damicore-normalizer 0.1.0__tar.gz

damicore_normalizer-0.1.0/.gitignore

@@ -0,0 +1,224 @@
+# 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/
+
+# Local scratch / generated output (never commit)
+.temp/
+.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__/
+
+# LaTeX build artefacts (papers)
+models/**/paper/*.aux
+models/**/paper/*.bbl
+models/**/paper/*.bcf
+models/**/paper/*.blg
+models/**/paper/*.fdb_latexmk
+models/**/paper/*.fls
+models/**/paper/*.log
+models/**/paper/*.out
+models/**/paper/*.run.xml
+models/**/paper/*.synctex.gz
+models/**/paper/*.toc
+models/**/paper/*.pdf

damicore_normalizer-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 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 Ennio Politi Lopes
+
+   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.

damicore_normalizer-0.1.0/PKG-INFO

@@ -0,0 +1,66 @@
+Metadata-Version: 2.5
+Name: damicore-normalizer
+Version: 0.1.0
+Summary: Dataset normalization stage for the DAMICORE pipeline.
+Project-URL: Homepage, https://github.com/Delbem-Research-and-Innovation/damicore
+Project-URL: Repository, https://github.com/Delbem-Research-and-Innovation/damicore
+Project-URL: Issues, https://github.com/Delbem-Research-and-Innovation/damicore/issues
+Project-URL: Documentation, https://github.com/Delbem-Research-and-Innovation/damicore/blob/main/docs/quickstart.md
+Project-URL: Changelog, https://github.com/Delbem-Research-and-Innovation/damicore/blob/main/CHANGELOG.md
+Author-email: Ennio Politi Lopes <enniolopes@users.noreply.github.com>
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: canonical-serialization,csv,damicore,normalization
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Typing :: Typed
+Requires-Python: <3.15,>=3.11
+Requires-Dist: pandas<4,>=2.2
+Requires-Dist: pydantic<3,>=2.10
+Description-Content-Type: text/markdown
+
+# damicore-normalizer
+
+damicore-normalizer deterministically serializes the columns or rows of a local
+CSV as canonical JSONL objects, recording the size and SHA-256 of every object.
+It is the first stage of the DAMICORE pipeline; most users install the aggregate
+`damicore` distribution, which runs all four stages end to end. Install this
+package alone to normalize datasets without the rest of the pipeline.
+
+```bash
+pip install damicore-normalizer
+```
+
+## Python
+
+```python
+from damicore_normalizer import NormalizationConfig, normalize_csv
+
+result = normalize_csv(
+    "dataset.csv",
+    "normalization",
+    config=NormalizationConfig(split="columns", chunk_rows=50_000),
+)
+```
+
+The call streams through `pandas.read_csv`, bounds open column files with an
+LRU pool, and writes the objects plus a `manifest.json` into the output
+directory. That normalization manifest is the input the sibling
+`damicore-distance` distribution consumes to compute the NCD matrix.
+
+## Links
+
+- Repository: <https://github.com/Delbem-Research-and-Innovation/damicore>
+- Issues: <https://github.com/Delbem-Research-and-Innovation/damicore/issues>
+- Documentation:
+  <https://github.com/Delbem-Research-and-Innovation/damicore/blob/main/docs/quickstart.md>
+
+Licensed under Apache-2.0.

damicore_normalizer-0.1.0/README.md

@@ -0,0 +1,37 @@
+# damicore-normalizer
+
+damicore-normalizer deterministically serializes the columns or rows of a local
+CSV as canonical JSONL objects, recording the size and SHA-256 of every object.
+It is the first stage of the DAMICORE pipeline; most users install the aggregate
+`damicore` distribution, which runs all four stages end to end. Install this
+package alone to normalize datasets without the rest of the pipeline.
+
+```bash
+pip install damicore-normalizer
+```
+
+## Python
+
+```python
+from damicore_normalizer import NormalizationConfig, normalize_csv
+
+result = normalize_csv(
+    "dataset.csv",
+    "normalization",
+    config=NormalizationConfig(split="columns", chunk_rows=50_000),
+)
+```
+
+The call streams through `pandas.read_csv`, bounds open column files with an
+LRU pool, and writes the objects plus a `manifest.json` into the output
+directory. That normalization manifest is the input the sibling
+`damicore-distance` distribution consumes to compute the NCD matrix.
+
+## Links
+
+- Repository: <https://github.com/Delbem-Research-and-Innovation/damicore>
+- Issues: <https://github.com/Delbem-Research-and-Innovation/damicore/issues>
+- Documentation:
+  <https://github.com/Delbem-Research-and-Innovation/damicore/blob/main/docs/quickstart.md>
+
+Licensed under Apache-2.0.

