From 485486c7ff986712ecb09e92217236d276d317c4 Mon Sep 17 00:00:00 2001 From: Claude Date: Mon, 12 Jan 2026 08:46:55 +0000 Subject: feat: deduplicate feed items by guid Use ROW_NUMBER() window function to filter out duplicate articles with the same guid across different feeds. This ensures each guid appears only once in unread/read article lists. - Add idx_articles_guid index for PARTITION BY performance - Modify GetUnreadArticles and GetReadArticles queries with CTE --- backend/db/queries/articles.sql | 40 ++++++++++++++++++++++++++-------------- 1 file changed, 26 insertions(+), 14 deletions(-) (limited to 'backend/db/queries/articles.sql') diff --git a/backend/db/queries/articles.sql b/backend/db/queries/articles.sql index 5acdada..bd4cd91 100644 --- a/backend/db/queries/articles.sql +++ b/backend/db/queries/articles.sql @@ -7,23 +7,35 @@ INNER JOIN feeds AS f ON a.feed_id = f.id WHERE a.id = ?; -- name: GetUnreadArticles :many -SELECT - a.id, a.feed_id, a.guid, a.title, a.url, a.is_read, - f.id as feed_id_2, f.url as feed_url, f.title as feed_title, f.is_subscribed as feed_is_subscribed -FROM articles AS a -INNER JOIN feeds AS f ON a.feed_id = f.id -WHERE a.is_read = 0 AND f.is_subscribed = 1 AND f.user_id = ? -ORDER BY a.id DESC +WITH ranked AS ( + SELECT + a.id, a.feed_id, a.guid, a.title, a.url, a.is_read, + f.id as feed_id_2, f.url as feed_url, f.title as feed_title, f.is_subscribed as feed_is_subscribed, + ROW_NUMBER() OVER (PARTITION BY a.guid ORDER BY a.id) as rn + FROM articles AS a + INNER JOIN feeds AS f ON a.feed_id = f.id + WHERE a.is_read = 0 AND f.is_subscribed = 1 AND f.user_id = ? +) +SELECT id, feed_id, guid, title, url, is_read, feed_id_2, feed_url, feed_title, feed_is_subscribed +FROM ranked +WHERE rn = 1 +ORDER BY id DESC LIMIT 100; -- name: GetReadArticles :many -SELECT - a.id, a.feed_id, a.guid, a.title, a.url, a.is_read, - f.id as feed_id_2, f.url as feed_url, f.title as feed_title, f.is_subscribed as feed_is_subscribed -FROM articles AS a -INNER JOIN feeds AS f ON a.feed_id = f.id -WHERE a.is_read = 1 AND f.is_subscribed = 1 AND f.user_id = ? -ORDER BY a.id DESC +WITH ranked AS ( + SELECT + a.id, a.feed_id, a.guid, a.title, a.url, a.is_read, + f.id as feed_id_2, f.url as feed_url, f.title as feed_title, f.is_subscribed as feed_is_subscribed, + ROW_NUMBER() OVER (PARTITION BY a.guid ORDER BY a.id) as rn + FROM articles AS a + INNER JOIN feeds AS f ON a.feed_id = f.id + WHERE a.is_read = 1 AND f.is_subscribed = 1 AND f.user_id = ? +) +SELECT id, feed_id, guid, title, url, is_read, feed_id_2, feed_url, feed_title, feed_is_subscribed +FROM ranked +WHERE rn = 1 +ORDER BY id DESC LIMIT 100; -- name: GetArticlesByFeed :many -- cgit v1.2.3-70-g09d2