gena-datasets 0.1.0__tar.gz

gena_datasets-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 TuluAI
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

gena_datasets-0.1.0/PKG-INFO

@@ -0,0 +1,67 @@
+Metadata-Version: 2.4
+Name: gena-datasets
+Version: 0.1.0
+Summary: Browse public Gena datasets and submit datasets for review.
+License-Expression: MIT
+Keywords: gena,datasets,tuluai,machine-learning
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# `gena-datasets`
+
+Python client for browsing public datasets and submitting a dataset to Gena for review.
+
+## Install
+
+```sh
+python -m pip install gena-datasets
+```
+
+## Read public datasets
+
+```python
+from gena_datasets import GenaDatasetsClient
+
+gena = GenaDatasetsClient()
+for item in gena.list_datasets():
+    print(item["id"], item["title"], item["license"])
+
+dataset = gena.get_dataset("tulueng100-reference")
+print(dataset["content"])
+```
+
+Public catalog access does not require sign-in. `download_dataset(id)` returns the original dataset file contents as text.
+
+## Submit a dataset
+
+```python
+id_token = current_firebase_user.get_id_token()
+submission = gena.submit_dataset(
+    {
+        "title": "Example collection",
+        "description": "A short description of the data and how it was collected.",
+        "language": "English",
+        "license": "CC BY 4.0",
+        "fileName": "examples.jsonl",
+        "content": '{"text":"Example"}\n',
+        "rightsConfirmed": True,
+    },
+    id_token=id_token,
+)
+
+print(submission["datasetId"], submission["status"])
+```
+
+Submissions are private while pending review. A designated Gena moderator must approve a submission before it becomes public. The contributor must have permission to share the data and choose a license that allows publication. Current uploads are limited to 900,000 bytes and `.csv`, `.json`, `.jsonl`, or `.txt` files.
+
+## API endpoints
+
+- `GET /api/gena/datasets`
+- `GET /api/gena/datasets/{id}`
+- `POST /api/gena/datasets` with a signed-in account token
+
+## License
+
+MIT

gena_datasets-0.1.0/README.md

@@ -0,0 +1,56 @@
+# `gena-datasets`
+
+Python client for browsing public datasets and submitting a dataset to Gena for review.
+
+## Install
+
+```sh
+python -m pip install gena-datasets
+```
+
+## Read public datasets
+
+```python
+from gena_datasets import GenaDatasetsClient
+
+gena = GenaDatasetsClient()
+for item in gena.list_datasets():
+    print(item["id"], item["title"], item["license"])
+
+dataset = gena.get_dataset("tulueng100-reference")
+print(dataset["content"])
+```
+
+Public catalog access does not require sign-in. `download_dataset(id)` returns the original dataset file contents as text.
+
+## Submit a dataset
+
+```python
+id_token = current_firebase_user.get_id_token()
+submission = gena.submit_dataset(
+    {
+        "title": "Example collection",
+        "description": "A short description of the data and how it was collected.",
+        "language": "English",
+        "license": "CC BY 4.0",
+        "fileName": "examples.jsonl",
+        "content": '{"text":"Example"}\n',
+        "rightsConfirmed": True,
+    },
+    id_token=id_token,
+)
+
+print(submission["datasetId"], submission["status"])
+```
+
+Submissions are private while pending review. A designated Gena moderator must approve a submission before it becomes public. The contributor must have permission to share the data and choose a license that allows publication. Current uploads are limited to 900,000 bytes and `.csv`, `.json`, `.jsonl`, or `.txt` files.
+
+## API endpoints
+
+- `GET /api/gena/datasets`
+- `GET /api/gena/datasets/{id}`
+- `POST /api/gena/datasets` with a signed-in account token
+
+## License
+
+MIT

gena_datasets-0.1.0/pyproject.toml

@@ -0,0 +1,19 @@
+[build-system]
+requires = ["setuptools>=77"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "gena-datasets"
+version = "0.1.0"
+description = "Browse public Gena datasets and submit datasets for review."
+readme = "README.md"
+requires-python = ">=3.9"
+keywords = ["gena", "datasets", "tuluai", "machine-learning"]
+license = "MIT"
+license-files = ["LICENSE"]
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+gena_datasets = ["py.typed"]

