feat(admin): startup hash backfill and hash-conflict resolution API
Release / build-and-push (push) Successful in 2m48s

Complete the SHA-256 lifecycle for preexisting databases: items
imported before hashing existed get hashed automatically, and any
content duplicates discovered in the process land on the new admin
Hash Conflicts page for an explicit keep/merge decision.

HashBackfillService (runs once 30s after startup, independent of
auto-scan):
- hashes every media_items row where file_sha256 IS NULL, resolving
  each path through LibraryService; per-item failures are logged and
  skipped so one unreadable file cannot block the pass
- no-op once everything is hashed (logged and skipped)
- finishes with a conflict sweep flagging every content-duplicate
  group via FindHashConflictGroups + CreateHashConflict; the sweep
  runs after the per-item pass because a preexisting pair only
  becomes detectable once both sides have their hash

API (admin-only):
- GET /api/admin/hash-conflicts - pending groups with member items
  and usage counts
- POST /api/admin/hash-conflicts/:id/resolve - action=keep_all, or
  action=keep with keep_uuid: validates the uuid belongs to the
  group, re-parents every other copy's child rows onto the kept item
  (reparent_media_item_children), deletes the losers, and records
  the resolution + resolving admin; accepts form or JSON bodies and
  returns the htmx resolved fragment

Page route /admin/hash-conflicts (admin-only) renders the template
with hydrated conflict data; HashConflictsHandler wired into the
router Config and constructed in main.

Verified end-to-end against the live database: duplicate detection,
pending listing, keep_all resolution, merge path (re-parent +
delete), and - critically - a resolved group is not re-flagged by a
later sweep (upsert no-op). Database restored afterward.
This commit is contained in:
2026-08-14 08:53:01 -04:00
parent 8004cb81a5
commit 03cb4c7869
5 changed files with 454 additions and 0 deletions
+62
View File
@@ -4,6 +4,7 @@ import (
"bytes"
"context"
"encoding/json"
"fmt"
"log"
"net/http"
"strconv"
@@ -944,6 +945,67 @@ func registerFrontendRoutes(cfg *Config) {
return c.HTML(http.StatusOK, buf.String())
}))
// Admin hash conflicts page: content-duplicate groups flagged during hash
// backfill or rescan, resolved by keeping all copies or merging into one.
frontendProtected.GET("/admin/hash-conflicts", handlers.AdminMiddleware(func(c *echo.Context) error {
user, err := getTemplateUserWithTheme(c, cfg)
if err != nil {
return renderErrorPage(c, "Error loading user", "user_load_error")
}
pending, err := cfg.Queries.ListPendingHashConflicts(c.Request().Context())
if err != nil {
return renderErrorPage(c, "Error loading hash conflicts", "conflicts_load_error")
}
conflicts := make([]templates.HashConflictData, 0, len(pending))
for _, p := range pending {
conflict := templates.HashConflictData{
ID: uuid.UUID(p.ID.Bytes).String(),
LibraryName: p.LibraryName,
SHA256: p.FileSha256,
SHAShort: p.FileSha256[:16] + "…",
CreatedAt: p.CreatedAt.Time.Format("Jan 2, 2006"),
Items: []templates.HashConflictItemData{},
}
items, err := cfg.Queries.ListMediaItemsBySHA256AndLibrary(c.Request().Context(), database.ListMediaItemsBySHA256AndLibraryParams{
FileSha256: pgtype.Text{String: p.FileSha256, Valid: true},
LibraryID: p.LibraryID,
})
if err != nil {
continue
}
for _, mi := range items {
counts, err := cfg.Queries.GetMediaItemUsageCounts(c.Request().Context(), mi.ID)
if err != nil {
counts = database.GetMediaItemUsageCountsRow{}
}
totalData := counts.ProgressCount + counts.HighlightsCount + counts.BookmarksCount + counts.NotesCount + counts.CollectionsCount
conflict.Items = append(conflict.Items, templates.HashConflictItemData{
ID: uuid.UUID(mi.ID.Bytes).String(),
Title: mi.Title,
Author: mi.Author.String,
FilePath: mi.FilePath,
FileSize: mi.FileSize.Int64,
UsageSummary: fmt.Sprintf("%d progress, %d highlights, %d bookmarks, %d notes, %d collections",
counts.ProgressCount, counts.HighlightsCount, counts.BookmarksCount, counts.NotesCount, counts.CollectionsCount),
HasReadingData: totalData > 0,
})
}
conflicts = append(conflicts, conflict)
}
var buf bytes.Buffer
err = templates.AdminHashConflicts(user, conflicts).Render(c.Request().Context(), &buf)
if err != nil {
return err
}
return c.HTML(http.StatusOK, buf.String())
}))
// Admin users page
frontendProtected.GET("/admin/users", handlers.AdminMiddleware(func(c *echo.Context) error {
user, err := getTemplateUserWithTheme(c, cfg)