Pete/internal/storage/queries.go

package storage

import (
	"database/sql"
	"encoding/json"
	"errors"
	"log/slog"
	"strings"
	"time"
)

func nowUnix() int64 {
	return time.Now().Unix()
}

// IsGUIDSeen checks if a GUID has already been ingested.
func IsGUIDSeen(guid string) bool {
	var count int
	if err := Get().QueryRow(`SELECT COUNT(*) FROM stories WHERE guid = ?`, guid).Scan(&count); err != nil {
		slog.Error("IsGUIDSeen query failed", "guid", guid, "err", err)
		return true // fail closed: assume seen to prevent duplicates
	}
	return count > 0
}

// InsertStory inserts a new story record.
func InsertStory(s *Story) error {
	classified := 0
	if s.Classified {
		classified = 1
	}
	paywalled := 0
	if s.Paywalled {
		paywalled = 1
	}
	var publishedAt any
	if s.PublishedAt > 0 {
		publishedAt = s.PublishedAt
	}
	_, err := Get().Exec(
		`INSERT INTO stories (guid, headline, lede, content, image_url, article_url, url_canonical, headline_norm, source, platforms, channel, classified, paywalled, seen_at, published_at)
		 VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)`,
		s.GUID, s.Headline, s.Lede, nullIfEmpty(s.Content), s.ImageURL, s.ArticleURL, nullIfEmpty(s.URLCanonical), nullIfEmpty(s.HeadlineNorm), s.Source, s.Platforms, s.Channel, classified, paywalled, s.SeenAt, publishedAt,
	)
	return err
}

// GetStoryReaderText returns the stored full article text and lede for a single
// story, for reader mode. found is false when no story has that id. The query
// mirrors the visible-story filter (classified, non-sentinel channel) so the
// public /api/article endpoint can't be enumerated to pull the captured bodies
// of discarded or not-yet-classified stories that never surface in the UI.
func GetStoryReaderText(id int64) (content, lede string, found bool, err error) {
	var c sql.NullString
	var l sql.NullString
	row := Get().QueryRow(
		`SELECT content, lede FROM stories
		 WHERE id = ? AND classified = 1 AND channel NOT IN ('_discarded', '_duplicate')`, id)
	switch err = row.Scan(&c, &l); {
	case errors.Is(err, sql.ErrNoRows):
		return "", "", false, nil
	case err != nil:
		return "", "", false, err
	}
	return c.String, l.String, true, nil
}

// nullIfEmpty returns a SQL NULL for empty strings so partial unique indexes
// (WHERE col IS NOT NULL) can hold multiple "unknown" rows without conflict.
func nullIfEmpty(s string) any {
	if s == "" {
		return nil
	}
	return s
}

// IsCanonicalSeen reports whether any story with this canonical URL exists.
// Empty input always returns false (no canonical = no dedup possible).
func IsCanonicalSeen(canonical string) bool {
	if canonical == "" {
		return false
	}
	var n int
	if err := Get().QueryRow(`SELECT COUNT(*) FROM stories WHERE url_canonical = ?`, canonical).Scan(&n); err != nil {
		slog.Error("IsCanonicalSeen query failed", "err", err)
		return true // fail closed
	}
	return n > 0
}

// IsHeadlineSeen reports whether a same-source story with this normalized
// headline already exists. Empty inputs return false.
func IsHeadlineSeen(source, headlineNorm string) bool {
	if source == "" || headlineNorm == "" {
		return false
	}
	var n int
	if err := Get().QueryRow(
		`SELECT COUNT(*) FROM stories WHERE source = ? AND headline_norm = ?`,
		source, headlineNorm).Scan(&n); err != nil {
		slog.Error("IsHeadlineSeen query failed", "err", err)
		return true
	}
	return n > 0
}

// WasCanonicalPostedRecently reports whether the canonical URL was posted to
// the given channel within `cooldownSeconds`. Empty canonical returns false.
func WasCanonicalPostedRecently(canonical, channel string, cooldownSeconds int64) bool {
	if canonical == "" || cooldownSeconds <= 0 {
		return false
	}
	cutoff := nowUnix() - cooldownSeconds
	var n int
	if err := Get().QueryRow(
		`SELECT COUNT(*) FROM post_log WHERE url_canonical = ? AND channel = ? AND posted_at >= ?`,
		canonical, channel, cutoff).Scan(&n); err != nil {
		slog.Error("WasCanonicalPostedRecently query failed", "err", err)
		return true // fail closed
	}
	return n > 0
}

