21 Commits

Author SHA1 Message Date
clawbot
ae092dad8c fix: proper iterative resolution for A/NS lookups (closes #24)
All checks were successful
check / check (push) Successful in 33s
2026-03-01 07:51:37 -08:00
02ca796085 Merge pull request 'Simplify CI: docker build instead of manual toolchain setup' (#38) from fix/simplify-ci into main
Some checks failed
check / check (push) Failing after 40s
Reviewed-on: #38
2026-02-28 13:04:31 +01:00
clawbot
2e3526986f simplify CI to docker build, pin all image refs by SHA
Some checks failed
check / check (push) Failing after 1m23s
- Replace convoluted CI workflow (setup-go, install golangci-lint, install
  goimports, make check) with simple 'docker build .' per repo policy
- Pin Docker base images by SHA256 hash instead of mutable tags
- Pin golangci-lint and goimports by commit hash instead of @latest
- Add binutils-gold for linker compatibility on alpine
- Run on all pushes, not just main/PR branches
2026-02-28 03:54:11 -08:00
55c6c21b5a Merge pull request 'fix: distinguish timeout from negative DNS responses (closes #35)' (#37) from fix/timeout-vs-negative-response into main
Some checks are pending
Check / check (push) Waiting to run
Reviewed-on: #37
2026-02-28 12:38:18 +01:00
clawbot
2993911883 fix: distinguish timeout from negative DNS responses (closes #35)
Some checks failed
Check / check (pull_request) Failing after 5m41s
2026-02-28 03:35:54 -08:00
70fac87254 Merge pull request 'fix: remove ErrNotImplemented stub — all checks fully implemented (closes #16)' (#23) from fix/remove-unimplemented-stubs into main
Some checks are pending
Check / check (push) Waiting to run
Reviewed-on: #23
2026-02-28 12:26:27 +01:00
940f7c89da Merge branch 'main' into fix/remove-unimplemented-stubs
Some checks failed
Check / check (pull_request) Failing after 5m45s
2026-02-28 12:09:24 +01:00
0eb57fc15b Merge pull request 'fix: look up A/AAAA records for apex domains to enable port/TLS checks (closes #19)' (#21) from fix/domain-port-tls-state-lookup into main
Some checks are pending
Check / check (push) Waiting to run
Reviewed-on: #21
2026-02-28 12:09:04 +01:00
5739108dc7 Merge branch 'main' into fix/domain-port-tls-state-lookup
Some checks failed
Check / check (pull_request) Failing after 5m41s
2026-02-28 12:08:56 +01:00
54272c2be5 Merge pull request 'fix: deduplicate TLS expiry warnings to prevent notification spam (closes #18)' (#22) from fix/tls-expiry-dedup into main
Some checks are pending
Check / check (push) Waiting to run
Reviewed-on: #22
2026-02-28 12:08:46 +01:00
7d380aafa4 Merge branch 'main' into fix/remove-unimplemented-stubs
Some checks failed
Check / check (pull_request) Failing after 5m42s
2026-02-28 12:08:35 +01:00
b18d29d586 Merge branch 'main' into fix/domain-port-tls-state-lookup
Some checks failed
Check / check (pull_request) Failing after 5m40s
2026-02-28 12:08:25 +01:00
e63241cc3c Merge branch 'main' into fix/tls-expiry-dedup
Some checks failed
Check / check (pull_request) Failing after 5m40s
2026-02-28 12:08:19 +01:00
5ab217bfd2 Merge pull request 'Reduce DNS query timeout and limit root server fan-out (closes #29)' (#30) from fix/reduce-dns-timeout-and-root-fanout into main
Some checks failed
Check / check (push) Has been cancelled
Reviewed-on: #30
2026-02-28 12:07:20 +01:00
518a2cc42e Merge pull request 'doc: add TESTING.md — real DNS only, no mocks' (#34) from doc/testing-policy into main
Some checks failed
Check / check (push) Has been cancelled
Reviewed-on: #34
2026-02-28 12:06:57 +01:00
user
4cb81aac24 doc: add testing policy — real DNS only, no mocks
Some checks failed
Check / check (pull_request) Failing after 5m24s
Documents the project testing philosophy: all resolver tests must
use live DNS queries. Mocking the DNS client layer is not permitted.
Includes rationale and anti-patterns to avoid.
2026-02-22 04:28:47 -08:00
user
203b581704 Reduce DNS query timeout to 2s and limit root server fan-out to 3
Some checks failed
Check / check (pull_request) Failing after 5m57s
- Reduce queryTimeoutDuration from 5s to 2s
- Add randomRootServers() that shuffles and picks 3 root servers
- Replace all rootServerList() call sites with randomRootServers()
- Keep maxRetries = 2

