ext_hurry_quit.json"
+    "t_time_day.json"
+    "t_user.json"
+    "t_user_account.json"
+    "t_user_upload_fault.json"
+)
+
+# 源端保持与现有 DataX 配置一致
+# 目标为 MySQL：10.10.14.210:22066 数据库 ylt 用户 ylt 密码 Ycharge666
+# 增量同步使用 REPLACE 实现覆盖更新
+PARAMS="-Dsrc_user=ylt -Dsrc_pwd=Ycharge666 -Dsrc_jdbc=jdbc:mysql://rm-bp1ux6tuk49er80t9xo.mysql.rds.aliyuncs.com:3306/yltcharge -Ddest_mysql_user=ylt -Ddest_mysql_pwd=Ycharge666 -Ddest_mysql_jdbc=jdbc:mysql://10.10.14.210:22066/yltcharge?useUnicode=true&characterEncoding=UTF-8&useSSL=false&rewriteBatchedStatements=true&autoReconnect=true&failOverReadOnly=false"
+
+SCRIPT_START_TIME=$(date '+%Y-%m-%d %H:%M:%S')
+SCRIPT_START_TIMESTAMP=$(date +%s)
+
+echo "DataX MySQL增量同步脚本 (MySQL -> MySQL)"
+echo "====================================="
+echo "DataX路径: $DATAX_PY"
+echo "配置文件目录: $CONF_DIR"
+echo "任务数量: ${#JOBS[@]}"
+echo "脚本开始时间: $SCRIPT_START_TIME"
+echo "策略: 每次同步最近10000条(由 reader 配置决定)，目标端使用 REPLACE 实现覆盖更新"
+echo "====================================="
+
+cd "$CONF_DIR" || { echo "错误: 无法进入配置文件目录 $CONF_DIR"; exit 1; }
+
+SUCCESS_COUNT=0
+FAIL_COUNT=0
+TOTAL=${#JOBS[@]}
+CURRENT=0
+
+for JOB in "${JOBS[@]}"; do
+    CURRENT=$((CURRENT + 1))
+    echo "任务 [$CURRENT/$TOTAL] $JOB"
+    echo "----------------------------------------"
+
+    if [ ! -f "$JOB" ]; then
+        echo "✗ 错误: 文件不存在 - $JOB"
+        FAIL_COUNT=$((FAIL_COUNT + 1))
+        echo "----------------------------------------"
+        continue
+    fi
+
+    START_TIME=$(date +%s)
+
+    TMP_FILE="/tmp/datax_mysql_inc_${JOB}"
+    /usr/bin/python - <<'PY' "$JOB" "$TMP_FILE"
+import json, sys, re
+src_path = sys.argv[1]
+dst_path = sys.argv[2]
+
+with open(src_path, 'r', encoding='utf-8') as f:
+    data = json.load(f)
+
+unit = data['job']['content'][0]
+reader = unit.get('reader', {})
+writer = unit.get('writer', {})
+rp = reader.get('parameter', {})
+wp = writer.get('parameter', {})
+
+table_name = None
+try:
+    table_name = wp.get('connection', [{}])[0].get('table', [None])[0]
+except Exception:
+    table_name = None
+if not table_name:
+    try:
+        table_name = rp.get('connection', [{}])[0].get('table', [None])[0]
+    except Exception:
+        table_name = None
+if not table_name:
+    q = rp.get('connection', [{}])[0].get('querySql', [None])[0]
+    if q:
+        m = re.search(r'FROM\\s+`?(\\w+)`?', q, re.IGNORECASE)
+        if m:
+            table_name = m.group(1)
+
+if not table_name:
+    raise RuntimeError("无法确定目标表名，请检查配置: %s" % src_path)
+
+columns = wp.get('column') or rp.get('column')
+if not columns:
+    raise RuntimeError("无法确定列列表，请检查配置: %s" % src_path)
+
+new_writer = {
+    "name": "mysqlwriter",
+    "parameter": {
+        "connection": [
+            {
+                "jdbcUrl": "${dest_mysql_jdbc}",
+                "table": [table_name]
+            }
+        ],
+        "username": "${dest_mysql_user}",
+        "password": "${dest_mysql_pwd}",
+        "column": columns,
+        "writeMode": "replace",
+        "batchSize": 2000,
+        "preSql": [],
+        "postSql": []
+    }
+}
+
+unit['writer'] = new_writer
+
+with open(dst_path, 'w', encoding='utf-8') as f:
+    json.dump(data, f, ensure_ascii=False, indent=4)
+PY
+
+    if [ $? -ne 0 ]; then
+        echo "✗ 错误: 生成 MySQL Writer 配置失败 - $JOB"
+        FAIL_COUNT=$((FAIL_COUNT + 1))
+        echo "----------------------------------------"
+        continue
+    fi
+
+    # 构造 Java 命令 (绕过 datax.py 以避免环境兼容问题)
+    CLASS_PATH="$DATAX_HOME/lib/*:$DATAX_HOME/conf:."
