Files
seaweedfs/weed/s3api/s3tables/handler.go
T
Chris LuandGitHub ec37ef5aaa iceberg: add view rename, scan-report and snapshots=refs to the catalog (#10776)
* iceberg: add view rename, scan-report and snapshots=refs to the catalog

Three gaps against the REST spec that clients hit in normal use:

Views had no rename, though tables did and views are stored the same way,
so the move is the same catalog-only pointer move. Tables and views share
a namespace directory, so both renames now refuse the other kind instead
of moving it.

Engines POST a scan or commit report after planning; a 404 there turns
into an error line per query. Accept the report and discard it - the
catalog keeps no metrics store.

LoadTable ignored ?snapshots=refs and always returned the whole snapshot
history, which is what clients use the parameter to avoid on long-lived
tables.

* iceberg: authorize view rename against the view ARN, tighten the metrics endpoint

Review follow-ups:

The shared rename checked the source against a table ARN whatever the
kind, so a policy scoped to a view's own ARN never matched and one
written for a table ARN was evaluated for a view. The entry kind now
carries the ARN builder.

The metrics endpoint truncated a report at 1 MiB and then failed to parse
it, answering 400 for a query that had actually succeeded. Read one byte
past the limit to tell "fits" from "cut short", and discard an oversized
report instead of rejecting it. Empty bodies and reports without a
report-type are now rejected, which the REST schema requires.

?snapshots= is defined for LoadTable, so it no longer filters what
CreateTable echoes back.
2026-08-16 12:56:45 -07:00

