#!/usr/bin/env bash
# ============================================================================
# prerender-static.sh — build aac.transaction.science as a self-contained
# static site.
#
# AAC ships as a static CSR-hydrate SPA, but it's a Leptos SSR app: the
# index.html the browser loads is the SSR server's *rendered* output (it carries
# the hydration island markers and the pre-rendered board). A plain
# `cargo leptos build` never emits that index.html, and it doesn't copy the
# PWA assets that live in `static/`. This script closes both gaps and makes the
# result safe to cache forever:
#
#   build   -> target/site/{pkg/, icons/, symbols/}   (cargo-leptos)
#   render  -> target/site/index.html                 (capture SSR `/`)
#   hash    -> pkg/aac-web.<sha256:12>.{js,wasm,css}  (and rewrite references)
#   vendor  -> target/site/vendor/mediapipe-<ver>-<rev>/  (eye gaze, same origin)
#   worker  -> target/site/sw.js                      (static/sw.js + precache list)
#
# Output: a self-contained `target/site/` ready to rsync to prod. Deploy it with
# no_cache_bust — the names are already content-hashed, and the service worker
# lists them. Idempotent.
#
# Hosting under a sub-path, or under another name, is a build-time choice; see
# AAC_BASE_PATH, AAC_SW_URL, AAC_APP_TITLE and AAC_HIDE_ENERGY in
# crates/aac-web/src/app.rs. This script builds the root-mounted default.
# ============================================================================
set -euo pipefail
cd "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"

PORT="${AAC_PRERENDER_PORT:-39207}"
SITE="target/site"
CACHE="${XDG_CACHE_HOME:-$HOME/.cache}/aac-rs"

# wasm-bindgen's CLI must match the crate version exactly (Cargo.toml pins it).
# Use a private copy of the right version rather than the machine's global one.
WBG_VER="$(awk '/^name = "wasm-bindgen"$/{getline; gsub(/version = |"/, ""); print; exit}' Cargo.lock)"
if ! wasm-bindgen --version 2>/dev/null | grep -qx "wasm-bindgen $WBG_VER"; then
  WBG_ROOT="$CACHE/wasm-bindgen-$WBG_VER"
  if [ ! -x "$WBG_ROOT/bin/wasm-bindgen" ]; then
    echo "▸ installing wasm-bindgen-cli $WBG_VER into $WBG_ROOT"
    cargo install --quiet --locked --root "$WBG_ROOT" wasm-bindgen-cli --version "$WBG_VER"
  fi
  export PATH="$WBG_ROOT/bin:$PATH"
fi

echo "▸ cargo leptos build --release"
rm -rf "$SITE/pkg"
cargo leptos build --release
find "$SITE/pkg" -name '*.d.ts' -delete
# Symbol sprites and their licences (cargo-leptos copies public/; a clean copy
# drops sprites of earlier builds, whose names carry another hash).
rm -rf "$SITE/symbols"
cp -R crates/aac-web/public/symbols "$SITE/symbols"
# Language packs for word prediction (data/lang: content-hashed, with their
# licence) under models/lang/, where the app's model store downloads a
# language's pack once, verifies it and keeps it (aac-web lang_packs.rs).
rm -rf "$SITE/models/lang"
mkdir -p "$SITE/models/lang"
cp data/lang/*.bin data/lang/index.json data/lang/LICENSE.md "$SITE/models/lang/"
# The pinyin index for typing Chinese on the on-screen keyboard (data/pinyin,
# content-hashed, with its licence): fetched only when Chinese is typed.
rm -rf "$SITE/models/pinyin"
mkdir -p "$SITE/models/pinyin"
cp data/pinyin/*.txt data/pinyin/index.json data/pinyin/LICENSE.md "$SITE/models/pinyin/"

echo "▸ starting SSR server on 127.0.0.1:$PORT to prerender /"
LOG="$(mktemp)"
LEPTOS_OUTPUT_NAME=aac-web \
LEPTOS_SITE_ROOT="$SITE" \
LEPTOS_SITE_PKG_DIR=pkg \
LEPTOS_SITE_ADDR="127.0.0.1:$PORT" \
LEPTOS_ENV=PROD \
  target/release/aac-web > "$LOG" 2>&1 &
SRV=$!
trap 'kill "$SRV" 2>/dev/null || true' EXIT