damicore_normalizer-0.1.0/pyproject.toml

@@ -0,0 +1,63 @@
+[project]
+name = "damicore-normalizer"
+version = "0.1.0"
+description = "Dataset normalization stage for the DAMICORE pipeline."
+readme = "README.md"
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+authors = [{ name = "Ennio Politi Lopes", email = "enniolopes@users.noreply.github.com" }]
+requires-python = ">=3.11,<3.15"
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Science/Research",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3 :: Only",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
+    "Operating System :: OS Independent",
+    "Topic :: Scientific/Engineering :: Information Analysis",
+    "Typing :: Typed",
+]
+keywords = ["damicore", "csv", "normalization", "canonical-serialization"]
+dependencies = [
+    "pandas>=2.2,<4",
+    "pydantic>=2.10,<3",
+]
+
+[project.urls]
+Homepage = "https://github.com/Delbem-Research-and-Innovation/damicore"
+Repository = "https://github.com/Delbem-Research-and-Innovation/damicore"
+Issues = "https://github.com/Delbem-Research-and-Innovation/damicore/issues"
+Documentation = "https://github.com/Delbem-Research-and-Innovation/damicore/blob/main/docs/quickstart.md"
+Changelog = "https://github.com/Delbem-Research-and-Innovation/damicore/blob/main/CHANGELOG.md"
+
+[build-system]
+requires = ["hatchling>=1.31.0,<2"]
+build-backend = "hatchling.build"
+
+# Workspace-only files are excluded on purpose: each package's Makefile only includes
+# ../package.mk, pyrightconfig.json extends ../../pyrightconfig.json, and tests/ depends
+# on the workspace conftest and dev tooling, so none of them work in an sdist unpacked
+# outside the monorepo. The repository .gitignore still ships: hatchling force-includes
+# the located VCS ignore file so an sdist-to-wheel build selects files the same way, and
+# `exclude` deliberately cannot override that.
+[tool.hatch.build.targets.sdist]
+exclude = ["Makefile", "pyrightconfig.json", "tests"]
+
+[tool.ruff]
+line-length = 100
+exclude = [".venv", "dist", "__pycache__"]
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "RUF100", "UP"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+pythonpath = ["src"]
+markers = ["unit: fast isolated unit tests"]
+# --cov-branch and the floor mirror the root configuration on purpose: coverage resolves
+# its config from the working directory, so a package-scoped run would otherwise report
+# line coverage with no threshold and read as a stronger result than it is.
+addopts = "--cov=damicore_normalizer --cov-branch --cov-report=term-missing --cov-fail-under=90"

damicore_normalizer-0.1.0/src/damicore_normalizer/__init__.py

@@ -0,0 +1,12 @@
+from damicore_normalizer.api import normalize_csv
+from damicore_normalizer.config import NormalizationConfig
+from damicore_normalizer.errors import NormalizerError
+from damicore_normalizer.manifest import NormalizationResult, ObjectDescriptor
+
+__all__ = [
+    "normalize_csv",
+    "NormalizationConfig",
+    "NormalizationResult",
+    "ObjectDescriptor",
+    "NormalizerError",
+]

