mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-08-21 14:46:58 +00:00
* s3tables: add the maintenance configuration APIs Stores the configuration verbatim as the wire shape under a new s3tables.maintenance extended attribute, so Get hands back what Put took and no translation layer can drift from the AWS model. Nothing reads the configuration yet. Put merges a single type into the stored map so configuring compaction does not drop snapshot management, and asserts the attribute's prior value so two concurrent Puts cannot silently clobber each other. * iceberg: apply the maintenance configuration in the worker The worker now reads the per-table and per-bucket maintenance configuration written by the control plane, so the wildcard plugin config is a default rather than the only setting a table can have. Table properties still win by default, since a table declaring its own layout is what every engine honours and the compactor has to agree with whoever writes the files. Clearing table_properties_override makes the maintenance configuration authoritative instead. Status is not part of that contest: a disabled type drops its operations and no property can re-enable them, so the operator's kill switch always holds. Manifest and delete-file rewrites have no AWS equivalent and ride with compaction. Detection reads both attributes from entries it already lists. * s3tables: report maintenance job status The worker records the outcome of each run in its own extended attribute, separate from the configuration so operator and worker writes do not contend, and GetTableMaintenanceJobStatus reads it back. Only the types a run touched are written, so a partial run cannot erase what an earlier one recorded. The reader fills in the rest: Disabled when the configuration switched a type off, Not_Yet_Run otherwise. Status is advisory, so a lost race is logged rather than failing a job whose work already committed. * s3tables: route the maintenance APIs over REST The five actions were only reachable by X-Amz-Target dispatch, which the AWS CLI and SDK do not use for this service. They address the operations by path, so the APIs were unreachable from any official client. * s3tables: fix the table bucket ARN field name GetTableBucketMaintenanceConfiguration emitted tableBucketArn where the wire field is tableBucketARN, as every other response in this package already spells it. Official SDK deserializers ignore the unknown key, so the required field came back unset. * s3tables: carry the compaction strategy through to the worker IcebergCompactionSettings modelled only targetFileSizeMB, so a request naming a strategy was accepted and then dropped on the way to storage. The worker now maps binpack and sort onto its own rewrite strategy and lets auto defer to the worker configuration. z-order is rejected rather than accepted and quietly binpacked. * s3tables: report bucket-level maintenance status GetTableMaintenanceJobStatus read only the table's configuration, so unreferenced file removal — which is configured on the bucket — reported Not_Yet_Run or a stale success after an operator disabled it. The merge helper now lives in this package and the worker shares it. * iceberg: delete orphans only after the non-current window AWS marks a file non-current once it has been unreferenced for unreferencedDays, then deletes it a further nonCurrentDays later. The cutoff was taken from unreferencedDays alone, so a 3/10 configuration hard-deleted on day three and threw away the ten day recovery window. remove_orphans deletes in one step rather than marking, so the cutoff is now the sum of the two. * s3tables: assert every attribute when rewriting an entry UpdateEntry writes the whole entry back from the snapshot the caller read, and its precondition only covers the keys the caller names. Both maintenance writers named one key, so a job status write could revert a maintenance configuration an operator had just disabled, turning an advisory write into a silent re-enable. Both now assert the entry's full attribute set, including the target key when absent so a concurrent create also fails the precondition. * s3tables: assert absent attributes when rewriting an entry The precondition covered the attributes present when the writer read the entry, so an attribute created between that read and the write was absent from it. A first-time PutTableMaintenanceConfiguration disabling