feat(build): 任务书 02 第四阶段代码——build 装入 CEUS 结果
- build.yaml 加必填字段 ceus_run（CEUS 运行目录或 null）。 - 不为 null 时按视频号找结果；在 failed.csv 里或缺结果目录的整例跳过，记 C15；关键帧图沿用 C14 检查。 - 资料库超声一路加 keyframes/<槽位>.png（去附加数据重编码）和 tic.json（白名单逐字段构造： 四条曲线的拟合成败与 R²、灌注指标、紫圈曲线是否可用、7 个槽位的定位与视频时间或原因）。 - manifest 的 CEUS 来源写运行号；泄露扫描已覆盖 tic.json，补命中测试。 - 真实构建等配准改完、全量 CEUS 运行之后再做。 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -0,0 +1,220 @@
|
||||
"""build 装入 CEUS 结果：C15 跳过、tic.json 只有白名单字段、关键帧去附加数据、运行目录不合规时停下。
|
||||
|
||||
预期的 tic.json 键集合照任务书 02 第四阶段的文字手写：四条曲线各自拟合是否成功和拟合优度（R²）；
|
||||
病灶两条曲线的灌注指标（同旧 replay summary 的 perfusion_metrics 段）；紫圈曲线是否可用；
|
||||
7 个槽位各自是否定位到、定位到的视频时间、未定位的原因。
|
||||
"""
|
||||
|
||||
import csv
|
||||
import json
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
from typing import Any, cast
|
||||
|
||||
import pytest
|
||||
from PIL import Image
|
||||
|
||||
from cadx.answers import read_aliases
|
||||
from cadx.build import BuildSummary, run_build
|
||||
from cadx.library import list_aliases, read_ultrasound, scan_for_leaks
|
||||
from fake_ceus_run import UNLOCATED_REASON, summary, write_run
|
||||
from fake_delivery import REPO_ROOT, make_delivery, write_config
|
||||
|
||||
NOW = datetime(2026, 10, 16, 11, 0, 0).astimezone()
|
||||
RUN_ID = "20261016-100000-abcdef0"
|
||||
LOCATED = ("D1", "D2", "F1")
|
||||
|
||||
_PERFUSION_KEYS = {
|
||||
"signal_domain",
|
||||
"time_origin",
|
||||
"area_curve",
|
||||
"values",
|
||||
"supporting_times_s",
|
||||
}
|
||||
_PERFUSION_VALUES = {
|
||||
"PE_au",
|
||||
"WiAUC_au_s",
|
||||
"RT_s",
|
||||
"mTTl_s",
|
||||
"TTP_s",
|
||||
"WiR_au_per_s",
|
||||
"WiPI_au",
|
||||
"WoAUC_au_s",
|
||||
"WiWoAUC_au_s",
|
||||
"FT_s",
|
||||
"WoR_au_per_s",
|
||||
}
|
||||
|
||||
|
||||
def _build(tmp_path: Path, count: int, run_dir: Path) -> BuildSummary:
|
||||
root = make_delivery(count).write(tmp_path / "delivery")
|
||||
return run_build(write_config(tmp_path, root, 1, None, run_dir), REPO_ROOT, NOW)
|
||||
|
||||
|
||||
def _skipped(answers_dir: Path) -> list[list[str]]:
|
||||
with (answers_dir / "skipped.csv").open(encoding="utf-8-sig", newline="") as handle:
|
||||
return list(csv.reader(handle))[1:]
|
||||
|
||||
|
||||
def _png_chunks(data: bytes) -> list[str]:
|
||||
chunks: list[str] = []
|
||||
offset = 8
|
||||
while offset < len(data):
|
||||
length = int.from_bytes(data[offset : offset + 4], "big")
|
||||
chunks.append(data[offset + 4 : offset + 8].decode("ascii"))
|
||||
offset += 12 + length
|
||||
return chunks
|
||||
|
||||
|
||||
def _key_tree(node: Any) -> Any:
|
||||
"""嵌套字典的键结构：字典换成「键 → 子结构」，其余值换成 None。"""
|
||||
if isinstance(node, dict):
|
||||
return {key: _key_tree(value) for key, value in cast(dict[str, Any], node).items()}
|
||||
return None
|
||||
|
||||
|
||||
def test_c15_skips_failed_and_missing_cases(tmp_path: Path) -> None:
|
||||
run = write_run(
|
||||
tmp_path / "runs" / RUN_ID,
|
||||
{"U001": LOCATED, "U004": LOCATED},
|
||||
[("U002", 2, "两半都没有绿框")],
|
||||
)
|
||||
result = _build(tmp_path, 4, run)
|
||||
assert [r.case_no for r in read_aliases(result.answers_dir)] == ["001", "004"]
|
||||
assert len(list_aliases(result.library_dir)) == 2
|
||||
skipped = _skipped(result.answers_dir)
|
||||
assert [row[:4] for row in skipped] == [
|
||||
["002", "C15", "CEUS 定量结果齐全", f"{RUN_ID}/failed.csv"],
|