# Wait for the listener (up to ~30s).
ready=false
for _ in $(seq 1 120); do
  if curl -sf "http://127.0.0.1:$PORT/" -o /dev/null 2>/dev/null; then ready=true; break; fi
  sleep 0.25
done
if ! $ready; then
  echo "✗ SSR server did not come up; log:" >&2; tail -5 "$LOG" >&2; exit 1
fi

echo "▸ capturing rendered / -> $SITE/index.html"
curl -sf "http://127.0.0.1:$PORT/" -o "$SITE/index.html"

kill "$SRV" 2>/dev/null || true
trap - EXIT

# Sanity-check the capture is the hydrating SSR shell, not an error page.
test -s "$SITE/index.html"
grep -q 'mod.hydrate' "$SITE/index.html" || { echo "✗ captured index.html is not the hydrating shell" >&2; exit 1; }
grep -q '<title>AAC' "$SITE/index.html" || { echo "✗ captured index.html missing expected title" >&2; exit 1; }

echo "▸ content-hashing pkg/"
hash12() { shasum -a 256 "$1" | cut -c1-12; }
# Portable in-place sed (BSD and GNU disagree about -i):  sed_i <args…> <file>
sed_i() { local f="${!#}"; sed "${@:1:$#-1}" "$f" > "$f.tmp" && mv "$f.tmp" "$f"; }
P="$SITE/pkg"
[ -f "$P/aac-web_bg.wasm" ] || mv "$P/aac-web.wasm" "$P/aac-web_bg.wasm"
W="$(hash12 "$P/aac-web_bg.wasm")";  mv "$P/aac-web_bg.wasm" "$P/aac-web.$W.wasm"
C="$(hash12 "$P/aac-web.css")";      mv "$P/aac-web.css" "$P/aac-web.$C.css"
# The glue may name its wasm; point it at the hashed file before hashing the glue.
sed_i -e "s#aac-web_bg\\.wasm#aac-web.$W.wasm#g" -e "s#aac-web\\.wasm#aac-web.$W.wasm#g" "$P/aac-web.js"
# wasm-bindgen names the snippet directory after the crate, not its contents,
# so a snippet keeps its URL from build to build, and Cloudflare gives every .js
# a 4-hour browser cache whatever Caddy sends. A returning visitor would then
# pair a new aac-web.js with an old snippet, and the app would not start (seen
# on 2026-09-30). Name each snippet directory by its contents too, before
# aac-web.js (whose imports name it) is hashed.
for d in "$P"/snippets/*/; do
  d="${d%/}"; name="$(basename "$d")"
  S="$(cd "$d" && find . -type f | LC_ALL=C sort | while IFS= read -r f; do printf '%s %s\n' "$f" "$(shasum -a 256 "$f" | cut -c1-64)"; done | shasum -a 256 | cut -c1-12)"
  mv "$d" "$P/snippets/$name-$S"
  # Only where the script loads it (`from "…"`, `import("…")`): the keys of
  # the WebAssembly import object keep the old path, which the .wasm names.
  sed_i -e "s#\(from *[\"']\)\./snippets/$name/#\1./snippets/$name-$S/#g" \
        -e "s#\(import( *[\"']\)\./snippets/$name/#\1./snippets/$name-$S/#g" "$P/aac-web.js"
  grep -q "snippets/$name-$S/" "$P/aac-web.js" || { echo "✗ aac-web.js does not import snippets/$name-$S" >&2; exit 1; }
  if grep -qE "(from *[\"']|import\( *[\"'])\./snippets/$name/" "$P/aac-web.js"; then
    echo "✗ aac-web.js still loads snippets/$name by its old name" >&2; exit 1
  fi
done
J="$(hash12 "$P/aac-web.js")";       mv "$P/aac-web.js" "$P/aac-web.$J.js"
sed_i \
  -e "s#/pkg/aac-web_bg\\.wasm#/pkg/aac-web.$W.wasm#g" \
  -e "s#/pkg/aac-web\\.wasm#/pkg/aac-web.$W.wasm#g" \
  -e "s#/pkg/aac-web\\.js#/pkg/aac-web.$J.js#g" \
  -e "s#/pkg/aac-web\\.css#/pkg/aac-web.$C.css#g" \
  "$SITE/index.html"
# Leptos's hydration loader builds its URLs from arguments:
#   (root, pkg_path, output_name, wasm_output_name)
LOADER='("", "pkg", "aac-web", "aac-web")'
grep -qF "$LOADER" "$SITE/index.html" || { echo "✗ hydration loader call not found — has Leptos changed its loader?" >&2; exit 1; }
sed_i "s#(\"\", \"pkg\", \"aac-web\", \"aac-web\")#(\"\", \"pkg\", \"aac-web.$J\", \"aac-web.$W\")#" "$SITE/index.html"
for f in "aac-web.$W.wasm" "aac-web.$J.js" "aac-web.$C.css" "\"aac-web.$J\", \"aac-web.$W\""; do
  grep -q "$f" "$SITE/index.html" || { echo "✗ index.html does not reference $f" >&2; exit 1; }
done

