mapkgsutils 0.0.3__tar.gz → 0.0.4__tar.gz

mapkgsutils-0.0.4/PKG-INFO

@@ -0,0 +1,114 @@
+Metadata-Version: 2.4
+Name: mapkgsutils
+Version: 0.0.4
+Summary: Utils shared by several mapping set generation tools for biomedical databases
+Keywords: snekpack,cookiecutter
+Author: Javier Millan Acosta
+Author-email: Javier Millan Acosta <javier.millanacosta@gmail.com>
+License-Expression: MIT
+License-File: LICENSE
+Classifier: Development Status :: 1 - Planning
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Framework :: Pytest
+Classifier: Framework :: Sphinx
+Classifier: Natural Language :: English
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3.10
+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: Programming Language :: Python :: 3 :: Only
+Classifier: Typing :: Typed
+Requires-Dist: more-itertools
+Requires-Dist: tqdm
+Requires-Dist: click
+Requires-Dist: more-click
+Requires-Dist: typing-extensions
+Requires-Dist: pydantic>=2.0
+Requires-Dist: pyyaml
+Requires-Dist: sssom==0.4.21
+Requires-Dist: sssom-schema==1.1.0a5
+Requires-Dist: curies>=0.7.0
+Requires-Dist: polars>=0.20.0
+Requires-Dist: polars-runtime-32
+Requires-Dist: pandas
+Requires-Dist: numpy
+Requires-Dist: httpx>=0.24.0
+Maintainer: Javier Millan Acosta
+Maintainer-email: Javier Millan Acosta <javier.millanacosta@gmail.com>
+Requires-Python: >=3.10
+Project-URL: Bug Tracker, https://github.com//mapkgsutils/issues
+Project-URL: Homepage, https://github.com//mapkgsutils
+Project-URL: Repository, https://github.com//mapkgsutils.git
+Project-URL: Documentation, https://mapkgsutils.readthedocs.io
+Project-URL: Funding, https://github.com/sponsors/jmillanacosta
+Description-Content-Type: text/markdown
+
+<!--
+<p align="center">
+  <img src="https://github.com//mapkgsutils/raw/main/docs/source/logo.png" height="150">
+</p>
+-->
+
+<h1 align="center">
+  MaPkgsUtilS
+</h1>
+
+<p align="center">
+    <a href="https://github.com//mapkgsutils/actions/workflows/tests.yml">
+        <img alt="Tests" src="https://github.com//mapkgsutils/actions/workflows/tests.yml/badge.svg" /></a>
+    <a href="https://pypi.org/project/mapkgsutils">
+        <img alt="PyPI" src="https://img.shields.io/pypi/v/mapkgsutils" /></a>
+    <a href="https://pypi.org/project/mapkgsutils">
+        <img alt="PyPI - Python Version" src="https://img.shields.io/pypi/pyversions/mapkgsutils" /></a>
+    <a href="https://github.com//mapkgsutils/blob/main/LICENSE">
+        <img alt="PyPI - License" src="https://img.shields.io/pypi/l/mapkgsutils" /></a>
+    <a href='https://mapkgsutils.readthedocs.io/en/latest/?badge=latest'>
+        <img src='https://readthedocs.org/projects/mapkgsutils/badge/?version=latest' alt='Documentation Status' /></a>
+    <a href="https://codecov.io/gh//mapkgsutils/branch/main">
+        <img src="https://codecov.io/gh//mapkgsutils/branch/main/graph/badge.svg" alt="Codecov status" /></a>  
+    <a href="https://github.com/cthoyt/cookiecutter-python-package">
+        <img alt="Cookiecutter template from @cthoyt" src="https://img.shields.io/badge/Cookiecutter-snekpack-blue" /></a>
+    <a href="https://github.com/astral-sh/ruff">
+        <img src="https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json" alt="Ruff" style="max-width:100%;"></a>
+    <a href="https://github.com//mapkgsutils/blob/main/.github/CODE_OF_CONDUCT.md">
+        <img src="https://img.shields.io/badge/Contributor%20Covenant-2.1-4baaaa.svg" alt="Contributor Covenant"/></a>
+    <!-- uncomment if you archive on zenodo
+    <a href="https://doi.org/10.5281/zenodo.XXXXXX">
+        <img src="https://zenodo.org/badge/DOI/10.5281/zenodo.XXXXXX.svg" alt="DOI"></a>
+    -->
+</p>
+
+Utils shared by several mapping set generation tools for biomedical databases.
+
+## 🚀 Installation
+
+<!-- Uncomment this section after your first ``just finish``
+The most recent release can be installed from
+[PyPI](https://pypi.org/project/mapkgsutils/) with uv:
+
+```console
+$ uv pip install mapkgsutils
+```
+
+or with pip:
+
+```console
+$ python3 -m pip install mapkgsutils
+```
+-->
+
+The most recent code and data can be installed directly from GitHub with uv:
+
+```console
+$ uv pip install git+https://github.com//mapkgsutils.git
+```
+
+or with pip:
+
+```console
+$ python3 -m pip install git+https://github.com//mapkgsutils.git
+```

