stoms 0.2.0__tar.gz

stoms-0.2.0/.github/workflows/docs.yml

@@ -0,0 +1,39 @@
+name: Publish documentation
+
+on:
+  push:
+    branches: [main]
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+concurrency:
+  group: pages
+  cancel-in-progress: false
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+      - run: pip install "mkdocs>=1.6"
+      - run: mkdocs build --strict
+      - uses: actions/upload-pages-artifact@v3
+        with:
+          path: site
+
+  deploy:
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    needs: build
+    runs-on: ubuntu-latest
+    steps:
+      - id: deployment
+        uses: actions/deploy-pages@v4

stoms-0.2.0/.gitignore

@@ -0,0 +1,248 @@
+
+# Created by https://www.gitignore.io/api/vim,macos,emacs,python,visualstudiocode
+# Edit at https://www.gitignore.io/?templates=vim,macos,emacs,python,visualstudiocode
+
+### Emacs ###
+# -*- mode: gitignore; -*-
+*~
+\#*\#
+/.emacs.desktop
+/.emacs.desktop.lock
+*.elc
+auto-save-list
+tramp
+.\#*
+
+# Org-mode
+.org-id-locations
+*_archive
+
+# flymake-mode
+*_flymake.*
+
+# eshell files
+/eshell/history
+/eshell/lastdir
+
+# elpa packages
+/elpa/
+
+# reftex files
+*.rel
+
+# AUCTeX auto folder
+/auto/
+
+# cask packages
+.cask/
+dist/
+
+# Flycheck
+flycheck_*.el
+
+# server auth directory
+/server/
+
+# projectiles files
+.projectile
+
+# directory configuration
+.dir-locals.el
+
+# network security
+/network-security.data
+
+
+### macOS ###
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+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
+.hypothesis/
+.pytest_cache/
+
+# 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
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.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
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.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/
+
+### Vim ###
+# Swap
+[._]*.s[a-v][a-z]
+[._]*.sw[a-p]
+[._]s[a-rt-v][a-z]
+[._]ss[a-gi-z]
+[._]sw[a-p]
+
+# Session
+Session.vim
+Sessionx.vim
+
+# Temporary
+.netrwhist
+# Auto-generated tag files
+tags
+# Persistent undo
+[._]*.un~
+
+### VisualStudioCode ###
+.vscode/*
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+
+# Weights & Biases
+wandb/
+
+# Model checkpoints
+*.pt
+*.pth
+*.ckpt
+
+# Scratch files (spikes, local issues)
+# .scratch/
+
+# End of https://www.gitignore.io/api/vim,macos,emacs,python,visualstudiocode
+
+temp/

stoms-0.2.0/.pre-commit-config.yaml

@@ -0,0 +1,13 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v6.0.0
+    hooks:
+      - id: end-of-file-fixer
+      - id: check-added-large-files
+        args: [--maxkb=500000]
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.15.22
+    hooks:
+      - id: ruff-check
+        args: [--fix]
+      - id: ruff-format

