2 Commits

Author SHA1 Message Date
andrew 068e7e9534 0.6.13: Fix watermark maintenance jobs, honest buy-link write reporting, Qobuz 403 diagnosis
scrub-watermark-text.py crashed on every run (missing import os). strip-watermark-art.py
was starved every Sunday by lock contention from strip-mb-tags' growing runtime -- moved
it to 01:00 so the rest of the weekly chain has room. enrich-buy-url.py's summary line
counted matches found, not successful writes, so a run where every metaflac write failed
(root-owned files) still reported "N tagged". pipeline-status.sh now tells a 403 from
Qobuz (Akamai/CDN block) apart from a 401 (actually expired token) -- re-exporting the
token does nothing for the former. Also fixes the dedup review table's "Caught by" badge
overflowing into the Keep column's format pill.
2026-07-22 13:09:34 -06:00
andrew e07e931c45 0.6.12: Redesign the dedup review table for faster, more accurate scanning
The keep/delete columns were raw paths in a fixed-width cell: ellipsis-
truncated, full text only on hover. Slow to scan (mousing over every
row to read the song name) and, once "fixed" with a tag-derived title/
artist header in a first pass of this change, actively worse for the
thing dedup review actually needs -- confirming two files are really
the same recording. Tags can be wrong; the filename on disk can't.

New layout: each candidate gets a title row (song title, large,
unclipped -- parsed from beets' known singleton path template,
Artist/Album/Title.ext) followed by a compact detail row. The detail
row shows a color-coded format pill (FLAC/MP3/etc, matching the same
quality judgment dedup-library.sh's rank_file() already makes) and the
full relative file path, always rendered as visible text -- never
hover-only -- so a real difference in filename, album, or folder is
still plainly visible even when tags line up. Shared artist collapses
onto the title row so it isn't repeated per side; a colored left rail
marks which side survives without having to read the words.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 10:15:27 -06:00
8 changed files with 240 additions and 65 deletions
+3 -3
View File
@@ -73,10 +73,10 @@ Optional, add these later if you want them:
Pull the prebuilt image onto your Docker host:
```bash
docker pull git.kretzer.club/andrew/alembic:0.6.11
docker pull git.kretzer.club/andrew/alembic:0.6.13
```
That is the whole install. You do not need to download the source or build anything. The `0.6.11` is the version; you can pin to it so nothing changes under you, or use `latest` to always get the newest.
That is the whole install. You do not need to download the source or build anything. The `0.6.13` is the version; you can pin to it so nothing changes under you, or use `latest` to always get the newest.
(If you would rather build it yourself from source, you can, but you do not need to.)
@@ -136,7 +136,7 @@ Create a file called `docker-compose.yml` on your server (put it wherever you ke
```yaml
services:
alembic:
image: git.kretzer.club/andrew/alembic:0.6.11
image: git.kretzer.club/andrew/alembic:0.6.13
container_name: alembic
ports:
- "8420:8420"
+68 -5
View File
@@ -1,3 +1,6 @@
import os
import re
from fastapi import APIRouter, BackgroundTasks, Depends, Request
from fastapi.responses import RedirectResponse
from fastapi.templating import Jinja2Templates
@@ -30,16 +33,76 @@ def _display_path(path: str) -> str:
return path[len(_LIBRARY_PREFIX):] if path.startswith(_LIBRARY_PREFIX) else path
# Compilation-style import paths carry a "$track " prefix on the filename
# (see pipeline/configs/beets config.yaml paths: comp/albumtype_soundtrack);
# singleton paths (the vast majority of this library) don't. Strip it either
# way so the title reads clean.
_TRACK_PREFIX_RE = re.compile(r"^\d{1,3}[\s.\-]+")
# rank_file() in dedup-library.sh always ranks FLAC above every other format
# and WAV below MP3 (a download glitch, never desirable) -- mirror that
# judgment in the format pill's color so it reads as "this one's the keeper"
# at a glance, not just a bare extension string.
_FORMAT_BADGE = {"flac": "badge-success", "wav": "badge-warning"}
def _split_display(path: str) -> dict:
"""Break a library display path into (artist, album, title, ext).
Beets' singleton path template is always
%the{$albumartist}/$album/$title (pipeline/configs/beets config.yaml,
paths:) -- every track in this library lands at exactly that shape, so
the last two segments are reliably album/filename. A path that doesn't
fit (an unexpected root-level file) degrades to showing the raw display
path as the title instead of guessing at structure that isn't there.