a type therefore lands, passes the per-key checks, and is then deleted by the stale whole-entry write. Every attribute this package stores is now asserted, absent ones included. The metadata commit and planning index writers rewrite the same entries and had the same exposure, so both use the shared snapshot too. * iceberg: implement the auto compaction strategy auto was accepted, stored and read back, but left the worker on its own default, so a sorted table configured as auto was compacted with binpack. AWS defines auto as sorting tables that declare a sort order and bin-packing the rest. That needs the table metadata, so the choice is made where the rewrite plan is resolved: an unsorted table falls back to binpack rather than failing the way an explicit sort request does. * s3tables: validate the maintenance setting ranges PUT accepted zero, negative and oversized values for every numeric setting. The worker then ignores a non-positive value and saturates an oversized one, so the configuration read back was not the one that ran. AWS bounds all five to 1..2147483647, which is now enforced. The fields are pointers so an explicit zero is distinguishable from an omitted one and can be rejected rather than silently ignored. * s3tables: give every entry writer the same compare-and-swap updateExtendedAttribute asserted the entry's attributes, but the helpers behind the metadata, policy and tag handlers still wrote the whole entry unconditionally. Any of them could land on a stale snapshot and delete a maintenance configuration an operator had just written. They all share one read-modify-write loop now, so the precondition and the bounded retry apply wherever an entry is rewritten. * s3tables: move the maintenance configuration with a renamed table RenameTable carried the metadata, version, policy and tags to the new name but left the maintenance configuration and job status behind. A table with snapshot management disabled came back enabled under its new name, and the stale configuration stayed on the old name where a table created there would inherit it. The decoupled-delete cleanup left the same two attributes behind. * s3tables: accept every AWS partition in ARNs The route regexes and the ARN patterns both hardcoded arn:aws, so valid aws-cn and aws-us-gov ARNs never reached a handler. The router now shares the partition-tolerant prefix with the parser, and a generated ARN uses the partition its region belongs to so it parses back. * s3tables: generate ARNs in the region's partition The handler's own ARN generators still formatted arn:aws directly rather than going through the partition-aware builder, so a China or GovCloud deployment routed the request but then returned a commercial ARN and matched IAM policies against it. The round-trip test missed this because parsing accepts any partition, so it now asserts the prefix the region implies. * s3tables: complete the ARN partition table aws-iso-e, aws-iso-f and aws-eusc were missing, so eu-isoe-*, us-isof-* and eusc-* regions fell through to the commercial partition. * s3tables: do not let a rename swallow a concurrent maintenance write Rename copied the source attributes early and cleared the source at the end, so a Put landing in between missed the copy to the destination and was then deleted by the cleanup. It succeeded and vanished. The cleanup now clears the source only while it still holds exactly what was copied, and returns a conflict otherwise. Put checks the catalog identity inside the same conditional mutation, so it also cannot write to a name that a rename or delete has already soft-deleted.
483 lines
15 KiB
Go
483 lines
15 KiB
Go
package s3tables
|
|
|
|
import (
|
|
"crypto/rand"
|
|
"encoding/hex"
|
|
"fmt"
|
|
"net/url"
|
|
"path"
|
|
"regexp"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
|
|
)
|
|
|
|
const (
|
|
bucketNamePatternStr = `[a-z0-9-]+`
|
|
tableNamespacePatternStr = `[a-z0-9_.-]+`
|
|
tableNamePatternStr = `[a-z0-9_-]+`
|
|
)
|
|
|
|
const (
|
|
tableObjectRootDirName = ".objects"
|
|
)
|
|
|
|
// ARNPartitionPatternStr matches any AWS partition, not just the commercial
|
|
// one: aws-cn and aws-us-gov ARNs are valid and must reach the handlers.
|
|
const ARNPartitionPatternStr = `aws[-a-z0-9]*`
|
|
|
|
// ARNPrefixPatternStr is the leading, partition-tolerant part of every S3
|
|
// Tables ARN. The HTTP router shares it so routes and parsing agree.