+    
+    # 构造 JVM 参数 (可根据服务器配置调整堆内存)
+    JVM_OPTS="-server -Xms1g -Xmx1g -XX:+HeapDumpOnOutOfMemoryError"
+    
+    # 执行 DataX
+    java $JVM_OPTS -classpath "$CLASS_PATH" \
+        -Dfile.encoding=UTF-8 \
+        -Dlogback.statusListenerClass=ch.qos.logback.core.status.NopStatusListener \
+        -Djava.security.egd=file:///dev/urandom \
+        -Ddatax.home="$DATAX_HOME" \
+        -Dlogback.configurationFile="$DATAX_HOME/conf/logback.xml" \
+        $PARAMS \
+        com.alibaba.datax.core.Engine \
+        -mode standalone \
+        -jobid -1 \
+        -job "$TMP_FILE"
+    
+    EXIT_CODE=$?
+
+    END_TIME=$(date +%s)
+    DURATION=$((END_TIME - START_TIME))
+
+    if [ $EXIT_CODE -eq 0 ]; then
+        echo "✓ 成功: $JOB 用时 ${DURATION}s"
+        SUCCESS_COUNT=$((SUCCESS_COUNT + 1))
+    else
+        echo "✗ 失败: $JOB 用时 ${DURATION}s (exit=$EXIT_CODE)"
+        FAIL_COUNT=$((FAIL_COUNT + 1))
+    fi
+
+    echo "----------------------------------------"
+done
+
+TOTAL_TIME=$(( $(date +%s) - SCRIPT_START_TIMESTAMP ))
+echo "完成: 成功 $SUCCESS_COUNT, 失败 $FAIL_COUNT, 总耗时 ${TOTAL_TIME}s"
+exit $([ $FAIL_COUNT -eq 0 ] && echo 0 || echo 1)
+
--- a/DataX/start_cron.sh
+++ b/DataX/start_cron.sh
@@ -1,86 +0,0 @@
-#!/bin/bash
-
-# ==========================================
-# DataX 增量同步定时任务配置脚本
-# 适用系统: Rocky Linux 9 / CentOS / RHEL
-# 功能: 添加每10分钟执行一次的 crontab 任务
-# ==========================================
-
-# 1. 基础配置
-# 假设您将整个文件夹上传到了 /usr/local/datax
-WORK_DIR="/usr/local/datax"
-SCRIPT_NAME="run_jobs_inc.sh"
-SCRIPT_PATH="$WORK_DIR/$SCRIPT_NAME"
-# 日志存放位置，建议单独放在 logs 目录
-LOG_FILE="$WORK_DIR/logs/datax_inc_cron.log"
-
-# 2. 检查环境
-echo "正在检查环境..."
-
-# 检查工作目录
-if [ ! -d "$WORK_DIR" ]; then
-    echo "错误: 工作目录 $WORK_DIR 不存在"
-    echo "请先将 DataX 配置相关文件上传至服务器的 $WORK_DIR"
-    exit 1
-fi
-
-# 检查脚本是否存在
-if [ ! -f "$SCRIPT_PATH" ]; then
-    echo "错误: 执行脚本 $SCRIPT_PATH 不存在"
-    echo "请确保 $SCRIPT_NAME 位于 $WORK_DIR 目录下"
-    exit 1
-fi
-
-# 创建日志目录
-if [ ! -d "$(dirname "$LOG_FILE")" ]; then
-    mkdir -p "$(dirname "$LOG_FILE")"
-    echo "创建日志目录: $(dirname "$LOG_FILE")"
-fi
-
-# 3. 赋予执行权限
-echo "正在赋予脚本执行权限..."
