excelizarr 0.1.0__tar.gz

excelizarr-0.1.0/LICENSE

@@ -0,0 +1,232 @@
+THE NOT FIT FOR PURPOSE LICENCE
+(the Apache License 2.0, wearing a hat)
+
+This tool is not fit for purpose. I don't care what your purpose is, this isn't
+it.
+
+It was written to find out whether a spreadsheet could be made cloud-native, a
+question nobody asked, and because a friend saving spreadsheets as HDF5 made me
+wonder.
+I think it works, more or less. The property tests think so too, but they only
+know about the spreadsheets they made up themselves. I make no guarantees.
+
+In particular, it is not fit for: financial reporting; anything an auditor will
+read; anything a regulator will read; anything your boss's boss will read; the
+model that decides interest rates, dosages, or whether the bridge stays up; or
+as a substitute for just keeping the .xlsx.
+
+If you find yourself storing a mission-critical spreadsheet in an object store as
+seven aligned typed arrays, please stop and reflect on the choices that led you
+here. Then use at your own risk.
+
+(Preamble adapted, with admiration, from Kai Striega's parquet-summary:
+https://github.com/Kai-Striega/parquet-summary)
+
+The preamble above is a joke and grants or withholds nothing. The actual terms
+are those of the Apache License, Version 2.0, reproduced unmodified below.
+Section 7 ("Disclaimer of Warranty") says the serious version of everything
+above, in capital letters.
+
+--------------------------------------------------------------------------------
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Charles Turner
+
+   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.

excelizarr-0.1.0/PKG-INFO

@@ -0,0 +1,127 @@
+Metadata-Version: 2.4
+Name: excelizarr
+Version: 0.1.0
+Summary: A cloud-native representation of an .xlsx workbook, in Zarr. Yes, really.
+Author-email: Charles Turner <charles.turner@anu.edu.au>
+Maintainer-email: Charles Turner <charles.turner@anu.edu.au>
+License: Apache Software License 2.0
+Project-URL: bugs, https://github.com/charles-turner-1/excelizarr/issues
+Project-URL: homepage, https://github.com/charles-turner-1/excelizarr
+Classifier: Development Status :: 3 - Alpha
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy
+Requires-Dist: openpyxl
+Requires-Dist: pandas
+Requires-Dist: zarr>=3.3
+Provides-Extra: fast
+Requires-Dist: python-calamine; extra == "fast"
+Provides-Extra: icechunk
+Requires-Dist: icechunk; extra == "icechunk"
+Provides-Extra: dev
+Requires-Dist: black; extra == "dev"
+Requires-Dist: coverage; extra == "dev"
+Requires-Dist: hypothesis; extra == "dev"
+Requires-Dist: mypy; extra == "dev"
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: ruff; extra == "dev"
+Provides-Extra: docs
+Requires-Dist: sphinx>=8; extra == "docs"
+Requires-Dist: myst-nb>=1.2; extra == "docs"
+Requires-Dist: pydata-sphinx-theme>=0.16; extra == "docs"
+Requires-Dist: sphinx-design; extra == "docs"
+Requires-Dist: sphinx-copybutton; extra == "docs"
+Requires-Dist: ipykernel; extra == "docs"
+Requires-Dist: icechunk; extra == "docs"
+Dynamic: license-file
+
+# excelizarr
+
+**A cloud-native representation of an `.xlsx` workbook. In Zarr. Yes, really.**
+
+> [!WARNING]
+> This is a bit of fun. It works and it's property-tested, but please don't put it
+> anywhere important. Claude wrote most of the code at my direction.
+
+A friend made me realise you could save an `.xlsx` spreadsheet as an HDF5 file. That
+raised an obvious question: why not Zarr? Then a workbook is chunked, compressed and
+cloud-readable, and with [Icechunk](https://icechunk.io) it's version-controlled too.
+
+```python
+import excelizarr as xz
+
+wb = xz.xlsx_to_zarr("model.xlsx", "s3://bucket/model.zarr")
+
+wb["Inputs!B2:D10"]                                               # fetches a few chunks
+df = xz.read_excel("s3://bucket/model.zarr", sheet_name="Inputs")  # == pd.read_excel
+xz.zarr_to_xlsx("s3://bucket/model.zarr", "roundtrip.xlsx")       # formulas intact
+```
+
+## How it works
+
+Each sheet becomes a zarr group of aligned, chunked (and sharded) 2D arrays:
+
+- `kind`: which type each cell holds
+- one array per value type: `number`, `string`, `bool`, `temporal`
+- `formula` and `numfmt`
+
+Zarr never writes a chunk that's all fill value, so unused types and empty space cost
+nothing. A range read fetches only the chunks it overlaps, and the root's consolidated
+metadata means opening a workbook is a single read. See
+[the format](docs/guide/format.md).
+
+- **`read_excel` parity.** `xz.read_excel` runs pandas' own Excel parser over the stored
+  cells, so every keyword behaves the same, and a hypothesis property checks the frames
+  match.
+- **Round trips.** Formulas, number formats, merged cells, column widths, frozen panes
+  and defined names all survive xlsx → zarr → xlsx.
+- **Any zarr store.** Local, `s3://`, in memory, a `ZipStore`, or an Icechunk session.
+- **In-place edits.** `wb["Inputs"]["B2"] = 42` rewrites the one shard that cell is in.
+
+## Is it fast?
+
+On a 50,000 × 20 sheet ([details](docs/guide/benchmarks.md)):
+
+| read | seconds |
+|---|---:|
+| `pd.read_excel` (openpyxl) | 2.97 |
+| `pd.read_excel` (calamine) | 0.63 |
+| `pd.read_hdf` | **0.017** |
+| `xz.read_excel` | 0.22 |
+| 100-cell range read | **0.004** |
+
+So HDF is still the right call for "the whole sheet as a DataFrame, fast". excelizarr
+is 14× faster than parsing the `.xlsx`, smaller on disk than either, and much better
+at the cloud-shaped jobs: range reads, partial access and version control.
+
+From S3 (`ap-southeast-2`, from Australia), on a 500,000 × 20 sheet
+([details](docs/guide/cloud.md#whole-sheets)):
+
+| read | seconds |
+|---|---:|
+| `pd.read_excel` (openpyxl) | 34.76 |
+| `pd.read_excel` (calamine) | 8.26 |
+| download + `pd.read_hdf` | **1.99** |
+| `xz.read_excel` | 2.96 |
+| open + 100-cell range read | **0.48** |
+
+The range read costs the same at 10,000 rows as at 500,000: it only ever fetches the
+chunks it needs.
+
+## Development
+
+```bash
+pixi run test             # hypothesis-heavy test suite
+pixi run -e docs docs     # executed MyST docs, warnings are errors
+pixi run -e bench bench   # the benchmark above
+```
+
+## Licence
+
+[The Not Fit For Purpose Licence](LICENSE), which is the Apache License 2.0 with a
+preamble. This tool is not fit for purpose. I don't care what your purpose is, this
+isn't it.