// MarkClassified marks a story as successfully classified and sets its channel.
func MarkClassified(guid, channel, platforms string) {
	exec("mark classified",
		`UPDATE stories SET classified = 1, channel = ?, platforms = ? WHERE guid = ?`,
		channel, platforms, guid)
}

// GetStoryByGUID returns the full story record for a GUID, or nil if not found.
func GetStoryByGUID(guid string) (*Story, error) {
	row := Get().QueryRow(
		`SELECT guid, headline, lede, image_url, article_url, source, platforms, channel, seen_at
		 FROM stories WHERE guid = ?`, guid)
	var s Story
	if err := row.Scan(&s.GUID, &s.Headline, &s.Lede, &s.ImageURL, &s.ArticleURL, &s.Source, &s.Platforms, &s.Channel, &s.SeenAt); err != nil {
		return nil, err
	}
	return &s, nil
}

// InsertPostLog records that a story was posted to a channel.
// Uses OR IGNORE to prevent duplicate posts for the same story+channel.
// forced=true marks the row as a manual !post override so it doesn't count
// against the global daily cap.
func InsertPostLog(guid, channel, eventID, urlCanonical string, forced bool) {
	f := 0
	if forced {
		f = 1
	}
	exec("insert post_log",
		`INSERT OR IGNORE INTO post_log (guid, channel, event_id, url_canonical, posted_at, forced) VALUES (?, ?, ?, ?, ?, ?)`,
		guid, channel, eventID, nullIfEmpty(urlCanonical), nowUnix(), f)
}

// GetLastPostTime returns the unix timestamp of the most recent post to a channel.
func GetLastPostTime(channel string) int64 {
	var t int64
	if err := Get().QueryRow(`SELECT COALESCE(MAX(posted_at), 0) FROM post_log WHERE channel = ?`, channel).Scan(&t); err != nil {
		slog.Error("GetLastPostTime query failed", "channel", channel, "err", err)
		return nowUnix() // fail closed: pretend we just posted to prevent flooding
	}
	return t
}

// CountAllPostsInWindow counts posts across ALL channels within a time window.
// Used for the global daily cap. Excludes forced (!post) entries so manual
// overrides don't eat into the auto-rotation budget.
func CountAllPostsInWindow(windowStart int64) int {
	var count int
	if err := Get().QueryRow(`SELECT COUNT(*) FROM post_log WHERE posted_at >= ? AND forced = 0`, windowStart).Scan(&count); err != nil {
		slog.Error("CountAllPostsInWindow query failed", "err", err)
		return 1<<31 - 1 // fail closed: huge number prevents posting
	}
	return count
}

// CountPostsInWindow counts posts to a channel within a time window.
func CountPostsInWindow(channel string, windowStart int64) int {
	var count int
	if err := Get().QueryRow(`SELECT COUNT(*) FROM post_log WHERE channel = ? AND posted_at >= ?`, channel, windowStart).Scan(&count); err != nil {
		slog.Error("CountPostsInWindow query failed", "channel", channel, "err", err)
		return 999 // fail closed: pretend burst cap reached to prevent flooding
	}
	return count
}

// LookupPostGUID finds the story GUID for a given Matrix event ID.
func LookupPostGUID(eventID string) (guid, channel string, found bool) {
	err := Get().QueryRow(
		`SELECT guid, channel FROM post_log WHERE event_id = ? LIMIT 1`, eventID).Scan(&guid, &channel)
	if err != nil {
		return "", "", false
	}
	return guid, channel, true
}

// InsertReaction records a reaction on a posted story.
// Uses OR IGNORE to deduplicate if Matrix delivers the same reaction twice.
func InsertReaction(postGUID, channel, eventID, emoji, userID string, reactedAt int64) {
	exec("insert reaction",
		`INSERT OR IGNORE INTO reactions (post_guid, channel, event_id, emoji, user_id, reacted_at) VALUES (?, ?, ?, ?, ?, ?)`,
		postGUID, channel, eventID, emoji, userID, reactedAt)
}

