webhooker/internal/config/config_test.go

package config_test

import (
	"bytes"
	"log/slog"
	"os"
	"testing"
	"time"

	"github.com/stretchr/testify/assert"
	"github.com/stretchr/testify/require"
	"go.uber.org/fx"
	"go.uber.org/fx/fxtest"
	"sneak.berlin/go/webhooker/internal/config"
	"sneak.berlin/go/webhooker/internal/globals"
	"sneak.berlin/go/webhooker/internal/logger"
)

// Shared subtest names for the env-parsing tables below, which all
// exercise the same three cases against different variables.
const (
	caseUnsetUsesDefault = "unset uses default"
	caseValidValueParsed = "valid value is parsed"
	caseUnparseableFails = "unparseable value fails startup"

	// cidrPrivateV4 is the sample trusted-proxy block the
	// TRUSTED_PROXIES cases are built from.
	cidrPrivateV4 = "10.0.0.0/8"

	// metricsAuthValue is the sample METRICS_PASSWORD the metrics
	// credential cases are built from. It is asserted absent from
	// the startup error, so it must not be a substring of either
	// variable name that error prints.
	metricsAuthValue = "s3cret"
)

func TestEnvironmentConfig(t *testing.T) {
	tests := []struct {
		name        string
		envValue    string
		envVars     map[string]string
		expectError bool
		isDev       bool
		isProd      bool
	}{
		{
			name:   "default is dev",
			isDev:  true,
			isProd: false,
		},
		{
			name:     "explicit dev",
			envValue: "dev",
			isDev:    true,
			isProd:   false,
		},
		{
			name:     "explicit prod",
			envValue: "prod",
			isDev:    false,
			isProd:   true,
		},
		{
			name:        "invalid environment",
			envValue:    "staging",
			expectError: true,
		},
	}

	for _, tt := range tests {
		t.Run(tt.name, func(t *testing.T) {
			// Cannot use t.Parallel() here because t.Setenv
			// is incompatible with parallel subtests.
			if tt.envValue != "" {
				t.Setenv(
					"WEBHOOKER_ENVIRONMENT", tt.envValue,
				)
			} else {
				require.NoError(t, os.Unsetenv(
					"WEBHOOKER_ENVIRONMENT",
				))
			}

			for k, v := range tt.envVars {
				t.Setenv(k, v)
			}

			if tt.expectError {
				testEnvironmentConfigError(t)
			} else {
				testEnvironmentConfigSuccess(
					t, tt.isDev, tt.isProd,
				)
			}
		})
	}
}

func testEnvironmentConfigError(t *testing.T) {
	t.Helper()

	var cfg *config.Config

	app := fx.New(
		fx.NopLogger,
		fx.Provide(
			globals.New,
			logger.New,
			config.New,
		),
		fx.Populate(&cfg),
	)

	assert.Error(t, app.Err())
}

func testEnvironmentConfigSuccess(
	t *testing.T,
	isDev, isProd bool,
) {
	t.Helper()

	var cfg *config.Config

	app := fxtest.New(
		t,
		fx.Provide(
			globals.New,
			logger.New,
			config.New,
		),
		fx.Populate(&cfg),
	)
	require.NoError(t, app.Err())

	app.RequireStart()

	defer app.RequireStop()

