Renaming part2 (#2665)

* rename the space

* rename hub-ci users/orgs + default databases

.github/workflows/_e2e_tests.yml

@@ -51,7 +51,7 @@ jobs:
           WORKER_SLEEP_SECONDS: "1"
           MONGO_PORT: ${{ env.mongo-port }}
           MONGO_REPLICASET: ${{ env.replicaset }}
-          COMMON_BLOCKED_DATASETS: "DSSUser/blocked-*"
+          COMMON_BLOCKED_DATASETS: "DVUser/blocked-*"
           ADMIN_HF_ORGANIZATION: "valid_org"
           E2E_ADMIN_USER_TOKEN: "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"
           # the containers need to access S3 and Cloudfront
@@ -109,7 +109,7 @@ jobs:
           PORT_REVERSE_PROXY: "8000"
           PROMETHEUS_MULTIPROC_DIR: "/tmp"
           WORKER_SLEEP_SECONDS: "1"
-          COMMON_BLOCKED_DATASETS: "DSSUser/blocked-*"
+          COMMON_BLOCKED_DATASETS: "DVUser/blocked-*"
           ADMIN_HF_ORGANIZATION: "valid_org"
           E2E_ADMIN_USER_TOKEN: "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"
         run: |

e2e/Makefile

@@ -16,7 +16,7 @@ export SEARCH_UVICORN_PORT := 9083
 export COMMON_HF_ENDPOINT := https://hub-ci.huggingface.co
 export COMMON_HF_TOKEN := hf_app_datasets-server_token
 # ^ hard coded, see e2e/tests/fixtures/hub.py
-export COMMON_BLOCKED_DATASETS := DSSUser/blocked-*
+export COMMON_BLOCKED_DATASETS := DVUser/blocked-*
 export LOG_LEVEL := DEBUG
 export MONGO_PORT := 27050
 export PARQUET_AND_INFO_COMMITTER_HF_TOKEN := hf_app_datasets-server-parquet-converter_token

e2e/tests/constants.py

@@ -4,14 +4,14 @@
 # see https://github.com/huggingface/moon-landing/blob/main/server/scripts/staging-seed-db.ts
 CI_APP_TOKEN = "hf_app_datasets-server_token"
 CI_HUB_ENDPOINT = "https://hub-ci.huggingface.co"
-NORMAL_USER = "DSSUser"
+NORMAL_USER = "DVUser"
 NORMAL_USER_TOKEN = "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"
 NORMAL_USER_COOKIE = "oMidckPVQYumfKrAHNYKqnbacRoLaMppHRRlfNbupNahzAHCzInBVbhgGosDneYXHVTKkkWygoMDxBfFUkFPIPiVWBtZtSTYIYTScnEKAJYkyGBAcbVTbokAygCCTWvH"
-NORMAL_ORG = "DSSNormalOrg"
-PRO_USER = "DSSProUser"
+NORMAL_ORG = "DVNormalOrg"
+PRO_USER = "DVProUser"
 PRO_USER_TOKEN = "hf_pro_user_token"
-ENTERPRISE_ORG = "DSSEnterpriseOrg"
-ENTERPRISE_USER = "DSSEnterpriseUser"
+ENTERPRISE_ORG = "DVEnterpriseOrg"
+ENTERPRISE_USER = "DVEnterpriseUser"
 ENTERPRISE_USER_TOKEN = "hf_enterprise_user_token"
 