damicore_normalizer-0.1.0/src/damicore_normalizer/api.py

@@ -0,0 +1,99 @@
+from __future__ import annotations
+
+import hashlib
+import json
+import os
+import tempfile
+from pathlib import Path
+
+from damicore_normalizer.config import NormalizationConfig
+from damicore_normalizer.csv_reader import scan_csv
+from damicore_normalizer.errors import NormalizerError
+from damicore_normalizer.manifest import (
+    NormalizationInput,
+    NormalizationManifest,
+    NormalizationResult,
+)
+
+
+def _sha256(path: Path, chunk_size: int = 4_194_304) -> str:
+    digest = hashlib.sha256()
+    with path.open("rb") as stream:
+        while chunk := stream.read(chunk_size):
+            digest.update(chunk)
+    return digest.hexdigest()
+
+
+def _atomic_json(path: Path, value: object) -> None:
+    payload = (
+        json.dumps(
+            value,
+            ensure_ascii=False,
+            indent=2,
+            sort_keys=True,
+            allow_nan=False,
+        )
+        + "\n"
+    )
+    descriptor, temporary_name = tempfile.mkstemp(dir=path.parent, prefix=f".{path.name}.")
+    try:
+        with os.fdopen(descriptor, "w", encoding="utf-8", newline="\n") as stream:
+            stream.write(payload)
+            stream.flush()
+            os.fsync(stream.fileno())
+        os.replace(temporary_name, path)
+    finally:
+        if os.path.exists(temporary_name):
+            os.unlink(temporary_name)
+
+
+def normalize_csv(
+    csv_path: str | Path,
+    output_dir: str | Path,
+    *,
+    config: NormalizationConfig | None = None,
+) -> NormalizationResult:
+    """Normalize a local CSV into deterministic versioned object artifacts."""
+    settings = config or NormalizationConfig()
+    source = Path(csv_path).resolve()
+    if not source.is_file():
+        raise NormalizerError(
+            f"CSV path is not a regular file: {source}",
+            code="input_validation_error",
+        )
+    before = source.stat()
+    destination = Path(output_dir).resolve()
+    if destination.exists() and (not destination.is_dir() or any(destination.iterdir())):
+        raise NormalizerError("output_dir must be absent or empty", code="output_conflict_error")
+    destination.mkdir(parents=True, exist_ok=True)
+    scan = scan_csv(source, settings, objects_dir=destination / "objects")
+    after = source.stat()
+    if (before.st_size, before.st_mtime_ns) != (after.st_size, after.st_mtime_ns):
+        raise NormalizerError("CSV changed during normalization", code="input_drift")
+    for item in scan.objects:
+        object_path = destination / item.relative_path
+        if object_path.stat().st_size != item.size_bytes or _sha256(object_path) != item.sha256:
+            raise NormalizerError(
+                f"normalized object failed validation: {item.object_id}",
+                code="artifact_validation_error",
+            )
+    manifest_path = destination / "manifest.json"
+    manifest = NormalizationManifest(
+        schema_version=1,
+        input=NormalizationInput(
+            path=str(source),
+            sha256=_sha256(source),
+            size_bytes=before.st_size,
+            delimiter=settings.delimiter,
+            encoding=settings.encoding,
+            split=settings.split,
+        ),
+        objects=scan.objects,
+    )
+    _atomic_json(manifest_path, manifest.model_dump(mode="json"))
+    return NormalizationResult(
+        manifest_path=manifest_path,
+        object_count=len(scan.objects),
+        total_bytes=scan.total_bytes,
+        objects=scan.objects,
+    )

damicore_normalizer-0.1.0/src/damicore_normalizer/config.py

@@ -0,0 +1,31 @@
+from __future__ import annotations
+
+import codecs
+from typing import Literal
+
+from pydantic import BaseModel, ConfigDict, Field, field_validator
+
+
+class NormalizationConfig(BaseModel):
+    """Configuration for deterministic CSV normalization."""
+
+    model_config = ConfigDict(frozen=True, extra="forbid")
+
+    split: Literal["columns", "rows"] = "columns"
+    delimiter: str = ","
+    encoding: str = "utf-8"
+    chunk_rows: int = Field(default=50_000, gt=0)
+    max_open_files: int = Field(default=64, gt=0)
+
+    @field_validator("delimiter")
+    @classmethod
+    def _validate_delimiter(cls, value: str) -> str:
+        if len(value) != 1:
+            raise ValueError("delimiter must contain exactly one Unicode character")
+        return value
+
+    @field_validator("encoding")
+    @classmethod
+    def _validate_encoding(cls, value: str) -> str:
+        codecs.lookup(value)
+        return value

