1

I'm parsing a csv file from google api with golang, the file is encoded in utf-16, code below try to read one record(skip header) and print the record, but it gives me the output like this which is weird:

, v=/09/20 00:35:42 k=Smartfren Andromax AD681H

I guess it's probably related with utf-16 encoding, but don't know the detail, here is the code: package main

import (
    "encoding/csv"
    "io"
    "log"
    "net/http"
    "strings"
)

var url = "http://storage.googleapis.com/play_public/supported_devices.csv"

func main() {

    resp, err := http.Get(url)
    if err != nil {
        return
    }
    defer resp.Body.Close()

    r := csv.NewReader(resp.Body)
    r.LazyQuotes = true
    r.FieldsPerRecord = -1
    // skip header
    r.Read()

    m := make(map[string]string)
    for {
        record, err := r.Read()
        if err == io.EOF {
            break
        }
        if err != nil {
            log.Println(err)
            continue
        }
        if len(record) >= 4 {
            m[strings.TrimSpace(record[3])] = strings.TrimSpace(record[1])
            for k, v := range m {
                log.Printf("k=%s, v=%s\n", k, v)
            }
            break
        }
    }
}

1 Answer 1

4

As you suspected, the input data must be transformed from a stream of UTF-16 encoded characters to UTF-8 encoded ones. You can do that by using the Go sub-repository package golang.org/x/text/encoding/unicode:

package main

import (
    "encoding/csv"
    "io"
    "log"
    "net/http"
    "strings"

    "golang.org/x/text/encoding/unicode"
)

var url = "http://storage.googleapis.com/play_public/supported_devices.csv"

func main() {

    resp, err := http.Get(url)
    if err != nil {
        return
    }
    defer resp.Body.Close()

    dec := unicode.UTF16(unicode.LittleEndian, unicode.UseBOM).NewDecoder()
    reader := dec.Reader(resp.Body)

    r := csv.NewReader(reader)
    r.LazyQuotes = true
    r.FieldsPerRecord = -1
    // skip header
    r.Read()

    m := make(map[string]string)
    for {
        record, err := r.Read()
        if err == io.EOF {
            break
        }
        if err != nil {
            log.Println(err)
            continue
        }
        if len(record) >= 4 {
            m[strings.TrimSpace(record[3])] = strings.TrimSpace(record[1])
            for k, v := range m {
                log.Printf("k=%s, v=%s\n", k, v)
            }
            break
        }
    }
}
Sign up to request clarification or add additional context in comments.

Comments

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.