feat(ingest): compute shape from the written .h5 in all save paths

sfm/waveform_store.py

@@ -41,6 +41,7 @@ from minimateplus.blastware_file import blastware_filename, write_blastware_file
 from minimateplus.framing import S3Frame
 from minimateplus.models import Event
 from sfm import event_hdf5
+from sfm.shape_metrics import shape_from_h5
 
 log = logging.getLogger("sfm.waveform_store")
 
@@ -262,6 +263,13 @@ class WaveformStore:
             serial, filename, filesize, len(a5_frames),
             hdf5_filename or "(skipped)", sidecar_path.name,
         )
+        _shape = shape_from_h5(hdf5_path) if hdf5_filename else None
+        _shape_rec = {
+            "shape_crest_factor":    _shape["crest_factor"],
+            "shape_near_peak_count": _shape["near_peak_count"],
+            "shape_sample_count":    _shape["sample_count"],
+            "shape_axis":            _shape["axis"],
+        } if _shape else {}
         return {
             "filename":            filename,
             "filesize":            filesize,
@@ -269,6 +277,7 @@ class WaveformStore:
             "a5_pickle_filename":  a5_path.name,
             "hdf5_filename":       hdf5_filename,
             "sidecar_filename":    sidecar_path.name,
+            **_shape_rec,
         }
 
     def save_imported_bw(
@@ -445,6 +454,13 @@ class WaveformStore:
             "h5=%s (no .a5.pkl — A5 source unavailable for BW-imported files)",
             serial, filename, filesize, hdf5_filename or "(skipped)",
         )
+        _shape = shape_from_h5(hdf5_path) if hdf5_filename else None
+        _shape_rec = {
+            "shape_crest_factor":    _shape["crest_factor"],
+            "shape_near_peak_count": _shape["near_peak_count"],
+            "shape_sample_count":    _shape["sample_count"],
+            "shape_axis":            _shape["axis"],
+        } if _shape else {}
         return ev, {
             "filename":           filename,
             "filesize":           filesize,
@@ -453,6 +469,7 @@ class WaveformStore:
             "hdf5_filename":      hdf5_filename,
             "sidecar_filename":   sidecar_path.name,
             "serial":             serial,
+            **_shape_rec,
         }
 
     def save_imported_idf(
@@ -727,6 +744,13 @@ class WaveformStore:
             hdf5_filename or "(skipped)",
             len(idf_intervals) if idf_intervals else 0,
         )
+        _shape = shape_from_h5(hdf5_path) if hdf5_filename else None
+        _shape_rec = {
+            "shape_crest_factor":    _shape["crest_factor"],
+            "shape_near_peak_count": _shape["near_peak_count"],
+            "shape_sample_count":    _shape["sample_count"],
+            "shape_axis":            _shape["axis"],
+        } if _shape else {}
         return ev, {
             "filename":           filename,
             "filesize":           filesize,
@@ -735,6 +759,7 @@ class WaveformStore:
             "hdf5_filename":      hdf5_filename,
             "sidecar_filename":   sidecar_path.name,
             "serial":             serial,
+            **_shape_rec,
         }
 
     def load_a5(self, serial: str, filename: str) -> Optional[list[S3Frame]]:

tests/test_save_shape.py

@@ -0,0 +1,13 @@
+from pathlib import Path
+
+from sfm.waveform_store import WaveformStore
+
+_FIX = Path(__file__).parent / "fixtures/histogram-extension-re/events-5-21-26/K558LL8B.7I0W"
+
+
+def test_save_imported_bw_attaches_shape(tmp_path):
+    store = WaveformStore(tmp_path / "waveforms")
+    ev, rec = store.save_imported_bw(_FIX.read_bytes(), source_path=_FIX, serial_hint="BE9558")
+    assert rec.get("shape_axis") in ("Tran", "Vert", "Long")
+    assert rec["shape_crest_factor"] > 0
+    assert rec["shape_sample_count"] > 200