Vellum/internal/media/discover.go

package media

import (
	"context"
	"database/sql"
	"fmt"
	"math/rand"
	"strings"
)

// RecordView increments a user's view count for an item.
//
// Called when an item is opened in a reader, so the count reflects consumption
// rather than a detail-page fetch. Opening the same thing repeatedly still
// counts: "most viewed" should reflect habit, not just distinct items.
func RecordView(ctx context.Context, db *sql.DB, userID, itemID int64) (int, error) {
	var views int
	err := db.QueryRowContext(ctx, `
		INSERT INTO item_views (user_id, item_id, views, last_viewed_at)
		VALUES (?, ?, 1, ?)
		ON CONFLICT (user_id, item_id)
		DO UPDATE SET views = views + 1, last_viewed_at = excluded.last_viewed_at
		RETURNING views`,
		userID, itemID, nowRFC3339()).Scan(&views)
	if err != nil {
		return 0, fmt.Errorf("media: record view: %w", err)
	}
	return views, nil
}

// MostViewed returns the user's most-opened items within the given libraries.
func MostViewed(ctx context.Context, db *sql.DB, userID int64, libraryIDs []int64, limit int) ([]shelfItem, error) {
	if len(libraryIDs) == 0 {
		return []shelfItem{}, nil
	}
	if limit <= 0 || limit > 100 {
		limit = 20
	}
	in, args := inClause(libraryIDs)
	args = append([]any{userID}, args...)
	args = append(args, limit)

	query := `
		SELECT i.id, i.library_id, i.kind, i.title, v.views, v.last_viewed_at
		FROM item_views v
		JOIN media_items i ON i.id = v.item_id
		WHERE v.user_id = ? AND i.missing = 0
		  AND i.library_id IN (` + in + `)
		ORDER BY v.views DESC, v.last_viewed_at DESC
		LIMIT ?`

	rows, err := db.QueryContext(ctx, query, args...)
	if err != nil {
		return nil, fmt.Errorf("media: most viewed: %w", err)
	}
	defer rows.Close()

	out := []shelfItem{}
	for rows.Next() {
		var s shelfItem
		if err := rows.Scan(&s.ID, &s.LibraryID, &s.Kind, &s.Title, &s.Views, &s.UpdatedAt); err != nil {
			return nil, err
		}
		out = append(out, s)
	}
	return out, rows.Err()
}

// itemRef is a lightweight item used by the suggestion and explore queries.
type itemRef struct {
	ID        int64
	LibraryID int64
	Kind      string
	Title     string
	Year      int
}

// engagement describes what a user has been consuming, which is the basis for
// suggestions.
type engagement struct {
	Kind   string
	Title  string
	Author string
}

// topEngagement finds the kind and author the user most recently engaged with,
// so suggestions can be explained in plain language.
func topEngagement(ctx context.Context, db *sql.DB, userID int64, libraryIDs []int64) (engagement, bool, error) {
	var e engagement
	// Scoped to libraries the user can still read. Without this, progress from a
	// library whose grant was revoked would keep steering the home screen's
	// suggestions — confusing on its own, and an information-flow leak about
	// content the user no longer has access to.
	in, inArgs := inClause(libraryIDs)
	args := append([]any{userID}, inArgs...)
	err := db.QueryRowContext(ctx, `
		SELECT i.kind, i.title,
		       COALESCE((SELECT p.name FROM item_people ip
		                 JOIN people p ON p.id = ip.person_id
		                 WHERE ip.item_id = i.id AND ip.role = 'author'
		                 ORDER BY ip.ord LIMIT 1), '')
		FROM progress p
		JOIN media_items i ON i.id = p.item_id
		WHERE p.user_id = ? AND i.missing = 0
		  AND i.library_id IN (`+in+`)
		ORDER BY p.updated_at DESC
		LIMIT 1`, args...).Scan(&e.Kind, &e.Title, &e.Author)
	if err == sql.ErrNoRows {
		return engagement{}, false, nil
	}
	if err != nil {
		return engagement{}, false, fmt.Errorf("media: top engagement: %w", err)
	}
	return e, true, nil
}

