#!/usr/bin/env sh
# The library and its reader, over every document, into $OUT/read/.
#
# What each produces:
#
#   read/dump-{d,g}/<doc>.ssp     the library's dump, loaded from the .ssp
#   read/dump-{d,g}/<doc>.db      the same, loaded from the .ocda.db
#   read/read-{d,g}/<doc>.ssp     ocda-read --tree, reading the .ssp
#   read/read-{d,g}/<doc>.db      the same, reading the .ocda.db
#
# The dumps are the interesting ones. All four of them should be identical:
# the two serialisations say the same thing, and the two languages read it the
# same way. `diff` says so, and the summary at the end counts it.
set -e
. "$(dirname "$0")/config.sh"
: "${ARTEFACTS:?set ARTEFACTS to a directory of .ssp and .ocda.db files}"
mkdir -p "$OUT/read"
for d in dump-d dump-g read-d read-g; do mkdir -p "$OUT/read/$d"; done

list=$(find "$ARTEFACTS" -name '*.ssp' | sort)
[ -n "$LIMIT" ] && list=$(echo "$list" | head -n "$LIMIT")

n=0; same=0; read_same=0
for ssp in $list; do
  stem=$(basename "$ssp" .ssp); lang=${stem##*.}; uid=${stem%.*}
  db=$(find "$ARTEFACTS" -name "$uid.ocda.db" | head -1)
  n=$((n+1))
  sh "$(dirname "$0")/one.sh" dump-d "$ssp" > "$OUT/read/dump-d/$stem.ssp"
  sh "$(dirname "$0")/one.sh" dump-g "$ssp" > "$OUT/read/dump-g/$stem.ssp"
  [ -n "$db" ] || continue
  sh "$(dirname "$0")/one.sh" dump-d "$db" "$lang" > "$OUT/read/dump-d/$stem.db"
  sh "$(dirname "$0")/one.sh" dump-g "$db" "$lang" > "$OUT/read/dump-g/$stem.db"
  # the four-way agreement, which is the library's whole claim
  if cmp -s "$OUT/read/dump-d/$stem.ssp" "$OUT/read/dump-d/$stem.db" \
  && cmp -s "$OUT/read/dump-g/$stem.ssp" "$OUT/read/dump-g/$stem.db" \
  && cmp -s "$OUT/read/dump-d/$stem.ssp" "$OUT/read/dump-g/$stem.ssp"
  then same=$((same+1))
  else echo "DUMPS DIFFER $stem"
  fi
  # ocda-read: the same from either form, and the same in either language,
  # the first line, which names the file read, set aside
  sh "$(dirname "$0")/one.sh" read-d "$ssp" "$lang" --tree | tail -n +2 > "$OUT/read/read-d/$stem.ssp"
  sh "$(dirname "$0")/one.sh" read-g "$ssp" "$lang" --tree | tail -n +2 > "$OUT/read/read-g/$stem.ssp"
  sh "$(dirname "$0")/one.sh" read-d "$db" "$lang" --tree | tail -n +2 > "$OUT/read/read-d/$stem.db"
  sh "$(dirname "$0")/one.sh" read-g "$db" "$lang" --tree | tail -n +2 > "$OUT/read/read-g/$stem.db"
  if cmp -s "$OUT/read/read-d/$stem.ssp" "$OUT/read/read-d/$stem.db" \
  && cmp -s "$OUT/read/read-g/$stem.ssp" "$OUT/read/read-g/$stem.db" \
  && cmp -s "$OUT/read/read-d/$stem.ssp" "$OUT/read/read-g/$stem.ssp"
  then read_same=$((read_same+1))
  else echo "OCDA-READ DIFFERS $stem"
  fi
done
echo
echo "documents read:                            $n"
echo "all four dumps identical                   $same"
echo "ocda-read, all four identical              $read_same"