#!/bin/sh
# Installs and runs the iris `bench` build on this checkout's own emulator
# (per this-machine-android's per-checkout-AVD rule; `emu serial` picks it)
# and prints the report -- the iris half of `app/transcript-bench.sh`'s
# job. No coordinates: the button is found by its accessibility label
# through `ui-trace`, per AGENTS.md's "Driving the UI".
#
# Usage: ./run-bench.sh [--apk PATH]
#   Defaults to this checkout's own release APK
#   (android-project/app/build/outputs/apk/release/app-release.apk) if it
#   exists, else the
#   debug one -- build one first with ./build-apk.sh.
set -eu
cd "$(dirname "$0")"

APK=""
while [ $# -gt 0 ]; do
    case "$1" in
        --apk) APK="$2"; shift 2 ;;
        *) echo "run-bench.sh: unknown argument: $1" >&2; exit 1 ;;
    esac
done
if [ -z "$APK" ]; then
    if [ -f android-project/app/build/outputs/apk/release/app-release.apk ]; then
        APK=android-project/app/build/outputs/apk/release/app-release.apk
    else
        APK=android-project/app/build/outputs/apk/debug/app-debug.apk
    fi
fi
if [ ! -f "$APK" ]; then
    echo "run-bench.sh: no APK at $APK -- run ./build-apk.sh first" >&2
    exit 1
fi

SERIAL=$(emu serial)
PKG=$(aapt2 dump badging "$APK" 2>/dev/null | sed -n "s/^package: name='\\([^']*\\)'.*/\\1/p")
if [ -z "$PKG" ]; then
    BUILD_TOOLS=$(ls -d "$HOME"/Android/Sdk/build-tools/*/ | sort -V | tail -1)
    PKG=$("${BUILD_TOOLS}aapt2" dump badging "$APK" | sed -n "s/^package: name='\\([^']*\\)'.*/\\1/p")
fi

echo "run-bench.sh: installing $APK ($PKG) on $SERIAL"
adb -s "$SERIAL" install -r "$APK" >/dev/null
adb -s "$SERIAL" shell am force-stop "$PKG"
adb -s "$SERIAL" logcat -c
adb -s "$SERIAL" shell am start -n "$PKG/dev.iris.android.demo.MainActivity" >/dev/null

ui-trace record -s "$SERIAL" -d 3000 --do "tap 'Run benchmark'" -o /tmp/run-bench-tap.txt >/dev/null

# Which adapter drew, before any number is printed. The emulator is a GLES
# machine -- its guest has no hardware Vulkan (docs/RUST.md, "What the
# emulator gives a GPU app") -- so iris's runtime fallback lands on `Gl`,
# and `Gl (... virgl ...)` is the host's real GPU while `Gl (...
# SwiftShader ...)` is the CPU. Those two produce frame times an order of
# magnitude apart and are otherwise indistinguishable in this report, so
# the line is printed rather than left in logcat for somebody to think of.
ADAPTER=$(adb -s "$SERIAL" logcat -d -s iris-android-app:I 2>/dev/null \
    | sed -n 's/.*\(iris renderer: .*\)/\1/p' | tail -1)
if [ -n "$ADAPTER" ]; then
    echo "run-bench.sh: $ADAPTER"
else
    echo "run-bench.sh: no 'iris renderer:' line in logcat -- cannot say what drew this run" >&2
fi

# Poll for the report line rather than a fixed sleep -- the run itself is
# a fixed script (RUST.md's "Benchmark v2": 16 flings, a 20s streaming
# phase, ~61s of typing, 10s of keyboard toggles, roughly 2.5 minutes end
# to end) but device speed varies. 260s cap rather than v1's 90s -- v2 is
# a longer script than v1's swipe-loop-only run.
# The report's own first line, not the bare "iris bench report:" prefix:
# `copy_report` logs that prefix too ("nothing to copy -- run the benchmark
# first", which the app emits at startup), so polling for the prefix
# returned instantly and the script printed a report that was never run.
REPORT_LINE="iris bench report: iris bench report"
i=0
while [ "$i" -lt 260 ]; do
    LINE=$(adb -s "$SERIAL" logcat -d -s iris-android-app:I 2>/dev/null | grep "$REPORT_LINE" || true)
    if [ -n "$LINE" ]; then
        break
    fi
    i=$((i + 1))
    sleep 1
done
if [ -z "$LINE" ]; then
    echo "run-bench.sh: no report after 260s -- check logcat by hand" >&2
    exit 1
fi
# -A 60 rather than v1's -A 6 -- v2's report has a per-phase block (four
# phases, four lines each) on top of the frames/bench sections v1 had.
adb -s "$SERIAL" logcat -d -s iris-android-app:I | grep -A 60 "$REPORT_LINE"