mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-08-17 20:57:27 +00:00
* fix(iceberg): use dot separator for namespace paths instead of unit separator The Iceberg REST Catalog handler was using \x1F (unit separator) to join multi-level namespaces when constructing S3 location and filer paths. The S3 Tables storage layer uses "." (dot) as the namespace separator, causing tables created via the Iceberg REST API to point to different paths than where S3 Tables actually stores them. Fixes #8959 * fix(iceberg): use dot separator in log messages for readable namespace output * fix(iceberg): use path.Join for S3 location path segments Use path.Join to construct the namespace/table path segments in fallback S3 locations for robustness and consistency with handleCreateTable. * test(iceberg): add multi-level namespace integration tests for Spark and Trino Add regression tests for #8959 that create a two-level namespace (e.g. "analytics.daily"), create a table under it, insert data, and query it back. This exercises the dot-separated namespace path construction and verifies that Spark/Trino can actually read the data at the S3 location returned by the Iceberg REST API. * fix(test): enable nested namespace in Trino Iceberg catalog config Trino requires `iceberg.rest-catalog.nested-namespace-enabled=true` to support multi-level namespaces. Without this, CREATE SCHEMA with a dotted name fails with "Nested namespace is not enabled for this catalog". * fix(test): parse Trino COUNT(*) output as integer instead of substring match Avoids false matches from strings.Contains(output, "3") by parsing the actual numeric result with strconv.Atoi and asserting equality. * fix(test): use separate Trino config for nested namespace test The nested-namespace-enabled=true setting in Trino changes how SHOW SCHEMAS works, causing "Internal error" for all tests sharing that catalog config. Move the flag to a dedicated config used only by TestTrinoMultiLevelNamespace. * fix(iceberg): support parent query parameter in ListNamespaces for nested namespaces Add handling for the Iceberg REST spec's `parent` query parameter in handleListNamespaces. When Trino has nested-namespace-enabled=true, it sends `GET /v1/namespaces?parent=<ns>` to list child namespaces. The parent value is decoded from the Iceberg unit separator format and converted to a dot-separated prefix for the S3 Tables layer. Also simplify TestTrinoMultiLevelNamespace to focus on namespace operations (create, list, show tables) rather than data operations, since Trino's REST catalog has a non-empty location check that conflicts with server-side metadata creation. * fix(test): expand Trino multi-level namespace test and merge config helpers - Expand TestTrinoMultiLevelNamespace to create a table with explicit location, insert rows, query them back, and verify the S3 file path contains the dot-separated namespace (not \x1F). This ensures the original #8959 bug would be caught by the Trino integration test. - Merge writeTrinoConfig and writeTrinoNestedNamespaceConfig into a single parameterized function using functional options.
160 lines
4.5 KiB
Go
160 lines
4.5 KiB
Go
package iceberg
|
|
|
|
import (
|
|
"encoding/json"
|
|
"fmt"
|
|
"net/http"
|
|
"os"
|
|
"strconv"
|
|
"strings"
|
|
|
|
"github.com/gorilla/mux"
|
|
"github.com/seaweedfs/seaweedfs/weed/glog"
|
|
"github.com/seaweedfs/seaweedfs/weed/s3api/s3_constants"
|
|
"github.com/seaweedfs/seaweedfs/weed/s3api/s3tables"
|
|
)
|
|
|
|
// parseNamespace parses the namespace from path parameter.
|
|
// Iceberg uses unit separator (0x1F) for multi-level namespaces.
|
|
// Note: mux already decodes URL-encoded path parameters, so we only split by unit separator.
|
|
func parseNamespace(encoded string) []string {
|
|
if encoded == "" {
|
|
return nil
|
|
}
|
|
parts := strings.Split(encoded, "\x1F")
|
|
// Filter empty parts
|
|
result := make([]string, 0, len(parts))
|
|
for _, p := range parts {
|
|
if p != "" {
|
|
result = append(result, p)
|
|
}
|
|
}
|
|
return result
|
|
}
|
|
|
|
// encodeNamespace encodes namespace parts using the Iceberg REST protocol's
|
|
// unit separator (0x1F) convention. This is only appropriate for protocol-level
|
|
// encoding (e.g. URL path parameters), NOT for filesystem/S3 paths.
|
|
func encodeNamespace(parts []string) string {
|
|
return strings.Join(parts, "\x1F")
|
|
}
|
|
|
|
// flattenNamespacePath joins namespace parts with "." for use in S3 location
|
|
// and filer paths, matching the S3 Tables storage layer convention.
|
|
func flattenNamespacePath(parts []string) string {
|
|
return strings.Join(parts, ".")