"""
display = _display_path(path)
parts = display.split("/")
if len(parts) >= 2:
artist, album, filename = parts[0], parts[-2], parts[-1]
title, ext = os.path.splitext(filename)
title = _TRACK_PREFIX_RE.sub("", title)
else:
artist, album = "", ""
title, ext = os.path.splitext(display)
return {
"path": path,
"display": display,
"artist": artist,
"album": album,
"title": title,
"ext": ext.lstrip(".").lower(),
}
def _file_size(path: str) -> int | None:
try:
return os.path.getsize(path)
except OSError:
return None
def _to_row(c) -> dict:
keep = _split_display(c.keep_path)
delete = _split_display(c.delete_path)
keep["size_bytes"] = _file_size(c.keep_path)
keep["badge"] = _FORMAT_BADGE.get(keep["ext"], "badge-muted")
delete["size_bytes"] = c.delete_size_bytes if c.delete_size_bytes is not None else _file_size(c.delete_path)
delete["badge"] = _FORMAT_BADGE.get(delete["ext"], "badge-muted")
return {
"id": c.id,
"pass_name": c.pass_name,
"pass_label": _pass_label(c.pass_name),
"keep_path": c.keep_path,
"delete_path": c.delete_path,
"keep_display": _display_path(c.keep_path),
"delete_display": _display_path(c.delete_path),
"delete_size_bytes": c.delete_size_bytes,
"keep": keep,
"delete": delete,
# Same-tag passes (numbered_sibling/case_insensitive/normalized) share
# artist/title almost always; cross_album_fuzzy and fuzzy_audio can
# legitimately differ (different credit, different album entirely) --
# the template only collapses shared context onto one line when it's
# actually shared, otherwise shows both sides in full.
"same_title": keep["title"].lower() == delete["title"].lower(),
"same_artist": keep["artist"].lower() == delete["artist"].lower(),
"same_album": keep["album"].lower() == delete["album"].lower(),
}
+12 -1
View File
@@ -155,8 +155,19 @@ MAINTENANCE_JOBS: dict[str, tuple[dict, callable]] = {
_log_rotation,
),
# ==== Weekly (Sunday) ====
# strip_mb_tags runs first here at 01:00 -- not 08:30 like the rest of
# this chain -- because its runtime isn't stable: 10m19s on 2026-07-12,
# 39.6min on 2026-07-19 (MusicBrainz lookup latency scales with library
# size and isn't under our control). At 08:30 that variance repeatedly
# starved every job behind it: strip_watermark_art waited the full
# SCHEDULED_LOCK_WAIT_SECONDS and gave up every week from 07-12 onward,
# and on 07-19 the starvation cascaded all the way through genre:run,
# normalize_casing, beets_update_sync, dedup:scan, and both gen_*_playlist
# jobs. 01:00 sits in the dead zone before the first playlist sync (05:00)
# and well after log_rotation (00:00), so even a run several times slower
# than 07-19's is guaranteed to release the lock long before 08:30.
"maintenance:strip_mb_tags": (
dict(minute=30, hour=8, day_of_week="sun"),
dict(minute=0, hour=1, day_of_week="sun"),
_lib("maintenance:strip_mb_tags", "strip-mb-tags.sh"),
),
"maintenance:strip_watermark_art": (
+61 -5
View File
@@ -475,11 +475,60 @@ tbody tr:hover { background: rgba(167, 139, 250, 0.055); }
tbody td.actions-cell { display: flex; gap: 0.5rem; flex-wrap: wrap; }
.dedup-table { table-layout: fixed; }
.dedup-table .path-cell {
overflow: hidden;
text-overflow: ellipsis;
white-space: nowrap;
max-width: 0; /* forces the cell to respect the colgroup width instead of the content's natural width */
/* Each candidate is its own <tbody> (title row + detail row) so the pair
highlights together on hover, and so :hover can bubble from either row
up to the shared group without JS. That means every detail row is now
a tbody's last-child, which would otherwise strip the separator between
one candidate and the next (the generic `tbody tr:last-child` rule above
assumed one shared tbody) -- restore it here, and only drop it for the
actual last group in the table. */
.dedup-table .dedup-row-group:hover td { background: rgba(167, 139, 250, 0.06); }
.dedup-table .dedup-detail-row td { border-bottom: 1px solid var(--border); }