 DATA = [

e2e/tests/test_11_api.py

@@ -223,7 +223,7 @@ def test_normal_user_blocked_private(csv_path: str) -> None:
         token=NORMAL_USER_TOKEN,
         files={"data.csv": csv_path},
         dataset_prefix="blocked-",
-        # ^ should be caught by COMMON_BLOCKED_DATASETS := "DSSUser/blocked-*"
+        # ^ should be caught by COMMON_BLOCKED_DATASETS := "DVUser/blocked-*"
         repo_settings={"private": True},
     ) as dataset:
         poll_parquet_until_ready_and_assert(
@@ -240,7 +240,7 @@ def test_normal_user_blocked_public(csv_path: str) -> None:
         token=NORMAL_USER_TOKEN,
         files={"data.csv": csv_path},
         dataset_prefix="blocked-",
-        # ^ should be caught by COMMON_BLOCKED_DATASETS := "DSSUser/blocked-*"
+        # ^ should be caught by COMMON_BLOCKED_DATASETS := "DVUser/blocked-*"
     ) as dataset:
         poll_parquet_until_ready_and_assert(
             dataset=dataset, expected_status_code=501, expected_error_code="DatasetInBlockListError"

front/admin_ui/README.md

@@ -12,7 +12,7 @@ pinned: false
 
 ## Datasets-server Admin UI
 
-Deployed at (internal) https://huggingface.co/spaces/datasets-maintainers/datasets-server-admin-ui
+Deployed at (internal) https://huggingface.co/spaces/datasets-maintainers/dataset-viewer-admin-ui
 
 ### Setup:
 

front/admin_ui/app.py

@@ -18,14 +18,14 @@
 
 DEV = os.environ.get("DEV", False)
 HF_ENDPOINT = os.environ.get("HF_ENDPOINT", "https://huggingface.co")
-PROD_DSS_ENDPOINT = os.environ.get(
-    "PROD_DSS_ENDPOINT", "https://datasets-server.huggingface.co"
+PROD_DV_ENDPOINT = os.environ.get(
+    "PROD_DV_ENDPOINT", "https://datasets-server.huggingface.co"
 )
-DEV_DSS_ENDPOINT = os.environ.get("DEV_DSS_ENDPOINT", "http://localhost:8100")
+DEV_DV_ENDPOINT = os.environ.get("DEV_DV_ENDPOINT", "http://localhost:8100")
 ADMIN_HF_ORGANIZATION = os.environ.get("ADMIN_HF_ORGANIZATION", "huggingface")
 HF_TOKEN = os.environ.get("HF_TOKEN")
 
-DSS_ENDPOINT = DEV_DSS_ENDPOINT if DEV else PROD_DSS_ENDPOINT
+DV_ENDPOINT = DEV_DV_ENDPOINT if DEV else PROD_DV_ENDPOINT
 
 
 # global state (shared with all the user sessions)
@@ -34,13 +34,13 @@
 
 def healthcheck():
     try:
-        response = requests.head(f"{DSS_ENDPOINT}/admin/healthcheck", timeout=10)
+        response = requests.head(f"{DV_ENDPOINT}/admin/healthcheck", timeout=10)
     except requests.ConnectionError as error:
-        return f"❌ Failed to connect to {DSS_ENDPOINT} (error {error})"
+        return f"❌ Failed to connect to {DV_ENDPOINT} (error {error})"
     if response.status_code == 200:
-        return f"*Connected to {DSS_ENDPOINT}*"
+        return f"*Connected to {DV_ENDPOINT}*"
     else:
-        return f"❌ Failed to connect to {DSS_ENDPOINT} (error {response.status_code})"
+        return f"❌ Failed to connect to {DV_ENDPOINT} (error {response.status_code})"
 
 
 def draw_graph(width, height):
@@ -126,7 +126,7 @@ def fetch_home_dashboard(token):
                     }
                     headers = {"Authorization": f"Bearer {token}"}
                     response = requests.get(
-                        f"{DSS_ENDPOINT}/admin/num-dataset-infos-by-builder-name",
+                        f"{DV_ENDPOINT}/admin/num-dataset-infos-by-builder-name",
                         headers=headers,
                         timeout=60,
                     )
@@ -165,7 +165,7 @@ def fetch_home_dashboard(token):
                             value=pd.DataFrame(
                                 {
                                     "Error": [
-                                        f"❌ Failed to fetch dataset infos from {DSS_ENDPOINT} (error {response.status_code})"
+                                        f"❌ Failed to fetch dataset infos from {DV_ENDPOINT} (error {response.status_code})"
                                     ]
                                 }
                             ),
@@ -181,7 +181,7 @@ def fetch_home_dashboard(token):
 