mapkgsutils-0.0.4/README.md

@@ -0,0 +1,65 @@
+<!--
+<p align="center">
+  <img src="https://github.com//mapkgsutils/raw/main/docs/source/logo.png" height="150">
+</p>
+-->
+
+<h1 align="center">
+  MaPkgsUtilS
+</h1>
+
+<p align="center">
+    <a href="https://github.com//mapkgsutils/actions/workflows/tests.yml">
+        <img alt="Tests" src="https://github.com//mapkgsutils/actions/workflows/tests.yml/badge.svg" /></a>
+    <a href="https://pypi.org/project/mapkgsutils">
+        <img alt="PyPI" src="https://img.shields.io/pypi/v/mapkgsutils" /></a>
+    <a href="https://pypi.org/project/mapkgsutils">
+        <img alt="PyPI - Python Version" src="https://img.shields.io/pypi/pyversions/mapkgsutils" /></a>
+    <a href="https://github.com//mapkgsutils/blob/main/LICENSE">
+        <img alt="PyPI - License" src="https://img.shields.io/pypi/l/mapkgsutils" /></a>
+    <a href='https://mapkgsutils.readthedocs.io/en/latest/?badge=latest'>
+        <img src='https://readthedocs.org/projects/mapkgsutils/badge/?version=latest' alt='Documentation Status' /></a>
+    <a href="https://codecov.io/gh//mapkgsutils/branch/main">
+        <img src="https://codecov.io/gh//mapkgsutils/branch/main/graph/badge.svg" alt="Codecov status" /></a>  
+    <a href="https://github.com/cthoyt/cookiecutter-python-package">
+        <img alt="Cookiecutter template from @cthoyt" src="https://img.shields.io/badge/Cookiecutter-snekpack-blue" /></a>
+    <a href="https://github.com/astral-sh/ruff">
+        <img src="https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json" alt="Ruff" style="max-width:100%;"></a>
+    <a href="https://github.com//mapkgsutils/blob/main/.github/CODE_OF_CONDUCT.md">
+        <img src="https://img.shields.io/badge/Contributor%20Covenant-2.1-4baaaa.svg" alt="Contributor Covenant"/></a>
+    <!-- uncomment if you archive on zenodo
+    <a href="https://doi.org/10.5281/zenodo.XXXXXX">
+        <img src="https://zenodo.org/badge/DOI/10.5281/zenodo.XXXXXX.svg" alt="DOI"></a>
+    -->
+</p>
+
+Utils shared by several mapping set generation tools for biomedical databases.
+
+## 🚀 Installation
+
+<!-- Uncomment this section after your first ``just finish``
+The most recent release can be installed from
+[PyPI](https://pypi.org/project/mapkgsutils/) with uv:
+
+```console
+$ uv pip install mapkgsutils
+```
+
+or with pip:
+
+```console
+$ python3 -m pip install mapkgsutils
+```
+-->
+
+The most recent code and data can be installed directly from GitHub with uv:
+
+```console
+$ uv pip install git+https://github.com//mapkgsutils.git
+```
+
+or with pip:
+
+```console
+$ python3 -m pip install git+https://github.com//mapkgsutils.git
+```

