Merge branch 'master' into amikai-itereach-pr

This reverts commit 6802fc5555.

.github/dependabot.yml

@@ -5,3 +5,8 @@ updates:
     directory: "/"
     schedule:
       interval: "daily"
+  # Enable version updates for GitHub action workflows
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "daily"

.github/workflows/test.yml

@@ -8,18 +8,18 @@ jobs:
   test:
     strategy:
       matrix:
-        go-version: [1.21.x, 1.22.x]
+        go-version: [1.23.x]
         os: [ubuntu-latest, macos-latest, windows-latest]
     runs-on: ${{ matrix.os }}
 
     steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
       - name: Install Go
-        uses: actions/setup-go@v3
+        uses: actions/setup-go@v5
         with:
           go-version: ${{ matrix.go-version }}
 
-      - name: Checkout code
-        uses: actions/checkout@v3
-
       - name: Test
         run: go test ./... -v -cover

README.md

@@ -40,6 +40,9 @@ Please note that starting with version `v1.9.0` of goquery, Go 1.18+ is required
 
 **Note that goquery's API is now stable, and will not break.**
 
+*    **2024-09-06 (v1.9.3)** : Update `go.mod` dependencies.
+*    **2024-04-29 (v1.9.2)** : Update `go.mod` dependencies.
+*    **2024-02-29 (v1.9.1)** : Improve allocation and performance of the `Map` function and `Selection.Map` method, better document the cascadia differences (thanks [@jwilsson](https://github.com/jwilsson)).
 *    **2024-02-22 (v1.9.0)** : Add a generic `Map` function, **goquery now requires Go version 1.18+** (thanks [@Fesaa](https://github.com/Fesaa)).
 *    **2023-02-18 (v1.8.1)** : Update `go.mod` dependencies, update CI workflow.
 *    **2021-10-25 (v1.8.0)** : Add `Render` function to render a `Selection` to an `io.Writer` (thanks [@anthonygedeon](https://github.com/anthonygedeon)).
@@ -89,7 +92,7 @@ Utility functions that are not in jQuery but are useful in Go are implemented as
 
 The complete [package reference documentation can be found here][doc].
 
-Please note that Cascadia's selectors do not necessarily match all supported selectors of jQuery (Sizzle). See the [cascadia project][cascadia] for details. Invalid selector strings compile to a `Matcher` that fails to match any node. Behaviour of the various functions that take a selector string as argument follows from that fact, e.g. (where `~` is an invalid selector string):
+Please note that Cascadia's selectors do not necessarily match all supported selectors of jQuery (Sizzle). See the [cascadia project][cascadia] for details. Also, the selectors work more like the DOM's `querySelectorAll`, than jQuery's matchers - they have no concept of contextual matching (for some concrete examples of what that means, see [this ticket](https://github.com/andybalholm/cascadia/issues/61)). In practice, it doesn't matter very often but it's something worth mentioning. Invalid selector strings compile to a `Matcher` that fails to match any node. Behaviour of the various functions that take a selector string as argument follows from that fact, e.g. (where `~` is an invalid selector string):
 
 * `Find("~")` returns an empty selection because the selector string doesn't match anything.
 * `Add("~")` returns a new selection that holds the same nodes as the original selection, because it didn't add any node (selector string didn't match anything).
@@ -159,6 +162,7 @@ func main() {
 - [goskyr](https://github.com/jakopako/goskyr), an easily configurable command-line scraper written in Go.
 - [goGetJS](https://github.com/davemolk/goGetJS), a tool for extracting, searching, and saving JavaScript files (with optional headless browser).
 - [fitter](https://github.com/PxyUp/fitter), a tool for selecting values from JSON, XML, HTML and XPath formatted pages.
+- [seltabl](github.com/conneroisu/seltabl), an orm-like package and supporting language server for extracting values from HTML
 
 ## Support
 
@@ -181,15 +185,15 @@ There are a number of ways you can support the project:
 
 The [BSD 3-Clause license][bsd], the same as the [Go language][golic]. Cascadia's license is [here][caslic].
 
-[jquery]: http://jquery.com/
-[go]: http://golang.org/
+[jquery]: https://jquery.com/
+[go]: https://go.dev/
 [cascadia]: https://github.com/andybalholm/cascadia
 [cascadiacli]: https://github.com/suntong/cascadia
-[bsd]: http://opensource.org/licenses/BSD-3-Clause
-[golic]: http://golang.org/LICENSE
+[bsd]: https://opensource.org/licenses/BSD-3-Clause
+[golic]: https://go.dev/LICENSE
 [caslic]: https://github.com/andybalholm/cascadia/blob/master/LICENSE
 [doc]: https://pkg.go.dev/github.com/PuerkitoBio/goquery
-[index]: http://api.jquery.com/index/
+[index]: https://api.jquery.com/index/
 [gonet]: https://github.com/golang/net/
 [html]: https://pkg.go.dev/golang.org/x/net/html
 [wiki]: https://github.com/PuerkitoBio/goquery/wiki/Tips-and-tricks

bench_iteration_test.go

@@ -25,6 +25,48 @@ func BenchmarkEach(b *testing.B) {
 	}
 }
 
+func BenchmarkEachIter(b *testing.B) {
+	var tmp, n int
+
+	b.StopTimer()
+	sel := DocW().Find("td")
+	b.StartTimer()
+	for i := 0; i < b.N; i++ {
+		for range sel.EachIter() {
+			tmp++
+		}
+		if n == 0 {
+			n = tmp
+		}
+	}
+	if n != 59 {
+		b.Fatalf("want 59, got %d", n)
+	}
+}
+
+func BenchmarkEachIterWithBreak(b *testing.B) {
+	var tmp, n int
+
+	b.StopTimer()
+	sel := DocW().Find("td")
+	b.StartTimer()
+	for i := 0; i < b.N; i++ {
+		tmp = 0
+		for range sel.EachIter() {
+			tmp++
+			if tmp >= 10 {
+				break
+			}
+		}
+		if n == 0 {
+			n = tmp
+		}
+	}
+	if n != 10 {
+		b.Fatalf("want 10, got %d", n)
+	}
+}
+
 func BenchmarkMap(b *testing.B) {
 	var tmp, n int
 

expand.go

@@ -62,7 +62,7 @@ func (s *Selection) AddBackFiltered(selector string) *Selection {
 }
 
