diff --git a/notes/Azkaban_Flow_1.0_的使用.md b/notes/Azkaban_Flow_1.0_的使用.md index 0f1b05b..a4b61f4 100644 --- a/notes/Azkaban_Flow_1.0_的使用.md +++ b/notes/Azkaban_Flow_1.0_的使用.md @@ -223,3 +223,6 @@ memCheck.enabled=false + + +
\ No newline at end of file diff --git a/notes/Azkaban_Flow_2.0_的使用.md b/notes/Azkaban_Flow_2.0_的使用.md index ff30338..51e4719 100644 --- a/notes/Azkaban_Flow_2.0_的使用.md +++ b/notes/Azkaban_Flow_2.0_的使用.md @@ -294,3 +294,6 @@ nodes: 1. [Azkaban Flow 2.0 Design](https://github.com/azkaban/azkaban/wiki/Azkaban-Flow-2.0-Design) 2. [Getting started with Azkaban Flow 2.0](https://github.com/azkaban/azkaban/wiki/Getting-started-with-Azkaban-Flow-2.0) + + +
\ No newline at end of file diff --git a/notes/Azkaban简介.md b/notes/Azkaban简介.md index 668fd69..625fe3d 100644 --- a/notes/Azkaban简介.md +++ b/notes/Azkaban简介.md @@ -74,3 +74,6 @@ Azkaban 和 Oozie 都是目前使用最为广泛的工作流调度程序，其 + **配置方面**：Azkaban Flow 1.0 基于 Properties 文件来定义工作流，这个时候的限制可能会多一点。但是在 Flow 2.0 就支持了 YARM。YARM 语法更加灵活简单，著名的微服务框架 Spring Boot 就采用的 YAML 代替了繁重的 XML。 + + +
\ No newline at end of file diff --git a/notes/Flink_Data_Sink.md b/notes/Flink_Data_Sink.md index f77559c..c1ee990 100644 --- a/notes/Flink_Data_Sink.md +++ b/notes/Flink_Data_Sink.md @@ -266,3 +266,6 @@ env.execute(); 2. Streaming Connectors：https://ci.apache.org/projects/flink/flink-docs-release-1.9/dev/connectors/index.html 3. Apache Kafka Connector： https://ci.apache.org/projects/flink/flink-docs-release-1.9/dev/connectors/kafka.html + + +
\ No newline at end of file diff --git a/notes/Flink_Data_Source.md b/notes/Flink_Data_Source.md index a8d065f..ec1bb86 100644 --- a/notes/Flink_Data_Source.md +++ b/notes/Flink_Data_Source.md @@ -282,3 +282,6 @@ bin/kafka-console-producer.sh --broker-list hadoop001:9092 --topic flink-stream- 1. data-sources：https://ci.apache.org/projects/flink/flink-docs-release-1.9/dev/datastream_api.html#data-sources 2. Streaming Connectors：https://ci.apache.org/projects/flink/flink-docs-release-1.9/dev/connectors/index.html 3. Apache Kafka Connector： https://ci.apache.org/projects/flink/flink-docs-release-1.9/dev/connectors/kafka.html + + +
\ No newline at end of file diff --git a/notes/Flink_Data_Transformation.md b/notes/Flink_Data_Transformation.md index 3f5a1c8..9478162 100644 --- a/notes/Flink_Data_Transformation.md +++ b/notes/Flink_Data_Transformation.md @@ -309,3 +309,6 @@ someStream.filter(...).slotSharingGroup("slotSharingGroupName"); ## 参考资料 Flink Operators： https://ci.apache.org/projects/flink/flink-docs-release-1.9/dev/stream/operators/ + + +
\ No newline at end of file diff --git a/notes/Flink_Windows.md b/notes/Flink_Windows.md index 816a6ed..7615f7f 100644 --- a/notes/Flink_Windows.md +++ b/notes/Flink_Windows.md @@ -126,3 +126,6 @@ public WindowedStream countWindow(long size, long slide) { ## 参考资料 Flink Windows： https://ci.apache.org/projects/flink/flink-docs-release-1.9/dev/stream/operators/windows.html + + +
\ No newline at end of file diff --git a/notes/Flink开发环境搭建.md b/notes/Flink开发环境搭建.md index a933e04..1b319cf 100644 --- a/notes/Flink开发环境搭建.md +++ b/notes/Flink开发环境搭建.md @@ -302,3 +302,6 @@ Flink 大多数版本都提供有 Scala 2.11 和 Scala 2.12 两个版本的安 + + +
\ No newline at end of file diff --git a/notes/Flink核心概念综述.md b/notes/Flink核心概念综述.md index 397ecc7..c4ae5a6 100644 --- a/notes/Flink核心概念综述.md +++ b/notes/Flink核心概念综述.md @@ -171,3 +171,6 @@ Flink 的所有组件都基于 Actor System 来进行通讯。Actor system是多 + + +
\ No newline at end of file diff --git a/notes/Flink状态管理与检查点机制.md b/notes/Flink状态管理与检查点机制.md index e5d3da2..d678daa 100644 --- a/notes/Flink状态管理与检查点机制.md +++ b/notes/Flink状态管理与检查点机制.md @@ -368,3 +368,6 @@ state.checkpoints.dir: hdfs://namenode:40010/flink/checkpoints + + +
\ No newline at end of file diff --git a/notes/Flume整合Kafka.md b/notes/Flume整合Kafka.md index 9cc34d1..c1f80dd 100644 --- a/notes/Flume整合Kafka.md +++ b/notes/Flume整合Kafka.md @@ -114,3 +114,6 @@ flume-ng agent \ 可以看到 `flume-kafka` 主题的消费端已经收到了对应的消息：
+ + +
\ No newline at end of file diff --git a/notes/Flume简介及基本使用.md b/notes/Flume简介及基本使用.md index f5f752e..f98c804 100644 --- a/notes/Flume简介及基本使用.md +++ b/notes/Flume简介及基本使用.md @@ -373,3 +373,6 @@ flume-ng agent \ 可以看到已经从 8888 端口监听到内容，并成功输出到控制台：
+ + +
\ No newline at end of file diff --git a/notes/HDFS-Java-API.md b/notes/HDFS-Java-API.md index f5ec70d..5d28f1e 100644 --- a/notes/HDFS-Java-API.md +++ b/notes/HDFS-Java-API.md @@ -386,3 +386,6 @@ public void getFileBlockLocations() throws Exception {