damicore_normalizer-0.1.0/src/damicore_normalizer/csv_reader.py

@@ -0,0 +1,251 @@
+from __future__ import annotations
+
+import codecs
+import csv
+import hashlib
+from collections import OrderedDict
+from collections.abc import Generator
+from contextlib import contextmanager
+from dataclasses import dataclass
+from pathlib import Path
+from typing import BinaryIO
+
+import pandas as pd
+
+from damicore_normalizer.config import NormalizationConfig
+from damicore_normalizer.errors import NormalizerError
+from damicore_normalizer.manifest import ObjectDescriptor
+from damicore_normalizer.serializer import serialize_cell, serialize_row
+
+# A single field may be this many characters during the csv.reader passes. csv defaults to
+# 131072, which pandas does not impose, so without this a well-formed wide cell would be
+# reported as malformed. The value is a bound the C long behind field_size_limit accepts on
+# every supported platform, not a contract: section 10.1 sets no field-size limit.
+_MAX_FIELD_CHARS = 2**31 - 1
+
+
+def _strip_bom(header: list[str], encoding: str) -> list[str]:
+    """Drop a leading UTF-8 BOM from the first column name, as pandas' C parser does.
+
+    Python's ``utf-8`` codec keeps the BOM, so without this the two readers disagree on the
+    first name and the per-chunk header check rejects a well-formed file. Decoding through
+    ``utf-8-sig`` instead would buffer past the header, which would misreport an undecodable
+    data row as a header failure.
+    """
+    if not header or codecs.lookup(encoding).name != "utf-8":
+        return header
+    return [header[0].removeprefix("\ufeff"), *header[1:]]
+
+
+@contextmanager
+def _relaxed_field_size_limit() -> Generator[None]:
+    """Lift csv's field-size cap for the duration of a validation pass.
+
+    The cap is process-global state, so it is restored on exit; the passes it wraps are
+    synchronous and do not run user code.
+    """
+    previous = csv.field_size_limit(_MAX_FIELD_CHARS)
+    try:
+        yield
+    finally:
+        csv.field_size_limit(previous)
+
+
+@dataclass(frozen=True)
+class ScanResult:
+    objects: tuple[ObjectDescriptor, ...]
+    total_bytes: int
+    max_serialized_chunk_bytes: int
+    row_count: int
+
+
+class _FilePool:
+    def __init__(self, root: Path, limit: int) -> None:
+        self._root = root
+        self._limit = limit
+        self._streams: OrderedDict[str, BinaryIO] = OrderedDict()
+
+    def write(self, name: str, payload: bytes) -> None:
+        stream = self._streams.pop(name, None)
+        if stream is None:
+            if len(self._streams) >= self._limit:
+                _, oldest = self._streams.popitem(last=False)
+                oldest.close()
+            stream = (self._root / name).open("ab")
+        self._streams[name] = stream
+        stream.write(payload)
+
+    def close(self) -> None:
+        for stream in self._streams.values():
+            stream.close()
+        self._streams.clear()
+
+
+def _read_header(path: Path, config: NormalizationConfig) -> list[str]:
+    try:
+        with (
+            _relaxed_field_size_limit(),
+            path.open("r", encoding=config.encoding, errors="strict", newline="") as stream,
+        ):
+            header = _strip_bom(
+                next(csv.reader(stream, delimiter=config.delimiter)), config.encoding
+            )
+    except (OSError, UnicodeError, csv.Error, StopIteration) as exc:
+        raise NormalizerError("Could not read a valid CSV header", code="csv_format_error") from exc
+    if not header or any(name == "" for name in header):
+        raise NormalizerError("CSV header names must be non-empty", code="csv_format_error")
+    if len(set(header)) != len(header):
+        raise NormalizerError("CSV header names must be unique", code="csv_format_error")
+    return header
+
+
+def _validate_record_widths(path: Path, config: NormalizationConfig, width: int) -> None:
+    """Reject any record whose field count disagrees with the mandatory header.
+
+    ``on_bad_lines="error"`` cannot express this rule on its own. When every data row carries
+    surplus fields, the C parser reads the leading ones as an index and those cells disappear;
+    when only a later row does, the surplus is dropped or reported depending on where the chunk
+    boundary falls; a short row is padded with a cell the input never contained. The canonical
+    bytes would then depend on ``chunk_rows``, which section 24.1 forbids.
+
+    ``csv.reader`` agrees with pandas on record boundaries and field counts once the two are
+    configured to match, so one streaming pass over the raw records makes the check total.
+    Two axes had to be aligned deliberately and are handled above: the BOM, which pandas
+    strips and this codec does not, and the field-size cap, which pandas does not impose. A
+    blank line is a third: ``skip_blank_lines=False`` defines it as a full-width empty row,
+    and pandas materializes it as one.
+    """
+    try:
+        with (
+            _relaxed_field_size_limit(),
+            path.open("r", encoding=config.encoding, errors="strict", newline="") as stream,
+        ):
+            reader = csv.reader(stream, delimiter=config.delimiter)
+            next(reader, None)
+            for number, record in enumerate(reader, start=2):