                         def get_is_valid_response(dataset: str):
                             return requests.get(
-                                f"{DSS_ENDPOINT}/is-valid?dataset={dataset}",
+                                f"{DV_ENDPOINT}/is-valid?dataset={dataset}",
                                 headers=headers,
                                 timeout=60,
                             )
@@ -289,7 +289,7 @@ def view_jobs(token):
                     global pending_jobs_df
                     headers = {"Authorization": f"Bearer {token}"}
                     response = requests.get(
-                        f"{DSS_ENDPOINT}/admin/pending-jobs",
+                        f"{DV_ENDPOINT}/admin/pending-jobs",
                         headers=headers,
                         timeout=60,
                     )
@@ -346,7 +346,7 @@ def view_jobs(token):
                                 value=pd.DataFrame(
                                     {
                                         "Error": [
-                                            f"❌ Failed to view pending jobs to {DSS_ENDPOINT} (error {response.status_code})"
+                                            f"❌ Failed to view pending jobs to {DV_ENDPOINT} (error {response.status_code})"
                                         ]
                                     }
                                 ),
@@ -478,7 +478,7 @@ def refresh_dataset(
                             params["difficulty"] = refresh_difficulty
                         params = urllib.parse.urlencode(params)
                         response = requests.post(
-                            f"{DSS_ENDPOINT}/admin/force-refresh/{refresh_type}?{params}",
+                            f"{DV_ENDPOINT}/admin/force-refresh/{refresh_type}?{params}",
                             headers=headers,
                             timeout=60,
                         )
@@ -542,7 +542,7 @@ def delete_and_recreate_dataset(
                     }
                     params = urllib.parse.urlencode(params)
                     response = requests.post(
-                        f"{DSS_ENDPOINT}/admin/recreate-dataset?{params}",
+                        f"{DV_ENDPOINT}/admin/recreate-dataset?{params}",
                         headers=headers,
                         timeout=60,
                     )
@@ -577,7 +577,7 @@ def delete_and_recreate_dataset(
                 def get_dataset_status(token, dataset):
                     headers = {"Authorization": f"Bearer {token}"}
                     response = requests.get(
-                        f"{DSS_ENDPOINT}/admin/dataset-status?dataset={dataset}",
+                        f"{DV_ENDPOINT}/admin/dataset-status?dataset={dataset}",
                         headers=headers,
                         timeout=60,
                     )

jobs/cache_maintenance/tests/conftest.py

@@ -22,8 +22,8 @@
 @fixture(scope="session")
 def monkeypatch_session() -> Iterator[MonkeyPatch]:
     monkeypatch_session = MonkeyPatch()
-    monkeypatch_session.setenv("CACHE_MONGO_DATABASE", "datasets_server_cache_test")
-    monkeypatch_session.setenv("QUEUE_MONGO_DATABASE", "datasets_server_queue_test")
+    monkeypatch_session.setenv("CACHE_MONGO_DATABASE", "dataset_viewer_cache_test")
+    monkeypatch_session.setenv("QUEUE_MONGO_DATABASE", "dataset_viewer_queue_test")
     monkeypatch_session.setenv("COMMON_HF_ENDPOINT", CI_HUB_ENDPOINT)
     monkeypatch_session.setenv("COMMON_HF_TOKEN", CI_APP_TOKEN)
     monkeypatch_session.setenv("DISCUSSIONS_BOT_ASSOCIATED_USER_NAME", CI_PARQUET_CONVERTER_USER)

