diff --git a/doc/_static/book.jpeg b/doc/_static/book.jpeg new file mode 100644 index 0000000..0dc875c Binary files /dev/null and b/doc/_static/book.jpeg differ diff --git a/doc/_toc.yml b/doc/_toc.yml index 8b2ee89..2264b30 100644 --- a/doc/_toc.yml +++ b/doc/_toc.yml @@ -4,7 +4,7 @@ subtrees: entries: - file: ch-big-data-intro/index entries: - - file: ch-big-data-intro/sec-bigdata + - file: ch-big-data-intro/bigdata - file: ch-big-data-intro/batch-stream - file: ch-big-data-intro/technologies - file: ch-big-data-intro/evolution @@ -46,10 +46,10 @@ subtrees: - file: ch-state-checkpoint/exercise-state - file: ch-flink-connectors/index entries: - - file: ch-flink-connectors/Exactly-Once-guarantee + - file: ch-flink-connectors/exactly-once - file: ch-flink-connectors/custom-source-and-sink - file: ch-flink-connectors/flink-connector - - file: ch-flink-connectors/exercise-stock-price-data-stream + - file: ch-flink-connectors/exercise-stock-price-with-source-sink - file: ch-table-sql/index entries: - file: ch-table-sql/table-overview @@ -62,9 +62,9 @@ subtrees: - file: ch-table-sql/exercise-iot - file: ch-deployment-and-configuration/index entries: - - file: ch-deployment-and-configuration/flink-deployment-and-configuration + - file: ch-deployment-and-configuration/deployment-and-configuration - file: ch-deployment-and-configuration/configuration-file - - file: ch-deployment-and-configuration/operator-chaining-and-slot-sharing - - file: ch-deployment-and-configuration/flink-command-line-interface-guide - - file: ch-deployment-and-configuration/hadoop-flink - - file: ch-deployment-and-configuration/experiment-job-coding-packaging-and-submission \ No newline at end of file + - file: ch-deployment-and-configuration/operator-chaining-slot-sharing + - file: ch-deployment-and-configuration/cli + - file: ch-deployment-and-configuration/flink-with-hadoop + - file: ch-deployment-and-configuration/exercise-job-submission \ No newline at end of file diff --git a/doc/ch-big-data-intro/sec-bigdata.md b/doc/ch-big-data-intro/bigdata.md similarity index 100% rename from doc/ch-big-data-intro/sec-bigdata.md rename to doc/ch-big-data-intro/bigdata.md diff --git a/doc/ch-big-data-intro/exercise-stream-with-kafka.md b/doc/ch-big-data-intro/exercise-stream-with-kafka.md index db924f0..25743d7 100644 --- a/doc/ch-big-data-intro/exercise-stream-with-kafka.md +++ b/doc/ch-big-data-intro/exercise-stream-with-kafka.md @@ -1,5 +1,5 @@ (exercise-stream-with-kafka)= -# 案例实战：使用 Kafka 构建文本数据流 +# 案例：使用 Kafka 构建文本数据流 尽管本书主题是 Flink，但是对数据流的整个生命周期有一个更全面的认识有助于我们理解大数据和流处理。{numref}`technologies` 简单介绍了 Kafka 这项技术，本节将介绍如何使用 Kafka 构建实时文本数据流，读者可以通过本节了解数据流管道的大致结构：数据生产者源源不断地生成数据流，数据流通过消息队列投递，数据消费者异步地对数据流进行处理。 diff --git a/doc/ch-datastream-api/exercise-stock-basic.md b/doc/ch-datastream-api/exercise-stock-basic.md index 0bf072a..6b0d03f 100644 --- a/doc/ch-datastream-api/exercise-stock-basic.md +++ b/doc/ch-datastream-api/exercise-stock-basic.md @@ -1,5 +1,5 @@ (exercise-stock-basic)= -# 习题 股票数据流处理 +# 案例实战：股票数据流处理 :::{note} diff --git a/doc/ch-deployment-and-configuration/flink-command-line-interface-guide.md b/doc/ch-deployment-and-configuration/cli.md similarity index 99% rename from doc/ch-deployment-and-configuration/flink-command-line-interface-guide.md rename to doc/ch-deployment-and-configuration/cli.md index 5bcf285..0be6b6a 100644 --- a/doc/ch-deployment-and-configuration/flink-command-line-interface-guide.md +++ b/doc/ch-deployment-and-configuration/cli.md @@ -1,4 +1,4 @@ -(flink-command-line-interface-guide)= +(sec-cli)= # 命令行工具 在生产环境中，Flink 使用命令行工具（Command Line Interface）来管理作业的执行。命令行工具本质上是一个可执行脚本，名为 flink，放置在 Flink 的主目录下的 bin 文件夹中。