|
|
const ARNPrefixPatternStr = `arn:` + ARNPartitionPatternStr + `:s3tables`
|
|
|
|
var (
|
|
bucketARNPattern = regexp.MustCompile(`^` + ARNPrefixPatternStr + `:[^:]*:[^:]*:bucket/(` + bucketNamePatternStr + `)$`)
|
|
tableARNPattern = regexp.MustCompile(`^` + ARNPrefixPatternStr + `:[^:]*:[^:]*:bucket/(` + bucketNamePatternStr + `)/table/(` + tableNamespacePatternStr + `)/(` + tableNamePatternStr + `)$`)
|
|
tagPattern = regexp.MustCompile(`^([\p{L}\p{Z}\p{N}_.:/=+\-@]*)$`)
|
|
)
|
|
|
|
// ARN parsing functions
|
|
|
|
// parseBucketNameFromARN extracts bucket name from table bucket ARN
|
|
// ARN format: arn:aws:s3tables:{region}:{account}:bucket/{bucket-name}
|
|
func parseBucketNameFromARN(arn string) (string, error) {
|
|
matches := bucketARNPattern.FindStringSubmatch(arn)
|
|
if len(matches) != 2 {
|
|
return "", fmt.Errorf("invalid bucket ARN: %s", arn)
|
|
}
|
|
bucketName := matches[1]
|
|
if !isValidBucketName(bucketName) {
|
|
return "", fmt.Errorf("invalid bucket name in ARN: %s", bucketName)
|
|
}
|
|
return bucketName, nil
|
|
}
|
|
|
|
// ParseBucketNameFromARN is a wrapper to validate bucket ARN for other packages.
|
|
func ParseBucketNameFromARN(arn string) (string, error) {
|
|
return parseBucketNameFromARN(arn)
|
|
}
|
|
|
|
// IsValidBucketName is a wrapper to validate a table bucket name for other packages.
|
|
func IsValidBucketName(name string) bool {
|
|
return isValidBucketName(name)
|
|
}
|
|
|
|
// parseTableFromARN extracts bucket name, namespace, and table name from ARN
|
|
// ARN format: arn:aws:s3tables:{region}:{account}:bucket/{bucket-name}/table/{namespace}/{table-name}
|
|
func parseTableFromARN(arn string) (bucketName, namespace, tableName string, err error) {
|
|
matches := tableARNPattern.FindStringSubmatch(arn)
|
|
if len(matches) != 4 {
|
|
return "", "", "", fmt.Errorf("invalid table ARN: %s", arn)
|
|
}
|
|
|
|
// Validate bucket name
|
|
bucketName = matches[1]
|
|
if err := validateBucketName(bucketName); err != nil {
|
|
return "", "", "", fmt.Errorf("invalid bucket name in ARN: %v", err)
|
|
}
|
|
|
|
namespace, err = validateNamespace([]string{matches[2]})
|
|
if err != nil {
|
|
return "", "", "", fmt.Errorf("invalid namespace in ARN: %v", err)
|
|
}
|
|
|
|
// URL decode and validate the table name from the ARN path component
|
|
tableNameUnescaped, err := url.PathUnescape(matches[3])
|
|
if err != nil {
|
|
return "", "", "", fmt.Errorf("invalid table name encoding in ARN: %v", err)
|
|
}
|
|
if _, err := validateTableName(tableNameUnescaped); err != nil {
|
|
return "", "", "", fmt.Errorf("invalid table name in ARN: %v", err)
|
|
}
|
|
return bucketName, namespace, tableNameUnescaped, nil
|
|
}
|
|
|
|
// Path helpers
|
|
|
|
// GetTableBucketPath returns the filer path for a table bucket
|
|
func GetTableBucketPath(bucketName string) string {
|
|
return path.Join(TablesPath, bucketName)
|
|
}
|
|
|
|
// GetNamespacePath returns the filer path for a namespace
|
|
func GetNamespacePath(bucketName, namespace string) string {
|
|
return path.Join(TablesPath, bucketName, namespace)
|
|
}
|
|
|
|
// GetTablePath returns the filer path for a table
|
|
func GetTablePath(bucketName, namespace, tableName string) string {
|
|
return path.Join(TablesPath, bucketName, namespace, tableName)
|
|
}
|
|
|
|
// TableDataDirFromMetadataLocation maps a table's s3:// metadata location to the
|
|
// filer directory holding its data. A renamed table is catalog-only, so its data
|
|
// stays at the original location while its catalog entry moves; this lets a drop
|
|
// purge the real data instead of the now-empty catalog path.
