feat(base): update resource ID generation to handle Unicode characters (

#313) The resource ID generation logic has been updated in both Python and TypeScript files to handle Unicode characters. This ensures that Unicode characters are properly encoded in the resource ID string, preventing any issues with special characters. The `encode_unicode` function has been added to both files to handle the encoding. This improvement enhances the reliability and compatibility of the resource ID generation process.
pluto-lang · Aug 5, 2024 · dbbfde4 · dbbfde4
1 parent 26ee4ff
commit dbbfde4
Show file tree

Hide file tree

Showing 5 changed files with 27 additions and 3 deletions.
diff --git a/.changeset/forty-spoons-live.md b/.changeset/forty-spoons-live.md
@@ -0,0 +1,7 @@
+---
+"@plutolang/base": patch
+---
+
+feat: update resource ID generation to handle Unicode characters
+
+The resource ID generation logic has been updated in both Python and TypeScript files to handle Unicode characters. This ensures that Unicode characters are properly encoded in the resource ID string, preventing any issues with special characters. The `encode_unicode` function has been added to both files to handle the encoding. This improvement enhances the reliability and compatibility of the resource ID generation process.
diff --git a/packages/base-py/CHANGELOG.md b/packages/base-py/CHANGELOG.md
@@ -1,5 +1,11 @@
 # pluto-base
 
+## 0.0.7
+
+feat: update resource ID generation to handle Unicode characters
+
+The resource ID generation logic has been updated in both Python and TypeScript files to handle Unicode characters. This ensures that Unicode characters are properly encoded in the resource ID string, preventing any issues with special characters. The `encode_unicode` function has been added to both files to handle the encoding. This improvement enhances the reliability and compatibility of the resource ID generation process.
+
 ## 0.0.6
 
 feat: add no-op infrastructure API to client SDK

diff --git a/packages/base-py/pluto_base/utils/resource_id.py b/packages/base-py/pluto_base/utils/resource_id.py
@@ -30,7 +30,7 @@ def gen_resource_id(
         resource_type,
         provided_name,
     )
-    resource_full_id = re.sub(r"[^_0-9a-zA-Z]+", "_", "_".join(args))
+    resource_full_id = re.sub(r"[^_0-9a-zA-Z]+", "_", encode_unicode("_".join(args)))
 
     if len(resource_full_id) <= RESOURCE_ID_MAX_LENGTH:
         return resource_full_id
@@ -41,3 +41,7 @@ def gen_resource_id(
         start = len(resource_full_id) - (RESOURCE_ID_MAX_LENGTH - len(hash_digest))
         end = len(resource_full_id)
         return resource_full_id[start:end] + hash_digest
+
+
+def encode_unicode(s: str) -> str:
+    return "".join(f"\\u{ord(c):04x}" if ord(c) > 255 else c for c in s)
diff --git a/packages/base-py/pyproject.toml b/packages/base-py/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "pluto-base"
-version = "0.0.6"
+version = "0.0.7"
 description = "The Base Library for Pluto Programming Language."
 authors = ["Jade Zheng <zheng.shoujian@outlook.com>"]
 license = "Apache-2.0"

diff --git a/packages/base/utils/resource-id.ts b/packages/base/utils/resource-id.ts
@@ -35,7 +35,7 @@ export function genResourceId(...args: readonly string[]): string {
     args = [currentProjectName(), currentStackName()].concat(args);
   }
 
-  const resourceFullId = args.join("_").replace(/[^_0-9a-zA-Z]+/g, "_");
+  const resourceFullId = encodeUnicode(args.join("_")).replace(/[^_0-9a-zA-Z]+/g, "_");
   if (resourceFullId.length <= RESOURCE_ID_MAX_LENGTH) {
     return resourceFullId;
   } else {
@@ -47,3 +47,10 @@ export function genResourceId(...args: readonly string[]): string {
     return resourceFullId.substring(start, end) + hash;
   }
 }
+
+function encodeUnicode(str: string): string {
+  // eslint-disable-next-line no-control-regex
+  return str.replace(/[^\x00-\xff]/g, (c) => {
+    return "\\u" + c.charCodeAt(0).toString(16);
+  });
+}