feat: Unicode component_codes and container_codes

Bumps version to 0.44.0

Author: kdmccormick

src/openedx_content/applets/collections/models.py

@@ -109,7 +109,8 @@ class Collection(models.Model):
     # collection's opaque key:
     # e.g. "lib-collection:{org_code}:{library_code}:{collection_code}"
     #       is the opaque key for a library collection.
-    collection_code = code_field()
+    # TODO: Consider supporting unicode https://github.com/openedx/openedx-platform/issues/38413
+    collection_code = code_field(unicode=False)
 
     title = case_insensitive_char_field(
         null=False,
@@ -179,7 +180,7 @@ class Meta:
                 ],
                 name="oel_coll_uniq_lp_key",
             ),
-            code_field_check("collection_code", name="oel_coll_collection_code_regex"),
+            code_field_check("collection_code", name="oel_coll_collection_code_regex", unicode=False),
         ]
         indexes = [
             models.Index(

src/openedx_content/applets/components/models.py

@@ -180,7 +180,7 @@ def pk(self):
     # component_code is an identifier that is local to the learning_package and
     # component_type. The publishable.entity_ref is derived from component_type
     # and component_code.
-    component_code = code_field()
+    component_code = code_field(unicode=True)
 
     class Meta:
         constraints = [
@@ -198,7 +198,7 @@ class Meta:
                 ],
                 name="oel_component_uniq_lc_ct_lk",
             ),
-            code_field_check("component_code", name="oel_component_code_regex"),
+            code_field_check("component_code", name="oel_component_code_regex", unicode=True),
         ]
         indexes = [
             # Global Component-Type/Component-Code Index:

src/openedx_content/applets/containers/models.py

@@ -189,7 +189,7 @@ class Container(PublishableEntityMixin):
     # container_code is an identifier that is local to the learning_package.
     # Unlike component_code, it is unique across all container types within
     # the same LearningPackage.
-    container_code = code_field()
+    container_code = code_field(unicode=True)
 
     @property
     def id(self) -> ID:
@@ -212,7 +212,7 @@ class Meta:
                 fields=["learning_package", "container_code"],
                 name="oel_container_uniq_lp_cc",
             ),
-            code_field_check("container_code", name="oel_container_code_regex"),
+            code_field_check("container_code", name="oel_container_code_regex", unicode=True),
         ]
 
     @classmethod

src/openedx_content/migrations/0009_rename_component_local_key_to_component_code.py

@@ -59,7 +59,7 @@ class Migration(migrations.Migration):
         migrations.AddConstraint(
             model_name='component',
             constraint=models.CheckConstraint(
-                condition=django.db.models.lookups.Regex(models.F('component_code'), '^[a-zA-Z0-9_.-]+\\Z'),
+                condition=django.db.models.lookups.Regex(models.F('component_code'), '^[\\w.-]+\\Z'),
                 name='oel_component_code_regex',
                 violation_error_message='Enter a valid "code name" consisting of letters, numbers, underscores, hyphens, or periods.',
             ),

src/openedx_content/migrations/0010_add_container_code.py

@@ -89,7 +89,7 @@ class Migration(migrations.Migration):
         migrations.AddConstraint(
             model_name='container',
             constraint=models.CheckConstraint(
-                condition=django.db.models.lookups.Regex(models.F('container_code'), '^[a-zA-Z0-9_.-]+\\Z'),
+                condition=django.db.models.lookups.Regex(models.F('container_code'), '^[\\w.-]+\\Z'),
                 name='oel_container_code_regex',
                 violation_error_message='Enter a valid "code name" consisting of letters, numbers, underscores, hyphens, or periods.',
             ),

src/openedx_content/migrations/0013_unicode_container_component_codes.py

@@ -0,0 +1,57 @@
+# Generated by Django 5.2.13 on 2026-04-23 14:15
+
+import re
+
+import django.core.validators
+import django.db.models.lookups
+from django.conf import settings
+from django.db import migrations, models
+
+import openedx_django_lib.fields
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('openedx_content', '0012_rename_componentversionmedia_key_to_path'),
+        migrations.swappable_dependency(settings.AUTH_USER_MODEL),
+    ]
+
+    operations = [
+        migrations.RemoveConstraint(
+            model_name='component',
+            name='oel_component_code_regex',
+        ),
+        migrations.RemoveConstraint(
+            model_name='container',
+            name='oel_container_code_regex',
+        ),
+        migrations.AlterField(
+            model_name='collection',
+            name='collection_code',
+            field=openedx_django_lib.fields.MultiCollationCharField(db_collations={'mysql': 'utf8mb4_bin', 'sqlite': 'BINARY'}, max_length=255, validators=[django.core.validators.RegexValidator(re.compile('^[a-zA-Z0-9_.-]+\\Z'), 'Enter a valid "code name" consisting of latin letters (A-Z, a-z), numbers, underscores, hyphens, or periods.', 'invalid')]),
+        ),
+        migrations.AlterField(
+            model_name='component',
+            name='component_code',
+            field=openedx_django_lib.fields.MultiCollationCharField(db_collations={'mysql': 'utf8mb4_bin', 'sqlite': 'BINARY'}, max_length=255, validators=[django.core.validators.RegexValidator(re.compile('^[\\w.-]+\\Z'), 'Enter a valid "code name" consisting of any letters, numbers, underscores, hyphens, or periods.', 'invalid')]),
+        ),
+        migrations.AlterField(
+            model_name='container',
+            name='container_code',
+            field=openedx_django_lib.fields.MultiCollationCharField(db_collations={'mysql': 'utf8mb4_bin', 'sqlite': 'BINARY'}, max_length=255, validators=[django.core.validators.RegexValidator(re.compile('^[\\w.-]+\\Z'), 'Enter a valid "code name" consisting of any letters, numbers, underscores, hyphens, or periods.', 'invalid')]),
+        ),
+        migrations.AddConstraint(
+            model_name='component',
+            constraint=models.CheckConstraint(condition=django.db.models.lookups.Regex(models.F('component_code'), '^[\\w.-]+\\Z'), name='oel_component_code_regex', violation_error_message='Enter a valid "code name" consisting of any letters, numbers, underscores, hyphens, or periods.'),
+        ),
+        migrations.AddConstraint(
+            model_name='container',
+            constraint=models.CheckConstraint(condition=django.db.models.lookups.Regex(models.F('container_code'), '^[\\w.-]+\\Z'), name='oel_container_code_regex', violation_error_message='Enter a valid "code name" consisting of any letters, numbers, underscores, hyphens, or periods.'),
+        ),
+        migrations.AlterConstraint(
+            model_name='collection',
+            name='oel_coll_collection_code_regex',
+            constraint=models.CheckConstraint(condition=django.db.models.lookups.Regex(models.F('collection_code'), '^[a-zA-Z0-9_.-]+\\Z'), name='oel_coll_collection_code_regex', violation_error_message='Enter a valid "code name" consisting of latin letters (A-Z, a-z), numbers, underscores, hyphens, or periods.'),
+        ),
+    ]

