[Refactor] remove name validations for dataset workspaces and usernames (#5575)

# Description
<!-- Please include a summary of the changes and the related issue.
Please also include relevant motivation and context. List any
dependencies that are required for this change. -->

This PR removes name pattern validations for datasets, workspaces, and
users.

**Type of change**
<!-- Please delete options that are not relevant. Remember to title the
PR according to the type of change -->

- Refactor (change restructuring the codebase without changing
functionality)
- Improvement (change adding some improvement to an existing
functionality)

**How Has This Been Tested**
<!-- Please add some reference about how your feature has been tested.
-->

**Checklist**
<!-- Please go over the list and make sure you've taken everything into
account -->

- I added relevant documentation
- I followed the style guidelines of this project
- I did a self-review of my code
- I made corresponding changes to the documentation
- I confirm My changes generate no new warnings
- I have added tests that prove my fix is effective or that my feature
works
- I have added relevant notes to the CHANGELOG.md file (See
https://keepachangelog.com/)

Author: frascuchon

argilla-server/CHANGELOG.md

@@ -16,6 +16,10 @@ These are the section headers that we use:
 
 ## [Unreleased]()
 
+### Removed
+
+- Removed name pattern validation for Workspaces, Datasets, and Users. ([#5575](https://github.com/argilla-io/argilla/pull/5575))
+
 ## [2.3.0](https://github.com/argilla-io/argilla/compare/v2.2.0...v2.3.0)
 
 ### Added

argilla-server/src/argilla_server/api/schemas/v1/datasets.py

@@ -25,14 +25,16 @@
 except ImportError:
     from typing_extensions import Annotated
 
-DATASET_NAME_REGEX = r"^(?!-|_)[a-zA-Z0-9-_ ]+$"
 DATASET_NAME_MIN_LENGTH = 1
 DATASET_NAME_MAX_LENGTH = 200
 DATASET_GUIDELINES_MIN_LENGTH = 1
 DATASET_GUIDELINES_MAX_LENGTH = 10000
 
 DatasetName = Annotated[
-    constr(regex=DATASET_NAME_REGEX, min_length=DATASET_NAME_MIN_LENGTH, max_length=DATASET_NAME_MAX_LENGTH),
+    constr(
+        min_length=DATASET_NAME_MIN_LENGTH,
+        max_length=DATASET_NAME_MAX_LENGTH,
+    ),
     Field(..., description="Dataset name"),
 ]
 

argilla-server/src/argilla_server/api/schemas/v1/users.py

@@ -19,7 +19,6 @@
 from argilla_server.enums import UserRole
 from argilla_server.pydantic_v1 import BaseModel, Field, constr
 
-USER_USERNAME_REGEX = "^(?!-|_)[A-za-z0-9-_]+$"
 USER_PASSWORD_MIN_LENGTH = 8
 USER_PASSWORD_MAX_LENGTH = 100
 
@@ -43,7 +42,7 @@ class Config:
 class UserCreate(BaseModel):
     first_name: constr(min_length=1, strip_whitespace=True)
     last_name: Optional[constr(min_length=1, strip_whitespace=True)]
-    username: str = Field(regex=USER_USERNAME_REGEX, min_length=1)
+    username: str = Field(..., min_length=1)
     role: Optional[UserRole]
     password: str = Field(min_length=USER_PASSWORD_MIN_LENGTH, max_length=USER_PASSWORD_MAX_LENGTH)
 

argilla-server/src/argilla_server/api/schemas/v1/workspaces.py

@@ -16,11 +16,8 @@
 from typing import List
 from uuid import UUID
 
-from argilla_server.constants import ES_INDEX_REGEX_PATTERN
 from argilla_server.pydantic_v1 import BaseModel, Field
 
-WORKSPACE_NAME_REGEX = ES_INDEX_REGEX_PATTERN
-
 
 class Workspace(BaseModel):
     id: UUID
@@ -33,7 +30,7 @@ class Config:
 
 
 class WorkspaceCreate(BaseModel):
-    name: str = Field(regex=WORKSPACE_NAME_REGEX, min_length=1)
+    name: str = Field(min_length=1)
 
 
 class Workspaces(BaseModel):

argilla-server/src/argilla_server/cli/database/users/migrate.py

@@ -18,8 +18,6 @@
 import typer
 import yaml
 
-from argilla_server.api.schemas.v1.users import USER_USERNAME_REGEX
-from argilla_server.api.schemas.v1.workspaces import WORKSPACE_NAME_REGEX
 from argilla_server.database import AsyncSessionLocal
 from argilla_server.models import User, UserRole
 from argilla_server.pydantic_v1 import BaseModel, Field, constr
@@ -31,12 +29,12 @@
 
 
 class WorkspaceCreate(BaseModel):
-    name: str = Field(..., regex=WORKSPACE_NAME_REGEX, min_length=1)
+    name: str = Field(..., min_length=1)
 
 
 class UserCreate(BaseModel):
     first_name: constr(strip_whitespace=True)
-    username: str = Field(..., regex=USER_USERNAME_REGEX, min_length=1)
+    username: str = Field(..., min_length=1)
     role: UserRole
     api_key: constr(min_length=1)
     password_hash: constr(min_length=1)

argilla-server/src/argilla_server/constants.py

@@ -39,6 +39,4 @@
 # The metadata field name prefix defined for protected (non-searchable) values
 PROTECTED_METADATA_FIELD_PREFIX = "_"
 