// Suggestions returns unstarted items related to what the user has been
// consuming: same author first, then the same kind, then anything recent.
//
// The rule is deliberately legible — a suggestion a person cannot understand is
// just noise. Each result carries the reason it was chosen.
func Suggestions(ctx context.Context, db *sql.DB, userID int64, libraryIDs []int64, limit int) ([]suggestion, error) {
	if len(libraryIDs) == 0 {
		return []suggestion{}, nil
	}
	if limit <= 0 || limit > 50 {
		limit = 20
	}

	e, hasEngagement, err := topEngagement(ctx, db, userID, libraryIDs)
	if err != nil {
		return nil, err
	}

	in, inArgs := inClause(libraryIDs)
	out := []suggestion{}
	seen := map[int64]bool{}

	add := func(rows *sql.Rows, reason string) error {
		defer rows.Close()
		for rows.Next() {
			var r itemRef
			if err := rows.Scan(&r.ID, &r.LibraryID, &r.Kind, &r.Title, &r.Year); err != nil {
				return err
			}
			if seen[r.ID] || len(out) >= limit {
				continue
			}
			seen[r.ID] = true
			out = append(out, suggestion{
				ID: r.ID, LibraryID: r.LibraryID, Kind: r.Kind,
				Title: r.Title, Year: r.Year, Reason: reason,
			})
		}
		return rows.Err()
	}

	// Unstarted = no progress row for this user. Note the parameter order: the
	// IN list comes first in the SQL, then the user id inside NOT EXISTS.
	base := `
		SELECT i.id, i.library_id, i.kind, i.title, COALESCE(i.year, 0)
		FROM media_items i
		WHERE i.missing = 0 AND i.library_id IN (` + in + `)
		  AND NOT EXISTS (SELECT 1 FROM progress p WHERE p.item_id = i.id AND p.user_id = ?)`

	if hasEngagement {
		// 1. Same author.
		if e.Author != "" {
			rows, err := db.QueryContext(ctx, base+`
				AND EXISTS (SELECT 1 FROM item_people ip JOIN people p ON p.id = ip.person_id
				            WHERE ip.item_id = i.id AND p.name = ?)
				ORDER BY i.added_at DESC LIMIT ?`,
				withLibs(inArgs, userID, e.Author, limit)...)
			if err != nil {
				return nil, fmt.Errorf("media: suggestions by author: %w", err)
			}
			if err := add(rows, "More by "+e.Author); err != nil {
				return nil, err
			}
		}

		// 2. Same kind.
		rows, err := db.QueryContext(ctx, base+`
			AND i.kind = ? ORDER BY i.added_at DESC LIMIT ?`,
			withLibs(inArgs, userID, e.Kind, limit)...)
		if err != nil {
			return nil, fmt.Errorf("media: suggestions by kind: %w", err)
		}
		if err := add(rows, "More "+kindNoun(e.Kind)); err != nil {
			return nil, err
		}
	}

	// 3. Anything recent, as a floor so the shelf is never empty.
	rows, err := db.QueryContext(ctx, base+`
		ORDER BY i.added_at DESC LIMIT ?`,
		withLibs(inArgs, userID, limit)...)
	if err != nil {
		return nil, fmt.Errorf("media: suggestions fallback: %w", err)
	}
	if err := add(rows, "Recently added"); err != nil {
		return nil, err
	}

	return out, nil
}

// Explore returns a mixed sample across every kind the user can see.
//
// Excludes anything already on the Continue shelf so the zone feels like
// discovery rather than a repeat. The shelf is sampled per kind: each kind
// present in the visible libraries gets a fair share of the limit, so one
// large library or format cannot drown out the rest. Within a kind the sample
// starts at a random id and walks an indexed, id-ordered range scan that stops
// once it has enough rows, so repeat visits surface different items without
// scanning or sorting the whole library.
func Explore(ctx context.Context, db *sql.DB, userID int64, libraryIDs []int64, limit int) ([]shelfItem, error) {
	if len(libraryIDs) == 0 {
		return []shelfItem{}, nil
	}
	if limit <= 0 || limit > 100 {
		limit = 30
	}

	in, inArgs := inClause(libraryIDs)

