Add songforge as independent repo with path layout.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
swl
2026-10-09 19:18:33 +08:00
co-authored by Cursor
commit f39deb1848
52 changed files with 10289 additions and 0 deletions
+173
View File
@@ -0,0 +1,173 @@
# -*- coding: utf-8 -*-
"""全局索引 catalog.jsonl:只存元数据,可从 runs 重建。"""
import json
import os
import re
from . import paths as pmod
def catalog_path(cfg):
p = cfg["paths"].get("catalog_file") or "songforge/index/catalog.jsonl"
return pmod.under_workflows(p)
def day_dir(runs_root, day=None):
"""runs_root/YYYY-MM-DD/"""
import datetime
if not day:
day = datetime.date.today().isoformat()
return os.path.join(runs_root, day)
def allocate_run_dir(runs_root, run_id, day=None):
"""占位 data/runs/YYYY-MM-DD/<run_id>/,返回绝对路径。"""
d = day_dir(runs_root, day)
pmod.ensure_dir(d)
path = os.path.join(d, run_id)
os.makedirs(path, exist_ok=False)
return path
def find_run_dir(runs_root, run_id):
"""在按日目录、_migrated、扁平根下查找 run 目录。"""
rid = (run_id or "").strip().rstrip("/\\")
if not rid:
return None
if os.path.isdir(rid) and os.path.isfile(os.path.join(rid, "manifest.json")):
return os.path.abspath(rid)
base = os.path.basename(rid.replace("/", os.sep))
if not os.path.isdir(runs_root):
return None
# 直接子目录(兼容旧扁平)
cand = os.path.join(runs_root, base)
if os.path.isfile(os.path.join(cand, "manifest.json")):
return cand
# 按日
for day in os.listdir(runs_root):
day_path = os.path.join(runs_root, day)
if not os.path.isdir(day_path):
continue
cand = os.path.join(day_path, base)
if os.path.isfile(os.path.join(cand, "manifest.json")):
return cand
# _migrated 下也可能套一层
if day in ("_migrated",):
for sub in os.listdir(day_path):
cand = os.path.join(day_path, sub)
if os.path.basename(cand) == base and \
os.path.isfile(os.path.join(cand, "manifest.json")):
return cand
# 全树兜底
for root, dirs, files in os.walk(runs_root):
if os.path.basename(root) == base and "manifest.json" in files:
return root
return None
def _entry_from_manifest(rundir, man):
results = man.get("results") or []
seeds = [r.get("seed") for r in results if r.get("seed") is not None]
files = []
for r in results:
for fn in r.get("files") or []:
files.append(fn)
day = None
m = re.search(r"(\d{4}-\d{2}-\d{2})", rundir.replace("\\", "/"))
if m:
day = m.group(1)
elif man.get("created"):
day = str(man["created"])[:10]
return {
"run_id": man.get("run_id") or os.path.basename(rundir),
"date": day,
"title": man.get("title"),
"style": man.get("style"),
"bpm": man.get("bpm"),
"key": man.get("key"),
"duration": man.get("duration"),
"seeds": seeds,
"qc_verdict": man.get("qc_verdict"),
"audio_files": files,
"path": rundir.replace("\\", "/"),
}
def append_entry(cfg, entry):
path = catalog_path(cfg)
pmod.ensure_dir(os.path.dirname(path))
with open(path, "a", encoding="utf-8") as f:
f.write(json.dumps(entry, ensure_ascii=False) + "\n")
return path
def update_qc_verdict(cfg, run_id, verdict):
"""重写 catalog:更新匹配 run_id 的 qc_verdict。"""
path = catalog_path(cfg)
if not os.path.isfile(path):
return
rows = []
with open(path, encoding="utf-8") as f:
for line in f:
line = line.strip()
if not line:
continue
try:
row = json.loads(line)
except ValueError:
continue
if row.get("run_id") == run_id:
row["qc_verdict"] = verdict
rows.append(row)
with open(path, "w", encoding="utf-8") as f:
for row in rows:
f.write(json.dumps(row, ensure_ascii=False) + "\n")
def rebuild(cfg):
"""扫描 runs_dir,重写 catalog.jsonl。"""
runs_root = pmod.under_workflows(cfg["paths"]["runs_dir"])
entries = []
if os.path.isdir(runs_root):
for root, dirs, files in os.walk(runs_root):
if "manifest.json" not in files:
continue
mp = os.path.join(root, "manifest.json")
try:
with open(mp, encoding="utf-8") as f:
man = json.load(f)
except (ValueError, OSError):
continue
entries.append(_entry_from_manifest(root, man))
entries.sort(key=lambda e: (e.get("date") or "", e.get("run_id") or ""))
path = catalog_path(cfg)
pmod.ensure_dir(os.path.dirname(path))
with open(path, "w", encoding="utf-8") as f:
for e in entries:
f.write(json.dumps(e, ensure_ascii=False) + "\n")
return path, len(entries)
def list_entries(cfg, day=None, limit=50):
path = catalog_path(cfg)
if not os.path.isfile(path):
return []
out = []
with open(path, encoding="utf-8") as f:
for line in f:
line = line.strip()
if not line:
continue
try:
row = json.loads(line)
except ValueError:
continue
if day and row.get("date") != day:
continue
out.append(row)
out.reverse()
return out[:limit]
def entry_from_gen(rundir, manifest):
return _entry_from_manifest(rundir, manifest)