feat(sync): server-side position authority — verify/heal progress anchors

Progress submissions now carry (percentage, context_text, epubcfi) and the server becomes the position authority: - VerifyProgressAnchor resolves the submitted standard CFI against the book's own XHTML, extracts the text at the anchor, and cross-checks it with the submitted context_text. A mismatch heals the anchor by text search (percentage disambiguates repeats) instead of storing a bad position. - The anchor's block element is derived as a cssSelector plus a block- relative character offset, and served on progress GET alongside the anchor document's href — readium-native handles that let clients re-open a book without parsing CFIs themselves. - context_text-only submissions (no CFI — the dumb-client tier) are anchored structurally from the context text. Motivation: cross-client progress sync (web foliate CFIs, KOReader CRE xpointers, readium-native apps) previously trusted each client's own locator math; the app's EPUB restore drifted ±pages because readium's paginator does not lay out far-from-viewport columns and the foliate- ported CFI walk ran against readium's mutated WebView DOM. Server-side verification heals both classes at ingest.
2026-09-26 14:43:34 -04:00
parent 1c1f5cf1bb
commit aec226af1a
6 changed files with 572 additions and 0 deletions
@@ -0,0 +1,158 @@
+package sync
+
+import (
+	"testing"
+)
+
+// The fixture (writeTestEPUB in cfi_converter_test.go): 6 spine docs.
+// doc2 = spine index 1 with two paragraphs:
+//   p1: "The family of Dashwood had long been settled in Sussex."
+//   p2: "Their estate was large, and their residence was at Norland Park."
+// Hand-derived local paths (html→body /4, body→div /4, div→p /4|/6,
+// p→text chunk /1):
+const (
+	dashwoodCFI    = "epubcfi(/6/4!/4/2/2/1:0)"
+	dashwoodText   = "The family of Dashwood had long been settled in Sussex."
+	estateCFI      = "epubcfi(/6/4!/4/2/4/1:0)"
+	estateText     = "Their estate was large, and their residence was at Norland Park."
+	dashwoodSelect = "body>div:nth-child(1)>p:nth-child(1)"
+	estateSelect   = "body>div:nth-child(1)>p:nth-child(2)"
+)
+
+func TestVerifyProgressAnchorAcceptsExact(t *testing.T) {
+	path := writeTestEPUB(t)
+	finalCFI, sel, _, charOff, healedPct, healed, err := VerifyProgressAnchor(path, dashwoodCFI, dashwoodText, 0.3)
+	_ = charOff
+	if err != nil {
+		t.Fatalf("verify error: %v", err)
+	}
+	if healed {
+		t.Errorf("exact anchor should not heal")
+	}
+	if healedPct != nil {
+		t.Errorf("exact anchor should not carry a healed percentage")
+	}
+	if finalCFI != dashwoodCFI {
+		t.Errorf("finalCFI = %q, want unchanged %q", finalCFI, dashwoodCFI)
+	}
+	if sel != dashwoodSelect {
+		t.Errorf("cssSelector = %q, want %q", sel, dashwoodSelect)
+	}
+}
+
+func TestVerifyProgressAnchorHealsMismatch(t *testing.T) {
+	path := writeTestEPUB(t)
+	// Anchored at p1 but the context is p2's text: the classic
+	// client-projection bug — the server must heal to the true location.
+	finalCFI, _, _, charOff, healedPct, healed, err := VerifyProgressAnchor(path, dashwoodCFI, estateText, 0.3)
+	_ = charOff
+	if err != nil {
+		t.Fatalf("verify error: %v", err)
+	}
+	if !healed {
+		t.Fatalf("expected healing, got none (cfi=%q)", finalCFI)
+	}
+	if finalCFI != estateCFI {
+		t.Errorf("healed CFI = %q, want %q", finalCFI, estateCFI)
+	}
+	if healedPct == nil || *healedPct <= 0 {
+		t.Errorf("healed percentage not recomputed: %v", healedPct)
+	}
+
+	// Healing must converge: re-verifying the healed anchor is a no-op.
