ch1/ch1-03

[giscus[bot]]

ch1/ch1-03

中文版

https://gopl-zh.github.io/ch1/ch1-03.html

[featherwit001]

dup3 处理存在一些缺陷。
当文件最后一行没有换行符时，最后一行的内容不会被计入。
例子如下：
a.txt 的内容 :
ccc【CRLF】
aaa

b.txt的内容：
ddd【CRLF】
ccc

执行go run .\dup3.go a.txt b.txt， 无输出

[Steve-Lee-CST]

[CRLF] 是 "\r\n"，[LF] 是 “\n”。所以Windows下counts的最终结果为：
{ "ccc\r": 1, "aaa": 1. "ccc": 1, "ddd\r": 1 }，自然不会有输出。

[Kosthi]

unix下是有的

[Muzych]

修改后的dup2提示，在map中多加一个文件名属性

[wlwqq]

练习1.4，构造新的map存储每一行对应的文件名称

func testDup2() {
	counts := make(map[string]int)
	line2file := make(map[string]string)

	files := os.Args[1:]

	if len(files) == 0 {
		fmt.Println("please input one or more file names")
	} 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, line2file)
			f.Close()
		}
	}
	for line, n := range counts {
		if n > 1 {
			fmt.Printf("%d\t%s\t%s\n", n, line, line2file[line])
		}
	}
}
func countLines(f *os.File, counts map[string]int, line2file map[string]string) {
	input := bufio.NewScanner(f)
	for input.Scan() {
		counts[input.Text()]++
		line2file[input.Text()] = f.Name()
	}
}

[Kosthi]

可能两个文件有相同的一行内容

[xianren68]

package main

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

func main() {
	// 用于记录每行出现次数的hash表
	hash := make(map[string]int)
	// 用于记录文件名的hash表,每一行对应的文件名存到一个数组中
	fileHash := make(map[string][]string)
	// 获取命令行参数
	files := os.Args[1:]
	// 如果为空，则在控制台上输入
	if len(files) == 0 {
		countlines(os.Stdin, hash, fileHash)
	} else {
		// 不为空，遍历文件列表
		for _, file := range files {
			// 打开文件
			f, err := os.Open(file)
			// 判断文件路径等是否出错
			if err != nil {
				fmt.Println(err)
				continue
			}
			// 传入contlines进行处理
			countlines(f, hash, fileHash)
			f.Close()
		}
	}

	for i, val := range hash {
		fmt.Println(i, val)
		// 打印出现的文件
		if val > 1 {
			for _, v := range fileHash[i] {
				fmt.Printf("%s ", v)
			}
			fmt.Println()
		}
	}

}

// 用于打印输入流中每一行出现的次数
func countlines(f *os.File, hash map[string]int, fileHash map[string][]string) {
	// 创建读入流
	input := bufio.NewScanner(f)
	// 一行一行读取
	for input.Scan() {
		hash[input.Text()]++
		// 将对应的文件名加入数组
		fileHash[input.Text()] = append(fileHash[input.Text()], f.Name())
	}
}

[NotHimmel]

func main() {
        counts := make(map[string]map[string]int)
        files  := os.Args[1:]
        if len(files) == 0 {
                countLines(os.Stdin, "", counts)
        } else {
                for _, args := range files {
                        f, err := os.Open(args)
                        if err != nil {
                                fmt.Fprintf(os.Stderr, "dup2: %v\n", err)
                                continue
                        }
                        countLines(f, args, counts)
                        f.Close()
                }
        }
                for fileName, maps := range counts {
                        for line, cnt := range maps {
                                if cnt > 1 {
                                        fmt.Printf("%d\t %s in file%s\n", cnt, line, fileName)
                                }
                        }
                }
}

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

[Sherlockfanchen]

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)
//fmt.Println(files)
}
}
}

func countLines(f *os.File, counts map[string]int) {
input := bufio.NewScanner(f)
for input.Scan() {
counts[input.Text()]++
//fmt.Println(counts)
for _, num := range counts {
if num > 1 {
fmt.Println(f.Name())
}
}
}