// GetNewestPostableStory returns the newest classified story from a source
// that has a real (non-sentinel) channel and has not yet been posted (no
// row in post_log). Returns (nil, nil) when nothing qualifies.
func GetNewestPostableStory(source string) (*Story, error) {
	row := Get().QueryRow(
		`SELECT guid, headline, lede, image_url, article_url, source, platforms, channel, seen_at
		 FROM stories
		 WHERE classified = 1
		   AND source = ?
		   AND channel IS NOT NULL
		   AND channel NOT IN ('_discarded', '_duplicate')
		   AND guid NOT IN (SELECT guid FROM post_log)
		 ORDER BY COALESCE(published_at, seen_at) DESC
		 LIMIT 1`, source)
	var s Story
	if err := row.Scan(&s.GUID, &s.Headline, &s.Lede, &s.ImageURL, &s.ArticleURL, &s.Source, &s.Platforms, &s.Channel, &s.SeenAt); err != nil {
		if errors.Is(err, sql.ErrNoRows) {
			return nil, nil
		}
		return nil, err
	}
	return &s, nil
}

// GetNewestPostableStoryByChannel returns the newest classified story routed
// to the given channel that has not yet been posted. Used by !post to satisfy
// on-demand requests in round-robin mode (where the in-memory queue is empty
// between ticks). Returns (nil, nil) when nothing qualifies.
func GetNewestPostableStoryByChannel(channel string) (*Story, error) {
	row := Get().QueryRow(
		`SELECT guid, headline, lede, image_url, article_url, source, platforms, channel, seen_at
		 FROM stories
		 WHERE classified = 1
		   AND channel = ?
		   AND guid NOT IN (SELECT guid FROM post_log)
		 ORDER BY COALESCE(published_at, seen_at) DESC
		 LIMIT 1`, channel)
	var s Story
	if err := row.Scan(&s.GUID, &s.Headline, &s.Lede, &s.ImageURL, &s.ArticleURL, &s.Source, &s.Platforms, &s.Channel, &s.SeenAt); err != nil {
		if errors.Is(err, sql.ErrNoRows) {
			return nil, nil
		}
		return nil, err
	}
	return &s, nil
}

// ListClassifiedByChannel returns up to `limit` classified stories routed to a
// real channel, newest first, with optional offset for pagination. Sentinel
// channels (_discarded, _duplicate) are excluded.
func ListClassifiedByChannel(channel string, limit, offset int) ([]Story, error) {
	rows, err := Get().Query(
		`SELECT s.id, s.guid, s.headline, s.lede, s.image_url, s.article_url, s.source, s.platforms, s.channel, s.paywalled, s.seen_at,
		        EXISTS(SELECT 1 FROM post_log p WHERE p.guid = s.guid) AS posted
		 FROM stories s
		 WHERE s.classified = 1
		   AND s.channel = ?
		 ORDER BY COALESCE(s.published_at, s.seen_at) DESC
		 LIMIT ? OFFSET ?`, channel, limit, offset)
	if err != nil {
		return nil, err
	}
	defer rows.Close()
	var out []Story
	for rows.Next() {
		var s Story
		if err := rows.Scan(&s.ID, &s.GUID, &s.Headline, &s.Lede, &s.ImageURL, &s.ArticleURL, &s.Source, &s.Platforms, &s.Channel, &s.Paywalled, &s.SeenAt, &s.Posted); err != nil {
			return nil, err
		}
		out = append(out, s)
	}
	return out, rows.Err()
}

// ListAllClassified returns up to `limit` classified stories across all real
// channels, newest first. Sentinel channels are excluded.
func ListAllClassified(limit, offset int) ([]Story, error) {
	rows, err := Get().Query(
		`SELECT s.id, s.guid, s.headline, s.lede, s.image_url, s.article_url, s.source, s.platforms, s.channel, s.paywalled, s.seen_at,
		        EXISTS(SELECT 1 FROM post_log p WHERE p.guid = s.guid) AS posted
		 FROM stories s
		 WHERE s.classified = 1
		   AND s.channel IS NOT NULL
		   AND s.channel NOT IN ('_discarded', '_duplicate')
		 ORDER BY COALESCE(s.published_at, s.seen_at) DESC
		 LIMIT ? OFFSET ?`, limit, offset)
	if err != nil {
		return nil, err
	}
	defer rows.Close()
	var out []Story
	for rows.Next() {
		var s Story
		if err := rows.Scan(&s.ID, &s.GUID, &s.Headline, &s.Lede, &s.ImageURL, &s.ArticleURL, &s.Source, &s.Platforms, &s.Channel, &s.Paywalled, &s.SeenAt, &s.Posted); err != nil {
			return nil, err
		}
		out = append(out, s)
	}
	return out, rows.Err()
}