**以上所有测试用例下载地址**：[HDFS Java API](https://github.com/heibaiying/BigData-Notes/tree/master/code/Hadoop/hdfs-java-api) + + +
\ No newline at end of file diff --git a/notes/HDFS常用Shell命令.md b/notes/HDFS常用Shell命令.md index 933eceb..d6cf787 100644 --- a/notes/HDFS常用Shell命令.md +++ b/notes/HDFS常用Shell命令.md @@ -139,3 +139,6 @@ hadoop fs -test - [defsz] URI # 示例 hadoop fs -test -e filename ``` + + +
\ No newline at end of file diff --git a/notes/Hadoop-HDFS.md b/notes/Hadoop-HDFS.md index 5e88e95..cfa57b0 100644 --- a/notes/Hadoop-HDFS.md +++ b/notes/Hadoop-HDFS.md @@ -174,3 +174,6 @@ HDFS 具有良好的跨平台移植性，这使得其他大数据计算框架都 2. Tom White . hadoop 权威指南 [M] . 清华大学出版社 . 2017. 3. [翻译经典 HDFS 原理讲解漫画](https://blog.csdn.net/hudiefenmu/article/details/37655491) + + +
\ No newline at end of file diff --git a/notes/Hadoop-MapReduce.md b/notes/Hadoop-MapReduce.md index 616bc9e..2163a09 100644 --- a/notes/Hadoop-MapReduce.md +++ b/notes/Hadoop-MapReduce.md @@ -382,3 +382,6 @@ job.setNumReduceTasks(WordCountDataUtils.WORD_LIST.size()); + + +
\ No newline at end of file diff --git a/notes/Hadoop-YARN.md b/notes/Hadoop-YARN.md index cd7cb90..10a8755 100644 --- a/notes/Hadoop-YARN.md +++ b/notes/Hadoop-YARN.md @@ -126,3 +126,6 @@ YARN 中的任务将其进度和状态 (包括 counter) 返回给应用管理器 + + +
\ No newline at end of file diff --git a/notes/Hbase_Java_API.md b/notes/Hbase_Java_API.md index c75522e..66dfef4 100644 --- a/notes/Hbase_Java_API.md +++ b/notes/Hbase_Java_API.md @@ -759,3 +759,6 @@ connection = ConnectionFactory.createConnection(config); 1. [连接 HBase 的正确姿势](https://yq.aliyun.com/articles/581702?spm=a2c4e.11157919.spm-cont-list.1.146c27aeFxoMsN%20%E8%BF%9E%E6%8E%A5HBase%E7%9A%84%E6%AD%A3%E7%A1%AE%E5%A7%BF%E5%8A%BF) 2. [Apache HBase ™ Reference Guide](http://hbase.apache.org/book.htm) + + +
\ No newline at end of file diff --git a/notes/Hbase_Shell.md b/notes/Hbase_Shell.md index d9417f2..6404c31 100644 --- a/notes/Hbase_Shell.md +++ b/notes/Hbase_Shell.md @@ -277,3 +277,6 @@ scan 'Student', FILTER=>"PrefixFilter('wr')" + + +
\ No newline at end of file diff --git a/notes/Hbase协处理器详解.md b/notes/Hbase协处理器详解.md index eb55627..50bdae7 100644 --- a/notes/Hbase协处理器详解.md +++ b/notes/Hbase协处理器详解.md @@ -488,3 +488,6 @@ hbase > get 'magazine','rowkey1','article:content' 1. [Apache HBase Coprocessors](http://hbase.apache.org/book.html#cp) 2. [Apache HBase Coprocessor Introduction](https://blogs.apache.org/hbase/entry/coprocessor_introduction) 3. [HBase 高階知識](https://www.itread01.com/content/1546245908.html) + + +
\ No newline at end of file diff --git a/notes/Hbase容灾与备份.md b/notes/Hbase容灾与备份.md index 2a3d150..bdebc1e 100644 --- a/notes/Hbase容灾与备份.md +++ b/notes/Hbase容灾与备份.md @@ -194,3 +194,6 @@ hbase> restore_snapshot '快照名' 1. [Online Apache HBase Backups with CopyTable](https://blog.cloudera.com/blog/2012/06/online-hbase-backups-with-copytable-2/) 2. [Apache HBase ™ Reference Guide](http://hbase.apache.org/book.htm) + + +
\ No newline at end of file diff --git a/notes/Hbase的SQL中间层_Phoenix.md b/notes/Hbase的SQL中间层_Phoenix.md index 9c4f004..7b64e3b 100644 --- a/notes/Hbase的SQL中间层_Phoenix.md +++ b/notes/Hbase的SQL中间层_Phoenix.md @@ -239,3 +239,6 @@ public class PhoenixJavaApi { # 参考资料 1. http://phoenix.apache.org/ + + +
\ No newline at end of file diff --git a/notes/Hbase简介.md b/notes/Hbase简介.md index 9a2f472..b406d92 100644 --- a/notes/Hbase简介.md +++ b/notes/Hbase简介.md @@ -86,3 +86,6 @@ Hbase 的表具有以下特点： + + +
\ No newline at end of file diff --git a/notes/Hbase系统架构及数据结构.md b/notes/Hbase系统架构及数据结构.md index eb66f4f..3d61164 100644 --- a/notes/Hbase系统架构及数据结构.md +++ b/notes/Hbase系统架构及数据结构.md @@ -220,3 +220,6 @@ HBase 系统遵循 Master/Salve 架构，由三种不同类型的组件组成： + + +
\ No newline at end of file diff --git a/notes/Hbase过滤器详解.md b/notes/Hbase过滤器详解.md index 69188cb..614d04e 100644 --- a/notes/Hbase过滤器详解.md +++ b/notes/Hbase过滤器详解.md @@ -443,3 +443,6 @@ scan.setFilter(filterList); ## 参考资料 [HBase: The Definitive Guide _> Chapter 4. Client API: Advanced Features](https://www.oreilly.com/library/view/hbase-the-definitive/9781449314682/ch04.html) + + +
\ No newline at end of file diff --git a/notes/HiveCLI和Beeline命令行的基本使用.md b/notes/HiveCLI和Beeline命令行的基本使用.md index cdbd8d7..38ad992 100644 --- a/notes/HiveCLI和Beeline命令行的基本使用.md +++ b/notes/HiveCLI和Beeline命令行的基本使用.md @@ -277,3 +277,6 @@ Hive 可选的配置参数非常多，在用到时查阅官方文档即可[Admin 1. [HiveServer2 Clients](https://cwiki.apache.org/confluence/display/Hive/HiveServer2+Clients) 2. [LanguageManual Cli](https://cwiki.apache.org/confluence/display/Hive/LanguageManual+Cli) 3. [AdminManual Configuration](https://cwiki.apache.org/confluence/display/Hive/AdminManual+Configuration) + + +