 // AddBackMatcher reduces the previous set of elements on the stack to those that match
-// the mateher, and adds them to the curernt set.
+// the matcher, and adds them to the current set.
 // It returns a new Selection object containing the current Selection combined
 // with the filtered previous one
 func (s *Selection) AddBackMatcher(m Matcher) *Selection {

go.mod

@@ -2,7 +2,7 @@ module github.com/PuerkitoBio/goquery
 
 require (
 	github.com/andybalholm/cascadia v1.3.2
-	golang.org/x/net v0.21.0
+	golang.org/x/net v0.29.0
 )
 
-go 1.18
+go 1.23

go.sum

@@ -10,8 +10,8 @@ golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v
 golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
 golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
 golang.org/x/net v0.9.0/go.mod h1:d48xBJpPfHeWQsugry2m+kC02ZBRGRgulfHnEXEuWns=
-golang.org/x/net v0.21.0 h1:AQyQV4dYCvJ7vGmJyKki9+PBdyvhkSd8EIx/qb0AYv4=
-golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44=
+golang.org/x/net v0.29.0 h1:5ORfpBpCs4HzDYoodCDBbwHzdR5UrLBZ3sOnUJmFoHo=
+golang.org/x/net v0.29.0/go.mod h1:gLkgy8jTGERgjzMic6DS9+SP0ajcu6Xu3Orq/SpETg0=
 golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=

iteration.go

@@ -1,5 +1,7 @@
 package goquery
 
+import "iter"
+
 // Each iterates over a Selection object, executing a function for each
 // matched element. It returns the current Selection object. The function
 // f is called for each element in the selection with the index of the
@@ -12,6 +14,18 @@ func (s *Selection) Each(f func(int, *Selection)) *Selection {
 	return s
 }
 
+// EachIter returns an iterator that yields the Selection object in order.
+// The implementation is similar to Each, but it returns an iterator instead.
+func (s *Selection) EachIter() iter.Seq2[int, *Selection] {
+	return func(yield func(int, *Selection) bool) {
+		for i, n := range s.Nodes {
+			if !yield(i, newSingleSelection(n, s.document)) {
+				return
+			}
+		}
+	}
+}
+
 // EachWithBreak iterates over a Selection object, executing a function for each
 // matched element. It is identical to Each except that it is possible to break
 // out of the loop by returning false in the callback function. It returns the
@@ -37,8 +51,10 @@ func (s *Selection) Map(f func(int, *Selection) string) (result []string) {
 // Map is the generic version of Selection.Map, allowing any type to be
 // returned.
 func Map[E any](s *Selection, f func(int, *Selection) E) (result []E) {
+	result = make([]E, len(s.Nodes))
+
 	for i, n := range s.Nodes {
-		result = append(result, f(i, newSingleSelection(n, s.document)))
+		result[i] = f(i, newSingleSelection(n, s.document))
 	}
 
 	return result

iteration_test.go

@@ -105,3 +105,39 @@ func TestGenericMap(t *testing.T) {
 		t.Errorf("Expected Map array result to have a length of 3, found %v.", len(vals))
 	}
 }
+
+func TestEachIter(t *testing.T) {
+	var cnt int
+
+	sel := Doc().Find(".hero-unit .row-fluid")
+
+	for i, s := range sel.EachIter() {
+		cnt++
+		t.Logf("At index %v, node %v", i, s.Nodes[0].Data)
+	}
+
+	sel = sel.Find("a")
+
+	if cnt != 4 {
+		t.Errorf("Expected Each() to call function 4 times, got %v times.", cnt)
+	}
+	assertLength(t, sel.Nodes, 6)
+}
+
+func TestEachIterWithBreak(t *testing.T) {
+	var cnt int
+
+	sel := Doc().Find(".hero-unit .row-fluid")
+	for i, s := range sel.EachIter() {
+		cnt++
+		t.Logf("At index %v, node %v", i, s.Nodes[0].Data)
+		break
+	}
+
+	sel = sel.Find("a")
+
+	if cnt != 1 {
+		t.Errorf("Expected Each() to call function 1 time, got %v times.", cnt)
+	}
+	assertLength(t, sel.Nodes, 6)
+}

traversal.go

@@ -20,6 +20,12 @@ const (
 // Find gets the descendants of each element in the current set of matched
 // elements, filtered by a selector. It returns a new Selection object
 // containing these matched elements.
+//
+// Note that as for all methods accepting a selector string, the selector is
+// compiled and applied by the cascadia package and inherits its behavior and
+// constraints regarding supported selectors. See the note on cascadia in
+// the goquery documentation here:
+// https://github.com/PuerkitoBio/goquery?tab=readme-ov-file#api
 func (s *Selection) Find(selector string) *Selection {
 	return pushStack(s, findWithMatcher(s.Nodes, compileMatcher(selector)))
 }