[do not merge]: Dry run for packages/bigframes migration

packages/bigframes/.coveragerc

@@ -0,0 +1,38 @@
+# -*- coding: utf-8 -*-
+#
+# Copyright 2024 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# Generated by synthtool. DO NOT EDIT!
+[run]
+branch = True
+omit =
+  google/__init__.py
+  google/cloud/__init__.py
+
+[report]
+fail_under = 35
+show_missing = True
+exclude_lines =
+    # Re-enable the standard pragma
+    pragma: NO COVER
+    # Ignore debug-only repr
+    def __repr__
+    # Ignore abstract methods
+    raise NotImplementedError
+omit =
+  */gapic/*.py
+  */proto/*.py
+  */site-packages/*.py
+  google/cloud/__init__.py

packages/bigframes/.flake8

@@ -0,0 +1,33 @@
+# -*- coding: utf-8 -*-
+#
+# Copyright 2024 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# Generated by synthtool. DO NOT EDIT!
+[flake8]
+ignore = E203, E231, E266, E501, W503
+exclude =
+  # Exclude generated code.
+  **/proto/**
+  **/gapic/**
+  **/services/**
+  **/types/**
+  *_pb2.py
+
+  # Standard linting exemptions.
+  **/.nox/**
+  __pycache__,
+  .git,
+  *.pyc,
+  conf.py

packages/bigframes/.gemini/common/constraints.md

@@ -0,0 +1,8 @@
+## Constraints
+
+- Only add git commits. Do not change git history.
+- Follow the spec file for development.
+  - Check off items in the "Acceptance
+    criteria" and "Detailed steps" sections with `[x]`.
+  - Please do this as they are completed.
+  - Refer back to the spec after each step.

packages/bigframes/.gemini/common/docs.md

@@ -0,0 +1,9 @@
+## Documentation
+
+If a method or property is implementing the same interface as a third-party
+package such as pandas or scikit-learn, place the relevant docstring in the
+corresponding `third_party/bigframes_vendored/package_name` directory, not in
+the `bigframes` directory. Implementations may be placed in the `bigframes`
+directory, though.
+
+@../tools/test_docs.md

packages/bigframes/.gemini/tasks/scalar_op.md

@@ -0,0 +1,67 @@
+## Adding a scalar operator
+
+For an example, see commit
+[c5b7fdae74a22e581f7705bc0cf5390e928f4425](https://github.com/googleapis/python-bigquery-dataframes/commit/c5b7fdae74a22e581f7705bc0cf5390e928f4425).
+
+To add a new scalar operator, follow these steps:
+
+1.  **Define the operation dataclass:**
+    - In `bigframes/operations/`, find the relevant file (e.g., `geo_ops.py` for geography functions) or create a new one.
+    - Create a new dataclass inheriting from `base_ops.UnaryOp` for unary
+      operators, `base_ops.BinaryOp` for binary operators, `base_ops.TernaryOp`
+      for ternary operators, or `base_ops.NaryOp for operators with many
+      arguments. Note that these operators are counting the number column-like
+      arguments. A function that takes only a single column but several literal
+      values would still be a `UnaryOp`.
+    - Define the `name` of the operation and any parameters it requires.
+    - Implement the `output_type` method to specify the data type of the result.
+
+2.  **Export the new operation:**
+    - In `bigframes/operations/__init__.py`, import your new operation dataclass and add it to the `__all__` list.
+
+3.  **Implement the user-facing function (pandas-like):**
+
+    - Identify the canonical function from pandas / geopandas / awkward array /
+      other popular Python package that this operator implements.
+    - Find the corresponding class in BigFrames. For example, the implementation
+      for most geopandas.GeoSeries methods is in
+      `bigframes/geopandas/geoseries.py`. Pandas Series methods are implemented
+      in `bigframes/series.py` or one of the accessors, such as `StringMethods`
+      in `bigframes/operations/strings.py`.
+    - Create the user-facing function that will be called by users (e.g., `length`).
+    - If the SQL method differs from pandas or geopandas in a way that can't be
+      made the same, raise a `NotImplementedError` with an appropriate message and
+      link to the feedback form.
+    - Add the docstring to the corresponding file in
+      `third_party/bigframes_vendored`, modeled after pandas / geopandas.
+
+4.  **Implement the user-facing function (SQL-like):**
+
+    - In `bigframes/bigquery/_operations/`, find the relevant file (e.g., `geo.py`) or create a new one.
+    - Create the user-facing function that will be called by users (e.g., `st_length`).
+    - This function should take a `Series` for any column-like inputs, plus any other parameters.
+    - Inside the function, call `series._apply_unary_op`,
+      `series._apply_binary_op`, or similar passing the operation dataclass you
+      created.
+    - Add a comprehensive docstring with examples.
+    - In `bigframes/bigquery/__init__.py`, import your new user-facing function and add it to the `__all__` list.
+
+5.  **Implement the compilation logic:**
+    - In `bigframes/core/compile/scalar_op_compiler.py`:
+        - If the BigQuery function has a direct equivalent in Ibis, you can often reuse an existing Ibis method.
+        - If not, define a new Ibis UDF using `@ibis_udf.scalar.builtin` to map to the specific BigQuery function signature.
+        - Create a new compiler implementation function (e.g., `geo_length_op_impl`).
+        - Register this function to your operation dataclass using `@scalar_op_compiler.register_unary_op` or `@scalar_op_compiler.register_binary_op`.
+        - This implementation will translate the BigQuery DataFrames operation into the appropriate Ibis expression.
+
+6.  **Add Tests:**
+    - Add system tests in the `tests/system/` directory to verify the end-to-end
+      functionality of the new operator. Test various inputs, including edge cases
+      and `NULL` values.
+
+      Where possible, run the same test code against pandas or GeoPandas and
+      compare that the outputs are the same (except for dtypes if BigFrames
+      differs from pandas).
+    - If you are overriding a pandas or GeoPandas property, add a unit test to
+      ensure the correct behavior (e.g., raising `NotImplementedError` if the
+      functionality is not supported).