\ No newline at end of file diff --git a/notes/Hive分区表和分桶表.md b/notes/Hive分区表和分桶表.md index d552575..e1d7924 100644 --- a/notes/Hive分区表和分桶表.md +++ b/notes/Hive分区表和分桶表.md @@ -166,3 +166,6 @@ SELECT * FROM page_view WHERE dt='2009-02-25'; ## 参考资料 1. [LanguageManual DDL BucketedTables](https://cwiki.apache.org/confluence/display/Hive/LanguageManual+DDL+BucketedTables) + + +
\ No newline at end of file diff --git a/notes/Hive常用DDL操作.md b/notes/Hive常用DDL操作.md index dc8f387..299ae80 100644 --- a/notes/Hive常用DDL操作.md +++ b/notes/Hive常用DDL操作.md @@ -448,3 +448,6 @@ SHOW CREATE TABLE ([db_name.]table_name|view_name); ## 参考资料 [LanguageManual DDL](https://cwiki.apache.org/confluence/display/Hive/LanguageManual+DDL) + + +
\ No newline at end of file diff --git a/notes/Hive常用DML操作.md b/notes/Hive常用DML操作.md index 6e633fa..28af9be 100644 --- a/notes/Hive常用DML操作.md +++ b/notes/Hive常用DML操作.md @@ -327,3 +327,6 @@ SELECT * FROM emp_ptn; 1. [Hive Transactions](https://cwiki.apache.org/confluence/display/Hive/Hive+Transactions) 2. [Hive Data Manipulation Language](https://cwiki.apache.org/confluence/display/Hive/LanguageManual+DML) + + +
\ No newline at end of file diff --git a/notes/Hive数据查询详解.md b/notes/Hive数据查询详解.md index 33d7838..12ca4cd 100644 --- a/notes/Hive数据查询详解.md +++ b/notes/Hive数据查询详解.md @@ -392,3 +392,6 @@ SET hive.exec.mode.local.auto=true; 2. [LanguageManual Joins](https://cwiki.apache.org/confluence/display/Hive/LanguageManual+Joins) 3. [LanguageManual GroupBy](https://cwiki.apache.org/confluence/display/Hive/LanguageManual+GroupBy) 4. [LanguageManual SortBy](https://cwiki.apache.org/confluence/display/Hive/LanguageManual+SortBy) + + +
\ No newline at end of file diff --git a/notes/Hive简介及核心概念.md b/notes/Hive简介及核心概念.md index 284159b..50915c7 100644 --- a/notes/Hive简介及核心概念.md +++ b/notes/Hive简介及核心概念.md @@ -200,3 +200,6 @@ CREATE TABLE page_view(viewTime INT, userid BIGINT) 3. [LanguageManual DDL](https://cwiki.apache.org/confluence/display/Hive/LanguageManual+DDL) 4. [LanguageManual Types](https://cwiki.apache.org/confluence/display/Hive/LanguageManual+Types) 5. [Managed vs. External Tables](https://cwiki.apache.org/confluence/display/Hive/Managed+vs.+External+Tables) + + +
\ No newline at end of file diff --git a/notes/Hive视图和索引.md b/notes/Hive视图和索引.md index 89aa9be..a269c41 100644 --- a/notes/Hive视图和索引.md +++ b/notes/Hive视图和索引.md @@ -234,3 +234,6 @@ SHOW INDEX ON emp; 2. [Materialized views](https://cwiki.apache.org/confluence/display/Hive/Materialized+views) 3. [Hive 索引](http://lxw1234.com/archives/2015/05/207.htm) 4. [Overview of Hive Indexes](https://cwiki.apache.org/confluence/display/Hive/LanguageManual+Indexing) + + +
\ No newline at end of file diff --git a/notes/Kafka消费者详解.md b/notes/Kafka消费者详解.md index 8c8b234..0642de1 100644 --- a/notes/Kafka消费者详解.md +++ b/notes/Kafka消费者详解.md @@ -390,3 +390,6 @@ broker 返回给消费者数据的等待时间，默认是 500ms。 1. Neha Narkhede, Gwen Shapira ,Todd Palino(著) , 薛命灯 (译) . Kafka 权威指南 . 人民邮电出版社 . 2017-12-26 + + +
\ No newline at end of file diff --git a/notes/Kafka深入理解分区副本机制.md b/notes/Kafka深入理解分区副本机制.md index 20a5499..2b7c92f 100644 --- a/notes/Kafka深入理解分区副本机制.md +++ b/notes/Kafka深入理解分区副本机制.md @@ -159,3 +159,6 @@ Exception: Replication factor: 3 larger than available brokers: 1. 1. Neha Narkhede, Gwen Shapira ,Todd Palino(著) , 薛命灯 (译) . Kafka 权威指南 . 人民邮电出版社 . 2017-12-26 2. [Kafka 高性能架构之道](http://www.jasongj.com/kafka/high_throughput/) + + +
\ No newline at end of file diff --git a/notes/Kafka生产者详解.md b/notes/Kafka生产者详解.md index 862db02..177a3c6 100644 --- a/notes/Kafka生产者详解.md +++ b/notes/Kafka生产者详解.md @@ -362,3 +362,6 @@ acks 参数指定了必须要有多少个分区副本收到消息，生产者才 ## 参考资料 1. Neha Narkhede, Gwen Shapira ,Todd Palino(著) , 薛命灯 (译) . Kafka 权威指南 . 人民邮电出版社 . 2017-12-26 + + +
\ No newline at end of file diff --git a/notes/Kafka简介.md b/notes/Kafka简介.md index 802e791..81808c4 100644 --- a/notes/Kafka简介.md +++ b/notes/Kafka简介.md @@ -65,3 +65,6 @@ Broker 是集群 (Cluster) 的组成部分。每一个集群都会选举出一 ## 参考资料 Neha Narkhede, Gwen Shapira ,Todd Palino(著) , 薛命灯 (译) . Kafka 权威指南 . 人民邮电出版社 . 2017-12-26 + + +
\ No newline at end of file diff --git a/notes/Scala函数和闭包.md b/notes/Scala函数和闭包.md index 482255c..2c1f59b 100644 --- a/notes/Scala函数和闭包.md +++ b/notes/Scala函数和闭包.md @@ -310,3 +310,6 @@ object ScalaApp extends App { + + +
\ No newline at end of file diff --git a/notes/Scala列表和集.md b/notes/Scala列表和集.md index 208d42e..3da271f 100644 --- a/notes/Scala列表和集.md +++ b/notes/Scala列表和集.md @@ -540,3 +540,6 @@ object ScalaApp extends App { 1. Martin Odersky . Scala 编程 (第 3 版)[M] . 电子工业出版社 . 2018-1-1 2. 凯.S.霍斯特曼 . 快学 Scala(第 2 版)[M] . 电子工业出版社 . 2017-7 + + +