	// One small grouped query tells us which kinds are actually present, so we
	// can give each of them a fair share of the shelf. Kinds with no visible
	// items are ignored.
	kindRows, err := db.QueryContext(ctx, `
		SELECT kind, count(*)
		FROM media_items
		WHERE missing = 0 AND library_id IN (`+in+`)
		GROUP BY kind`, inArgs...)
	if err != nil {
		return nil, fmt.Errorf("media: explore: %w", err)
	}
	kinds := []string{}
	for kindRows.Next() {
		var kind string
		var n int64
		if err := kindRows.Scan(&kind, &n); err != nil {
			kindRows.Close()
			return nil, err
		}
		if n > 0 {
			kinds = append(kinds, kind)
		}
	}
	if err := kindRows.Err(); err != nil {
		kindRows.Close()
		return nil, err
	}
	kindRows.Close()

	if len(kinds) == 0 {
		return []shelfItem{}, nil
	}

	// Divide the limit across the kinds that exist: one each, then spread the
	// remainder over the first kinds. If there are more kinds than slots, the
	// extras get nothing on this visit.
	base := limit / len(kinds)
	rem := limit % len(kinds)

	seen := map[int64]bool{}
	out := []shelfItem{}

	// appendRows runs one bounded, id-ordered range scan for a kind and appends
	// any rows not already seen. before selects the wrap-around half of the id
	// range (id < start) instead of the forward half (id >= start). It returns
	// how many new rows were added.
	appendRows := func(kind string, start int64, before bool, n int) (int, error) {
		if n <= 0 {
			return 0, nil
		}
		cmp := ">="
		if before {
			cmp = "<"
		}
		q := `
			SELECT i.id, i.library_id, i.kind, i.title, 0, i.added_at
			FROM media_items i
			WHERE i.missing = 0 AND i.library_id IN (` + in + `)
			  AND i.kind = ?
			  AND i.id ` + cmp + ` ?
			  AND NOT EXISTS (
			      SELECT 1 FROM progress p
			      WHERE p.item_id = i.id AND p.user_id = ? AND p.finished = 0
			  )
			ORDER BY i.id
			LIMIT ?`
		rows, err := db.QueryContext(ctx, q, withLibs(inArgs, kind, start, userID, n)...)
		if err != nil {
			return 0, fmt.Errorf("media: explore: %w", err)
		}
		defer rows.Close()

		added := 0
		for rows.Next() {
			var s shelfItem
			if err := rows.Scan(&s.ID, &s.LibraryID, &s.Kind, &s.Title, &s.Percent, &s.UpdatedAt); err != nil {
				return added, err
			}
			if seen[s.ID] {
				continue
			}
			seen[s.ID] = true
			out = append(out, s)
			added++
		}
		return added, rows.Err()
	}

	for i, kind := range kinds {
		share := base
		if i < rem {
			share++
		}
		if share <= 0 {
			continue
		}

		var maxID int64
		if err := db.QueryRowContext(ctx, `
			SELECT COALESCE(MAX(id), 0)
			FROM media_items
			WHERE missing = 0 AND library_id IN (`+in+`) AND kind = ?`,
			withLibs(inArgs, kind)...).Scan(&maxID); err != nil {
			return nil, fmt.Errorf("media: explore: %w", err)
		}
		if maxID <= 0 {
			continue
		}

		// A random start keeps repeat visits from showing the same slice.
		start := rand.Int63n(maxID) + 1

		got, err := appendRows(kind, start, false, share)
		if err != nil {
			return nil, err
		}
		if got < share {
			// The start landed near the end of the id range; wrap to the
			// beginning to fill the kind's share.
			if _, err := appendRows(kind, start, true, share-got); err != nil {
				return nil, err
			}
		}
	}

	// Mix the kinds instead of leaving them in contiguous blocks, then trim.
	rand.Shuffle(len(out), func(a, b int) { out[a], out[b] = out[b], out[a] })
	if len(out) > limit {
		out = out[:limit]
	}
	return out, nil
}

// withLibs builds a query argument list: the IN-list args first (they appear
// first in these queries), then whatever follows.
//
// Written explicitly because the parameter order in the SQL is not the order
// the caller naturally thinks in, and getting it wrong silently swaps a user id
// for a library id.
func withLibs(inArgs []any, rest ...any) []any {
	out := make([]any, 0, len(inArgs)+len(rest))
	out = append(out, inArgs...)
	out = append(out, rest...)
	return out
}

// kindNoun turns a media kind into something readable in a sentence.
func kindNoun(kind string) string {
	switch kind {
	case "ebooks":
		return "books"
	case "comics":
		return "comics"
	case "audiobooks":
		return "audiobooks"
	case "music":
		return "music"
	case "photos":
		return "photos"
	case "games":
		return "games"
	default:
		return strings.ReplaceAll(kind, "-", " ")
	}
}