Skip to content

wanghai-tech / hikoon-ACR

Go to a project
Toggle navigation
Toggle navigation pinning
Commit 3b4b3684 3b4b3684db879c726713a3719bad04ad251cd0a7 by cnb.bofCdSsphPA
Options

Collapse the song-centric directory workflow into one live runner 

Constraint: Keep the current real-directory onboarding path executable end-to-end on this host while exposing exact/semantic backend selection in one reproducible report.
Rejected: Leave the song-centric pipeline as multiple manual commands only | It raises handoff cost and makes repeated host validation slower and noisier.
Confidence: high
Scope-risk: narrow
Directive: Use run_songcentric_directory_pipeline_live.py as the default smoke/verification entrypoint for the current song-centric ingestion path.
Tested: /usr/local/miniconda3/bin/python acr-engine/scripts/run_songcentric_directory_pipeline_live.py --dsn postgres://d2:d2pass@127.0.0.1:5432/d2 --schema acr_songcentric_test --input-root acr-engine/data/songcentric_builder_smoke --output-dir acr-engine/data/pgvector_eval/music20; git diff --check; /usr/local/miniconda3/bin/python scripts/check_markdown_links.py --root docs returned OK for 11 active markdown files
Not-tested: very large directory trees and true semantic runtime readiness on this host
1 parent 35d883a8
Inline Side-by-side
Showing 10 changed files with 282 additions and 0 deletions
{
"input_root": "/workspace/acr-engine/data/songcentric_builder_smoke",
"output": "/workspace/acr-engine/data/pgvector_eval/music20/songcentric_pipeline_manifest.jsonl",
"song_count": 2,
"asset_count": 2,
"window_count": 5,
"window_ms": 5000,
"stride_ms": 2500,
"set_name": "phase1_hot_reference_v1"
}
\ No newline at end of file
{
"input_manifest": "/workspace/acr-engine/data/pgvector_eval/music20/songcentric_pipeline_manifest.jsonl",
"output_manifest": "/workspace/acr-engine/data/pgvector_eval/music20/songcentric_pipeline_manifest_with_features.jsonl",
"rows": 2,
"wav_windows_seen": 5,
"features_added": 10,
"matcher_fingerprint_count": 5,
"fallback_fingerprint_count": 0,
"semantic_runtime_available": false,
"semantic_runtime_missing": [
"torch",
"torchaudio",
"transformers"
],
"semantic_runtime_ready_count": 0,
"semantic_fallback_count": 5
}
\ No newline at end of file
{
"schema": "acr_songcentric_test",
"manifest": "acr-engine/data/pgvector_eval/music20/songcentric_pipeline_manifest_with_features.jsonl",
"imported": [
{
"song_id": 8,
"asset_id": 16,
"window_ids": [
17,
18,
19
],
"feature_ids": [
20,
11,
21,
13,
22,
15
],
"membership_ids": [
8
]
},
{
"song_id": 9,
"asset_id": 20,
"window_ids": [
21,
22
],
"feature_ids": [
23,
17,
24,
19
],
"membership_ids": [
9
]
}
],
"counts": {
"media_entity": 9,
"audio_object": 22,
"feature_fact": 24,
"set_membership": 9
},
"window_lineage_sample": {
"window_id": 22,
"asset_id": 20,
"song_id": 9,
"title": "song beta",
"start_ms": 1000,
"end_ms": 6000
},
"feature_lineage_sample": {
"feature_type": "fingerprint",
"model_name": "chromaprint_matcher",
"model_version": "phase1_local",
"feature_set_name": "chromaprint_matcher_5s",
"window_id": 22,
"song_id": 9,
"title": "song beta"
}
}
\ No newline at end of file
{"song": {"biz_key": "song_alpha", "title": "song alpha", "artist_name": "artist a"}, "asset": {"source_type": "official", "storage_uri": "/workspace/acr-engine/data/songcentric_builder_smoke/song_alpha/artist_a/clip1.wav", "storage_scheme": "file", "checksum": "path:/workspace/acr-engine/data/songcentric_builder_smoke/song_alpha/artist_a/clip1.wav", "codec": "wav", "sample_rate": 16000, "channels": 1, "duration_ms": 8000}, "windows": [{"start_ms": 0, "end_ms": 5000}, {"start_ms": 2500, "end_ms": 7500}, {"start_ms": 3000, "end_ms": 8000}], "memberships": [{"set_type": "reference_set", "set_name": "phase1_hot_reference_v1", "member_type": "asset", "priority": 100}]}