}

在最后添加如果map里面的值大于1 则打印当前的文件名。

[CatalinaElf]

dup3在windows中可能会出现问题，由于windows中的换行默认使用的是\r\n，所以需要将上述代码进行一些修改

func main() {
	counts := make(map[string]int)
	for _, path := range os.Args[1:] {
		file, _ := os.ReadFile(path)
		for _, line := range strings.Split(string(file), "\r\n") {
			counts[line]++
		}
	}
	fmt.Println(counts)
	for data, number := range counts {
		if number > 1 {
			fmt.Printf("重复的行为：%s，重复的次数为：%d\r\n", data, number)
		}
	}
}

[CatalinaElf]

练习1.4：

// 出现重复行时打印重复行、重复次数、出现重复行的文件名称
func main() {
	counts := make(map[string]int)
	fileNameMap := make(map[string]string)
	for _, path := range os.Args[1:] {
		file, err := os.Open(path)
		if err != nil {
			_, _ = fmt.Fprintf(os.Stderr, err.Error())
		}
		countLine(file, counts, fileNameMap)
		_ = file.Close()
	}
	fmt.Println(counts)
	for data, number := range counts {
		if number > 1 {
			fmt.Printf("重复行：%s，出现重复行的文件名称：%s，重复次数：%d\r\n", data, fileNameMap[data], number)
		}
	}
}

func countLine(file *os.File, counts map[string]int, nameMap map[string]string) {
	input := bufio.NewScanner(file)
	for input.Scan() {
		counts[input.Text()]++
		nameMap[input.Text()] = file.Name()
	}
}

[Rexoen]

Exercise 1.4 support show filenames when duplicate lines are in multiple files.

package main

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

func main() {
	counts := make(map[string]int)
	fnmap := make(map[string]string)
	files := os.Args[1:]
	if len(files) == 0 {
		countLines(os.Stdin, counts, fnmap)
	} 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, fnmap)
			f.Close()
		}
	}
	for line, n := range counts {
		if n > 1 {
			fmt.Printf("%d\t%s\t%s\n", n, line, fnmap[line])
		}
	}
}

func countLines(f *os.File, counts map[string]int, line2file map[string]string) {
	input := bufio.NewScanner(f)
	for input.Scan() {
		counts[input.Text()]++
		if _, ok := line2file[input.Text()]; ok {
			if !strings.Contains(line2file[input.Text()], f.Name()) {
				line2file[input.Text()] += " " + f.Name()
			}
		} else {
			line2file[input.Text()] = f.Name()
		}
	}
}

[Kosthi]

练习 1.4：

package main

import (
	"bufio"
	"fmt"
	"log"
	"os"
	"strings"
)

func countLines(f *os.File, counts map[string]int, line2file map[string]string) {
	reader := bufio.NewScanner(f)
	for reader.Scan() {
		counts[reader.Text()]++
		if !strings.Contains(line2file[reader.Text()], f.Name()) {
			line2file[reader.Text()] += f.Name() + " "
		}
	}
}

func main() {
	counts := make(map[string]int)
	line2file := make(map[string]string)

	if len(os.Args) == 1 {
		countLines(os.Stdin, counts, line2file)
	} else {
		for _, arg := range os.Args[1:] {
			f, err := os.Open(arg)
			if err != nil {
				log.Fatal("Wrong in open file.")
			}
			countLines(f, counts, line2file)
			f.Close()
		}
	}

	for text, n := range counts {
		if n > 1 {
			fmt.Println(text, n, strings.TrimSuffix(line2file[text], " "))
		}
	}
}

[diaoyiduoxue]

// Dup1 prints the text of each line that appears more than
// once in the standard input, preceded by its count.
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)
        }
    }
}

这段代码要如何结束输入？

[shihkei]

ctrl+c

[captain5]

我的是ctrl+d

[ReReniao]

