WIP HTML -> guided navigation conversion

pkg/content/element/attributes.go

@@ -3,6 +3,9 @@ package element
 type AttributeKey string
 
 const AcessibilityLabelAttributeKey AttributeKey = "accessibilityLabel"
+const AccessibilityDetailsAttributeKey AttributeKey = "accessibilityDetails"
+const AccessibilityLabeledByAttributeKey AttributeKey = "accessibilityLabeledBy"
+const AccessibilityDescribedByAttributeKey AttributeKey = "accessibilityDescribedBy"
 const LanguageAttributeKey AttributeKey = "language"
 
 // An attribute is an arbitrary key-value metadata pair.

pkg/content/element/element.go

@@ -86,7 +86,7 @@ func (e AudioElement) MarshalJSON() ([]byte, error) {
 	res := ElementToMap(e)
 	res["text"] = e.Text()
 	res["link"] = e.EmbeddedLink()
-	res["@type"] = "Video"
+	res["@type"] = "Audio"
 	return json.Marshal(res)
 }
 

pkg/content/iterator/html_converter.go

@@ -474,6 +474,7 @@ func (c *HTMLConverter) flushText() {
 	if len(c.breadcrumbs) > 0 {
 		el := c.breadcrumbs[len(c.breadcrumbs)-1].node
 		for _, at := range el.Attr {
+			// THIS IS WRONG! need epub:type so split the str
 			if at.Namespace == "http://www.idpf.org/2007/ops" && at.Key == "type" && at.Val == "footnote" {
 				bestRole = element.Footnote{}
 				break

pkg/guidednavigation/converter/a11y.go

@@ -0,0 +1,153 @@
+package converter
+
+import (
+	"encoding/xml"
+	"slices"
+	"strings"
+
+	"github.com/readium/go-toolkit/pkg/guidednavigation"
+	"golang.org/x/net/html"
+	"golang.org/x/net/html/atom"
+)
+
+func getElementByID(n *html.Node, id string) *html.Node {
+	if n.Type == html.ElementNode {
+		for _, a := range n.Attr {
+			if a.Key == "id" && a.Val == id {
+				return n
+			}
+		}
+	}
+	for c := n.FirstChild; c != nil; c = c.NextSibling {
+		if res := getElementByID(c, id); res != nil {
+			return res
+		}
+	}
+	return nil
+}
+
+func nodeIsHidden(n *html.Node) bool {
+	for _, attr := range n.Attr {
+		if attr.Key == "aria-hidden" && attr.Val == "true" {
+			return true
+		}
+		if attr.Key == "hidden" {
+			return true
+		}
+	}
+	return false
+}
+
+func nodeText(sb *strings.Builder, n *html.Node) {
+	var f func(*html.Node)
+	f = func(n *html.Node) {
+		if n.Type == html.TextNode {
+			sb.WriteString(n.Data)
+		}
+		if n.FirstChild != nil {
+			for c := n.FirstChild; c != nil; c = c.NextSibling {
+				f(c)
+			}
+		}
+	}
+	f(n)
+}
+
+// https://www.w3.org/TR/accname/#terminology
+// Returns the node's accessibility text if existent, and whether or not the node is visible in the first place.
+func ExtractNodeAria(el *html.Node) (*guidednavigation.GuidedNavigationText, bool) {
+	// 2.A
+	if nodeIsHidden(el) {
+		return nil, false
+	}
+
+	// 2.B
+	if labelledBy := strings.TrimSpace(getAttr(el, "aria-labelledby")); labelledBy != "" {
+		rawIds := strings.Split(strings.TrimSpace(labelledBy), " ")
+		ids := make([]string, 0, len(rawIds))
+		for _, v := range rawIds {
+			if v != "" && !slices.Contains(ids, v) {
+				ids = append(ids, v)
+			}
+		}
+
+		// Traverse up to the root of the document
+		doc := el
+		for doc.Parent != nil {
+			doc = doc.Parent
+		}
+
+		labelNodes := make([]*html.Node, 0, len(ids))
+		for _, v := range ids {
+			n := getElementByID(doc, v)
+			if n != nil {
+				labelNodes = append(labelNodes, n)
+			}
+		}
+		if len(labelNodes) > 0 {
+			var sb strings.Builder
+			for i, n := range labelNodes {
+				if nodeIsHidden(n) {
+					continue
+				}
+				if label := getAttr(n, "aria-label"); label != "" {
+					sb.WriteString(label)
+				} else {
+					nodeText(&sb, n)
+				}
+
+				if i < len(labelNodes)-1 {
+					sb.WriteRune(' ') // Add a space at the end
+				}
+			}
+			text := strings.TrimSpace(sb.String())
+			if text != "" {
+				return &guidednavigation.GuidedNavigationText{
+					Plain: text,
+				}, true
+			}
+		}
+	}
+
+	// 2.C
+	if label := strings.TrimSpace(getAttr(el, "aria-label")); label != "" {
+		return &guidednavigation.GuidedNavigationText{
+			Plain: label,
+		}, true
+	}
+
+	// 2.D
+	// TODO: more support for els
+	if el.DataAtom == atom.Img {
+		if alt := strings.TrimSpace(getAttr(el, "alt")); alt != "" {
+			return &guidednavigation.GuidedNavigationText{
+				Plain: alt,
+			}, true
+		}
+	}
+
+	return nil, true
+}
+
+func ConvertElementToSSMLTag(a atom.Atom) (string, []xml.Attr) {
+	switch a {
+	case atom.Em:
+		return "emphasis", nil
+	case atom.B:
+		return "emphasis", nil
+	case atom.I:
+		return "emphasis", []xml.Attr{{
+			Name:  xml.Name{Local: "level"},
+			Value: "reduced",
+		}}
+	case atom.Strong:
+		return "emphasis", []xml.Attr{{
+			Name:  xml.Name{Local: "level"},
+			Value: "strong",
+		}}
+	case atom.Br:
+		return "break", nil
+	default:
+		return "", nil
+	}
+}

