live-photo-concat/set_mtime_from_metadata.py

#!/usr/bin/env python3
"""Set a media file's filesystem modification time to match its embedded
creation-time metadata.

Some tools (e.g. Synology Photos, for videos) sort/date by filesystem mtime
instead of parsing embedded metadata, so a file with correct metadata but a
wrong mtime (common after copying, downloading, exporting, or a bad backup
restore) can show up filed under the wrong date. This resets mtime (and
atime) to match the file's own embedded creation time.

Handles, in priority order per format:
    .mov/.mp4/.m4v  -- ffprobe container tags: com.apple.quicktime.creationdate
                        (local time, explicit UTC offset -- preferred when
                        present) or creation_time (usually UTC, generic
                        encoder tag). Falls back to exiftool's CreateDate /
                        MediaCreateDate (QuickTime atoms, UTC per spec) if
                        ffprobe finds neither -- some non-Apple encoders only
                        populate those.
    .avi            -- exiftool's RIFF DateTimeOriginal (IDIT chunk). This is
                        the camera's own local wall-clock time with no
                        timezone info, unlike the QuickTime tags above.
    .jpg/.jpeg/.png/.tif/.tiff/.heic/.heif/.arw/.cr2/.dng/.raw
                    -- exiftool's EXIF DateTimeOriginal (the .arw/.cr2/.dng/
                       .raw camera-raw formats carry standard EXIF too).
                       Also local wall-clock time with no timezone info.

Values with no timezone offset (AVI, EXIF, and ffprobe's bare creation_time
fallback path is UTC-aware so it's unaffected) are interpreted using this
machine's system timezone, DST included -- same as GNU `touch -d` or Python's
datetime.timestamp() on a naive datetime. If you're running this somewhere
other than the timezone the footage was actually shot in, the result will be
wrong; there is no metadata to disambiguate that.

Placeholder/unset timestamps some cameras write when their clock was never
set (e.g. the literal "0000:00:00 00:00:00", or years before MIN_YEAR) are
treated as "no metadata found", not a real timestamp.

Usage:
    ./set_mtime_from_metadata.py video1.mov photo1.jpg ...
    ./set_mtime_from_metadata.py --dry-run *.mov
    ./set_mtime_from_metadata.py --dir /path/to/library          # recursive, prompts before applying
    ./set_mtime_from_metadata.py --dir /path/to/library --yes    # recursive, unattended
    ./set_mtime_from_metadata.py --dir /path/to/library --only-photo --dry-run
    ./set_mtime_from_metadata.py --dir /path/to/library --only-video --yes

Requirements:
    - ffprobe on PATH (for .mov/.mp4/.m4v)
    - exiftool on PATH (for .avi and photo formats, and as an mp4/mov fallback)
"""
import argparse
import os
import subprocess
import sys
from datetime import datetime
from pathlib import Path

# Preference order: the Apple tag is local time (matches what Photos/Finder
# display); the generic tag is whatever the encoder wrote, usually UTC.
QUICKTIME_TAG_PRIORITY = ["com.apple.quicktime.creationdate", "creation_time"]

QUICKTIME_EXTS = {".mov", ".mp4", ".m4v"}
AVI_EXTS = {".avi"}
VIDEO_EXTS = QUICKTIME_EXTS | AVI_EXTS
EXIF_PHOTO_EXTS = {
    ".jpg", ".jpeg", ".png", ".tif", ".tiff", ".heic", ".heif",
    ".arw", ".cr2", ".dng", ".raw",  # camera raw formats -- standard EXIF via exiftool
}
ALL_SUPPORTED_EXTS = VIDEO_EXTS | EXIF_PHOTO_EXTS

# Synology (and other NAS/sync tool) internal housekeeping directories that
# only ever contain generated thumbnails/cache, never real source media --
# pruned from --dir's recursive walk so they don't show up as noisy skips.
SKIP_DIR_NAMES = {"@eaDir", "#recycle", "#snapshot", ".SynologyWorkingDirectory"}