	assert.Equal(t, isDev, cfg.IsDev())
	assert.Equal(t, isProd, cfg.IsProd())
}

func TestRetentionSweepInterval(t *testing.T) {
	tests := []struct {
		name        string
		set         bool
		value       string
		expectError bool
		// sentinel, when set, must be wrapped by the startup
		// error; every error case must additionally name the
		// variable in its message.
		sentinel error
		expected time.Duration
	}{
		{
			name:     caseUnsetUsesDefault,
			set:      false,
			expected: time.Hour,
		},
		{
			name:     caseValidValueParsed,
			set:      true,
			value:    "15m",
			expected: 15 * time.Minute,
		},
		{
			name:        caseUnparseableFails,
			set:         true,
			value:       "not-a-duration",
			expectError: true,
		},
		{
			// A non-positive period panics the ticker in the
			// reaper and archive-sweeper goroutines, long after
			// startup has reported success, so it has to fail
			// here instead.
			name:        "zero fails startup",
			set:         true,
			value:       "0s",
			expectError: true,
			sentinel:    config.ErrNonPositiveValue,
		},
		{
			name:        "negative fails startup",
			set:         true,
			value:       "-1h",
			expectError: true,
			sentinel:    config.ErrNonPositiveValue,
		},
	}

	for _, tt := range tests {
		t.Run(tt.name, func(t *testing.T) {
			// Cannot use t.Parallel() here because t.Setenv
			// is incompatible with parallel subtests.
			t.Setenv("WEBHOOKER_ENVIRONMENT", "dev")

			if tt.set {
				t.Setenv("RETENTION_SWEEP_INTERVAL", tt.value)
			} else {
				require.NoError(t, os.Unsetenv(
					"RETENTION_SWEEP_INTERVAL",
				))
			}

			if tt.expectError {
				expectStartupErrorFor(
					t, "RETENTION_SWEEP_INTERVAL", tt.sentinel,
				)
			} else {
				testRetentionSweepIntervalSuccess(t, tt.expected)
			}
		})
	}
}

// startupError builds the app config.New belongs to and returns
// the error fx reports, which is non-nil whenever an environment
// value is set but invalid.
func startupError(t *testing.T) error {
	t.Helper()

	var cfg *config.Config

	app := fx.New(
		fx.NopLogger,
		fx.Provide(
			globals.New,
			logger.New,
			config.New,
		),
		fx.Populate(&cfg),
	)

	return app.Err()
}

// expectStartupError asserts that fx refuses to build the app,
// which is what a set-but-invalid environment value must cause.
func expectStartupError(t *testing.T) {
	t.Helper()

	assert.Error(t, startupError(t))
}

// expectStartupErrorFor asserts that startup fails, that the error
// names the offending variable so an operator can find it, and,
// when sentinel is non-nil, that it wraps that sentinel.
func expectStartupErrorFor(
	t *testing.T,
	key string,
	sentinel error,
) {
	t.Helper()

	err := startupError(t)
	require.ErrorContains(t, err, key)

	if sentinel != nil {
		require.ErrorIs(t, err, sentinel)
	}
}

func testRetentionSweepIntervalSuccess(
	t *testing.T,
	expected time.Duration,
) {
	t.Helper()

	var cfg *config.Config

	app := fxtest.New(
		t,
		fx.Provide(
			globals.New,
			logger.New,
			config.New,
		),
		fx.Populate(&cfg),
	)
	require.NoError(t, app.Err())

	app.RequireStart()

	defer app.RequireStop()

	assert.Equal(t, expected, cfg.RetentionSweepInterval)
}

func TestSessionIdleTimeout(t *testing.T) {
	tests := []struct {
		name        string
		set         bool
		value       string
		expectError bool
		expected    time.Duration
	}{
		{
			name:     caseUnsetUsesDefault,
			set:      false,
			expected: 24 * time.Hour,
		},
		{
			name:     caseValidValueParsed,
			set:      true,
			value:    "30m",
			expected: 30 * time.Minute,
		},
		{
			name:        caseUnparseableFails,
			set:         true,
			value:       "not-a-duration",
			expectError: true,
		},
		{
			// Non-positive is "idle expiry disabled" for this
			// variable, not a configuration error: unlike
			// RETENTION_SWEEP_INTERVAL it never becomes a ticker
			// period.
			name:     "zero disables idle expiry",
			set:      true,
			value:    "0s",
			expected: 0,
		},
		{
			name:     "negative disables idle expiry",
			set:      true,
			value:    "-1h",
			expected: -time.Hour,
		},
	}

