#!/usr/bin/env bash
# SUM Parts - make the extracted dataset match what the loader globs for
#
# pcl.zip ships splits named train / validate / test. The dataset class asks for
# split='val':
#
#     if split == "train" or split == 'val':
#         self.data_list = glob.glob(os.path.join(data_root, split, "*.ply"))
#
# so `validate/` is never found and validation silently runs on 0 samples --
# the same quiet failure mode as a wrong data_root. Symlink val -> validate.
#
# Track layout after extraction:
#   face_labeling/{face_cen,possion,random,texsp}_pcl/  -> 13-class triangle
#   pixel_labeling/{possion,random,texsp}_pcl/          -> 20-class texture
#
# cfgs/sumv2_triangle uses data_root ../../data/sumv2_tri_texpcl, i.e. the
# triangle track sampled with the texture-superpixel sampler:
#   face_labeling/texsp_pcl
set -euo pipefail

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

echo "=== linking val -> validate in every track ==="
for track in "$DATA"/face_labeling/*_pcl "$DATA"/pixel_labeling/*_pcl; do
    [ -d "$track" ] || continue
    if [ -d "$track/validate" ] && [ ! -e "$track/val" ]; then
        ln -sfn validate "$track/val"
        echo "  linked $(basename "$(dirname "$track")")/$(basename "$track")/val -> validate"
    fi
done

echo
echo "=== split sizes ==="
printf '%-40s %6s %6s %6s\n' "track" "train" "val" "test"
for track in "$DATA"/face_labeling/*_pcl "$DATA"/pixel_labeling/*_pcl; do
    [ -d "$track" ] || continue
    rel="$(basename "$(dirname "$track")")/$(basename "$track")"
    # -L so the val symlink is followed; plain find would report 0 and look
    # like the link did not work
    tr=$(find -L "$track/train" -name '*.ply' 2>/dev/null | wc -l)
    va=$(find -L "$track/val" -name '*.ply' 2>/dev/null | wc -l)
    te=$(find -L "$track/test" -name '*.ply' 2>/dev/null | wc -l)
    printf '%-40s %6s %6s %6s\n' "$rel" "$tr" "$va" "$te"
done

echo
echo "=== recommended data_root ==="
echo "  triangle (13 classes) : $DATA/face_labeling/texsp_pcl"
echo "  texture  (20 classes) : $DATA/pixel_labeling/texsp_pcl"

echo "SPLIT DONE"