1 files changed, 47 insertions, 0 deletions
diff --git a/pipeline/read.sh b/pipeline/read.sh
new file mode 100755
index 0000000..b3129a5
--- /dev/null
+++ b/pipeline/read.sh
@@ -0,0 +1,47 @@
+#!/bin/sh
+# Every reader and both libraries, over every document, into $OUT/read/.
+#
+# What each produces:
+#
+#   read/ssp-{d,g}/<doc>.txt      the .ssp readers' summary
+#   read/db-{d,g}/<doc>.txt       the .ocda.db readers' summary
+#   read/dump-{d,g}/<doc>.ssp     the library's dump, loaded from the .ssp
+#   read/dump-{d,g}/<doc>.db      the same, loaded from the .ocda.db
+#
+# The dumps are the interesting ones. All four of them should be identical:
+# the two serialisations say the same thing, and the two languages read it the
+# same way. `diff` says so, and the summary at the end counts it.
+set -e
+. "$(dirname "$0")/config.sh"
+: "${ARTEFACTS:?set ARTEFACTS to a directory of .ssp and .ocda.db files}"
+mkdir -p "$OUT/read"
+for d in ssp-d ssp-g db-d db-g dump-d dump-g; do mkdir -p "$OUT/read/$d"; done
+
+list=$(find "$ARTEFACTS" -name '*.ssp' | sort)
+[ -n "$LIMIT" ] && list=$(echo "$list" | head -n "$LIMIT")
+
+n=0; same=0
+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 "$0")/one.sh" ssp-d "$ssp" > "$OUT/read/ssp-d/$stem.txt"
+  sh "$(dirname "$0")/one.sh" ssp-g "$ssp" > "$OUT/read/ssp-g/$stem.txt"
+  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 "$0")/one.sh" db-d "$db" > "$OUT/read/db-d/$stem.txt"
+  sh "$(dirname "$0")/one.sh" db-g "$db" > "$OUT/read/db-g/$stem.txt"
+  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
+done
+echo
+echo "documents read:                            $n"
+echo "all four dumps identical                   $same"