#!/usr/bin/env bash
#
# Cold-start baseline: installs nothing, measures the app that is already on the device.
#
#   ./tools/measure-startup.sh          # three runs
#   ./tools/measure-startup.sh 5        # five runs
#
# Why `am start -W` rather than a benchmark library: it needs no new module and no instrumented
# test APK, and "time from tap to first frame" is exactly what it reports. What it does *not* do is
# measure anything inside the app — folder open, thumbnail paint and search latency need a
# macrobenchmark module (see docs/PERFORMANCE.md for what is still missing and why).
set -euo pipefail

runs=${1:-3}
package=de.softwareapp_hb.filemanager.debug
component="$package/de.softwareapp_hb.filemanager.MainActivity"

if ! adb shell pm list packages | grep -qx "package:$package"; then
    echo "measure-startup: $package is not installed." >&2
    echo "  ./gradlew :app:assembleDebug && adb install -r app/build/outputs/apk/debug/app-debug.apk" >&2
    exit 2
fi

version=$(adb shell dumpsys package "$package" | sed -n 's/.*versionName=\([^ ]*\).*/\1/p' | head -1)
echo "package $package ($version), $runs cold starts"

# One start that is thrown away. The first launch after an install pays for dexopt and JIT, and
# folding that into a median is how a baseline gets written that nothing can meet.
adb shell am force-stop "$package"
sleep 1
adb shell am start -W -n "$component" >/dev/null
sleep 2

times=$(
    for run in $(seq 1 "$runs"); do
        adb shell am force-stop "$package"
        sleep 1
        adb shell am start -W -n "$component" | sed -n 's/^TotalTime: //p' | tr -d '\r'
    done | sort -n
)

echo "runs (ms): $(echo "$times" | tr '\n' ' ')"
# Median of an odd count; for an even count this takes the lower of the two middle runs, which is
# the honest side to err on when the point is to notice a regression.
echo "$times" | awk '
    { value[NR] = $1 }
    END {
        printf "median: %d ms  (min %d, max %d)\n", value[int((NR + 1) / 2)], value[1], value[NR]
    }
'