|
|
func TableDataDirFromMetadataLocation(metadataLocation string) string {
|
|
loc := strings.TrimSuffix(metadataLocation, "/")
|
|
if idx := strings.LastIndex(loc, "/metadata/"); idx != -1 {
|
|
loc = loc[:idx]
|
|
}
|
|
loc = strings.TrimPrefix(loc, "s3://")
|
|
if loc == "" {
|
|
return ""
|
|
}
|
|
return path.Join(TablesPath, loc)
|
|
}
|
|
|
|
// GetTableObjectRootDir returns the root path for table bucket object storage
|
|
func GetTableObjectRootDir() string {
|
|
return path.Join(TablesPath, tableObjectRootDirName)
|
|
}
|
|
|
|
// GetTableObjectBucketPath returns the filer path for table bucket object storage
|
|
func GetTableObjectBucketPath(bucketName string) string {
|
|
return path.Join(GetTableObjectRootDir(), bucketName)
|
|
}
|
|
|
|
// Metadata structures
|
|
|
|
type tableBucketMetadata struct {
|
|
Name string `json:"name"`
|
|
CreatedAt time.Time `json:"createdAt"`
|
|
OwnerAccountID string `json:"ownerAccountId"`
|
|
}
|
|
|
|
// namespaceMetadata stores metadata for a namespace
|
|
type namespaceMetadata struct {
|
|
Namespace []string `json:"namespace"`
|
|
CreatedAt time.Time `json:"createdAt"`
|
|
OwnerAccountID string `json:"ownerAccountId"`
|
|
Properties map[string]string `json:"properties,omitempty"`
|
|
}
|
|
|
|
// tableMetadataInternal stores metadata for a table
|
|
type tableMetadataInternal struct {
|
|
Name string `json:"name"`
|
|
Namespace string `json:"namespace"`
|
|
Format string `json:"format"`
|
|
CreatedAt time.Time `json:"createdAt"`
|
|
ModifiedAt time.Time `json:"modifiedAt"`
|
|
OwnerAccountID string `json:"ownerAccountId"`
|
|
VersionToken string `json:"versionToken"`
|
|
MetadataVersion int `json:"metadataVersion"`
|
|
MetadataLocation string `json:"metadataLocation,omitempty"`
|
|
Metadata *TableMetadata `json:"metadata,omitempty"`
|
|
}
|
|
|
|
// IsTableBucketEntry returns true when the entry is marked as a table bucket.
|
|
func IsTableBucketEntry(entry *filer_pb.Entry) bool {
|
|
if entry == nil || entry.Extended == nil {
|
|
return false
|
|
}
|
|
_, ok := entry.Extended[ExtendedKeyTableBucket]
|
|
return ok
|
|
}
|
|
|
|
// entryType returns the entry-type marker for a catalog entry. Tables and views
|
|
// share the same on-disk layout; the marker distinguishes them. An absent marker
|
|
// means table for back-compat.
|
|
func entryType(extended map[string][]byte) string {
|
|
if extended == nil {
|
|
return EntryTypeTable
|
|
}
|
|
if v, ok := extended[ExtendedKeyEntryType]; ok && len(v) > 0 {
|
|
return string(v)
|
|
}
|
|
return EntryTypeTable
|
|
}
|
|
|
|
// Utility functions
|
|
|
|
// validateBucketName validates bucket name and returns an error if invalid.
|
|
// Bucket names must contain only lowercase letters, numbers, and hyphens.
|
|
// Length must be between 3 and 63 characters.
|
|
// Must start and end with a letter or digit.
|
|
// Reserved prefixes/suffixes are rejected.