	for _, tt := range tests {
		t.Run(tt.name, func(t *testing.T) {
			// Cannot use t.Parallel() here because t.Setenv
			// is incompatible with parallel subtests.
			t.Setenv("WEBHOOKER_ENVIRONMENT", "dev")

			if tt.set {
				t.Setenv("SESSION_IDLE_TIMEOUT", tt.value)
			} else {
				require.NoError(t, os.Unsetenv(
					"SESSION_IDLE_TIMEOUT",
				))
			}

			if tt.expectError {
				expectStartupError(t)
			} else {
				testSessionIdleTimeoutSuccess(t, tt.expected)
			}
		})
	}
}

func testSessionIdleTimeoutSuccess(
	t *testing.T,
	expected time.Duration,
) {
	t.Helper()

	var cfg *config.Config

	app := fxtest.New(
		t,
		fx.Provide(
			globals.New,
			logger.New,
			config.New,
		),
		fx.Populate(&cfg),
	)
	require.NoError(t, app.Err())

	app.RequireStart()

	defer app.RequireStop()

	assert.Equal(t, expected, cfg.SessionIdleTimeout)
}

func TestDefaultDataDir(t *testing.T) {
	for _, env := range []string{"", "dev", "prod"} {
		name := env
		if name == "" {
			name = "unset"
		}

		t.Run("env="+name, func(t *testing.T) {
			// Cannot use t.Parallel() here because t.Setenv
			// is incompatible with parallel subtests.
			if env != "" {
				t.Setenv("WEBHOOKER_ENVIRONMENT", env)
			} else {
				require.NoError(t, os.Unsetenv(
					"WEBHOOKER_ENVIRONMENT",
				))
			}

			require.NoError(t, os.Unsetenv("DATA_DIR"))

			var cfg *config.Config

			app := fxtest.New(
				t,
				fx.Provide(
					globals.New,
					logger.New,
					config.New,
				),
				fx.Populate(&cfg),
			)
			require.NoError(t, app.Err())

			app.RequireStart()

			defer app.RequireStop()

			assert.Equal(
				t, "/var/lib/webhooker", cfg.DataDir,
			)
		})
	}
}

// TestDataDirHelper pins the exported resolver against the value
// Config carries. The entry point takes the DATA_DIR lock through the
// helper before the fx graph exists, so the two disagreeing would mean
// locking one directory and writing to another.
func TestDataDirHelper(t *testing.T) {
	for _, set := range []string{"", "/tmp/webhooker-datadir-helper"} {
		name := "set"
		if set == "" {
			name = "unset"
		}

		t.Run(name, func(t *testing.T) {
			// Cannot use t.Parallel() here because t.Setenv
			// is incompatible with parallel subtests.
			if set == "" {
				require.NoError(t, os.Unsetenv("DATA_DIR"))
			} else {
				t.Setenv("DATA_DIR", set)
			}

			expected := set
			if expected == "" {
				expected = config.DefaultDataDir
			}

			assert.Equal(t, expected, config.DataDir())
		})
	}
}

func TestReceiverRateLimit(t *testing.T) {
	tests := []struct {
		name        string
		set         bool
		value       string
		expectError bool
		// sentinel, when set, must be wrapped by the startup
		// error; every error case must additionally name the
		// variable in its message.
		sentinel error
		expected int
	}{
		{
			name:     caseUnsetUsesDefault,
			set:      false,
			expected: 120,
		},
		{
			name:     caseValidValueParsed,
			set:      true,
			value:    "30",
			expected: 30,
		},
		{
			name:        caseUnparseableFails,
			set:         true,
			value:       "not-a-number",
			expectError: true,
		},
		{
			name:        "zero fails startup",
			set:         true,
			value:       "0",
			expectError: true,
			sentinel:    config.ErrNonPositiveValue,
		},
		{
			name:        "negative fails startup",
			set:         true,
			value:       "-5",
			expectError: true,
			sentinel:    config.ErrNonPositiveValue,
		},
	}