excelizarr-0.1.0/README.md

@@ -0,0 +1,86 @@
+# excelizarr
+
+**A cloud-native representation of an `.xlsx` workbook. In Zarr. Yes, really.**
+
+> [!WARNING]
+> This is a bit of fun. It works and it's property-tested, but please don't put it
+> anywhere important. Claude wrote most of the code at my direction.
+
+A friend made me realise you could save an `.xlsx` spreadsheet as an HDF5 file. That
+raised an obvious question: why not Zarr? Then a workbook is chunked, compressed and
+cloud-readable, and with [Icechunk](https://icechunk.io) it's version-controlled too.
+
+```python
+import excelizarr as xz
+
+wb = xz.xlsx_to_zarr("model.xlsx", "s3://bucket/model.zarr")
+
+wb["Inputs!B2:D10"]                                               # fetches a few chunks
+df = xz.read_excel("s3://bucket/model.zarr", sheet_name="Inputs")  # == pd.read_excel
+xz.zarr_to_xlsx("s3://bucket/model.zarr", "roundtrip.xlsx")       # formulas intact
+```
+
+## How it works
+
+Each sheet becomes a zarr group of aligned, chunked (and sharded) 2D arrays:
+
+- `kind`: which type each cell holds
+- one array per value type: `number`, `string`, `bool`, `temporal`
+- `formula` and `numfmt`
+
+Zarr never writes a chunk that's all fill value, so unused types and empty space cost
+nothing. A range read fetches only the chunks it overlaps, and the root's consolidated
+metadata means opening a workbook is a single read. See
+[the format](docs/guide/format.md).
+
+- **`read_excel` parity.** `xz.read_excel` runs pandas' own Excel parser over the stored
+  cells, so every keyword behaves the same, and a hypothesis property checks the frames
+  match.
+- **Round trips.** Formulas, number formats, merged cells, column widths, frozen panes
+  and defined names all survive xlsx → zarr → xlsx.
+- **Any zarr store.** Local, `s3://`, in memory, a `ZipStore`, or an Icechunk session.
+- **In-place edits.** `wb["Inputs"]["B2"] = 42` rewrites the one shard that cell is in.
+
+## Is it fast?
+
+On a 50,000 × 20 sheet ([details](docs/guide/benchmarks.md)):
+
+| read | seconds |
+|---|---:|
+| `pd.read_excel` (openpyxl) | 2.97 |
+| `pd.read_excel` (calamine) | 0.63 |
+| `pd.read_hdf` | **0.017** |
+| `xz.read_excel` | 0.22 |
+| 100-cell range read | **0.004** |
+
+So HDF is still the right call for "the whole sheet as a DataFrame, fast". excelizarr
+is 14× faster than parsing the `.xlsx`, smaller on disk than either, and much better
+at the cloud-shaped jobs: range reads, partial access and version control.
+
+From S3 (`ap-southeast-2`, from Australia), on a 500,000 × 20 sheet
+([details](docs/guide/cloud.md#whole-sheets)):
+
+| read | seconds |
+|---|---:|
+| `pd.read_excel` (openpyxl) | 34.76 |
+| `pd.read_excel` (calamine) | 8.26 |
+| download + `pd.read_hdf` | **1.99** |
+| `xz.read_excel` | 2.96 |
+| open + 100-cell range read | **0.48** |
+
+The range read costs the same at 10,000 rows as at 500,000: it only ever fetches the
+chunks it needs.
+
+## Development
+
+```bash
+pixi run test             # hypothesis-heavy test suite
+pixi run -e docs docs     # executed MyST docs, warnings are errors
+pixi run -e bench bench   # the benchmark above
+```
+
+## Licence
+
+[The Not Fit For Purpose Licence](LICENSE), which is the Apache License 2.0 with a
+preamble. This tool is not fit for purpose. I don't care what your purpose is, this
+isn't it.