// ListForFeed returns up to `limit` classified stories for the outbound RSS and
// JSON feeds, newest first. Unlike the web list queries it also selects the full
// `content` and `published_at`, which the feeds need for content:encoded bodies
// and real pubDates. channel == "" spans all real channels; otherwise it scopes
// to that one channel. Sentinel channels are always excluded.
func ListForFeed(channel string, limit int) ([]Story, error) {
	const cols = `s.id, s.guid, s.headline, s.lede, s.content, s.image_url, s.article_url, s.url_canonical, s.source, s.channel, s.seen_at, s.published_at`
	var (
		rows *sql.Rows
		err  error
	)
	if channel == "" {
		rows, err = Get().Query(
			`SELECT `+cols+`
			 FROM stories s
			 WHERE s.classified = 1
			   AND s.channel IS NOT NULL
			   AND s.channel NOT IN ('_discarded', '_duplicate')
			 ORDER BY COALESCE(s.published_at, s.seen_at) DESC
			 LIMIT ?`, limit)
	} else {
		rows, err = Get().Query(
			`SELECT `+cols+`
			 FROM stories s
			 WHERE s.classified = 1
			   AND s.channel = ?
			 ORDER BY COALESCE(s.published_at, s.seen_at) DESC
			 LIMIT ?`, channel, limit)
	}
	if err != nil {
		return nil, err
	}
	defer rows.Close()
	var out []Story
	for rows.Next() {
		var s Story
		var content, canonical sql.NullString
		var published sql.NullInt64
		if err := rows.Scan(&s.ID, &s.GUID, &s.Headline, &s.Lede, &content, &s.ImageURL, &s.ArticleURL, &canonical, &s.Source, &s.Channel, &s.SeenAt, &published); err != nil {
			return nil, err
		}
		s.Content = content.String
		s.URLCanonical = canonical.String
		s.PublishedAt = published.Int64
		out = append(out, s)
	}
	return out, rows.Err()
}

// ListRecentlyPosted returns up to `limit` stories that have been posted to
// Matrix, ordered by post time (newest first). Posted is always true.
func ListRecentlyPosted(limit int) ([]Story, error) {
	rows, err := Get().Query(
		`SELECT s.id, s.guid, s.headline, s.lede, s.image_url, s.article_url, s.source, s.platforms, s.channel, s.paywalled, s.seen_at
		 FROM stories s
		 JOIN post_log p ON p.guid = s.guid
		 GROUP BY s.guid
		 ORDER BY MAX(p.posted_at) DESC
		 LIMIT ?`, limit)
	if err != nil {
		return nil, err
	}
	defer rows.Close()
	var out []Story
	for rows.Next() {
		var s Story
		if err := rows.Scan(&s.ID, &s.GUID, &s.Headline, &s.Lede, &s.ImageURL, &s.ArticleURL, &s.Source, &s.Platforms, &s.Channel, &s.Paywalled, &s.SeenAt); err != nil {
			return nil, err
		}
		s.Posted = true
		out = append(out, s)
	}
	return out, rows.Err()
}

// CountClassifiedByChannel returns how many classified stories exist for a channel.
func CountClassifiedByChannel(channel string) (int, error) {
	var n int
	err := Get().QueryRow(
		`SELECT COUNT(*) FROM stories WHERE classified = 1 AND channel = ?`,
		channel).Scan(&n)
	return n, err
}

// IsKnownImageURL reports whether any story has this exact image_url. Used
// by the thumbnail proxy to guard against arbitrary URL fetches.
func IsKnownImageURL(url string) bool {
	if url == "" {
		return false
	}
	var n int
	if err := Get().QueryRow(`SELECT COUNT(*) FROM stories WHERE image_url = ? LIMIT 1`, url).Scan(&n); err != nil {
		slog.Error("IsKnownImageURL query failed", "err", err)
		return false
	}
	return n > 0
}