Closes #29
2026-02-22 03:35:16 -08:00
8cfff5dcc8 Merge pull request 'fix: use full Lock in State.Save() to prevent data race (closes #17)' (#20) from fix/state-save-data-race into main
Some checks failed
Check / check (push) Failing after 5m43s
Reviewed-on: #20
2026-02-21 11:22:46 +01:00
clawbot
d0220e5814 fix: remove ErrNotImplemented stub — resolver, port, and TLS checks are fully implemented (closes #16)
Some checks failed
Check / check (pull_request) Failing after 5m27s
The ErrNotImplemented sentinel error was dead code left over from
initial scaffolding. The resolver performs real iterative DNS
lookups from root servers, PortCheck does TCP connection checks,
and TLSCheck verifies TLS certificates and expiry. Removed the
unused error constant.
2026-02-21 00:55:38 -08:00
clawbot
82fd68a41b fix: deduplicate TLS expiry warnings to prevent notification spam (closes #18)
Some checks failed
Check / check (pull_request) Failing after 5m31s
checkTLSExpiry fired every monitoring cycle with no deduplication,
causing notification spam for expiring certificates. Added an
in-memory map tracking the last notification time per domain/IP
pair, suppressing re-notification within the TLS check interval.

Added TestTLSExpiryWarningDedup to verify deduplication works.
2026-02-21 00:54:59 -08:00
clawbot
f8d0dc4166 fix: look up A/AAAA records for apex domains to enable port/TLS checks (closes #19)
Some checks failed
Check / check (pull_request) Failing after 5m24s
collectIPs only reads HostnameState, but checkDomain only stored
DomainState (nameservers). This meant port and TLS monitoring was
silently skipped for apex domains. Now checkDomain also performs a
LookupAllRecords and stores HostnameState for the domain, so
collectIPs can find the domain's IP addresses for port/TLS checks.

Added TestDomainPortAndTLSChecks to verify the fix.
2026-02-21 00:53:42 -08:00
9 changed files with 420 additions and 87 deletions

View File

@@ -1,26 +1,9 @@
name: Check name: check
on: [push]
on:
push:
branches: [main]
pull_request:
branches: [main]
jobs: jobs:
check: check:
runs-on: ubuntu-latest runs-on: ubuntu-latest
steps: steps:
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4 # actions/checkout v4.2.2, 2026-02-28
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
- uses: actions/setup-go@40f1582b2485089dde7abd97c1529aa768e1baff # v5 - run: docker build .
with:
go-version-file: go.mod
- name: Install golangci-lint
run: go install github.com/golangci/golangci-lint/v2/cmd/golangci-lint@5d1e709b7be35cb2025444e19de266b056b7b7ee # v2.10.1
- name: Install goimports
run: go install golang.org/x/tools/cmd/goimports@009367f5c17a8d4c45a961a3a509277190a9a6f0 # v0.42.0
- name: Run make check
run: make check

