merge main (0.78.1) into tonemap before release

2026-08-30 18:55:14 +02:00
parent b563155a37 1a102ce81a
commit 375f6e58be
8 changed files with 251 additions and 85 deletions
@@ -144,7 +144,7 @@ class TestCodecsFromStreams:


 class TestRunFfprobeJson:
-    """The single ffprobe-JSON invocation point (shared by probe_codecs + upload._probe). A failed
+    """The single ffprobe-JSON invocation point (shared by probe_codecs + probe.probe_media). A failed
    probe or unparseable output must degrade to None, not raise — the malformed-input safety the old
    parse_probe_streams string parser used to own now lives here."""

@@ -7,9 +7,9 @@ guards that keep an upload out of paths that assume a re-fetchable source (edit

 DB-backed (real Postgres) — skipped when no database is reachable. `settings.download_root` is
 pointed at a per-test tmp dir so ingest's on-disk moves are isolated. The ingest/route tests
-monkeypatch `_probe` so they don't shell out to ffprobe; the classifier's OWN parsing (image →
-file, cover-art skip, dims, duration) is covered directly by `TestProbeClassifier` below, which
-stubs one level down (`run_ffprobe_json`) and exercises the real `_probe`.
+monkeypatch the shared `probe.probe_media` so they don't shell out to ffprobe; the classifier's OWN
+parsing (image → file, cover-art skip, dims, duration) is covered directly by `TestProbeClassifier`
+below, which stubs one level down (`run_ffprobe_json`) and exercises the real `probe_media`.
 """

 from pathlib import Path
@@ -18,6 +18,7 @@ import pytest

 from app.config import settings
 from app.downloads import mediakind, quota, storage
+from app.downloads import probe as probemod
 from app.downloads import upload as uploadmod
 from app.models import DownloadQuota, MediaAsset

@@ -42,7 +43,9 @@ def _root(tmp_path, monkeypatch):


 def _probe(monkeypatch, result):
-    monkeypatch.setattr(uploadmod, "_probe", lambda _p: result)
+    # upload ingest now calls the shared `probe.probe_media` (same ground-truth ffprobe the download
+    # worker uses); patch it at that shared home.
+    monkeypatch.setattr(probemod, "probe_media", lambda _p: result)


 def test_ingest_generic_file_is_download_only(db, make_user, _root, monkeypatch):
@@ -325,16 +328,16 @@ def test_ingest_cleans_up_placed_files_on_commit_failure(db, make_user, _root, m
    assert db.query(MediaAsset).count() == 0  # the flushed asset rolled back — no dangling row


-# --- classifier: the REAL _probe parsing (stubs ffprobe one level down) ----------------------
-# The ingest/route tests above stub _probe wholesale; these exercise _probe's OWN logic — image
+# --- classifier: the REAL probe_media parsing (stubs ffprobe one level down) ------------------
+# The ingest/route tests above stub probe_media wholesale; these exercise its OWN logic — image
 # detection, the cover-art skip, dimension/duration parsing — by faking only run_ffprobe_json, so a
 # regression in the classifier the force-download guarantee leans on is actually caught.


 class TestProbeClassifier:
    def _probe_with(self, monkeypatch, data):
-        monkeypatch.setattr(uploadmod.editmod, "run_ffprobe_json", lambda *a, **k: data)
-        return uploadmod._probe(Path("x"))
+        monkeypatch.setattr(probemod.editmod, "run_ffprobe_json", lambda *a, **k: data)
+        return probemod.probe_media(Path("x"))

