Files
swlandCursor 6d79ab93a2
selftest / selftest (push) Canceled after 0s
Add align/recheck/compare, plugins, and refresh Agent docs.
Wire deliver_report/listen_pack/retry hooks; gen --auto-retry and intro light check; make AGENTS_MIN the up-to-date agent entry with full command map.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-10 13:03:44 +08:00

197 lines
7.2 KiB
Python
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# -*- coding: utf-8 -*-
"""扩展命令:compare / align / recheck。"""
import json
import os
import subprocess
from ..config import loader
from ..core import catalog as catmod
from ..core import paths as pmod
from ..lyrics import align as alignmod
from ..lyrics import meter
from .common import build_cfg, resolve_profile, runs_root, style_of
from .qc import find_qc_python
def _load_run(cfg, run_id):
rundir = catmod.find_run_dir(runs_root(cfg), run_id)
if not rundir:
return None, None, None
man = {}
mp = os.path.join(rundir, "manifest.json")
if os.path.isfile(mp):
with open(mp, encoding="utf-8") as f:
man = json.load(f)
qc = {}
qp = os.path.join(rundir, "qc.json")
if os.path.isfile(qp):
with open(qp, encoding="utf-8") as f:
qc = json.load(f)
return rundir, man, qc
def _qc_rows(qc):
if not qc:
return []
return qc.get("rows") or qc.get("results") or []
def _first_audio(cfg, man, rundir):
music = man.get("output_dir") or pmod.music_dir(cfg, pmod.comfy_root(cfg=cfg))
for r in man.get("results") or []:
for fn in r.get("files") or []:
p = fn if os.path.isabs(fn) else os.path.join(music, os.path.basename(fn))
if os.path.isfile(p):
return p
# 也搜 rundir
p2 = os.path.join(rundir, os.path.basename(fn))
if os.path.isfile(p2):
return p2
return None
def cmd_compare(args):
cfg = loader.load({})
ids = []
for part in (args.runs or []):
ids.extend([x.strip() for x in part.split(",") if x.strip()])
if len(ids) < 2:
print("[错误] 至少两个 run:songforge compare --runs a,b")
return 2
print("%-26s %-8s %-5s %-5s %-6s %-8s %-7s %-8s %s"
% ("run_id", "style", "BPM", "dur", "QC", "onset", "衬词比",
"voice_nn", "title"))
for rid in ids:
rundir, man, qc = _load_run(cfg, rid)
if not rundir:
print("%-26s (找不到)" % rid)
continue
rows = [r for r in _qc_rows(qc) if r.get("group") != "baseline"]
r0 = rows[0] if rows else {}
verd = None
for v in (qc.get("verdicts") or []):
verd = v.get("verdict")
break
if not verd:
verd = man.get("qc_verdict") or "-"
print("%-26s %-8s %-5s %-5s %-6s %-8s %-7s %-8s %s"
% ((man.get("run_id") or rid)[:26],
(man.get("style") or "-")[:8],
man.get("bpm") or "-",
man.get("duration") or "-",
(verd or "-")[:6],
r0.get("vocal_onset") if r0.get("vocal_onset") is not None else "-",
("%.0f%%" % (float(r0.get("intro_filler_ratio") or 0) * 100))
if r0 else "-",
(str(r0.get("voice_nn") or "-"))[:8],
(man.get("title") or "-")[:16]))
return 0
def cmd_align(args):
cfg = build_cfg(args)
st = style_of(cfg, args.style, args)
if args.lyrics_file:
with open(args.lyrics_file, encoding="utf-8") as f:
raw = f.read()
elif args.lyrics:
raw = args.lyrics
else:
print("[错误] 需要 --lyrics-file 或 --lyrics")
return 2
prof = resolve_profile(args)
cfg_ly = meter.pick(cfg["lyrics"], prof)
out, diag = alignmod.align_lyrics(
raw, st["duration"], st["bpm"], cfg_ly, target=args.target)
