bookhoard/internal/sync/cfi_verify_test.go

package sync

import (
	"fmt"
	"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)
	}
}

// The emoji in fixture doc2's third paragraph are astral plane runes:
// one rune, two UTF-16 code units. Every wire offset (CFI terminals,
// the served char_offset) must therefore be UTF-16, while the book-wide
// character_offset column stays rune-based.
//
// Case 1: the context starts at rune 31 of the paragraph text ("The
// family crest shows a globe " = 31 BMP runes), so its UTF-16 offset is
// also 31 — the currencies agree.
//
// Case 2: the context starts at rune 33 ("and a rocket ..."), with the
// astral 🌍 (rune 31, units 31-32) BEFORE the offset — the UTF-16 offset
// is 34, one more than the rune offset. That +1 is the whole point of
// the boundary conversion.
//
// Local path: p3 of doc2's div = /4/2/6, text chunk /1.
func TestAstralOffsetCurrency(t *testing.T) {
	path := writeTestEPUB(t)
	cases := []struct {
		name     string
		context  string
		wantTerm int
	}{
		{"before any emoji", "🌍 and a rocket 🚀 flying onward.", 31},
		{"after one emoji", "and a rocket 🚀 flying onward.", 34},
	}
	for _, tc := range cases {
		t.Run(tc.name, func(t *testing.T) {
			wantCFI := fmt.Sprintf("epubcfi(/6/4!/4/2/6/1:%d)", tc.wantTerm)

			finalCFI, sel, _, charOff, bookOff, _, healed, err := VerifyProgressAnchor(path, "", tc.context, 0.3)
			if err != nil {
				t.Fatalf("heal error: %v", err)
			}
			if !healed {
				t.Fatalf("expected heal from context-only submission")
			}
			if finalCFI != wantCFI {
				t.Errorf("healed CFI = %q, want %q (UTF-16 terminal)", finalCFI, wantCFI)
			}
			if sel != "body>div:nth-child(1)>p:nth-child(3)" {
				t.Errorf("cssSelector = %q", sel)
			}
			if charOff == nil || *charOff != tc.wantTerm {
				t.Errorf("block char_offset = %v, want %d UTF-16 units", charOff, tc.wantTerm)
			}
			if bookOff == nil || *bookOff <= 0 {
				t.Errorf("book offset = %v, want a positive book-wide rune offset", bookOff)
			}

			// Round trip: the healed CFI must verify exactly, with the
			// same UTF-16 block handle and a stable book offset.
			finalCFI2, _, _, charOff2, bookOff2, healedPct2, healed2, err := VerifyProgressAnchor(path, finalCFI, tc.context, 0.3)
			if err != nil {
				t.Fatalf("re-verify error: %v", err)
			}
			if healed2 || healedPct2 != nil {
				t.Errorf("exact round trip should not heal (healed=%v)", healed2)
			}
			if finalCFI2 != wantCFI {
				t.Errorf("re-verified CFI = %q, want %q", finalCFI2, wantCFI)
			}
			if charOff2 == nil || *charOff2 != tc.wantTerm {
				t.Errorf("re-verified block char_offset = %v, want %d", charOff2, tc.wantTerm)
			}
			if bookOff2 == nil || bookOff == nil || *bookOff2 != *bookOff {
				t.Errorf("book offset unstable: %v vs %v", bookOff2, bookOff)
			}
		})
	}
}

// The book-wide offset must order anchors the way the book orders them:
// a later paragraph in the same document has a strictly larger
// character_offset.
func TestBookOffsetOrdering(t *testing.T) {
	path := writeTestEPUB(t)
	_, _, _, _, book1, _, _, err1 := VerifyProgressAnchor(path, dashwoodCFI, dashwoodText, 0.3)
	_, _, _, _, book2, _, _, err2 := VerifyProgressAnchor(path, estateCFI, estateText, 0.3)
	if err1 != nil || err2 != nil {
		t.Fatalf("verify errors: %v %v", err1, err2)
	}
	if book1 == nil || book2 == nil {
		t.Fatalf("book offsets missing: %v %v", book1, book2)
	}
	if *book2 <= *book1 {
		t.Errorf("estate offset %d should exceed dashwood offset %d", *book2, *book1)
	}
}