445 lines
14 KiB
Go

package s3tables
import (
"context"
"encoding/json"
"errors"
"fmt"
"io"
"net/http"
"reflect"
"strings"
"github.com/seaweedfs/seaweedfs/weed/glog"
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
"github.com/seaweedfs/seaweedfs/weed/s3api/s3_constants"
)
const (
TablesPath = s3_constants.DefaultBucketsPath
DefaultAccountID = "000000000000"
DefaultRegion = "us-east-1"
// Extended entry attributes for metadata storage
ExtendedKeyTableBucket = "s3tables.tableBucket"
ExtendedKeyMetadata = "s3tables.metadata"
ExtendedKeyMetadataVersion = "s3tables.metadataVersion"
ExtendedKeyPolicy = "s3tables.policy"
ExtendedKeyTags = "s3tables.tags"
ExtendedKeyMaintenance = "s3tables.maintenance"
// Written by the maintenance worker, read by GetTableMaintenanceJobStatus.
// Separate from ExtendedKeyMaintenance so worker and operator writes do not
// contend on the same attribute.
ExtendedKeyMaintenanceStatus = "s3tables.maintenanceStatus"
ExtendedKeyEntryType = "s3tables.entryType"
// Entry-type marker values for ExtendedKeyEntryType. Absent or "table" means
// a table; views are stored like tables but tagged "view".
EntryTypeTable = "table"
EntryTypeView = "view"
// Maximum request body size (10MB)
maxRequestBodySize = 10 * 1024 * 1024
)
var (
ErrVersionTokenMismatch = errors.New("version token mismatch")
ErrAccessDenied = errors.New("access denied")
ErrTableAlreadyExists = errors.New("table already exists")
)
type ResourceType string
const (
ResourceTypeBucket ResourceType = "bucket"
ResourceTypeTable ResourceType = "table"
)
// S3TablesHandler handles S3 Tables API requests
type S3TablesHandler struct {
region string
accountID string
defaultAllow bool // Whether to allow access by default (for zero-config IAM)
trusted bool // Trusted local tooling (shell/admin) bypasses authorization
iamAuthorizer IAMAuthorizer
}
// NewS3TablesHandler creates a new S3 Tables handler
func NewS3TablesHandler() *S3TablesHandler {
return &S3TablesHandler{
region: DefaultRegion,
accountID: DefaultAccountID,
defaultAllow: false,
}
}
// SetRegion sets the AWS region for ARN generation
func (h *S3TablesHandler) SetRegion(region string) {
if region != "" {
h.region = region
}
}
// SetAccountID sets the AWS account ID for ARN generation
func (h *S3TablesHandler) SetAccountID(accountID string) {
if accountID != "" {
h.accountID = accountID
}
}
// SetDefaultAllow sets whether to allow access by default
func (h *S3TablesHandler) SetDefaultAllow(allow bool) {
h.defaultAllow = allow
}
// SetTrusted lets local tooling that talks to the filer directly (shell, admin
// console) bypass authorization. HTTP-facing callers must not set it.
func (h *S3TablesHandler) SetTrusted(trusted bool) {
h.trusted = trusted
}
// FilerClient interface for filer operations
type FilerClient interface {
WithFilerClient(streamingMode bool, fn func(client filer_pb.SeaweedFilerClient) error) error
}
// HandleRequest is the main entry point for S3 Tables API requests
func (h *S3TablesHandler) HandleRequest(w http.ResponseWriter, r *http.Request, filerClient FilerClient) {
operation := r.Header.Get("X-Amz-Target")
if operation != "" {
if idx := strings.LastIndex(operation, "."); idx != -1 {
operation = operation[idx+1:]
}
}
if operation == "" {
glog.V(1).Infof("S3Tables: missing X-Amz-Target header")
h.writeError(w, http.StatusBadRequest, ErrCodeInvalidRequest, "Missing X-Amz-Target header")
return
}
glog.V(3).Infof("S3Tables: handling operation %s", operation)
var err error
switch operation {
// Table Bucket operations
case "CreateTableBucket":
err = h.handleCreateTableBucket(w, r, filerClient)
case "GetTableBucket":
err = h.handleGetTableBucket(w, r, filerClient)
case "ListTableBuckets":
err = h.handleListTableBuckets(w, r, filerClient)
case "DeleteTableBucket":
err = h.handleDeleteTableBucket(w, r, filerClient)
// Table Bucket Policy operations
case "PutTableBucketPolicy":
err = h.handlePutTableBucketPolicy(w, r, filerClient)
case "GetTableBucketPolicy":
err = h.handleGetTableBucketPolicy(w, r, filerClient)
case "DeleteTableBucketPolicy":
err = h.handleDeleteTableBucketPolicy(w, r, filerClient)
// Namespace operations
case "CreateNamespace":
err = h.handleCreateNamespace(w, r, filerClient)
case "GetNamespace":
err = h.handleGetNamespace(w, r, filerClient)
case "UpdateNamespace":
err = h.handleUpdateNamespace(w, r, filerClient)
case "ListNamespaces":
err = h.handleListNamespaces(w, r, filerClient)
case "DeleteNamespace":
err = h.handleDeleteNamespace(w, r, filerClient)
// Table operations
case "CreateTable":
err = h.handleCreateTable(w, r, filerClient)
case "RegisterTable":
err = h.handleRegisterTable(w, r, filerClient)
case "GetTable":
err = h.handleGetTable(w, r, filerClient)