excelizarr-0.1.0/pyproject.toml

@@ -0,0 +1,207 @@
+[build-system]
+requires = ["setuptools>=64", "versioneer[toml]==0.29"]
+build-backend = "setuptools.build_meta"
+
+
+[project]
+name = "excelizarr"
+description = "A cloud-native representation of an .xlsx workbook, in Zarr. Yes, really."
+readme = "README.md"
+requires-python = ">=3.12"
+authors = [{ name = "Charles Turner", email = "charles.turner@anu.edu.au" }]
+maintainers = [{ name = "Charles Turner", email = "charles.turner@anu.edu.au" }]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: Apache Software License",
+    "Operating System :: OS Independent",
+]
+license = { text = "Apache Software License 2.0" }
+dependencies = [
+    "numpy",
+    "openpyxl", # the full-fidelity reader and the only writer: formulas, formats, merges
+    "pandas",
+    "zarr>=3.3",  # Store.get_ranges: shard reads coalesce
+]
+
+dynamic = ["version"]
+
+[project.optional-dependencies]
+# The calamine-backed reader (cell-level types, unlike fastexcel's column-typed Arrow):
+fast = ["python-calamine"]
+# Version-controlled spreadsheets. Any zarr store works; this just makes it fun.
+icechunk = ["icechunk"]
+dev = [
+    "black",      # formatting
+    "coverage",   # testing
+    "hypothesis", # testing (property-based)
+    "mypy",       # linting
+    "pytest",     # testing
+    "ruff",       # linting
+]
+# Declared once, consumed twice: pixi exposes every optional-dependency group as a
+# feature of the same name, and Read the Docs installs ``.[docs]`` with pip.
+docs = [
+    "sphinx>=8",
+    "myst-nb>=1.2",               # MyST pages *and* executed code cells; it bundles myst-parser
+    "pydata-sphinx-theme>=0.16",
+    "sphinx-design",
+    "sphinx-copybutton",
+    "ipykernel",                  # myst-nb executes pages through a Jupyter kernel
+    "icechunk",                   # the version-control page is executed
+]
+
+[project.urls]
+bugs = "https://github.com/charles-turner-1/excelizarr/issues"
+homepage = "https://github.com/charles-turner-1/excelizarr"
+
+[tool.setuptools]
+package-dir = { "" = "src" }
+
+[tool.setuptools.package-data]
+"*" = ["*.*"]
+
+
+# Mypy
+# ----
+
+[tool.mypy]
+files = "src"
+exclude = ["src/excelizarr/_version.py"]
+strict = true
+warn_unreachable = true
+warn_no_return = true
+allow_subclassing_any = true
+
+[[tool.mypy.overrides]]
+# versioneer-generated. ``exclude`` keeps it out of ``mypy`` runs that discover files,
+# but pre-commit passes ``src`` explicitly, which bypasses ``exclude``.
+module = ["excelizarr._version"]
+ignore_errors = true
+
+[[tool.mypy.overrides]]
+# Neither ships type information.
+module = ["openpyxl.*", "python_calamine.*"]
+ignore_missing_imports = true
+
+[tool.versioneer]
+VCS = "git"
+style = "pep440"
+versionfile_source = "src/excelizarr/_version.py"
+versionfile_build = "excelizarr/_version.py"
+tag_prefix = "v"
+parentdir_prefix = "excelizarr-"
+
+[tool.coverage.run]
+omit = ["*/_version.py"]
+
+[tool.ruff]
+target-version = "py312"
+exclude = [".git", ".mypy_cache", ".ruff_cache", ".venv", ".pixi", "_build", "build", "dist", "versioneer.py", "_version.py", "tests"]
+
+[tool.ruff.lint]
+# E402: module level import not at top of file
+# E501: line too long - let black worry about that
+# D105: magic methods carry their meaning in the name
+# D205: black owns the wrapping of multi-sentence summaries
+ignore = ["E402", "E501", "D105", "D205"]
+select = ["F", "E", "W", "I", "UP", "D"]
+
+[tool.ruff.lint.per-file-ignores]
+"tests/**" = ["D401"]