\ No newline at end of file diff --git a/notes/Scala基本数据类型和运算符.md b/notes/Scala基本数据类型和运算符.md index d54fb46..308d5e0 100644 --- a/notes/Scala基本数据类型和运算符.md +++ b/notes/Scala基本数据类型和运算符.md @@ -272,3 +272,6 @@ res6: Boolean = true ## 参考资料 1. Martin Odersky . Scala 编程 (第 3 版)[M] . 电子工业出版社 . 2018-1-1 + + +
\ No newline at end of file diff --git a/notes/Scala数组.md b/notes/Scala数组.md index d7215a8..d576243 100644 --- a/notes/Scala数组.md +++ b/notes/Scala数组.md @@ -191,3 +191,6 @@ object ScalaApp extends App { 1. Martin Odersky . Scala 编程 (第 3 版)[M] . 电子工业出版社 . 2018-1-1 2. 凯.S.霍斯特曼 . 快学 Scala(第 2 版)[M] . 电子工业出版社 . 2017-7 + + +
\ No newline at end of file diff --git a/notes/Scala映射和元组.md b/notes/Scala映射和元组.md index ec47e12..eb4b5af 100644 --- a/notes/Scala映射和元组.md +++ b/notes/Scala映射和元组.md @@ -280,3 +280,6 @@ object ScalaApp extends App { 1. Martin Odersky . Scala 编程 (第 3 版)[M] . 电子工业出版社 . 2018-1-1 2. 凯.S.霍斯特曼 . 快学 Scala(第 2 版)[M] . 电子工业出版社 . 2017-7 + + +
\ No newline at end of file diff --git a/notes/Scala模式匹配.md b/notes/Scala模式匹配.md index 7c65267..91ddad5 100644 --- a/notes/Scala模式匹配.md +++ b/notes/Scala模式匹配.md @@ -170,3 +170,6 @@ object ScalaApp extends App { 1. Martin Odersky . Scala 编程 (第 3 版)[M] . 电子工业出版社 . 2018-1-1 2. 凯.S.霍斯特曼 . 快学 Scala(第 2 版)[M] . 电子工业出版社 . 2017-7 + + +
\ No newline at end of file diff --git a/notes/Scala流程控制语句.md b/notes/Scala流程控制语句.md index 8b1c219..78f9988 100644 --- a/notes/Scala流程控制语句.md +++ b/notes/Scala流程控制语句.md @@ -209,3 +209,6 @@ println(s"Hello, ${name}! Next year, you will be ${age + 1}.") 1. Martin Odersky . Scala 编程 (第 3 版)[M] . 电子工业出版社 . 2018-1-1 2. 凯.S.霍斯特曼 . 快学 Scala(第 2 版)[M] . 电子工业出版社 . 2017-7 + + +
\ No newline at end of file diff --git a/notes/Scala简介及开发环境配置.md b/notes/Scala简介及开发环境配置.md index e16065e..57f64db 100644 --- a/notes/Scala简介及开发环境配置.md +++ b/notes/Scala简介及开发环境配置.md @@ -131,3 +131,6 @@ IDEA 默认不支持 Scala 语言的开发，需要通过插件进行扩展。 1. Martin Odersky(著)，高宇翔 (译) . Scala 编程 (第 3 版)[M] . 电子工业出版社 . 2018-1-1 2. https://www.scala-lang.org/download/ + + +
\ No newline at end of file diff --git a/notes/Scala类和对象.md b/notes/Scala类和对象.md index 881ebe2..65cb39a 100644 --- a/notes/Scala类和对象.md +++ b/notes/Scala类和对象.md @@ -410,3 +410,6 @@ true 1. Martin Odersky . Scala 编程 (第 3 版)[M] . 电子工业出版社 . 2018-1-1 2. 凯.S.霍斯特曼 . 快学 Scala(第 2 版)[M] . 电子工业出版社 . 2017-7 + + +
\ No newline at end of file diff --git a/notes/Scala类型参数.md b/notes/Scala类型参数.md index 26be482..299391f 100644 --- a/notes/Scala类型参数.md +++ b/notes/Scala类型参数.md @@ -465,3 +465,6 @@ def min[T <: SuperComparable[T]](p: Pair[T]) = {} 1. Martin Odersky . Scala 编程 (第 3 版)[M] . 电子工业出版社 . 2018-1-1 2. 凯.S.霍斯特曼 . 快学 Scala(第 2 版)[M] . 电子工业出版社 . 2017-7 + + +
\ No newline at end of file diff --git a/notes/Scala继承和特质.md b/notes/Scala继承和特质.md index 5b6bd4a..9e871cb 100644 --- a/notes/Scala继承和特质.md +++ b/notes/Scala继承和特质.md @@ -416,3 +416,6 @@ class Employee extends Person with InfoLogger with ErrorLogger {...} + + +
\ No newline at end of file diff --git a/notes/Scala隐式转换和隐式参数.md b/notes/Scala隐式转换和隐式参数.md index 37b63ce..fcf9e21 100644 --- a/notes/Scala隐式转换和隐式参数.md +++ b/notes/Scala隐式转换和隐式参数.md @@ -354,3 +354,6 @@ object Pair extends App { + + +
\ No newline at end of file diff --git a/notes/Scala集合类型.md b/notes/Scala集合类型.md index edcb831..33d2819 100644 --- a/notes/Scala集合类型.md +++ b/notes/Scala集合类型.md @@ -257,3 +257,6 @@ res8: Boolean = false 1. https://docs.scala-lang.org/overviews/collections/overview.html 2. https://docs.scala-lang.org/overviews/collections/trait-traversable.html 3. https://docs.scala-lang.org/overviews/collections/trait-iterable.html + + +
\ No newline at end of file diff --git a/notes/SparkSQL_Dataset和DataFrame简介.md b/notes/SparkSQL_Dataset和DataFrame简介.md index 3ddc40c..d6e0672 100644 --- a/notes/SparkSQL_Dataset和DataFrame简介.md +++ b/notes/SparkSQL_Dataset和DataFrame简介.md @@ -145,3 +145,6 @@ DataFrame、DataSet 和 Spark SQL 的实际执行流程都是相同的： 2. [Spark SQL, DataFrames and Datasets Guide](https://spark.apache.org/docs/latest/sql-programming-guide.html) 3. [且谈 Apache Spark 的 API 三剑客：RDD、DataFrame 和 Dataset(译文)](https://www.infoq.cn/article/three-apache-spark-apis-rdds-dataframes-and-datasets) 4. [A Tale of Three Apache Spark APIs: RDDs vs DataFrames and Datasets(原文)](https://databricks.com/blog/2016/07/14/a-tale-of-three-apache-spark-apis-rdds-dataframes-and-datasets.html) + + +
