bookhoard/internal/services/series_parsing_test.go

package services

import (
	"os"
	"path/filepath"
	"strings"
	"testing"

	"github.com/jackc/pgx/v5/pgtype"
)

func TestSplitSeriesString(t *testing.T) {
	cases := []struct{ in, name, seq string }{
		{"The Witcher #3", "The Witcher", "3"},
		{"Name #1a", "Name", "1a"},
		{"No Sequence", "No Sequence", ""},
		{"Name #1#a", "Name #1#a", ""}, // embedded # is not a sequence
	}
	for _, c := range cases {
		name, seq := splitSeriesString(c.in)
		if name != c.name || seq != c.seq {
			t.Errorf("splitSeriesString(%q) = (%q, %q), want (%q, %q)", c.in, name, seq, c.name, c.seq)
		}
	}
}

func TestSeriesSequenceNumber(t *testing.T) {
	cases := []struct {
		in    string
		num   float64
		found bool
		lossy bool
	}{
		{"3", 3, true, false},
		{"1.5", 1.5, true, false},
		{"1a", 1, true, true},
		{"Book 2", 2, true, true},
		{"2, Dramatized Adaptation", 2, true, true},
		{"", 0, false, false},
		{"novella", 0, false, false},
	}
	for _, c := range cases {
		num, found, lossy := seriesSequenceNumber(c.in)
		if num != c.num || found != c.found || lossy != c.lossy {
			t.Errorf("seriesSequenceNumber(%q) = (%v,%v,%v), want (%v,%v,%v)",
				c.in, num, found, lossy, c.num, c.found, c.lossy)
		}
	}
}

// The A2c headline bug: ABS abmetadata writes series as an array of
// "Name #seq" STRINGS. The old parser only accepted object arrays and
// silently dropped every ABS-matched series.
func TestParseSeriesCandidatesStringArray(t *testing.T) {
	raw := []byte(`["The Witcher #3", "The Witcher (Reading Order) #5"]`)
	candidates := parseSeriesCandidates(raw)
	if len(candidates) != 2 {
		t.Fatalf("got %d candidates, want 2", len(candidates))
	}
	if candidates[0].Name != "The Witcher" || candidates[0].Number != 3 || !candidates[0].HasNum {
		t.Errorf("candidate[0] = %+v", candidates[0])
	}
	if candidates[1].Name != "The Witcher (Reading Order)" || candidates[1].Number != 5 {
		t.Errorf("candidate[1] = %+v", candidates[1])
	}
	if !isPlaylistSeriesName(candidates[1].Name) {
		t.Errorf("reading-order entry must classify as playlist-ish")
	}
	if isPlaylistSeriesName(candidates[0].Name) {
		t.Errorf("publication series must not classify as playlist-ish")
	}
}

func TestParseSeriesCandidatesOtherShapes(t *testing.T) {
	objs := parseSeriesCandidates([]byte(`[{"series":"Great Series","sequence":"2.5"}]`))
	if len(objs) != 1 || objs[0].Name != "Great Series" || objs[0].Number != 2.5 {
		t.Errorf("object form: %+v", objs)
	}
	libation := parseSeriesCandidates([]byte(`"Libation Series #4"`))
	if len(libation) != 1 || libation[0].Name != "Libation Series" || libation[0].Number != 4 {
		t.Errorf("plain string form: %+v", libation)
	}
	if parseSeriesCandidates([]byte(`null`)) != nil {
		t.Errorf("null must yield no candidates")
	}
}

func TestIsPlaylistSeriesName(t *testing.T) {
	positives := []string{
		"The Witcher (Reading Order)",
		"Discworld Reading Order",
		"Narnia Chronological Order",
		"Robin Hobb in order",
		"Series Publication Order",
		"Middle Earth Timeline",
	}
	for _, p := range positives {
		if !isPlaylistSeriesName(p) {
			t.Errorf("%q should be playlist-ish", p)
		}
	}
	negatives := []string{"The Witcher", "Witcher Saga", "The Timeline of..."}
	for _, n := range negatives {
		if isPlaylistSeriesName(n) {
			t.Errorf("%q must not be playlist-ish", n)
		}
	}
}

func TestDeriveSeriesFromText(t *testing.T) {
	name, num, hasNum, ok := deriveSeriesFromText("The Witcher, Book 3")
	if !ok || name != "The Witcher" || num != 3 || !hasNum {
		t.Errorf("got (%q,%v,%v,%v)", name, num, hasNum, ok)
	}
	name, num, hasNum, ok = deriveSeriesFromText("The Witcher, Book 1.5")
	if !ok || name != "The Witcher" || num != 1.5 || !hasNum {
		t.Errorf("decimal: got (%q,%v,%v,%v)", name, num, hasNum, ok)
	}
	// Not obviously a series tail → must refuse rather than guess.
	for _, negative := range []string{"1984", "The Fellowship", "Book Ends"} {
		if _, _, _, ok := deriveSeriesFromText(negative); ok {
			t.Errorf("%q must not derive a series", negative)
		}
	}
}