||||
["003", "C15", "CEUS 定量结果齐全", f"{RUN_ID}/U003"],
|
||||
]
|
||||
assert json.loads(skipped[0][5]) == "第 2 步失败：两半都没有绿框"
|
||||
assert "没有这一例的结果目录" in json.loads(skipped[1][5])
|
||||
assert result.skipped_by_check == {"C15": 2}
|
||||
manifest = json.loads((result.library_dir / "manifest.json").read_text(encoding="utf-8"))
|
||||
assert manifest["ceus_source"] == RUN_ID
|
||||
|
||||
|
||||
def test_tic_json_has_exactly_the_listed_fields(tmp_path: Path) -> None:
|
||||
result = _build(tmp_path, 1, write_run(tmp_path / "runs" / RUN_ID, {"U001": LOCATED}, []))
|
||||
(alias,) = list_aliases(result.library_dir)
|
||||
tic = read_ultrasound(result.library_dir, alias).tic
|
||||
perfusion = {
|
||||
**dict.fromkeys(_PERFUSION_KEYS - {"values", "supporting_times_s"}),
|
||||
"values": dict.fromkeys(_PERFUSION_VALUES),
|
||||
"supporting_times_s": dict.fromkeys(("TI", "mTT", "TO")),
|
||||
}
|
||||
slot = {"located": None, "video_time_s": None, "reason": None}
|
||||
curves = ("roi_all", "roi_perf", "roi_pan", "background_circle")
|
||||
assert _key_tree(tic) == {
|
||||
"fits": {name: {"success": None, "r2": None} for name in curves},
|
||||
"perfusion_metrics": {"roi_all": perfusion, "roi_perf": None},
|
||||
"pan_curve_usable": None,
|
||||
"keyframes": {s: slot for s in ("B0", "D1", "D2", "D3", "D4", "F1", "F2")},
|
||||
}
|
||||
assert tic is not None
|
||||
assert tic["fits"]["roi_all"] == {"success": True, "r2": 0.93}
|
||||
assert tic["fits"]["roi_pan"] == {"success": False, "r2": None}
|
||||
assert tic["pan_curve_usable"] is False
|
||||
assert tic["perfusion_metrics"]["roi_all"]["values"]["PE_au"] == 1.0
|
||||
# 假数据里 D1 是第 2 个槽位：视频时间 1 × 2.5 秒。
|
||||
assert tic["keyframes"]["D1"] == {"located": True, "video_time_s": 2.5, "reason": None}
|
||||
assert tic["keyframes"]["D4"] == {
|
||||
"located": False,
|
||||
"video_time_s": None,
|
||||
"reason": UNLOCATED_REASON,
|
||||
}
|
||||
|
||||
|
||||
def test_keyframes_metadata_dropped_and_pixels_kept(tmp_path: Path) -> None:
|
||||
run = write_run(tmp_path / "runs" / RUN_ID, {"U001": LOCATED}, [])
|
||||
result = _build(tmp_path, 1, run)
|
||||
(alias,) = list_aliases(result.library_dir)
|
||||
route = read_ultrasound(result.library_dir, alias)
|
||||
assert sorted(route.keyframes) == sorted(LOCATED)
|
||||
for slot, copied in route.keyframes.items():
|
||||
assert (
|
||||
copied == result.library_dir / "cases" / alias / "ultrasound/keyframes" / f"{slot}.png"
|
||||
)
|
||||
with Image.open(run / "U001" / "keyframes" / f"{slot}.png") as original:
|
||||
assert "Source" in original.info and "exif" in original.info
|
||||
pixels = original.tobytes()
|
||||
with Image.open(copied) as image:
|
||||
assert image.mode == "RGB" and image.tobytes() == pixels
|
||||
assert "Source" not in image.info and "exif" not in image.info
|
||||
assert _png_chunks(copied.read_bytes()) == ["IHDR", "IDAT", "IEND"]
|
||||
|
||||
|
||||
def test_null_ceus_run_has_no_ceus_files(tmp_path: Path) -> None:
|
||||
root = make_delivery(2).write(tmp_path / "delivery")
|
||||
result = run_build(write_config(tmp_path, root, 1, None, None), REPO_ROOT, NOW)
|
||||
for alias in list_aliases(result.library_dir):
|
||||
route = read_ultrasound(result.library_dir, alias)
|
||||
assert route.tic is None and route.keyframes == {}
|
||||
assert sorted(