# Eye gaze loads MediaPipe from vendor/mediapipe-<version>-<revision>/ on this
# origin (crates/aac-web/src/bindings/mediapipe_init.js), so turning on the
# camera makes no third-party request and the app stays cross-origin isolated.
rm -rf "$SITE/vendor"
bash third_party/mediapipe/vendor.sh "$SITE" "$CACHE"
MP_DIR="$(cd "$SITE/vendor" && echo mediapipe-*)"
[ -d "$SITE/vendor/$MP_DIR" ] || { echo "✗ vendor.sh left no vendor/mediapipe-* directory" >&2; exit 1; }

# On-device voices, downloaded only when the person asks (neural_voice.rs):
# the Moonshine WASM runtime, vendored and pinned like MediaPipe, and the
# voice packs, built outside git by tools/voices/build_voices.py, under
# voices/ (cloned, not copied, on APFS), once tools/voices/check_packs.py
# has matched them to the committed catalogue. A build without them must say
# so (AAC_VOICES=none): a deploy would otherwise delete the voices it serves.
rm -rf "$SITE/voices"
if [ "${AAC_VOICES:-}" = "none" ]; then
  echo "▸ AAC_VOICES=none: no better voices in this build; the app offers the device's voices only"
else
  bash third_party/moonshine-wasm/vendor.sh "$SITE" "$CACHE"
  VOICES="${AAC_VOICES_DIR:-$(cd ../../.. && pwd)/aac-voice-packs}"
  python3 tools/voices/check_packs.py "$VOICES" \
    || { echo "✗ build the packs (tools/voices/build_voices.py), or set AAC_VOICES=none to build without better voices" >&2; exit 1; }
  cp -cR "$VOICES" "$SITE/voices" 2>/dev/null || cp -R "$VOICES" "$SITE/voices"
  # index.json and LICENSES.md keep their names from one catalogue to the next,
  # and the builder stamps every file with one fixed time: give these two this
  # build's own, or rsync's size-and-time check would keep prod's old pointer,
  # to a catalogue its --delete has just removed.
  touch "$SITE/voices/index.json" "$SITE/voices/LICENSES.md"
fi
# The sentence helper, downloaded only when the person asks (ai_helper.rs):
# Google's LiteRT-LM web runtime, vendored and pinned like Moonshine, and the
# model's parts, built outside git by tools/ai/build_ai.py, under ai/ (cloned,
# not copied, on APFS), once tools/ai/check_packs.py has matched them to the
# committed catalogue. A build without them must say so (AAC_AI=none).
rm -rf "$SITE/ai"
if [ "${AAC_AI:-}" = "none" ]; then
  echo "▸ AAC_AI=none: no sentence helper in this build"
else
  bash third_party/litert-lm/vendor.sh "$SITE" "$CACHE"
  AI="${AAC_AI_DIR:-$(cd ../../.. && pwd)/aac-ai-packs}"
  python3 tools/ai/check_packs.py "$AI" \
    || { echo "✗ build the model parts (tools/ai/build_ai.py), or set AAC_AI=none to build without the sentence helper" >&2; exit 1; }
  cp -cR "$AI" "$SITE/ai" 2>/dev/null || cp -R "$AI" "$SITE/ai"
  touch "$SITE/ai/index.json" "$SITE/ai/LICENSES.md"
fi
# The listener, downloaded only when the person asks (listen.rs):
# onnxruntime-web, vendored and pinned like LiteRT-LM, and the model's files,
# built outside git by tools/asr/build_asr.py, under asr/ (cloned, not
# copied, on APFS), once tools/asr/check_packs.py has matched them to the
# committed catalogue. A build without them must say so (AAC_ASR=none).
rm -rf "$SITE/asr"
