test(sync): add cross-element matching tests, enable <em> KEPUB conversion test

cfi_converter_test.go: - TestFindTextInNode_SingleTextNode: baseline single-node match - TestFindTextInNode_CrossEmElement: 'Vokalia and Consonantia' across two <em> elements — verifies match returns the 'Vokalia' text node - TestFindTextInNode_CrossStrongElement: text crossing <strong> boundary - TestFindTextInNode_DoesNotCrossParagraphs: verifies block boundary enforcement — text split across <p> elements is NOT matched - TestFindTextInNode_NestedFormatting: <em><strong> nesting - TestFindBlockParent: verifies findBlockParent walks up through inline elements to find block-level <p> - TestCollectInlineText: verifies text segments are collected in order with correct content kepub_cfi_converter_test.go: - TestKEPUBConvertWithEmElements: previously skipped, now expects exact precision and verifies round-trip conversion works for text spanning <em> element boundaries
2026-06-03 20:00:54 -04:00
parent d5018936a0
commit 307a43f6b0
2 changed files with 154 additions and 1 deletions
@@ -1,7 +1,10 @@
 package sync

 import (
+	"strings"
 	"testing"
+
+	"golang.org/x/net/html"
 )

 func TestParseCREXPointer(t *testing.T) {
@@ -351,3 +354,141 @@ func TestReversePercentageFallback(t *testing.T) {
 		t.Error("expected empty XPointer for percentage fallback")
 	}
 }
+
+func TestFindTextInNode_SingleTextNode(t *testing.T) {
+	doc := parseTestHTML(`<html><body><p>Hello world this is a test</p></body></html>`)
+	body := findBody(doc)
+
+	node, offset := findTextInNode(body, "Hello world")
+	if node == nil {
+		t.Fatal("expected to find text")
+	}
+	if offset != 0 {
+		t.Errorf("offset = %d, want 0", offset)
+	}
+}
+
+func TestFindTextInNode_CrossEmElement(t *testing.T) {
+	doc := parseTestHTML(`<html><body><p>the countries <em>Vokalia</em> and <em>Consonantia</em> live here</p></body></html>`)
+	body := findBody(doc)
+
+	node, offset := findTextInNode(body, "Vokalia and Consonantia")
+	if node == nil {
+		t.Fatal("expected to find text across <em> elements")
+	}
+	if node.Data != "Vokalia" {
+		t.Errorf("expected match in 'Vokalia' text node, got %q", node.Data)
+	}
+	if offset != 0 {
+		t.Errorf("offset = %d, want 0", offset)
+	}
+}
+
+func TestFindTextInNode_CrossStrongElement(t *testing.T) {
+	doc := parseTestHTML(`<html><body><p>Some <strong>bold and italic</strong> text here</p></body></html>`)
+	body := findBody(doc)
+
+	node, _ := findTextInNode(body, "bold and italic text")
+	if node == nil {
+		t.Fatal("expected to find text across <strong> boundary")
+	}
+	if node.Data != "bold and italic" {
+		t.Errorf("expected match in 'bold and italic' text node, got %q", node.Data)
+	}
+}
+
+func TestFindTextInNode_DoesNotCrossParagraphs(t *testing.T) {
+	doc := parseTestHTML(`<html><body><p>first paragraph</p><p>second paragraph</p></body></html>`)
+	body := findBody(doc)
+
+	node, _ := findTextInNode(body, "paragraph second")
+	if node != nil {
+		t.Error("should not match text across <p> boundaries")
+	}
+}
+
+func TestFindTextInNode_NestedFormatting(t *testing.T) {
+	doc := parseTestHTML(`<html><body><p>before <em><strong>bold italic</strong></em> after</p></body></html>`)
+	body := findBody(doc)
+
+	node, offset := findTextInNode(body, "bold italic after")
+	if node == nil {
+		t.Fatal("expected to find text across nested formatting")
+	}
+	if node.Data != "bold italic" {
+		t.Errorf("expected match in 'bold italic' text node, got %q", node.Data)
+	}
+	_ = offset
+}
+
+func TestFindBlockParent(t *testing.T) {
+	doc := parseTestHTML(`<html><body><p>text <em>inside <strong>deep</strong></em></p></body></html>`)
+	body := findBody(doc)
+
+	var deepNode *html.Node
+	var walk func(*html.Node)
+	walk = func(n *html.Node) {
+		if n.Type == html.TextNode && n.Data == "deep" {
+			deepNode = n
+			return
+		}
+		for c := n.FirstChild; c != nil; c = c.NextSibling {
+			walk(c)
+		}
+	}
+	walk(body)
+
+	if deepNode == nil {
+		t.Fatal("could not find 'deep' text node")
+	}
+
+	block := findBlockParent(deepNode)
+	if block == nil {
+		t.Fatal("expected block parent")
+	}
+	if block.Data != "p" {
+		t.Errorf("block parent = %q, want 'p'", block.Data)
+	}
+}
+
+func TestCollectInlineText(t *testing.T) {
+	doc := parseTestHTML(`<html><body><p>the countries <em>Vokalia</em> and <em>Consonantia</em> live</p></body></html>`)
+	body := findBody(doc)
+
+	var p *html.Node
+	var walk func(*html.Node)
+	walk = func(n *html.Node) {
+		if n.Type == html.ElementNode && n.Data == "p" {
+			p = n
+			return
+		}
+		for c := n.FirstChild; c != nil; c = c.NextSibling {
+			walk(c)
+		}
+	}
+	walk(body)
+
+	if p == nil {
+		t.Fatal("could not find <p> element")
+	}
+
+	segments := collectInlineText(p)
+
+	var collected []rune
+	for _, seg := range segments {
+		collected = append(collected, seg.runes...)
+	}
+
+	flattened := strings.TrimSpace(string(collected))
+	if flattened != "the countries Vokalia and Consonantia live" {
+		t.Errorf("collected text = %q", flattened)
+	}
+}
+
+func parseTestHTML(s string) *html.Node {
+	doc, err := html.Parse(strings.NewReader(s))
+	if err != nil {
+		panic(err)
+	}
+	return doc
+}