-ES_INDEX_REGEX_PATTERN = r"^(?!-|_)[a-z0-9-_]+$"
-
 JS_MAX_SAFE_INTEGER = 9007199254740991

argilla-server/tests/unit/api/handlers/v1/test_datasets.py

@@ -916,10 +916,6 @@ async def test_create_dataset_with_invalid_length_guidelines(
         "dataset_json",
         [
             {"name": ""},
-            {"name": "123$abc"},
-            {"name": "unit@test"},
-            {"name": "-test-dataset"},
-            {"name": "_test-dataset"},
             {"name": "a" * (DATASET_NAME_MAX_LENGTH + 1)},
             {"name": "test-dataset", "guidelines": ""},
             {"name": "test-dataset", "guidelines": "a" * (DATASET_GUIDELINES_MAX_LENGTH + 1)},
@@ -4777,10 +4773,6 @@ async def test_update_dataset(self, async_client: "AsyncClient", db: "AsyncSessi
         [
             {"name": None},
             {"name": ""},
-            {"name": "123$abc"},
-            {"name": "unit@test"},
-            {"name": "-test-dataset"},
-            {"name": "_test-dataset"},
             {"name": "a" * (DATASET_NAME_MAX_LENGTH + 1)},
             {"name": "test-dataset", "guidelines": ""},
             {"name": "test-dataset", "guidelines": "a" * (DATASET_GUIDELINES_MAX_LENGTH + 1)},

argilla-server/tests/unit/api/handlers/v1/users/test_create_user.py

@@ -201,23 +201,6 @@ async def test_create_user_with_existent_username(
 
         assert (await db.execute(select(func.count(User.id)))).scalar() == 2
 
-    async def test_create_user_with_invalid_username(
-        self, db: AsyncSession, async_client: AsyncClient, owner_auth_header: dict
-    ):
-        response = await async_client.post(
-            self.url(),
-            headers=owner_auth_header,
-            json={
-                "first_name": "First name",
-                "last_name": "Last name",
-                "username": "invalid username",
-                "password": "12345678",
-            },
-        )
-
-        assert response.status_code == 422
-        assert (await db.execute(select(func.count(User.id)))).scalar() == 1
-
     async def test_create_user_with_invalid_min_length_first_name(
         self, db: AsyncSession, async_client: AsyncClient, owner_auth_header: dict
     ):

argilla-server/tests/unit/api/handlers/v1/workspaces/test_create_workspace.py

@@ -87,18 +87,6 @@ async def test_create_workspace_with_existent_name(
 
         assert (await db.execute(select(func.count(Workspace.id)))).scalar() == 1
 
-    async def test_create_workspace_with_invalid_name(
-        self, db: AsyncSession, async_client: AsyncClient, owner_auth_header: dict
-    ):
-        response = await async_client.post(
-            self.url(),
-            headers=owner_auth_header,
-            json={"name": "invalid name"},
-        )
-
-        assert response.status_code == 422
-        assert (await db.execute(select(func.count(Workspace.id)))).scalar() == 0
-
     async def test_create_workspace_with_invalid_min_length_name(
         self, db: AsyncSession, async_client: AsyncClient, owner_auth_header: dict
     ):

argilla-server/tests/unit/cli/database/users/test_create.py

@@ -15,11 +15,11 @@
 from typing import TYPE_CHECKING
 
 import pytest
-from argilla_server.contexts import accounts
-from argilla_server.models import User, UserRole, Workspace
 from click.testing import CliRunner
 from typer import Typer
 
+from argilla_server.contexts import accounts
+from argilla_server.models import User, UserRole, Workspace
 from tests.factories import UserSyncFactory, WorkspaceSyncFactory
 
 if TYPE_CHECKING:
@@ -131,17 +131,6 @@ def test_create_with_input_username(sync_db: "Session", cli_runner: CliRunner, c
     assert sync_db.query(User).filter_by(username="username").first()
 
 
-def test_create_with_invalid_username(sync_db: "Session", cli_runner: CliRunner, cli: Typer):
-    result = cli_runner.invoke(
-        cli,
-        "database users create --first-name first-name --username -Invalid-Username --password 12345678 --role owner",
-    )
-
-    assert result.exit_code == 1
-    assert sync_db.query(User).count() == 0
-    assert sync_db.query(Workspace).count() == 0
-
-
 def test_create_with_existing_username(sync_db: "Session", cli_runner: CliRunner, cli: Typer):
     UserSyncFactory.create(username="username")
 
@@ -243,15 +232,3 @@ def test_create_with_existent_workspaces(sync_db: "Session", cli_runner: CliRunn
     user = sync_db.query(User).filter_by(username="username").first()
     assert user
     assert [ws.name for ws in user.workspaces] == ["workspace-a", "workspace-b", "workspace-c"]
-
-
-def test_create_with_invalid_workspaces(sync_db: "Session", cli_runner: CliRunner, cli: Typer):
-    result = cli_runner.invoke(
-        cli,
-        "database users create --first-name first-name --username username --role owner --password 12345678 "
-        "--workspace workspace-a --workspace 'invalid workspace' --workspace workspace-c",
-    )
-
-    assert result.exit_code == 1
-    assert sync_db.query(User).count() == 0
-    assert sync_db.query(Workspace).count() == 0