jobs/cache_maintenance/tests/constants.py

@@ -3,9 +3,9 @@
 
 # see https://github.com/huggingface/moon-landing/blob/main/server/scripts/staging-seed-db.ts
 CI_APP_TOKEN = "hf_app_datasets-server_token"
-CI_PARQUET_CONVERTER_USER = "DSSParquetConverterUser"
+CI_PARQUET_CONVERTER_USER = "DVParquetConverterUser"
 CI_PARQUET_CONVERTER_APP_TOKEN = "hf_app_datasets-server-parquet-converter_token"
 CI_HUB_ENDPOINT = "https://hub-ci.huggingface.co"
 CI_URL_TEMPLATE = CI_HUB_ENDPOINT + "/{repo_id}/resolve/{revision}/{filename}"
-CI_USER = "DSSUser"
+CI_USER = "DVUser"
 CI_USER_TOKEN = "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"

jobs/mongodb_migration/README.md

@@ -10,7 +10,7 @@ The script can be configured using environment variables. They are grouped by sc
 
 Set environment variables to configure the job (`DATABASE_MIGRATIONS_` prefix):
 
-- `DATABASE_MIGRATIONS_MONGO_DATABASE`: the name of the database used for storing the migrations history. Defaults to `"datasets_server_maintenance"`.
+- `DATABASE_MIGRATIONS_MONGO_DATABASE`: the name of the database used for storing the migrations history. Defaults to `"dataset_viewer_maintenance"`.
 - `DATABASE_MIGRATIONS_MONGO_URL`: the URL used to connect to the mongo db server. Defaults to `"mongodb://localhost:27017"`.
 
 ### Common

jobs/mongodb_migration/src/mongodb_migration/config.py

@@ -6,7 +6,7 @@
 from environs import Env
 from libcommon.config import CacheConfig, LogConfig, QueueConfig
 
-DATABASE_MIGRATIONS_MONGO_DATABASE = "datasets_server_maintenance"
+DATABASE_MIGRATIONS_MONGO_DATABASE = "dataset_viewer_maintenance"
 DATABASE_MIGRATIONS_MONGO_URL = "mongodb://localhost:27017"
 
 

jobs/mongodb_migration/tests/test_plan.py

@@ -17,7 +17,7 @@
 
 @pytest.fixture(autouse=True)
 def migrations_mongo_resource(mongo_host: str) -> Iterator[MigrationsMongoResource]:
-    database = "datasets_server_migrations_test"
+    database = "dataset_viewer_migrations_test"
     if "test" not in database:
         raise ValueError("Test must be launched on a test mongo database")
     with MigrationsMongoResource(database=database, host=mongo_host) as resource:

libs/libapi/tests/conftest.py

@@ -59,8 +59,8 @@ def image_path() -> str:
 @fixture(scope="session")
 def monkeypatch_session(tmp_path_factory: TempPathFactory) -> Iterator[MonkeyPatch]:
     monkeypatch_session = MonkeyPatch()
-    monkeypatch_session.setenv("CACHE_MONGO_DATABASE", "datasets_server_cache_test")
-    monkeypatch_session.setenv("QUEUE_MONGO_DATABASE", "datasets_server_queue_test")
+    monkeypatch_session.setenv("CACHE_MONGO_DATABASE", "dataset_viewer_cache_test")
+    monkeypatch_session.setenv("QUEUE_MONGO_DATABASE", "dataset_viewer_queue_test")
     yield monkeypatch_session
     monkeypatch_session.undo()
 

libs/libcommon/README.md

@@ -47,14 +47,14 @@ Set the common environment variables to configure the logs:
 
 Set environment variables to configure the storage of precomputed API responses in a MongoDB database (the "cache"):
 
-- `CACHE_MONGO_DATABASE`: name of the database used for storing the cache. Defaults to `datasets_server_cache`.
+- `CACHE_MONGO_DATABASE`: name of the database used for storing the cache. Defaults to `dataset_viewer_cache`.
 - `CACHE_MONGO_URL`: URL used to connect to the MongoDB server. Defaults to `mongodb://localhost:27017`.
 
 ## Queue configuration
 
 Set environment variables to configure the job queues to precompute API responses. The job queues are stored in a MongoDB database.
 