src/openedx_core/__init__.py

@@ -6,4 +6,4 @@
 """
 
 # The version for the entire repository
-__version__ = "0.43.0"
+__version__ = "0.44.0"

src/openedx_django_lib/fields.py

@@ -119,15 +119,21 @@ def immutable_uuid_field() -> models.UUIDField:
 
 
 # Alphanumeric, hyphens, underscores, periods
-CODE_REGEX = re.compile(r"^[a-zA-Z0-9_.-]+\Z")
+CODE_REGEX_ASCII = re.compile(r"^[a-zA-Z0-9_.-]+\Z")
 
+# Anything which passes isalnum(), plus underscores, hyphens, and periods
+CODE_REGEX_UNICODE = re.compile(r"^[\w.-]+\Z", flags=re.UNICODE)
 
-_CODE_VIOLATION_MSG = _(
-    'Enter a valid "code name" consisting of letters, numbers, underscores, hyphens, or periods.'
+_CODE_VIOLATION_MSG_ASCII = _(
+    'Enter a valid "code name" consisting of latin letters (A-Z, a-z), numbers, underscores, hyphens, or periods.'
+)
+
+_CODE_VIOLATION_MSG_UNICODE = _(
+    'Enter a valid "code name" consisting of any letters, numbers, underscores, hyphens, or periods.'
 )
 
 
-def code_field(**kwargs) -> MultiCollationCharField:
+def code_field(unicode: bool, **kwargs) -> MultiCollationCharField:
     """
     Field to hold a 'code', i.e. a slug-like local identifier.
 
@@ -139,19 +145,18 @@ def code_field(**kwargs) -> MultiCollationCharField:
         blank=False,
         validators=[
             RegexValidator(
-                CODE_REGEX,
-                # Translators: "letters" means latin letters: a-z and A-Z.
-                _CODE_VIOLATION_MSG,
+                CODE_REGEX_UNICODE if unicode else CODE_REGEX_ASCII,
+                _CODE_VIOLATION_MSG_UNICODE if unicode else _CODE_VIOLATION_MSG_ASCII,
                 "invalid",
             ),
         ],
         **kwargs,
     )
 
 
-def code_field_check(field_name: str, *, name: str) -> models.CheckConstraint:
+def code_field_check(field_name: str, *, name: str, unicode: bool) -> models.CheckConstraint:
     """
-    Return a ``CheckConstraint`` that enforces :data:`CODE_REGEX` at the DB level.
+    Return a ``CheckConstraint`` that enforces :data:`CODE_REGEX_UNICODE` or :data:`CODE_REGEX_ASCII` at the DB level.
 
     Django validators (used by :func:`code_field`) are not called on ``.save()``
     or ``.update()``.  Adding this constraint ensures the regex is also enforced
@@ -162,13 +167,22 @@ def code_field_check(field_name: str, *, name: str) -> models.CheckConstraint:
 
         class Meta:
             constraints = [
-                code_field_check("my_code_field", name="myapp_mymodel_my_code_field_regex"),
+                code_field_check(
+                    "my_code_field",
+                    name="myapp_mymodel_my_code_field_regex",
+                    unicode=True/False,  # Make sure this matches the code_field!
+                ),
             ]
     """
     return models.CheckConstraint(
-        condition=Regex(models.F(field_name), CODE_REGEX.pattern),
+        condition=Regex(
+            models.F(field_name),
+            (CODE_REGEX_UNICODE if unicode else CODE_REGEX_ASCII).pattern,
+        ),
         name=name,
-        violation_error_message=_CODE_VIOLATION_MSG,
+        violation_error_message=(
+            _CODE_VIOLATION_MSG_UNICODE if unicode else _CODE_VIOLATION_MSG_ASCII
+        ),
     )