drwily/Pete
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Order stories by feed publish time, not ingest time

Browse Source
This commit is contained in:
prosolis
2026-05-25 18:49:47 -07:00
parent 58493006e1
commit f52f26ff8d
6 changed files with 47 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
internal/storage/db.go
View File

@@ -81,6 +81,7 @@ func runMigrations(d *sql.DB) error {
addColumnIfMissing(d, "stories", "url_canonical", "TEXT")
addColumnIfMissing(d, "stories", "headline_norm", "TEXT")
addColumnIfMissing(d, "stories", "paywalled", "INTEGER NOT NULL DEFAULT 0")
addColumnIfMissing(d, "stories", "published_at", "INTEGER")
addColumnIfMissing(d, "post_log", "url_canonical", "TEXT")
addColumnIfMissing(d, "round_robin_state", "last_channel", "TEXT")

18
internal/storage/queries.go
View File

@@ -33,10 +33,14 @@ func InsertStory(s *Story) error {
if s.Paywalled {
paywalled = 1
}
var publishedAt any
if s.PublishedAt > 0 {
publishedAt = s.PublishedAt
}
_, err := Get().Exec(
`INSERT INTO stories (guid, headline, lede, image_url, article_url, url_canonical, headline_norm, source, platforms, channel, classified, paywalled, seen_at)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)`,
s.GUID, s.Headline, s.Lede, s.ImageURL, s.ArticleURL, nullIfEmpty(s.URLCanonical), nullIfEmpty(s.HeadlineNorm), s.Source, s.Platforms, s.Channel, classified, paywalled, s.SeenAt,
`INSERT INTO stories (guid, headline, lede, image_url, article_url, url_canonical, headline_norm, source, platforms, channel, classified, paywalled, seen_at, published_at)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)`,
s.GUID, s.Headline, s.Lede, s.ImageURL, s.ArticleURL, nullIfEmpty(s.URLCanonical), nullIfEmpty(s.HeadlineNorm), s.Source, s.Platforms, s.Channel, classified, paywalled, s.SeenAt, publishedAt,
)
return err
}
@@ -185,7 +189,7 @@ func GetNewestPostableStory(source string) (*Story, error) {
AND channel IS NOT NULL
AND channel NOT IN ('_discarded', '_duplicate')
AND guid NOT IN (SELECT guid FROM post_log)
ORDER BY seen_at DESC
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 {
@@ -208,7 +212,7 @@ func GetNewestPostableStoryByChannel(channel string) (*Story, error) {
WHERE classified = 1
AND channel = ?
AND guid NOT IN (SELECT guid FROM post_log)
ORDER BY seen_at DESC
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 {
@@ -230,7 +234,7 @@ func ListClassifiedByChannel(channel string, limit, offset int) ([]Story, error)
FROM stories s
WHERE s.classified = 1
AND s.channel = ?
ORDER BY s.seen_at DESC
ORDER BY COALESCE(s.published_at, s.seen_at) DESC
LIMIT ? OFFSET ?`, channel, limit, offset)
if err != nil {
return nil, err
@@ -257,7 +261,7 @@ func ListAllClassified(limit, offset int) ([]Story, error) {
WHERE s.classified = 1
AND s.channel IS NOT NULL
AND s.channel NOT IN ('_discarded', '_duplicate')
ORDER BY s.seen_at DESC
ORDER BY COALESCE(s.published_at, s.seen_at) DESC
LIMIT ? OFFSET ?`, limit, offset)
if err != nil {
return nil, err

3
internal/storage/schema.go
View File

@@ -15,7 +15,8 @@ CREATE TABLE IF NOT EXISTS stories (
channel TEXT,
classified INTEGER NOT NULL DEFAULT 0,
paywalled INTEGER NOT NULL DEFAULT 0,
seen_at INTEGER NOT NULL
seen_at INTEGER NOT NULL,
published_at INTEGER
);
CREATE TABLE IF NOT EXISTS post_log (

3
internal/storage/types.go
View File

@@ -16,5 +16,6 @@ type Story struct {
Classified bool
Paywalled bool // source article is gated; ArticleURL may be an archive snapshot
SeenAt int64
Posted bool // true if this story has been posted to Matrix (joined from post_log)
PublishedAt int64 // from RSS pubDate/Atom published; 0 if missing. Future dates are clamped to SeenAt at ingest.
Posted bool // true if this story has been posted to Matrix (joined from post_log)
}