.dedup-table .dedup-row-group:last-of-type .dedup-detail-row td { border-bottom: none; }
.dedup-title-row td { padding: 0.75rem 1.1rem 0.2rem; border-bottom: none; }
.dedup-detail-row td { padding-top: 0.15rem; }
.dedup-title {
font-family: var(--font-display);
font-size: 1.02rem;
font-weight: 700;
color: var(--fg);
line-height: 1.35;
overflow-wrap: anywhere;
}
.dedup-title-alt { font-weight: 400; color: var(--muted); }
.dedup-context { font-size: 0.8rem; margin-top: 0.15rem; }
/* A thin colored rail on each side echoes the keep/delete verdict itself --
green for the copy that survives, muted-pink for the one on the chopping
block -- so which side is which reads before you've even read the words. */
.dedup-side {
display: flex;
align-items: center;
gap: 0.55rem;
padding-left: 0.65rem;
border-left: 2px solid transparent;
min-height: 1.6rem;
}
.dedup-side-keep { border-left-color: var(--status-success); }
.dedup-side-delete { border-left-color: var(--status-danger); }
.dedup-side-size { font-size: 0.78rem; white-space: nowrap; flex-shrink: 0; }
/* The actual filename/path -- always visible, never truncated. Tags can be
wrong; this is the ground truth for judging whether two files are really
the same recording, so it can't be hover-only the way it was in the first
pass of this redesign. */
.dedup-side-path {
padding-left: 0.65rem;
margin-top: 0.2rem;
font-size: 0.78rem;
color: var(--muted-2);
overflow-wrap: anywhere;
line-height: 1.4;
}
.empty-row td { padding: 2.5rem 1rem; text-align: center; }
@@ -509,6 +558,13 @@ tbody td.actions-cell { display: flex; gap: 0.5rem; flex-wrap: wrap; }
.badge-pulse::before { animation: pulse-dot 1.4s ease-in-out infinite; }
@keyframes pulse-dot { 0%, 100% { opacity: 1; } 50% { opacity: 0.35; } }
/* The dedup "Caught by" column is only 10.75rem wide -- "Acoustically
Similar" at the default badge size overflowed past it and rendered on
top of the keep-side format pill. Smaller size/padding/tracking keeps it
inside the column instead of shrinking the column itself, which would
just crowd the Keep/Delete path columns next to it. */
.badge-caughtby { font-size: 0.6rem; padding: 0.24rem 0.55rem; letter-spacing: 0.02em; }
/* ---- stacked status bar (playlist track reconciliation) ---- */
.status-bar {
+72 -43
View File
@@ -1,5 +1,65 @@
{% extends "base.html" %}
{% block title %}Dedup — alembic{% endblock %}
{% macro candidate_rows(c, mode) %}
<tbody class="dedup-row-group">
<tr class="dedup-title-row">
<td colspan="{{ 5 if mode == 'pending' else 4 }}">
{% if c.same_title %}
<div class="dedup-title">{{ c.keep.title }}</div>
{% else %}
<div class="dedup-title">{{ c.keep.title }} <span class="dedup-title-alt">/ {{ c.delete.title }}</span></div>
{% endif %}
{% if c.same_artist and c.same_album and c.keep.album %}
<div class="dedup-context muted">{{ c.keep.artist }} · {{ c.keep.album }}</div>
{% elif c.same_artist %}
<div class="dedup-context muted">{{ c.keep.artist }}</div>
{% else %}
<div class="dedup-context muted">{{ c.keep.artist }} / {{ c.delete.artist }}</div>
{% endif %}
</td>
</tr>
<tr class="dedup-detail-row">
{% if mode == 'pending' %}
<td><input type="checkbox" name="candidate_id" value="{{ c.id }}" form="bulk-delete-form"></td>
{% endif %}
<td><span class="badge badge-caughtby {{ 'badge-warning' if c.pass_label == 'Acoustically Similar' else 'badge-info' }}" title="{{ c.pass_name }}">{{ c.pass_label }}</span></td>
<td>
<div class="dedup-side dedup-side-keep">
<span class="badge {{ c.keep.badge }}">{{ c.keep.ext or '?' }}</span>
{% if c.keep.size_bytes %}<span class="muted dedup-side-size">{{ (c.keep.size_bytes / 1024 / 1024) | round(1) }} MB</span>{% endif %}
</div>
<div class="dedup-side-path mono muted">{{ c.keep.display }}</div>
</td>
<td>
<div class="dedup-side dedup-side-delete">
<span class="badge {{ c.delete.badge }}">{{ c.delete.ext or '?' }}</span>
{% if c.delete.size_bytes %}<span class="muted dedup-side-size">{{ (c.delete.size_bytes / 1024 / 1024) | round(1) }} MB</span>{% endif %}
