2

I need to split a string like "aa bb cc dd ee ff" in golang to

["aa bb" "bb cc" "cc dd" "dd ee" "ee ff"]

I'm trying this:

re := regexp.MustCompile("[a-z]+\\s+[a-z]+")
fmt.Printf("%q\n", re.FindAllString("aa bb cc dd ee ff", -1))

But it returns:

["aa bb" "cc dd" "ee ff"]
nanolab
  • 337
  • 1
  • 3
  • 9

3 Answers3

2

For example,

package main

import (
    "fmt"
    "strings"
)

func pairs(s string) []string {
    var p []string
    fs := strings.Fields(s)
    if len(fs) >= 2 {
        p = make([]string, 0, len(fs)-1)
        for i, f := range fs[1:len(fs)] {
            p = append(p, fs[i]+" "+f)
        }
    }
    return p
}

func main() {
    s := "aa bb cc dd ee ff"
    fmt.Printf("%q\n", s)
    p := pairs(s)
    fmt.Printf("%q\n", p)
}

Output:

"aa bb cc dd ee ff"
["aa bb" "bb cc" "cc dd" "dd ee" "ee ff"]
peterSO
  • 158,998
  • 31
  • 281
  • 276
0

You forget to say that it's a repeating pattern:

([a-z]+\\s+[a-z]+)*


The solution ((?=([a-z]{2}\s+[a-z]{2})*)) needs lookahead which is not available in go

Community
  • 1
  • 1
Thomas Ayoub
  • 29,063
  • 15
  • 95
  • 142
0

You can iterate with a bufio.Scanner:

package main

import (
   "bufio"
   "strings"
)

func abc(data []byte, eof bool) (int, []byte, error) {
   if eof {
      return 0, nil, nil
   }
   a := -1
   for b, c := range data {
      if c == ' ' {
         if a >= 0 {
            return a+1, data[:b], nil
         }
         a = b
      }
   }
   return len(data), data, nil
}

func main() {
   s := bufio.NewScanner(strings.NewReader("aa bb cc dd ee ff"))
   s.Split(abc)
   for s.Scan() {
      println(s.Text())
   }
}

https://golang.org/pkg/bufio#Scanner.Split

Zombo
  • 1
  • 62
  • 391
  • 407