它的功能主要包括：提交、取消作业，罗列当前正在执行和排队的作业、获取某个作业的信息，设置 Savepoint 等。 diff --git a/doc/ch-deployment-and-configuration/configuration-file.md b/doc/ch-deployment-and-configuration/configuration-file.md index fcce07a..044469b 100644 --- a/doc/ch-deployment-and-configuration/configuration-file.md +++ b/doc/ch-deployment-and-configuration/configuration-file.md @@ -1,4 +1,4 @@ -(configuration-file)= +(sec-configuration-file)= # 配置文件 在前文的介绍中，我们曾多次提到 Flink 主目录下的 `conf/flink-conf.yaml` 文件，这个文件在作业配置中起到了至关重要的作用。 diff --git a/doc/ch-deployment-and-configuration/flink-deployment-and-configuration.md b/doc/ch-deployment-and-configuration/deployment-and-configuration.md similarity index 99% rename from doc/ch-deployment-and-configuration/flink-deployment-and-configuration.md rename to doc/ch-deployment-and-configuration/deployment-and-configuration.md index 1c7e2ef..a22adfb 100644 --- a/doc/ch-deployment-and-configuration/flink-deployment-and-configuration.md +++ b/doc/ch-deployment-and-configuration/deployment-and-configuration.md @@ -1,4 +1,4 @@ -(flink-deployment-and-configuration)= +(sec-deployment-and-configuration)= # Flink 集群部署模式 当前，信息系统基础设施正在飞速发展，常见的基础设施包括物理机集群、虚拟机集群、容器集群等。为了兼容这些基础设施，Flink 曾在 1.7 版本中做了重构，提出了第 3 章中所示的 Master-Worker 架构，该架构可以兼容几乎所有主流信息系统的基础设施，包括 Standalone 集群、Hadoop YARN 集群或 Kubernetes 集群。 diff --git a/doc/ch-deployment-and-configuration/experiment-job-coding-packaging-and-submission.md b/doc/ch-deployment-and-configuration/exercise-job-submission.md similarity index 95% rename from doc/ch-deployment-and-configuration/experiment-job-coding-packaging-and-submission.md rename to doc/ch-deployment-and-configuration/exercise-job-submission.md index 53c1ab2..aa74e44 100644 --- a/doc/ch-deployment-and-configuration/experiment-job-coding-packaging-and-submission.md +++ b/doc/ch-deployment-and-configuration/exercise-job-submission.md @@ -1,5 +1,5 @@ -(experiment-job-coding-packaging-and-submission)= -# 实验 作业编码、打包与提交 +(sec-exercise-job-submission)= +# 案例实战：作业编码、打包与提交 本章的重点是集群部署与作业提交，本实验也与此相关。 diff --git a/doc/ch-deployment-and-configuration/hadoop-flink.md b/doc/ch-deployment-and-configuration/flink-with-hadoop.md similarity index 99% rename from doc/ch-deployment-and-configuration/hadoop-flink.md rename to doc/ch-deployment-and-configuration/flink-with-hadoop.md index 49b4732..c663077 100644 --- a/doc/ch-deployment-and-configuration/hadoop-flink.md +++ b/doc/ch-deployment-and-configuration/flink-with-hadoop.md @@ -1,4 +1,4 @@ -(hadoop-flink)= +(sec-flink-with-hadoop)= # 与 Hadoop 集成 Flink 可以和 Hadoop 生态圈的组件紧密结合，比如 9.1 节中提到，Flink 可以使用 YARN 作为资源调度器，或者读取 HDFS、HBase 中的数据。在使用 Hadoop 前，我们需要确认已经安装了 Hadoop，并配置了环境变量 `HADOOP_CONF_DIR`，如下环境变量配置是 Hadoop 安装过程所必需的。 diff --git a/doc/ch-deployment-and-configuration/operator-chaining-and-slot-sharing.md b/doc/ch-deployment-and-configuration/operator-chaining-slot-sharing.md similarity index 99% rename from doc/ch-deployment-and-configuration/operator-chaining-and-slot-sharing.md rename to doc/ch-deployment-and-configuration/operator-chaining-slot-sharing.md index 526d968..1305c1f 100644 --- a/doc/ch-deployment-and-configuration/operator-chaining-and-slot-sharing.md +++ b/doc/ch-deployment-and-configuration/operator-chaining-slot-sharing.md @@ -1,4 +1,4 @@ -(operator-chaining-and-slot-sharing)= +(sec-operator-chaining-slot-sharing)= # 算子链与槽位共享 在第 3 章中我们曾介绍了算子链和槽位共享的概念。默认情况下，这两个功能都是开启的。 diff --git a/doc/ch-flink-connectors/custom-source-and-sink.md b/doc/ch-flink-connectors/custom-source-and-sink.md index 0447fbb..76897d7 100644 --- a/doc/ch-flink-connectors/custom-source-and-sink.md +++ b/doc/ch-flink-connectors/custom-source-and-sink.md @@ -1,4 +1,5 @@ -(custom-source-and-sink)= +(sec-custom-source-and-sink)= + # 自定义 Source 和 Sink 本节将从原理和实现两个方面来介绍 Flink 的 Source 和 Sink。 