</div>
<div class="dedup-side-path mono muted">{{ c.delete.display }}</div>
</td>
<td class="actions-cell">
{% if mode == 'pending' %}
<form method="post" action="/dedup/confirm" class="inline"
onsubmit="return confirm('Permanently delete this file from disk?\n{{ c.delete.display }}')">
<input type="hidden" name="candidate_id" value="{{ c.id }}">
<button type="submit" class="btn btn-sm btn-danger">Delete</button>
</form>
<form method="post" action="/dedup/ignore" class="inline">
<input type="hidden" name="candidate_id" value="{{ c.id }}">
<button type="submit" class="btn btn-sm btn-ghost" title="Keep both copies and never flag this pair again">Keep both</button>
</form>
{% else %}
<form method="post" action="/dedup/unignore" class="inline">
<input type="hidden" name="candidate_id" value="{{ c.id }}">
<button type="submit" class="btn btn-sm btn-ghost">Un-ignore</button>
</form>
{% endif %}
</td>
</tr>
</tbody>
{% endmacro %}
{% block content %}
<div class="page-header">
<div>
@@ -18,48 +78,30 @@
{% endif %}
<h2>Pending candidates</h2>
<p class="muted" style="margin-top:-0.5rem;">Paths are relative to the library root. Hover a name for the full path.</p>
<p class="muted" style="margin-top:-0.5rem;">Song title up top so you can scan straight down the list; the actual file path is always shown underneath each side so you can check they're really the same file before confirming.</p>
<form id="bulk-delete-form" method="post" action="/dedup/confirm"
onsubmit="return confirm('Permanently delete every selected file from disk? This cannot be undone.')"></form>
<div class="table-wrap scroll">
<table class="dedup-table">
<colgroup>
<col style="width:2.2rem"><col style="width:9.5rem"><col style="width:28%">
<col style="width:28%"><col style="width:5rem"><col style="width:9rem">
<col style="width:2.2rem"><col style="width:10.75rem"><col style="width:37.5%">
<col style="width:37.5%"><col style="width:10rem">
</colgroup>
<thead>
<tr><th></th><th>Caught by</th><th>Keep</th><th>Delete</th><th>Size</th><th>Action</th></tr>
<tr><th></th><th>Caught by</th><th>Keep</th><th>Delete</th><th>Action</th></tr>
</thead>
<tbody>
{% set pass_badge = {"File Naming": "badge-info", "Acoustically Similar": "badge-warning"} %}
{% for c in candidates %}
<tr>
<td><input type="checkbox" name="candidate_id" value="{{ c.id }}" form="bulk-delete-form"></td>
<td><span class="badge {{ pass_badge.get(c.pass_label, 'badge-info') }}" title="{{ c.pass_name }}">{{ c.pass_label }}</span></td>
<td class="muted mono path-cell" title="{{ c.keep_path }}">{{ c.keep_display }}</td>
<td class="mono path-cell" title="{{ c.delete_path }}">{{ c.delete_display }}</td>
<td class="muted">{{ (c.delete_size_bytes / 1024 / 1024) | round(1) if c.delete_size_bytes else '?' }} MB</td>
<td class="actions-cell">
<form method="post" action="/dedup/confirm" class="inline"
onsubmit="return confirm('Permanently delete this file from disk?\n{{ c.delete_display }}')">
<input type="hidden" name="candidate_id" value="{{ c.id }}">
<button type="submit" class="btn btn-sm btn-danger">Delete</button>
</form>
<form method="post" action="/dedup/ignore" class="inline">
<input type="hidden" name="candidate_id" value="{{ c.id }}">
<button type="submit" class="btn btn-sm btn-ghost" title="Keep both copies and never flag this pair again">Keep both</button>
</form>
</td>
</tr>
{{ candidate_rows(c, 'pending') }}
{% else %}
<tr class="empty-row"><td colspan="6">
<tbody>
<tr class="empty-row"><td colspan="5">
<div class="empty-state">
<span class="sparkle" style="position:relative; display:inline-block; margin-bottom:0.5rem;"></span>
<p class="muted" style="margin:0;">No pending candidates. Run a scan.</p>
</div>
</td></tr>
{% endfor %}
</tbody>
{% endfor %}
</table>
</div>
{% if candidates %}
@@ -72,28 +114,15 @@
<div class="table-wrap scroll">
<table class="dedup-table">
<colgroup>
<col style="width:9.5rem"><col style="width:33%">
