在 Go 中读取非 UTF-8 编码的文本文件

package main

import (
    "bufio"
    "fmt"
    "log"
    "os"

    "golang.org/x/text/encoding/simplifiedchinese"
    "golang.org/x/text/transform"
)

// 编码方式，这里选择 GBK。可以根据需要替换为其他编码，例如 traditionalchinese.Big5
var enc = simplifiedchinese.GBK

func main() {
    const filename = "example_GBK_file"
    exampleWriteGBK(filename)
    exampleReadGBK(filename)
}

func exampleReadGBK(filename string) {
    // 从 GBK 编码的文件中读取 UTF-8 文本。
    f, err := os.Open(filename)
    if err != nil {
        log.Fatal(err)
    }
    defer f.Close()

    // 使用 transform.NewReader 将 GBK 转换为 UTF-8
    r := transform.NewReader(f, enc.NewDecoder())

    // 从 r 中读取转换后的 UTF-8 数据。
    // 这里以逐行读取为例：
    sc := bufio.NewScanner(r)
    for sc.Scan() {
        fmt.Printf("Read line: %s\n", sc.Text()) // 使用 sc.Text() 获取 UTF-8 字符串
    }
    if err := sc.Err(); err != nil {
        log.Fatal(err)
    }
}

func exampleWriteGBK(filename string) {
    // 将 UTF-8 文本写入 GBK 编码的文件。
    f, err := os.Create(filename)
    if err != nil {
        log.Fatal(err)
    }
    defer f.Close()

    // 使用 transform.NewWriter 将 UTF-8 转换为 GBK
    w := transform.NewWriter(f, enc.NewEncoder())

    // 将 UTF-8 数据写入 w。
    _, err = fmt.Fprintln(w,
        `In 1995, China National Information Technology Standardization
Technical Committee set down the Chinese Internal Code Specification
(Chinese: 汉字内码扩展规范（GBK）; pinyin: Hànzì Nèimǎ
Kuòzhǎn Guīfàn (GBK)), Version 1.0, known as GBK 1.0, which is a
slight extension of Codepage 936. The newly added 95 characters were not
found in GB 13000.1-1993, and were provisionally assigned Unicode PUA
code points.`)
    if err != nil {
        log.Fatal(err)
    }
}