CHANGELOG.md

@@ -8,6 +8,8 @@ All notable changes to seismo-relay are documented here.
 
 ### Added
 
+- **Raw BW ASCII report (.TXT) preservation.**  `save_imported_bw` now writes the paired `_ASCII.TXT` to `<store>/<serial>/<filename>_ASCII.TXT` alongside the binary at ingest time.  Previously the .TXT was parsed into the sidecar's `bw_report` projection and then discarded — meaning parser bug fixes couldn't be applied retroactively without re-forwarding from the watcher PC.  Now the raw .TXT lives in the waveform store permanently (~15 KB per event; ~210 MB total for a 14k-event store; negligible).  Sidecar's `source.txt_filename` field records the saved path; backfill_sidecars preserves it across regens.  New `GET /db/events/{id}/ascii_report.txt` endpoint serves the raw .TXT for any event ingested after this change.  Events ingested before today still return 404 from that endpoint until re-forwarded.  Architectural rationale: with BW Mail / Forwarding Agent being phased out of the operator workflow, the XML/PDF/WMF that those tools produced are no longer available — the binary + .TXT (created by BW ACH itself) are our authoritative source for everything going forward.
+
 - **Event Report PDF generation** — `GET /db/events/{id}/report.pdf` returns a single-page letter-portrait PDF for any event with waveform data on disk.  Covers every field a Blastware Event Report includes: header metadata (date/time, trigger source, range, sample rate, project/client/operator/location, serial+firmware, battery, calibration, file name), microphone block (PSPL in dB(L) + psi, ZC freq, channel test), per-channel stats table (rows differ for waveform vs histogram), Peak Vector Sum, and the 4-channel plot.  Iterated against real Blastware reference PDFs (uploaded to `example-events/pdfsnstuff/`):
    - **Waveform layout**: header shows Date/Time, Trigger Source, Range, Sample Rate; stats table has PPV / ZC Freq / Time (Rel. to Trig) / Peak Accel / Peak Disp / Sensor Check; bottom plot is 4-channel line waveform (MicL top → Tran bottom), shared time axis in seconds, dashed trigger line + triangle marker at t=0, symmetric Y on geo channels, zero-anchored on mic, "0.0" baseline label on right per BW convention; footer shows `Time X sec/div   Amplitude Geo: Y in/s/div   Mic: 0.001 psi(L)/div` and the trigger window `▶━━◀` marker.  USBM RI8507/OSMRE compliance chart placeholder upper-right.
    - **Histogram layout**: header shows Start / Finish / Intervals At Size / Range / Sample Rate (no Trigger Source — histograms aren't triggered); NO USBM chart; stats table has PPV / ZC Freq / Date / Time / Sensor Check; bottom plot is per-interval bar chart, Y-axis 0-to-peak (never negative), 0.0 baseline at the bottom; footer shows `Time INTERVAL_SIZE /div   Amplitude Geo: Y in/s/div   Mic: 0.001 psi(L)/div`.

minimateplus/event_file_io.py

@@ -332,6 +332,7 @@ def event_to_sidecar_dict(
     blastware_filesize: int,
     blastware_sha256: str,
     source_kind: str = "sfm-live",
+    txt_filename: Optional[str] = None,
     a5_pickle_filename: Optional[str] = None,
     tool_version: str = _TOOL_VERSION_DEFAULT,
     captured_at: Optional[datetime.datetime] = None,
@@ -448,6 +449,7 @@ def event_to_sidecar_dict(
             "captured_at":        captured_at.isoformat() + "Z" if captured_at.tzinfo is None else captured_at.isoformat(),
             "tool_version":       tool_version,
             "a5_pickle_filename": a5_pickle_filename,
+            "txt_filename":       txt_filename,
         },
 
         "review": review or {

scripts/backfill_sidecars.py

@@ -300,12 +300,17 @@ def main(argv=None) -> int:
                 preserved_review     = None
                 preserved_ext        = None
                 preserved_bw_report  = None
+                preserved_txt_fn     = None
                 if sidecar_path.exists():
                     try:
                         _existing = event_file_io.read_sidecar(sidecar_path)
                         preserved_review    = _existing.get("review")
                         preserved_ext       = _existing.get("extensions")
                         preserved_bw_report = _existing.get("bw_report")
+                        # Preserve txt_filename so backfills don't blank out the
+                        # pointer to the saved raw .TXT (events ingested after
+                        # 2026-05-27 have this).
+                        preserved_txt_fn    = (_existing.get("source") or {}).get("txt_filename")
                     except Exception:
                         pass
 