packages/bigframes/.gemini/tools/style_nox.md

@@ -0,0 +1,18 @@
+## Code Style with nox
+
+- We use the automatic code formatter `black`. You can run it using
+  the nox session `format`. This will eliminate many lint errors. Run via:
+
+  ```bash
+  nox -r -s format
+  ```
+
+- PEP8 compliance is required, with exceptions defined in the linter configuration.
+  If you have ``nox`` installed, you can test that you have not introduced
+  any non-compliant code via:
+
+  ```
+  nox -r -s lint
+  ```
+
+- When writing tests, use the idiomatic "pytest" style.

packages/bigframes/.gemini/tools/test_docs.md

@@ -0,0 +1,10 @@
+## Testing code samples
+
+Code samples are very important for accurate documentation. We use the "doctest"
+framework to ensure the samples are functioning as expected. After adding a code
+sample, please ensure it is correct by running doctest. To run the samples
+doctests for just a single method, refer to the following example:
+
+```bash
+pytest --doctest-modules bigframes/pandas/__init__.py::bigframes.pandas.cut
+```

packages/bigframes/.gemini/tools/test_nox.md

@@ -0,0 +1,28 @@
+## Testing with nox
+
+Use `nox` to instrument our tests.
+
+- To test your changes, run unit tests with `nox`:
+
+  ```bash
+  nox -r -s unit
+  ```
+
+- To run a single unit test:
+
+  ```bash
+  nox -r -s unit-3.14 -- -k <name of test>
+  ```
+
+- Ignore this step if you lack access to Google Cloud resources. To run system
+  tests, you can execute::
+
+   # Run all system tests
+   $ nox -r -s system
+
+   # Run a single system test
+   $ nox -r -s system-3.14 -- -k <name of test>
+
+- The codebase must have better coverage than it had previously after each
+  change. You can test coverage via `nox -s unit system cover` (takes a long
+  time). Omit `system` if you lack access to cloud resources.