|
|
func validateBucketName(name string) error {
|
|
if name == "" {
|
|
return fmt.Errorf("bucket name is required")
|
|
}
|
|
|
|
if len(name) < 3 || len(name) > 63 {
|
|
return fmt.Errorf("bucket name must be between 3 and 63 characters")
|
|
}
|
|
|
|
// Must start and end with a letter or digit
|
|
start := name[0]
|
|
end := name[len(name)-1]
|
|
if !((start >= 'a' && start <= 'z') || (start >= '0' && start <= '9')) {
|
|
return fmt.Errorf("bucket name must start with a letter or digit")
|
|
}
|
|
if !((end >= 'a' && end <= 'z') || (end >= '0' && end <= '9')) {
|
|
return fmt.Errorf("bucket name must end with a letter or digit")
|
|
}
|
|
|
|
// Allowed characters: a-z, 0-9, -
|
|
for i := 0; i < len(name); i++ {
|
|
ch := name[i]
|
|
if (ch >= 'a' && ch <= 'z') || (ch >= '0' && ch <= '9') || ch == '-' {
|
|
continue
|
|
}
|
|
return fmt.Errorf("bucket name can only contain lowercase letters, numbers, and hyphens")
|
|
}
|
|
|
|
// Reserved prefixes
|
|
reservedPrefixes := []string{"xn--", "sthree-", "amzn-s3-demo-", "aws"}
|
|
for _, p := range reservedPrefixes {
|
|
if strings.HasPrefix(name, p) {
|
|
return fmt.Errorf("bucket name cannot start with reserved prefix: %s", p)
|
|
}
|
|
}
|
|
|
|
// Reserved suffixes
|
|
reservedSuffixes := []string{"-s3alias", "--ol-s3", "--x-s3", "--table-s3"}
|
|
for _, s := range reservedSuffixes {
|
|
if strings.HasSuffix(name, s) {
|
|
return fmt.Errorf("bucket name cannot end with reserved suffix: %s", s)
|
|
}
|
|
}
|
|
|
|
return nil
|
|
}
|
|
|
|
// BuildBucketARN builds a bucket ARN with the provided region and account ID.
|
|
// If region is empty, the ARN will omit the region field.
|
|
func BuildBucketARN(region, accountID, bucketName string) (string, error) {
|
|
if bucketName == "" {
|
|
return "", fmt.Errorf("bucket name is required")
|
|
}
|
|
if err := validateBucketName(bucketName); err != nil {
|
|
return "", err
|
|
}
|
|
if accountID == "" {
|
|
accountID = DefaultAccountID
|
|
}
|
|
return buildARN(region, accountID, fmt.Sprintf("bucket/%s", bucketName)), nil
|
|
}
|
|
|
|
// BuildTableARN builds a table ARN with the provided region and account ID.
|
|
func BuildTableARN(region, accountID, bucketName, namespace, tableName string) (string, error) {
|
|
if bucketName == "" {
|
|
return "", fmt.Errorf("bucket name is required")
|
|
}
|
|
if err := validateBucketName(bucketName); err != nil {
|
|
return "", err
|
|
}
|
|
if namespace == "" {
|
|
return "", fmt.Errorf("namespace is required")
|
|
}
|
|
normalizedNamespace, err := validateNamespace([]string{namespace})
|
|
if err != nil {
|
|
return "", err
|
|
}
|
|
if tableName == "" {
|
|
return "", fmt.Errorf("table name is required")
|
|
}
|
|
normalizedTable, err := validateTableName(tableName)
|
|
if err != nil {
|
|
return "", err
|
|
}
|
|
if accountID == "" {
|
|
accountID = DefaultAccountID
|
|
}
|
|
return buildARN(region, accountID, fmt.Sprintf("bucket/%s/table/%s/%s", bucketName, normalizedNamespace, normalizedTable)), nil
|
|
}
|
|
|
|
func buildARN(region, accountID, resourcePath string) string {
|
|
return fmt.Sprintf("arn:%s:s3tables:%s:%s:%s", arnPartitionForRegion(region), region, accountID, resourcePath)
|
|
}
|
|
|
|
// arnPartitionForRegion returns the ARN partition a region belongs to, so an
|
|
// ARN this handler emits round-trips through a client in that partition.