\ No newline at end of file diff --git a/notes/SparkSQL外部数据源.md b/notes/SparkSQL外部数据源.md index f2dd0fe..765a75f 100644 --- a/notes/SparkSQL外部数据源.md +++ b/notes/SparkSQL外部数据源.md @@ -497,3 +497,6 @@ df.write.option(“maxRecordsPerFile”, 5000) 1. Matei Zaharia, Bill Chambers . Spark: The Definitive Guide[M] . 2018-02 2. https://spark.apache.org/docs/latest/sql-data-sources.html + + +
\ No newline at end of file diff --git a/notes/SparkSQL常用聚合函数.md b/notes/SparkSQL常用聚合函数.md index c94a15c..cf70bce 100644 --- a/notes/SparkSQL常用聚合函数.md +++ b/notes/SparkSQL常用聚合函数.md @@ -337,3 +337,6 @@ object SparkSqlApp { ## 参考资料 1. Matei Zaharia, Bill Chambers . Spark: The Definitive Guide[M] . 2018-02 + + +
\ No newline at end of file diff --git a/notes/SparkSQL联结操作.md b/notes/SparkSQL联结操作.md index 23178f1..5b178ae 100644 --- a/notes/SparkSQL联结操作.md +++ b/notes/SparkSQL联结操作.md @@ -183,3 +183,6 @@ empDF.join(broadcast(deptDF), joinExpression).show() ## 参考资料 1. Matei Zaharia, Bill Chambers . Spark: The Definitive Guide[M] . 2018-02 + + +
\ No newline at end of file diff --git a/notes/Spark_RDD.md b/notes/Spark_RDD.md index 9b28445..1ae1a24 100644 --- a/notes/Spark_RDD.md +++ b/notes/Spark_RDD.md @@ -235,3 +235,6 @@ RDD(s) 及其之间的依赖关系组成了 DAG(有向无环图)，DAG 定义了 + + +
\ No newline at end of file diff --git a/notes/Spark_Streaming与流处理.md b/notes/Spark_Streaming与流处理.md index 0c8b719..22cd826 100644 --- a/notes/Spark_Streaming与流处理.md +++ b/notes/Spark_Streaming与流处理.md @@ -77,3 +77,6 @@ storm 和 Flink 都是真正意义上的流计算框架，但 Spark Streaming 1. [Spark Streaming Programming Guide](https://spark.apache.org/docs/latest/streaming-programming-guide.html) 2. [What is stream processing?](https://www.ververica.com/what-is-stream-processing) + + +
\ No newline at end of file diff --git a/notes/Spark_Streaming基本操作.md b/notes/Spark_Streaming基本操作.md index a1d1d97..1e8cf47 100644 --- a/notes/Spark_Streaming基本操作.md +++ b/notes/Spark_Streaming基本操作.md @@ -333,3 +333,6 @@ storm storm flink azkaban ## 参考资料 Spark 官方文档：http://spark.apache.org/docs/latest/streaming-programming-guide.html + + +
\ No newline at end of file diff --git a/notes/Spark_Streaming整合Flume.md b/notes/Spark_Streaming整合Flume.md index e2a9e6f..e79b141 100644 --- a/notes/Spark_Streaming整合Flume.md +++ b/notes/Spark_Streaming整合Flume.md @@ -357,3 +357,6 @@ spark-submit \ - [streaming-flume-integration](https://spark.apache.org/docs/latest/streaming-flume-integration.html) - 关于大数据应用常用的打包方式可以参见：[大数据应用常用打包方式](https://github.com/heibaiying/BigData-Notes/blob/master/notes/大数据应用常用打包方式.md) + + +
\ No newline at end of file diff --git a/notes/Spark_Streaming整合Kafka.md b/notes/Spark_Streaming整合Kafka.md index 375f30c..67b5db4 100644 --- a/notes/Spark_Streaming整合Kafka.md +++ b/notes/Spark_Streaming整合Kafka.md @@ -319,3 +319,6 @@ bin/kafka-console-producer.sh --broker-list hadoop001:9092 --topic spark-streami ## 参考资料 1. https://spark.apache.org/docs/latest/streaming-kafka-0-10-integration.html + + +
\ No newline at end of file diff --git a/notes/Spark_Structured_API的基本使用.md b/notes/Spark_Structured_API的基本使用.md index 30056aa..6be29c5 100644 --- a/notes/Spark_Structured_API的基本使用.md +++ b/notes/Spark_Structured_API的基本使用.md @@ -242,3 +242,6 @@ spark.sql("SELECT ename,job FROM global_temp.gemp").show() ## 参考资料 [Spark SQL, DataFrames and Datasets Guide > Getting Started](https://spark.apache.org/docs/latest/sql-getting-started.html) + + +
\ No newline at end of file diff --git a/notes/Spark_Transformation和Action算子.md b/notes/Spark_Transformation和Action算子.md index 150f0bb..c830bcc 100644 --- a/notes/Spark_Transformation和Action算子.md +++ b/notes/Spark_Transformation和Action算子.md @@ -416,3 +416,6 @@ sc.parallelize(list).saveAsTextFile("/usr/file/temp") [RDD Programming Guide](http://spark.apache.org/docs/latest/rdd-programming-guide.html#rdd-programming-guide) + + +
\ No newline at end of file diff --git a/notes/Spark简介.md b/notes/Spark简介.md index bb91551..53b1baf 100644 --- a/notes/Spark简介.md +++ b/notes/Spark简介.md @@ -92,3 +92,6 @@ MLlib 是 Spark 的机器学习库。其设计目标是使得机器学习变得 GraphX 是 Spark 中用于图形计算和图形并行计算的新组件。在高层次上，GraphX 通过引入一个新的图形抽象来扩展 RDD(一种具有附加到每个顶点和边缘的属性的定向多重图形)。为了支持图计算，GraphX 提供了一组基本运算符（如： subgraph，joinVertices 和 aggregateMessages）以及优化后的 Pregel API。此外，GraphX 还包括越来越多的图形算法和构建器，以简化图形分析任务。 ## + + +
\ No newline at end of file diff --git a/notes/Spark累加器与广播变量.md b/notes/Spark累加器与广播变量.md index ca4da08..a6bdcb8 100644 --- a/notes/Spark累加器与广播变量.md +++ b/notes/Spark累加器与广播变量.md @@ -103,3 +103,6 @@ sc.parallelize(broadcastVar.value).map(_ * 10).collect() [RDD Programming Guide](http://spark.apache.org/docs/latest/rdd-programming-guide.html#rdd-programming-guide) + + +
