diff options
Diffstat (limited to 'org')
| -rw-r--r-- | org/tests_for_document_abstraction_shell_scripts.org | 193 |
1 files changed, 191 insertions, 2 deletions
diff --git a/org/tests_for_document_abstraction_shell_scripts.org b/org/tests_for_document_abstraction_shell_scripts.org index ab2dc35..d62bf17 100644 --- a/org/tests_for_document_abstraction_shell_scripts.org +++ b/org/tests_for_document_abstraction_shell_scripts.org @@ -46,7 +46,8 @@ # 3 test-abstraction-db.sh the two serialisations agree # 4 test-abstraction-db-roundtrip.sh the .db can be read back whole # 5 test-ocn-alignment.sh the languages agree on their ocns -# 6 test-epub-validity.sh the epubs a reader can actually open +# 6 test-acceptance-db-to-pod.sh a database gives its document back +# 7 test-epub-validity.sh the epubs a reader can actually open # # None of them calls another, and each can be run on its own. The order # matters only for reading the result: @@ -65,6 +66,13 @@ # translations and reports nothing about the other documents. It will # fail if those translations are mended, which is the right moment to # hear about it. +# - 6 is the acceptance test for the document source claim, and the widest +# of them: it builds a document from its pod and again from the database +# that build produced, and requires the two output trees to be identical. +# Where 3 and 4 check one serialisation against another, this checks a +# whole document through the whole pipeline twice. If it fails and the +# others pass, what broke is the carrying or the materialising rather +# than the abstraction. set -e @@ -91,6 +99,7 @@ test-abstraction-ssp-roundtrip.sh test-abstraction-db.sh test-abstraction-db-roundtrip.sh test-ocn-alignment.sh +test-acceptance-db-to-pod.sh test-epub-validity.sh" PASSED=0 @@ -1073,7 +1082,186 @@ else exit 1 fi #+END_SRC -** 6. test epub validity +** 6. test acceptance db to pod + +#+HEADER: :tangle ../test/test-acceptance-db-to-pod.sh +#+HEADER: :tangle-mode (identity #o755) +#+HEADER: :shebang "#!/usr/bin/env sh" +#+BEGIN_SRC shell +# test-acceptance-db-to-pod.sh +# +# The acceptance test for the document source claim: a .ocda.db carries +# everything a pod does, so a pod written back out of it builds the same +# document. +# +# Two runs of the same spine, with the same flags, over the same document: +# +# A the pod -> artefacts and outputs +# B A's database -> pod -> artefacts and outputs +# +# and `diff -r` between the two output trees must be empty. That single +# comparison covers more than it appears: the written pod tree (markup, conf, +# images, translation catalogues), the .ssp files, the .ocda.db itself, the +# digests.txt, and the text, html and epub built from them. +# +# Two things the runs must share for the comparison to mean anything: +# +# the site configuration. The abstraction depends only on pod content, +# but a document's metadata pages carry the site's url, which comes from +# a .dr/config_local_site found *above* the pod. A materialised pod sits +# in a directory of the run's making with no such file, so the pod for +# run A is copied out of the sample set to a neutral place rather than +# read where it lies. Without that, a sound comparison shows ~22 files +# differing in a url and reads as corruption. +# +# the flags. The dom structure tags the .ssp records are computed only +# when an action needs them, so two runs asking for different things +# build different abstractions from the same markup. Both runs here ask +# for the same set. +# +# Not compared: the pod archive. --pod is not asked for, so neither run +# writes one. The archive is a container around bytes that are compared +# here already, and its own bytes are not part of what the database claims +# to carry. +# +# Also asserted: --ocda-verify passes on the database, which is the other +# half of the claim. The comparison says the pod comes back; verify says the +# abstraction it makes is the one recorded with it. +# +# Usage: +# SpinePOD=../../markup/sisudoc-spine-samples/markup/pod-samples/pod \ +# ./test/test-acceptance-db-to-pod.sh ./bin/spine-ldc +# +# Exit codes: +# 0 every document round trips with no difference +# 1 differences found (printed) +# 2 set-up problem (no $SpinePOD, no binary, no