diff --git a/doc/ch-flink-connectors/Exactly-Once-guarantee.md b/doc/ch-flink-connectors/exactly-once.md similarity index 99% rename from doc/ch-flink-connectors/Exactly-Once-guarantee.md rename to doc/ch-flink-connectors/exactly-once.md index 4a986fb..8fc2dbf 100644 --- a/doc/ch-flink-connectors/Exactly-Once-guarantee.md +++ b/doc/ch-flink-connectors/exactly-once.md @@ -1,4 +1,4 @@ -(Exactly-Once-guarantee)= +(sec-exactly-once)= # Flink 端到端的 Exactly-Once 保障 ## 故障恢复与一致性保障 diff --git a/doc/ch-flink-connectors/exercise-stock-price-data-stream.md b/doc/ch-flink-connectors/exercise-stock-price-with-source-sink.md similarity index 93% rename from doc/ch-flink-connectors/exercise-stock-price-data-stream.md rename to doc/ch-flink-connectors/exercise-stock-price-with-source-sink.md index 339d9b2..8573641 100644 --- a/doc/ch-flink-connectors/exercise-stock-price-data-stream.md +++ b/doc/ch-flink-connectors/exercise-stock-price-with-source-sink.md @@ -1,5 +1,5 @@ -(exercise-stock-price-data-stream)= -# 实验 读取并输出股票价格数据流 +(sec-exercise-stock-price-with-source-sink)= +# 案例实战：读取并输出股票价格数据流 经过本章的学习，读者应该基本了解了 Flink Connector 的使用方法，本节我们继续以股票交易场景来模拟数据流的输入和输出。 diff --git a/doc/ch-programming-basics/exercise-dev-environment.md b/doc/ch-programming-basics/exercise-dev-environment.md index 23b6a70..d79673b 100644 --- a/doc/ch-programming-basics/exercise-dev-environment.md +++ b/doc/ch-programming-basics/exercise-dev-environment.md @@ -1,5 +1,5 @@ (exercise-dev-environment)= -# 案例实战 Flink 开发环境搭建 +# 案例实战：Flink 开发环境搭建 本案例实战主要带领读者完成对 Flink 开发环境的搭建。 diff --git a/doc/ch-state-checkpoint/exercise-state.md b/doc/ch-state-checkpoint/exercise-state.md index aadc6db..04bfd99 100644 --- a/doc/ch-state-checkpoint/exercise-state.md +++ b/doc/ch-state-checkpoint/exercise-state.md @@ -1,5 +1,5 @@ (exercise-state)= -# 练习：电商用户行为 +# 案例实战：电商用户行为 :::{note} diff --git a/doc/ch-system-design/exercise-wordcount.md b/doc/ch-system-design/exercise-wordcount.md index a381479..ac5528e 100644 --- a/doc/ch-system-design/exercise-wordcount.md +++ b/doc/ch-system-design/exercise-wordcount.md @@ -1,5 +1,5 @@ (exercise-wordcount)= -# 练习：WordCount +# 案例实战：WordCount :::{note} diff --git a/doc/ch-table-sql/exercise-iot.md b/doc/ch-table-sql/exercise-iot.md index e68e39d..e05b765 100644 --- a/doc/ch-table-sql/exercise-iot.md +++ b/doc/ch-table-sql/exercise-iot.md @@ -1,5 +1,5 @@ (exercise-iot)= -# 练习：SQL on IoT +# 案例实战：SQL on IoT :::{note} diff --git a/doc/ch-time-window/exercise-stock.md b/doc/ch-time-window/exercise-stock.md index 151df0f..b091d90 100644 --- a/doc/ch-time-window/exercise-stock.md +++ b/doc/ch-time-window/exercise-stock.md @@ -1,5 +1,5 @@ (exercise-stock)= -# 练习：股票价格 +# 案例实战：股票价格 :::{note} diff --git a/doc/index.md b/doc/index.md index 0feb167..44606af 100644 --- a/doc/index.md +++ b/doc/index.md @@ -7,6 +7,9 @@ :columns: 3 :class: sd-m-auto +```{image} ./_static/book.jpeg +:width: 150px +``` ::: @@ -19,6 +22,9 @@ % The SVG rendering breaks latex builds for the GitHub badge, so only include in HTML ```{only} html [![](https://img.shields.io/github/stars/godaai/flink-book-zh?style=for-the-badge)](https://github.com/godaai/flink-book-zh) + +[![](https://img.shields.io/badge/JD-%E8%B4%AD%E4%B9%B0%E9%93%BE%E6%8E%A5-red?style=for-the-badge)](https://item.jd.com/13154364.html) + ``` ::: @@ -27,21 +33,7 @@ ## 主要作者 -::::{grid} -:class-container: text-center -:gutter: 3 - -:::{grid-item-card} -:link-type: doc -:class-header: bg-light - -鲁蔚征 -^^^ - -现就职于中国人民大学，CCF高性能计算专业委员会执行委员，主要研究大数据与机器学习系统。 -::: - -:::: +* 鲁蔚征，现就职于中国人民大学，CCF高性能计算专业委员会执行委员，主要研究大数据与机器学习系统。 ## 赞赏与支持