CoopAllTheThings/tests/audio_loopback_test.cpp

// Integration test for WASAPI process-loopback capture (the audio mirror's fallback
// backend). Spawns coop_tone.exe rendering a sine wave at several source formats and
// verifies non-silent audio actually arrives for each. Loopback captures the game's audio
// *post-mix* at the device endpoint format, so it is format-agnostic by construction --
// whatever rate/channels the source renders, the captured audio is correct at the device
// rate. This test confirms that for the common source formats. Exits 0 on pass, 1 on fail.
//
// Requires a working default render endpoint; on a headless machine it reports SKIP and
// exits 0.

#include <cstdio>
#include <string>
#include <vector>

#include <windows.h>

#include <audioclient.h>
#include <mmdeviceapi.h>
#include <mmreg.h>

#include "audio/process_loopback_capture.hpp"

using namespace coop;

namespace {

// Directory of this test executable (coop_tone.exe is built alongside it).
std::wstring exe_dir()
{
	wchar_t path[MAX_PATH] = {};
	GetModuleFileNameW(nullptr, path, MAX_PATH);
	std::wstring s(path);
	const size_t slash = s.find_last_of(L"\\/");
	return slash == std::wstring::npos ? L"." : s.substr(0, slash);
}

// Read from `pipe` until `token` appears or `timeout_ms` elapses (echoing to stdout).
bool wait_for_token(HANDLE pipe, const char* token, DWORD timeout_ms)
{
	std::string acc;
	const DWORD end = GetTickCount() + timeout_ms;
	while (GetTickCount() < end) {
		DWORD avail = 0;
		if (PeekNamedPipe(pipe, nullptr, 0, nullptr, &avail, nullptr) && avail > 0) {
			char buf[256];
			DWORD read = 0;
			if (ReadFile(pipe, buf, sizeof(buf) - 1, &read, nullptr) && read > 0) {
				acc.append(buf, read);
				std::fwrite(buf, 1, read, stdout);
				if (acc.find(token) != std::string::npos) {
					return true;
				}
				continue;
			}
		}
		Sleep(20);
	}
	return false;
}

// Spawn coop_tone with `tone_args` and capture its audio via process loopback for ~1.5 s.
// Returns true if enough non-silent audio arrived (i.e. loopback handled this source
// format correctly). `endpoint_fmt` is the device format loopback renders into.
bool capture_one(const WAVEFORMATEX* endpoint_fmt, const std::wstring& tone_args, const char* label)
{
	std::printf("--- %s ---\n", label);
	HANDLE read_pipe = nullptr;
	HANDLE write_pipe = nullptr;
	SECURITY_ATTRIBUTES sa = {sizeof(sa), nullptr, TRUE};
	if (!CreatePipe(&read_pipe, &write_pipe, &sa, 0)) {
		std::printf("FAIL: CreatePipe\n");
		return false;
	}
	SetHandleInformation(read_pipe, HANDLE_FLAG_INHERIT, 0);

	std::wstring cmd = L"\"" + exe_dir() + L"\\coop_tone.exe\" " + tone_args;
	STARTUPINFOW si = {};
	si.cb = sizeof(si);
	si.dwFlags = STARTF_USESTDHANDLES;
	si.hStdOutput = write_pipe;
	si.hStdError = write_pipe;
	PROCESS_INFORMATION pi = {};
	std::vector<wchar_t> cmd_buf(cmd.begin(), cmd.end());
	cmd_buf.push_back(L'\0');
	if (!CreateProcessW(nullptr, cmd_buf.data(), nullptr, nullptr, TRUE, 0, nullptr, nullptr, &si, &pi)) {
		std::printf("FAIL: CreateProcess(coop_tone) err=%lu\n", GetLastError());
		CloseHandle(read_pipe);
		CloseHandle(write_pipe);
		return false;
	}
	CloseHandle(write_pipe); // keep only the read end

	bool ok = false;
	if (!wait_for_token(read_pipe, "TONE_RENDERING", 5000)) {
		std::printf("FAIL: tone generator never started rendering\n");
	} else {
		ProcessLoopbackCapture capture;
		const bool started = capture.start(pi.dwProcessId, endpoint_fmt, nullptr);
		std::printf("Capture start: %s, targeting pid %lu\n", started ? "ok" : "FAILED", pi.dwProcessId);
		Sleep(1500);

		const auto nonsilent = capture.nonsilent_frames();
		capture.stop();

		// Expect at least ~0.2 s of non-silent audio for a 1.5 s capture.
		const unsigned long long need = endpoint_fmt->nSamplesPerSec / 5;
		std::printf("Non-silent frames: %llu (need >= %llu)\n", static_cast<unsigned long long>(nonsilent), need);
		ok = nonsilent >= need;
		std::printf("%s\n", ok ? "PASS" : "FAIL: too few non-silent frames");
	}

	TerminateProcess(pi.hProcess, 0);
	WaitForSingleObject(pi.hProcess, 2000);
	CloseHandle(pi.hThread);
	CloseHandle(pi.hProcess);
	CloseHandle(read_pipe);
	return ok;
}

} // namespace

int main()
{
	if (FAILED(CoInitializeEx(nullptr, COINIT_MULTITHREADED))) {
		std::printf("FAIL: CoInitializeEx\n");
		return 1;
	}

	WAVEFORMATEX* fmt = default_render_format();
	if (!fmt) {
		std::printf("SKIP: no default render endpoint (no audio device?)\n");
		CoUninitialize();
		return 0;
	}
	std::printf("Endpoint format: %u Hz, %u ch, %u-bit\n", fmt->nSamplesPerSec, fmt->nChannels, fmt->wBitsPerSample);

	// Each case spawns coop_tone at a different source format; loopback should capture all
	// of them correctly because it captures post-mix at the device endpoint format.
	// Args: <seconds> <freq> <rate> <channels> <bits> <float|pcm>. ~8 s outlives capture.
	struct Case {
		std::wstring args;
		const char* label;
	};
	const Case cases[] = {
	    {L"8 440", "device default format"},
	    {L"8 440 44100 2 16 pcm", "44100 Hz stereo 16-bit PCM"},
	    {L"8 440 48000 2 32 float", "48000 Hz stereo 32-bit float"},
	    {L"8 660 96000 2 32 float", "96000 Hz stereo 32-bit float"},
	};

	int failures = 0;
	for (const Case& c : cases) {
		if (!capture_one(fmt, c.args, c.label)) {
			++failures;
		}
	}

	CoTaskMemFree(fmt);
	CoUninitialize();
	std::printf(failures == 0 ? "AUDIO LOOPBACK TEST PASS\n" : "AUDIO LOOPBACK TEST FAILED (%d)\n", failures);
	return failures == 0 ? 0 : 1;
}