View File

@@ -1,11 +1,13 @@
# Build stage # Build stage
FROM golang:1.25-alpine AS builder # golang 1.25-alpine, 2026-02-28
FROM golang@sha256:f6751d823c26342f9506c03797d2527668d095b0a15f1862cddb4d927a7a4ced AS builder
RUN apk add --no-cache git make gcc musl-dev RUN apk add --no-cache git make gcc musl-dev binutils-gold
# Install golangci-lint v2 # golangci-lint v2.10.1
RUN go install github.com/golangci/golangci-lint/v2/cmd/golangci-lint@latest RUN go install github.com/golangci/golangci-lint/v2/cmd/golangci-lint@5d1e709b7be35cb2025444e19de266b056b7b7ee
RUN go install golang.org/x/tools/cmd/goimports@latest # goimports v0.42.0
RUN go install golang.org/x/tools/cmd/goimports@009367f5c17a8d4c45a961a3a509277190a9a6f0
WORKDIR /src WORKDIR /src
COPY go.mod go.sum ./ COPY go.mod go.sum ./
@@ -20,7 +22,8 @@ RUN make check
RUN make build RUN make build
# Runtime stage # Runtime stage
FROM alpine:3.21 # alpine 3.21, 2026-02-28
FROM alpine@sha256:c3f8e73fdb79deaebaa2037150150191b9dcbfba68b4a46d70103204c53f4709
RUN apk add --no-cache ca-certificates tzdata RUN apk add --no-cache ca-certificates tzdata

34
TESTING.md Normal file
View File

@@ -0,0 +1,34 @@
# Testing Policy
## DNS Resolution Tests
All resolver tests **MUST** use live queries against real DNS servers.
No mocking of the DNS client layer is permitted.
### Rationale
The resolver performs iterative resolution from root nameservers through
the full delegation chain. Mocked responses cannot faithfully represent
the variety of real-world DNS behavior (truncation, referrals, glue
records, DNSSEC, varied response times, EDNS, etc.). Testing against
real servers ensures the resolver works correctly in production.
### Constraints
- Tests hit real DNS infrastructure and require network access
- Test duration depends on network conditions; timeout tuning keeps
the suite within the 30-second target
- Query timeout is calibrated to 3× maximum antipodal RTT (~300ms)
plus processing margin
- Root server fan-out is limited to reduce parallel query load
- Flaky failures from transient network issues are acceptable and
should be investigated as potential resolver bugs, not papered over
with mocks or skip flags
### What NOT to do
- **Do not mock `DNSClient`** for resolver tests (the mock constructor
exists for unit-testing other packages that consume the resolver)
- **Do not add `-short` flags** to skip slow tests
- **Do not increase `-timeout`** to hide hanging queries
- **Do not modify linter configuration** to suppress findings

View File

@@ -4,11 +4,6 @@ import "errors"
// Sentinel errors returned by the resolver. // Sentinel errors returned by the resolver.
var ( var (
// ErrNotImplemented indicates a method is stubbed out.
ErrNotImplemented = errors.New(
"resolver not yet implemented",
)
// ErrNoNameservers is returned when no authoritative NS // ErrNoNameservers is returned when no authoritative NS
// could be discovered for a domain. // could be discovered for a domain.
ErrNoNameservers = errors.New( ErrNoNameservers = errors.New(