	for _, tt := range tests {
		t.Run(tt.name, func(t *testing.T) {
			// Cannot use t.Parallel() here because t.Setenv
			// is incompatible with parallel subtests.
			t.Setenv("WEBHOOKER_ENVIRONMENT", "dev")

			if tt.set {
				t.Setenv("RECEIVER_RATE_LIMIT", tt.value)
			} else {
				require.NoError(t, os.Unsetenv(
					"RECEIVER_RATE_LIMIT",
				))
			}

			if tt.expectError {
				expectStartupErrorFor(
					t, "RECEIVER_RATE_LIMIT", tt.sentinel,
				)
			} else {
				testReceiverRateLimitSuccess(t, tt.expected)
			}
		})
	}
}

func testReceiverRateLimitSuccess(
	t *testing.T,
	expected int,
) {
	t.Helper()

	var cfg *config.Config

	app := fxtest.New(
		t,
		fx.Provide(
			globals.New,
			logger.New,
			config.New,
		),
		fx.Populate(&cfg),
	)
	require.NoError(t, app.Err())

	app.RequireStart()

	defer app.RequireStop()

	assert.Equal(t, expected, cfg.ReceiverRateLimit)
}

func TestTrustedProxies(t *testing.T) {
	tests := []struct {
		name        string
		set         bool
		value       string
		expectError bool
		expected    []string
	}{
		{
			// The default must be "trust nobody": an empty list
			// means forwarded headers are ignored, never that
			// every peer may speak for the client.
			name:     caseUnsetUsesDefault,
			set:      false,
			expected: []string{},
		},
		{
			name:     "blank value trusts nothing",
			set:      true,
			value:    "  ",
			expected: []string{},
		},
		{
			name:  caseValidValueParsed,
			set:   true,
			value: cidrPrivateV4 + ", 192.168.1.7 ,2001:db8::/32",
			expected: []string{
				cidrPrivateV4, "192.168.1.7/32", "2001:db8::/32",
			},
		},
		{
			name:     "host bits are masked off",
			set:      true,
			value:    "10.1.2.3/8",
			expected: []string{cidrPrivateV4},
		},
		{
			// Peer addresses are unmapped before they are
			// matched, so an IPv4-mapped prefix kept in that
			// form could never match anything.
			name:     "IPv4-mapped prefix is unmapped",
			set:      true,
			value:    "::ffff:10.0.0.0/104",
			expected: []string{cidrPrivateV4},
		},
		{
			name:        caseUnparseableFails,
			set:         true,
			value:       cidrPrivateV4 + ",not-an-address",
			expectError: true,
		},
		{
			name:        "out-of-range prefix length fails startup",
			set:         true,
			value:       "10.0.0.0/33",
			expectError: true,
		},
	}

	for _, tt := range tests {
		t.Run(tt.name, func(t *testing.T) {
			// Cannot use t.Parallel() here because t.Setenv
			// is incompatible with parallel subtests.
			t.Setenv("WEBHOOKER_ENVIRONMENT", "dev")

			if tt.set {
				t.Setenv("TRUSTED_PROXIES", tt.value)
			} else {
				require.NoError(t, os.Unsetenv("TRUSTED_PROXIES"))
			}

			if tt.expectError {
				expectStartupErrorFor(
					t, "TRUSTED_PROXIES", config.ErrInvalidCIDR,
				)
			} else {
				testTrustedProxiesSuccess(t, tt.expected)
			}
		})
	}
}

func testTrustedProxiesSuccess(
	t *testing.T,
	expected []string,
) {
	t.Helper()

	var cfg *config.Config

	app := fxtest.New(
		t,
		fx.Provide(
			globals.New,
			logger.New,
			config.New,
		),
		fx.Populate(&cfg),
	)
	require.NoError(t, app.Err())

	app.RequireStart()

	defer app.RequireStop()

	got := make([]string, 0, len(cfg.TrustedProxies))
	for _, prefix := range cfg.TrustedProxies {
		got = append(got, prefix.String())
	}