|
|
}
|
|
|
|
func parseS3Location(location string) (bucketName, tablePath string, err error) {
|
|
if !strings.HasPrefix(location, "s3://") {
|
|
return "", "", fmt.Errorf("unsupported location: %s", location)
|
|
}
|
|
trimmed := strings.TrimPrefix(location, "s3://")
|
|
trimmed = strings.TrimSuffix(trimmed, "/")
|
|
if trimmed == "" {
|
|
return "", "", fmt.Errorf("invalid location: %s", location)
|
|
}
|
|
parts := strings.SplitN(trimmed, "/", 2)
|
|
bucketName = parts[0]
|
|
if bucketName == "" {
|
|
return "", "", fmt.Errorf("invalid location bucket: %s", location)
|
|
}
|
|
if len(parts) == 2 {
|
|
tablePath = parts[1]
|
|
}
|
|
return bucketName, tablePath, nil
|
|
}
|
|
|
|
func tableLocationFromMetadataLocation(metadataLocation string) string {
|
|
trimmed := strings.TrimSuffix(metadataLocation, "/")
|
|
if idx := strings.LastIndex(trimmed, "/metadata/"); idx != -1 {
|
|
return trimmed[:idx]
|
|
}
|
|
return trimmed
|
|
}
|
|
|
|
// writeJSON writes a JSON response.
|
|
func writeJSON(w http.ResponseWriter, status int, v interface{}) {
|
|
w.Header().Set("Content-Type", "application/json")
|
|
w.WriteHeader(status)
|
|
if v != nil {
|
|
data, err := json.Marshal(v)
|
|
if err != nil {
|
|
glog.Errorf("Iceberg: failed to encode response: %v", err)
|
|
return
|
|
}
|
|
w.Write(data)
|
|
}
|
|
}
|
|
|
|
// writeError writes an Iceberg error response.
|
|
func writeError(w http.ResponseWriter, status int, errType, message string) {
|
|
resp := ErrorResponse{
|
|
Error: ErrorModel{
|
|
Message: message,
|
|
Type: errType,
|
|
Code: status,
|
|
},
|
|
}
|
|
writeJSON(w, status, resp)
|
|
}
|
|
|
|
// getBucketFromPrefix extracts table bucket name from prefix parameter.
|
|
// For now, we use the prefix as the table bucket name.
|
|
func getBucketFromPrefix(r *http.Request) string {
|
|
vars := mux.Vars(r)
|
|
if prefix := vars["prefix"]; prefix != "" {
|
|
return prefix
|
|
}
|
|
if bucket := os.Getenv("S3TABLES_DEFAULT_BUCKET"); bucket != "" {
|
|
return bucket
|
|
}
|
|
// Default bucket if no prefix - use "warehouse" for Iceberg
|
|
return "warehouse"
|
|
}
|
|
|
|
// buildTableBucketARN builds an ARN for a table bucket.
|
|
func buildTableBucketARN(bucketName string) string {
|
|
arn, _ := s3tables.BuildBucketARN(s3tables.DefaultRegion, s3_constants.AccountAdminId, bucketName)
|
|
return arn
|
|
}
|
|
|
|
const (
|
|
defaultListPageSize = 1000
|
|
maxListPageSize = 1000
|
|
)
|
|
|
|
func getPaginationQueryParam(r *http.Request, primary, fallback string) string {
|
|
if v := strings.TrimSpace(r.URL.Query().Get(primary)); v != "" {
|
|
return v
|
|
}
|
|
return strings.TrimSpace(r.URL.Query().Get(fallback))
|
|
}
|
|
|
|
func parsePagination(r *http.Request) (pageToken string, pageSize int, err error) {
|
|
pageToken = getPaginationQueryParam(r, "pageToken", "page-token")
|
|
pageSize = defaultListPageSize
|
|
|
|
pageSizeValue := getPaginationQueryParam(r, "pageSize", "page-size")
|
|
if pageSizeValue == "" {
|
|
return pageToken, pageSize, nil
|
|
}
|
|
|
|
parsedPageSize, parseErr := strconv.Atoi(pageSizeValue)
|
|
if parseErr != nil || parsedPageSize <= 0 {
|
|
return pageToken, 0, fmt.Errorf("invalid pageSize %q: must be a positive integer", pageSizeValue)
|
|
}
|
|
if parsedPageSize > maxListPageSize {
|
|
return pageToken, 0, fmt.Errorf("invalid pageSize %q: must be <= %d", pageSizeValue, maxListPageSize)
|
|
}
|
|
|
|
return pageToken, parsedPageSize, nil
|
|
}
|
|
|
|
func normalizeNamespaceProperties(properties map[string]string) map[string]string {
|
|
if properties == nil {
|
|
return map[string]string{}
|
|
}
|
|
return properties
|
|
}
|