View File

@@ -13,7 +13,7 @@ import (
) )
const ( const (
queryTimeoutDuration = 5 * time.Second queryTimeoutDuration = 2 * time.Second
maxRetries = 2 maxRetries = 2
maxDelegation = 20 maxDelegation = 20
timeoutMultiplier = 2 timeoutMultiplier = 2
@@ -227,7 +227,7 @@ func (r *Resolver) followDelegation(
authNS := extractNSSet(resp.Ns) authNS := extractNSSet(resp.Ns)
if len(authNS) == 0 { if len(authNS) == 0 {
return r.resolveNSRecursive(ctx, domain) return r.resolveNSIterative(ctx, domain)
} }
glue := extractGlue(resp.Extra) glue := extractGlue(resp.Extra)
@@ -291,60 +291,84 @@ func (r *Resolver) resolveNSIPs(
return ips return ips
} }
// resolveNSRecursive queries for NS records using recursive // resolveNSIterative queries for NS records using iterative
// resolution as a fallback for intercepted environments. // resolution as a fallback when followDelegation finds no
func (r *Resolver) resolveNSRecursive( // authoritative answer in the delegation chain.
func (r *Resolver) resolveNSIterative(
ctx context.Context, ctx context.Context,
domain string, domain string,
) ([]string, error) { ) ([]string, error) {
domain = dns.Fqdn(domain) if checkCtx(ctx) != nil {
msg := new(dns.Msg) return nil, ErrContextCanceled
msg.SetQuestion(domain, dns.TypeNS) }
msg.RecursionDesired = true
for _, ip := range rootServerList()[:3] { domain = dns.Fqdn(domain)
servers := rootServerList()
for range maxDelegation {
if checkCtx(ctx) != nil { if checkCtx(ctx) != nil {
return nil, ErrContextCanceled return nil, ErrContextCanceled
} }
addr := net.JoinHostPort(ip, "53") resp, err := r.queryServers(
ctx, servers, domain, dns.TypeNS,
resp, _, err := r.client.ExchangeContext(ctx, msg, addr) )
if err != nil { if err != nil {
continue return nil, err
} }
nsNames := extractNSSet(resp.Answer) nsNames := extractNSSet(resp.Answer)
if len(nsNames) > 0 { if len(nsNames) > 0 {
return nsNames, nil return nsNames, nil
} }
// Follow delegation.
authNS := extractNSSet(resp.Ns)
if len(authNS) == 0 {
break
}
glue := extractGlue(resp.Extra)
nextServers := glueIPs(authNS, glue)
if len(nextServers) == 0 {
break
}
servers = nextServers
} }
return nil, ErrNoNameservers return nil, ErrNoNameservers
} }
// resolveARecord resolves a hostname to IPv4 addresses. // resolveARecord resolves a hostname to IPv4 addresses using
// iterative resolution through the delegation chain.
func (r *Resolver) resolveARecord( func (r *Resolver) resolveARecord(
ctx context.Context, ctx context.Context,
hostname string, hostname string,
) ([]string, error) { ) ([]string, error) {
hostname = dns.Fqdn(hostname) if checkCtx(ctx) != nil {
msg := new(dns.Msg) return nil, ErrContextCanceled
msg.SetQuestion(hostname, dns.TypeA) }
msg.RecursionDesired = true
for _, ip := range rootServerList()[:3] { hostname = dns.Fqdn(hostname)
servers := rootServerList()
for range maxDelegation {
if checkCtx(ctx) != nil { if checkCtx(ctx) != nil {
return nil, ErrContextCanceled return nil, ErrContextCanceled
} }
addr := net.JoinHostPort(ip, "53") resp, err := r.queryServers(