func TestSplitTitleOnSubtitle(t *testing.T) {
	title, subtitle, split := splitTitleOnSubtitle("Baptism of Fire: The Witcher, Book 3")
	if !split || title != "Baptism of Fire" || subtitle != "The Witcher, Book 3" {
		t.Errorf("got (%q,%q,%v)", title, subtitle, split)
	}
	// Arbitrary colons never split.
	_, _, split = splitTitleOnSubtitle("Star Wars: A New Hope")
	if split {
		t.Errorf("non-series colon must not split")
	}
}

func TestApplyTitleDerivedSeries(t *testing.T) {
	// The user's actual naming, two-level folder, no sidecar anywhere.
	meta := &MediaMetadata{Title: "Baptism of Fire: The Witcher, Book 3"}
	applyTitleDerivedSeries(meta)
	if meta.Series != "The Witcher" || meta.SeriesNumber != 3 {
		t.Errorf("series = %q #%v, want The Witcher #3", meta.Series, meta.SeriesNumber)
	}
	if meta.Title != "Baptism of Fire: The Witcher, Book 3" {
		t.Errorf("fallback must never mutate the display title, got %q", meta.Title)
	}

	// Subtitle already split by the folder parser: number + name both land.
	meta = &MediaMetadata{Title: "Blood of Elves", Subtitle: "The Witcher, Book 1"}
	applyTitleDerivedSeries(meta)
	if meta.Series != "The Witcher" || meta.SeriesNumber != 1 {
		t.Errorf("series = %q #%v, want The Witcher #1", meta.Series, meta.SeriesNumber)
	}

	// Existing series data is never overwritten (blanks-only fallback)...
	meta = &MediaMetadata{Title: "X", Subtitle: "Derived, Book 9", Series: "Real Series"}
	applyTitleDerivedSeries(meta)
	if meta.Series != "Real Series" || meta.SeriesNumber != 0 {
		t.Errorf("a number from a different series name must not apply, got %q #%v", meta.Series, meta.SeriesNumber)
	}
	// ...but a number whose derived name MATCHES the existing series fills it.
	meta = &MediaMetadata{Title: "X", Subtitle: "Real Series, Book 9", Series: "Real Series"}
	applyTitleDerivedSeries(meta)
	if meta.Series != "Real Series" || meta.SeriesNumber != 9 {
		t.Errorf("matching-name number must fill, got %q #%v", meta.Series, meta.SeriesNumber)
	}
}

func TestPickSmartGenre(t *testing.T) {
	// The real Malazan Audible blob: one string, four genres.
	genre, all := pickSmartGenre([]string{"Epic, Action & Adventure, Military, Sword & Sorcery"})
	if genre != "action & adventure" {
		t.Errorf("genre = %q, want action & adventure", genre)
	}
	if len(all) != 4 {
		t.Errorf("candidates = %v, want the 4 split parts", all)
	}
	// Format noise never wins.
	if genre, _ := pickSmartGenre([]string{"Audiobook"}); genre != "" {
		t.Errorf("audiobook is not a genre, got %q", genre)
	}
	// Fiction is the floor: alone it resolves, against a real shelf it loses.
	if genre, _ := pickSmartGenre([]string{"Fiction"}); genre != "fiction" {
		t.Errorf("plain Fiction should still resolve, got %q", genre)
	}
	// Genre model v2: Epic Fantasy is a SUBGENRE — the genre column gets
	// its parent shelf and the specific label lives in tags. (Intended
	// change from the old longest-match behavior, which returned
	// "epic fantasy" here.)
	if genre, _ := pickSmartGenre([]string{"Fiction", "Epic Fantasy"}); genre != "fantasy" {
		t.Errorf("subgenre must resolve to its shelf, got %q", genre)
	}
	// User-verified traces (Batch B decision):
	if genre, _ := pickSmartGenre([]string{"Pirates", "Adventure"}); genre != "adventure" {
		t.Errorf("direct shelf beats mapped subgenre, got %q", genre)
	}
	if genre, _ := pickSmartGenre([]string{"Pirates"}); genre != "adventure" {
		t.Errorf("mapped subgenre alone resolves to its shelf, got %q", genre)
	}
	if genre, _ := pickSmartGenre([]string{"Sci-Fi", "Science Fiction", "Fiction"}); genre != "science fiction" {
		t.Errorf("direct shelf beats floor, got %q", genre)
	}
	// Type-words describe the library type, not a shelf.
	if genre, _ := pickSmartGenre([]string{"Manga"}); genre != "" {
		t.Errorf("manga is a type-word, got %q", genre)
	}
	// Unknown-only input: no shelf is known — tags carry it, never guess.
	if genre, all := pickSmartGenre([]string{"Completely Made-Up Genre"}); genre != "" {
		t.Errorf("unknown-only input must leave genre empty, got %q (tags=%v)", genre, all)
	}
}

func TestNormalizeLanguageCode(t *testing.T) {
	cases := []struct{ in, want string }{
		{"English", "en"},
		{"en", "en"},
		{"German", "de"},
		{"", ""},
		{"Norwegian (Bokmål)", ""}, // too long for VARCHAR(10); dropped, never truncated
		{"Pig Latin", "Pig Latin"}, // unknown display name that fits: kept
	}
	for _, c := range cases {
		if got := normalizeLanguageCode(c.in); got != c.want {
			t.Errorf("normalizeLanguageCode(%q) = %q, want %q", c.in, got, c.want)
		}
	}
}