dest = args.out or (args.lyrics_file and (
os.path.splitext(args.lyrics_file)[0] + "_aligned.txt"))
if not dest:
dest = os.path.join(pmod.tmp_today(cfg), "aligned.txt")
pmod.ensure_dir(os.path.dirname(dest))
with open(dest, "w", encoding="utf-8") as f:
f.write(out)
print("== align ==")
print(" 音节 %d -> %d 目标 %d 窗口 %d~%d ok=%s"
% (diag["before"], diag["after"], diag["want"],
diag["win_lo"], diag["win_hi"], diag.get("ok")))
print(" 写出: %s" % dest)
if not diag.get("ok"):
print(" [WARN] %s" % diag.get("note"))
return 1
return 0
def run_intro_check(cfg, audio_path, bpm=104, intro_bars=8, lang="zh"):
"""子进程开曲轻检。返回 (code, blob)。"""
py = find_qc_python(cfg)
if not py:
return 2, dict(error="no qc_python")
worker = os.path.join(pmod.PKG_ROOT, "tools", "intro_check_worker.py")
job = dict(file=os.path.abspath(audio_path), bpm=bpm,
intro_bars=intro_bars, lang=lang)
env = dict(os.environ)
env["PYTHONIOENCODING"] = "utf-8"
env["SONGFORGE_COMFY_ROOT"] = pmod.comfy_root(cfg=cfg)
try:
r = subprocess.run(
[py, worker, json.dumps(job, ensure_ascii=False)],
capture_output=True, env=env, timeout=600)
except subprocess.TimeoutExpired:
return 2, dict(error="timeout")
out = r.stdout.decode("utf-8", "replace")
if "###JSON###" not in out:
return 2, dict(error="no json", log=out[-800:])
blob = json.loads(out.split("###JSON###", 1)[1].strip())
return (0 if not blob.get("error") else 1), blob
def cmd_recheck(args):
cfg = loader.load({})
rundir, man, _qc = _load_run(cfg, args.run)
if not rundir:
print("[错误] 找不到 run: %s" % args.run)
return 2
audio = args.file or _first_audio(cfg, man, rundir)
if not audio or not os.path.isfile(audio):
print("[错误] 找不到音频。可传 --file")
return 2
bpm = args.bpm or man.get("bpm") or 104
bars = args.intro_bars or man.get("intro_bars") or 8
lang = args.lang or man.get("language") or "zh"
code, blob = run_intro_check(cfg, audio, bpm=bpm, intro_bars=bars, lang=lang)
outp = os.path.join(rundir, "intro_check.json")
with open(outp, "w", encoding="utf-8") as f:
json.dump(blob, f, ensure_ascii=False, indent=1)
print(json.dumps(blob, ensure_ascii=False, indent=1))
print("报告: %s" % outp)
if blob.get("error"):
return 2
return 0 if blob.get("ok") else 1
def add_extras(sub):
c = sub.add_parser("compare", help="对比多次 run 的 QC/开曲指标")
c.add_argument("--runs", action="append", required=True,
help="run_id 列表,逗号分隔,可多次")
c.set_defaults(func=cmd_compare)
a = sub.add_parser("align", help="歌词音节一键对齐到 target 放行窗")
a.add_argument("--style", required=True)
a.add_argument("--lyrics-file", dest="lyrics_file")
a.add_argument("--lyrics")
a.add_argument("--out", help="输出路径(默认 *_aligned.txt)")
a.add_argument("--bpm", type=int)
a.add_argument("--dur", type=int)
a.add_argument("--target", type=int, help="目标音节(默认取建议值)")
a.add_argument("--chill-vocal", dest="chill_vocal", action="store_true")
a.add_argument("--density-profile", dest="density_profile")
a.set_defaults(func=cmd_align)
r = sub.add_parser("recheck", help="开曲轻检(前奏窗 ASR 衬词)")
r.add_argument("--run", required=True)
r.add_argument("--file", help="直接指定音频")
r.add_argument("--bpm", type=int)
r.add_argument("--intro-bars", dest="intro_bars", type=int)
r.add_argument("--lang", default=None)
r.set_defaults(func=cmd_recheck)