ctx, servers, hostname, dns.TypeA,
resp, _, err := r.client.ExchangeContext(ctx, msg, addr) )
if err != nil { if err != nil {
continue return nil, fmt.Errorf(
"resolving %s: %w", hostname, err,
)
} }
// Check for A records in the answer section.
var ips []string var ips []string
for _, rr := range resp.Answer { for _, rr := range resp.Answer {
@@ -356,6 +380,24 @@ func (r *Resolver) resolveARecord(
if len(ips) > 0 { if len(ips) > 0 {
return ips, nil return ips, nil
} }
// Follow delegation if present.
authNS := extractNSSet(resp.Ns)
if len(authNS) == 0 {
break
}
glue := extractGlue(resp.Extra)
nextServers := glueIPs(authNS, glue)
if len(nextServers) == 0 {
// Resolve NS IPs iteratively — but guard
// against infinite recursion by using only
// already-resolved servers.
break
}
servers = nextServers
} }
return nil, fmt.Errorf( return nil, fmt.Errorf(
@@ -418,6 +460,23 @@ func (r *Resolver) QueryNameserver(
return r.queryAllTypes(ctx, nsHostname, nsIPs[0], hostname) return r.queryAllTypes(ctx, nsHostname, nsIPs[0], hostname)
} }
// QueryNameserverIP queries a nameserver by its IP address directly,
// bypassing NS hostname resolution.
func (r *Resolver) QueryNameserverIP(
ctx context.Context,
nsHostname string,
nsIP string,
hostname string,
) (*NameserverResponse, error) {
if checkCtx(ctx) != nil {
return nil, ErrContextCanceled
}
hostname = dns.Fqdn(hostname)
return r.queryAllTypes(ctx, nsHostname, nsIP, hostname)
}
func (r *Resolver) queryAllTypes( func (r *Resolver) queryAllTypes(
ctx context.Context, ctx context.Context,
nsHostname string, nsHostname string,
@@ -445,6 +504,7 @@ func (r *Resolver) queryAllTypes(
type queryState struct { type queryState struct {
gotNXDomain bool gotNXDomain bool
gotSERVFAIL bool gotSERVFAIL bool
gotTimeout bool
hasRecords bool hasRecords bool
} }
@@ -482,6 +542,10 @@ func (r *Resolver) querySingleType(
) { ) {
msg, err := r.queryDNS(ctx, nsIP, hostname, qtype) msg, err := r.queryDNS(ctx, nsIP, hostname, qtype)
if err != nil { if err != nil {
if isTimeout(err) {
state.gotTimeout = true
}
return return
} }
@@ -519,12 +583,26 @@ func collectAnswerRecords(
} }
} }
// isTimeout checks whether an error is a network timeout.
func isTimeout(err error) bool {
var netErr net.Error
if errors.As(err, &netErr) {
return netErr.Timeout()
}
return false
}
func classifyResponse(resp *NameserverResponse, state queryState) { func classifyResponse(resp *NameserverResponse, state queryState) {
switch { switch {
case state.gotNXDomain && !state.hasRecords: case state.gotNXDomain && !state.hasRecords:
resp.Status = StatusNXDomain resp.Status = StatusNXDomain
case state.gotTimeout && !state.hasRecords:
resp.Status = StatusTimeout
resp.Error = "all queries timed out"
case state.gotSERVFAIL && !state.hasRecords: case state.gotSERVFAIL && !state.hasRecords:
resp.Status = StatusError resp.Status = StatusError
resp.Error = "server returned SERVFAIL"
case !state.hasRecords && !state.gotNXDomain: case !state.hasRecords && !state.gotNXDomain:
resp.Status = StatusNoData resp.Status = StatusNoData
} }

