#!/usr/bin/env bash
# SUM Parts - modernise APIs the upstream code uses that newer runtimes removed
#
# Two families, same root cause (2022 code on a 2025 toolchain):
#   1. numpy aliases removed in numpy 1.24
#   2. collections ABCs moved to collections.abc in python 3.10
#
# The upstream env pins numpy 1.20, where np.long / np.int / np.float / np.bool
# / np.object / np.str still existed as aliases. numpy 1.24 removed them, so on
# any modern numpy the dataset loaders die inside a DataLoader worker with
#
#     AttributeError: module 'numpy' has no attribute 'long'
#
# and the traceback points at the worker, not at the version mismatch.
#
# Downgrading numpy is not an option here: torch 2.0.1 needs numpy<2 but
# numpy 1.20 has no python 3.10 wheels. So patch the source instead.
#
# Mapping follows what the aliases actually were:
#   np.long   -> np.int64   (alias of python int, i.e. C long)
#   np.int    -> int
#   np.float  -> float
#   np.bool   -> bool
#   np.object -> object
#   np.str    -> str
#
# Idempotent: re-running finds nothing to change. Writes .bak files on first
# touch only.
set -euo pipefail

REPO="${1:-$HOME/sum-parts/semantic_segmentation/PointNeXt_bundle}"

if [ ! -d "$REPO/openpoints" ]; then
    echo "error: $REPO does not look like PointNeXt_bundle" >&2
    exit 1
fi

cd "$REPO"

ABCS='Iterable\|Mapping\|MutableMapping\|Sequence\|Callable\|Hashable\|Iterator\|Container\|Sized'
PATTERN="np\.long\b\|np\.int\b\|np\.float\b\|np\.bool\b\|np\.object\b\|np\.str\b\|collections\.\($ABCS\)\b"

echo "=== before ==="
grep -rn "$PATTERN" --include='*.py' . || echo "  (none)"

# \b keeps np.int from matching np.int32/np.int64, np.float from np.float32, etc.
# The collections rule skips anything already written as collections.abc.X.
find . -name '*.py' -print0 | xargs -0 sed -i.bak \
    -e 's/\bnp\.long\b/np.int64/g' \
    -e 's/\bnp\.int\b/int/g' \
    -e 's/\bnp\.float\b/float/g' \
    -e 's/\bnp\.bool\b/bool/g' \
    -e 's/\bnp\.object\b/object/g' \
    -e 's/\bnp\.str\b/str/g' \
    -e "s/\bcollections\.\($ABCS\)\b/collections.abc.\1/g"

# sed -i.bak writes a .bak for every file it opens, not just changed ones
find . -name '*.py.bak' -print0 | while IFS= read -r -d '' b; do
    if cmp -s "$b" "${b%.bak}"; then rm -f "$b"; fi
done

# `import collections` alone does not pull in collections.abc on every python,
# so make sure any file that now references collections.abc imports it.
grep -rl 'collections\.abc\.' --include='*.py' . | while IFS= read -r f; do
    if ! grep -q '^import collections.abc' "$f"; then
        sed -i 's/^import collections$/import collections\nimport collections.abc/' "$f"
    fi
done

echo
echo "=== after ==="
if grep -rn "$PATTERN" --include='*.py' .; then
    echo "WARNING: some occurrences remain" >&2
else
    echo "  clean"
fi

echo
echo "=== files changed (.bak kept) ==="
find . -name '*.py.bak' | sed 's/\.bak$//' || true

echo "PATCH DONE"