# Reject anything dated before this as a clock-never-set placeholder rather
# than a real timestamp (observed in the wild: "0000:00:00 00:00:00").
MIN_YEAR = 1990


def parse_quicktime_timestamp(raw):
    raw = raw.strip().replace("Z", "+0000")
    for fmt in ("%Y-%m-%dT%H:%M:%S%z", "%Y-%m-%dT%H:%M:%S.%f%z"):
        try:
            dt = datetime.strptime(raw, fmt)
            return dt if dt.year >= MIN_YEAR else None
        except ValueError:
            continue
    return None


def fetch_via_ffprobe(path):
    """QuickTime container tags via ffprobe, container-level first then the
    first video stream's tags. Returns a tz-aware datetime, or None."""
    tag_list = ",".join(QUICKTIME_TAG_PRIORITY)
    for scope, extra_args in (("format_tags", []), ("stream_tags", ["-select_streams", "v:0"])):
        try:
            out = subprocess.run(
                ["ffprobe", "-v", "error", *extra_args,
                 "-show_entries", f"{scope}={tag_list}",
                 "-of", "default=noprint_wrappers=1:nokey=0", str(path)],
                check=True, capture_output=True, text=True,
            ).stdout
        except subprocess.CalledProcessError as e:
            raise RuntimeError(e.stderr.strip() or str(e)) from e
        tags = dict(line.split("=", 1) for line in out.strip().splitlines() if "=" in line)
        for tag in QUICKTIME_TAG_PRIORITY:
            raw = tags.get(f"TAG:{tag}")
            if raw:
                dt = parse_quicktime_timestamp(raw)
                if dt:
                    return dt
    return None


def fetch_via_exiftool(path, tags, assume_utc=False):
    """First non-empty value among `tags` (in order) via exiftool, as
    printed with -d for a stable "%Y:%m:%d %H:%M:%S" format. Returns a
    datetime (tz-aware UTC if assume_utc, else naive/local), or None."""
    try:
        out = subprocess.run(
            ["exiftool", "-s3", "-d", "%Y:%m:%d %H:%M:%S", *[f"-{t}" for t in tags], str(path)],
            check=True, capture_output=True, text=True,
        ).stdout
    except subprocess.CalledProcessError as e:
        raise RuntimeError(e.stderr.strip() or str(e)) from e
    except FileNotFoundError as e:
        raise RuntimeError("exiftool not found on PATH") from e
    for line in out.splitlines():
        raw = line.strip()
        if not raw:
            continue
        try:
            dt = datetime.strptime(raw, "%Y:%m:%d %H:%M:%S")
        except ValueError:
            continue
        if dt.year < MIN_YEAR:
            continue
        if assume_utc:
            from datetime import timezone
            dt = dt.replace(tzinfo=timezone.utc)
        return dt
    return None


def fetch_creation_time(path):
    """Best-effort embedded creation time for a media file, dispatched by
    extension. Returns a datetime (naive = interpret as this machine's
    local time; aware = absolute, tz conversion handled automatically by
    .timestamp()), or None if nothing usable was found."""
    ext = path.suffix.lower()

    if ext in QUICKTIME_EXTS:
        dt = fetch_via_ffprobe(path)
        if dt:
            return dt
        # Fallback: some non-Apple encoders don't populate either ffprobe
        # tag but do have exiftool-readable QuickTime atoms. These are UTC
        # per the QuickTime spec.
        return fetch_via_exiftool(path, ["MediaCreateDate", "CreateDate"], assume_utc=True)

    if ext in AVI_EXTS:
        return fetch_via_exiftool(path, ["DateTimeOriginal"])

    if ext in EXIF_PHOTO_EXTS:
        return fetch_via_exiftool(path, ["DateTimeOriginal", "CreateDate"])