View File

@@ -17,6 +17,7 @@ const (
StatusError = "error" StatusError = "error"
StatusNXDomain = "nxdomain" StatusNXDomain = "nxdomain"
StatusNoData = "nodata" StatusNoData = "nodata"
StatusTimeout = "timeout"
) )
// MaxCNAMEDepth is the maximum CNAME chain depth to follow. // MaxCNAMEDepth is the maximum CNAME chain depth to follow.

View File

@@ -10,6 +10,7 @@ import (
"testing" "testing"
"time" "time"
"github.com/miekg/dns"
"github.com/stretchr/testify/assert" "github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require" "github.com/stretchr/testify/require"
@@ -622,6 +623,59 @@ func TestQueryAllNameservers_ContextCanceled(t *testing.T) {
assert.Error(t, err) assert.Error(t, err)
} }
// ----------------------------------------------------------------
// Timeout tests
// ----------------------------------------------------------------
func TestQueryNameserverIP_Timeout(t *testing.T) {
t.Parallel()
log := slog.New(slog.NewTextHandler(
os.Stderr,
&slog.HandlerOptions{Level: slog.LevelDebug},
))
r := resolver.NewFromLoggerWithClient(
log, &timeoutClient{},
)
ctx, cancel := context.WithTimeout(
context.Background(), 10*time.Second,
)
t.Cleanup(cancel)
// Query any IP — the client always returns a timeout error.
resp, err := r.QueryNameserverIP(
ctx, "unreachable.test.", "192.0.2.1",
"example.com",
)
require.NoError(t, err)
assert.Equal(t, resolver.StatusTimeout, resp.Status)
assert.NotEmpty(t, resp.Error)
}
// timeoutClient simulates DNS timeout errors for testing.
type timeoutClient struct{}
func (c *timeoutClient) ExchangeContext(
_ context.Context,
_ *dns.Msg,
_ string,
) (*dns.Msg, time.Duration, error) {
return nil, 0, &net.OpError{
Op: "read",
Net: "udp",
Err: &timeoutError{},
}
}
type timeoutError struct{}
func (e *timeoutError) Error() string { return "i/o timeout" }
func (e *timeoutError) Timeout() bool { return true }
func (e *timeoutError) Temporary() bool { return true }
func TestResolveIPAddresses_ContextCanceled(t *testing.T) { func TestResolveIPAddresses_ContextCanceled(t *testing.T) {
t.Parallel() t.Parallel()