\ No newline at end of file diff --git a/notes/Spark部署模式与作业提交.md b/notes/Spark部署模式与作业提交.md index cb8289b..66749d2 100644 --- a/notes/Spark部署模式与作业提交.md +++ b/notes/Spark部署模式与作业提交.md @@ -246,3 +246,6 @@ spark-submit \ + + +
\ No newline at end of file diff --git a/notes/Spring+Mybtais+Phoenix整合.md b/notes/Spring+Mybtais+Phoenix整合.md index 29f0660..4a2698b 100644 --- a/notes/Spring+Mybtais+Phoenix整合.md +++ b/notes/Spring+Mybtais+Phoenix整合.md @@ -384,3 +384,6 @@ UPSERT INTO us_population VALUES('CA','San Diego',1255540); UPSERT INTO us_population VALUES('CA','San Jose',912332); ``` + + +
\ No newline at end of file diff --git a/notes/Sqoop基本使用.md b/notes/Sqoop基本使用.md index d4cec85..513a0b5 100644 --- a/notes/Sqoop基本使用.md +++ b/notes/Sqoop基本使用.md @@ -385,3 +385,6 @@ $ sqoop import ... --map-column-java id=String,value=Integer ## 参考资料 [Sqoop User Guide (v1.4.7)](http://sqoop.apache.org/docs/1.4.7/SqoopUserGuide.html) + + +
\ No newline at end of file diff --git a/notes/Sqoop简介与安装.md b/notes/Sqoop简介与安装.md index 7603b8d..27b4a90 100644 --- a/notes/Sqoop简介与安装.md +++ b/notes/Sqoop简介与安装.md @@ -145,3 +145,6 @@ if [ ! -d "${ZOOKEEPER_HOME}" ]; then fi ``` + + +
\ No newline at end of file diff --git a/notes/Storm三种打包方式对比分析.md b/notes/Storm三种打包方式对比分析.md index e021817..5b39fa7 100644 --- a/notes/Storm三种打包方式对比分析.md +++ b/notes/Storm三种打包方式对比分析.md @@ -313,3 +313,6 @@ jar:file:/usr/appjar/storm-hdfs-integration-1.0.jar!/defaults.yaml] ## 参考资料 关于 maven-shade-plugin 的更多配置可以参考： [maven-shade-plugin 入门指南](https://www.jianshu.com/p/7a0e20b30401) + + +
\ No newline at end of file diff --git a/notes/Storm和流处理简介.md b/notes/Storm和流处理简介.md index 2949d75..e505c00 100644 --- a/notes/Storm和流处理简介.md +++ b/notes/Storm和流处理简介.md @@ -96,3 +96,6 @@ storm 和 Flink 都是真正意义上的实时计算框架。其对比如下： 1. [What is stream processing?](https://www.ververica.com/what-is-stream-processing) 2. [流计算框架 Flink 与 Storm 的性能对比](http://bigdata.51cto.com/art/201711/558416.htm) + + +
\ No newline at end of file diff --git a/notes/Storm核心概念详解.md b/notes/Storm核心概念详解.md index 11cf338..b7208f3 100644 --- a/notes/Storm核心概念详解.md +++ b/notes/Storm核心概念详解.md @@ -157,3 +157,6 @@ Task 是组成 Component 的代码单元。Topology 启动后，1 个 Component 3. [Understanding the Parallelism of a Storm Topology](http://storm.apache.org/releases/1.2.2/Understanding-the-parallelism-of-a-Storm-topology.html) 4. [Storm nimbus 单节点宕机的处理](https://blog.csdn.net/daiyutage/article/details/52049519) + + +
\ No newline at end of file diff --git a/notes/Storm编程模型详解.md b/notes/Storm编程模型详解.md index 1cabfdc..28f328b 100644 --- a/notes/Storm编程模型详解.md +++ b/notes/Storm编程模型详解.md @@ -509,3 +509,6 @@ private String productData() { 1. [Running Topologies on a Production Cluster](http://storm.apache.org/releases/2.0.0-SNAPSHOT/Running-topologies-on-a-production-cluster.html) 2. [Pre-defined Descriptor Files](http://maven.apache.org/plugins/maven-assembly-plugin/descriptor-refs.html) + + +
\ No newline at end of file diff --git a/notes/Storm集成HBase和HDFS.md b/notes/Storm集成HBase和HDFS.md index 2c9c146..53ac365 100644 --- a/notes/Storm集成HBase和HDFS.md +++ b/notes/Storm集成HBase和HDFS.md @@ -487,3 +487,6 @@ SimpleHBaseMapper mapper = new SimpleHBaseMapper() 1. [Apache HDFS Integration](http://storm.apache.org/releases/2.0.0-SNAPSHOT/storm-hdfs.html) 2. [Apache HBase Integration](http://storm.apache.org/releases/2.0.0-SNAPSHOT/storm-hbase.html) + + +
\ No newline at end of file diff --git a/notes/Storm集成Kakfa.md b/notes/Storm集成Kakfa.md index 5645bc0..f27717f 100644 --- a/notes/Storm集成Kakfa.md +++ b/notes/Storm集成Kakfa.md @@ -365,3 +365,6 @@ public class DefaultRecordTranslator implements RecordTranslator { ## 参考资料 1. [Storm Kafka Integration (0.10.x+)](http://storm.apache.org/releases/2.0.0-SNAPSHOT/storm-kafka-client.html) + + +
\ No newline at end of file diff --git a/notes/Storm集成Redis详解.md b/notes/Storm集成Redis详解.md index 13cbaa4..46f2ff7 100644 --- a/notes/Storm集成Redis详解.md +++ b/notes/Storm集成Redis详解.md @@ -653,3 +653,6 @@ public class CustomRedisCountApp { ## 参考资料 1. [Storm Redis Integration](http://storm.apache.org/releases/2.0.0-SNAPSHOT/storm-redis.html) + + +
\ No newline at end of file diff --git a/notes/Zookeeper_ACL权限控制.md b/notes/Zookeeper_ACL权限控制.md index 478a730..5b4b6ff 100644 --- a/notes/Zookeeper_ACL权限控制.md +++ b/notes/Zookeeper_ACL权限控制.md @@ -281,3 +281,6 @@ public class AclOperation { ``` > 完整源码见本仓库： https://github.com/heibaiying/BigData-Notes/tree/master/code/Zookeeper/curator + + +