-- `QUEUE_MONGO_DATABASE`: name of the database used for storing the queue. Defaults to `datasets_server_queue`.
+- `QUEUE_MONGO_DATABASE`: name of the database used for storing the queue. Defaults to `dataset_viewer_queue`.
 - `QUEUE_MONGO_URL`: URL used to connect to the MongoDB server. Defaults to `mongodb://localhost:27017`.
 
 ## S3 configuration

libs/libcommon/src/libcommon/config.py

@@ -173,7 +173,7 @@ def from_env(cls) -> "LogConfig":
             )
 
 
-CACHE_MONGO_DATABASE = "datasets_server_cache"
+CACHE_MONGO_DATABASE = "dataset_viewer_cache"
 CACHE_MONGO_URL = "mongodb://localhost:27017"
 
 
@@ -192,7 +192,7 @@ def from_env(cls) -> "CacheConfig":
             )
 
 
-QUEUE_MONGO_DATABASE = "datasets_server_queue"
+QUEUE_MONGO_DATABASE = "dataset_viewer_queue"
 QUEUE_MONGO_URL = "mongodb://localhost:27017"
 
 

libs/libcommon/src/libcommon/constants.py

@@ -5,8 +5,8 @@
 CACHE_MONGOENGINE_ALIAS = "cache"
 HF_DATASETS_CACHE_APPNAME = "hf_datasets_cache"
 PARQUET_METADATA_CACHE_APPNAME = "datasets_server_parquet_metadata"
-DESCRIPTIVE_STATISTICS_CACHE_APPNAME = "datasets_server_descriptive_statistics"
-DUCKDB_INDEX_CACHE_APPNAME = "datasets_server_duckdb_index"
+DESCRIPTIVE_STATISTICS_CACHE_APPNAME = "dataset_viewer_descriptive_statistics"
+DUCKDB_INDEX_CACHE_APPNAME = "dataset_viewer_duckdb_index"
 DUCKDB_INDEX_DOWNLOADS_SUBDIRECTORY = "downloads"
 DUCKDB_INDEX_JOB_RUNNER_SUBDIRECTORY = "job_runner"
 DUCKDB_VERSION = "0.10.0"

libs/libcommon/src/libcommon/viewer_utils/asset.py

@@ -14,8 +14,6 @@
 from libcommon.storage import StrPath, remove_dir
 from libcommon.storage_client import StorageClient
 
-ASSET_DIR_MODE = 0o755
-DATASETS_SERVER_MDATE_FILENAME = ".dss"
 SUPPORTED_AUDIO_EXTENSION_TO_MEDIA_TYPE = {".wav": "audio/wav", ".mp3": "audio/mpeg"}
 
 

libs/libcommon/tests/conftest.py

@@ -47,7 +47,7 @@ def queue_mongo_host(env: Env) -> str:
 
 @fixture
 def queue_mongo_resource(queue_mongo_host: str) -> Iterator[QueueMongoResource]:
-    database = "datasets_server_queue_test"
+    database = "dataset_viewer_queue_test"
     host = queue_mongo_host
     if "test" not in database:
         raise ValueError("Test must be launched on a test mongo database")
@@ -61,7 +61,7 @@ def queue_mongo_resource(queue_mongo_host: str) -> Iterator[QueueMongoResource]:
 
 @fixture
 def cache_mongo_resource(cache_mongo_host: str) -> Iterator[CacheMongoResource]:
-    database = "datasets_server_cache_test"
+    database = "dataset_viewer_cache_test"
     host = cache_mongo_host
     if "test" not in database:
         raise ValueError("Test must be launched on a test mongo database")

libs/libcommon/tests/constants.py

@@ -6,13 +6,13 @@
 CI_HUB_ENDPOINT = "https://hub-ci.huggingface.co"
 PROD_HUB_ENDPOINT = "https://huggingface.co"
 #
-NORMAL_USER = "DSSUser"
+NORMAL_USER = "DVUser"
 NORMAL_USER_TOKEN = "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"
-NORMAL_ORG = "DSSNormalOrg"
-PRO_USER = "DSSProUser"
+NORMAL_ORG = "DVNormalOrg"
+PRO_USER = "DVProUser"
 PRO_USER_TOKEN = "hf_pro_user_token"
-ENTERPRISE_ORG = "DSSEnterpriseOrg"
-ENTERPRISE_USER = "DSSEnterpriseUser"
+ENTERPRISE_ORG = "DVEnterpriseOrg"
+ENTERPRISE_USER = "DVEnterpriseUser"
 ENTERPRISE_USER_TOKEN = "hf_enterprise_user_token"
 