samples) + +set -e + +SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)" +SPINE_DIR="$(cd "$SCRIPT_DIR/.." && pwd)" + +if [ -z "$SpinePOD" ]; then + echo "ERROR: \$SpinePOD is not set." >&2 + echo " e.g. SpinePOD=../../markup/sisudoc-spine-samples/markup/pod-samples/pod" >&2 + exit 2 +fi +SAMPLES_RAW="$SPINE_DIR/$SpinePOD" +if [ -d "$SAMPLES_RAW" ]; then + SAMPLES_DIR="$(cd "$SAMPLES_RAW" && pwd)" +else + SAMPLES_DIR="$SAMPLES_RAW" +fi +if [ ! -d "$SAMPLES_DIR" ]; then + echo "ERROR: sample documents not found at $SAMPLES_DIR" >&2 + exit 2 +fi + +SPINE_BIN="${1:-}" +if [ -z "$SPINE_BIN" ]; then + if [ -x "$SPINE_DIR/result/bin/spine" ]; then SPINE_BIN="$SPINE_DIR/result/bin/spine" + elif [ -x "$SPINE_DIR/bin/spine-ldc" ]; then SPINE_BIN="$SPINE_DIR/bin/spine-ldc" + elif [ -x "$SPINE_DIR/bin/spine" ]; then SPINE_BIN="$SPINE_DIR/bin/spine" + else + echo "ERROR: spine binary not found. Specify path as argument." >&2 + exit 2 + fi +fi + +# the documents to round trip. live-manual is the one that exercises every +# part: ten languages, inserts, and a tools/po4a catalogue tree. The second +# has images, which live-manual has none of, and is a single language. +DOCS="${SpineAcceptanceDocs:-live-manual the_wealth_of_networks.yochai_benkler}" + +# the same flags for both runs: the pod tree, both abstraction artefacts, and +# three output formats over them +FLAGS="--source --show-abstraction --ocda-db --text --html --epub" + +OUT_DIR="$SCRIPT_DIR/current-acceptance" +rm -rf "$OUT_DIR" +mkdir -p "$OUT_DIR/pods" + +echo "spine binary: $SPINE_BIN" +echo "samples: $SAMPLES_DIR" + +FAILURES=0 +DOCS_DONE=0 + +for doc in $DOCS; do + if [ ! -d "$SAMPLES_DIR/$doc" ]; then + echo "MISSING sample: $doc" + FAILURES=$((FAILURES + 1)) + continue + fi + echo "── $doc" + + # the pod, copied where no .dr/ sits above it + cp -a "$SAMPLES_DIR/$doc" "$OUT_DIR/pods/$doc" + + # A: from the pod + if ! $SPINE_BIN $FLAGS --output="$OUT_DIR/a.$doc" "$OUT_DIR/pods/$doc" \ + > "$OUT_DIR/a.$doc.out" 2> "$OUT_DIR/a.$doc.err"; then + echo " FAIL: the run from the pod exited non-zero" + tail -3 "$OUT_DIR/a.$doc.err" | sed 's/^/ /' + FAILURES=$((FAILURES + 1)) + continue + fi + + db=$(find "$OUT_DIR/a.$doc/pod" -maxdepth 1 -name "*.ocda.db" | head -1) + if [ ! -f "$db" ]; then + echo " FAIL: the run from the pod wrote no database" + FAILURES=$((FAILURES + 1)) + continue + fi + + # the database says the markup it carries still makes the abstraction it + # holds. Checked before the build, because a build from it checks the same + # thing and would stop; asked here on its own so that a failure says which + # of the two claims broke + if ! $SPINE_BIN --ocda-verify="$db" --output="$OUT_DIR/v.$doc" \ + > "$OUT_DIR/v.$doc.out" 2> "$OUT_DIR/v.$doc.err"; then + echo " FAIL: --ocda-verify on $(basename "$db")" + grep -E "no longer|records no" "$OUT_DIR/v.$doc.err" | head -3 | sed 's/^/ /' + FAILURES=$((FAILURES + 1)) + continue + fi + verified=$(grep -E "^verify: " "$OUT_DIR/v.$doc.out" | head -1) + [ -n "$verified" ] && echo " $verified" + + # B: from the database + if ! $SPINE_BIN $FLAGS --output="$OUT_DIR/b.$doc" "$db" \ + > "$OUT_DIR/b.$doc.out" 2> "$OUT_DIR/b.$doc.err"; then + echo " FAIL: the run from the database exited non-zero" + tail -3 "$OUT_DIR/b.$doc.err" | sed 's/^/ /' + FAILURES=$((FAILURES + 1)) + continue + fi + + # and the whole of it, held against the whole of it + if diff -rq "$OUT_DIR/a.$doc" "$OUT_DIR/b.$doc" > "$OUT_DIR/d.$doc" 2>&1; then + n=$(find "$OUT_DIR/b.$doc" -type f | wc -l) + echo " ok: $n files, no differences" + DOCS_DONE=$((DOCS_DONE + 1)) + else + echo " FAIL: $(grep -c . "$OUT_DIR/d.$doc") difference(s)" + head -8 "$OUT_DIR/d.$doc" | sed 's/^/ /' + FAILURES=$((FAILURES + 1)) + fi +done + +rm -rf "$OUT_DIR" + +if [ "$FAILURES" -eq 0 ]; then + echo "PASS: $DOCS_DONE document(s) build identically from their database" + exit 0 +else + echo "FAIL: $FAILURES document(s) do not" + exit 1 +fi +#+END_SRC + +** 7. test epub validity #+HEADER: :tangle ../test/test-epub-validity.sh #+HEADER: :tangle-mode (identity #o755) @@ -1195,6 +1383,7 @@ fi echo "PASS: $FATALS fatal and $ERRORS errors, both within what is recorded" exit 0 #+END_SRC + * collection search db + cgi form ** test search db schema |