0.2.3

.vscode/settings.json

@@ -1,11 +1,14 @@
 {
 "cSpell.words": [
+"arraystack",
 "autoplay",
+"Combinators",
 "DOCTYPEDTD",
 "emirpasic",
 "gohtml",
 "Kottue",
 "linkedliststack",
+"println",
 "yosssi"
 ]
 }

FUTURE-CHANGELOG.md

@@ -1,2 +1 @@
-## v0.0.3
-- Closest
+

README.md

@@ -26,35 +26,27 @@ import (
 - Querying
 
 ## Example
+
 Heres an example of fetching a website and parsing and then using querying methods.
+
 ```go
 res, err := http.Get("https://www.metalsucks.net/")
 if err != nil {
 t.Fatal(err)
 }
 defer res.Body.Close()
 
-//Parses the given html reader and then returns the root node and an error.
 node, err := GoHtml.Decode(res.Body)
 if err != nil {
 t.Fatal(err)
 }
 
-nodeList := node.GetElementsByClassName("post-title")
-iter := nodeList.IterNodeList()
-for node := range iter{
-print(node.GetInnerText())
+nodeList := node.QuerySelectorAll(".left-content article .post-title")
+for node := range nodeList.IterNodeList(){
+println(node.GetInnerText())
 }
 ```
 
-## Changelog
-
-Changes, bug fixes and new features in this version.
-- add: Tokenizer
-- add: NodeTreeBuilder
-- renamed: QuerySelector to Query
-- renamed: QuerySelectorAll to QueryAll
-
 ## Documentation
 
 Fully fledged [documentation](https://pkg.go.dev/github.com/udan-jayanith/GoHTML) is available at [go.pkg](https://pkg.go.dev/)

benchmarks/benchmark_test.go

@@ -6,7 +6,9 @@ import(
 "net/http"
 "time"
 )
-
+/*
+Adapted from [GoQuery example](https://github.com/PuerkitoBio/goquery?tab=readme-ov-file#examples)
+*/
 func TestFetchPostCovers(t *testing.T){
 res, err := http.Get("https://www.metalsucks.net/")
 if err != nil {
@@ -20,7 +22,7 @@ func TestFetchPostCovers(t *testing.T){
 t.Fatal(err)
 }
 
-nodeList := node.QueryAll(".sm-feat .clearfix article")
+nodeList := node.QuerySelectorAll(".left-content article .post-title")
 t.Log("Got ", nodeList.Len(), " post titles.")
 iter := nodeList.IterNodeList()
 for node := range iter{

classList.go

@@ -68,7 +68,7 @@ func (classList ClassList) Encode() string {
 return classes
 }
 
-// EncodeTo encode className for the node.
+// EncodeTo encodes classNames for the node.
 // If node is nil EncodeTo does nothing.
 func (classList ClassList) EncodeTo(node *Node){
 if node == nil {

classList_test.go

@@ -1,31 +1,63 @@
 package GoHtml_test
 
-import(
+import (
+"fmt"
 "testing"
-"github.com/udan-jayanith/GoHTML"
+
+GoHtml "github.com/udan-jayanith/GoHTML"
 )
 
-func TestClasses(t *testing.T){
+func TestClasses(t *testing.T) {
 node := GoHtml.CreateNode("div")
 node.SetAttribute("class", "div-container main")
 
 classList := GoHtml.NewClassList()
 classList.DecodeFrom(node)
-if !classList.Contains("main"){
+if !classList.Contains("main") {
 t.Fatal("")
 return
 }
 classList.DeleteClass("main")
-if classList.Contains("main"){
+if classList.Contains("main") {
 t.Fatal("")
 return
 }
 
 classList.AppendClass("main-div")
-if !classList.Contains("main-div"){
+if !classList.Contains("main-div") {
 t.Fatal("")
 return
 }
 
