= 2011-10-31 =

== Crawlzilla ==

 * 最近看到 Google+ Ripples 就是先前一直覺得 Crawlzilla 可以做的分析，把文章跟文章之間的關係找出來。
 * [[Image(http://sociable.co/wp-content/uploads/2011/10/google-ripples.png)]]

== Hadoop ==

 * Hadoop 與 MySQL 的關係：

{{{
#!graphviz
digraph g {
  rankdir=LR; 
  subgraph cluster_1 {
   node [shape=box,width=1.0,style=filled,color=red]; 
   label = "Hadoop\n資料處理框架\nData Processing Framework";
   "HDFS"->"MapReduce";
   color=blue;
  }
  subgraph cluster_2 {
    node [shape=box,width=1.0,style=filled,color=green]; 
    label = "MySQL\n資料庫\nDatabase";
    "結構化資料\nStructured\nData";
   color=red;
  }
  node [shape=box,width=1.0,style=filled,color=gray];
  "非結構化資料\nUnstructured\nData" -> "HDFS";
  "MapReduce" -> "結構化資料\nStructured\nData";
}
}}}
 * Hadoop 與 HBase 的關係：

{{{
#!graphviz
digraph g {
  rankdir=LR; 
  subgraph cluster_2 {
    node [shape=box,width=1.0,style=filled,color=green]; 
    label = "HBase\n分散式資料存儲\nDistributed Datastore";
    color=red;
    subgraph cluster_3 {
     node [shape=box,width=1.0,style=filled]; 
     label = "HDFS";
     "結構化資料\nStructured\nData";
     node [shape=box,width=1.0,style=filled,color=red];
     "HDFS";
    }
  }
    subgraph cluster_1 {
     node [shape=box,width=1.0,style=filled,color=red]; 
     label = "Hadoop\n資料處理框架\nData Processing Framework";
     "HDFS"->"MapReduce";
     color=blue;
    }
  node [shape=box,width=1.0,style=filled,color=gray];
  "非結構化資料\nUnstructured\nData" -> "HDFS";
  "MapReduce" -> "結構化資料\nStructured\nData";
}
}}}