#!/usr/bin/env bash
# Fetch `.mul` files other people wrote, which is the only corpus that says
# whether this repository's reader survives contact with the format as it is
# actually used.
#
#   ./scripts/fetch-mul-corpus.sh
#   ./scripts/fetch-mul-corpus.sh /somewhere/else
#
# Prints the corpus path on stdout, so it composes:
#
#   HELM_MUL_CORPUS="$(./scripts/fetch-mul-corpus.sh)" \
#     cargo test -p helm-unitfile --test corpus -- --ignored --nocapture
#
# A MegaMek install ships 28 `.mul` files and they are all MegaMek's own,
# written by one writer for one purpose. These are forces people saved: some
# from MegaMek, some from MekHQ, some from tools that are neither, over
# several years of the format. That is the population a file arriving from a
# player is drawn from.
#
# Nothing fetched here is committed and nothing is redistributed, the same
# posture this repository takes to a MegaMek install. The repositories below
# are public and pinned by commit, and their licences are their own - one is
# GPL-2.0, two say nothing at all - which is a reason to read them and not a
# reason to ship them.
#
# A repository that moves does not change what is tested: the pin is the
# corpus. Repointing one is a commit, so a figure that moves has something
# that says why.
#
# One writer is not fetchable and has to be generated: MekBay, MegaMek's own
# web client, writes `.mul` files that exist nowhere in public code. Generate
# some into `<corpus>/mekbay-generated/` by driving https://mekbay.com in a
# browser - Force Generator, REROLL, CREATE, then Share Force and the MUL
# button - capturing what the page hands to the download. It writes a `<crew>`
# element where MegaMek writes `<pilot>`, and finding that took eight files.
set -euo pipefail

# owner/repo commit
REPOS=(
  "MegaMek/mm-data 5e630eab38ce3dbfb032343fa9504d94043c2d67"
  "nx78/shackclient 557953c0b727059c1c8ca60d3fa8e724d00f9299"
  "mothmind/clusterstrike-crew-game df96e911b382ebc52f279ebb858fd105ac492305"
  "Eudicods/let-the-bots-fight ef4ee58a86df72c6af1b3b7f99d94dd6887fdc96"
  "maldun/UltraMekCore 8d4d8484311e1552eeb929fcdef1e061be544943"
)

out="${1:-$HOME/.cache/helm/mul-corpus}"
mkdir -p "$out"

work="$(mktemp -d)"
trap 'rm -rf "$work"' EXIT

for entry in "${REPOS[@]}"; do
  read -r repo sha <<<"$entry"
  slug="${repo//\//-}"
  dest="$out/$slug"
  # A pin that is already unpacked is the same bytes it was: nothing to do.
  if [[ -f "$dest/.commit" ]] && [[ "$(cat "$dest/.commit")" == "$sha" ]]; then
    echo "have $repo@${sha:0:8}" >&2
    continue
  fi

  echo "fetching $repo@${sha:0:8}" >&2
  tarball="$work/$slug.tar.gz"
  curl -fsSL "https://codeload.github.com/$repo/tar.gz/$sha" -o "$tarball"

  rm -rf "$dest"
  mkdir -p "$dest"
  # Only the `.mul` files, and flattened: a name that keeps its path is a name
  # a failing test can be traced back to the file it came from.
  unpacked="$work/$slug"
  mkdir -p "$unpacked"
  tar -xzf "$tarball" -C "$unpacked" --strip-components=1 --wildcards '*.mul' 2>/dev/null || true
  found=0
  while IFS= read -r -d '' file; do
    rel="${file#"$unpacked"/}"
    cp "$file" "$dest/${rel//\//_}"
    found=$((found + 1))
  done < <(find "$unpacked" -name '*.mul' -print0)
  echo "$sha" >"$dest/.commit"
  echo "  $found files" >&2
done

echo "$out"