-chmod +x "$SCRIPT_PATH"
-
-# 4. 配置 Crontab
-# 任务定义: 每10分钟执行一次 (*/10)
-# >> $LOG_FILE 2>&1 : 将标准输出和错误输出都追加写入日志文件
-CRON_CMD="*/10 * * * * /bin/bash $SCRIPT_PATH >> $LOG_FILE 2>&1"
-
-# 检查任务是否已存在 (避免重复添加)
-# 使用 grep 查找包含脚本路径的行
-EXISTING_JOB=$(crontab -l 2>/dev/null | grep "$SCRIPT_PATH")
-
-if [ -n "$EXISTING_JOB" ]; then
-    echo "警告: 检测到该脚本的定时任务已存在:"
-    echo "  $EXISTING_JOB"
-    echo "----------------------------------------"
-    read -p "是否先删除旧任务再重新添加? (y/n): " -n 1 -r
-    echo
-    if [[ ! $REPLY =~ ^[Yy]$ ]]; then
-        echo "已取消操作，未修改 Crontab。"
-        exit 0
-    fi
-    
-    # 移除旧任务 (通过 grep -v 反向过滤掉包含脚本路径的行)
-    # 注意: 这会保留其他不相关的定时任务
-    crontab -l 2>/dev/null | grep -v "$SCRIPT_PATH" | crontab -
-    echo "旧任务已移除"
-fi
-
-# 添加新任务
-# (crontab -l; echo "new job") | crontab - 这种写法可以保留原有任务并追加新任务
-(crontab -l 2>/dev/null; echo "$CRON_CMD") | crontab -
-
-# 5. 验证与提示
-echo "----------------------------------------"
-echo "✅ 定时任务设置成功!"
-echo "----------------------------------------"
-echo "当前用户的 Crontab 列表:"
-crontab -l
-echo "----------------------------------------"
-echo "执行策略: 每10分钟执行一次"
-echo "日志文件: $LOG_FILE"
-echo "----------------------------------------"
-echo "提示: 请确保 crond 服务正在运行"
-echo "检查命令: systemctl status crond"
-echo "启动命令: systemctl start crond"
--- a/DataX/start_cron_doris_inc.sh
+++ b/DataX/start_cron_doris_inc.sh
@@ -0,0 +1,33 @@
+#!/bin/bash
+WORK_DIR="/usr/local/datax"
+SCRIPT_NAME="run_jobs_inc_doris.sh"
+SCRIPT_PATH="$WORK_DIR/$SCRIPT_NAME"
+LOG_FILE="$WORK_DIR/logs/datax_inc_doris_cron.log"
+
+export PATH=$PATH:/usr/local/bin:/usr/bin:/bin:/usr/sbin:/sbin
+[ -f /etc/profile ] && . /etc/profile
+[ -f ~/.bash_profile ] && . ~/.bash_profile
+[ -f ~/.profile ] && . ~/.profile
+
+echo "正在检查环境..."
