catcrafts.net/tools/publish-media.sh

#!/bin/sh
# Publish a recording or screenshot to catcrafts.net and print the URL to put in
# the fediverse post.
#
#   usage: tools/publish-media.sh [-r] [-c CRF] <file>...
#
#     -r, --raw       upload the file unchanged (no transcode, no poster)
#     -c, --crf N     AV1 quality, lower is better (default 32)
#
# WHY THIS EXISTS: the media used to be uploaded to a third-party file host and
# then mirrored back at build time by tools/fetch-media.sh. That worked until a
# 167 MB recording hit the mirror's size cap, and the deploy failed on a file we
# had sitting on disk the whole time. Publishing to our own origin FIRST inverts
# it — the URL in the post is already the URL the page wants, so there is nothing
# to download, no size cap to clear, and no third party who can be slow, rate-
# limit us, or delete the file that IS the post.
#
# The name is the content hash, matching what fetch-media.sh produces, which is
# what makes Caddy's one-year immutable cache on /media honest: different bytes
# can never appear under a name someone already has cached.
#
# TRANSCODE: phone recordings are enormous for what they show — the one that
# started this was 78 s of a dark room at 17 Mbps, 167 MB, where denoising and
# AV1 give the same picture in 15 MB. Dark handheld footage is mostly sensor
# noise, which is expensive to encode and worth nothing, so hqdn3d earns its
# place before the encoder rather than after it.
#
# ROTATION: phones record landscape and attach a display matrix instead of
# rotating pixels. Transcoding bakes the rotation into the frames, so what every
# downstream consumer measures is what the viewer actually sees — see the
# rotation note in fetch-media.sh for what goes wrong when it does not.
#
# NOTE ON AV1: nothing here emits a fallback encoding, and the <video> tag the
# site renders carries a single src. Browsers without AV1 (Safari before 17, and
# Apple hardware older than A17/M3) get an element that will not play rather than
# a degraded one. Pass --raw, or re-encode to H.264, if that audience matters for
# a particular post.

set -eu

MEDIA_HOST="${MEDIA_HOST:-root@catcrafts.net}"
MEDIA_PATH="${MEDIA_PATH:-/srv/catcrafts-app/media}"
SITE_ORIGIN="${SITE_ORIGIN:-https://catcrafts.net}"
CRF="${CRF:-32}"
RAW=0

for c in ffmpeg ffprobe sha256sum ssh scp; do
    command -v "$c" >/dev/null 2>&1 || { echo "publish-media: $c not found" >&2; exit 1; }
done

FILES=""
while [ $# -gt 0 ]; do
    case "$1" in
        -r|--raw)  RAW=1; shift ;;
        -c|--crf)  CRF="$2"; shift 2 ;;
        -h|--help) sed -n '2,10p' "$0"; exit 0 ;;
        -*)        echo "publish-media: unknown option: $1" >&2; exit 1 ;;
        *)         FILES="$FILES $1"; shift ;;
    esac
done
[ -n "$FILES" ] || { echo "publish-media: no input file. See --help." >&2; exit 1; }

WORK="$(mktemp -d)"
trap 'rm -rf "$WORK"' EXIT

# Upload only what is not already there. The name is the content hash, so a name
# that exists on the mount holds these exact bytes and re-sending them would
# change nothing — which makes re-running this script on the same file free, and
# makes a half-finished batch safe to just run again.
publish_file() {
    local_file=$1
    remote_name=$2
    if ssh -o BatchMode=yes "$MEDIA_HOST" "test -f '$MEDIA_PATH/$remote_name'"; then
        echo "  already published: $remote_name"
        return 0
    fi
    # Land it under a temporary name and move it into place, so a reader can
    # never see a partial file under the name its hash promises.
    scp -q -o BatchMode=yes "$local_file" "$MEDIA_HOST:$MEDIA_PATH/.$remote_name.part"
    ssh -o BatchMode=yes "$MEDIA_HOST" \
        "chmod 0644 '$MEDIA_PATH/.$remote_name.part' && \
         mv -f '$MEDIA_PATH/.$remote_name.part' '$MEDIA_PATH/$remote_name'"
    echo "  uploaded: $remote_name"
}

for src in $FILES; do
    [ -f "$src" ] || { echo "publish-media: no such file: $src" >&2; exit 1; }
    echo "$src"

    ext=$(printf '%s' "$src" | sed -E 's/.*\.([A-Za-z0-9]+)$/\1/' | tr 'A-Z' 'a-z')
    kind=other
    case "$ext" in
        mp4|webm|mov|mkv|avi) kind=video ;;
        png|jpg|jpeg|webp|gif|avif) kind=image ;;
    esac

    poster=""
    if [ "$RAW" = 1 ] || [ "$kind" = other ]; then
        payload="$src"
        out_ext="$ext"
    elif [ "$kind" = video ]; then
        payload="$WORK/out.mp4"
        out_ext=mp4
        echo "  transcoding to AV1 (crf $CRF)…"
        ffmpeg -nostdin -v error -i "$src" \
               -vf "hqdn3d=4:3:6:4.5" \
               -c:v libsvtav1 -preset 4 -crf "$CRF" -pix_fmt yuv420p -g 240 \
               -movflags +faststart \
               -c:a aac -b:a 96k -ac 1 \
               "$payload" -y
        # AAC rather than Opus on purpose: Opus-in-MP4 is still uneven in exactly
        # the players most likely to be shaky about AV1 anyway, and the audio is
        # a rounding error next to the video either way.
        poster="$WORK/poster.webp"
        # A frame a third of the way in, which beats frame 0 — recordings tend to
        # open on a lock screen, a hand moving into place, or a fade.
        dur=$(ffprobe -v error -show_entries format=duration \
                      -of default=nw=1:nk=1 "$payload" 2>/dev/null || echo 0)
        at=$(awk -v d="$dur" 'BEGIN { printf "%.2f", (d > 3 ? d / 3 : 0) }')
        ffmpeg -nostdin -v error -ss "$at" -i "$payload" -frames:v 1 \
               -vf "scale=720:-2" -c:v libwebp -quality 80 "$poster" -y
    else
        payload="$WORK/out.webp"
        out_ext=webp
        echo "  converting to webp…"
        ffmpeg -nostdin -v error -i "$src" -c:v libwebp -quality 82 "$payload" -y
    fi

    hash=$(sha256sum "$payload" | cut -c1-16)
    name="$hash.$out_ext"
    publish_file "$payload" "$name"

    # The poster is named after the VIDEO's hash, not its own. That is the whole
    # point: fetch-media.sh finds it by name, with nothing to look up, when the
    # instance did not manage to make a thumbnail — pict-rs will not read AV1, so
    # for these uploads that is the normal case rather than the exception.
    if [ -n "$poster" ] && [ -f "$poster" ]; then
        publish_file "$poster" "$hash.poster.webp"
    fi

    url="$SITE_ORIGIN/media/$name"
    # Confirm it is actually being served before handing over a URL that is about
    # to be pasted into a post, where a 404 is public and permanent.
    code=$(curl -s -o /dev/null -w '%{http_code}' --max-time 30 "$url" || echo 000)
    if [ "$code" = 200 ]; then
        printf '  %s\n' "$url"
    else
        echo "  WARNING: $url answered HTTP $code — do not post this link yet" >&2
    fi
    printf '  %s -> %s (%s)\n' \
        "$(du -h "$src" | cut -f1)" "$(du -h "$payload" | cut -f1)" "$name"
done