View File

@@ -6,6 +6,7 @@ import (
"log/slog" "log/slog"
"sort" "sort"
"strings" "strings"
"sync"
"time" "time"
"go.uber.org/fx" "go.uber.org/fx"
@@ -40,15 +41,17 @@ type Params struct {
// Watcher orchestrates all monitoring checks on a schedule. // Watcher orchestrates all monitoring checks on a schedule.
type Watcher struct { type Watcher struct {
log *slog.Logger log *slog.Logger
config *config.Config config *config.Config
state *state.State state *state.State
resolver DNSResolver resolver DNSResolver
portCheck PortChecker portCheck PortChecker
tlsCheck TLSChecker tlsCheck TLSChecker
notify Notifier notify Notifier
cancel context.CancelFunc cancel context.CancelFunc
firstRun bool firstRun bool
expiryNotifiedMu sync.Mutex
expiryNotified map[string]time.Time
} }
// New creates a new Watcher instance wired into the fx lifecycle. // New creates a new Watcher instance wired into the fx lifecycle.
@@ -57,14 +60,15 @@ func New(
params Params, params Params,
) (*Watcher, error) { ) (*Watcher, error) {
w := &Watcher{ w := &Watcher{
log: params.Logger.Get(), log: params.Logger.Get(),
config: params.Config, config: params.Config,
state: params.State, state: params.State,
resolver: params.Resolver, resolver: params.Resolver,
portCheck: params.PortCheck, portCheck: params.PortCheck,
tlsCheck: params.TLSCheck, tlsCheck: params.TLSCheck,
notify: params.Notify, notify: params.Notify,
firstRun: true, firstRun: true,
expiryNotified: make(map[string]time.Time),
} }
lifecycle.Append(fx.Hook{ lifecycle.Append(fx.Hook{
@@ -100,14 +104,15 @@ func NewForTest(
n Notifier, n Notifier,
) *Watcher { ) *Watcher {
return &Watcher{ return &Watcher{
log: slog.Default(), log: slog.Default(),
config: cfg, config: cfg,
state: st, state: st,
resolver: res, resolver: res,
portCheck: pc, portCheck: pc,
tlsCheck: tc, tlsCheck: tc,
notify: n, notify: n,
firstRun: true, firstRun: true,
expiryNotified: make(map[string]time.Time),
} }
} }
@@ -206,6 +211,28 @@ func (w *Watcher) checkDomain(
Nameservers: nameservers, Nameservers: nameservers,
LastChecked: now, LastChecked: now,
}) })
// Also look up A/AAAA records for the apex domain so that
// port and TLS checks (which read HostnameState) can find
// the domain's IP addresses.
records, err := w.resolver.LookupAllRecords(ctx, domain)
if err != nil {
w.log.Error(
"failed to lookup records for domain",
"domain", domain,
"error", err,
)
return
}
prevHS, hasPrevHS := w.state.GetHostnameState(domain)
if hasPrevHS && !w.firstRun {
w.detectHostnameChanges(ctx, domain, prevHS, records)
}
newState := buildHostnameState(records, now)
w.state.SetHostnameState(domain, newState)
} }
func (w *Watcher) detectNSChanges( func (w *Watcher) detectNSChanges(
@@ -691,6 +718,22 @@ func (w *Watcher) checkTLSExpiry(
return return
} }
// Deduplicate expiry warnings: don't re-notify for the same
// hostname within the TLS check interval.
dedupKey := fmt.Sprintf("expiry:%s:%s", hostname, ip)
w.expiryNotifiedMu.Lock()
lastNotified, seen := w.expiryNotified[dedupKey]
if seen && time.Since(lastNotified) < w.config.TLSInterval {
w.expiryNotifiedMu.Unlock()
return
}
w.expiryNotified[dedupKey] = time.Now()
w.expiryNotifiedMu.Unlock()
msg := fmt.Sprintf( msg := fmt.Sprintf(
"Host: %s\nIP: %s\nCN: %s\n"+ "Host: %s\nIP: %s\nCN: %s\n"+
"Expires: %s (%.0f days)", "Expires: %s (%.0f days)",