{"song": {"biz_key": "song_beta", "title": "song beta", "artist_name": "artist b"}, "asset": {"source_type": "official", "storage_uri": "/workspace/acr-engine/data/songcentric_builder_smoke/song_beta/artist_b/clip2.wav", "storage_scheme": "file", "checksum": "path:/workspace/acr-engine/data/songcentric_builder_smoke/song_beta/artist_b/clip2.wav", "codec": "wav", "sample_rate": 16000, "channels": 1, "duration_ms": 6000}, "windows": [{"start_ms": 0, "end_ms": 5000}, {"start_ms": 1000, "end_ms": 6000}], "memberships": [{"set_type": "reference_set", "set_name": "phase1_hot_reference_v1", "member_type": "asset", "priority": 100}]}
{"song": {"biz_key": "song_alpha", "title": "song alpha", "artist_name": "artist a"}, "asset": {"source_type": "official", "storage_uri": "/workspace/acr-engine/data/songcentric_builder_smoke/song_alpha/artist_a/clip1.wav", "storage_scheme": "file", "checksum": "path:/workspace/acr-engine/data/songcentric_builder_smoke/song_alpha/artist_a/clip1.wav", "codec": "wav", "sample_rate": 16000, "channels": 1, "duration_ms": 8000}, "windows": [{"start_ms": 0, "end_ms": 5000, "features": [{"feature_type": "fingerprint", "model_name": "chromaprint_matcher", "model_version": "phase1_local", "feature_set_name": "chromaprint_matcher_5s", "fingerprint_value": "dc0c731425f360787f462da693ff4a50", "checksum": "chromaprint:dc0c731425f36078", "metadata_json": {"hash_count": 2643, "hash_sample": [[1842187, 11], [1842188, 11], [1842189, 11], [1842201, 11], [1842212, 11], [1842213, 11], [1842214, 11], [1842438, 11]]}}, {"feature_type": "embedding", "model_name": "local_wavehash_embed", "model_version": "v1", "feature_set_name": "wavehash_embed_5s", "feature_schema_ver": "v1", "embedding_dim": 8, "embedding_uri": "inline://593c7a661cc87444:0:5000", "vector_table_name": "audio_embedding_vector_8_placeholder", "checksum": "emb:593c7a661cc87444", "metadata_json": {"energy": 30555200, "rate": 16000, "channels": 1, "semantic_backend": "local_fallback", "runtime_missing": ["torch", "torchaudio", "transformers"]}}]}, {"start_ms": 2500, "end_ms": 7500, "features": [{"feature_type": "fingerprint", "model_name": "chromaprint_matcher", "model_version": "phase1_local", "feature_set_name": "chromaprint_matcher_5s", "fingerprint_value": "dc0c731425f360787f462da693ff4a50", "checksum": "chromaprint:dc0c731425f36078", "metadata_json": {"hash_count": 2643, "hash_sample": [[1842187, 11], [1842188, 11], [1842189, 11], [1842201, 11], [1842212, 11], [1842213, 11], [1842214, 11], [1842438, 11]]}}, {"feature_type": "embedding", "model_name": "local_wavehash_embed", "model_version": "v1", "feature_set_name": "wavehash_embed_5s", "feature_schema_ver": "v1", "embedding_dim": 8, "embedding_uri": "inline://593c7a661cc87444:2500:7500", "vector_table_name": "audio_embedding_vector_8_placeholder", "checksum": "emb:593c7a661cc87444", "metadata_json": {"energy": 30555200, "rate": 16000, "channels": 1, "semantic_backend": "local_fallback", "runtime_missing": ["torch", "torchaudio", "transformers"]}}]}, {"start_ms": 3000, "end_ms": 8000, "features": [{"feature_type": "fingerprint", "model_name": "chromaprint_matcher", "model_version": "phase1_local", "feature_set_name": "chromaprint_matcher_5s", "fingerprint_value": "dc0c731425f360787f462da693ff4a50", "checksum": "chromaprint:dc0c731425f36078", "metadata_json": {"hash_count": 2643, "hash_sample": [[1842187, 11], [1842188, 11], [1842189, 11], [1842201, 11], [1842212, 