gena_datasets-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

gena_datasets-0.1.0/src/gena_datasets/__init__.py

@@ -0,0 +1,115 @@
+"""Python client for public Gena datasets and moderated submissions."""
+
+from __future__ import annotations
+
+import json
+from typing import Any, Mapping, Optional
+from urllib.error import HTTPError, URLError
+from urllib.request import Request, urlopen
+
+__all__ = ["GenaDatasetsClient", "GenaDatasetsError"]
+
+DEFAULT_BASE_URL = "https://tuluai.app"
+
+
+class GenaDatasetsError(RuntimeError):
+    """An API or network error returned by Gena."""
+
+    def __init__(self, message: str, status: int = 0) -> None:
+        super().__init__(message)
+        self.status = status
+
+
+class GenaDatasetsClient:
+    """Access Gena's public catalog and submit datasets for review."""
+
+    def __init__(self, base_url: str = DEFAULT_BASE_URL, timeout: float = 20.0) -> None:
+        self.base_url = base_url.rstrip("/")
+        self.timeout = timeout
+
+    def _request(
+        self,
+        path: str,
+        *,
+        method: str = "GET",
+        body: Optional[Mapping[str, Any]] = None,
+        id_token: Optional[str] = None,
+    ) -> dict[str, Any]:
+        headers = {"Accept": "application/json"}
+        data = None
+        if body is not None:
+            headers["Content-Type"] = "application/json"
+            data = json.dumps(body, ensure_ascii=False).encode("utf-8")
+        if id_token:
+            headers["Authorization"] = "Bearer " + id_token
+
+        request = Request(
+            self.base_url + path,
+            data=data,
+            headers=headers,
+            method=method,
+        )
+        try:
+            with urlopen(request, timeout=self.timeout) as response:
+                result = json.loads(response.read().decode("utf-8"))
+        except HTTPError as error:
+            try:
+                payload = json.loads(error.read().decode("utf-8"))
+                message = payload.get("error", "The Gena dataset request failed.")
+            except (ValueError, AttributeError):
+                message = "The Gena dataset request failed."
+            raise GenaDatasetsError(str(message), error.code) from None
+        except (URLError, TimeoutError, OSError):
+            raise GenaDatasetsError("Could not reach the Gena dataset API.") from None
+        except (ValueError, UnicodeDecodeError):
+            raise GenaDatasetsError("Gena returned an unreadable response.") from None
+
+        if not isinstance(result, dict):
+            raise GenaDatasetsError("Gena returned an unexpected response.")
+        return result
+
+    def list_datasets(self) -> list[dict[str, Any]]:
+        """Return metadata for approved public datasets."""
+        result = self._request("/api/gena/datasets")
+        datasets = result.get("datasets", [])
+        if not isinstance(datasets, list):
+            raise GenaDatasetsError("Gena returned an unexpected dataset list.")
+        return datasets
+
+    def get_dataset(self, dataset_id: str) -> dict[str, Any]:
+        """Return approved dataset metadata and original file content."""
+        if not isinstance(dataset_id, str) or not dataset_id or any(
+            character not in "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789_-"
+            for character in dataset_id
+        ) or len(dataset_id) > 128:
+            raise ValueError("Enter a valid Gena dataset ID.")
+        result = self._request("/api/gena/datasets/" + dataset_id)
+        dataset = result.get("dataset")
+        if not isinstance(dataset, dict):
+            raise GenaDatasetsError("Gena returned an unexpected dataset.")
+        return dataset
+
+    def download_dataset(self, dataset_id: str) -> str:
+        """Return the source file contents for a public dataset."""
+        return self.get_dataset(dataset_id)["content"]
+
+    def submit_dataset(
+        self,
+        dataset: Mapping[str, Any],
+        *,
+        id_token: str,
+    ) -> dict[str, Any]:
+        """Submit a dataset privately for moderator review.
+
+        A successful response means the submission is pending review, not public.
+        """
+        if not id_token or not isinstance(id_token, str):
+            raise ValueError("Pass a current sign-in token to submit a dataset.")
+        if dataset.get("rightsConfirmed") is not True:
+            raise ValueError("Confirm that you have the rights to submit this dataset.")
+        return self._request(
+            "/api/gena/datasets",
+            method="POST",
+            body=dataset,
+            id_token=id_token,
+        )

