Files
s3/test/s3tables/catalog/pyiceberg_test.go
zooqueen dd74d3e6d6 Replace AGPL MinIO fork with Apache-2.0 SeaweedFS fork; rebrand CLI weed->s3
hanzoai/s3 was an AGPL-3.0 MinIO fork whose network-copyleft blocks embedding
and reselling as a managed service. Replace it wholesale with a fork of
SeaweedFS (github.com/seaweedfs/seaweedfs, Apache-2.0, Go) which ships a
built-in S3 gateway + Filer.

- License: AGPL-3.0 -> Apache-2.0 (upstream LICENSE kept verbatim, incl.
  "Copyright 2025 Chris Lu"); NOTICE added crediting SeaweedFS. No AGPL/BUSL/
  SSPL/GPL or enterprise ("ee") files remain.
- Module: go.mod path set to github.com/hanzoai/s3 with a self-replace
  (replace github.com/seaweedfs/seaweedfs => ./) so the ~1800 internal Go files
  keep their upstream import paths with zero churn. Internal identifiers and
  import paths are intentionally NOT renamed.
- CLI rebrand: the binary is built as `s3` (was `weed`); root usage, per-command
  help/usage/flag strings, shell autocomplete program name, and the product name
  in CLI output now read "Hanzo S3" / `s3`. Users never see `weed`.
  (e.g. `s3 server`, `s3 filer`, `s3 master`, `s3 volume`, `s3 s3`, `s3 mount`.)
- Build: `make` (or `go build -o s3 ./weed`) builds the `s3` binary green;
  `cmd/weed-db` and `cmd/weed-sql` also build; `go vet ./weed/command/` clean.
- README/LLM.md rewritten for Hanzo S3; AGENTS.md/CLAUDE.md symlinks preserved.
- Dropped a 33MB prebuilt Mach-O `stress` binary upstream had committed; `.gitignore`
  updated to ignore the `s3` build output.
2026-06-18 23:41:25 -07:00

138 lines
4.4 KiB
Go

// Package catalog provides integration tests for the Iceberg REST Catalog API.
// This file adds PyIceberg-based compatibility tests using Docker.
package catalog
import (
"fmt"
"os"
"os/exec"
"path/filepath"
"testing"
)
// TestPyIcebergRestCatalog tests the Iceberg REST Catalog using PyIceberg client in Docker.
// This provides a more comprehensive test than DuckDB as PyIceberg fully exercises the REST API.
//
// Prerequisites:
// - Docker must be available
// - SeaweedFS must be running with Iceberg REST enabled
//
// To run manually:
//
// cd test/s3tables/catalog
// docker compose -f docker-compose.test.yaml up --build
func TestPyIcebergRestCatalog(t *testing.T) {
if testing.Short() {
t.Skip("Skipping integration test in short mode")
}
env := sharedEnv
if !env.dockerAvailable {
t.Skip("Docker not available, skipping PyIceberg integration test")
}
// Create the test bucket first
bucketName := "pyiceberg-compat-test-" + randomSuffix()
createTableBucket(t, env, bucketName)
// Build the test working directory path
testDir := filepath.Join(env.seaweedDir, "test", "s3tables", "catalog")
// Run PyIceberg test using Docker
catalogURL := fmt.Sprintf("http://host.docker.internal:%d", env.icebergPort)
s3Endpoint := fmt.Sprintf("http://host.docker.internal:%d", env.s3Port)
warehouse := fmt.Sprintf("s3://%s/", bucketName)
// Build the test image first for faster repeated runs
buildCmd := exec.Command("docker", "build", "-t", "iceberg-rest-test", "-f", "Dockerfile.pyiceberg", ".")
buildCmd.Dir = testDir
if out, err := buildCmd.CombinedOutput(); err != nil {
t.Fatalf("Failed to build test image: %v\n%s", err, string(out))
}
cmd := exec.Command("docker", "run", "--rm",
"--add-host", "host.docker.internal:host-gateway",
"-e", fmt.Sprintf("AWS_ENDPOINT_URL=%s", s3Endpoint),
"-v", fmt.Sprintf("%s:/app:ro", testDir),
"iceberg-rest-test",
"python3", "/app/test_rest_catalog.py",
"--catalog-url", catalogURL,
"--warehouse", warehouse,
"--prefix", bucketName,
)
cmd.Dir = testDir
cmd.Stdout = os.Stdout
cmd.Stderr = os.Stderr
t.Logf("Running PyIceberg REST catalog test...")
t.Logf(" Catalog URL: %s", catalogURL)
t.Logf(" Warehouse: %s", warehouse)
if err := cmd.Run(); err != nil {
t.Errorf("PyIceberg test failed: %v", err)
}
}
// TestPyIcebergRestCatalogAuthenticated tests the Iceberg REST Catalog using PyIceberg with authentication.
// This test uses the default admin credentials that SeaweedFS creates on startup.
func TestPyIcebergRestCatalogAuthenticated(t *testing.T) {
if testing.Short() {
t.Skip("Skipping integration test in short mode")
}
env := sharedEnv
if !env.dockerAvailable {
t.Skip("Docker not available, skipping PyIceberg integration test")
}
// Use default admin credentials
testAccessKey := "admin"
testSecretKey := "admin"
// Create the test bucket first (using unauthenticated request, which works with DefaultAllow)
bucketName := "pyiceberg-auth-test-" + randomSuffix()
createTableBucket(t, env, bucketName)
// Build the test working directory path
testDir := filepath.Join(env.seaweedDir, "test", "s3tables", "catalog")
// Run PyIceberg test using Docker with authentication
catalogURL := fmt.Sprintf("http://host.docker.internal:%d", env.icebergPort)
s3Endpoint := fmt.Sprintf("http://host.docker.internal:%d", env.s3Port)
warehouse := fmt.Sprintf("s3://%s/", bucketName)
// Build the test image first for faster repeated runs
buildCmd := exec.Command("docker", "build", "-t", "iceberg-rest-test", "-f", "Dockerfile.pyiceberg", ".")
buildCmd.Dir = testDir
if out, err := buildCmd.CombinedOutput(); err != nil {
t.Fatalf("Failed to build test image: %v\n%s", err, string(out))
}
cmd := exec.Command("docker", "run", "--rm",
"--add-host", "host.docker.internal:host-gateway",
"-e", fmt.Sprintf("AWS_ENDPOINT_URL=%s", s3Endpoint),
"-v", fmt.Sprintf("%s:/app:ro", testDir),
"iceberg-rest-test",
"python3", "/app/test_rest_catalog_auth.py",
"--catalog-url", catalogURL,
"--warehouse", warehouse,
"--prefix", bucketName,
"--access-key", testAccessKey,
"--secret-key", testSecretKey,
)
cmd.Dir = testDir
cmd.Stdout = os.Stdout
cmd.Stderr = os.Stderr
t.Logf("Running PyIceberg REST catalog test with authentication...")
t.Logf(" Catalog URL: %s", catalogURL)
t.Logf(" Warehouse: %s", warehouse)
t.Logf(" Access Key: %s", testAccessKey)
if err := cmd.Run(); err != nil {
t.Errorf("PyIceberg authenticated test failed: %v", err)
}
}