strata-client 0.3.0__tar.gz

strata_client-0.3.0/.gitignore

@@ -0,0 +1,251 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# macOS
+.DS_Store
+
+# Rust build artifacts
+rust/target/
+
+# Strata demo data (generated)
+demo-warehouse/
+benchmarks/results/
+site/
+
+# Internal design and planning docs — kept local only.
+docs/internal/
+
+# Auto-generated example renderings produced by the export hook
+# (docs_hooks/export_examples.py). Regenerated on every `mkdocs build`.
+docs/examples/
+
+# Per-notebook runtime state — artifacts, blobs, console output,
+# environment lockfiles, example DuckDB files. Generated whenever a
+# notebook runs; never meant to be shared.
+examples/*/.strata/
+examples/*/uv.lock
+examples/*/*.db
+examples/*/*.duckdb
+experiments/**/.strata/
+experiments/**/uv.lock
+experiments/**/*.db
+experiments/**/*.duckdb
+# Experiment runtime/scratch: per-server cache + artifact blobs (named
+# .strata-server-<thing>/, not .strata/) and the Arrow blobs they hold —
+# hundreds of MB, GitHub-rejected. Experiment *code* (e.g. circle_packing_26/)
+# stays tracked; only this generated state is ignored.
+experiments/**/.strata-server*/
+experiments/**/*.arrow
+experiments/**/*.arrowstream
+
+# Frontend build output, copied into the package by the release
+# workflow. Source of truth lives at frontend/dist/.
+src/strata/_frontend/
+
+# Claude Code session state
+.claude/

strata_client-0.3.0/PKG-INFO

@@ -0,0 +1,63 @@
+Metadata-Version: 2.4
+Name: strata-client
+Version: 0.3.0
+Summary: Lightweight Python client for Strata — materialize, persist, and query artifacts over HTTP.
+Project-URL: Homepage, https://github.com/bearing-research/strata
+Project-URL: Repository, https://github.com/bearing-research/strata
+Author-email: Fangchen Li <fangchen.li@outlook.com>
+License-Expression: Apache-2.0
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Requires-Python: >=3.12
+Requires-Dist: httpx>=0.28.0
+Requires-Dist: pyarrow>=18.0.0
+Provides-Extra: all
+Requires-Dist: datafusion>=50.1.0; extra == 'all'
+Requires-Dist: duckdb>=1.1.0; extra == 'all'
+Requires-Dist: pandas>=2.0.0; extra == 'all'
+Requires-Dist: polars>=1.36.1; extra == 'all'
+Provides-Extra: datafusion
+Requires-Dist: datafusion>=50.1.0; extra == 'datafusion'
+Provides-Extra: duckdb
+Requires-Dist: duckdb>=1.1.0; extra == 'duckdb'
+Provides-Extra: pandas
+Requires-Dist: pandas>=2.0.0; extra == 'pandas'
+Provides-Extra: polars
+Requires-Dist: polars>=1.36.1; extra == 'polars'
+Description-Content-Type: text/markdown
+
+# strata-client
+
+A lightweight Python client for a [Strata](https://github.com/bearing-research/strata)
+server. Depends only on `httpx` + `pyarrow` — none of the server's stack
+(no pyiceberg / fastapi / duckdb / pydantic, no Rust extension), so it drops
+into any analysis venv, training image, CI job, or notebook without dragging
+the deployable service along.
+
+```bash
+pip install strata-client
+```
+
+```python
+from strata_client import StrataClient
+
+with StrataClient() as client:  # resolves the server URL from
+                                # STRATA_SERVER_URL / STRATA_HOST / STRATA_PORT
+    art = client.materialize(
+        inputs=["file:///warehouse#db.events"],
+        transform={"executor": "scan@v1", "params": {}},
+    )
+    table = client.fetch(art.uri)
+
+    # Registry: names, aliases, tags, audit
+    client.put(table, name="team/dataset/raw")
+    client.set_alias("taxi/tip-model", "champion", art.artifact_id, art.version)
+```
+
+The server distribution (`strata-notebook`) depends on this package and
+re-exports it as `strata.client` for backward compatibility.

strata_client-0.3.0/README.md

@@ -0,0 +1,30 @@
+# strata-client
+
+A lightweight Python client for a [Strata](https://github.com/bearing-research/strata)
+server. Depends only on `httpx` + `pyarrow` — none of the server's stack
+(no pyiceberg / fastapi / duckdb / pydantic, no Rust extension), so it drops
+into any analysis venv, training image, CI job, or notebook without dragging
+the deployable service along.
+
+```bash
+pip install strata-client
+```
+
+```python
+from strata_client import StrataClient
+
+with StrataClient() as client:  # resolves the server URL from
+                                # STRATA_SERVER_URL / STRATA_HOST / STRATA_PORT
+    art = client.materialize(
+        inputs=["file:///warehouse#db.events"],
+        transform={"executor": "scan@v1", "params": {}},
+    )
+    table = client.fetch(art.uri)
+
+    # Registry: names, aliases, tags, audit
+    client.put(table, name="team/dataset/raw")
+    client.set_alias("taxi/tip-model", "champion", art.artifact_id, art.version)
+```
+
+The server distribution (`strata-notebook`) depends on this package and
+re-exports it as `strata.client` for backward compatibility.