{mapkgsutils-0.0.3 → mapkgsutils-0.0.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "uv_build"
 
 [project]
 name = "mapkgsutils"
-version = "0.0.3"
+version = "0.0.4"
 description = "Utils shared by several mapping set generation tools for biomedical databases"
 readme = "README.md"
 authors = [
@@ -236,7 +236,7 @@ known-first-party = [
 docstring-code-format = true
 
 [tool.bumpversion]
-current_version = "0.0.3"
+current_version = "0.0.4"
 parse = "(?P<major>\\d+)\\.(?P<minor>\\d+)\\.(?P<patch>\\d+)(?:-(?P<release>[0-9A-Za-z-]+(?:\\.[0-9A-Za-z-]+)*))?(?:\\+(?P<build>[0-9A-Za-z-]+(?:\\.[0-9A-Za-z-]+)*))?"
 serialize = [
     "{major}.{minor}.{patch}-{release}+{build}",

{mapkgsutils-0.0.3 → mapkgsutils-0.0.4}/src/mapkgsutils/config/schema.py

@@ -65,11 +65,11 @@ class DistributionEraSchema(BaseModel):
 class DatasourceConfigSchema(BaseModel):
     """Top-level schema for a ``config/<datasource>.yaml`` file.
 
-    ``name``, ``prefix``, and ``curie_base_url`` are required -- they are the
-    only fields :class:`~mapkgsutils.parsers.base.DatasourceConfig` declares
-    without a default. Every other recognized key is optional and permissive
-    in shape; unrecognized top-level keys are not an error here (see
-    :func:`validate_config_dict`), only a warning.
+    ``name``, ``prefix``, and ``curie_base_url`` are the only fields
+    :class:`~mapkgsutils.parsers.base.DatasourceConfig` declares without a
+    default, so they're required here too. Every other recognized key is
+    optional and permissive in shape. Unrecognized top-level keys just get a
+    warning (see :func:`validate_config_dict`), not a hard error.
     """
 
     model_config = ConfigDict(extra="allow")
@@ -99,7 +99,6 @@ class DatasourceConfigSchema(BaseModel):
     distribution_eras: list[DistributionEraSchema] = Field(default_factory=list)
     xref_sources: list[XrefSourceSchema] = Field(default_factory=list)
     species: dict[str, Any] = Field(default_factory=dict)
-    genome_build: dict[str, Any] = Field(default_factory=dict)
     subset: dict[str, Any] = Field(default_factory=dict)
     mappingset: dict[str, Any] = Field(default_factory=dict)
     mapping: dict[str, Any] = Field(default_factory=dict)

{mapkgsutils-0.0.3 → mapkgsutils-0.0.4}/src/mapkgsutils/consolidate.py

@@ -1,15 +1,12 @@
 """Generic mapping-date consolidation: cache I/O and the release/date walk skeleton.
 
-A versioned datasource's per-row deprecation/change date isn't always
-recorded anywhere in a single release -- recovering it means walking every
-historical release once and recording the first/last release each mapping
-(keyed by its version-independent pair hash) was seen in. This module is the
-datasource-agnostic half of that: cache I/O, the release-walk and
-single-pass-date loop shapes, and materializing the cache back into a real
-SSSOM mapping set. Per-datasource dispatch (which versions exist, how to
-download/parse one, which mapping-set class to build) is supplied by the
-caller as plain callables/values -- see :mod:`pysec2pri.consolidate` for a
-concrete binding.
+A versioned datasource doesn't always record when a mapping first appeared.
+Recovering that date means walking every historical release once and
+recording the first/last release each mapping (keyed by its
+version-independent pair hash) was seen in.
+
+This module provides the cache I/O, the release-walk and single-pass-date
+loop shapes, and rebuilding the cache back into a real SSSOM mapping set.
 """
 