|
||||
p.name for p in (result.library_dir / "cases" / alias / "ultrasound").iterdir()
|
||||
) == [
|
||||
"key.png",
|
||||
"report.txt",
|
||||
]
|
||||
|
||||
|
||||
def test_scan_finds_nothing_then_hits_video_id_in_tic_json(tmp_path: Path) -> None:
|
||||
run = write_run(tmp_path / "runs" / RUN_ID, {"U001": LOCATED, "U002": LOCATED}, [])
|
||||
result = _build(tmp_path, 2, run)
|
||||
forbidden = ["P001", "P002", "U001", "U002", "U001_roi2.mp4", "U002_roi2.mp4", "U999"]
|
||||
assert scan_for_leaks(result.library_dir, forbidden, ("name",)) == []
|
||||
alias = list_aliases(result.library_dir)[0]
|
||||
tic_path = result.library_dir / "cases" / alias / "ultrasound" / "tic.json"
|
||||
tic = json.loads(tic_path.read_text(encoding="utf-8"))
|
||||
tic["keyframes"]["D4"]["reason"] = "见 U002 第 3 帧"
|
||||
tic_path.write_text(json.dumps(tic, ensure_ascii=False), encoding="utf-8")
|
||||
hits = scan_for_leaks(result.library_dir, forbidden, ("name",))
|
||||
assert [(Path(h.file).name, h.kind, h.term) for h in hits] == [("tic.json", "字符串", "U002")]
|
||||
|
||||
|
||||
def test_reason_with_video_id_stops_build(tmp_path: Path) -> None:
|
||||
run = write_run(tmp_path / "runs" / RUN_ID, {"U001": LOCATED}, [])
|
||||
content = summary("U001", LOCATED)
|
||||
content["anchor_frames"]["D4"]["reason"] = "U001 的 D4 不在视频里"
|
||||
(run / "U001" / "summary.json").write_text(json.dumps(content), encoding="utf-8")
|
||||
with pytest.raises(ValueError, match="视频号或路径"):
|
||||
_build(tmp_path, 1, run)
|
||||
assert not (tmp_path / "library").exists()
|
||||
|
||||
|
||||
def test_keyframe_that_cannot_be_reencoded_skips_case_as_c14(tmp_path: Path) -> None:
|
||||
run = write_run(tmp_path / "runs" / RUN_ID, {"U001": LOCATED, "U002": LOCATED}, [])
|
||||
Image.new("I;16", (4, 4)).save(run / "U002" / "keyframes" / "D2.png", format="PNG")
|
||||
result = _build(tmp_path, 2, run)
|
||||
assert [r.case_no for r in read_aliases(result.answers_dir)] == ["001"]
|
||||
skipped = _skipped(result.answers_dir)
|
||||
assert [row[:4] for row in skipped] == [
|
||||
["002", "C14", "关键图能原样重编码", f"{RUN_ID}/U002/keyframes/D2.png"]
|
||||
]
|
||||
|
||||
|
||||
def _assert_stops(tmp_path: Path, run: Path, error: type[Exception]) -> None:
|
||||
with pytest.raises(error):
|
||||
_build(tmp_path, 1, run)
|
||||
assert not (tmp_path / "library").exists() and not (tmp_path / "answers").exists()
|
||||
|
||||
|
||||
def test_run_dir_missing_stops(tmp_path: Path) -> None:
|
||||
_assert_stops(tmp_path, tmp_path / "runs" / RUN_ID, FileNotFoundError)
|
||||
|
||||
|
||||
def test_partial_run_dir_stops(tmp_path: Path) -> None:
|
||||
run = write_run(tmp_path / "runs" / f"{RUN_ID}.partial", {"U001": LOCATED}, [])
|
||||
_assert_stops(tmp_path, run, ValueError)
|
||||
|
||||
|
||||
def test_run_dir_without_failed_csv_stops(tmp_path: Path) -> None:
|
||||
run = write_run(tmp_path / "runs" / RUN_ID, {"U001": LOCATED}, [])
|
||||
(run / "failed.csv").unlink()
|
||||
_assert_stops(tmp_path, run, FileNotFoundError)
|
||||
|
||||
|
||||
def test_run_dir_without_snapshot_stops(tmp_path: Path) -> None:
|
||||
run = write_run(tmp_path / "runs" / RUN_ID, {"U001": LOCATED}, [])
|
||||
(run / "snapshot" / "snapshot.json").unlink()
|
||||
_assert_stops(tmp_path, run, FileNotFoundError)
|
||||
Reference in New Issue
Block a user