diff options
Diffstat (limited to 'pipeline/read.sh')
| -rwxr-xr-x | pipeline/read.sh | 21 |
1 files changed, 18 insertions, 3 deletions
diff --git a/pipeline/read.sh b/pipeline/read.sh index b3129a5..ddbebe4 100755 --- a/pipeline/read.sh +++ b/pipeline/read.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/usr/bin/env sh # Every reader and both libraries, over every document, into $OUT/read/. # # What each produces: @@ -7,6 +7,8 @@ # read/db-{d,g}/<doc>.txt the .ocda.db readers' summary # read/dump-{d,g}/<doc>.ssp the library's dump, loaded from the .ssp # read/dump-{d,g}/<doc>.db the same, loaded from the .ocda.db +# read/read-{d,g}/<doc>.ssp ocda-read --tree, reading the .ssp +# read/read-{d,g}/<doc>.db the same, reading the .ocda.db # # The dumps are the interesting ones. All four of them should be identical: # the two serialisations say the same thing, and the two languages read it the @@ -15,12 +17,12 @@ set -e . "$(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/$d"; done +for d in ssp-d ssp-g db-d db-g dump-d dump-g read-d read-g; do mkdir -p "$OUT/read/$d"; done list=$(find "$ARTEFACTS" -name '*.ssp' | sort) [ -n "$LIMIT" ] && list=$(echo "$list" | head -n "$LIMIT") -n=0; same=0 +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) @@ -41,7 +43,20 @@ for ssp in $list; do then same=$((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" |