stoms-0.2.0/AUTHORS

@@ -0,0 +1 @@
+Ralf Wanzenboeck <ralf.wanzenboeck@tuwien.ac.at>

stoms-0.2.0/CONTEXT.md

@@ -0,0 +1,187 @@
+# STOMS (Storage Tool Of Minor Significance)
+
+AtomsLedger is an immutable, provenance-first record store for atomistic
+research data. Every ledger has the same data model and behavior; ledger scopes
+only describe the user's workflow and data-stewardship role.
+
+## Ledger Scopes
+
+**Dev-ledger**:
+A SQLite ledger used for local experimentation, prototyping, or scoping. A
+project may use any number of dev-ledgers at any point in its lifecycle.
+_Avoid_: scratch ledger, test ledger
+
+**Project-ledger**:
+A SQLite ledger used as the authoritative record for one research project,
+including production results and selected dev data.
+_Avoid_: project namespace, project partition
+
+**Research-ledger**:
+A SQLite ledger that holds data from multiple research projects.
+_Avoid_: master ledger, global ledger
+
+**Promotion**:
+The additive transfer of records from one ledger into another. It does not have
+scope-specific storage semantics; target ledger-entry IDs are not transferred.
+_Avoid_: sync, merge, move
+
+**Ingestion**:
+The creation of immutable ledger records from structures or calculation results
+produced outside the ledger. Record provenance and tags are selected at this
+boundary and cannot be changed afterward.
+_Avoid_: import, tagging, annotation
+
+**Tag**:
+A user-defined exact, case-sensitive string. Ingestion tags are attached through
+immutable record provenance; post-ingestion tags are mutable annotations stored
+in SQLite association tables. Namespaced forms such as `project:foo` and
+`split:train` are recommended but not enforced.
+_Avoid_: label, mutable category
+
+**Effective tags**:
+The union of immutable ingestion tags and append-only post-ingestion tags. Reads,
+queries, catalog entries, selections, and exports expose effective tags without
+changing provenance or record fingerprints.
+_Avoid_: rewritten provenance tags
+
+**Minimum provenance**:
+The required `created_by` and `purpose` values on every ingested structure and
+evaluation. Immutable ingestion tags, notes, and strict JSON `metadata` provide
+optional per-record audit context. Structure-production configuration belongs to
+`StructureSourceSpec`; workflow definitions and parent lineage are outside the
+ledger's scope.
+_Avoid_: workflow specification, provenance registry
+
+**Training dataset**:
+An aggregation of selected structures for model training. Evaluations provide
+labels for those structures but are not the dataset itself.
+_Avoid_: saved query, mutable record collection
+
+**Dynamic saved query**:
+An immutable saved query whose criteria are evaluated against the ledger when
+used, so matching membership may grow as records are ingested.
+_Avoid_: live table, mutable query
+
+**Frozen saved query**:
+An immutable saved query that selects explicit record identities, fixing its
+membership without duplicating record payloads.
+_Avoid_: copied dataset, data snapshot
+
+**Saved query**:
+An optional immutable query definition with a user-supplied unique label. STOMS
+does not save ordinary queries automatically and rejects a duplicate label. It
+defines a view over structure criteria and evaluator requirements; listing saved
+queries exposes both selections. Every saved query has exactly one evaluator
+selector.
+_Avoid_: dataset, query version
+
+**Strict paired selection**:
+A request for specified structures and evaluator requirements that succeeds
+only when every requested structure has every required evaluation. Missing data
+causes an error rather than producing a partial result.
+_Avoid_: best-effort pairing, partial selection
+
+**Catalog**:
+A read-only facility for listing and searching ledger metadata and evaluation
+availability before requesting strict data selections. For every matched
+structure, it exposes available evaluator identities and property names without
+loading numerical result payloads.
+_Avoid_: data browser, mutable index
+
+**Evaluator selector**:
+A caller-defined set of exact `MethodSpec` field requirements used to select
+evaluations. The caller chooses its granularity, from one supplied field to a
+complete method specification; the ledger does not infer scientific equivalence.
+For strict selection, it must match exactly one evaluation for every selected
+structure; zero or multiple matches are errors.
+_Avoid_: evaluator equivalence, fuzzy method match
+
+**Evaluator label**:
+The human-readable evaluator name stored in `MethodSpec.name`. Version, code,
+model ID, and parameters provide structured disambiguation; tags do not define
+evaluator identity.
+_Avoid_: evaluator tag, method tag
+
+**Record retrieval**:
+The default read operation returns complete immutable structure and evaluation
+records. Callers extract numerical properties for their own analysis.
+_Avoid_: plot data, analysis result
+
+**Numerical projection**:
+An application-neutral read operation that returns aligned record identities
+and NumPy values for one selected numerical property without computing analysis
+metrics or plots. It retains the original selection query as metadata and fails
+when the selected values have different declared units.
+_Avoid_: parity data, metric result
+
+**Default units**:
+The units assigned during ingestion when a standard numerical property has no
+explicit unit. Energy defaults to `eV`, forces to `eV/angstrom`, and node energy
+to `eV`; an explicit unit overrides the corresponding default.
+_Avoid_: implicit units, assumed units
+
+**Node energy**:
+A one-dimensional optional output from MACE with one value for every graph node.
+For the current MACE inputs, its shape is `(n,)`, where `n` is the structure's
+atom count. It is not a STOMS-defined per-atom-energy concept.
+_Avoid_: per-atom energy, atomic energy
+
+**Standard evaluation properties**:
+The initial property contract comprises total `energy` as a scalar or
+one-element array, optional `forces` with shape `(n, 3)`, and optional MACE
+`node_energy` with shape `(n,)`, where `n` is the structure's atom count.
+_Avoid_: calculator state, analysis result
+
+**Export traceability**:
+The structure and evaluation identities, tags, evaluator label, and declared
+units retained with an exported extxyz frame.
+_Avoid_: training metadata, plot metadata
+
+**Default extxyz labels**:
+An extxyz training export writes total energy as `REF_energy` in `Atoms.info`
+and forces as `REF_forces` in `Atoms.arrays`. Optional `node_energy` is omitted
+unless explicitly requested; when included, it is `REF_node_energy` in
+`Atoms.arrays`. Callers may override all three labels.
+_Avoid_: ASE calculator results, implicit export mapping
+
+## Record Identity
+
+**Ledger-entry ID**:
+A target-owned identifier used to store a record in one ledger. It is local
+bookkeeping and is not part of the immutable record data.
+_Avoid_: record identity, portable ID
+
+**Record identity**:
+An opaque UUID minted when an immutable record is first created and preserved
+when that record is promoted to another ledger.
+_Avoid_: primary key, ledger-entry ID
+
+**Creation timestamp**:
+A required timezone-aware UTC timestamp recording when an immutable record was
+created. It is preserved during promotion and is not optional provenance.
+_Avoid_: optional metadata, transfer time
+
+**Record fingerprint**:
+A deterministic hash of every immutable part of a record except its
+ledger-entry ID. It verifies that a promoted record is unchanged.
+_Avoid_: content hash, primary key
+
+**Scientific content equality**:
+Equality of a record's scientific payload independent of provenance, timestamp,
+and record identity. For structures, this is represented by
+`structure_content_hash`, which covers the calculator-free ASE snapshot.
+_Avoid_: record equality, transfer equality
+
+**Structure content hash**:
+A deterministic hash of the calculator-free ASE arrays, cell, PBC, `Atoms.info`,
+and constraints stored in a structure record. It identifies scientific
+structure content independently of provenance and record identity.
+_Avoid_: structure record ID, provenance fingerprint
+
+**Structure content conflict**:
+An ingestion input whose calculator-free content matches an existing structure
+but whose immutable ingestion provenance differs. Single ingestion reports
+`StructureContentMatch` values without inserting; a conflicting batch is
+rolled back and raises `StructureContentConflictError`, unless the caller opts
+into equivalent-atoms insertion with `allow_equivalent_atoms=True`.
+_Avoid_: duplicate record, equivalent record insertion

stoms-0.2.0/LICENSE

@@ -0,0 +1,177 @@
+
+                                 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