 classList.EncodeTo(node)
+}
+
+func ExampleClassList_Contains() {
+//Creates a div that has classes video-container and main-contents
+div := GoHtml.CreateNode("div")
+div.SetAttribute("class", "video-container main-contents")
+
+classList := GoHtml.NewClassList()
+//Add the classes in the div to the class list
+classList.DecodeFrom(div)
+
+//Checks wether the following classes exists in the classList
+fmt.Println(classList.Contains("container"))
+fmt.Println(classList.Contains("video-container"))
+
+//Output:
+//false
+//true
+}
+
+func ExampleClassList_Encode(){
+classList := GoHtml.NewClassList()
+
+//Add classes to the class list
+classList.AppendClass("container")
+classList.AppendClass("warper")
+classList.AppendClass("main-content")
+
+//This would output something like this "warper container main-content". Order of the output is not guaranteed.
+fmt.Println(classList.Encode())
 }

node-list.go

@@ -5,7 +5,7 @@ import (
 "iter"
 )
 
-//NodeList can store nodes by appended order.
+//NodeList can store nodes by appended order and can iterate over the node list by invoking IterNodeList method.
 type NodeList struct {
 list *list.List
 currentEl *list.Element

node-list_test.go

@@ -1,6 +1,7 @@
 package GoHtml_test
 
 import (
+"fmt"
 "os"
 "testing"
 
@@ -13,6 +14,7 @@ func TestIterNodeList1(t *testing.T) {
 t.Fatal(err)
 return
 }
+defer file.Close()
 
 node, err := GoHtml.Decode(file)
 if err != nil {
@@ -39,4 +41,20 @@ func TestIterNodeList2(t *testing.T){
 for node := range iter{
 t.Log(node)
 }
+}
+
+func ExampleNodeList(){
+nodeList := GoHtml.NewNodeList()
+nodeList.Append(GoHtml.CreateNode("br"))
+nodeList.Append(GoHtml.CreateNode("hr"))
+nodeList.Append(GoHtml.CreateNode("div"))
+
+iter := nodeList.IterNodeList()
+for node := range iter{
+fmt.Println(node.GetTagName())
+}
+//Output: 
+//br
+//hr 
+//div
 }

node-tree.go

@@ -2,6 +2,7 @@ package GoHtml
 
 import (
 "strings"
+
 "golang.org/x/net/html"
 )
 
@@ -38,7 +39,7 @@ func (node *Node) SetPreviousNode(previousNode *Node) {
 node.previousNode = previousNode
 }
 
-// GetChildNode returns the first child elements of this node.
+// GetChildNode returns the first child node of this node.
 func (node *Node) GetChildNode() *Node {
 return node.childNode
 }
@@ -75,7 +76,7 @@ func (node *Node) GetAttribute(attributeName string) (string, bool) {
 // RemoveAttribute remove or delete the specified attribute.
 func (node *Node) RemoveAttribute(attributeName string) {
 delete(node.attributes, strings.TrimSpace(strings.ToLower(attributeName)))
-
+
 }
 
 // IterateAttributes calls callback at every attribute in the node by passing attribute and value of the node.
@@ -114,19 +115,21 @@ func (node *Node) AppendChild(childNode *Node) {
 
 lastNode := node.GetChildNode().GetLastNode()
 childNode.SetPreviousNode(lastNode)
+childNode.setParentNode(lastNode.GetParent())
 lastNode.SetNextNode(childNode)
 }
 
 // Append inserts the newNode to end of the node chain.
 func (node *Node) Append(newNode *Node) {
 lastNode := node.GetLastNode()
 newNode.SetPreviousNode(lastNode)
+newNode.setParentNode(lastNode.GetParent())
 lastNode.SetNextNode(newNode)
 }
 
 // GetParent returns a pointer to the parent node.
 func (node *Node) GetParent() *Node {
-return node.GetFirstNode().getParentNode()
+return node.parentNode
 }
 
