minimateplus/blastware_file.py

@@ -151,6 +151,7 @@ MLG CRC:
 from __future__ import annotations
 
 import datetime
+import logging
 import struct
 from pathlib import Path
 from typing import Optional, Union
@@ -158,6 +159,8 @@ from typing import Optional, Union
 from .framing import S3Frame
 from .models import Event, MonitorLogEntry, Timestamp
 
+log = logging.getLogger(__name__)
+
 # ── File header constants ─────────────────────────────────────────────────────
 
 # Common 16-byte prefix shared by waveform files and MLG (confirmed from binary inspection).
@@ -502,6 +505,51 @@ def blastware_filename(event: Event, serial: str, ach: bool = False) -> str:
     return prefix + stem + ext
 
 
+# ── A5 frame classifier ───────────────────────────────────────────────────────────
+
+# ASCII markers that identify a compliance-config / metadata frame.
+# These strings appear in the A5 bulk stream as part of the device's
+# compliance setup payload.  They should NEVER appear in raw ADC waveform
+# frames (which are binary-heavy, < 20 % printable ASCII).
+_METADATA_FRAME_MARKERS = (
+    b"Project:",
+    b"Client:",
+    b"Standard Recording Setup",
+    b"Extended Notes",
+    b"User Name:",
+    b"Seis Loc:",
+)
+
+
+def classify_frame(frame: S3Frame) -> str:
+    """
+    Classify an A5 bulk waveform stream frame by its content.
+
+    Returns one of:
+        "terminator"    — page_key == 0x0000
+        "probe_or_strt" — data contains b"STRT" (the initial probe response)
+        "metadata"      — data contains ASCII compliance-config markers
+        "waveform"      — predominantly binary (< 20 % printable ASCII)
+        "unknown"       — none of the above criteria matched
+
+    Used by write_blastware_file() to filter non-waveform frames out of
+    the reconstructed body so that metadata blocks (Project:, Client:, …)
+    and spurious STRT records do not corrupt the output file.
+    """
+    if frame.page_key == 0x0000:
+        return "terminator"
+    data = bytes(frame.data)
+    if b"STRT" in data:
+        return "probe_or_strt"
+    if any(m in data for m in _METADATA_FRAME_MARKERS):
+        return "metadata"
+    if len(data) > 0:
+        printable = sum(1 for b in data if 32 <= b < 127)
+        if printable / len(data) < 0.20:
+            return "waveform"
+    return "unknown"
+
+
 # ── Waveform file writer ───────────────────────────────────────────────────────────
 
 def write_blastware_file(
@@ -631,12 +679,29 @@ def write_blastware_file(
     all_bytes = bytearray()
 
     for fi, frame in enumerate(body_frames):
+        ftype = classify_frame(frame)
+        print(f"Frame {fi}: type={ftype}, page_key={frame.page_key:04x}, len={len(frame.data)}")
+
         if fi == 0:
+            # Probe frame: always process regardless of classification.
+            # It holds the STRT record; probe_skip positions us past it.
             skip = probe_skip
-        elif fi == 1:
+        elif ftype == "waveform":
-            skip = 13   # 7-byte frame.data prefix + 6-byte first-chunk header
+            skip = 13 if fi == 1 else 12
         else:
-            skip = 12   # 7-byte frame.data prefix + 5-byte chunk header
+            # Skip metadata, probe_or_strt, and unknown frames.
+            if b"STRT" in bytes(frame.data):
+                log.warning(
+                    "write_blastware_file: frame %d (%s) contains STRT — skipping",
+                    fi, ftype,
+                )
+            else:
+                log.debug(
+                    "write_blastware_file: frame %d classified as %s — skipping",
+                    fi, ftype,
+                )
+            continue
+
         all_bytes.extend(_frame_body_bytes(frame, skip))
 
     # Terminator contributes its content, which ends with the 26-byte footer.