See https://github.com/chrislusf/gleam/blob/master/README.md
Many people may know Gleam used to support only LuaJIT for distributed map
reduce.
After several rounds of re-thinking, I came down to this syntax to do it
via pure Go. Please let me know whether it seems ok or can be better.
Chris
package main
import (
"strings"
"os"
"github.com/chrislusf/gleam/flow"
"github.com/chrislusf/gleam/gio"
)
var (
MapperTokenizer = gio.RegisterMapper(tokenize)
MapperAddOne = gio.RegisterMapper(addOne)
ReducerSum = gio.RegisterReducer(sum)
)
func main(){
gio.Init() // required, place it right after main() starts
flow.New().TextFile("/etc/passwd").
Mapper(MapperTokenizer). // invoke the registered "tokenize" mapper
function.
Mapper(MapperAddOne). // invoke the registered "addOne" mapper
function.
ReducerBy(ReducerSum). // invoke the registered "sum" reducer
function.
Sort(flow.OrderBy(2, true)).
Fprintf(os.Stdout, "%s %d\n").Run()
}
func tokenize(row []interface{}) error {
line := string(row[0].([]byte))
for _, s := range strings.FieldsFunc(line, func(r rune) bool {
return !('A' <= r && r <= 'Z' || 'a' <= r && r <= 'z' || '0' <= r && r
<= '9')
}) {
gio.Emit(s)
}
return nil
}
func addOne(row []interface{}) error {
word := string(row[0].([]byte))
gio.Emit(word, 1)
return nil
}
func sum(x, y interface{}) (interface{}, error) {
return x.(uint64) + y.(uint64), nil
}
--
You received this message because you are subscribed to the Google Groups
"golang-nuts" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to golang-nuts+unsubscr...@googlegroups.com.
For more options, visit https://groups.google.com/d/optout.