@@ -334,6 +339,7 @@ def main(argv=None) -> int:
                     blastware_sha256=bw_sha,
                     source_kind=source_kind,
                     a5_pickle_filename=a5_filename,
+                    txt_filename=preserved_txt_fn,
                     review=preserved_review,
                     extensions=preserved_ext,
                 )

sfm/server.py

@@ -2178,6 +2178,39 @@ def db_event_blastware_file(event_id: str) -> FileResponse:
     )
 
 
+@app.get("/db/events/{event_id}/ascii_report.txt")
+def db_event_ascii_report_txt(event_id: str):
+    """Serve the raw BW ASCII report (.TXT) for an event, when preserved.
+
+    Returns 404 for events ingested before the .TXT-preservation feature
+    landed (2026-05-27) — those events have only the parsed ``bw_report``
+    block in the sidecar, not the raw .TXT.  Re-forwarding from the
+    watcher PC will populate the .TXT going forward.
+    """
+    row = _get_db().get_event(event_id)
+    if row is None:
+        raise HTTPException(status_code=404, detail=f"Event {event_id} not found")
+    serial   = row.get("serial")
+    filename = row.get("blastware_filename")
+    if not serial or not filename:
+        raise HTTPException(status_code=404, detail="Event has no associated BW file")
+    txt_path = _get_store().open_txt(serial, filename)
+    if txt_path is None:
+        raise HTTPException(
+            status_code=404,
+            detail=(
+                f"Raw .TXT not preserved for {filename}.  Events ingested "
+                "before 2026-05-27 don't have it; re-forward from the "
+                "watcher PC to populate."
+            ),
+        )
+    return FileResponse(
+        path=str(txt_path),
+        media_type="text/plain",
+        filename=txt_path.name,
+    )
+
+
 @app.get("/db/events/{event_id}/report.pdf")
 def db_event_report_pdf(event_id: str):
     """Render an Instantel-style Event Report as a PDF.

sfm/waveform_store.py

@@ -108,11 +108,30 @@ class WaveformStore:
         """Return absolute path to the .h5 clean-waveform file for a given event."""
         return self._serial_dir(serial) / f"{filename}.h5"
 
+    def txt_path_for(self, serial: str, filename: str) -> Path:
+        """Return absolute path to the preserved BW ASCII report (.TXT)
+        for a given event.
+
+        We name it ``<filename>_ASCII.TXT`` to match BW's own filename
+        convention in the ACH folder.  Saved at ingest time alongside
+        the binary so the parser bug fixes can be applied retroactively
+        by re-parsing without needing to re-forward from the watcher PC.
+        """
+        return self._serial_dir(serial) / f"{filename}_ASCII.TXT"
+
     def open_blastware(self, serial: str, filename: str) -> Optional[Path]:
         """Return absolute path to an existing event file or None."""
         bw_path, _ = self.paths_for(serial, filename)
         return bw_path if bw_path.exists() else None
 
+    def open_txt(self, serial: str, filename: str) -> Optional[Path]:
+        """Return absolute path to the preserved BW ASCII report for an
+        event, or None if the .TXT wasn't saved at ingest time (events
+        ingested before .TXT preservation landed will show None until
+        re-forwarded)."""
+        p = self.txt_path_for(serial, filename)
+        return p if p.exists() else None
+
     # ── save / load ─────────────────────────────────────────────────────────────
 
     def save(
@@ -357,6 +376,28 @@ class WaveformStore:
         filesize = bw_path.stat().st_size
         sha256   = event_file_io.file_sha256(bw_path)
 
+        # 1b. preserve the raw BW ASCII report (.TXT) alongside the binary.
+        # Saved at <root>/<serial>/<filename>_ASCII.TXT.  Lets us re-parse
+        # offline after parser fixes without needing to re-forward from
+        # the watcher PC.  Negligible storage cost (~15 KB per event).
+        # Skipped silently when no report was supplied (live download path,
+        # manual upload without paired TXT).
+        txt_filename: Optional[str] = None
+        if bw_report_text is not None:
+            try:
+                txt_path = self.txt_path_for(serial, filename)
+                if isinstance(bw_report_text, bytes):
+                    txt_path.write_bytes(bw_report_text)
+                else:
+                    txt_path.write_text(bw_report_text)
+                txt_filename = txt_path.name
+            except Exception as exc:
+                log.warning(
+                    "save_imported_bw: failed to save TXT for %s: %s — "
+                    "continuing without it",
+                    filename, exc,
+                )
+
         # 2. write the .h5 clean-waveform file from the parsed Event.
         # Note: peaks here are computed from raw samples (the BW file
         # doesn't carry the device-authoritative 0C peaks).  Best-effort.
@@ -393,6 +434,7 @@ class WaveformStore:
             blastware_sha256=sha256,
             source_kind="bw-import",
             a5_pickle_filename=None,
+            txt_filename=txt_filename,
             review=existing_review,
             bw_report=bw_report,
         )