\ No newline at end of file diff --git a/notes/Zookeeper_Java客户端Curator.md b/notes/Zookeeper_Java客户端Curator.md index 0725f5f..eba7ca5 100644 --- a/notes/Zookeeper_Java客户端Curator.md +++ b/notes/Zookeeper_Java客户端Curator.md @@ -334,3 +334,6 @@ public void permanentChildrenNodesWatch() throws Exception { Thread.sleep(1000 * 1000); //休眠以观察测试效果 } ``` + + +
\ No newline at end of file diff --git a/notes/Zookeeper常用Shell命令.md b/notes/Zookeeper常用Shell命令.md index 2358117..2b48bcf 100644 --- a/notes/Zookeeper常用Shell命令.md +++ b/notes/Zookeeper常用Shell命令.md @@ -263,3 +263,6 @@ Mode: standalone Node count: 167 ``` + + +
\ No newline at end of file diff --git a/notes/Zookeeper简介及核心概念.md b/notes/Zookeeper简介及核心概念.md index 29dc72d..6bfcd57 100644 --- a/notes/Zookeeper简介及核心概念.md +++ b/notes/Zookeeper简介及核心概念.md @@ -205,3 +205,6 @@ Zookeeper 还能解决大多数分布式系统中的问题： + + +
\ No newline at end of file diff --git a/notes/installation/Azkaban_3.x_编译及部署.md b/notes/installation/Azkaban_3.x_编译及部署.md index b9984b2..d2a45b7 100644 --- a/notes/installation/Azkaban_3.x_编译及部署.md +++ b/notes/installation/Azkaban_3.x_编译及部署.md @@ -122,3 +122,6 @@ tar -zxvf azkaban-solo-server-3.70.0.tar.gz
+ + +
\ No newline at end of file diff --git a/notes/installation/Flink_Standalone_Cluster.md b/notes/installation/Flink_Standalone_Cluster.md index 0ccf0d6..bfd2025 100644 --- a/notes/installation/Flink_Standalone_Cluster.md +++ b/notes/installation/Flink_Standalone_Cluster.md @@ -268,3 +268,6 @@ the classpath/dependencies. + [Standalone Cluster](https://ci.apache.org/projects/flink/flink-docs-release-1.9/ops/deployment/cluster_setup.html#standalone-cluster) + [JobManager High Availability (HA)](https://ci.apache.org/projects/flink/flink-docs-release-1.9/ops/jobmanager_high_availability.html) + + +
\ No newline at end of file diff --git a/notes/installation/HBase单机环境搭建.md b/notes/installation/HBase单机环境搭建.md index 56cc598..566b6a9 100644 --- a/notes/installation/HBase单机环境搭建.md +++ b/notes/installation/HBase单机环境搭建.md @@ -225,3 +225,6 @@ hadoop001 验证方式二 ：访问 HBase Web UI 界面，需要注意的是 1.2 版本的 HBase 的访问端口为 `60010`
+ + +
\ No newline at end of file diff --git a/notes/installation/HBase集群环境搭建.md b/notes/installation/HBase集群环境搭建.md index d57bf60..80a7182 100644 --- a/notes/installation/HBase集群环境搭建.md +++ b/notes/installation/HBase集群环境搭建.md @@ -198,3 +198,6 @@ hadoop002 上的 HBase 出于备用状态：
+ + +
\ No newline at end of file diff --git a/notes/installation/Hadoop单机环境搭建.md b/notes/installation/Hadoop单机环境搭建.md index 0531668..1bc301d 100644 --- a/notes/installation/Hadoop单机环境搭建.md +++ b/notes/installation/Hadoop单机环境搭建.md @@ -260,3 +260,6 @@ cp mapred-site.xml.template mapred-site.xml 方式二：查看 Web UI 界面，端口号为 `8088`：
+ + +
\ No newline at end of file diff --git a/notes/installation/Hadoop集群环境搭建.md b/notes/installation/Hadoop集群环境搭建.md index 477dea4..88515d0 100644 --- a/notes/installation/Hadoop集群环境搭建.md +++ b/notes/installation/Hadoop集群环境搭建.md @@ -231,3 +231,6 @@ start-yarn.sh hadoop jar /usr/app/hadoop-2.6.0-cdh5.15.2/share/hadoop/mapreduce/hadoop-mapreduce-examples-2.6.0-cdh5.15.2.jar pi 3 3 ``` + + +
\ No newline at end of file diff --git a/notes/installation/Linux下Flume的安装.md b/notes/installation/Linux下Flume的安装.md index 2e8b46a..3aef07f 100644 --- a/notes/installation/Linux下Flume的安装.md +++ b/notes/installation/Linux下Flume的安装.md @@ -66,3 +66,6 @@ export JAVA_HOME=/usr/java/jdk1.8.0_201 ![flume-version](https://github.com/heibaiying/BigData-Notes/blob/master/pictures/flume-version.png) + + +
\ No newline at end of file diff --git a/notes/installation/Linux下JDK安装.md b/notes/installation/Linux下JDK安装.md index 5459e04..3923a4d 100644 --- a/notes/installation/Linux下JDK安装.md +++ b/notes/installation/Linux下JDK安装.md @@ -53,3 +53,6 @@ Java(TM) SE Runtime Environment (build 1.8.0_201-b09) Java HotSpot(TM) 64-Bit Server VM (build 25.201-b09, mixed mode) ``` + + +
\ No newline at end of file diff --git a/notes/installation/Linux下Python安装.md b/notes/installation/Linux下Python安装.md index 20fa191..707f26e 100644 --- a/notes/installation/Linux下Python安装.md +++ b/notes/installation/Linux下Python安装.md @@ -69,3 +69,6 @@ Type "help", "copyright", "credits" or "license" for more information. [root@hadoop001 app]# ``` + + +
\ No newline at end of file diff --git a/notes/installation/Linux环境下Hive的安装部署.md b/notes/installation/Linux环境下Hive的安装部署.md index 802b23f..22a0e72 100644 --- a/notes/installation/Linux环境下Hive的安装部署.md +++ b/notes/installation/Linux环境下Hive的安装部署.md @@ -179,3 +179,6 @@ Hive 内置了 HiveServer 和 HiveServer2 服务，两者都允许客户端使 ```