+                if record and len(record) != width:
+                    raise NormalizerError(
+                        f"CSV line {number} has {len(record)} fields but the header declares "
+                        f"{width}",
+                        code="csv_format_error",
+                    )
+    except (OSError, UnicodeError, csv.Error) as exc:
+        raise NormalizerError("CSV parsing failed", code="csv_format_error") from exc
+
+
+def scan_csv(
+    csv_path: str | Path,
+    config: NormalizationConfig,
+    *,
+    objects_dir: Path | None = None,
+) -> ScanResult:
+    """Scan canonical object bytes; optionally persist them through the same path."""
+    path = Path(csv_path).resolve()
+    if not path.is_file():
+        raise NormalizerError(
+            f"CSV path is not a regular file: {path}",
+            code="input_validation_error",
+        )
+    header = _read_header(path, config)
+    if config.split == "columns" and len(header) < 2:
+        raise NormalizerError(
+            "columns split requires at least two columns",
+            code="csv_format_error",
+        )
+
+    # Structure is settled before anything is created, so a malformed CSV never leaves a
+    # partially written objects directory behind.
+    _validate_record_widths(path, config, len(header))
+
+    if objects_dir is not None:
+        objects_dir.mkdir(parents=True, exist_ok=False)
+
+    column_hashes = [hashlib.sha256() for _ in header]
+    column_sizes = [0 for _ in header]
+    row_objects: list[ObjectDescriptor] = []
+    max_chunk_bytes = 0
+    row_count = 0
+    pool = _FilePool(objects_dir, config.max_open_files) if objects_dir is not None else None
+
+    try:
+        chunks = pd.read_csv(
+            path,
+            sep=config.delimiter,
+            encoding=config.encoding,
+            dtype=str,
+            keep_default_na=False,
+            na_filter=False,
+            skip_blank_lines=False,
+            chunksize=config.chunk_rows,
+            on_bad_lines="error",
+            quotechar='"',
+            doublequote=True,
+            comment=None,
+            # No inference of any kind, including an index inferred from row width. Records
+            # are already known to match the header, so this only pins the parser's contract.
+            index_col=False,
+        )
+        for chunk in chunks:
+            if list(chunk.columns) != header:
+                raise NormalizerError("CSV header changed while parsing", code="csv_format_error")
+            chunk_bytes = 0
+            for values in chunk.itertuples(index=False, name=None):
+                text_values = tuple(str(value) for value in values)
+                row_count += 1
+                if config.split == "rows":
+                    payload = serialize_row(text_values)
+                    object_id = f"row_{row_count:06d}"
+                    relative_path = f"objects/{object_id}.jsonl"
+                    digest = hashlib.sha256(payload).hexdigest()
+                    row_objects.append(
+                        ObjectDescriptor(
+                            object_id=object_id,
+                            label=object_id,
+                            relative_path=relative_path,
+                            size_bytes=len(payload),
+                            sha256=digest,
+                        )
+                    )
+                    if objects_dir is not None:
+                        (objects_dir / f"{object_id}.jsonl").write_bytes(payload)
+                    chunk_bytes += len(payload)
+                else:
+                    for index, value in enumerate(text_values):
+                        payload = serialize_cell(value)
+                        column_hashes[index].update(payload)
+                        column_sizes[index] += len(payload)
+                        chunk_bytes += len(payload)
+                        if pool is not None:
+                            pool.write(f"column_{index + 1:06d}.jsonl", payload)
+            max_chunk_bytes = max(max_chunk_bytes, chunk_bytes)
+    except NormalizerError:
+        raise
+    except (OSError, UnicodeError, ValueError) as exc:
+        # pd.errors.ParserError is a ValueError subclass, already caught above.
+        raise NormalizerError("CSV parsing failed", code="csv_format_error") from exc
+    finally:
+        if pool is not None:
+            pool.close()
+
+    if row_count == 0 or (config.split == "rows" and row_count < 2):
+        raise NormalizerError("CSV does not contain enough data rows", code="csv_format_error")
+
+    if config.split == "columns":
+        objects = tuple(
+            ObjectDescriptor(
+                object_id=f"column_{index + 1:06d}",
+                label=label,
+                relative_path=f"objects/column_{index + 1:06d}.jsonl",
+                size_bytes=column_sizes[index],
+                sha256=column_hashes[index].hexdigest(),
+            )
+            for index, label in enumerate(header)
+        )
+    else:
+        objects = tuple(row_objects)
+    return ScanResult(
+        objects=objects,
+        total_bytes=sum(item.size_bytes for item in objects),
+        max_serialized_chunk_bytes=max_chunk_bytes,
+        row_count=row_count,
+    )

