Merge branch 'glebtv-setHtml'

Optimizes the *Selection.Text method and reduces allocations.

README.md

@@ -13,7 +13,7 @@ Please note that because of the net/html dependency, goquery requires Go1.1+.
     $ go get github.com/PuerkitoBio/goquery
 
 (optional) To run unit tests:
-    
+
     $ cd $GOPATH/src/github.com/PuerkitoBio/goquery
     $ go test
 
@@ -26,6 +26,8 @@ Please note that because of the net/html dependency, goquery requires Go1.1+.
 
 **Note that goquery's API is now stable, and will not break.**
 
+*    **2017-02-12 (v1.1.0)** : Add `SetHtml` and `SetText` (thanks to @glebtv).
+*    **2016-12-29 (v1.0.2)** : Optimize allocations for `Selection.Text` (thanks to @radovskyb).
 *    **2016-08-28 (v1.0.1)** : Optimize performance for large documents.
 *    **2016-07-27 (v1.0.0)** : Tag version 1.0.0.
 *    **2016-06-15** : Invalid selector strings internally compile to a `Matcher` implementation that never matches any node (instead of a panic). So for example, `doc.Find("~")` returns an empty `*Selection` object.
@@ -84,7 +86,7 @@ import (
 )
 
 func ExampleScrape() {
-  doc, err := goquery.NewDocument("http://metalsucks.net") 
+  doc, err := goquery.NewDocument("http://metalsucks.net")
   if err != nil {
     log.Fatal(err)
   }

doc/tips.md

@@ -13,7 +13,7 @@ and then:
 ```
 // Load the URL
 res, err := http.Get(url)
-if e != nil {
+if err != nil {
     // handle error
 }
 defer res.Body.Close()
@@ -65,4 +65,4 @@ Thanks to github user @jmoiron.
 [otto]: https://github.com/robertkrimen/otto
 [exotto]: https://gist.github.com/cryptix/87127f76a94183747b53
 [iconv]: http://godoc.org/?q=iconv
-[text]: http://godoc.org/code.google.com/p/go.text/encoding
+[text]: https://godoc.org/golang.org/x/text/encoding

manipulation.go

@@ -270,6 +270,17 @@ func (s *Selection) ReplaceWithNodes(ns ...*html.Node) *Selection {
 	return s.Remove()
 }
 
+// Set the html content of each element in the selection to specified html string.
+func (s *Selection) SetHtml(html string) *Selection {
+	return setHtmlNodes(s, parseHtml(html)...)
+}
+
+// Set the content of each element in the selection to specified content. The
+// provided text string is escaped.
+func (s *Selection) SetText(text string) *Selection {
+	return s.SetHtml(html.EscapeString(text))
+}
+
 // Unwrap removes the parents of the set of matched elements, leaving the matched
 // elements (and their siblings, if any) in their place.
 // It returns the original selection.
@@ -481,6 +492,18 @@ func parseHtml(h string) []*html.Node {
 	return nodes
 }
 
+func setHtmlNodes(s *Selection, ns ...*html.Node) *Selection {
+	for _, n := range s.Nodes {
+		for c := n.FirstChild; c != nil; c = n.FirstChild {
+			n.RemoveChild(c)
+		}
+		for _, c := range ns {
+			n.AppendChild(cloneNode(c))
+		}
+	}
+	return s
+}
+
 // Get the first child that is an ElementNode
 func getFirstChildEl(n *html.Node) *html.Node {
 	c := n.FirstChild

manipulation_test.go

@@ -278,6 +278,66 @@ func TestReplaceWithHtml(t *testing.T) {
 	printSel(t, doc.Selection)
 }
 
+func TestSetHtml(t *testing.T) {
+	doc := Doc2Clone()
+	q := doc.Find("#main, #foot")
+	q.SetHtml(`<div id="replace">test</div>`)
+
+	assertLength(t, doc.Find("#replace").Nodes, 2)
+	assertLength(t, doc.Find("#main, #foot").Nodes, 2)
+
+	if q.Text() != "testtest" {
+		t.Errorf("Expected text to be %v, found %v", "testtest", q.Text())
+	}
+
+	printSel(t, doc.Selection)
+}
+
+func TestSetHtmlNoMatch(t *testing.T) {
+	doc := Doc2Clone()
+	q := doc.Find("#notthere")
+	q.SetHtml(`<div id="replace">test</div>`)
+
+	assertLength(t, doc.Find("#replace").Nodes, 0)
+
+	printSel(t, doc.Selection)
+}
+
+func TestSetHtmlEmpty(t *testing.T) {
+	doc := Doc2Clone()
+	q := doc.Find("#main")
+	q.SetHtml(``)
+
+	assertLength(t, doc.Find("#main").Nodes, 1)
+	assertLength(t, doc.Find("#main").Children().Nodes, 0)
+	printSel(t, doc.Selection)
+}
+
+func TestSetText(t *testing.T) {
+	doc := Doc2Clone()
+	q := doc.Find("#main, #foot")
+	repl := "<div id=\"replace\">test</div>"
+	q.SetText(repl)
+
+	assertLength(t, doc.Find("#replace").Nodes, 0)
+	assertLength(t, doc.Find("#main, #foot").Nodes, 2)
+
+	if q.Text() != (repl + repl) {
+		t.Errorf("Expected text to be %v, found %v", (repl + repl), q.Text())
+	}
+
+	h, err := q.Html()
+	if err != nil {
+		t.Errorf("Error: %v", err)
+	}
+	esc := "&lt;div id=&#34;replace&#34;&gt;test&lt;/div&gt;"
+	if h != esc {
+		t.Errorf("Expected html to be %v, found %v", esc, h)
+	}
+
+	printSel(t, doc.Selection)
+}
+
 func TestReplaceWithSelection(t *testing.T) {
 	doc := Doc2Clone()
 	sel := doc.Find("#nf6").ReplaceWithSelection(doc.Find("#nf5"))

property.go

@@ -63,9 +63,22 @@ func (s *Selection) Text() string {
 	var buf bytes.Buffer
 
 	// Slightly optimized vs calling Each: no single selection object created
-	for _, n := range s.Nodes {
-		buf.WriteString(getNodeText(n))
+	var f func(*html.Node)
+	f = func(n *html.Node) {
+		if n.Type == html.TextNode {
+			// Keep newlines and spaces, like jQuery
+			buf.WriteString(n.Data)
+		}
+		if n.FirstChild != nil {
+			for c := n.FirstChild; c != nil; c = c.NextSibling {
+				f(c)
+			}
+		}
 	}
+	for _, n := range s.Nodes {
+		f(n)
+	}
+
 	return buf.String()
 }
 
@@ -192,22 +205,6 @@ func (s *Selection) ToggleClass(class ...string) *Selection {
 	return s
 }
 
-// Get the specified node's text content.
-func getNodeText(node *html.Node) string {
-	if node.Type == html.TextNode {
-		// Keep newlines and spaces, like jQuery
-		return node.Data
-	} else if node.FirstChild != nil {
-		var buf bytes.Buffer
-		for c := node.FirstChild; c != nil; c = c.NextSibling {
-			buf.WriteString(getNodeText(c))
-		}
-		return buf.String()
-	}
-
-	return ""
-}
-
 func getAttributePtr(attrName string, n *html.Node) *html.Attribute {
 	if n == nil {
 		return nil