+if [ ! -d "$WORK_DIR" ]; then
+    echo "错误: 工作目录 $WORK_DIR 不存在"; exit 1
+fi
+if [ ! -f "$SCRIPT_PATH" ]; then
+    echo "错误: 执行脚本 $SCRIPT_PATH 不存在"; exit 1
+fi
+if [ ! -d "$(dirname "$LOG_FILE")" ]; then
+    mkdir -p "$(dirname "$LOG_FILE")"
+fi
+
+chmod +x "$SCRIPT_PATH"
+CRON_CMD="*/10 * * * * /bin/bash $SCRIPT_PATH >> $LOG_FILE 2>&1"
+
+EXISTING_JOB=$(crontab -l 2>/dev/null | grep "$SCRIPT_PATH")
+if [ -n "$EXISTING_JOB" ]; then
+    crontab -l 2>/dev/null | grep -v "$SCRIPT_PATH" | crontab -
+fi
+(crontab -l 2>/dev/null; echo "$CRON_CMD") | crontab -
+
+echo "✅ Doris 增量定时任务设置成功"
+crontab -l
--- a/DataX/start_cron_mysql_inc.sh
+++ b/DataX/start_cron_mysql_inc.sh
@@ -0,0 +1,33 @@
+#!/bin/bash
+WORK_DIR="/usr/local/datax"
+SCRIPT_NAME="run_jobs_inc_mysql.sh"
+SCRIPT_PATH="$WORK_DIR/$SCRIPT_NAME"
+LOG_FILE="$WORK_DIR/logs/datax_inc_mysql_cron.log"
+
+export PATH=$PATH:/usr/local/bin:/usr/bin:/bin:/usr/sbin:/sbin
+[ -f /etc/profile ] && . /etc/profile
+[ -f ~/.bash_profile ] && . ~/.bash_profile
+[ -f ~/.profile ] && . ~/.profile
+
+echo "正在检查环境..."
+if [ ! -d "$WORK_DIR" ]; then
+    echo "错误: 工作目录 $WORK_DIR 不存在"; exit 1
+fi
+if [ ! -f "$SCRIPT_PATH" ]; then
+    echo "错误: 执行脚本 $SCRIPT_PATH 不存在"; exit 1
+fi
+if [ ! -d "$(dirname "$LOG_FILE")" ]; then
+    mkdir -p "$(dirname "$LOG_FILE")"
+fi
+
+chmod +x "$SCRIPT_PATH"
+CRON_CMD="*/10 * * * * /bin/bash $SCRIPT_PATH >> $LOG_FILE 2>&1"
+
+EXISTING_JOB=$(crontab -l 2>/dev/null | grep "$SCRIPT_PATH")
+if [ -n "$EXISTING_JOB" ]; then
+    crontab -l 2>/dev/null | grep -v "$SCRIPT_PATH" | crontab -
+fi
+(crontab -l 2>/dev/null; echo "$CRON_CMD") | crontab -
+
+echo "✅ MySQL 增量定时任务设置成功"
+crontab -l
--- a/DataX/stop_cron.sh
+++ b/DataX/stop_cron.sh
@@ -1,60 +0,0 @@
-#!/bin/bash
-
-# ==========================================
-# DataX 增量同步定时任务停止脚本
-# 适用系统: Rocky Linux 9 / CentOS / RHEL
-# 功能: 移除 run_jobs_inc.sh 的 crontab 任务
-# 场景: 全量同步前防止增量任务干扰
-# ==========================================
-
-# 1. 基础配置 (需与 start_cron.sh 保持一致以确保匹配正确)
-WORK_DIR="/usr/local/datax"
-SCRIPT_NAME="run_jobs_inc.sh"
-SCRIPT_PATH="$WORK_DIR/$SCRIPT_NAME"
-
-# 2. 检查任务是否存在
-echo "正在检查定时任务..."
-
-# 使用 grep 查找包含脚本路径的行
-EXISTING_JOB=$(crontab -l 2>/dev/null | grep "$SCRIPT_PATH")
-
-if [ -z "$EXISTING_JOB" ]; then
-    echo "----------------------------------------"
-    echo "提示: 未发现该脚本的定时任务，无需停止。"
-    echo "目标脚本: $SCRIPT_PATH"
-    echo "----------------------------------------"
-    exit 0
-fi
-
-echo "发现正在运行的定时任务:"
-echo "  $EXISTING_JOB"
-echo "----------------------------------------"
-
-# 3. 移除任务
-echo "正在移除任务..."
