Go：为 XML 解码提升嵌套结构中的字段

Question

我有一个 XML 传输结构如下：

type urlset struct {
    XMLName xml.Name `xml:"urlset"`
    URL     []struct {
        Loc  string `xml:"loc"`
        News struct {
            Publishdate string `xml:"publication_date"`
            Title       string `xml:"title"`
            Summary     string `xml:"keywords"`
        } `xml:"news"`
    } `xml:"url"`
}

想在嵌套结构News中提升字段怎么办？

我希望我可以直接访问新闻字段并打印如下值

var URLset urlset
if xmlBytes, err := getXML(url); err != nil {
    fmt.Printf("Failed to get XML: %v", err)
} else {
    xml.Unmarshal(xmlBytes, &URLset)
}
/************************** XML parser *************************/
for _, URLElement := range URLset.URL {
fmt.Println(
    "[Element]:",
    "\nTitle #", URLElement.title,
    "\nPublicationDate #", URLElement.Publishdate,
    "\nSummary#", URLElement.Summary,
        "\nLoc #", URLElement.Loc, "\n")
}

这是我的完整代码Go Playground

Answer 1

省略名称将嵌入自身。

例子

package main

import "fmt"

type Animal struct {
    Name string
}

type Cat struct {
    Animal // 👈 Omit name
}

type Dog struct {
    A Animal // 👈 have name "A"
}

func main() {
    cat := Cat{Animal{"Kitty"}}
    fmt.Println(cat.Name)        // OK
    fmt.Println(cat.Animal.Name) // OK too
    dog := Dog{Animal{"Snoopy"}}
    // fmt.Println(dog.Name)   // Error: type Dog has no field or method Name
    fmt.Println(dog.A.Name) // OK too
}

go游乐场

---

你的情况

看足够了（其他的和你的一样。）

package main

import (
    "encoding/xml"
    "fmt"
    "io/ioutil"
    "net/http"
)

type News struct { // 👈 move to here
    Publishdate string `xml:"news>publication_date"` // 👈 Use ">" to tell its parent. https://github.com/golang/go/blob/0a1a092c4b56a1d4033372fbd07924dad8cbb50b/src/encoding/xml/typeinfo.go#L198-L199
    Title       string `xml:"news>title"`
    Summary     string `xml:"news>keywords"`
}

type urlset struct {
    XMLName xml.Name `xml:"urlset"`
    URL     []struct {
        Loc  string `xml:"loc"`
        News `xml:"news"` // 👈 do not give the name
    } `xml:"url"`
}

func getXML(url string) ([]byte, error) {
    resp, err := http.Get(url)
    if err != nil {
        return []byte{}, fmt.Errorf("GET error: %v", err)
    }
    defer resp.Body.Close()

    if resp.StatusCode != http.StatusOK {
        return []byte{}, fmt.Errorf("Status error: %v", resp.StatusCode)
    }

    data, err := ioutil.ReadAll(resp.Body)
    if err != nil {
        return []byte{}, fmt.Errorf("Read body: %v", err)
    }
    return data, nil
}

func main() {

    var URLset urlset
    /* To avoid the link not working in the future, I write the value directly.
    url := "https://www.dw.com/de/news-sitemap.xml"
    if xmlBytes, err := getXML(url); err != nil {
        fmt.Printf("Failed to get XML: %v", err)
    } else {
        xml.Unmarshal(xmlBytes, &URLset)
    }
    */

    xmlBytes := []byte(`
<urlset>
    <url>
        <loc>https://www.dw.com/de/kopf-an-kopf-rennen-bei-parlamentswahl-in-australien/a-61887162</loc>
        <news:news>
            <news:publication>
                <news:name>Deutsche Welle</news:name>
                <news:language>de</news:language>
            </news:publication>
            <news:publication_date>2022-05-21T11:28:55.875Z</news:publication_date>
            <news:title>Kopf-an-Kopf-Rennen bei Parlamentswahl in Australien</news:title>
            <news:keywords>Australien,Parlamentswahl,Scott Morrison,Anthony Albanese,Labor-Partei,Liberale</news:keywords>
        </news:news>
        <image:image>
            <image:loc>https://static.dw.com/image/61872101_403.jpg</image:loc>
            <image:caption>Der australische Premierminister Scott Morrison (r.) und sein Herausforderer, Oppositionsführer Anthony Albanese</image:caption>
        </image:image>
    </url>
    <url>
        <loc>https://www.dw.com/de/ukraine-aktuell-selenskyj-verlangt-entsch%C3%A4digungsfonds/a-61885143</loc>
        <news:news>
            <news:publication>
                <news:name>Deutsche Welle</news:name>
                <news:language>de</news:language>
            </news:publication>
            <news:publication_date>2022-05-21T11:10:21.813Z</news:publication_date>
            <news:title>Ukraine aktuell: Selenskyj verlangt Entschädigungsfonds</news:title>
            <news:keywords>Ukraine,Krieg,Russland,Wolodymyr Selenskyj,Wladimir Putin,Mariupol</news:keywords>
        </news:news>
        <image:image>
            <image:loc>https://static.dw.com/image/61885205_403.jpg</image:loc>
            <image:caption>75. Filmfestival Cannes | Rede von Wolodymyr Selenskyj</image:caption>
        </image:image>
    </url>
<urlset>
`)

    xml.Unmarshal(xmlBytes, &URLset)
    /************************** XML parser *************************/
    for _, URLElement := range URLset.URL {
        /*
           fmt.Println(
               "[Element]:",
               "\nTitle #", URLElement.News.Title,
               "\nPublicationDate #", URLElement.News.Publishdate,
               "\nSummary#", URLElement.News.Summary,
               "\nLoc #", URLElement.Loc, "\n")
        */

        fmt.Println( // 👈 Now, this work!
            "[Element]:",
            "\nTitle #", URLElement.Title,
            "\nPublicationDate #", URLElement.Publishdate,
            "\nSummary#", URLElement.Summary,
            "\nLoc #", URLElement.Loc, "\n")
    }
}

关于 XML 命名空间

• XML 命名空间提供了一种避免元素名称冲突的方法。
• 元帅.go
• 阅读.go
• typeinfo.go：准备字段名称和父母。 现在你知道为什么是“>”了吧

更多例子

• ExampleUnmarshal这个链接来自go/src/encoding/xml/example_test.go其实所有的例子都很容易理解。 所以很适合学习。