The Go Programming Language Exercise 1.4

dup.go

//
// The Go Programming Language - Excercise 1.4
//
// Mingjie Li ([email protected])
// Jun 16, 2016
//

package main

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

func main() {
	counts := make(map[string]map[string]int)
	files := os.Args[1:]
	if len(files) == 0 {
		countLines(os.Stdin, "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, arg, counts)
			f.Close()
		}
	}
	for line, filenames := range counts {
		fileCount := len(filenames)
		if fileCount == 1 {
			total := 0
			for _, count := range filenames {
				total += count
			}
			if total <= 1 {
				continue
			}
		}

		fmt.Printf("[Found in %d file(s)]\t%s\n", fileCount, line)
		for name, count := range filenames {
			fmt.Printf("\t%d hit(s) in %s\n", count, name)
		}
	}
}

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

dup1.txt

aaa
aaa
aaa
aaa
aaa
bbb
ccc

dup2.txt

aaa
ccc
ddd

dup3.txt

ccc
ddd
xxx

dup4.txt

xxx
yyy
yyy
yyy
yyy
yyy
www

The Go Programming Language Exercise 1.4

$ ./dup dup*.txt
[Found in 1 file(s)]    yyy
        5 hit(s) in dup4.txt
[Found in 2 file(s)]    aaa
        5 hit(s) in dup1.txt
        1 hit(s) in dup2.txt
[Found in 3 file(s)]    ccc
        1 hit(s) in dup3.txt
        1 hit(s) in dup1.txt
        1 hit(s) in dup2.txt
[Found in 2 file(s)]    ddd
        1 hit(s) in dup2.txt
        1 hit(s) in dup3.txt
[Found in 2 file(s)]    xxx
        1 hit(s) in dup4.txt
        1 hit(s) in dup3.txt

Hi, Mingjie,

I was struggling with how to start this solution. Found this gist and when I saw counts := make(map[string]map[string]int) I knew how to approach the problem.

I posted my own gist, https://gist.github.com/zacharysyoung/e93862dc9a78cfe2ae964cdca71f38f0

https://gist.github.com/zacharysyoung/e93862dc9a78cfe2ae964cdca71f38f0

Nice sol for ex 1.4 :)

slight tweak to just track duplicates

package main

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

func main() {
	counts := make(map[string]map[string]int)
	files := os.Args[1:]
	if len(files) == 0 {
		countLines(os.Stdin, "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, arg, counts)
			f.Close()
		}
	}

	for line, filenames := range counts {
		for fn, ct := range filenames {
			if ct > 1 {
				fmt.Println(line, "is duplicated in ", fn, ct, "times")
			}
		}
	}
}

func countLines(f *os.File, filename string, counts map[string]map[string]int) {
	input := bufio.NewScanner(f)
	for input.Scan() {
		if counts[input.Text()] == nil {
			counts[input.Text()] = make(map[string]int)
		}
		counts[input.Text()][filename]++
	}
}