11], [1842213, 11], [1842214, 11], [1842438, 11]]}}, {"feature_type": "embedding", "model_name": "local_wavehash_embed", "model_version": "v1", "feature_set_name": "wavehash_embed_5s", "feature_schema_ver": "v1", "embedding_dim": 8, "embedding_uri": "inline://593c7a661cc87444:3000:8000", "vector_table_name": "audio_embedding_vector_8_placeholder", "checksum": "emb:593c7a661cc87444", "metadata_json": {"energy": 30555200, "rate": 16000, "channels": 1, "semantic_backend": "local_fallback", "runtime_missing": ["torch", "torchaudio", "transformers"]}}]}], "memberships": [{"set_type": "reference_set", "set_name": "phase1_hot_reference_v1", "member_type": "asset", "priority": 100}]}
{"song": {"biz_key": "song_beta", "title": "song beta", "artist_name": "artist b"}, "asset": {"source_type": "official", "storage_uri": "/workspace/acr-engine/data/songcentric_builder_smoke/song_beta/artist_b/clip2.wav", "storage_scheme": "file", "checksum": "path:/workspace/acr-engine/data/songcentric_builder_smoke/song_beta/artist_b/clip2.wav", "codec": "wav", "sample_rate": 16000, "channels": 1, "duration_ms": 6000}, "windows": [{"start_ms": 0, "end_ms": 5000, "features": [{"feature_type": "fingerprint", "model_name": "chromaprint_matcher", "model_version": "phase1_local", "feature_set_name": "chromaprint_matcher_5s", "fingerprint_value": "d8fc2442b4ec3ce5ae180c5845cffccb", "checksum": "chromaprint:d8fc2442b4ec3ce5", "metadata_json": {"hash_count": 2202, "hash_sample": [[2763289, 23], [2763524, 23], [2763541, 23], [2763549, 23], [2763566, 23], [2763801, 23], [2764050, 23], [2764075, 23]]}}, {"feature_type": "embedding", "model_name": "local_wavehash_embed", "model_version": "v1", "feature_set_name": "wavehash_embed_5s", "feature_schema_ver": "v1", "embedding_dim": 8, "embedding_uri": "inline://4ed2ccfa55b10b88:0:5000", "vector_table_name": "audio_embedding_vector_8_placeholder", "checksum": "emb:4ed2ccfa55b10b88", "metadata_json": {"energy": 30555680, "rate": 16000, "channels": 1, "semantic_backend": "local_fallback", "runtime_missing": ["torch", "torchaudio", "transformers"]}}]}, {"start_ms": 1000, "end_ms": 6000, "features": [{"feature_type": "fingerprint", "model_name": "chromaprint_matcher", "model_version": "phase1_local", "feature_set_name": "chromaprint_matcher_5s", "fingerprint_value": "d8fc2442b4ec3ce5ae180c5845cffccb", "checksum": "chromaprint:d8fc2442b4ec3ce5", "metadata_json": {"hash_count": 2202, "hash_sample": [[2763289, 23], [2763524, 23], [2763541, 23], [2763549, 23], [2763566, 23], [2763801, 23], [2764050, 23], [2764075, 23]]}}, {"feature_type": "embedding", "model_name": "local_wavehash_embed", "model_version": "v1", "feature_set_name": "wavehash_embed_5s", "feature_schema_ver": "v1", "embedding_dim": 8, "embedding_uri": "inline://4ed2ccfa55b10b88:1000:6000", "vector_table_name": "audio_embedding_vector_8_placeholder", "checksum": "emb:4ed2ccfa55b10b88", "metadata_json": {"energy": 30555680, "rate": 16000, "channels": 1, "semantic_backend": "local_fallback", "runtime_missing": ["torch", "torchaudio", "transformers"]}}]}], "memberships": [{"set_type": "reference_set", "set_name": "phase1_hot_reference_v1", "member_type": "asset", "priority": 100}]}
{
"schema": "acr_songcentric_test",
"input_root": "acr-engine/data/songcentric_builder_smoke",
"steps": [
{
"name": "build_manifest",
"command": "/usr/local/miniconda3/bin/python acr-engine/scripts/build_songcentric_manifest_from_directory.py --input-root acr-engine/data/songcentric_builder_smoke --output acr-engine/data/pgvector_eval/music20/songcentric_pipeline_manifest.jsonl --report-output acr-engine/data/pgvector_eval/music20/songcentric_pipeline_build_report.json",
