workspace import-dir: default-exclude .git, .databricks, node_modules

NEXT_CHANGELOG.md

@@ -10,6 +10,7 @@
 
 * Added `databricks aitools` command group for installing Databricks skills into your coding agents (Claude Code, Cursor, Codex CLI, OpenCode, GitHub Copilot, Antigravity). Skills are fetched from [github.com/databricks/databricks-agent-skills](https://github.com/databricks/databricks-agent-skills) and either symlinked into each agent's skills directory or copied into the current project. Use `databricks aitools install` to set up, `update` to pull newer versions, `list` to see what's available, and `uninstall` to remove them. Pick where they go with `--scope=project|global` (`--scope=both` is accepted on `update` and `list`).
 * `[__settings__].default_profile` is now consulted as a fallback by `databricks api`, `databricks auth token`, and bundle commands when neither `--profile` nor `DATABRICKS_CONFIG_PROFILE` is set. `databricks auth token` continues to give precedence to `DATABRICKS_HOST` over `default_profile`. For bundle commands, `default_profile` only applies when the bundle does not pin its own `workspace.host`.
+* `databricks workspace import-dir` now skips `.git`, `.databricks`, and `node_modules` directories during recursive imports. To import one of these directories deliberately, pass it as `SOURCE_PATH` ([#5118](https://github.com/databricks/cli/pull/5118)).
 * `databricks postgres create-role --help` now documents the `--json` body shape and rejects the common mistake of wrapping the body in `{"role": ...}` client-side with a hint pointing at the correct shape ([#5111](https://github.com/databricks/cli/pull/5111)).
 
 ### Bundles

cmd/workspace/workspace/import_dir.go

@@ -23,6 +23,22 @@ type importDirOptions struct {
 	overwrite bool
 }
 
+// defaultSkipDirs are directory names skipped when walking the source tree.
+// The previous behavior copied these verbatim into the workspace, which:
+//   - leaks .git/config (often containing template-repo origin URLs and
+//     occasionally cached credentials) into deployed app source trees
+//   - copies the local bundle cache (.databricks) on top of any remote one
+//   - uploads node_modules/ for JS/TS apps, which is large and gets
+//     reinstalled in the runtime anyway
+//
+// Reported as DEPLOY-04 #2 in the EMEA Apps gaps doc; users have been
+// working around it by post-deploy scrubbing scripts.
+var defaultSkipDirs = map[string]struct{}{
+	".git":         {},
+	".databricks":  {},
+	"node_modules": {},
+}
+
 // The callback function imports the file specified at sourcePath. This function is
 // meant to be used in conjunction with fs.WalkDir
 //
@@ -48,6 +64,15 @@ func (opts importDirOptions) callback(ctx context.Context, workspaceFiler filer.
 			return err
 		}
 
+		// Skip default-excluded directories (e.g. .git, .databricks). The check
+		// excludes the explicit root so a user who passes ".git" as the source
+		// can still copy it deliberately.
+		if d.IsDir() && sourcePath != sourceDir {
+			if _, skip := defaultSkipDirs[d.Name()]; skip {
+				return fs.SkipDir
+			}
+		}
+
 		// localName is the name for the file in the local file system
 		localName, err := filepath.Rel(sourceDir, sourcePath)
 		if err != nil {
@@ -117,6 +142,10 @@ func newImportDir() *cobra.Command {
 	cmd.Long = `
 Import a directory recursively from the local file system to a Databricks workspace.
 Notebooks will have their extensions (one of .scala, .py, .sql, .ipynb, .r) stripped
+
+By default, .git, .databricks, and node_modules directories encountered during
+the recursive import are skipped. To import one of these directories deliberately,
+pass it as SOURCE_PATH.
 `
 
 	cmd.Annotations = make(map[string]string)