packages/bigframes/.gemini/tools/test_pytest.md

@@ -0,0 +1,9 @@
+## Testing with pytest
+
+Use `pytest` to instrument our tests.
+
+- To test your changes, run `pytest`:
+
+  ```bash
+  pytest <test_file>::<test_case>
+  ```

packages/bigframes/.gitignore

@@ -0,0 +1,70 @@
+*.py[cod]
+*.sw[op]
+
+# C extensions
+*.so
+
+# Packages
+*.egg
+*.egg-info
+dist
+build
+eggs
+.eggs
+parts
+bin
+var
+sdist
+develop-eggs
+.installed.cfg
+lib
+lib64
+__pycache__
+
+# Installer logs
+pip-log.txt
+
+# Unit test / coverage reports
+.coverage
+.nox
+.cache
+.pytest_cache
+
+
+# Mac
+.DS_Store
+
+# JetBrains
+.idea
+
+# VS Code
+.vscode
+
+# emacs
+*~
+
+# Built documentation
+docs/_build
+bigquery/docs/generated
+docs.metadata
+
+# Virtual environment
+env/
+venv/
+
+# Test logs
+coverage.xml
+*sponge_log.xml
+
+# System test environment variables.
+system_tests/local_test_setup
+tests/js/node_modules/
+
+# Make sure a generated file isn't accidentally committed.
+pylintrc
+pylintrc.test
+dummy.pkl
+.mypy_cache/
+
+# Gemini
+GEMINI.md

packages/bigframes/.isort.cfg

@@ -0,0 +1,7 @@
+[settings]
+profile=black
+force_sort_within_sections=True
+lexicographical=True
+single_line_exclusions=('typing',)
+order_by_type=False
+group_by_package=True

packages/bigframes/.librarian/state.yaml

@@ -0,0 +1,11 @@
+image: us-central1-docker.pkg.dev/cloud-sdk-librarian-prod/images-prod/python-librarian-generator@sha256:160860d189ff1c2f7515638478823712fa5b243e27ccc33a2728669fa1e2ed0c
+libraries:
+  - id: bigframes
+    version: 2.37.0
+    last_generated_commit: ""
+    apis: []
+    source_roots:
+      - .
+    preserve_regex: []
+    remove_regex: []
+    tag_format: v{version}

packages/bigframes/.pre-commit-config.yaml

@@ -0,0 +1,59 @@
+# Copyright 2023 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+default_install_hook_types:
+-   pre-commit
+-   commit-msg
+
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.0.1
+    hooks:
+    -   id: trailing-whitespace
+    -   id: end-of-file-fixer
+        exclude: "^tests/unit/core/compile/sqlglot/.*snapshots"
+    -   id: check-yaml
+-   repo: https://github.com/pycqa/isort
+    rev: 5.12.0
+    hooks:
+    -   id: isort
+        name: isort (python)
+-   repo: https://github.com/psf/black
+    rev: 23.7.0
+    hooks:
+    - id: black
+-   repo: https://github.com/pycqa/flake8
+    rev: 7.1.2
+    hooks:
+    - id: flake8
+-   repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.15.0
+    hooks:
+    -   id: mypy
+        additional_dependencies: [types-requests, types-tabulate, types-PyYAML, pandas-stubs<=2.2.3.241126]
+        exclude: "^third_party"
+        args: ["--check-untyped-defs", "--explicit-package-bases", "--ignore-missing-imports"]
+-   repo: https://github.com/biomejs/pre-commit
+    rev: v2.2.4
+    hooks:
+    -   id: biome-check
+        files: '\.(js|css)$'
+-   repo: https://github.com/compilerla/conventional-pre-commit
+    rev: fdde5f0251edbfc554795afdd6df71826d6602f3
+    hooks:
+      - id: conventional-pre-commit
+        stages: [commit-msg]
+        args: []

packages/bigframes/.repo-metadata.json

@@ -0,0 +1,16 @@
+{
+    "name": "bigframes",
+    "name_pretty": "A unified Python API in BigQuery",
+    "product_documentation": "https://cloud.google.com/bigquery",
+    "client_documentation": "https://cloud.google.com/python/docs/reference/bigframes/latest",
+    "issue_tracker": "https://github.com/googleapis/python-bigquery-dataframes/issues",
+    "release_level": "preview",
+    "language": "python",
+    "library_type": "INTEGRATION",
+    "repo": "googleapis/python-bigquery-dataframes",
+    "distribution_name": "bigframes",
+    "api_id": "bigquery.googleapis.com",
+    "default_version": "",
+    "codeowner_team": "@googleapis/bigquery-dataframe-team",
+    "api_shortname": "bigquery"
+}