audio-key: truncate at 5min + mojibake support

bin/mtag/audio-bpm.py

@@ -59,8 +59,6 @@ def main():
 
     try:
         det(tf)
-    except:
-        pass
     finally:
         os.unlink(tf)
 

bin/mtag/audio-key-slicing.py

@@ -0,0 +1,123 @@
+#!/usr/bin/env python
+
+import re
+import os
+import sys
+import tempfile
+import subprocess as sp
+
+import keyfinder
+
+from copyparty.util import fsenc
+
+"""
+dep: github/mixxxdj/libkeyfinder
+dep: pypi/keyfinder
+dep: ffmpeg
+
+note: this is a janky edition of the regular audio-key.py,
+  slicing the files at 20sec intervals and keeping 5sec from each,
+  surprisingly accurate but still garbage (446 ok, 69 bad, 13% miss)
+
+  it is fast tho
+"""
+
+
+def get_duration():
+    # TODO provide ffprobe tags to mtp as json
+
+    # fmt: off
+    dur = sp.check_output([
+        "ffprobe",
+        "-hide_banner",
+        "-v", "fatal",
+        "-show_streams",
+        "-show_format",
+        fsenc(sys.argv[1])
+    ])
+    # fmt: on
+
+    dur = dur.decode("ascii", "replace").split("\n")
+    dur = [x.split("=")[1] for x in dur if x.startswith("duration=")]
+    dur = [float(x) for x in dur if re.match(r"^[0-9\.,]+$", x)]
+    return list(sorted(dur))[-1] if dur else None
+
+
+def get_segs(dur):
+    # keep first 5s of each 20s,
+    # keep entire last segment
+    ofs = 0
+    segs = []
+    while True:
+        seg = [ofs, 5]
+        segs.append(seg)
+        if dur - ofs < 20:
+            seg[-1] = int(dur - seg[0])
+            break
+
+        ofs += 20
+
+    return segs
+
+
+def slice(tf):
+    dur = get_duration()
+    dur = min(dur, 600)  # max 10min
+    segs = get_segs(dur)
+
+    # fmt: off
+    cmd = [
+        "ffmpeg",
+        "-nostdin",
+        "-hide_banner",
+        "-v", "fatal",
+        "-y"
+    ]
+
+    for seg in segs:
+        cmd.extend([
+            "-ss", str(seg[0]),
+            "-i", fsenc(sys.argv[1])
+        ])
+    
+    filt = ""
+    for n, seg in enumerate(segs):
+        filt += "[{}:a:0]atrim=duration={}[a{}]; ".format(n, seg[1], n)
+    
+    prev = "a0"
+    for n in range(1, len(segs)):
+        nxt = "b{}".format(n)
+        filt += "[{}][a{}]acrossfade=d=0.5[{}]; ".format(prev, n, nxt)
+        prev = nxt
+
+    cmd.extend([
+        "-filter_complex", filt[:-2],
+        "-map", "[{}]".format(nxt),
+        "-sample_fmt", "s16",
+        tf
+    ])
+    # fmt: on
+
+    # print(cmd)
+    sp.check_call(cmd)
+
+
+def det(tf):
+    slice(tf)
+    print(keyfinder.key(tf).camelot())
+
+
+def main():
+    with tempfile.NamedTemporaryFile(suffix=".flac", delete=False) as f:
+        f.write(b"h")
+        tf = f.name
+
+    try:
+        det(tf)
+    finally:
+        os.unlink(tf)
+        pass
+
+
+if __name__ == "__main__":
+    main()

bin/mtag/audio-key.py

@@ -1,18 +1,52 @@
 #!/usr/bin/env python
 
+import os
 import sys
+import tempfile
+import subprocess as sp
 import keyfinder
 
+from copyparty.util import fsenc
+
 """
 dep: github/mixxxdj/libkeyfinder
 dep: pypi/keyfinder
 dep: ffmpeg
-
-note: cannot fsenc
 """
 
 
-try:
-    print(keyfinder.key(sys.argv[1]).camelot())
-except:
-    pass
+# tried trimming the first/last 5th, bad idea,
+# misdetects 9a law field (Sphere Caliber) as 10b,
+# obvious when mixing 9a ghostly parapara ship
+
+
+def det(tf):
+    # fmt: off
+    sp.check_call([
+        "ffmpeg",
+        "-nostdin",
+        "-hide_banner",
+        "-v", "fatal",
+        "-y", "-i", fsenc(sys.argv[1]),
+        "-t", "300",
+        "-sample_fmt", "s16",
+        tf
+    ])
+    # fmt: on
+
+    print(keyfinder.key(tf).camelot())
+
+
+def main():
+    with tempfile.NamedTemporaryFile(suffix=".flac", delete=False) as f:
+        f.write(b"h")
+        tf = f.name
+
+    try:
+        det(tf)
+    finally:
+        os.unlink(tf)
+
+
+if __name__ == "__main__":
+    main()

docs/notes.sh

@@ -106,6 +106,12 @@ find -iname up2k.db | while IFS= read -r x; do sqlite3 "$x" 'select substr(w,1,1
 # unschedule mtp scan for all files somewhere under "enc/"
 sqlite3 -readonly up2k.db 'select substr(up.w,1,16) from up inner join mt on mt.w = substr(up.w,1,16) where rd like "enc/%" and +mt.k = "t:mtp"' > keys; awk '{printf "delete from mt where w = \"%s\" and +k = \"t:mtp\";\n", $0}' <keys | tee /dev/stderr | sqlite3 up2k.db
 
+# compare metadata key "key" between two databases
+sqlite3 -readonly up2k.db.key-full 'select w, v from mt where k = "key" order by w' > k1; sqlite3 -readonly up2k.db 'select w, v from mt where k = "key" order by w' > k2; ok=0; ng=0; while IFS='|' read w k2; do k1="$(grep -E "^$w" k1 | sed -r 's/.*\|//')"; [ "$k1" = "$k2" ] && ok=$((ok+1)) || { ng=$((ng+1)); printf '%3s %3s  %s\n' "$k1" "$k2" "$(sqlite3 -readonly up2k.db.key-full "select * from up where substr(w,1,16) = '$w'" | sed -r 's/\|/ | /g')"; }; done < <(cat k2); echo "match $ok   diff $ng"
+
+# actually this is much better
+sqlite3 -readonly up2k.db.key-full 'select w, v from mt where k = "key" order by w' > k1; sqlite3 -readonly up2k.db 'select mt.w, mt.v, up.rd, up.fn from mt inner join up on mt.w = substr(up.w,1,16) where mt.k = "key" order by up.rd, up.fn' > k2; ok=0; ng=0; while IFS='|' read w k2 path; do k1="$(grep -E "^$w" k1 | sed -r 's/.*\|//')"; [ "$k1" = "$k2" ] && ok=$((ok+1)) || { ng=$((ng+1)); printf '%3s %3s  %s\n' "$k1" "$k2" "$path"; }; done < <(cat k2); echo "match $ok   diff $ng"
+
 
 ##
 ## media