cmd/workspace/workspace/import_dir_test.go

@@ -0,0 +1,156 @@
+package workspace
+
+import (
+	"context"
+	"io"
+	"io/fs"
+	"os"
+	"path/filepath"
+	"slices"
+	"testing"
+
+	"github.com/databricks/cli/libs/cmdio"
+	"github.com/databricks/cli/libs/filer"
+	"github.com/databricks/cli/libs/flags"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// recordingFiler captures Mkdir and Write calls so a test can assert which
+// paths were visited by the import-dir walker.
+type recordingFiler struct {
+	dirs  []string
+	files []string
+}
+
+func (r *recordingFiler) Mkdir(ctx context.Context, p string) error {
+	r.dirs = append(r.dirs, p)
+	return nil
+}
+
+func (r *recordingFiler) Write(ctx context.Context, p string, reader io.Reader, mode ...filer.WriteMode) error {
+	r.files = append(r.files, p)
+	return nil
+}
+
+func (r *recordingFiler) Read(ctx context.Context, p string) (io.ReadCloser, error) {
+	return nil, fs.ErrNotExist
+}
+
+func (r *recordingFiler) Delete(ctx context.Context, p string, mode ...filer.DeleteMode) error {
+	return nil
+}
+
+func (r *recordingFiler) ReadDir(ctx context.Context, p string) ([]fs.DirEntry, error) {
+	return nil, fs.ErrNotExist
+}
+
+func (r *recordingFiler) Stat(ctx context.Context, name string) (fs.FileInfo, error) {
+	return nil, fs.ErrNotExist
+}
+
+func writeFile(t *testing.T, root, rel, contents string) {
+	t.Helper()
+	full := filepath.Join(root, rel)
+	require.NoError(t, os.MkdirAll(filepath.Dir(full), 0o755))
+	require.NoError(t, os.WriteFile(full, []byte(contents), 0o644))
+}
+
+func runWalk(t *testing.T, sourceDir string) *recordingFiler {
+	t.Helper()
+	rec := &recordingFiler{}
+	ctx := cmdio.InContext(t.Context(),
+		cmdio.NewIO(t.Context(), flags.OutputText, nil, io.Discard, io.Discard, "", ""))
+	opts := importDirOptions{sourceDir: sourceDir, targetDir: "/Workspace/x", overwrite: true}
+	cb := opts.callback(ctx, rec)
+	require.NoError(t, filepath.WalkDir(sourceDir, cb))
+	return rec
+}
+
+func TestImportDirSkipsGitDirectory(t *testing.T) {
+	src := t.TempDir()
+	writeFile(t, src, "app.py", "print('hi')")
+	writeFile(t, src, ".git/config", "[remote]\n  url = git@github.com:org/template.git")
+	writeFile(t, src, ".git/HEAD", "ref: refs/heads/main")
+	writeFile(t, src, ".git/objects/abc123", "binary")
+
+	rec := runWalk(t, src)
+
+	slices.Sort(rec.files)
+	assert.Equal(t, []string{"app.py"}, rec.files)
+	for _, d := range rec.dirs {
+		assert.NotContains(t, d, ".git", "no .git directory should be created in the workspace")
+	}
+}
+
+func TestImportDirSkipsNestedGitDirectory(t *testing.T) {
+	src := t.TempDir()
+	writeFile(t, src, "app.py", "print('hi')")
+	writeFile(t, src, "vendor/sub/.git/config", "[remote]\n  url = ...")
+	writeFile(t, src, "vendor/sub/lib.py", "def f(): pass")
+
+	rec := runWalk(t, src)
+
+	slices.Sort(rec.files)
+	assert.Equal(t, []string{"app.py", filepath.ToSlash("vendor/sub/lib.py")}, rec.files)
+	for _, d := range rec.dirs {
+		assert.NotContains(t, d, ".git")
+	}
+}
+
+func TestImportDirSkipsDatabricksCacheDirectory(t *testing.T) {
+	src := t.TempDir()
+	writeFile(t, src, "databricks.yml", "bundle:\n  name: x")
+	writeFile(t, src, ".databricks/bundle/state.json", "{}")
+
+	rec := runWalk(t, src)
+
+	slices.Sort(rec.files)
+	assert.Equal(t, []string{"databricks.yml"}, rec.files)
+	for _, d := range rec.dirs {
+		assert.NotContains(t, d, ".databricks")
+	}
+}
+
+func TestImportDirSkipsNodeModulesDirectory(t *testing.T) {
+	src := t.TempDir()
+	writeFile(t, src, "package.json", "{}")
+	writeFile(t, src, "app.js", "console.log('hi')")
+	writeFile(t, src, "node_modules/react/index.js", "module.exports = {}")
+	writeFile(t, src, "node_modules/.package-lock.json", "{}")
+
+	rec := runWalk(t, src)
+
+	slices.Sort(rec.files)
+	assert.Equal(t, []string{"app.js", "package.json"}, rec.files)
+	for _, d := range rec.dirs {
+		assert.NotContains(t, d, "node_modules")
+	}
+}
+
+func TestImportDirCopiesGitignoreFile(t *testing.T) {
+	src := t.TempDir()
+	writeFile(t, src, ".gitignore", "*.pyc\n")
+	writeFile(t, src, "app.py", "print('hi')")
+
+	rec := runWalk(t, src)
+
+	slices.Sort(rec.files)
+	assert.Equal(t, []string{".gitignore", "app.py"}, rec.files)
+}
+
+func TestImportDirAllowsExplicitGitRoot(t *testing.T) {
+	// If a user explicitly passes a .git directory as the source root, copy
+	// it: the skip rule applies to .git dirs encountered during the walk,
+	// not to a deliberately-named root.
+	src := t.TempDir()
+	gitRoot := filepath.Join(src, ".git")
+	require.NoError(t, os.MkdirAll(gitRoot, 0o755))
+	writeFile(t, gitRoot, "HEAD", "ref: refs/heads/main")
+	writeFile(t, gitRoot, "config", "[core]\n")
+
+	rec := runWalk(t, gitRoot)
+
+	slices.Sort(rec.files)
+	assert.Equal(t, []string{"HEAD", "config"}, rec.files)
+}