+	finalCFI2, _, _, _, healedPct2, healed2, err := VerifyProgressAnchor(path, finalCFI, estateText, 0.3)
+	if err != nil {
+		t.Fatalf("re-verify error: %v", err)
+	}
+	if healed2 {
+		t.Errorf("healed anchor should be stable, got healed again to %q (pct %v)", finalCFI2, healedPct2)
+	}
+	if finalCFI2 != finalCFI {
+		t.Errorf("re-verify CFI = %q, want %q", finalCFI2, finalCFI)
+	}
+}
+
+func TestVerifyProgressAnchorHealsUnresolvable(t *testing.T) {
+	path := writeTestEPUB(t)
+	// Element index 99 is out of range in doc2 — the anchor cannot resolve.
+	bogus := "epubcfi(/6/4!/4/2/99/1:0)"
+	finalCFI, _, _, charOff, healedPct, healed, err := VerifyProgressAnchor(path, bogus, dashwoodText, 0.05)
+	_ = charOff
+	if err != nil {
+		t.Fatalf("verify error: %v", err)
+	}
+	if !healed {
+		t.Fatal("unresolvable anchor should heal from context")
+	}
+	if finalCFI != dashwoodCFI {
+		t.Errorf("healed CFI = %q, want the Dashwood anchor %q", finalCFI, dashwoodCFI)
+	}
+	if healedPct == nil {
+		t.Errorf("healed percentage not recomputed")
+	}
+}
+
+func TestVerifyProgressAnchorDumbClient(t *testing.T) {
+	path := writeTestEPUB(t)
+	// No CFI at all — a client that only knows percentage + context is
+	// fully supported: the server anchors structurally from the text.
+	finalCFI, sel, _, charOff, healedPct, healed, err := VerifyProgressAnchor(path, "", estateText, 0.3)
+	_ = charOff
+	if err != nil {
+		t.Fatalf("verify error: %v", err)
+	}
+	if !healed {
+		t.Fatal("context-only submission should count as anchored-by-heal")
+	}
+	if finalCFI != estateCFI {
+		t.Errorf("anchored CFI = %q, want %q", finalCFI, estateCFI)
+	}
+	if sel != estateSelect {
+		t.Errorf("cssSelector = %q, want %q", sel, estateSelect)
+	}
+	if healedPct == nil {
+		t.Errorf("percentage not recomputed for context-only anchor")
+	}
+}
+
+func TestContextMatches(t *testing.T) {
+	block := "The family of Dashwood had long been settled in Sussex."
+	cases := []struct {
+		name      string
+		serverCtx string
+		submitted string
+		want      bool
+	}{
+		{"exact", block, block, true},
+		{"suffix of block", block, "settled in Sussex.", true},
+		{"block is suffix", "settled in Sussex.", block, true},
+		{"mid-block substring", block, "Dashwood had long been", true},
+		{"different text", block, "completely unrelated words here", false},
+		{"too short", block, "the", false},
+		{"empty submitted", block, "", false},
+		{"empty server", "", "some long enough context text", false},
+	}
+	for _, tc := range cases {
+		if got := contextMatches(tc.serverCtx, tc.submitted); got != tc.want {
+			t.Errorf("contextMatches(%q, %q) = %v, want %v", tc.serverCtx, tc.submitted, got, tc.want)
+		}
+	}
+}
+
+func TestParseStandardCFIRange(t *testing.T) {
+	// Web progress CFIs are range CFIs; parse must resolve to the start arm.
+	spineIndex, localSteps, err := parseEPUBCFI("epubcfi(/6/4!/4/4:0,/4/4:53)")
+	if err != nil {
+		t.Fatalf("parse error: %v", err)
+	}
+	if spineIndex != 1 {
+		t.Errorf("spineIndex = %d, want 1", spineIndex)
+	}
+	if len(localSteps) != 4 {
+		t.Fatalf("steps = %d, want 4 (parent + start arm)", len(localSteps))
+	}
+	last := localSteps[len(localSteps)-1]
+	if last.Index != 4 || !last.HasOffset || last.Offset != 53 {
+		t.Errorf("start-arm step = %+v, want /4:0", last)
+	}
+}