+ + +
\ No newline at end of file diff --git a/notes/installation/Spark开发环境搭建.md b/notes/installation/Spark开发环境搭建.md index c961ed6..60fe77f 100644 --- a/notes/installation/Spark开发环境搭建.md +++ b/notes/installation/Spark开发环境搭建.md @@ -176,3 +176,6 @@ IDEA 默认不支持 Scala 语言的开发，需要通过插件进行扩展。 **另外在 IDEA 中以本地模式运行 Spark 项目是不需要在本机搭建 Spark 和 Hadoop 环境的。** + + +
\ No newline at end of file diff --git a/notes/installation/Spark集群环境搭建.md b/notes/installation/Spark集群环境搭建.md index 7b4eb2e..24ded20 100644 --- a/notes/installation/Spark集群环境搭建.md +++ b/notes/installation/Spark集群环境搭建.md @@ -188,3 +188,6 @@ spark-submit \ 100 ``` + + +
\ No newline at end of file diff --git a/notes/installation/Storm单机环境搭建.md b/notes/installation/Storm单机环境搭建.md index efcf586..95806fd 100644 --- a/notes/installation/Storm单机环境搭建.md +++ b/notes/installation/Storm单机环境搭建.md @@ -79,3 +79,6 @@ nohup sh storm logviewer & 验证方式二： 访问 8080 端口，查看 Web-UI 界面：
+ + +
\ No newline at end of file diff --git a/notes/installation/Storm集群环境搭建.md b/notes/installation/Storm集群环境搭建.md index 69b9c21..2afc41e 100644 --- a/notes/installation/Storm集群环境搭建.md +++ b/notes/installation/Storm集群环境搭建.md @@ -165,3 +165,6 @@ nohup sh storm logviewer & 这里手动模拟主 `Nimbus` 异常的情况，在 hadoop001 上使用 `kill` 命令杀死 `Nimbus` 的线程，此时可以看到 hadoop001 上的 `Nimbus` 已经处于 `offline` 状态，而 hadoop002 上的 `Nimbus` 则成为新的 `Leader`。
+ + +
\ No newline at end of file diff --git a/notes/installation/Zookeeper单机环境和集群环境搭建.md b/notes/installation/Zookeeper单机环境和集群环境搭建.md index eec970b..7698a4f 100644 --- a/notes/installation/Zookeeper单机环境和集群环境搭建.md +++ b/notes/installation/Zookeeper单机环境和集群环境搭建.md @@ -185,3 +185,6 @@ echo "3" > /usr/local/zookeeper-cluster/data/myid
+ + +
\ No newline at end of file diff --git a/notes/installation/基于Zookeeper搭建Hadoop高可用集群.md b/notes/installation/基于Zookeeper搭建Hadoop高可用集群.md index d54db8d..5d69f31 100644 --- a/notes/installation/基于Zookeeper搭建Hadoop高可用集群.md +++ b/notes/installation/基于Zookeeper搭建Hadoop高可用集群.md @@ -512,3 +512,6 @@ yarn-daemon.sh start resourcemanager [Hadoop NameNode 高可用 (High Availability) 实现解析](https://www.ibm.com/developerworks/cn/opensource/os-cn-hadoop-name-node/index.html) + + +
\ No newline at end of file diff --git a/notes/installation/基于Zookeeper搭建Kafka高可用集群.md b/notes/installation/基于Zookeeper搭建Kafka高可用集群.md index 3a3fb6b..85502f1 100644 --- a/notes/installation/基于Zookeeper搭建Kafka高可用集群.md +++ b/notes/installation/基于Zookeeper搭建Kafka高可用集群.md @@ -237,3 +237,6 @@ bin/kafka-topics.sh --describe --bootstrap-server hadoop001:9092 --topic my-repl + + +
\ No newline at end of file diff --git a/notes/installation/虚拟机静态IP及多IP配置.md b/notes/installation/虚拟机静态IP及多IP配置.md index aee8ceb..fc6c49e 100644 --- a/notes/installation/虚拟机静态IP及多IP配置.md +++ b/notes/installation/虚拟机静态IP及多IP配置.md @@ -116,3 +116,6 @@ DEVICE=enp0s8 使用时只需要根据所处的网络环境，勾选对应的网卡即可，不使用的网卡尽量不要勾选启动。
+ + +
\ No newline at end of file diff --git a/notes/大数据学习路线.md b/notes/大数据学习路线.md index acaffe0..fe1520c 100644 --- a/notes/大数据学习路线.md +++ b/notes/大数据学习路线.md @@ -167,3 +167,6 @@ Scala 是一门综合了面向对象和函数式编程概念的静态类型的 以上就是个人关于大数据的学习心得和路线推荐。本片文章对大数据技术栈做了比较狭义的限定，随着学习的深入，大家也可以把 Python 语言、推荐系统、机器学习等逐步加入到自己的大数据技术栈中。 + + +
\ No newline at end of file diff --git a/notes/大数据常用软件安装指南.md b/notes/大数据常用软件安装指南.md index 390afb8..6c39b51 100644 --- a/notes/大数据常用软件安装指南.md +++ b/notes/大数据常用软件安装指南.md @@ -65,3 +65,6 @@ hadoop-2.6.0-cdh5.15.2.tar.gz hbase-1.2.0-cdh5.15.2 hive-1.1.0-cdh5.15.2.tar.gz ``` + + +
\ No newline at end of file diff --git a/notes/大数据应用常用打包方式.md b/notes/大数据应用常用打包方式.md index f166e3d..adab226 100644 --- a/notes/大数据应用常用打包方式.md +++ b/notes/大数据应用常用打包方式.md @@ -304,3 +304,6 @@ Strom 官方文档 Running Topologies on a Production Cluster 章节： + maven-dependency-plugin : http://maven.apache.org/components/plugins/maven-dependency-plugin/ 关于 maven-shade-plugin 的更多配置也可以参考该博客： [maven-shade-plugin 入门指南](https://www.jianshu.com/p/7a0e20b30401) + + +
\ No newline at end of file diff --git a/notes/大数据技术栈思维导图.md b/notes/大数据技术栈思维导图.md index a28d256..d6e312c 100644 --- a/notes/大数据技术栈思维导图.md +++ b/notes/大数据技术栈思维导图.md @@ -1,2 +1,5 @@
+ + +
\ No newline at end of file diff --git a/notes/资料分享与工具推荐.md b/notes/资料分享与工具推荐.md index b7e3b33..031d758 100644 --- a/notes/资料分享与工具推荐.md +++ b/notes/资料分享与工具推荐.md @@ -54,3 +54,6 @@ ProcessOn 式一个在线绘图平台，使用起来非常便捷，可以用于 官方网站：https://www.processon.com/ + + +
\ No newline at end of file diff --git a/pictures/weixin-desc.png b/pictures/weixin-desc.png index 3217ead..e6a2b6d 100644 Binary files a/pictures/weixin-desc.png and b/pictures/weixin-desc.png differ