xmlparser

README

xml stream parser

xml-stream-parser is xml parser for GO. It is efficient to parse large xml data with streaming fashion.

Usage

<?xml version="1.0" encoding="UTF-8"?>
<bookstore number="2" loc="273456">
   <book>
      <title>The Iliad and The Odyssey</title>
      <price>12.95</price>
      <comments>
         <userComment rating="4">Best translation I've read.</userComment>
         <userComment rating="2">I like other versions better.</userComment>
      </comments>
   </book>
   <book>
      <title>Anthology of World Literature</title>
      <price>24.95</price>
      <comments>
         <userComment rating="3">Needs more modern literature.</userComment>
         <userComment rating="4">Excellent overview of world literature.</userComment>
      </comments>
   </book>
   <journal>
      <title>Journal of XML parsing</title>
      <issue>1</issue>
   </journal>
</bookstore>

Stream over books and journals

f, _ := os.Open("input.xml")
br := bufio.NewReaderSize(f,65536)
parser := xmlparser.NewXMLParser(br, "book", "journal")

for xml := range parser.Stream() {
   fmt.Println(xml.Childs["title"][0].InnerText)
   if xml.Name == "book" {
      fmt.Println(xml.Childs["comments"][0].Childs["userComment"][0].Attrs["rating"])
      fmt.Println(xml.Childs["comments"][0].Childs["userComment"][0].InnerText)
   }
}

Skip tags for speed

parser := xmlparser.NewXMLParser(br, "book").SkipElements([]string{"price", "comments"})

Attributes only

parser := xmlparser.NewXMLParser(br, "bookstore", "book").ParseAttributesOnly("bookstore")

Error handlings

for xml := range parser.Stream() {
   if xml.Err !=nil {
      // handle error
   }
}

Progress of parsing

// total byte read to calculate the progress of parsing
parser.TotalReadSize

Xpath query provides alternative to default fast access for different usecases

parser := xmlparser.NewXMLParser(bufreader, "bookstore").EnableXpath()

for xml := range p.Stream() {
   // select books 
   xml.SelectElements("//book")
   xml.SelectElements("./book")
   xml.SelectElements("book")
   // select titles
   xml.SelectElements("./book/title")
   // select book with price condition
   xml.SelectElements("//book[price>=20.95]"))
   //comments with rating 4
   xml.SelectElements("//book/comments/userComment[@rating='4']")
}
// for evaluate function or reuse existing xpath expression
// sum of all the book price
expr, err := p.CompileXpath("sum(//book/price)")
price := expr.Evaluate(p.CreateXPathNavigator(xml)).(float64)

xpath functionality implemented via xpath library check more examples in its documentation

If you interested check also json parser which works similarly

Documentation

Index

• type XMLElement
  • func (n *XMLElement) FirstChild() *XMLElement
  • func (n *XMLElement) LastChild() *XMLElement
  • func (n *XMLElement) NextSibling() *XMLElement
  • func (n *XMLElement) PrevSibling() *XMLElement
  • func (n *XMLElement) SelectElement(exp string) (*XMLElement, error)
  • func (n *XMLElement) SelectElements(exp string) ([]*XMLElement, error)
• type XMLParser
  • func NewXMLParser(reader *bufio.Reader, loopElements ...string) *XMLParser
  • func (x *XMLParser) CompileXpath(expr string) (*xpath.Expr, error)
  • func (x *XMLParser) CreateXPathNavigator(top *XMLElement) *XmlNodeNavigator
  • func (x *XMLParser) EnableXpath() *XMLParser
  • func (x *XMLParser) ParseAttributesOnly(loopElements ...string) *XMLParser
  • func (x *XMLParser) SkipElements(skipElements []string) *XMLParser
  • func (x *XMLParser) SkipOuterElements() *XMLParser
  • func (x *XMLParser) Stream() chan *XMLElement
• type XmlNodeNavigator
  • func (x *XmlNodeNavigator) Copy() xpath.NodeNavigator
  • func (x *XmlNodeNavigator) Current() *XMLElement
  • func (x *XmlNodeNavigator) LocalName() string
  • func (x *XmlNodeNavigator) MoveTo(other xpath.NodeNavigator) bool
  • func (x *XmlNodeNavigator) MoveToChild() bool
  • func (x *XmlNodeNavigator) MoveToFirst() bool
  • func (x *XmlNodeNavigator) MoveToNext() bool
  • func (x *XmlNodeNavigator) MoveToNextAttribute() bool
  • func (x *XmlNodeNavigator) MoveToParent() bool
  • func (x *XmlNodeNavigator) MoveToPrevious() bool
  • func (x *XmlNodeNavigator) MoveToRoot()
  • func (x *XmlNodeNavigator) NodeType() xpath.NodeType
  • func (x *XmlNodeNavigator) Prefix() string
  • func (x *XmlNodeNavigator) String() string
  • func (x *XmlNodeNavigator) Value() string