练习1.4 在输出重复行时打印文件名。
思路是直接将文件名放进map的键中，使用前面说过的字符串拼接运算符+。

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,"stdin")
	}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,arg)
			f.Close()
		}
	}
	for line,n := range counts {

		if n > 1 {
			fmt.Printf("%d\t%s\n",n, line)
		}
	}
}

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

[ReReniao]

测试输入：
go run dup2.go test.txt test1.txt
其中test：
1
22
22
333
333
333
test：
1
22
22
333
333
333
输出：
2 22 test.txt
3 333 test.txt
2 22 test1.txt
3 333 test1.txt

[ReReniao]

也可以按作者使用‘’\t‘’制表符拼接

[De1a]

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, "stdin")
	} 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, arg)
			f.Close()
		}
	}
	for line, n := range counts {
		if n > 1 {
/
			fmt.Printf("%d\t%s\n", n, line)
		}
	}
}

func countLines(f *os.File, counts map[string]int, fileName string) {
	input := bufio.NewScanner(f)
	for input.Scan() {
		counts[input.Text()]++
		if counts[input.Text()] > 1 && fileName != "stdin" {
			fmt.Printf("%s: %s\n", fileName, input.Text())
		}
	}
}

[longyi-xw]

package main

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

func main() {
	//dup1()
	//dup2()
	dup3()
}

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

func dup2() {
	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, "dup: %v\n", err)
				continue
			}
			countLines(f, counts)
			_ = f.Close()
		}
	}
	countPrint(counts)
}

func countLines(f *os.File, counts map[string]int) {
	input := bufio.NewScanner(f)
	fmt.Println("Please enter: ")
	for input.Scan() {
		line := input.Text()
		counts[line]++
	}
}
func countPrint(counts map[string]int) {
	for line, n := range counts {
		if n > 1 {
			fmt.Printf("k: %s\tv: %d\n", line, n)
		}
	}
}

func dup1() {
	counts := make(map[string]int)
	input := bufio.NewScanner(os.Stdin)
	fmt.Println("Please enter: ")
	for input.Scan() {
		text := input.Text()
		counts[text]++
		if text == "exit" {
			break
		}
	}
	countPrint(counts)
}

[lyb88999]

package main

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

func main() {
counts := make(map[string]int)
files := os.Args[1:]
if len(files) == 0 {
countLines2(os.Stdin, counts)
} else {
for _, arg := range files {
clear(counts)
f, err := os.Open(arg)
if err != nil {
fmt.Fprintf(os.Stderr, "dup2:%v\n", err)
continue
}
countLines2(f, counts)
f.Close()
for line, n := range counts {
if n > 1 {
fmt.Printf("%s\t%d\t%s\n", arg, n, line)
}
}
}
}
}

func countLines2(f *os.File, counts map[string]int) {
input := bufio.NewScanner(f)
for input.Scan() {
counts[input.Text()]++
}
}

[jianfei96]

ioutil.ReadFile is deprecated: As of Go 1.16, this function simply calls [os.ReadFile].

[jianfei96]

练习

// Dup2 prints the count and text of lines that appear more than once
// in the input.  It reads from stdin or from a list of named files.
package main

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

func main() {

	files := os.Args[1:]
	if len(files) == 0 {
		counts := make(map[string]int)
		countLines(os.Stdin, counts)
		printResult(counts, "")
	} else {
		for _, arg := range files {
			counts := make(map[string]int)
			f, err := os.Open(arg)
			if err != nil {
				fmt.Fprintf(os.Stderr, "dup2: %v\n", err)
				continue
			}
			countLines(f, counts)
			f.Close()
			printResult(counts, f.Name())
		}
	}

}

func printResult(counts map[string]int, fileName string) {
	for line, n := range counts {
		if n > 1 {
			fmt.Printf("%d\t%s\t%s\n", n, line, fileName)
		}
	}
}