if [ "${AAC_ASR:-}" = "none" ]; then
  echo "▸ AAC_ASR=none: no listener in this build"
else
  bash third_party/onnxruntime-web/vendor.sh "$SITE" "$CACHE"
  ASR="${AAC_ASR_DIR:-$(cd ../../.. && pwd)/aac-asr-packs}"
  python3 tools/asr/check_packs.py "$ASR" \
    || { echo "✗ build the listener's files (tools/asr/build_asr.py), or set AAC_ASR=none to build without the listener" >&2; exit 1; }
  cp -cR "$ASR" "$SITE/asr" 2>/dev/null || cp -R "$ASR" "$SITE/asr"
  touch "$SITE/asr/index.json" "$SITE/asr/LICENSES.md"
fi
# First letters, downloaded only when the person asks (abbrev.rs): it runs
# on the listener's onnxruntime-web (vendored above, or here when the
# listener is not in this build), with its own worker and Hugging Face's
# tokenizer library, vendored and pinned like it, and the model's files,
# built outside git by tools/ae/build_ae.py, under ae/ (cloned, not copied,
# on APFS), once tools/ae/check_packs.py has matched them to the committed
# catalogue. A build without them must say so (AAC_AE=none).
rm -rf "$SITE/ae"
if [ "${AAC_AE:-}" = "none" ]; then
  echo "▸ AAC_AE=none: no first letters in this build"
else
  [ "${AAC_ASR:-}" = "none" ] && bash third_party/onnxruntime-web/vendor.sh "$SITE" "$CACHE"
  bash third_party/hf-tokenizers/vendor.sh "$SITE" "$CACHE"
  AE="${AAC_AE_DIR:-$(cd ../../.. && pwd)/aac-ae-packs}"
  python3 tools/ae/check_packs.py "$AE" \
    || { echo "✗ build first letters' files (tools/ae/build_ae.py), or set AAC_AE=none to build without first letters" >&2; exit 1; }
  cp -cR "$AE" "$SITE/ae" 2>/dev/null || cp -R "$AE" "$SITE/ae"
  touch "$SITE/ae/index.json" "$SITE/ae/LICENSES.md"
fi
# The loaders of the sentence helper, the listener and first letters must
# never reach another site.
AI_SNIP="$(grep -rl 'ensure_engine' "$SITE/pkg/snippets" || true)"
[ -n "$AI_SNIP" ] || { echo "✗ the sentence helper's snippet is not in pkg/snippets" >&2; exit 1; }
if grep -nE 'https?://' $AI_SNIP; then echo "✗ the sentence helper's snippet names another site" >&2; exit 1; fi
LISTEN_SNIP="$(grep -rl 'listen_once' "$SITE/pkg/snippets" || true)"
[ -n "$LISTEN_SNIP" ] || { echo "✗ the listener's snippet is not in pkg/snippets" >&2; exit 1; }
if grep -nE 'https?://' $LISTEN_SNIP; then echo "✗ the listener's snippet names another site" >&2; exit 1; fi
AE_SNIP="$(grep -rl '__aacLettersEngine' "$SITE/pkg/snippets" || true)"
[ -n "$AE_SNIP" ] || { echo "✗ first letters' snippet is not in pkg/snippets" >&2; exit 1; }
if grep -nE 'https?://' $AE_SNIP; then echo "✗ first letters' snippet names another site" >&2; exit 1; fi
SNIP="$(grep -rl 'initialize_face_landmarker' "$SITE/pkg/snippets" || true)"
[ -n "$SNIP" ] || { echo "✗ eye-tracking snippet not found in pkg/snippets" >&2; exit 1; }
if grep -nE 'https?://' $SNIP; then echo "✗ eye-tracking snippet loads from a third party" >&2; exit 1; fi