	assert.Equal(t, expected, got)
}

// TestSharedRateLimitBucketWarning covers the startup warning that
// tells an operator a deployment behind a reverse proxy shares one
// rate-limit bucket between every client, which turns the receiver
// limits into service-wide ceilings and collapses login failure
// counting. It must fire whenever TRUSTED_PROXIES is empty,
// in any environment: WEBHOOKER_ENVIRONMENT defaults to dev, so gating
// on it would silence the warning for exactly the operator who never
// configured the deployment. It stays quiet once proxies are named.
func TestSharedRateLimitBucketWarning(t *testing.T) {
	tests := []struct {
		name           string
		environment    string
		trustedProxies string
		expectWarning  bool
	}{
		{
			name:          "prod without trusted proxies warns",
			environment:   config.EnvironmentProd,
			expectWarning: true,
		},
		{
			name:           "prod with trusted proxies is quiet",
			environment:    config.EnvironmentProd,
			trustedProxies: cidrPrivateV4,
			expectWarning:  false,
		},
		{
			// The default environment. An internet-exposed
			// deployment whose operator never set
			// WEBHOOKER_ENVIRONMENT lands here and has exactly
			// the exposure the warning announces.
			name:          "dev without trusted proxies warns",
			environment:   config.EnvironmentDev,
			expectWarning: true,
		},
		{
			name:           "dev with trusted proxies is quiet",
			environment:    config.EnvironmentDev,
			trustedProxies: cidrPrivateV4,
			expectWarning:  false,
		},
	}

	for _, tt := range tests {
		t.Run(tt.name, func(t *testing.T) {
			// Cannot use t.Parallel() here because t.Setenv
			// is incompatible with parallel subtests.
			t.Setenv("WEBHOOKER_ENVIRONMENT", tt.environment)

			if tt.trustedProxies == "" {
				require.NoError(
					t, os.Unsetenv("TRUSTED_PROXIES"),
				)
			} else {
				t.Setenv("TRUSTED_PROXIES", tt.trustedProxies)
			}

			var buf bytes.Buffer

			log := slog.New(slog.NewJSONHandler(
				&buf, &slog.HandlerOptions{
					Level: slog.LevelDebug,
				},
			))

			require.NoError(
				t,
				config.WarnSharedRateLimitBucketForTest(log),
			)

			if !tt.expectWarning {
				assert.Empty(t, buf.String())

				return
			}

			logged := buf.String()

			assert.Contains(t, logged, `"level":"WARN"`)
			assert.Contains(t, logged, "TRUSTED_PROXIES")
			assert.Contains(t, logged, "share one bucket")
			assert.Contains(
				t, logged, "throttle every other client's failed logins",
			)
			// The warning must not claim a lockout the login
			// endpoint no longer permits: credentials are verified
			// before any budget is spent.
			assert.Contains(
				t, logged, "a correct password still gets in",
			)
			// The text must stay accurate for a developer with
			// nothing in front of the process, where an empty
			// list costs nothing.
			assert.Contains(
				t, logged, "nothing proxying to this process",
			)
		})
	}
}

// metricsEnv describes what one subtest below puts in the
// environment for a single METRICS_ variable. A variable that is
// set to the empty string and one that is not set at all are
// distinct inputs here, because the reported bug arrived through
// the first of them.
type metricsEnv struct {
	set   bool
	value string
}

// unset leaves the variable out of the environment entirely.
func unset() metricsEnv {
	return metricsEnv{set: false, value: ""}
}

// setTo sets the variable, including to the empty string.
func setTo(value string) metricsEnv {
	return metricsEnv{set: true, value: value}
}

// metricsAuthCase is one row of the table in TestMetricsAuthConfig,
// named so the table can live in its own function and keep the test
// itself short.
type metricsAuthCase struct {
	name        string
	username    metricsEnv
	password    metricsEnv
	expectError bool
	expectAuth  bool
}