 DEFAULT_CONFIG = "default"

libs/libcommon/tests/test_resources.py

@@ -17,10 +17,10 @@
 
 
 def test_database_resource(queue_mongo_host: str) -> None:
-    database_1 = "datasets_server_1"
-    database_2 = "datasets_server_2"
+    database_1 = "dataset_viewer_1"
+    database_2 = "dataset_viewer_2"
     host = queue_mongo_host
-    mongoengine_alias = "datasets_server_mongo_alias"
+    mongoengine_alias = "dataset_viewer_mongo_alias"
     server_selection_timeout_ms = 5_000
     resource_1 = MongoResource(
         database=database_1,
@@ -63,7 +63,7 @@ def test_database_resource_errors(
 ) -> None:
     if not host:
         host = queue_mongo_host
-    database = "datasets_server_test"
+    database = "dataset_viewer_test"
     resource = MongoResource(
         database=database,
         host=host,

services/admin/tests/conftest.py

@@ -21,8 +21,8 @@ def monkeypatch_session(hf_endpoint: str, hf_token: str, tmp_path_factory: TempP
     assets_root = str(tmp_path_factory.mktemp("assets_root"))
     monkeypatch_session.setenv("CACHED_ASSETS_STORAGE_ROOT", assets_root)
     monkeypatch_session.setenv("ASSETS_STORAGE_ROOT", assets_root)
-    monkeypatch_session.setenv("CACHE_MONGO_DATABASE", "datasets_server_cache_test")
-    monkeypatch_session.setenv("QUEUE_MONGO_DATABASE", "datasets_server_queue_test")
+    monkeypatch_session.setenv("CACHE_MONGO_DATABASE", "dataset_viewer_cache_test")
+    monkeypatch_session.setenv("QUEUE_MONGO_DATABASE", "dataset_viewer_queue_test")
     monkeypatch_session.setenv("COMMON_HF_ENDPOINT", hf_endpoint)
     monkeypatch_session.setenv("COMMON_HF_TOKEN", hf_token)
     monkeypatch_session.setenv("ADMIN_HF_TIMEOUT_SECONDS", "10")

services/admin/tests/fixtures/hub.py

@@ -15,7 +15,7 @@
 from huggingface_hub.utils._errors import hf_raise_for_status
 
 # see https://github.com/huggingface/moon-landing/blob/main/server/scripts/staging-seed-db.ts
-CI_HUB_USER = "DSSUser"
+CI_HUB_USER = "DVUser"
 CI_HUB_USER_API_TOKEN = "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"
 
 CI_HUB_ENDPOINT = "https://hub-ci.huggingface.co"

services/admin/tests/test_app_real.py

@@ -15,8 +15,8 @@
 @fixture(scope="module")
 def real_monkeypatch() -> Iterator[MonkeyPatch]:
     monkeypatch = MonkeyPatch()
-    monkeypatch.setenv("CACHE_MONGO_DATABASE", "datasets_server_cache_test")
-    monkeypatch.setenv("QUEUE_MONGO_DATABASE", "datasets_server_queue_test")
+    monkeypatch.setenv("CACHE_MONGO_DATABASE", "dataset_viewer_cache_test")
+    monkeypatch.setenv("QUEUE_MONGO_DATABASE", "dataset_viewer_queue_test")
     monkeypatch.setenv("COMMON_HF_ENDPOINT", "https://huggingface.co")
     monkeypatch.setenv("COMMON_HF_TOKEN", "")
     yield monkeypatch