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()
}

[vegetablest]

package main

import (
"fmt"
"os"
"strings"
)

func main() {
counts := make(map[string]int)
for _, file := range os.Args[1:] {
if data, err := os.ReadFile(file); err == nil {
for _, line := range strings.Split(string(data), "\n") {
counts[file + ":" + line]++
}
} else {
fmt.Fprintf(os.Stderr, "dup3: %v\n", err)
continue
}
}
for file_line, value := range counts {
if value > 1 {
result := strings.SplitN(file_line, ":", 2)
fmt.Printf("%s\t%d\t%s\n", result[0], value, result[1])
}
}
}

[vegetablest]

package main

import (
	"fmt"
	"os"
	"strings"
)

func main() {
	counts := make(map[string]int)
	for _, file := range os.Args[1:] {
		if data, err := os.ReadFile(file); err == nil {
			for _, line := range strings.Split(string(data), "\n") {
				counts[file + ":" + line]++
			}
		} else {
			fmt.Fprintf(os.Stderr, "dup3: %v\n", err)
			continue
		}
	}
	for file_line, value := range counts {
		if value > 1 {
			result := strings.SplitN(file_line, ":", 2)
			fmt.Printf("%s\t%d\t%s\n", result[0], value, result[1])
		}
	}
}

[ConstasJ]

顺带一提，ioutils.ReadFile从Go 1.16开始已经被弃用，请改用os.ReadFile

[GaytHub]

打卡

[coderZoe]

练习：

func dup2() {
	counts := make(map[string][]string)
	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 len(n) > 1 {
			//如果打印的文件名嫌有重复的就写个函数，用map记录下打印过的
			fmt.Printf("%v\t%d\t%s\n", n, len(n), line)
		}
	}
}

func countLines(f *os.File, counts map[string][]string) {
	input := bufio.NewScanner(f)
	for input.Scan() {
		var slice = counts[input.Text()]
		if slice == nil {
			slice = []string{f.Name()}
		} else {
			slice = append(slice, f.Name())
		}
		counts[input.Text()] = slice
	}
}

[Platohykj]

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, "stdin")
} else {
for filename, arg := range files {
f, err := os.Open(arg)
if err != nil {
fmt.Fprintf(os.Stderr, "dup2: %v\n", err)
continue
}
countLines(f, counts, files[filename])
f.Close()
}
}
for line, n := range counts {
if n > 1 {
fmt.Printf("%d\t%s\n", n, line)
}
}
}

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

[zhaoyanggh]

// Dup2 prints the count and text of lines that appear more than once
// in the input. It reads from stdin or from a list of named files.
package main

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

func main() {
counts := make(map[string]int)
files := os.Args[1:]
fileName := ""
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
}
fileName = f.Name()
countLines(f, counts)
f.Close()
}
}
for line, n := range counts {
if n > 1 {
fmt.Printf("%d\t%s\t%s\n", n, line, fileName)
}
}
}

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()
}

[Apahno]

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)
//	}
//}

}

func countLines(f *os.File, counts map[string]int) {
dupfilename := make(map[string]int)
input := bufio.NewScanner(f)
for input.Scan() {
counts[input.Text()]++
dupfilename[input.Text()]++
}
for _, n := range dupfilename {
if n > 1 {
fmt.Printf("出现重复行的文件名是%s\n", f.Name())
break
}
}
// NOTE: ignoring potential errors from input.Err()
}

[skyfisher]

// Dup2 prints the count and text of lines that appear more than once
// in the input. It reads from stdin or from a list of named files.
package main

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

func main() {
counts := make(map[string]int)
map_line2file := make(map[string][]string)
files := os.Args[1:]
if len(files) == 0 {
countLines(os.Stdin, counts, map_line2file)
} 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, map_line2file)

		// 当文件中出现重复行时，输出文件名
		for line, n := range(counts) {
			if n > 1 {
				fmt.Printf("%s, %s\n", arg,line)
			}
		}
        f.Close()
    }
}
for line, n := range counts {
    if n > 1 {
        fmt.Printf("%d\t%s\t%s\n", n, line, strings.Join(map_line2file[line], " "))
    }
}

