#!/bin/sh
#
# Regenerate superhero_offset_200s.flac — the real-audio fixture behind VR-014, the
# audio-signature offset-recovery validation.
#
#     sh make_offset_fixture.sh /path/to/clips
#
# Why real audio and not a second synthetic tone: jray_audio_v1_tone.flac pins
# the *arithmetic* (IR-005) and is deliberately built so every band and every
# energy class appears. It cannot answer the question VR-014 asks — whether the
# peak-bin sequence of ordinary film audio is distinctive enough that sliding
# one signature against another finds the true alignment and only the true
# alignment. Tones are pathologically easy for that; dialogue and score are not.
#
# Source: scene clips from SuperHero (TRECVID DVU development set), the corpus
# this repo already uses for the replay fixtures — tests/fixtures/dumps/superhero.h5
# are dumps of these same clips. Each is under the 120 s window on its own
# (29-77 s), so they are concatenated in scene order to make a source long
# enough that a 120 s window can slide inside it.
#
# 200 s is chosen, not arbitrary: the window is 120 s and the match search is
# capped at +/-600 frames (~55.7 s), so a source of 120 + 56 s is the shortest
# one that can place two windows at the edge of the cap. The 200 s here leaves
# room to go past it as well, which is what lets the test check that an
# out-of-range offset is declined rather than guessed.
#
# Encoded mono at 11025 Hz, 16-bit, which is exactly what the signature decodes
# to anyway. That keeps a 200 s fixture at ~2.4 MB instead of ~20 MB, and makes
# every trim below sample-exact — the test measures offset recovery, not the
# resampler, which tests/test_audio_signature.cpp already covers (UT-103).
#
# FLAC because it is lossless: the decoded PCM is the same on every machine, so
# a signature computed from this file is reproducible. A lossy fixture would
# make the measurement depend on the decoder version.
#
# sha256 of the committed file:
#   4a952e46a090a9acd9eae56996250ec03e08e0d04ee139ac0a42f1690a536c83
# A regenerated file that hashes differently means the source clips or the
# encoder changed, and VR-014's recorded numbers should be re-measured — the
# offsets will still be exact, but the scores are this audio's.

set -eu

CLIPS="${1:-../../../../hero}"
OUT="$(dirname "$0")/superhero_offset_200s.flac"
LIST="$(mktemp)"
trap 'rm -f "$LIST"' EXIT

for scene in 13 27 28 31 46; do
    clip="$CLIPS/SuperHero-$scene.webm"
    [ -f "$clip" ] || { echo "missing clip: $clip" >&2; exit 1; }
    echo "file '$(cd "$(dirname "$clip")" && pwd)/$(basename "$clip")'" >> "$LIST"
done

ffmpeg -nostdin -v error -y -f concat -safe 0 -i "$LIST" \
    -vn -t 200 -ac 1 -ar 11025 -sample_fmt s16 \
    -c:a flac -compression_level 12 "$OUT"

echo "wrote $OUT"
sha256sum "$OUT" 2>/dev/null || shasum -a 256 "$OUT"