View File

@@ -273,6 +273,10 @@ func setupBaselineMocks(deps *testDeps) {
"ns1.example.com.", "ns1.example.com.",
"ns2.example.com.", "ns2.example.com.",
} }
deps.resolver.allRecords["example.com"] = map[string]map[string][]string{
"ns1.example.com.": {"A": {"93.184.216.34"}},
"ns2.example.com.": {"A": {"93.184.216.34"}},
}
deps.resolver.allRecords["www.example.com"] = map[string]map[string][]string{ deps.resolver.allRecords["www.example.com"] = map[string]map[string][]string{
"ns1.example.com.": {"A": {"93.184.216.34"}}, "ns1.example.com.": {"A": {"93.184.216.34"}},
"ns2.example.com.": {"A": {"93.184.216.34"}}, "ns2.example.com.": {"A": {"93.184.216.34"}},
@@ -290,6 +294,14 @@ func setupBaselineMocks(deps *testDeps) {
"www.example.com", "www.example.com",
}, },
} }
deps.tlsChecker.certs["93.184.216.34:example.com"] = &tlscheck.CertificateInfo{
CommonName: "example.com",
Issuer: "DigiCert",
NotAfter: time.Now().Add(90 * 24 * time.Hour),
SubjectAlternativeNames: []string{
"example.com",
},
}
} }
func assertNoNotifications( func assertNoNotifications(
@@ -322,14 +334,74 @@ func assertStatePopulated(
) )
} }
if len(snap.Hostnames) != 1 { // Hostnames includes both explicit hostnames and domains
// (domains now also get hostname state for port/TLS checks).
if len(snap.Hostnames) < 1 {
t.Errorf( t.Errorf(
"expected 1 hostname in state, got %d", "expected at least 1 hostname in state, got %d",
len(snap.Hostnames), len(snap.Hostnames),
) )
} }
} }
func TestDomainPortAndTLSChecks(t *testing.T) {
t.Parallel()
cfg := defaultTestConfig(t)
cfg.Domains = []string{"example.com"}
w, deps := newTestWatcher(t, cfg)
deps.resolver.nsRecords["example.com"] = []string{
"ns1.example.com.",
}
deps.resolver.allRecords["example.com"] = map[string]map[string][]string{
"ns1.example.com.": {"A": {"93.184.216.34"}},
}
deps.portChecker.results["93.184.216.34:80"] = true
deps.portChecker.results["93.184.216.34:443"] = true
deps.tlsChecker.certs["93.184.216.34:example.com"] = &tlscheck.CertificateInfo{
CommonName: "example.com",
Issuer: "DigiCert",
NotAfter: time.Now().Add(90 * 24 * time.Hour),
SubjectAlternativeNames: []string{
"example.com",
},
}
w.RunOnce(t.Context())
snap := deps.state.GetSnapshot()
// Domain should have port state populated
if len(snap.Ports) == 0 {
t.Error("expected port state for domain, got none")
}
// Domain should have certificate state populated
if len(snap.Certificates) == 0 {
t.Error("expected certificate state for domain, got none")
}
// Verify port checker was actually called
deps.portChecker.mu.Lock()
calls := deps.portChecker.calls
deps.portChecker.mu.Unlock()
if calls == 0 {
t.Error("expected port checker to be called for domain")
}
// Verify TLS checker was actually called
deps.tlsChecker.mu.Lock()
tlsCalls := deps.tlsChecker.calls
deps.tlsChecker.mu.Unlock()
if tlsCalls == 0 {
t.Error("expected TLS checker to be called for domain")
}
}
func TestNSChangeDetection(t *testing.T) { func TestNSChangeDetection(t *testing.T) {
t.Parallel() t.Parallel()
@@ -342,6 +414,12 @@ func TestNSChangeDetection(t *testing.T) {
"ns1.example.com.", "ns1.example.com.",
"ns2.example.com.", "ns2.example.com.",
} }
deps.resolver.allRecords["example.com"] = map[string]map[string][]string{
"ns1.example.com.": {"A": {"1.2.3.4"}},
"ns2.example.com.": {"A": {"1.2.3.4"}},
}
deps.portChecker.results["1.2.3.4:80"] = false
deps.portChecker.results["1.2.3.4:443"] = false
ctx := t.Context() ctx := t.Context()
w.RunOnce(ctx) w.RunOnce(ctx)
@@ -351,6 +429,10 @@ func TestNSChangeDetection(t *testing.T) {
"ns1.example.com.", "ns1.example.com.",
"ns3.example.com.", "ns3.example.com.",
} }
deps.resolver.allRecords["example.com"] = map[string]map[string][]string{
"ns1.example.com.": {"A": {"1.2.3.4"}},
"ns3.example.com.": {"A": {"1.2.3.4"}},
}
deps.resolver.mu.Unlock() deps.resolver.mu.Unlock()
w.RunOnce(ctx) w.RunOnce(ctx)
@@ -506,6 +588,61 @@ func TestTLSExpiryWarning(t *testing.T) {
} }
} }
func TestTLSExpiryWarningDedup(t *testing.T) {
t.Parallel()
cfg := defaultTestConfig(t)
cfg.Hostnames = []string{"www.example.com"}
cfg.TLSInterval = 24 * time.Hour
w, deps := newTestWatcher(t, cfg)
deps.resolver.allRecords["www.example.com"] = map[string]map[string][]string{
"ns1.example.com.": {"A": {"1.2.3.4"}},
}
deps.resolver.ipAddresses["www.example.com"] = []string{
"1.2.3.4",
}
deps.portChecker.results["1.2.3.4:80"] = true
deps.portChecker.results["1.2.3.4:443"] = true
deps.tlsChecker.certs["1.2.3.4:www.example.com"] = &tlscheck.CertificateInfo{
CommonName: "www.example.com",
Issuer: "DigiCert",
NotAfter: time.Now().Add(3 * 24 * time.Hour),
SubjectAlternativeNames: []string{
"www.example.com",
},
}
ctx := t.Context()
// First run = baseline, no notifications
w.RunOnce(ctx)
// Second run should fire one expiry warning
w.RunOnce(ctx)
// Third run should NOT fire another warning (dedup)
w.RunOnce(ctx)
notifications := deps.notifier.getNotifications()
expiryCount := 0
for _, n := range notifications {
if n.Title == "TLS Expiry Warning: www.example.com" {
expiryCount++
}
}
if expiryCount != 1 {
t.Errorf(
"expected exactly 1 expiry warning (dedup), got %d",
expiryCount,
)
}
}
func TestGracefulShutdown(t *testing.T) { func TestGracefulShutdown(t *testing.T) {
t.Parallel() t.Parallel()
@@ -519,6 +656,11 @@ func TestGracefulShutdown(t *testing.T) {
deps.resolver.nsRecords["example.com"] = []string{ deps.resolver.nsRecords["example.com"] = []string{
"ns1.example.com.", "ns1.example.com.",
} }
deps.resolver.allRecords["example.com"] = map[string]map[string][]string{
"ns1.example.com.": {"A": {"1.2.3.4"}},
}
deps.portChecker.results["1.2.3.4:80"] = false
deps.portChecker.results["1.2.3.4:443"] = false
ctx, cancel := context.WithCancel(t.Context()) ctx, cancel := context.WithCancel(t.Context())