pkg/guidednavigation/converter/converter.go

@@ -0,0 +1,42 @@
+package converter
+
+import (
+	"context"
+	"strings"
+
+	"github.com/pkg/errors"
+	"github.com/readium/go-toolkit/pkg/fetcher"
+	"github.com/readium/go-toolkit/pkg/guidednavigation"
+	"github.com/readium/go-toolkit/pkg/manifest"
+	"golang.org/x/net/html"
+	"golang.org/x/net/html/atom"
+)
+
+func Do(ctx context.Context, resource fetcher.Resource, locator manifest.Locator) (*guidednavigation.GuidedNavigationDocument, error) {
+	raw, rerr := fetcher.ReadResourceAsString(ctx, resource)
+	if rerr != nil {
+		return nil, errors.Wrap(rerr, "failed reading HTML string of "+resource.Link().Href.String())
+	}
+
+	document, err := html.ParseWithOptions(
+		strings.NewReader(raw),
+		html.ParseOptionEnableScripting(false),
+	)
+	if err != nil {
+		return nil, errors.Wrap(err, "failed parsing HTML of "+resource.Link().Href.String())
+	}
+
+	body := childOfType(document, atom.Body, true)
+	if body == nil {
+		return nil, errors.New("HTML of " + resource.Link().Href.String() + " doesn't have a <body>")
+	}
+
+	contentConverter := NewHTMLConverter(locator)
+
+	// Traverse the document's HTML
+	contentConverter.Convert(body)
+
+	return &guidednavigation.GuidedNavigationDocument{
+		Guided: contentConverter.Result(),
+	}, nil
+}

pkg/guidednavigation/converter/converter_test.go

@@ -0,0 +1,76 @@
+package converter
+
+import (
+	"context"
+	"encoding/json"
+	"testing"
+
+	"github.com/readium/go-toolkit/pkg/fetcher"
+	"github.com/readium/go-toolkit/pkg/manifest"
+	"github.com/stretchr/testify/require"
+)
+
+func TestDo(t *testing.T) {
+	f := fetcher.NewBytesResource(manifest.Link{
+		Href: manifest.MustNewHREFFromString("hello.xhtml", false),
+	}, func() []byte {
+		return []byte(`
+		<!doctype html>
+		<html xmlns:epub="http://www.idpf.org/2007/ops"><!-- lang="en" xml:lang="en" -->
+		<body>
+			<p xml:lang="fr">Paragraphe avec image: <img src="src/image.jpg" alt="A cool image" /></p>
+			<p xml:lang="fr">Paragraphe avec image #1 <img src="src/image.jpg" alt="A cool image" /> et #2 <img src="src/image.jpg" alt="A second cool image" />!</p>
+			<p xml:lang="fr"><img src="src/image.jpg" alt="The coolest image" /> et <img src="src/image.jpg" alt="The boring image" /></p>
+			<p>A paragraph with: <img src="src/image.jpg" alt="A cool image" /><em xml:lang="fr">est cool!</em></p>
+			<p><i>Simple paragraph</i></p>
+			<p>This job requires a certain <em xml:lang="fr">savoir faire</em> that can only be acquired over time.</p>
+			<p>This is a paragraph <b>with some very-<em>strong</em> bold</b> text!</p>
+			<p>Just<br />testing<br>some<br /> breaks! And useless <span>elements</span>...</p>
+
+			<div>
+			<span id="pg04" role="doc-pagebreak" epub:type="pagebreak" title="4"/>
+			<p>And the next pagebreak is in the middle <span id="pg05" role="doc-pagebreak" epub:type="pagebreak" title="4"/> of a sentence.</p>
+			</div>
+
+
+			<section role="doc-chapter" epub:type="chapter">
+				<h1>Title of the chapter</h1>
+			</section>
+			<ul>
+				<li>First item</li>
+				<li>Second item</li>
+				<li>Third item</li>
+			</ul>
+			<p aria-hidden="true">Hidden <b>text!</b> <img src="with_image.jpg" />...</p>
+			<p aria-hidden="true">More Hidden text</p>
+			<p aria-hidden="true">More Hidden text</p>
+
+			<img src="image1.avif" alt="Alternative text using the alt attribute">
+			<span role="img" aria-label="Rating: 4 out of 5 stars">
+				<span>★</span>
+				<span>★</span>
+				<span>★</span>
+				<span>★</span>
+				<span>☆</span>
+			</span>
+			<figure aria-labelledby="cat-caption"> 
+				<pre>
+				 /\_/\
+				( o.o )
+				   ^ 
+				</pre>
+				<figcaption id="cat-caption">
+				ASCII Art of a cat face
+				</figcaption>
+			</figure>
+		</body>
+		</html>`)
+	})
+
+	nav, err := Do(context.Background(), f, manifest.Locator{
+		Href: f.Link().Href.Resolve(nil, nil),
+	})
+	require.NoError(t, err)
+	bin, _ := json.MarshalIndent(nav, "", "  ")
+	t.Log(string(bin))
+}