    def test_probe_failure_is_a_generic_file(self, monkeypatch):
        # run_ffprobe_json returns None (ffprobe failed / not media) → all None → derive() == FILE.
@@ -392,3 +395,109 @@ class TestProbeClassifier:
        }
        v, a, w, h, d = self._probe_with(monkeypatch, data)
        assert d is None and mediakind.derive(v, a) == mediakind.AUDIO
+
+
+# --- resolve_media_facts: probe-of-the-file wins over yt-dlp's info (the FB regression fix) ---------
+# The download worker's finalize must classify from the ACTUAL file, not the extractor's `info` dict.
+# yt-dlp omits vcodec/acodec/dims for some sources (Facebook), and deriving media_kind from those
+# nulls turned a real H.264 video into a download-only 'file' (no in-app play). These pin that the
+# probe is authoritative and `info` is only a gap-filler.
+
+
+class TestResolveMediaFacts:
+    # These stub run_ffprobe_json (one level below probe_media) so the REAL probe parsing + the
+    # probe-vs-info precedence are exercised together — the precedence keys off whether ffprobe RAN.
+    @staticmethod
+    def _ffprobe(monkeypatch, data):
+        monkeypatch.setattr(probemod.editmod, "run_ffprobe_json", lambda *a, **k: data)
+
+    def test_probe_wins_when_info_lacks_codecs(self, monkeypatch):
+        # THE original regression: info has no vcodec/acodec/dims (Facebook), but the file probes as
+        # h264/aac.
+        self._ffprobe(
+            monkeypatch,
+            {
+                "format": {"format_name": "mov,mp4,m4a"},
+                "streams": [
+                    {"codec_type": "video", "codec_name": "h264", "width": 720, "height": 1280},
+                    {"codec_type": "audio", "codec_name": "aac"},
+                ],
+            },
+        )
+        v, a, w, h = probemod.resolve_media_facts(Path("x"), {"width": None, "height": None})
+        assert (v, a, w, h) == ("h264", "aac", 720, 1280)
+        assert mediakind.derive(v, a) == mediakind.VIDEO  # NOT 'file'
+
+    def test_probe_wins_over_a_DIFFERING_populated_info(self, monkeypatch):
+        # Both the probe AND info are populated but DISAGREE (info carries a pre-remux/pre-merge codec).
+        # The finished file on disk is ground truth, so the probe wins outright — pins the precedence a
+        # `info or probe` inversion would silently break.
+        self._ffprobe(
+            monkeypatch,
+            {
+                "format": {"format_name": "mov,mp4,m4a"},
+                "streams": [
+                    {"codec_type": "video", "codec_name": "h264", "width": 1920, "height": 1080},
+                    {"codec_type": "audio", "codec_name": "aac"},
+                ],
+            },
+        )
+        v, a, w, h = probemod.resolve_media_facts(
+            Path("x"), {"vcodec": "vp9", "acodec": "opus", "width": 640, "height": 480}
+        )
+        assert (v, a, w, h) == ("h264", "aac", 1920, 1080)  # probe, not info
+
+    def test_cover_art_audio_download_is_not_resurrected_to_video_by_info(self, monkeypatch):
+        # THE bug this fix targets: an audio-mode download from a progressive source embeds cover art,
+        # and yt-dlp's info still carries the source's video codec. The probe correctly finds only audio
+        # (the attached_pic is skipped); info's vcodec must NOT resurrect a video track → media_kind
+        # stays audio, not a broken in-app 'video'.
+        self._ffprobe(
+            monkeypatch,
+            {
+                "format": {"format_name": "mp3", "duration": "180.0"},
+                "streams": [
+                    {
+                        "codec_type": "video",
+                        "codec_name": "mjpeg",
+                        "disposition": {"attached_pic": 1},
+                    },
+                    {"codec_type": "audio", "codec_name": "mp3"},
+                ],
+            },
+        )
+        v, a, w, h = probemod.resolve_media_facts(
+            Path("x"), {"vcodec": "avc1", "acodec": "mp4a", "width": 1280, "height": 720}
+        )
+        assert v is None and a == "mp3"  # info's avc1 did NOT win
+        assert mediakind.derive(v, a) == mediakind.AUDIO  # NOT VIDEO
+
+    def test_still_image_download_is_not_resurrected_to_video_by_info(self, monkeypatch):
+        # A downloaded still image: the probe returns no vcodec (image-format guard). info's image
+        # "vcodec" must not turn it into a broken 'video' → stays a generic file.
+        self._ffprobe(
+            monkeypatch,
+            {
+                "format": {"format_name": "png_pipe"},
+                "streams": [{"codec_type": "video", "codec_name": "png", "width": 8, "height": 8}],
+            },
+        )
+        v, a, w, h = probemod.resolve_media_facts(
+            Path("x"), {"vcodec": "png", "width": 8, "height": 8}
+        )
+        assert v is None and mediakind.derive(v, a) == mediakind.FILE
+
+    def test_info_fills_in_only_when_ffprobe_could_not_read_the_file(self, monkeypatch):
+        # ffprobe failed entirely (None) → fall back to info so we never regress the working path.
+        self._ffprobe(monkeypatch, None)
+        v, a, w, h = probemod.resolve_media_facts(
+            Path("x"), {"vcodec": "vp9", "acodec": "opus", "width": 1920, "height": 1080}
+        )
+        assert (v, a, w, h) == ("vp9", "opus", 1920, 1080)
+
+    def test_info_none_codec_string_is_treated_as_absent(self, monkeypatch):
+        # yt-dlp writes the literal "none" for a missing stream — it must not become a codec name.
+        self._ffprobe(monkeypatch, None)  # probe failed → info path, where the "none" scrub applies
+        v, a, w, h = probemod.resolve_media_facts(Path("x"), {"vcodec": "none", "acodec": "aac"})
+        assert (v, a) == (None, "aac")
+        assert mediakind.derive(v, a) == mediakind.AUDIO