1 files changed, 70 insertions, 0 deletions
diff --git a/packages/meshbay-node/src/meshbay_node/media_probe.py b/packages/meshbay-node/src/meshbay_node/media_probe.py
new file mode 100644
index 0000000..8ad883d
--- /dev/null
+++ b/packages/meshbay-node/src/meshbay_node/media_probe.py
@@ -0,0 +1,70 @@
+"""
+ffprobe wrapper shared by stream-time codec detection (transport/webrtc_server.py)
+and index-time technical-field enrichment (indexer/enrich.py).
+
+Split out of webrtc_server.py so the indexer package (which webrtc_server.py
+already imports from) can call it too without a circular import.
+"""
+
+import asyncio
+import json
+
+_H264_PROFILES = {"Baseline": "42", "Main": "4d", "High": "64", "High 10": "6e"}
+
+
+async def probe_video(path: str) -> tuple[str | None, float, bool, int | None, int | None]:
+    """
+    Probe video file with ffprobe, return (MSE codec string, duration,
+    has_audio, width, height).
+
+    The audio half of the codec string is always "mp4a.40.2" (AAC-LC) or
+    absent — never the source's real audio codec — because the streaming
+    path always transcodes audio to AAC and never copies it: MSE in every
+    mainstream browser only decodes AAC/Opus, and a source codec outside
+    that (AC-3, E-AC-3, DTS, ...) is at best silently unplayable and at
+    worst, for E-AC-3 at least, makes ffmpeg itself refuse to write the
+    fragmented MP4 header ("Cannot write moov atom before EAC3 packets
+    parsed" — reproduced against a real 5.1 E-AC-3 WEB-DL). Video stays
+    whatever it actually is: it is always copied, never transcoded.
+
+    width/height come from the same ffprobe call (one extra `-show_entries`
+    field, no second process spawn) — resolution is deliberately never
+    guessed from the filename (docs/mediacenter.md §3.5).
+    """
+    proc = await asyncio.create_subprocess_exec(
+        "ffprobe", "-v", "error",
+        "-show_entries", "stream=codec_name,profile,level,codec_type,width,height",
+        "-show_entries", "format=duration",
+        "-of", "json", path,
+        stdout=asyncio.subprocess.PIPE, stderr=asyncio.subprocess.PIPE,
+    )
+    stdout, _ = await proc.communicate()
+    info = json.loads(stdout)
+    duration = float(info.get("format", {}).get("duration", 0))
+
+    v_codec = ""
+    has_audio = False
+    width: int | None = None
+    height: int | None = None
+    for s in info.get("streams", []):
+        if s.get("codec_type") == "video" and not v_codec:
+            cn = s.get("codec_name", "")
+            if cn == "h264":
+                p = _H264_PROFILES.get(s.get("profile", "High"), "64")
+                lvl = int(s.get("level", 40))
+                v_codec = f"avc1.{p}00{lvl:02x}"
+            elif cn == "hevc":
+                v_codec = "hev1.1.6.L93.B0"
+            elif cn == "vp9":
+                v_codec = "vp09.00.10.08"
+            elif cn == "av1":
+                v_codec = "av01.0.01M.08"
+            width = s.get("width")
+            height = s.get("height")
+        elif s.get("codec_type") == "audio":
+            has_audio = True
+
+    if not v_codec:
+        return None, duration, has_audio, width, height
+    codec = f"{v_codec},mp4a.40.2" if has_audio else v_codec
+    return codec, duration, has_audio, width, height