+
+[tool.ruff.lint.pydocstyle]
+convention = "numpy"
+
+[tool.ruff.lint.isort]
+known-first-party = ["excelizarr"]
+
+[tool.pytest.ini_options]
+addopts = "--hypothesis-show-statistics"
+
+
+# Pixi
+# ----
+
+[tool.pixi.workspace]
+channels = ["conda-forge"]
+name = "excelizarr"
+platforms = ["osx-arm64", "linux-64", "win-64"]
+
+[tool.pixi.dependencies]
+python = ">=3.12"
+numpy = "*"
+openpyxl = "*"
+pandas = "*"
+zarr = ">=3.3"
+versioneer = ">=0.29,<0.30"
+setuptools = ">=64"
+
+[tool.pixi.pypi-dependencies]
+excelizarr = { editable = true, path = "." }
+
+[tool.pixi.environments]
+default = { features = ["dev", "test", "fast", "icechunk"], solve-group = "default" }
+test-py312 = { features = ["py312", "test", "fast", "icechunk"] }
+test-py313 = { features = ["py313", "test", "fast", "icechunk"] }
+# The bare arm: no fastexcel, no icechunk. Their tests ``importorskip``, and this is the
+# environment that proves excelizarr itself never needs either.
+test-minimal = { features = ["test"] }
+docs = { features = ["docs", "fast"], solve-group = "default" }
+# Only the benchmark script needs these: the HDF comparison is the whole point of it.
+bench = { features = ["bench", "fast"], solve-group = "default" }
+
+[tool.pixi.feature.fast.dependencies]
+python-calamine = "*"
+
+[tool.pixi.feature.icechunk.dependencies]
+icechunk = "*"
+
+[tool.pixi.feature.test.dependencies]
+pytest = ">=8.4.2"
+coverage = "*"
+hypothesis = "*"
+
+[tool.pixi.feature.test.tasks]
+test = { cmd = "pytest tests", description = "Run tests" }
+test-cov = { cmd = "coverage run -m --source=excelizarr pytest tests && coverage xml", description = "Run tests with coverage and generate xml report" }
+
+[tool.pixi.feature.dev.dependencies]
+pre-commit = ">=4.2.0,<5"
+ruff = "*"
+black = "*"
+mypy = "*"
+pandas-stubs = "*"
+
+[tool.pixi.feature.dev.tasks]
+ruff = { cmd = "ruff check src", description = "Run ruff checks" }
+black = { cmd = "black src tests benchmarks", description = "Run the black formatter" }
+mypy = { cmd = "mypy", description = "Run mypy type checks (config: [tool.mypy])" }
+pre-commit = { cmd = "pre-commit run --all-files", description = "Run pre-commit hooks" }
+pre-commit-install = { cmd = "pre-commit install", description = "Install pre-commit hooks" }
+
+[tool.pixi.feature.docs.tasks]
+docs = { cmd = "sphinx-build -W --keep-going -b html docs docs/_build/html", description = "Build the docs (warnings are errors)" }
+
+[tool.pixi.feature.bench.dependencies]
+pytables = "*"
+
+[tool.pixi.feature.bench.tasks]
+bench = { cmd = "python benchmarks/bench_read.py", description = "Time xlsx vs HDF vs Zarr reads" }
+
+[tool.pixi.feature.py312.dependencies]
+python = "3.12.*"
+
+[tool.pixi.feature.py313.dependencies]
+python = "3.13.*"
+
+[tool.numpydoc_validation]
+checks = [
+    "PR01", "PR02", "PR03", "PR04", "PR05", "PR06", "PR07",
+    "RT01", "RT03", "RT04",
+    "GL02", "GL03",
+    "YD01",
+]
+# Single-underscore helpers are private and documented as much as they need, which is
+# often one line. Dunders still validate: ``__getitem__``/``__setitem__`` are API here.
+exclude = ['\._[a-z]\w*$']

excelizarr-0.1.0/setup.cfg

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

excelizarr-0.1.0/setup.py

@@ -0,0 +1,11 @@
+# type: ignore
+"""Shim so versioneer can supply the version; the real metadata is in pyproject.toml."""
+
+from setuptools import setup
+
+import versioneer
+
+setup(
+    version=versioneer.get_version(),
+    cmdclass=versioneer.get_cmdclass(),
+)