damicore_normalizer-0.1.0/src/damicore_normalizer/errors.py

@@ -0,0 +1,10 @@
+from __future__ import annotations
+
+
+class NormalizerError(Exception):
+    """Base error raised by the standalone normalizer package."""
+
+    def __init__(self, message: str, *, code: str = "normalizer_error", **context: object) -> None:
+        super().__init__(message)
+        self.code = code
+        self.context = context

damicore_normalizer-0.1.0/src/damicore_normalizer/manifest.py

@@ -0,0 +1,52 @@
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Literal
+
+from pydantic import BaseModel, ConfigDict, Field, field_validator
+
+
+class ObjectDescriptor(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="forbid", strict=True)
+
+    object_id: str
+    label: str
+    relative_path: str
+    size_bytes: int = Field(ge=0)
+    sha256: str = Field(pattern=r"^[0-9a-f]{64}$")
+
+    @field_validator("relative_path")
+    @classmethod
+    def _relative_path_is_contained(cls, value: str) -> str:
+        path = Path(value)
+        if path.is_absolute() or ".." in path.parts or path.as_posix() != value:
+            raise ValueError("relative_path must be a contained POSIX path")
+        return value
+
+
+class NormalizationInput(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="forbid", strict=True)
+
+    path: str
+    sha256: str = Field(pattern=r"^[0-9a-f]{64}$")
+    size_bytes: int = Field(ge=0)
+    delimiter: str = Field(min_length=1, max_length=1)
+    encoding: str
+    split: Literal["columns", "rows"]
+
+
+class NormalizationManifest(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="forbid", strict=True)
+
+    schema_version: Literal[1]
+    input: NormalizationInput
+    objects: tuple[ObjectDescriptor, ...]
+
+
+class NormalizationResult(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="forbid", strict=True)
+
+    manifest_path: Path
+    object_count: int = Field(ge=0)
+    total_bytes: int = Field(ge=0)
+    objects: tuple[ObjectDescriptor, ...]

damicore_normalizer-0.1.0/src/damicore_normalizer/serializer.py

@@ -0,0 +1,14 @@
+from __future__ import annotations
+
+import json
+from collections.abc import Sequence
+
+
+def serialize_cell(value: str) -> bytes:
+    return (json.dumps(value, ensure_ascii=False, separators=(",", ":")) + "\n").encode("utf-8")
+
+
+def serialize_row(values: Sequence[str]) -> bytes:
+    return (json.dumps(list(values), ensure_ascii=False, separators=(",", ":")) + "\n").encode(
+        "utf-8"
+    )