Golang encoding/xml: Difference between revisions
From wikinotes
| Line 137: | Line 137: | ||
</syntaxhighlight> | </syntaxhighlight> | ||
</blockquote><!-- Custom Deserializers --> | </blockquote><!-- Custom Deserializers --> | ||
== Arbitrary XML == | |||
<blockquote> | |||
<syntaxhighlight lang="go"> | |||
import ( | |||
"encoding/xml" | |||
"fmt" | |||
) | |||
type Html struct { | |||
xmlName xml.Name `xml:"html"` | |||
Children []Node `xml:",any"` | |||
} | |||
type Node struct { | |||
Children []Node `xml:",any"` // recursively catch all nodes | |||
Attrs []string `xml:",any,attr"` // attr-values (ex. 'pages/index' in '<a href="pages/index">index</a>') | |||
Content string `xml:",innerxml"` // value (ex. 'Title' in '<h1>Title</h1>') | |||
} | |||
func main() { | |||
// define raw html | |||
raw := ` | |||
<html> | |||
<p><a href="abc">ABC</a></p> | |||
<blockquote><p><a href="def">DEF</a></p></blockquote> | |||
</html>` | |||
// deserialize recursively | |||
var parsed Html | |||
xml.Unmarshal([]byte(raw), &parsed) | |||
fmt.Println(parsed) | |||
} | |||
// {{ } [{[{[] [abc] ABC}] [] <a href="abc">ABC</a>} {[{[{[] [def] DEF}] [] <a href="def">DEF</a>}] [] <p><a href="def">DEF</a></p>}]} | |||
</syntaxhighlight> | |||
</blockquote><!-- Arbitrary XML --> | |||
</blockquote><!-- Deserialization --> | </blockquote><!-- Deserialization --> | ||
Revision as of 04:03, 10 July 2022
go's builtin library for parsing xml.
See also: golang encoding, xml
A more detailed introduction to go's encoding interface can be seen in golang encoding/json.
NOTE:
Golang's builtin xml library does not support the full xml spec.
Confirm your needs are supported before using it
Documentation
official docs https://pkg.go.dev/encoding/xml@go1.18.3
Tutorials
tutorialedge https://tutorialedge.net/golang/parsing-xml-with-golang/
Struct Tags
See full details here
type User struct { Name `xml:"Name"` // <User><Name>value</Name></User> Color `xml:"color,attr"` // <User color="value"></User> Skip `xml:"-"` // <User></User> }XML namespaces are supported, by providing a prefix to the xml tag.
type Html struct { XMLName xml.Name `xml:"http://www.w3.org/1999/xhtml html` } // <html xmlns="http://www.w3.org/1999/xhtml"> // <!-- ... --> // </html>Known issues:
- schema validation does not appear to be supported
Serializing
Basics
type User struct { Id int `xml:"id"` Name string `xml:"name,attr"` } func main() { user := User{123, "will"} bytes, _ := xml.Marshal(&user) fmt.Println(string(bytes)) // <User name="will"><id>123</id></User> }
Deserialization
Basics
type User struct { Id int `xml:"id"` Name string `xml:"name,attr"` } func main() { user := User{123, "will"} bytes, _ := xml.Marshal(&user) fmt.Println(string(bytes)) // <User name="will"><id>123</id></User> }Non-Homogenous XML
XML is generally not homogenous.
Record each possible sub-element as a field on your object.
If an element can occur multiple times, declare it as an array.
You can ignore elements by not defining fields for them.encoded := ` <mediawiki> <siteinfo> abc </siteinfo> <page> <title>Main Page</title> </page> <page> <title>Linux</title> </page> </mediawiki> ` type Result struct { XMLName xml.Name `xml:"mediawiki"` // root node SiteInfo string `xml:"siteinfo"` // only one 'siteinfo' element under 'mediawiki' Page []Page `xml:"page"` // multiple 'page' elements under 'mediawiki' } type Page struct { Title string `xml:"title"` } var result Result xml.Unmarshall([]byte(encoded), &result) fmt.Println(result.Page[0].Title.Text) // LinuxCustom Deserializers
TODO:
finish
func (revision *Revision) UnmarshalXML(d *xml.Decoder, start xml.Startelement) error { return nil }Arbitrary XML
import ( "encoding/xml" "fmt" ) type Html struct { xmlName xml.Name `xml:"html"` Children []Node `xml:",any"` } type Node struct { Children []Node `xml:",any"` // recursively catch all nodes Attrs []string `xml:",any,attr"` // attr-values (ex. 'pages/index' in '<a href="pages/index">index</a>') Content string `xml:",innerxml"` // value (ex. 'Title' in '<h1>Title</h1>') } func main() { // define raw html raw := ` <html> <p><a href="abc">ABC</a></p> <blockquote><p><a href="def">DEF</a></p></blockquote> </html>` // deserialize recursively var parsed Html xml.Unmarshal([]byte(raw), &parsed) fmt.Println(parsed) } // {{ } [{[{[] [abc] ABC}] [] <a href="abc">ABC</a>} {[{[{[] [def] DEF}] [] <a href="def">DEF</a>}] [] <p><a href="def">DEF</a></p>}]}
