#!/usr/bin/env bash
# SUM Parts - lay the demo tile out as a train/val/test split
#
# demo.zip ships a single showcase tile, not a split. The dataset class globs
# <data_root>/{train,val,test}/*.ply, so nothing runs until that structure
# exists.
#
# WARNING: this puts the SAME tile in all three splits. That is fine for a
# pipeline smoke test (does the chain survive?) and meaningless as a
# measurement -- every val/test number it produces is train-set memorisation.
# Do not quote any mIoU from this layout.
#
# Track selection follows the cfg directory name: cfgs/sumv2_triangle uses
# data_root ../../data/sumv2_tri_texpcl, i.e. the triangle (face-label) track
# sampled with the texture-superpixel sampler -> face_labeling_pcl/*_texsp_pcl.ply
set -euo pipefail

DATA="$HOME/sum-parts/data"

# track name -> source ply
declare -A SRC=(
    [sumv2_tri_texpcl]="$DATA/pcl/face_labeling_pcl/demo_texsp_pcl.ply"
    [sumv2_tex_texpcl]="$DATA/pcl/texture_labeling_pcl/demo_texsp_pcl.ply"
)

for track in "${!SRC[@]}"; do
    src="${SRC[$track]}"
    if [ ! -f "$src" ]; then
        echo "skip $track: $src not found"
        continue
    fi
    echo "=== $track <- $(basename "$src") ==="
    for split in train val test; do
        mkdir -p "$DATA/$track/$split"
        # hardlink: same tile in three splits, one copy on disk
        ln -f "$src" "$DATA/$track/$split/$(basename "$src")"
    done
    # a stale presample cache silently overrides the ply files
    rm -rf "$DATA/$track/processed"
done

echo
echo "=== layout ==="
for track in "${!SRC[@]}"; do
    [ -d "$DATA/$track" ] || continue
    for split in train val test; do
        n=$(find "$DATA/$track/$split" -name '*.ply' 2>/dev/null | wc -l)
        printf '%-20s %-6s %s ply\n' "$track" "$split" "$n"
    done
done

echo "SPLIT DONE"