}

func countLines(f *os.File, counts map[string]int, map_line2file map[string][]string) {
input := bufio.NewScanner(f)
for input.Scan() {
counts[input.Text()]++

	// 判断文件名是否已经在数组中，如果不再，则不添加文件名
	if stringIn(map_line2file[input.Text()], f.Name()) {
		continue
	} else {
		map_line2file[input.Text()] = append(map_line2file[input.Text()], f.Name())
	}
}
// NOTE: ignoring potential errors from input.Err()

}

// 判断字符数组中是否有某个元素
func stringIn(m_list []string, element string) bool {
for _, m := range m_list {
if m == element {
return true
}
}
return false
}

[swanGooseMan]

for line, n := range counts {
	if n > 1 {
		fmt.Printf("%d\t%s\t%s\n", n, line, os.Args[1])
	}
}

[qq1u]

package main

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

func main() {
	mapping := make(map[string][]string)

	counts := make(map[string]int)
	files := os.Args[1:]
	if len(files) == 0 {
		countLines(os.Stdin, counts, mapping)
	} 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, mapping)
			f.Close()
		}
	}
	for line, n := range counts {
		if n > 1 {
			fmt.Printf("%d\tfilename%s: %s\n", n, mapping[line], line)
		}
	}
}

func countLines(f *os.File, counts map[string]int, mapping map[string][]string) {
	input := bufio.NewScanner(f)
	line := 1
	for input.Scan() {
		text := input.Text()
		counts[text]++
		mapping[text] = append(mapping[text], fmt.Sprintf("%s:%d", f.Name(), line))
		line++
	}
}

[blair-0]

package main

import (
"fmt"
"os"
"strings"
)

type Counts struct {
linecounts int
filecounts map[string]int
}

func main() {
dup := make(map[string]*Counts)

for _, filename := range os.Args[1:] {
	data, err := os.ReadFile(filename)
	if err != nil {
		fmt.Fprintf(os.Stderr, "dup3: %v\n", err)
		continue
	}
	for _, line := range strings.Split(string(data), "\n") {
		_, exists := dup[line]
		if !exists {
			dup[line] = &Counts{
				linecounts: 0,
				filecounts: make(map[string]int),
			}

		}
		dup[line].linecounts++
		dup[line].filecounts[filename]++
	}
}

for line, ct := range dup {
	if ct.linecounts > 1 {
		fmt.Printf("%d\t%s\n\tfilenames: %v\n", ct.linecounts, line, ct.filecounts)
	}
}

}

[blair-0]

package main

import (
"fmt"
"os"
"strings"
)

type Counts struct {
linecounts int
filecounts map[string]int
}

func main() {
dup := make(map[string]*Counts)

for _, filename := range os.Args[1:] {
	data, err := os.ReadFile(filename)
	if err != nil {
		fmt.Fprintf(os.Stderr, "dup3: %v\n", err)
		continue
	}
	for _, line := range strings.Split(string(data), "\n") {
		_, exists := dup[line]
		if !exists {
			dup[line] = &Counts{
				linecounts: 0,
				filecounts: make(map[string]int),
			}

		}
		dup[line].linecounts++
		dup[line].filecounts[filename]++
	}
}

for line, ct := range dup {
	if ct.linecounts > 1 {
		fmt.Printf("%d\t%s\n\tfilenames: %v\n", ct.linecounts, line, ct.filecounts)
	}
}

}

[chineseandy]

/**
添加了退出循环条件，不然下面的代码都不执行吧
*/
func main() {
counts := make(map[string]int)
input := bufio.NewScanner(os.Stdin)
for input.Scan() {
counts[input.Text()]++
if input.Text() == "exit" {
break
}
}
for line, n := range counts {
if n > 1 {
fmt.Printf("%d\t%s\n", n, line)
}
}
}