"returncode": 0
},
{
"name": "enrich_features",
"command": "/usr/local/miniconda3/bin/python acr-engine/scripts/enrich_songcentric_manifest_with_local_features.py --input-manifest acr-engine/data/pgvector_eval/music20/songcentric_pipeline_manifest.jsonl --output-manifest acr-engine/data/pgvector_eval/music20/songcentric_pipeline_manifest_with_features.jsonl --report-output acr-engine/data/pgvector_eval/music20/songcentric_pipeline_enrich_report.json",
"returncode": 0
},
{
"name": "import_manifest",
"command": "/usr/local/miniconda3/bin/python acr-engine/scripts/import_songcentric_manifest_live.py --dsn postgres://d2:d2pass@127.0.0.1:5432/d2 --schema acr_songcentric_test --manifest acr-engine/data/pgvector_eval/music20/songcentric_pipeline_manifest_with_features.jsonl --output acr-engine/data/pgvector_eval/music20/songcentric_pipeline_import_report.json",
"returncode": 0
}
],
"build_summary": {
"input_root": "/workspace/acr-engine/data/songcentric_builder_smoke",
"output": "/workspace/acr-engine/data/pgvector_eval/music20/songcentric_pipeline_manifest.jsonl",
"song_count": 2,
"asset_count": 2,
"window_count": 5,
"window_ms": 5000,
"stride_ms": 2500,
"set_name": "phase1_hot_reference_v1"
},
"enrich_summary": {
"wav_windows_seen": 5,
"features_added": 10,
"matcher_fingerprint_count": 5,
"fallback_fingerprint_count": 0,
"semantic_runtime_available": false,
"semantic_runtime_missing": [
"torch",
"torchaudio",
"transformers"
],
"semantic_runtime_ready_count": 0,
"semantic_fallback_count": 5
},
"import_counts": {
"media_entity": 9,
"audio_object": 22,
"feature_fact": 24,
"set_membership": 9
},
"feature_lineage_sample": {
"feature_type": "fingerprint",
"model_name": "chromaprint_matcher",
"model_version": "phase1_local",
"feature_set_name": "chromaprint_matcher_5s",
"window_id": 22,
"song_id": 9,
"title": "song beta"
}
}
\ No newline at end of file
#!/usr/bin/env /usr/local/miniconda3/bin/python
from __future__ import annotations
import argparse
import json
import subprocess
from pathlib import Path
ROOT = Path(__file__).resolve().parents[1]
PYTHON = '/usr/local/miniconda3/bin/python'
def run_step(name: str, cmd: list[str]) -> dict:
proc = subprocess.run(cmd, cwd=str(ROOT.parent), capture_output=True, text=True)
return {
'name': name,
'command': ' '.join(cmd),
'returncode': proc.returncode,
'stdout': proc.stdout,
'stderr': proc.stderr,
}
def load_json(path: Path) -> dict:
return json.loads(path.read_text())
def main() -> int:
parser = argparse.ArgumentParser()
parser.add_argument('--dsn', required=True)
parser.add_argument('--schema', default='acr_songcentric_test')
parser.add_argument('--input-root', default='acr-engine/data/songcentric_builder_smoke')
parser.add_argument('--output-dir', default='acr-engine/data/pgvector_eval/music20')
args = parser.parse_args()
out_dir = (ROOT.parent / args.output_dir).resolve()
out_dir.mkdir(parents=True, exist_ok=True)
manifest = out_dir / 'songcentric_pipeline_manifest.jsonl'
build_report = out_dir / 'songcentric_pipeline_build_report.json'
enriched_manifest = out_dir / 'songcentric_pipeline_manifest_with_features.jsonl'
enrich_report = out_dir / 'songcentric_pipeline_enrich_report.json'
import_report = out_dir / 'songcentric_pipeline_import_report.json'
steps = []
steps.append(run_step('build_manifest', [
PYTHON, 'acr-engine/scripts/build_songcentric_manifest_from_directory.py',
'--input-root', args.input_root,
'--output', str(manifest.relative_to(ROOT.parent)),
'--report-output', str(build_report.relative_to(ROOT.parent)),
]))
if steps[-1]['returncode'] != 0:
raise SystemExit(json.dumps({'failed_step': steps[-1]}, ensure_ascii=False, indent=2))
steps.append(run_step('enrich_features', [
PYTHON, 'acr-engine/scripts/enrich_songcentric_manifest_with_local_features.py',
'--input-manifest', str(manifest.relative_to(ROOT.parent)),
'--output-manifest', str(enriched_manifest.relative_to(ROOT.parent)),
'--report-output', str(enrich_report.relative_to(ROOT.parent)),
]))
if steps[-1]['returncode'] != 0:
raise SystemExit(json.dumps({'failed_step': steps[-1]}, ensure_ascii=False, indent=2))
steps.append(run_step('import_manifest', [
PYTHON, 'acr-engine/scripts/import_songcentric_manifest_live.py',
'--dsn', args.dsn,
'--schema', args.schema,
'--manifest', str(enriched_manifest.relative_to(ROOT.parent)),
'--output', str(import_report.relative_to(ROOT.parent)),
]))
if steps[-1]['returncode'] != 0:
raise SystemExit(json.dumps({'failed_step': steps[-1]}, ensure_ascii=False, indent=2))
build = load_json(build_report)
enrich = load_json(enrich_report)
imp = load_json(import_report)
summary = {
'schema': args.schema,
'input_root': args.input_root,
'steps': [{k: v for k, v in s.items() if k in ('name', 'command', 'returncode')} for s in steps],
'build_summary': build,
'enrich_summary': {
'wav_windows_seen': enrich['wav_windows_seen'],
'features_added': enrich['features_added'],
'matcher_fingerprint_count': enrich['matcher_fingerprint_count'],
'fallback_fingerprint_count': enrich['fallback_fingerprint_count'],
'semantic_runtime_available': enrich['semantic_runtime_available'],
'semantic_runtime_missing': enrich['semantic_runtime_missing'],
'semantic_runtime_ready_count': enrich['semantic_runtime_ready_count'],
'semantic_fallback_count': enrich['semantic_fallback_count'],
},
'import_counts': imp['counts'],
'feature_lineage_sample': imp.get('feature_lineage_sample'),
}
report_path = out_dir / 'songcentric_pipeline_runner_report.json'
report_path.write_text(json.dumps(summary, ensure_ascii=False, indent=2))
print(json.dumps(summary, ensure_ascii=False, indent=2))
return 0
if __name__ == '__main__':
raise SystemExit(main())
## 2026-06-04
- 新增 `acr-engine/scripts/run_songcentric_directory_pipeline_live.py`，把“真实目录 -> manifest -> 特征补全 -> live PostgreSQL 导入”收敛为一条可重复执行的 runner，并输出 exact/semantic backend 选择与导入计数摘要。
- 升级 `enrich_songcentric_manifest_with_local_features.py` 为 runtime-aware 语义适配器选择：当前 host 上因缺少 `torch/torchaudio/transformers`，semantic lane 明确写入 `local_wavehash_embed` fallback，并把缺失依赖固化到 report/metadata 中。
- 升级 `enrich_songcentric_manifest_with_local_features.py`：目录链中的 fingerprint 现优先复用仓库内 `ChromaprintMatcher`，并在 live PostgreSQL 上验证 5 个 wav windows 全部命中 matcher 路径、`fallback_fingerprint_count=0`。
......
......@@ -326,6 +326,25 @@ flowchart TD
这说明当前 host 上 semantic lane 还未接真实模型，但链路已经具备明确的运行时分流与可审计证据。
### 4.10 一键 song-centric 目录链 runner
```mermaid
flowchart TD
A[run_songcentric_directory_pipeline_live.py] --> B[build manifest]
B --> C[enrich features]
C --> D[import manifest]
D --> E[runner report]
```
当前 runner：[`acr-engine/scripts/run_songcentric_directory_pipeline_live.py`](../acr-engine/scripts/run_songcentric_directory_pipeline_live.py)
它会在一条命令里输出：
- 目录扫描结果
- exact lane 是否走 `ChromaprintMatcher`
- semantic lane 是否 runtime-ready
- live PostgreSQL 导入后的计数与 lineage 样例
---
## 5. 最常用 SQL 样例
......
......@@ -153,6 +153,7 @@ model_registry -> feature_set_registry -> audio_embedding / audio_fingerprint ->
- `acr-engine/scripts/run_phase1_worker_contract_smoke_live.py`
- `acr-engine/scripts/run_embedding_vector_table_negative_matrix_live.py`
- `acr-engine/scripts/validate_audio_embedding_asset_upsert_live.py`
- `acr-engine/scripts/run_songcentric_directory_pipeline_live.py`
---
......