gena_datasets-0.1.0/src/gena_datasets/py.typed

@@ -0,0 +1 @@
+

gena_datasets-0.1.0/src/gena_datasets.egg-info/PKG-INFO

@@ -0,0 +1,67 @@
+Metadata-Version: 2.4
+Name: gena-datasets
+Version: 0.1.0
+Summary: Browse public Gena datasets and submit datasets for review.
+License-Expression: MIT
+Keywords: gena,datasets,tuluai,machine-learning
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# `gena-datasets`
+
+Python client for browsing public datasets and submitting a dataset to Gena for review.
+
+## Install
+
+```sh
+python -m pip install gena-datasets
+```
+
+## Read public datasets
+
+```python
+from gena_datasets import GenaDatasetsClient
+
+gena = GenaDatasetsClient()
+for item in gena.list_datasets():
+    print(item["id"], item["title"], item["license"])
+
+dataset = gena.get_dataset("tulueng100-reference")
+print(dataset["content"])
+```
+
+Public catalog access does not require sign-in. `download_dataset(id)` returns the original dataset file contents as text.
+
+## Submit a dataset
+
+```python
+id_token = current_firebase_user.get_id_token()
+submission = gena.submit_dataset(
+    {
+        "title": "Example collection",
+        "description": "A short description of the data and how it was collected.",
+        "language": "English",
+        "license": "CC BY 4.0",
+        "fileName": "examples.jsonl",
+        "content": '{"text":"Example"}\n',
+        "rightsConfirmed": True,
+    },
+    id_token=id_token,
+)
+
+print(submission["datasetId"], submission["status"])
+```
+
+Submissions are private while pending review. A designated Gena moderator must approve a submission before it becomes public. The contributor must have permission to share the data and choose a license that allows publication. Current uploads are limited to 900,000 bytes and `.csv`, `.json`, `.jsonl`, or `.txt` files.
+
+## API endpoints
+
+- `GET /api/gena/datasets`
+- `GET /api/gena/datasets/{id}`
+- `POST /api/gena/datasets` with a signed-in account token
+
+## License
+
+MIT

gena_datasets-0.1.0/src/gena_datasets.egg-info/SOURCES.txt

@@ -0,0 +1,10 @@
+LICENSE
+README.md
+pyproject.toml
+src/gena_datasets/__init__.py
+src/gena_datasets/py.typed
+src/gena_datasets.egg-info/PKG-INFO
+src/gena_datasets.egg-info/SOURCES.txt
+src/gena_datasets.egg-info/dependency_links.txt
+src/gena_datasets.egg-info/top_level.txt
+tests/test_client.py

gena_datasets-0.1.0/src/gena_datasets.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

gena_datasets-0.1.0/src/gena_datasets.egg-info/top_level.txt

@@ -0,0 +1 @@
+gena_datasets

gena_datasets-0.1.0/tests/test_client.py

@@ -0,0 +1,61 @@
+import json
+import sys
+import unittest
+from pathlib import Path
+from unittest.mock import patch
+
+sys.path.insert(0, str(Path(__file__).parents[1] / "src"))
+
+from gena_datasets import GenaDatasetsClient, GenaDatasetsError  # noqa: E402
+
+
+class FakeResponse:
+    def __init__(self, body):
+        self.body = json.dumps(body).encode("utf-8")
+
+    def __enter__(self):
+        return self
+
+    def __exit__(self, *_):
+        return None
+
+    def read(self):
+        return self.body
+
+
+class GenaDatasetsClientTests(unittest.TestCase):
+    def test_lists_public_datasets(self):
+        with patch("gena_datasets.urlopen", return_value=FakeResponse({"datasets": [{"id": "sample"}]})) as open_url:
+            result = GenaDatasetsClient().list_datasets()
+        self.assertEqual(result[0]["id"], "sample")
+        self.assertEqual(open_url.call_args.args[0].full_url, "https://tuluai.app/api/gena/datasets")
+
+    def test_downloads_original_content(self):
+        with patch(
+            "gena_datasets.urlopen",
+            return_value=FakeResponse({"dataset": {"id": "sample", "content": '{"x":1}'}}),
+        ):
+            content = GenaDatasetsClient().download_dataset("sample")
+        self.assertEqual(content, '{"x":1}')
+
+    def test_submits_with_bearer_token_and_requires_rights_confirmation(self):
+        response = {"datasetId": "sample", "status": "pending"}
+        dataset = {"title": "Sample", "rightsConfirmed": True}
+        with patch("gena_datasets.urlopen", return_value=FakeResponse(response)) as open_url:
+            result = GenaDatasetsClient().submit_dataset(dataset, id_token="current-token")
+        request = open_url.call_args.args[0]
+        self.assertEqual(request.get_method(), "POST")
+        self.assertEqual(request.get_header("Authorization"), "Bearer current-token")
+        self.assertEqual(json.loads(request.data), dataset)
+        self.assertEqual(result["status"], "pending")
+
+        with self.assertRaises(ValueError):
+            GenaDatasetsClient().submit_dataset({"rightsConfirmed": False}, id_token="current-token")
+
+    def test_rejects_invalid_dataset_ids(self):
+        with self.assertRaises(ValueError):
+            GenaDatasetsClient().get_dataset("bad/id")
+
+
+if __name__ == "__main__":
+    unittest.main()