case "ListTables":
err = h.handleListTables(w, r, filerClient)
case "UpdateTable":
err = h.handleUpdateTable(w, r, filerClient)
case "DeleteTable":
err = h.handleDeleteTable(w, r, filerClient)
case "RenameTable":
err = h.handleRenameTable(w, r, filerClient)
// View operations
case "CreateView":
err = h.handleCreateView(w, r, filerClient)
case "GetView":
err = h.handleGetView(w, r, filerClient)
case "ListViews":
err = h.handleListViews(w, r, filerClient)
case "UpdateView":
err = h.handleUpdateView(w, r, filerClient)
case "DeleteView":
err = h.handleDeleteView(w, r, filerClient)
case "RenameView":
err = h.handleRenameView(w, r, filerClient)
// Table Policy operations
case "PutTablePolicy":
err = h.handlePutTablePolicy(w, r, filerClient)
case "GetTablePolicy":
err = h.handleGetTablePolicy(w, r, filerClient)
case "DeleteTablePolicy":
err = h.handleDeleteTablePolicy(w, r, filerClient)
// Maintenance configuration operations
case "PutTableBucketMaintenanceConfiguration":
err = h.handlePutTableBucketMaintenanceConfiguration(w, r, filerClient)
case "GetTableBucketMaintenanceConfiguration":
err = h.handleGetTableBucketMaintenanceConfiguration(w, r, filerClient)
case "PutTableMaintenanceConfiguration":
err = h.handlePutTableMaintenanceConfiguration(w, r, filerClient)
case "GetTableMaintenanceConfiguration":
err = h.handleGetTableMaintenanceConfiguration(w, r, filerClient)
case "GetTableMaintenanceJobStatus":
err = h.handleGetTableMaintenanceJobStatus(w, r, filerClient)
// Tagging operations
case "TagResource":
err = h.handleTagResource(w, r, filerClient)
case "ListTagsForResource":
err = h.handleListTagsForResource(w, r, filerClient)
case "UntagResource":
err = h.handleUntagResource(w, r, filerClient)
default:
h.writeError(w, http.StatusBadRequest, ErrCodeInvalidRequest, fmt.Sprintf("Unknown operation: %s", operation))
return
}
if err != nil {
glog.Errorf("S3Tables: error handling %s: %v", operation, err)
}
}
// Principal/authorization helpers
// getAccountID returns a stable caller identifier for ownership and permission checks.
// Reflection depends on the identity shape produced by JWT/STS auth (Account *struct{Id string},
// Claims map[string]interface{} containing string values for preferred_username/sub, and optional
// identity name/header values). Changing those fields without updating the reflection here will
// break the handler, so refactorers should replace this with a typed interface if needed.
func (h *S3TablesHandler) getAccountID(r *http.Request) string {
identityRaw := s3_constants.GetIdentityFromContext(r)
if identityRaw != nil {
// Use reflection to access identity fields and avoid import cycles.
val := reflect.ValueOf(identityRaw)
if val.Kind() == reflect.Ptr {
val = val.Elem()
}
if val.Kind() == reflect.Struct {
// Prefer stable claims from JWT/STS identities. Only "sub" is guaranteed durable per OIDC;
// preferred_username is ergonomic but can rotate and may orphan ownership data, while email
// is explicitly excluded to avoid storing PII in metadata.
claimsField := val.FieldByName("Claims")
if claimsField.IsValid() && claimsField.Kind() == reflect.Map && !claimsField.IsNil() && claimsField.Type().Key().Kind() == reflect.String {
for _, claimKey := range []string{"sub", "preferred_username"} {
claimVal := claimsField.MapIndex(reflect.ValueOf(claimKey))
if !claimVal.IsValid() {
continue
}
if claimVal.Kind() == reflect.Interface && !claimVal.IsNil() {
claimVal = claimVal.Elem()
}
if claimVal.Kind() == reflect.String {
if principal := normalizePrincipalID(claimVal.String()); principal != "" {
return principal
}
}
}
}
accountField := val.FieldByName("Account")
if accountField.IsValid() && !accountField.IsNil() {
accountVal := accountField.Elem()
if accountVal.Kind() == reflect.Struct {
idField := accountVal.FieldByName("Id")
if idField.IsValid() && idField.Kind() == reflect.String {
if principal := normalizePrincipalID(idField.String()); principal != "" {
// Account-less identities default to the admin account; only
// keep it for real admins, else use the unique identity name.
if principal != s3_constants.AccountAdminId || hasAdminAction(getIdentityActions(r)) {
return principal
}
}
}
}
}
}
}
if identityName := s3_constants.GetIdentityNameFromContext(r); identityName != "" {
if principal := normalizePrincipalID(identityName); principal != "" {
return principal
}
}
if accountID := r.Header.Get(s3_constants.AmzAccountId); accountID != "" {
if principal := normalizePrincipalID(accountID); principal != "" {
return principal
}
}
return h.accountID
}
// normalizePrincipalID collapses ARN and identity strings to a key that is stable within a single account.
// WARNING: this assumes identity names are unique per account; distinct principals such as