echo "▸ bundling PWA assets and the service worker"
cp crates/aac-web/static/manifest.json "$SITE/manifest.json"
# Precache: the shell, the manifest, every file in pkg/ (including wasm-bindgen
# snippets such as the eye-tracking loader), the icons, and every symbol sprite
# the prerendered board draws (the default set and the sets it falls back to),
# so symbols show offline from the first visit, and their LICENSES.md. Other sprites are cached by the
# worker the first time they are drawn.
PRECACHE=("/" "/manifest.json")
while IFS= read -r f; do PRECACHE+=("/${f#"$SITE"/}"); done < <(find "$SITE/pkg" "$SITE/icons" -type f | LC_ALL=C sort)
DRAWN="$(grep -oE '/symbols/[a-z]+\.[0-9a-f]{12}\.svg' "$SITE/index.html" | LC_ALL=C sort -u || true)"
[ -n "$DRAWN" ] || { echo "✗ the prerendered board draws no symbols" >&2; exit 1; }
for u in $DRAWN; do
  [ -f "$SITE$u" ] || { echo "✗ index.html draws $u, which the build does not ship" >&2; exit 1; }
  PRECACHE+=("$u")
done
# Settings links the symbols' licences; the worker serves it offline too.
[ -f "$SITE/symbols/LICENSES.md" ] || { echo "✗ the build does not ship symbols/LICENSES.md" >&2; exit 1; }
PRECACHE+=("/symbols/LICENSES.md")
SYMBOL_FILES="[$(cd "$SITE/symbols" && printf '"%s",' *.svg | sed 's/,$//')]"
VERSION="$(for u in "${PRECACHE[@]}"; do
  if [ "$u" = "/" ]; then f="$SITE/index.html"; else f="$SITE$u"; fi
  printf '%s %s\n' "$u" "$(shasum -a 256 "$f" | cut -c1-64)"
done | shasum -a 256 | cut -c1-12)"
LIST="[$(printf '"%s",' "${PRECACHE[@]}" | sed 's/,$//')]"
# The worker keeps only the current vendor directory in its vendor cache.
sed -e "s#__VERSION__#$VERSION#" -e "s#__PRECACHE_URLS__#$LIST#" -e "s#__VENDOR_DIRS__#[\"$MP_DIR/\"]#" \
    -e "s#__SYMBOL_FILES__#$SYMBOL_FILES#" \
  crates/aac-web/static/sw.js > "$SITE/sw.js"
grep -q "__" "$SITE/sw.js" && grep -nE "__[A-Z_]+__" "$SITE/sw.js" && { echo "✗ sw.js has an unfilled placeholder" >&2; exit 1; }

echo "✓ self-contained dist ready at $SITE/ (service worker $VERSION, ${#PRECACHE[@]} files precached)"
ls -1 "$SITE" "$SITE/pkg"