#!/usr/bin/env bash
# fetch-corpus.sh [cache_dir]
#
# Download the corpora pinned in conformance/corpus.txt into the (gitignored)
# cache: <cache>/src/<name> is a shallow, sparse, blob-filtered checkout of the
# pinned commit and <cache>/corpus/<name> links to the swept root inside it.
# A corpus already checked out at its pinned commit is left alone, so a second
# run costs nothing and needs no network.
set -euo pipefail
HERE="$(cd "$(dirname "$0")" && pwd)"
CACHE="${1:-${CONFORMANCE_CACHE:-$HERE/.cache}}"
mkdir -p "$CACHE/src" "$CACHE/corpus"
CACHE="$(cd "$CACHE" && pwd)"

retry() { local i; for i in 1 2 3 4; do "$@" && return 0; sleep $((i * 5)); done; return 1; }

grep -v '^[[:space:]]*\(#\|$\)' "$HERE/corpus.txt" | while read -r name url commit root patterns; do
  src="$CACHE/src/$name"
  if [ -d "$src/.git" ] && [ "$(git -C "$src" rev-parse HEAD 2>/dev/null)" = "$commit" ]; then
    echo "cached   $name @ ${commit:0:12}"
  else
    echo "fetching $name @ ${commit:0:12} from $url"
    rm -rf "$src"
    git init -q "$src"
    git -C "$src" remote add origin "$url"
    git -C "$src" config advice.detachedHead false
    if [ -n "$patterns" ]; then
      git -C "$src" config core.sparseCheckout true
      # no-cone patterns (globs); `set -f` keeps the shell from expanding them
      (set -f; printf '%s\n' $patterns) > "$src/.git/info/sparse-checkout"
    fi
    retry git -C "$src" fetch -q --depth 1 --filter=blob:none origin "$commit"
    retry git -C "$src" checkout -q FETCH_HEAD
    got="$(git -C "$src" rev-parse HEAD)"
    [ "$got" = "$commit" ] || { echo "error: $name checked out $got, expected $commit" >&2; exit 1; }
  fi
  ln -sfn "$src/$root" "$CACHE/corpus/$name"
done
echo "corpus ready in $CACHE/corpus"