joe/everytab
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

shuffle bundle generation using a bucket approach in the assembler

Browse source
This commit is contained in:
Joe Lothan 2026-05-26 09:11:15 -04:00
parent 4b09a3219a
commit df2eaa251c
2 changed files with 47 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

6
pipeline/05_bundle_gen/db.go
View file

@ -13,12 +13,14 @@ type HostRow struct {
HtmlTitle string
IframeAllowed bool
BestIconHash string
RandomOrder float64
}
// fetchHostsPage gets a page of hosts with titles, ordered by id for disk locality.
// random_order is included for bundle bucket assignment (randomized bundles).
func fetchHostsPage(ctx context.Context, pool *pgxpool.Pool, lastID int64, limit int) ([]HostRow, error) {
rows, err := pool.Query(ctx, `
SELECT id, hostname, protocol, html_title, COALESCE(iframe_allowed, true), COALESCE(best_icon_hash, '')
SELECT id, hostname, protocol, html_title, COALESCE(iframe_allowed, true), COALESCE(best_icon_hash, ''), random_order
FROM hosts
WHERE html_title IS NOT NULL AND id > $1
ORDER BY id
@ -32,7 +34,7 @@ func fetchHostsPage(ctx context.Context, pool *pgxpool.Pool, lastID int64, limit
var hosts []HostRow
for rows.Next() {
var h HostRow
if err := rows.Scan(&h.ID, &h.Hostname, &h.Protocol, &h.HtmlTitle, &h.IframeAllowed, &h.BestIconHash); err != nil {
if err := rows.Scan(&h.ID, &h.Hostname, &h.Protocol, &h.HtmlTitle, &h.IframeAllowed, &h.BestIconHash, &h.RandomOrder); err != nil {
return nil, err
}
hosts = append(hosts, h)