Go 查找重复的行

第一种：os.stdin

package main

import (
    "bufio"
    "fmt"
    "os"
)

func main() {
    counts := make(map[string]int)
    input := bufio.NewScanner(os.Stdin)
    for input.Scan() {
        counts[input.Text()]++
    }
    // NOTE: ignoring potential errors from input.Err()
    for line, n := range counts {
        if n > 1 {
            fmt.Printf("%d\t%s\n", n, line)
        }
    }
}

第二种：判断文件重复行

$ cat test.txt 
1112
111
222
333
222
222

package main

import (
    "bufio"
    "fmt"
    "os"
)

func main() {
    counts := make(map[string]int)
    files := os.Args[1:]
    if len(files) == 0 {
        countLines(os.Stdin, counts)
    } else {
        for _, arg := range files {
            f, err := os.Open(arg)
            if err != nil {
                fmt.Fprintf(os.Stderr, "dup2: %v\n", err)
                continue
            }
            countLines(f, counts)
            f.Close()
        }
    }
    for line, n := range counts {
        if n > 1 {
            fmt.Printf("%d\t%s\n", n, line) //打印重复数与行内容
        }
    }
}

func countLines(f *os.File, counts map[string]int) {
    input := bufio.NewScanner(f)
    for input.Scan() {
        counts[input.Text()]++
    }
    // NOTE: ignoring potential errors from input.Err()
}

$ go build dup2.go
$ ./dup2 test.txt
3   222

第三种：根据标识符判断重复内容

$ cat test.txt
111 111
111
111
222
2 2
3 4 4

package main

import (
    "fmt"
    "io/ioutil"
    "os"
    "strings"
)

func main() {
    counts := make(map[string]int)
    for _, filename := range os.Args[1:] {
        data, err := ioutil.ReadFile(filename)
        if err != nil {
            fmt.Fprintf(os.Stderr, "dup3: %v\n", err)
            continue
        }
        for _, line := range strings.Split(string(data), "\n") {
            counts[line]++
        }
    }
    for line, n := range counts {
        if n > 1 {
            fmt.Printf("%d\t%s\n", n, line)
        }
    }
}

$ ./dup3 a.txt 
2    111

参考

• 书籍：go圣经