strata_client-0.3.0/pyproject.toml

@@ -0,0 +1,45 @@
+[project]
+name = "strata-client"
+version = "0.3.0"
+description = "Lightweight Python client for Strata — materialize, persist, and query artifacts over HTTP."
+readme = "README.md"
+requires-python = ">=3.12"
+license = "Apache-2.0"
+authors = [{ name = "Fangchen Li", email = "fangchen.li@outlook.com" }]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
+]
+dependencies = [
+    "httpx>=0.28.0",
+    "pyarrow>=18.0.0",
+]
+
+# Optional integrations: query Strata directly from duckdb / pandas / polars /
+# datafusion. Each pulls only its own engine; the base client stays slim.
+# (The arrow integration needs only pyarrow, already a base dependency.)
+[project.optional-dependencies]
+duckdb = ["duckdb>=1.1.0"]
+pandas = ["pandas>=2.0.0"]
+polars = ["polars>=1.36.1"]
+datafusion = ["datafusion>=50.1.0"]
+all = ["duckdb>=1.1.0", "pandas>=2.0.0", "polars>=1.36.1", "datafusion>=50.1.0"]
+
+[project.urls]
+Homepage = "https://github.com/bearing-research/strata"
+Repository = "https://github.com/bearing-research/strata"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/strata_client"]
+
+[tool.hatch.build.targets.sdist]
+include = ["src/strata_client", "README.md"]

strata_client-0.3.0/src/strata_client/__init__.py

@@ -0,0 +1,52 @@
+"""strata_client — a lightweight Python client for a Strata server.
+
+Depends only on ``httpx`` + ``pyarrow`` — none of the Strata server's stack
+(no pyiceberg / fastapi / duckdb / pydantic, no Rust extension). Install it
+anywhere you want to *use* Strata as a library::
+
+    pip install strata-client
+
+    from strata_client import StrataClient
+
+    with StrataClient() as client:
+        art = client.materialize(
+            inputs=["file:///warehouse#db.events"],
+            transform={"executor": "scan@v1", "params": {}},
+        )
+        table = client.fetch(art.uri)
+
+The server distribution (``strata-notebook``) depends on this package and
+re-exports it as ``strata.client`` / ``strata.filters`` for backward
+compatibility. See docs/internal/design-strata-client.md.
+"""
+
+from strata_client.client import (
+    Artifact,
+    AsyncStrataClient,
+    RetryConfig,
+    StrataClient,
+    eq,
+    ge,
+    gt,
+    le,
+    lt,
+    ne,
+)
+from strata_client.filters import Filter, FilterOp, FilterValue, compute_filter_fingerprint
+
+__all__ = [
+    "Artifact",
+    "AsyncStrataClient",
+    "Filter",
+    "FilterOp",
+    "FilterValue",
+    "RetryConfig",
+    "StrataClient",
+    "compute_filter_fingerprint",
+    "eq",
+    "ge",
+    "gt",
+    "le",
+    "lt",
+    "ne",
+]

strata_client-0.3.0/src/strata_client/_clientconfig.py

@@ -0,0 +1,69 @@
+"""Slim server-URL resolution for the client.
+
+The full :class:`strata.config.StrataConfig` pulls in pydantic, pydantic-settings,
+and notebook submodules — far more than a client needs just to find the server.
+This module replicates *only* the server-URL resolution, standard library only,
+so ``StrataClient()`` can locate the server without importing the server's config
+stack. ``StrataClient(config=...)`` still accepts a full ``StrataConfig`` (it has
+a ``server_url``); this is just the default path.
+
+Resolution precedence (highest wins):
+
+1. ``STRATA_SERVER_URL`` env var (a full URL — the simplest knob for pointing a
+   client at a remote server; not read by the server config itself).
+2. ``STRATA_HOST`` / ``STRATA_PORT`` env vars.
+3. ``[tool.strata]`` ``host`` / ``port`` in the nearest ``pyproject.toml``.
+4. Defaults ``127.0.0.1:8765`` — matching ``StrataConfig`` defaults.
+"""
+
+from __future__ import annotations
+
+import os
+import tomllib
+from pathlib import Path
+from typing import Protocol
+
+_DEFAULT_HOST = "127.0.0.1"
+_DEFAULT_PORT = 8765
+
+
+class HasServerUrl(Protocol):
+    """Anything carrying a ``server_url`` — e.g. a full ``StrataConfig``."""
+
+    @property
+    def server_url(self) -> str: ...
+
+
+def _find_pyproject() -> Path | None:
+    """Find pyproject.toml in the current or a parent directory."""
+    current = Path.cwd()
+    for parent in [current, *current.parents]:
+        candidate = parent / "pyproject.toml"
+        if candidate.exists():
+            return candidate
+    return None
+
+
+def _pyproject_strata() -> dict:
+    """Return the ``[tool.strata]`` table, or ``{}`` if none is found."""
+    path = _find_pyproject()
+    if path is None:
+        return {}
+    try:
+        with open(path, "rb") as f:
+            data = tomllib.load(f)
+    except (OSError, tomllib.TOMLDecodeError):
+        return {}
+    return data.get("tool", {}).get("strata", {})
+
+
+def resolve_server_url() -> str:
+    """Resolve the Strata server URL for a client (see module docstring)."""
+    direct = os.environ.get("STRATA_SERVER_URL")
+    if direct:
+        return direct
+
+    strata_table = _pyproject_strata()
+    host = os.environ.get("STRATA_HOST") or strata_table.get("host") or _DEFAULT_HOST
+    port = os.environ.get("STRATA_PORT") or strata_table.get("port") or _DEFAULT_PORT
+    return f"http://{host}:{port}"