Files
bucketeer/internal/config/config.go
T
StasonJatham 62a7d2eb2e provider capability model, on-demand scan/backfill, more providers
Readability capabilities (exists/object_readable/listable) are now tracked
separately instead of a single exposure flag, matching how providers differ:
- Azure 'Blob' mode = object readable, not listable; 'Container' = listable
- Cloudflare R2 public URLs are never anonymously listable (root 500); R2 is
  object-read only and is no longer probed for listing
- S3/GCS: 200 list = listable; 403 + readable index.html/robots.txt =
  object readable only
New columns: cloud_assets.listable, cloud_assets.object_readable.

Azure: account-level container listing is never anonymous; discover containers
by probing a bounded common-name set (or the container from a URL path), then
list blobs.

Classifier: added the legacy AWS '.s3-<region>.amazonaws.com' bucket form.

On-demand scan: POST /api/scan {target} classifies a host or URL, follows CNAME
for custom domains, probes, and indexes readable resources; Azure container
comes from the URL path. UI has a Scan box.

Backfill: POST /api/reprobe re-probes already-discovered assets with the current
checks and indexes any readable ones, recovering findings from earlier probes.

DNS: CNAME-only enrichment (A/AAAA resolved only for matches), 64 workers,
larger queue.

Verified live against real public resources:
  veteran1.nyc3.digitaloceanspaces.com            listable, entries
  bucket-01.s3-eu-west-1.amazonaws.com            listable, entries
  tartugeo-podcast.storage.googleapis.com         listable, entries
  eroticfeeldev.blob.core.windows.net/images      listable, entries
2026-09-22 14:47:49 +02:00

179 lines
4.7 KiB
Go

// Package config loads all ctcloud configuration from environment variables.
// There are no configuration files at runtime.
package config
import (
"fmt"
"os"
"strconv"
"strings"
"time"
)
type Config struct {
DatabaseURL string
DBMaxConns int
DNSServers []string
DNSWorkers int
DNSTimeout time.Duration
DNSCacheSize int
DNSMaxCNAMEdepth int
DNSPositiveTTL time.Duration
DNSNegativeTTL time.Duration
DedupSize int
DirectQueueSize int
DNSQueueSize int
DBQueueSize int
DBBatchSize int
DBFlushInterval time.Duration
ActiveProbing bool
ProbeWorkers int
ProbeTimeout time.Duration
ProbeQueueSize int
ProbeDeep bool
IndexEnabled bool
IndexMaxObjects int
MetricsAddr string
UIUser string
UIPass string
LogLevel string
LogFormat string
StatsInterval time.Duration
LogListSource string
StartAtEnd bool
ShutdownTimeout time.Duration
DedupeTTL time.Duration
}
// DefaultLogListSource is the public CT log list used by certspotter.
const DefaultLogListSource = "https://www.gstatic.com/ct/log_list/v3/log_list.json"
func Load() (*Config, error) {
c := &Config{
DatabaseURL: os.Getenv("DATABASE_URL"),
DBMaxConns: envInt("DB_MAX_CONNS", 8),
DNSServers: envList("DNS_SERVERS", nil),
DNSWorkers: envInt("DNS_WORKERS", 64),
DNSTimeout: envDuration("DNS_TIMEOUT", 5*time.Second),
DNSCacheSize: envInt("DNS_CACHE_SIZE", 1<<18),
DedupSize: envInt("DEDUP_SIZE", 1<<18),
DNSMaxCNAMEdepth: envInt("DNS_MAX_CNAME_DEPTH", 8),
DNSPositiveTTL: envDuration("DNS_POSITIVE_TTL", 10*time.Minute),
DNSNegativeTTL: envDuration("DNS_NEGATIVE_TTL", 1*time.Minute),
DirectQueueSize: envInt("DIRECT_QUEUE_SIZE", 8192),
DNSQueueSize: envInt("DNS_QUEUE_SIZE", 262144),
DBQueueSize: envInt("DB_QUEUE_SIZE", 8192),
DBBatchSize: envInt("DB_BATCH_SIZE", 500),
DBFlushInterval: envDuration("DB_FLUSH_INTERVAL", 2*time.Second),
ActiveProbing: envBool("ACTIVE_PROBING", false),
ProbeWorkers: envInt("PROBE_WORKERS", 8),
ProbeTimeout: envDuration("PROBE_TIMEOUT", 5*time.Second),
ProbeQueueSize: envInt("PROBE_QUEUE_SIZE", 1<<16),
ProbeDeep: envBool("PROBE_DEEP", true),
IndexEnabled: envBool("INDEX_ENABLED", true),
IndexMaxObjects: envInt("INDEX_MAX_OBJECTS", 1000),
MetricsAddr: envString("METRICS_ADDR", ":9090"),
UIUser: envString("UI_USER", ""),
UIPass: envString("UI_PASS", ""),
LogLevel: envString("LOG_LEVEL", "info"),
LogFormat: envString("LOG_FORMAT", "text"),
StatsInterval: envDuration("STATS_INTERVAL", 60*time.Second),
LogListSource: envString("LOG_LIST_SOURCE", DefaultLogListSource),
StartAtEnd: envBool("START_AT_END", false),
ShutdownTimeout: envDuration("SHUTDOWN_TIMEOUT", 20*time.Second),
DedupeTTL: envDuration("DEDUP_TTL", time.Hour),
}
if err := c.validate(); err != nil {
return nil, err
}
return c, nil
}
func (c *Config) validate() error {
if c.DatabaseURL == "" {
return fmt.Errorf("DATABASE_URL is required")
}
if c.DNSWorkers < 1 {
return fmt.Errorf("DNS_WORKERS must be >= 1")
}
if c.DNSMaxCNAMEdepth < 1 {
return fmt.Errorf("DNS_MAX_CNAME_DEPTH must be >= 1")
}
if c.DirectQueueSize < 1 || c.DNSQueueSize < 1 || c.DBQueueSize < 1 {
return fmt.Errorf("queue sizes must be >= 1")
}
if c.DBBatchSize < 1 {
return fmt.Errorf("DB_BATCH_SIZE must be >= 1")
}
switch c.LogLevel {
case "debug", "info", "warn", "error":
default:
return fmt.Errorf("LOG_LEVEL must be one of debug, info, warn, error")
}
switch c.LogFormat {
case "text", "json":
default:
return fmt.Errorf("LOG_FORMAT must be text or json")
}
return nil
}
func envList(key string, def []string) []string {
v := os.Getenv(key)
if v == "" {
return def
}
parts := strings.Split(v, ",")
out := make([]string, 0, len(parts))
for _, p := range parts {
if p = strings.TrimSpace(p); p != "" {
out = append(out, p)
}
}
if len(out) == 0 {
return def
}
return out
}
func envString(key, def string) string {
if v := os.Getenv(key); v != "" {
return v
}
return def
}
func envInt(key string, def int) int {
if v := os.Getenv(key); v != "" {
if n, err := strconv.Atoi(strings.TrimSpace(v)); err == nil {
return n
}
}
return def
}
func envBool(key string, def bool) bool {
if v := os.Getenv(key); v != "" {
if b, err := strconv.ParseBool(strings.TrimSpace(v)); err == nil {
return b
}
}
return def
}
func envDuration(key string, def time.Duration) time.Duration {
if v := os.Getenv(key); v != "" {
if d, err := time.ParseDuration(strings.TrimSpace(v)); err == nil {
return d
}
}
return def
}