|
|
func arnPartitionForRegion(region string) string {
|
|
switch {
|
|
case strings.HasPrefix(region, "cn-"):
|
|
return "aws-cn"
|
|
case strings.HasPrefix(region, "us-gov-"):
|
|
return "aws-us-gov"
|
|
case strings.HasPrefix(region, "us-iso-"):
|
|
return "aws-iso"
|
|
case strings.HasPrefix(region, "us-isob-"):
|
|
return "aws-iso-b"
|
|
case strings.HasPrefix(region, "eu-isoe-"):
|
|
return "aws-iso-e"
|
|
case strings.HasPrefix(region, "us-isof-"):
|
|
return "aws-iso-f"
|
|
case strings.HasPrefix(region, "eusc-"):
|
|
return "aws-eusc"
|
|
default:
|
|
return "aws"
|
|
}
|
|
}
|
|
|
|
// ValidateTags validates tags for S3 Tables.
|
|
func ValidateTags(tags map[string]string) error {
|
|
if len(tags) > 10 {
|
|
return fmt.Errorf("validate tags: %d tags more than 10", len(tags))
|
|
}
|
|
for k, v := range tags {
|
|
if len(k) > 128 {
|
|
return fmt.Errorf("validate tags: tag key longer than 128")
|
|
}
|
|
if !tagPattern.MatchString(k) {
|
|
return fmt.Errorf("validate tags key %s error, incorrect key", k)
|
|
}
|
|
if len(v) > 256 {
|
|
return fmt.Errorf("validate tags: tag value longer than 256")
|
|
}
|
|
if !tagPattern.MatchString(v) {
|
|
return fmt.Errorf("validate tags value %s error, incorrect value", v)
|
|
}
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// isValidBucketName validates bucket name characters (kept for compatibility)
|
|
// Deprecated: use validateBucketName instead
|
|
func isValidBucketName(name string) bool {
|
|
return validateBucketName(name) == nil
|
|
}
|
|
|
|
// generateVersionToken generates a unique, unpredictable version token
|
|
func generateVersionToken() string {
|
|
b := make([]byte, 16)
|
|
if _, err := rand.Read(b); err != nil {
|
|
// Fallback to timestamp if crypto/rand fails
|
|
return fmt.Sprintf("%x", time.Now().UnixNano())
|
|
}
|
|
return hex.EncodeToString(b)
|
|
}
|
|
|
|
// splitPath splits a path into directory and name components using stdlib
|
|
func splitPath(p string) (dir, name string) {
|
|
dir = path.Dir(p)
|
|
name = path.Base(p)
|
|
return
|
|
}
|
|
|
|
func validateNamespacePart(name string) error {
|
|
if len(name) < 1 || len(name) > 255 {
|
|
return fmt.Errorf("namespace name must be between 1 and 255 characters")
|
|
}
|
|
|
|
// Prevent path traversal and multi-segment paths
|
|
if name == "." || name == ".." {
|
|
return fmt.Errorf("namespace name cannot be '.' or '..'")