<col style="width:33%"><col style="width:5rem"><col style="width:7rem">
<col style="width:10.75rem"><col style="width:39.25%">
<col style="width:39.25%"><col style="width:7rem">
</colgroup>
<thead>
<tr><th>Caught by</th><th>Keep</th><th>Delete</th><th>Size</th><th></th></tr>
<tr><th>Caught by</th><th>Keep</th><th>Delete</th><th></th></tr>
</thead>
<tbody>
{% for c in ignored %}
<tr>
<td><span class="badge badge-muted" title="{{ c.pass_name }}">{{ c.pass_label }}</span></td>
<td class="muted mono path-cell" title="{{ c.keep_path }}">{{ c.keep_display }}</td>
<td class="muted mono path-cell" title="{{ c.delete_path }}">{{ c.delete_display }}</td>
<td class="muted">{{ (c.delete_size_bytes / 1024 / 1024) | round(1) if c.delete_size_bytes else '?' }} MB</td>
<td>
<form method="post" action="/dedup/unignore" class="inline">
<input type="hidden" name="candidate_id" value="{{ c.id }}">
<button type="submit" class="btn btn-sm btn-ghost">Un-ignore</button>
</form>
</td>
</tr>
{{ candidate_rows(c, 'ignored') }}
{% endfor %}
</tbody>
</table>
</div>
{% endif %}
+12 -4
View File
@@ -458,7 +458,7 @@ def main():
+ (f" upgrade-from={sorted(upgrade_from)}" if upgrade_from else ""))
print(f"[enrich] {len(flacs)} FLAC files in library\n")
looked = found = upgraded = 0
looked = found = upgraded = write_failed = 0
by_source = {s: 0 for s in cascade}
touched = []
for p in flacs:
@@ -519,17 +519,25 @@ def main():
if set_flac_tag(sp, BUY_URL_TAG, url):
touched.append(sp)
else:
print(" ! metaflac write failed")
write_failed += 1
print(" ! metaflac write failed (permissions? disk full?) -- NOT tagged")
else:
touched.append(sp)
if found % 50 == 0:
print(f" ...{found} links from {looked} lookups so far", flush=True)
print(f"\n[enrich] {looked} lookups, {found} {'tagged' if args.apply else 'would-tag'}"
# touched is only appended to on an actual successful write (apply mode)
# or a would-tag match (dry run) -- len(touched) is what really landed on
# disk. `found` counts matches regardless of write outcome, so reporting
# `found` here as "tagged" lied about full success on 2026-07-22, when
# every write in the run failed (root-owned files under explo/) but the
# summary line still read "51 tagged".
print(f"\n[enrich] {looked} lookups, {len(touched)} {'tagged' if args.apply else 'would-tag'}"
f" ({', '.join(f'{s}={by_source[s]}' for s in cascade)})"
f" no-match={looked - found}"
+ (f" upgraded={upgraded}" if upgrade_from else ""))
+ (f" upgraded={upgraded}" if upgrade_from else "")
+ (f" WRITE-FAILED={write_failed}" if write_failed else ""))
if args.apply and touched and az_key and args.azuracast_base:
print("[enrich] telling AzuraCast to reprocess touched files...")
+8
View File
@@ -425,6 +425,14 @@ PYEOF
case "$q_code" in
200) mark_ok "Qobuz token" "valid (buy-link lookup live)" ;;
401) mark_warn "Qobuz token" "EXPIRED — re-export X-User-Auth-Token to ${ALEMBIC_CONFIG_DIR:-/config}/pipeline/qobuz/token" ;;
# A genuinely expired/bad token gets a JSON 401 from Qobuz's own API.
# 403 instead means the request never reached that code at all -- Qobuz's
# Akamai edge is rejecting the request outright (seen 2026-07-22: the
# exact same request got this "Access Denied"/edgesuite.net block from
# alembic's VPN egress IP, but a clean 401 from a non-VPN IP). Re-
# exporting the token does nothing for that -- it's the egress IP's
# reputation, not the credential. Say so, so it isn't mistaken for 401.
403) mark_warn "Qobuz token" "blocked (HTTP 403, likely Akamai/CDN, not the token) — VPN egress IP may be flagged; re-exporting the token won't fix this" ;;
*) mark_warn "Qobuz token" "check failed (HTTP ${q_code:-none})" ;;
esac
else
+1 -1
View File
@@ -29,7 +29,7 @@ Usage:
scrub-watermark-text.py # dry run
scrub-watermark-text.py --apply # actually strip
"""
import sys, re, argparse
import os, sys, re, argparse
from pathlib import Path
from mutagen import File as MFile
from mutagen.id3 import ID3, ID3NoHeaderError