-
-# 备份当前的 crontab
-BACKUP_FILE="/tmp/crontab_backup_$(date +%Y%m%d_%H%M%S).txt"
-crontab -l > "$BACKUP_FILE" 2>/dev/null
-echo "已备份当前 Crontab 到: $BACKUP_FILE"
-
-# 核心逻辑: 移除包含脚本路径的行
-# grep -v "$SCRIPT_PATH" : 排除包含脚本路径的行
-# crontab - : 将过滤后的内容重新写入 crontab
-crontab -l 2>/dev/null | grep -v "$SCRIPT_PATH" | crontab -
-
-# 4. 验证结果
-REMAINING_JOB=$(crontab -l 2>/dev/null | grep "$SCRIPT_PATH")
-
-if [ -z "$REMAINING_JOB" ]; then
-    echo "----------------------------------------"
-    echo "✅ 增量同步定时任务已成功停止 (移除)!"
-    echo "----------------------------------------"
-    echo "当前用户的 Crontab 列表:"
-    crontab -l
-    echo "----------------------------------------"
-    echo "现在您可以安全地执行全量同步操作了。"
-else
-    echo "❌ 停止失败，任务仍然存在。请尝试手动编辑: crontab -e"
-    exit 1
-fi
--- a/DataX/stop_cron_doris_inc.sh
+++ b/DataX/stop_cron_doris_inc.sh
@@ -0,0 +1,29 @@
+#!/bin/bash
+WORK_DIR="/usr/local/datax"
+SCRIPT_NAME="run_jobs_inc_doris.sh"
+SCRIPT_PATH="$WORK_DIR/$SCRIPT_NAME"
+
+export PATH=$PATH:/usr/local/bin:/usr/bin:/bin:/usr/sbin:/sbin
+[ -f /etc/profile ] && . /etc/profile
+[ -f ~/.bash_profile ] && . ~/.bash_profile
+[ -f ~/.profile ] && . ~/.profile
+
+echo "正在检查定时任务..."
+EXISTING_JOB=$(crontab -l 2>/dev/null | grep "$SCRIPT_PATH")
+if [ -z "$EXISTING_JOB" ]; then
+    echo "提示: 未发现 Doris 增量任务，无需停止。"
+    exit 0
+fi
+
+BACKUP_FILE="/tmp/crontab_backup_$(date +%Y%m%d_%H%M%S).txt"
+crontab -l > "$BACKUP_FILE" 2>/dev/null
+crontab -l 2>/dev/null | grep -v "$SCRIPT_PATH" | crontab -
+
+REMAINING_JOB=$(crontab -l 2>/dev/null | grep "$SCRIPT_PATH")
+if [ -z "$REMAINING_JOB" ]; then
+    echo "✅ Doris 增量定时任务已停止"
+    crontab -l
+else
+    echo "❌ 停止失败，请手动执行: crontab -e"
+    exit 1
+fi
--- a/DataX/stop_cron_mysql_inc.sh
+++ b/DataX/stop_cron_mysql_inc.sh
@@ -0,0 +1,29 @@
+#!/bin/bash
+WORK_DIR="/usr/local/datax"
+SCRIPT_NAME="run_jobs_inc_mysql.sh"
+SCRIPT_PATH="$WORK_DIR/$SCRIPT_NAME"
+
+export PATH=$PATH:/usr/local/bin:/usr/bin:/bin:/usr/sbin:/sbin
+[ -f /etc/profile ] && . /etc/profile
+[ -f ~/.bash_profile ] && . ~/.bash_profile
+[ -f ~/.profile ] && . ~/.profile
+
+echo "正在检查定时任务..."
+EXISTING_JOB=$(crontab -l 2>/dev/null | grep "$SCRIPT_PATH")
+if [ -z "$EXISTING_JOB" ]; then
+    echo "提示: 未发现 MySQL 增量任务，无需停止。"
+    exit 0
+fi
+
+BACKUP_FILE="/tmp/crontab_backup_$(date +%Y%m%d_%H%M%S).txt"
+crontab -l > "$BACKUP_FILE" 2>/dev/null
+crontab -l 2>/dev/null | grep -v "$SCRIPT_PATH" | crontab -
+
+REMAINING_JOB=$(crontab -l 2>/dev/null | grep "$SCRIPT_PATH")
+if [ -z "$REMAINING_JOB" ]; then
+    echo "✅ MySQL 增量定时任务已停止"
+    crontab -l
+else
+    echo "❌ 停止失败，请手动执行: crontab -e"
+    exit 1
+fi