 // GetLastNode returns the last node in the node branch.
@@ -203,3 +206,21 @@ func (node *Node) RemoveNode() {
 func (node *Node) IsTextNode() bool {
 return node.GetTagName() == ""
 }
+
+// Closest traverses the node tree and its parents (heading toward the root node) until it finds a node that matches the selector and returns that node.
+// Adapted from [https://developer.mozilla.org/en-US/docs/Web/API/Element/closest](MDN Element: closest() method)
+func (node *Node) Closest(selector string) *Node {
+traverser := NewTraverser(node)
+selectors := TokenizeSelectorsAndCombinators(selector)
+
+for traverser.GetCurrentNode() != nil {
+if matchFromRightMostSelectors(traverser.GetCurrentNode(), selectors) {
+break
+} else if traverser.GetCurrentNode().GetPreviousNode() == nil {
+traverser.SetCurrentNodeTo(traverser.GetCurrentNode().GetParent())
+} else {
+traverser.Previous()
+}
+}
+return traverser.GetCurrentNode()
+}

node-tree_test.go

@@ -112,4 +112,24 @@ func TestRemoveNode(t *testing.T){
 
 //p.RemoveNode()
 //t.Log(GoHtml.NodeTreeToHTML(article))
+}
+
+func TestClosest(t *testing.T){
+node, err := testFile4NodeTree()
+if err != nil{
+t.Fatal(err)
+}
+node = node.GetElementByClassName("ordered-item")
+if node == nil {
+t.Fatal("Node is nil.")
+}
+
+node = node.Closest("img+.ordered-list")
+if node == nil {
+t.Fatal("Node is nil")
+}else if node.GetTagName() != "ol"{
+t.Fatal("Unexpected element.")
+}
+
+
 }

parser.go

@@ -3,24 +3,23 @@ package GoHtml
 import (
 "io"
 "strings"
+
 "golang.org/x/net/html"
 )
 
-
 // Decode reads from rd and create a node-tree. Then returns the root node and nil.
 func Decode(r io.Reader) (*Node, error) {
 t := NewTokenizer(r)
 nodeTreeBuilder := NewNodeTreeBuilder()
 for {
 tt := t.Advanced()
-if tt == html.ErrorToken{
+if tt == html.ErrorToken {
 break
 }
 
-nodeTreeBuilder.WriteNodeTree(t.CurrentNode(), tt)
+nodeTreeBuilder.WriteNodeTree(t.GetCurrentNode(), tt)
 }
 return nodeTreeBuilder.GetRootNode(), nil
-
 }
 
 // HTMLToNodeTree return html code as a node-tree. If error were to occur it would be SyntaxError.
@@ -30,4 +29,3 @@ func HTMLToNodeTree(html string) (*Node, error) {
 return node, err
 }
 
-

parser_test.go

@@ -1,6 +1,7 @@
 package GoHtml_test
 
 import (
+"fmt"
 "os"
 "strings"
 "testing"
@@ -14,6 +15,7 @@ func TestDecode(t *testing.T) {
 t.Fatal(err)
 return
 }
+defer file.Close()
 
 node, err := GoHtml.Decode(file)
 if err != nil {
@@ -24,3 +26,31 @@ func TestDecode(t *testing.T) {
 var builder strings.Builder
 GoHtml.Encode(&builder, node)
 }
+
+func ExampleDecode() {
+r := strings.NewReader(`
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<meta name="viewport" content="width=device-width, initial-scale=1.0">
+<title>User Profile</title>
+</head>
+<body>
+<h1 class="username">Udan</h1>
+<p class="email">udanjayanith@gmail.com</p>
+<p>Joined: 01/08/2024</p>
+</body>
+</html>
+`)
+
+rootNode, _ := GoHtml.Decode(r)
+
+titleNode := rootNode.QuerySelector("title")
+title := ""
+if titleNode != nil {
+title = titleNode.GetInnerText()
+}
+fmt.Println(title)
+//Output: User Profile
+}