// metricsAuthCases enumerates every combination of the two
// credentials, counting "set to the empty string" and "not set at
// all" as separate inputs on each side.
func metricsAuthCases() []metricsAuthCase {
	return []metricsAuthCase{
		{
			name:     "both unset leaves metrics unmounted",
			username: unset(),
			password: unset(),
		},
		{
			name:     "both empty leaves metrics unmounted",
			username: setTo(""),
			password: setTo(""),
		},
		{
			name:       "both set enables metrics auth",
			username:   setTo("metrics"),
			password:   setTo(metricsAuthValue),
			expectAuth: true,
		},
		{
			name:        "username with unset password fails",
			username:    setTo("metrics"),
			password:    unset(),
			expectError: true,
		},
		{
			name:        "username with empty password fails",
			username:    setTo("metrics"),
			password:    setTo(""),
			expectError: true,
		},
		{
			name:        "password with unset username fails",
			username:    unset(),
			password:    setTo(metricsAuthValue),
			expectError: true,
		},
		{
			name:        "password with empty username fails",
			username:    setTo(""),
			password:    setTo(metricsAuthValue),
			expectError: true,
		},
	}
}

// TestMetricsAuthConfig covers every combination of METRICS_USERNAME
// and METRICS_PASSWORD. Either both carry a value, in which case
// /metrics is served behind basic auth, or neither does, in which
// case the route is never mounted. One without the other is a
// startup error rather than a fallback: mounting on the username
// alone published /metrics behind a credential map that accepted an
// empty password, which is the defect this test exists to pin. See
// https://git.eeqj.de/sneak/webhooker/issues/205.
func TestMetricsAuthConfig(t *testing.T) {
	for _, tt := range metricsAuthCases() {
		t.Run(tt.name, func(t *testing.T) {
			// Cannot use t.Parallel() here because t.Setenv
			// is incompatible with parallel subtests.
			if tt.username.set {
				t.Setenv("METRICS_USERNAME", tt.username.value)
			} else {
				require.NoError(
					t, os.Unsetenv("METRICS_USERNAME"),
				)
			}

			if tt.password.set {
				t.Setenv("METRICS_PASSWORD", tt.password.value)
			} else {
				require.NoError(
					t, os.Unsetenv("METRICS_PASSWORD"),
				)
			}

			if tt.expectError {
				assertMetricsAuthRejected(t)

				return
			}

			assertMetricsAuthAccepted(t, tt.expectAuth)
		})
	}
}

// assertMetricsAuthRejected requires that fx refused to build the
// graph, that the failure is ErrIncompleteMetricsAuth, and that the
// operator is told both variable names — the point of failing here
// rather than degrading is that the message says what to fix.
func assertMetricsAuthRejected(t *testing.T) {
	t.Helper()

	var cfg *config.Config

	app := fx.New(
		fx.NopLogger,
		fx.Provide(globals.New, logger.New, config.New),
		fx.Populate(&cfg),
	)

	err := app.Err()
	require.Error(t, err)
	require.ErrorIs(t, err, config.ErrIncompleteMetricsAuth)
	assert.Contains(t, err.Error(), "METRICS_USERNAME")
	assert.Contains(t, err.Error(), "METRICS_PASSWORD")
	// The password is a secret and must not reach a startup error.
	assert.NotContains(t, err.Error(), metricsAuthValue)
}

// assertMetricsAuthAccepted requires that startup succeeded and that
// MetricsAuthEnabled — the single value the /metrics mount and the
// startup log both read — reports what the environment asked for.
func assertMetricsAuthAccepted(t *testing.T, expectAuth bool) {
	t.Helper()

	var cfg *config.Config

	app := fxtest.New(
		t,
		fx.Provide(globals.New, logger.New, config.New),
		fx.Populate(&cfg),
	)
	require.NoError(t, app.Err())

	app.RequireStart()

	defer app.RequireStop()

	assert.Equal(t, expectAuth, cfg.MetricsAuthEnabled())
}