    return None


def iter_batch_files(root, allowed_exts):
    for dirpath, dirnames, filenames in os.walk(root):
        dirnames[:] = [d for d in dirnames if d not in SKIP_DIR_NAMES]
        for name in filenames:
            if Path(name).suffix.lower() in allowed_exts:
                yield Path(dirpath) / name


def plan_for(path):
    """Returns (path, datetime, error_message). Exactly one of
    (datetime, error_message) is set."""
    if not path.is_file():
        return path, None, "not found"
    try:
        dt = fetch_creation_time(path)
    except RuntimeError as e:
        return path, None, f"metadata read failed ({e})"
    if dt is None:
        return path, None, "no creation-time metadata found"
    return path, dt, None


def main():
    parser = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
    parser.add_argument("files", nargs="*", type=Path, help="Media files to fix")
    parser.add_argument("--dir", type=Path, help="Recursively scan this directory for supported files instead of (or in addition to) explicit FILES")
    type_group = parser.add_mutually_exclusive_group()
    type_group.add_argument("--only-photo", action="store_true", help="Only consider photo formats (jpg/jpeg/png/tif/tiff/heic/heif/arw/cr2/dng/raw)")
    type_group.add_argument("--only-video", action="store_true", help="Only consider video formats (mov/mp4/m4v/avi)")
    parser.add_argument("--dry-run", action="store_true", help="Show what would change without modifying anything or prompting")
    parser.add_argument("--yes", "-y", "--unattended", dest="yes", action="store_true", help="Apply changes without an interactive confirmation prompt")
    args = parser.parse_args()

    if not args.files and not args.dir:
        parser.error("no files given -- pass FILES and/or --dir")

    allowed_exts = EXIF_PHOTO_EXTS if args.only_photo else VIDEO_EXTS if args.only_video else ALL_SUPPORTED_EXTS

    targets = []
    excluded_by_type = []
    for f in args.files:
        if f.suffix.lower() not in allowed_exts:
            excluded_by_type.append((f, "excluded by --only-photo/--only-video"))
            continue
        targets.append(f)
    if args.dir:
        if not args.dir.is_dir():
            print(f"error: --dir {args.dir}: not a directory", file=sys.stderr)
            sys.exit(2)
        targets.extend(sorted(iter_batch_files(args.dir, allowed_exts)))
    if not targets:
        for f, err in excluded_by_type:
            print(f"skip: {f}: {err}", file=sys.stderr)
        print("nothing to do: no files matched (check --only-photo/--only-video and the extensions under --dir)", file=sys.stderr)
        sys.exit(1 if excluded_by_type else 0)

    plans = [plan_for(f) for f in targets]
    ok_plans = [(p, dt) for p, dt, err in plans if err is None]
    skipped = excluded_by_type + [(p, err) for p, dt, err in plans if err is not None]

    for p, err in skipped:
        print(f"skip: {p}: {err}", file=sys.stderr)

    if not ok_plans:
        print("nothing to do: no files had usable creation-time metadata", file=sys.stderr)
        sys.exit(1 if skipped else 0)

    for p, dt in ok_plans:
        current = datetime.fromtimestamp(p.stat().st_mtime, tz=dt.tzinfo)
        verb = "would set" if args.dry_run else "set"
        print(f"{verb}: {p}: {current.isoformat()} -> {dt.isoformat()}", file=sys.stderr)

    if args.dry_run:
        sys.exit(1 if skipped else 0)

    if not args.yes:
        answer = input(f"\nApply {len(ok_plans)} mtime change(s)? [y/N] ").strip().lower()
        if answer not in ("y", "yes"):
            print("aborted, no changes made", file=sys.stderr)
            sys.exit(1)

    exit_code = 1 if skipped else 0
    for p, dt in ok_plans:
        ts = dt.timestamp()
        os.utime(p, (ts, ts))
    print(f"done: {len(ok_plans)} file(s) updated, {len(skipped)} skipped", file=sys.stderr)
    sys.exit(exit_code)


if __name__ == "__main__":
    main()