// GetRoundRobinState returns the last channel posted by the round-robin
// scheduler and the timestamp of that tick. Empty string + 0 if no state yet.
func GetRoundRobinState() (lastChannel string, lastTickAt int64, err error) {
	row := Get().QueryRow(`SELECT last_channel, last_tick_at FROM round_robin_state WHERE id = 1`)
	var lc *string
	if scanErr := row.Scan(&lc, &lastTickAt); scanErr != nil {
		if errors.Is(scanErr, sql.ErrNoRows) {
			return "", 0, nil
		}
		return "", 0, scanErr
	}
	if lc != nil {
		lastChannel = *lc
	}
	return lastChannel, lastTickAt, nil
}

// SetRoundRobinState persists the last-posted channel and tick timestamp.
func SetRoundRobinState(lastChannel string, tickAt int64) {
	exec("set round_robin_state",
		`INSERT INTO round_robin_state (id, last_channel, last_tick_at) VALUES (1, ?, ?)
		 ON CONFLICT(id) DO UPDATE SET last_channel = excluded.last_channel, last_tick_at = excluded.last_tick_at`,
		lastChannel, tickAt)
}

// SearchStories runs an FTS5 query against headline + lede and returns the
// best-ranked classified stories (real channels only), newest-ish first via
// bm25. The user query is tokenized and each token becomes a prefix match;
// FTS5 special characters are stripped so user input cannot break syntax.
func SearchStories(query string, limit int) ([]Story, error) {
	fts := buildFTSQuery(query)
	if fts == "" {
		return nil, nil
	}
	rows, err := Get().Query(
		`SELECT s.guid, s.headline, s.lede, s.image_url, s.article_url, s.source, s.platforms, s.channel, s.paywalled, s.seen_at,
		        EXISTS(SELECT 1 FROM post_log p WHERE p.guid = s.guid) AS posted
		 FROM stories_fts f
		 JOIN stories s ON s.id = f.rowid
		 WHERE f.stories_fts MATCH ?
		   AND s.classified = 1
		   AND s.channel IS NOT NULL
		   AND s.channel NOT IN ('_discarded', '_duplicate')
		 ORDER BY bm25(stories_fts) ASC, s.seen_at DESC
		 LIMIT ?`, fts, limit)
	if err != nil {
		return nil, err
	}
	defer rows.Close()
	var out []Story
	for rows.Next() {
		var s Story
		if err := rows.Scan(&s.GUID, &s.Headline, &s.Lede, &s.ImageURL, &s.ArticleURL, &s.Source, &s.Platforms, &s.Channel, &s.Paywalled, &s.SeenAt, &s.Posted); err != nil {
			return nil, err
		}
		out = append(out, s)
	}
	return out, rows.Err()
}

func buildFTSQuery(raw string) string {
	var tokens []string
	var cur strings.Builder
	flush := func() {
		if cur.Len() > 0 {
			tokens = append(tokens, cur.String())
			cur.Reset()
		}
	}
	for _, r := range raw {
		switch {
		case r >= 'a' && r <= 'z', r >= 'A' && r <= 'Z', r >= '0' && r <= '9':
			cur.WriteRune(r)
		case r > 127:
			cur.WriteRune(r)
		default:
			flush()
		}
	}
	flush()
	for i, t := range tokens {
		tokens[i] = "\"" + t + "\"*"
	}
	return strings.Join(tokens, " ")
}

// MarshalPlatforms converts a string slice to a JSON array string for storage.
func MarshalPlatforms(platforms []string) string {
	if len(platforms) == 0 {
		return "[]"
	}
	data, err := json.Marshal(platforms)
	if err != nil {
		slog.Error("marshal platforms failed", "err", err)
		return "[]"
	}
	return string(data)
}

// UnmarshalPlatforms converts a JSON array string back to a string slice.
func UnmarshalPlatforms(raw string) []string {
	if raw == "" || raw == "[]" {
		return nil
	}
	var platforms []string
	if err := json.Unmarshal([]byte(raw), &platforms); err != nil {
		slog.Error("unmarshal platforms failed", "err", err, "raw", raw)
		return nil
	}
	return platforms
}