clawhdf5/examples/wasm-viewer/test/browser.sh

#!/usr/bin/env bash
# Load the viewer page in headless Chromium and check what it renders.
#
#   browser.sh FIXTURE_DIR
#
# FIXTURE_DIR holds fixture.h5 from make_fixture.py (and big.h5 when it was
# run with WASM_BIG_MB); ../pkg must be built. test/serve.py serves the
# page and, under /fix, the fixtures, with HTTP range requests (no copies,
# no links). The page is opened with ?file=fix/<name>&path=<object>, which
# opens the file with openUrl (range requests), builds the tree down to
# <object> and shows it; the rendered DOM is dumped and checked for the
# values libhdf5 reads and for the request counter.
#
# Browser: $CHROME, else chromium/google-chrome on PATH, else a Playwright
# download under ~/.cache/ms-playwright. Exit 3 when none is found.
# BROWSER_DEBUG=/some/prefix saves each rendered page as prefix.<path>.html.
set -euo pipefail

HERE="$(cd "$(dirname "$0")" && pwd)"
FIX="$(cd "$1" && pwd)"
PY="${CLAWHDF5_PYTHON:-python3}"

chrome="${CHROME:-}"
if [ -z "$chrome" ]; then
    for c in chromium chromium-browser google-chrome chrome-headless-shell; do
        if command -v "$c" >/dev/null; then chrome="$(command -v "$c")"; break; fi
    done
fi
if [ -z "$chrome" ]; then
    chrome="$(ls -d "$HOME"/.cache/ms-playwright/chromium_headless_shell-*/chrome-headless-shell-linux64/chrome-headless-shell 2>/dev/null | tail -1 || true)"
fi
if [ -z "$chrome" ] || [ ! -x "$chrome" ]; then
    echo "no Chromium found (set CHROME)" >&2
    exit 3
fi

profiles="$(mktemp -d)"
server=""
cleanup() {
    [ -n "$server" ] && kill "$server" 2>/dev/null || true
    rm -rf "$profiles"
}
trap cleanup EXIT

"$PY" "$HERE/serve.py" --root "fix=$FIX" --root "=$HERE/.." > "$profiles/port" &
server=$!
for _ in $(seq 50); do
    [ -s "$profiles/port" ] && break
    sleep 0.1
done
port="$(head -1 "$profiles/port")"

fails=0
# A fresh profile per page: a second instance on the same profile fails.
render() {
    local profile
    profile="$(mktemp -d "$profiles/profile.XXXXXX")"
    "$chrome" --headless --no-sandbox --disable-gpu --user-data-dir="$profile" \
        --virtual-time-budget=20000 \
        --dump-dom "http://127.0.0.1:$port/index.html?file=$1&path=$2" 2>/dev/null
}
# expect FILE PATH TEXT...: every TEXT appears in the page rendered for PATH
# of FILE (a URL relative to the page); "re:TEXT" is an extended regex.
expect() {
    local file="$1" path="$2" dom
    shift 2
    dom="$(render "$file" "$path")"
    [ -n "${BROWSER_DEBUG:-}" ] && printf "%s\n" "$dom" > "$BROWSER_DEBUG.$(echo "$file$path" | tr / _).html"
    for text in "$@"; do
        local flag=-qF
        if [ "${text#re:}" != "$text" ]; then flag=-qE; text="${text#re:}"; fi
        if ! grep $flag -- "$text" <<<"$dom"; then
            echo "FAIL: page for $file $path lacks: $text" >&2
            fails=$((fails + 1))
        fi
    done
    echo "rendered $file $path"
}

H5=fix/fixture.h5
# Tree (root expanded; the group row carries its path) and root attributes.
expect $H5 "/" 'data-path="/sensors"' 'data-path="/grid"' '<td>title</td><td>"wasm fixture"</td>' \
    '<td>big</td><td>9223372036854775813</td>' '(compound{x: f64, n: i32})'
# A chunked, deflated 2-D dataset: type, shape, the first window of values;
# the request counter.
expect $H5 "/grid" '<dd>f64</dd>' '<dd>(6, 10)</dd>' '<th>9</th>' '<td>0.25</td>' '<td>14.75</td>' \
    'showing rows 0–5, columns 0–9 of 60 values' 'request' 'fetched (100.0%)'
# Nested path revealed through the tree; big-endian float32.
expect $H5 "/sensors/temp" 'data-path="/sensors/temp"' '<dd>f32</dd>' '<td>21.5</td>' '<td>22.25</td>'
# 64-bit integers stay exact; strings; array datatype cells.
expect $H5 "/u64" '<td>18446744073709551615</td>'
expect $H5 "/vlen_str" '<td>"двa"</td>' '<dd>vlen string</dd>'
expect $H5 "/pairs" '<td>[2, 3]</td>' '<dd>array[2]&lt;i32&gt;</dd>'
# 3-D: leading dimension held at 0, window over the last two.
expect $H5 "/cube" '<dd>(2, 5, 6)</dd>' '<td>29</td>' 'dim 0'
# HDF5 2.0 native complex (written when h5py's libhdf5 is 2.0 or later):
# each cell is the [re, im] pair.
if "$PY" -c 'import sys, h5py; sys.exit(not getattr(h5py.get_config(), "has_native_complex", False))'; then
    expect $H5 "/native_c128" '<dd>complex&lt;f64&gt;</dd>' '<dd>(3, 2)</dd>' '<td>[1, -1.5]</td>' \
        '<td>[5, -7.5]</td>'
fi
# Unsupported type: an error, not values.
expect $H5 "/table" 'class="error"' 'reading compound{x: f64, n: i32} datasets is not supported'
# Cross-origin: the page is on 127.0.0.1, the file on localhost. CORS that
# exposes Content-Range, and CORS that exposes nothing (/unexposed/: the
# browser hides Content-Range and ETag, so the page learns the length with
# a HEAD request, which the server's log must show).
expect "http://localhost:$port/$H5" "/grid" '<td>14.75</td>' 'request'
get() { "$PY" -c 'import sys, urllib.request; print(urllib.request.urlopen(sys.argv[1]).read().decode())' "$1"; }
get "http://127.0.0.1:$port/__reset" >/dev/null
expect "http://localhost:$port/unexposed/$H5" "/grid" '<td>0.25</td>' '<td>14.75</td>' 'request'
heads="$(get "http://127.0.0.1:$port/__stats" | "$PY" -c \
    'import json, sys; print(sum(1 for l in json.load(sys.stdin)["log"] if l[4] == "HEAD" and l[0].endswith("fixture.h5")))')"
if [ "$heads" -lt 1 ]; then
    echo "FAIL: no HEAD request for the length with unexposed headers" >&2
    fails=$((fails + 1))
fi
# A server without range support: the file is downloaded whole, and says so.
expect norange/$H5 "/grid" '<td>14.75</td>' 'downloaded whole'
# A large file: a small dataset, and a window of the large one, fetch a few
# blocks (the counter shows a small percentage: "(1.5%)", not "(100.0%)").
if [ -f "$FIX/big.h5" ]; then
    expect fix/big.h5 "/small" '<td>1.5</td>' '<td>3.25</td>' 're:MiB of 191 MiB fetched \([0-9]\.[0-9]%\)'
    expect fix/big.h5 "/big" '<dd>(25000000)</dd>' '<td>0</td>' '<td>24.5</td>' \
        're:MiB of 191 MiB fetched \([0-9]\.[0-9]%\)'
fi

if [ "$fails" -gt 0 ]; then
    echo "browser: $fails checks failed" >&2
    exit 1
fi
echo "browser: all checks passed ($chrome)"