Allow Unicode letters in bundle variable reference paths

NEXT_CHANGELOG.md

@@ -15,6 +15,7 @@
 
 
 ### Bundles
+* Bundle variable references now accept Unicode letters in path segments (e.g. `${var.变量}`). ([#5532](https://github.com/databricks/cli/pull/5532))
 * Set the default `data_security_mode` to `DATA_SECURITY_MODE_AUTO` in bundle templates ([#5452](https://github.com/databricks/cli/pull/5452)).
 * Mark vector search index index_subtype as backend_default to prevent drift after deployment ([#5454](https://github.com/databricks/cli/pull/5454)).
 * `bundle deployment migrate`: handle resources added to or removed from `databricks.yml` since the last Terraform deploy ([#5463](https://github.com/databricks/cli/pull/5463)).

acceptance/bundle/variables/unicode_reference/databricks.yml

@@ -0,0 +1,11 @@
+bundle:
+  name: unicode-vars
+
+variables:
+  变量:
+    default: hello
+
+resources:
+  jobs:
+    foo:
+      name: ${var.变量}

acceptance/bundle/variables/unicode_reference/output.txt

@@ -0,0 +1,3 @@
+
+>>> [CLI] bundle validate -o json
+"hello"

acceptance/bundle/variables/unicode_reference/script

@@ -0,0 +1 @@
+trace $CLI bundle validate -o json | jq .resources.jobs.foo.name

bundle/internal/schema/main.go

@@ -12,12 +12,16 @@ import (
 	"github.com/databricks/cli/bundle/config"
 	"github.com/databricks/cli/bundle/config/resources"
 	"github.com/databricks/cli/bundle/config/variable"
+	"github.com/databricks/cli/libs/dyn/dynvar"
 	"github.com/databricks/cli/libs/jsonschema"
 	"github.com/databricks/databricks-sdk-go/service/jobs"
 )
 
+// interpolationPattern builds a JSON Schema regex for ${prefix.path...} references.
+// Path segments use [dynvar.BaseVarDef]; unlike the runtime matcher in ref.go, this
+// requires a fixed prefix (var, resources, ...) and at least one ".segment" after it.
 func interpolationPattern(s string) string {
-	return fmt.Sprintf(`\$\{(%s(\.[a-zA-Z]+([-_]?[a-zA-Z0-9]+)*(\[[0-9]+\])*)+)\}`, s)
+	return fmt.Sprintf(`\$\{(%s(\.%s(\[[0-9]+\])*)+)\}`, s, dynvar.BaseVarDef)
 }
 
 func addInterpolationPatterns(typ reflect.Type, s jsonschema.Schema) jsonschema.Schema {

bundle/internal/schema/testdata/fail/invalid_unicode_variable_reference.yml

@@ -0,0 +1,7 @@
+bundle:
+  name: invalid-unicode-ref
+
+resources:
+  jobs:
+    foo:
+      max_concurrent_runs: ${var.🌍}

bundle/internal/schema/testdata/fail/nfd_unicode_variable_reference.yml

@@ -0,0 +1,8 @@
+bundle:
+  name: nfd-unicode-ref
+
+resources:
+  jobs:
+    foo:
+      # café in NFD (e + U+0301 combining acute); not accepted by \p{L} segment matching.
+      max_concurrent_runs: ${var.café}

bundle/internal/schema/testdata/pass/cjk_numeral_variable_reference.yml

@@ -0,0 +1,11 @@
+bundle:
+  name: cjk-numeral-var
+
+variables:
+  九世界:
+    default: 1
+
+resources:
+  jobs:
+    foo:
+      max_concurrent_runs: ${var.九世界}

bundle/internal/schema/testdata/pass/unicode_variable_reference.yml

@@ -0,0 +1,11 @@
+bundle:
+  name: unicode-vars
+
+variables:
+  变量:
+    default: hello
+
+resources:
+  jobs:
+    foo:
+      name: ${var.变量}

bundle/internal/schema/testdata/pass/variable_reference_separators.yml

@@ -0,0 +1,11 @@
+bundle:
+  name: separator-vars
+
+variables:
+  world__world:
+    default: hello
+
+resources:
+  jobs:
+    foo:
+      name: ${var.world__world}