// arn:aws:iam::111:user/alice and arn:aws:iam::222:user/alice will both normalize to "alice".
// If future work adds multi-account support, revisit this function to include the account ID or full ARN
// so ownership checks remain correct.
func normalizePrincipalID(id string) string {
id = strings.TrimSpace(id)
if id == "" {
return ""
}
// If this is an ARN (common for assumed roles), use the trailing segment as a
// stable-ish principal key instead of embedding the full ARN in ownership fields.
if strings.HasPrefix(id, "arn:") {
if idx := strings.LastIndex(id, "/"); idx >= 0 && idx+1 < len(id) {
return strings.TrimSpace(id[idx+1:])
}
if idx := strings.LastIndex(id, ":"); idx >= 0 && idx+1 < len(id) {
return strings.TrimSpace(id[idx+1:])
}
return strings.TrimSpace(id)
}
return id
}
// getIdentityActions extracts the action list from the identity object in the request context.
// Uses reflection to avoid import cycles with s3api package.
func getIdentityActions(r *http.Request) []string {
val, ok := getIdentityStructValue(r)
if !ok {
return nil
}
actionsField := val.FieldByName("Actions")
if !actionsField.IsValid() || actionsField.Kind() != reflect.Slice {
return nil
}
// Convert actions to string slice
actions := make([]string, actionsField.Len())
for i := 0; i < actionsField.Len(); i++ {
action := actionsField.Index(i)
// Action is likely a custom type (e.g., type Action string)
// Convert to string using String() or direct string conversion
if action.Kind() == reflect.String {
actions[i] = action.String()
} else if action.CanInterface() {
// Try to convert via fmt.Sprint
actions[i] = fmt.Sprint(action.Interface())
}
}
return actions
}
// Request/Response helpers
func (h *S3TablesHandler) readRequestBody(r *http.Request, v interface{}) error {
defer r.Body.Close()
// Limit request body size to prevent unbounded reads
limitedReader := io.LimitReader(r.Body, maxRequestBodySize+1)
body, err := io.ReadAll(limitedReader)
if err != nil {
return fmt.Errorf("failed to read request body: %w", err)
}
// Check if body exceeds size limit
if len(body) > maxRequestBodySize {
return fmt.Errorf("request body too large: exceeds maximum size of %d bytes", maxRequestBodySize)
}
if len(body) == 0 {
return nil
}
if err := json.Unmarshal(body, v); err != nil {
return fmt.Errorf("failed to decode request: %w", err)
}
return nil
}
// Response writing helpers
func (h *S3TablesHandler) writeJSON(w http.ResponseWriter, status int, data interface{}) {
w.Header().Set("Content-Type", "application/x-amz-json-1.1")
w.WriteHeader(status)
if data != nil {
if err := json.NewEncoder(w).Encode(data); err != nil {
glog.Errorf("S3Tables: failed to encode response: %v", err)
}
}
}
func (h *S3TablesHandler) writeError(w http.ResponseWriter, status int, code, message string) {
w.Header().Set("Content-Type", "application/x-amz-json-1.1")
w.WriteHeader(status)
errorResponse := map[string]interface{}{
"__type": code,
"message": message,
}
if err := json.NewEncoder(w).Encode(errorResponse); err != nil {
glog.Errorf("S3Tables: failed to encode error response: %v", err)
}
}
// ARN generation helpers
func (h *S3TablesHandler) generateTableBucketARN(ownerAccountID, bucketName string) string {
return buildARN(h.region, ownerAccountID, fmt.Sprintf("bucket/%s", bucketName))
}
func (h *S3TablesHandler) generateTableARN(ownerAccountID, bucketName, tableID string) string {
return buildARN(h.region, ownerAccountID, fmt.Sprintf("bucket/%s/table/%s", bucketName, tableID))
}
func (h *S3TablesHandler) generateViewARN(ownerAccountID, bucketName, viewID string) string {
return buildARN(h.region, ownerAccountID, fmt.Sprintf("bucket/%s/view/%s", bucketName, viewID))
}
// generateS3BucketARN builds the plain S3 ARN used for IAM resource matching.
func (h *S3TablesHandler) generateS3BucketARN(bucketName string) string {
return fmt.Sprintf("arn:%s:s3:::%s", arnPartitionForRegion(h.region), bucketName)
}
func isAuthError(err error) bool {
var authErr *AuthError
return errors.As(err, &authErr) || errors.Is(err, ErrAccessDenied)
}
func (h *S3TablesHandler) readTags(ctx context.Context, client filer_pb.SeaweedFilerClient, path string) (map[string]string, error) {
data, err := h.getExtendedAttribute(ctx, client, path, ExtendedKeyTags)
if err != nil {
if errors.Is(err, ErrAttributeNotFound) {
return nil, nil
}
return nil, err
}
tags := make(map[string]string)
if err := json.Unmarshal(data, &tags); err != nil {
return nil, fmt.Errorf("failed to unmarshal tags: %w", err)
}
return tags, nil
}
func mapKeys(tags map[string]string) []string {
if len(tags) == 0 {
return nil
}
keys := make([]string, 0, len(tags))
for key := range tags {
keys = append(keys, key)
}
return keys
}