倒排索引 mr實現
阿新 • • 發佈：2018-11-09
Map階段
<0,"this is google">
....
context.write("google ->a.txt",1); context.write("google ->a.txt",1); context.write("google ->a.txt",1); context.write("google ->a.txt",1); context.write("google ->a.txt",1);
context.write("google ->b.txt",1); context.write("google ->b.txt",1); context.write("google ->b.txt",1); -------------------------------------------------------- combiner階段 <"google ->a.txt",1> <"google ->a.txt",1> <"google ->a.txt",1> <"google ->a.txt",1> <"google ->a.txt",1>
<"google ->b.txt",1> <"google ->b.txt",1> <"google ->b.txt",1>
context.write("google ","a.txt->5"); context.write("google ","b.txt->3"); -------------------------------------------------------- Reducer階段 <"hello",{"a.txt->5","b.txt->3"}>
context.write("hello","a.txt->5 b.txt->3"); ------------------------------------------------------- hello "a.txt->5 b.txt->3" tom "a.txt->2 b.txt->1" kitty "a.txt->1" .......
context.write("google ->a.txt",1); context.write("google ->a.txt",1); context.write("google ->a.txt",1); context.write("google ->a.txt",1); context.write("google ->a.txt",1);
context.write("google ->b.txt",1); context.write("google ->b.txt",1); context.write("google ->b.txt",1); -------------------------------------------------------- combiner階段 <"google ->a.txt",1> <"google ->a.txt",1> <"google ->a.txt",1> <"google ->a.txt",1> <"google ->a.txt",1>
<"google ->b.txt",1> <"google ->b.txt",1> <"google ->b.txt",1>
context.write("google ","a.txt->5"); context.write("google ","b.txt->3"); -------------------------------------------------------- Reducer階段 <"hello",{"a.txt->5","b.txt->3"}>
context.write("hello","a.txt->5 b.txt->3"); ------------------------------------------------------- hello "a.txt->5 b.txt->3" tom "a.txt->2 b.txt->1" kitty "a.txt->1" .......