Types

type XMLElement

type XMLElement struct {
	Name      string
	Attrs     map[string]string
	InnerText string
	Childs    map[string][]XMLElement
	Err       error
	// contains filtered or unexported fields
}

func (*XMLElement) FirstChild

func (n *XMLElement) FirstChild() *XMLElement

func (*XMLElement) LastChild

func (n *XMLElement) LastChild() *XMLElement

func (*XMLElement) NextSibling

func (n *XMLElement) NextSibling() *XMLElement

func (*XMLElement) PrevSibling

func (n *XMLElement) PrevSibling() *XMLElement

func (*XMLElement) SelectElement

func (n *XMLElement) SelectElement(exp string) (*XMLElement, error)

SelectElement finds child elements with the specified xpath expression.

func (*XMLElement) SelectElements

func (n *XMLElement) SelectElements(exp string) ([]*XMLElement, error)

SelectElements finds child elements with the specified xpath expression.

type XMLParser

type XMLParser struct {
	TotalReadSize uint64
	// contains filtered or unexported fields
}

func NewXMLParser

func NewXMLParser(reader *bufio.Reader, loopElements ...string) *XMLParser

func (*XMLParser) CompileXpath

func (x *XMLParser) CompileXpath(expr string) (*xpath.Expr, error)

Compile the given xpath expression

func (*XMLParser) CreateXPathNavigator

func (x *XMLParser) CreateXPathNavigator(top *XMLElement) *XmlNodeNavigator

CreateXPathNavigator creates a new xpath.NodeNavigator for the specified html.Node.

func (*XMLParser) EnableXpath

func (x *XMLParser) EnableXpath() *XMLParser

func (*XMLParser) ParseAttributesOnly

func (x *XMLParser) ParseAttributesOnly(loopElements ...string) *XMLParser

func (*XMLParser) SkipElements

func (x *XMLParser) SkipElements(skipElements []string) *XMLParser

func (*XMLParser) SkipOuterElements

func (x *XMLParser) SkipOuterElements() *XMLParser

by default skip elements works for stream elements childs if this method called parser skip also outer elements

func (*XMLParser) Stream

func (x *XMLParser) Stream() chan *XMLElement

type XmlNodeNavigator

type XmlNodeNavigator struct {
	// contains filtered or unexported fields
}

func (*XmlNodeNavigator) Copy

func (x *XmlNodeNavigator) Copy() xpath.NodeNavigator

func (*XmlNodeNavigator) Current

func (x *XmlNodeNavigator) Current() *XMLElement

func (*XmlNodeNavigator) LocalName

func (x *XmlNodeNavigator) LocalName() string

func (*XmlNodeNavigator) MoveTo

func (x *XmlNodeNavigator) MoveTo(other xpath.NodeNavigator) bool

func (*XmlNodeNavigator) MoveToChild

func (x *XmlNodeNavigator) MoveToChild() bool

func (*XmlNodeNavigator) MoveToFirst

func (x *XmlNodeNavigator) MoveToFirst() bool

func (*XmlNodeNavigator) MoveToNext

func (x *XmlNodeNavigator) MoveToNext() bool

func (*XmlNodeNavigator) MoveToNextAttribute

func (x *XmlNodeNavigator) MoveToNextAttribute() bool

func (*XmlNodeNavigator) MoveToParent

func (x *XmlNodeNavigator) MoveToParent() bool

func (*XmlNodeNavigator) MoveToPrevious

func (x *XmlNodeNavigator) MoveToPrevious() bool

func (*XmlNodeNavigator) MoveToRoot

func (x *XmlNodeNavigator) MoveToRoot()

func (*XmlNodeNavigator) NodeType

func (x *XmlNodeNavigator) NodeType() xpath.NodeType

func (*XmlNodeNavigator) Prefix

func (x *XmlNodeNavigator) Prefix() string

func (*XmlNodeNavigator) String

func (x *XmlNodeNavigator) String() string

func (*XmlNodeNavigator) Value

func (x *XmlNodeNavigator) Value() string