|
|
}
|
|
if strings.Contains(name, "/") {
|
|
return fmt.Errorf("namespace name cannot contain '/'")
|
|
}
|
|
|
|
// Must start and end with a letter or digit
|
|
start := name[0]
|
|
end := name[len(name)-1]
|
|
if !((start >= 'a' && start <= 'z') || (start >= '0' && start <= '9')) {
|
|
return fmt.Errorf("namespace name must start with a letter or digit")
|
|
}
|
|
if !((end >= 'a' && end <= 'z') || (end >= '0' && end <= '9')) {
|
|
return fmt.Errorf("namespace name must end with a letter or digit")
|
|
}
|
|
|
|
// Allowed characters: a-z, 0-9, _, - (hyphen interior; start/end checked above)
|
|
for _, ch := range name {
|
|
if (ch >= 'a' && ch <= 'z') || (ch >= '0' && ch <= '9') || ch == '_' || ch == '-' {
|
|
continue
|
|
}
|
|
return fmt.Errorf("invalid namespace name: only 'a-z', '0-9', '_', and '-' are allowed")
|
|
}
|
|
|
|
// Reserved prefix
|
|
if strings.HasPrefix(name, "aws") {
|
|
return fmt.Errorf("namespace name cannot start with reserved prefix 'aws'")
|
|
}
|
|
|
|
return nil
|
|
}
|
|
|
|
func normalizeNamespace(namespace []string) ([]string, error) {
|
|
if len(namespace) == 0 {
|
|
return nil, fmt.Errorf("namespace is required")
|
|
}
|
|
|
|
parts := namespace
|
|
if len(namespace) == 1 {
|
|
parts = strings.Split(namespace[0], ".")
|
|
}
|
|
|
|
normalized := make([]string, 0, len(parts))
|
|
for _, part := range parts {
|
|
if err := validateNamespacePart(part); err != nil {
|
|
return nil, err
|
|
}
|
|
normalized = append(normalized, part)
|
|
}
|
|
return normalized, nil
|
|
}
|
|
|
|
// validateNamespace validates namespace identifiers and returns an internal namespace key.
|
|
// A single dotted namespace value is interpreted as multi-level namespace for compatibility
|
|
// with path-style APIs, for example "analytics.daily" => ["analytics", "daily"].
|
|
func validateNamespace(namespace []string) (string, error) {
|
|
parts, err := normalizeNamespace(namespace)
|
|
if err != nil {
|
|
return "", err
|
|
}
|
|
return flattenNamespace(parts), nil
|
|
}
|
|
|
|
// ParseNamespace parses a namespace string into namespace parts.
|
|
func ParseNamespace(namespace string) ([]string, error) {
|
|
return normalizeNamespace([]string{namespace})
|
|
}
|
|
|
|
// validateTableName validates a table name
|
|
func validateTableName(name string) (string, error) {
|
|
if len(name) < 1 || len(name) > 255 {
|
|
return "", fmt.Errorf("table name must be between 1 and 255 characters")
|
|
}
|
|
if name == "." || name == ".." || strings.Contains(name, "/") {
|
|
return "", fmt.Errorf("invalid table name: cannot be '.', '..' or contain '/'")
|
|
}
|
|
|
|
// First character must be a letter or digit
|
|
start := name[0]
|
|
if !((start >= 'a' && start <= 'z') || (start >= '0' && start <= '9')) {
|
|
return "", fmt.Errorf("table name must start with a letter or digit")
|
|
}
|
|
|
|
// Allowed characters: a-z, 0-9, _, - (start checked above)
|
|
for _, ch := range name {
|
|
if (ch >= 'a' && ch <= 'z') || (ch >= '0' && ch <= '9') || ch == '_' || ch == '-' {
|
|
continue
|
|
}
|
|
return "", fmt.Errorf("invalid table name: only 'a-z', '0-9', '_', and '-' are allowed")
|
|
}
|
|
return name, nil
|
|
}
|
|
|
|
// ValidateTableName is a wrapper to validate table name for other packages.
|
|
func ValidateTableName(name string) (string, error) {
|
|
return validateTableName(name)
|
|
}
|
|
|
|
// flattenNamespace joins namespace elements into a single string (using dots as per AWS S3 Tables)
|
|
func flattenNamespace(namespace []string) string {
|
|
if len(namespace) == 0 {
|
|
return ""
|
|
}
|
|
return strings.Join(namespace, ".")
|
|
}
|
|
|
|
func expandNamespace(namespace string) []string {
|
|
if namespace == "" {
|
|
return nil
|
|
}
|
|
parts, err := ParseNamespace(namespace)
|
|
if err != nil {
|
|
return []string{namespace}
|
|
}
|
|
return parts
|
|
}
|