// End-to-end: a REAL ABS-shaped sidecar (string-array series, the shape
// every ABS-matched book writes) must land series, language, explicit and
// the full author array.
func TestExtractAudiobookshelfSidecarStringArraySeries(t *testing.T) {
	dir := t.TempDir()
	sidecar := `{
		"title": "Blood of Elves",
		"authors": ["Andrzej Sapkowski"],
		"narrators": ["Peter Kenny"],
		"series": ["The Witcher #1", "The Witcher (Reading Order) #3"],
		"genres": ["Fiction"],
		"language": "English",
		"explicit": true,
		"publisher": "Orbit"
	}`
	if err := os.WriteFile(filepath.Join(dir, "metadata.json"), []byte(sidecar), 0644); err != nil {
		t.Fatal(err)
	}
	meta := extractAudiobookshelfSidecar(filepath.Join(dir, "book.m4b"))
	if meta == nil {
		t.Fatal("sidecar not extracted")
	}
	if meta.Series != "The Witcher" || meta.SeriesNumber != 1 {
		t.Errorf("series = %q #%v", meta.Series, meta.SeriesNumber)
	}
	if len(meta.Authors) != 1 || meta.Authors[0] != "Andrzej Sapkowski" {
		t.Errorf("authors array = %v", meta.Authors)
	}
	if meta.Language != "en" {
		t.Errorf("language = %q, want en", meta.Language)
	}
	if !meta.Explicit {
		t.Errorf("explicit flag lost")
	}
	if len(meta.PlaylistSeries) != 1 || meta.PlaylistSeries[0].Name != "The Witcher (Reading Order)" {
		t.Errorf("playlist series = %+v", meta.PlaylistSeries)
	}
	if meta.AlternateInfo != "" {
		t.Errorf("playlist entry must not leak into alternate_info, got %q", meta.AlternateInfo)
	}
}

// Additional real series (the Drizzt case: Icewind Dale #1 = Legend of
// Drizzt #4) land in alternate_info with the comic-established shape.
func TestExtractAudiobookshelfSidecarExtraSeriesToAlternateInfo(t *testing.T) {
	dir := t.TempDir()
	sidecar := `{
		"title": "The Crystal Shard",
		"authors": ["R.A. Salvatore"],
		"series": [
			{"series": "The Icewind Dale Trilogy", "sequence": "1"},
			{"series": "The Legend of Drizzt", "sequence": "4"}
		]
	}`
	if err := os.WriteFile(filepath.Join(dir, "metadata.json"), []byte(sidecar), 0644); err != nil {
		t.Fatal(err)
	}
	meta := extractAudiobookshelfSidecar(filepath.Join(dir, "book.m4b"))
	if meta.Series != "The Icewind Dale Trilogy" || meta.SeriesNumber != 1 {
		t.Errorf("series = %q #%v", meta.Series, meta.SeriesNumber)
	}
	if meta.AlternateInfo == "" {
		t.Fatal("second series must land in alternate_info")
	}
	// Lossy sequence text is preserved, never silently dropped.
	meta2 := extractAudiobookshelfSidecarPath(t, dir, `{"title":"X","series":["Saga #1a"]}`)
	if meta2 == nil || meta2.Series != "Saga" || meta2.SeriesNumber != 1 {
		t.Fatalf("lossy series = %+v", meta2)
	}
	if meta2.AlternateInfo == "" || !strings.Contains(meta2.AlternateInfo, "series_sequence_raw") || !strings.Contains(meta2.AlternateInfo, "1a") {
		t.Errorf("raw sequence not preserved: %q", meta2.AlternateInfo)
	}
}

func extractAudiobookshelfSidecarPath(t *testing.T, dir, json string) *MediaMetadata {
	t.Helper()
	// extractAudiobookshelfSidecar looks for exactly "metadata.json"; use a
	// fresh dir per call instead.
	fresh := t.TempDir()
	if err := os.WriteFile(filepath.Join(fresh, "metadata.json"), []byte(json), 0644); err != nil {
		t.Fatal(err)
	}
	return extractAudiobookshelfSidecar(filepath.Join(fresh, "book.m4b"))
}

// The series page tiebreaker rides on the same ordering contract the
// scanner feeds: numbers sort numerically, NULLs last (§3.6).
func TestSeriesNumberFloatOrderingValues(t *testing.T) {
	if !(pgtype.Float8{Float64: 1}.Float64 < pgtype.Float8{Float64: 1.5}.Float64) {
		t.Fatal("1 must sort before 1.5")
	}
}