 from __future__ import annotations
@@ -44,9 +41,9 @@ CACHE_COLUMNS = (
     "last_seen_version",
     "last_seen_date",
     # JSON-encoded snapshot of the mapping's own fields (subject_id,
-    # object_id, predicate_id, ...) as last seen -- used to materialize the
-    # consolidated index as a real SSSOM mapping set (see
-    # build_consolidated_mapping_set). Empty for legacy/hand-built rows.
+    # object_id, predicate_id, ...) as last seen. Used to rebuild the cache
+    # into a real SSSOM mapping set later (see build_consolidated_mapping_set).
+    # Empty for legacy/hand-built rows.
     "fields_json",
 )
 
@@ -129,12 +126,12 @@ def _mapping_fields_json(m: Any) -> str:
     """JSON-encode a mapping's own fields (excluding mapping_date/record_id).
 
     Snapshots a mapping's current shape (subject_id, object_id,
-    predicate_id, ...) so the consolidated index can later be materialized
-    as a real SSSOM mapping set (see :func:`build_consolidated_mapping_set`).
-    ``default=str`` handles enum-valued fields like ``mapping_cardinality``,
-    which round-trip cleanly back through ``Mapping(**fields)``. Returns
-    ``"{}"`` for non-dataclass stand-ins (e.g. test doubles) that don't carry
-    a full field set -- callers skip materializing those rows.
+    predicate_id, ...) so :func:`build_consolidated_mapping_set` can rebuild
+    it into a real SSSOM mapping set later. ``default=str`` handles
+    enum-valued fields like ``mapping_cardinality``, which round-trip
+    cleanly back through ``Mapping(**fields)``. Returns ``"{}"`` for
+    non-dataclass stand-ins (e.g. test doubles); callers skip those rows
+    rather than materializing them.
     """
     from dataclasses import fields as dataclass_fields
     from dataclasses import is_dataclass
@@ -203,15 +200,18 @@ def build_consolidated_mapping_set(
     mapping_set_class: type[Any],
     record_namespace: str,
     mapping_set_metadata: Mapping[str, Any],
+    cardinality_on: str = "id",
 ) -> Any:
     """Materialize the consolidated index as a real SSSOM mapping set.
 
-    Each record's stored field snapshot (from the most recent release where
-    it was seen) is rebuilt into a ``Mapping``, with ``mapping_date``
-    overridden to its ``first_seen_date`` -- the date of appearance, rather
-    than whatever date the snapshot's own release happened to carry -- and
-    ``record_id`` re-scoped with a trailing ``consolidate`` segment, marking
-    the IRI as a derived, cross-release product.
+    Each row's ``mapping_date`` and ``subject_source_version``/
+    ``object_source_version`` are overridden from the record's
+    ``first_seen_date``/``first_seen_version``: the date of first
+    appearance and the release it first appeared in, rather than whatever
+    the last-seen snapshot happened to carry. The two stay in their own
+    fields. A release version (e.g. ChEBI's "183") is not a date and never
+    goes in ``mapping_date``, and a real date never goes in the version
+    fields.
 
     Args:
         records: ``record_id -> fields`` dict as read by :func:`read_cache`.
@@ -221,6 +221,8 @@ def build_consolidated_mapping_set(
             ``record_id``.
         mapping_set_metadata: ``mapping_set_id``/``curie_map``/``license``/...
             metadata for the resulting mapping set.
+        cardinality_on: ``"id"`` or ``"label"``, forwarded to
+            :meth:`~mapkgsutils.parsers.base.BaseMappingSet._compute_cardinalities`.
 
     Returns:
         A ``mapping_set_class`` instance with cardinalities computed.
@@ -243,7 +245,15 @@ def build_consolidated_mapping_set(
             # nothing to materialize into a real Mapping; date bookkeeping
             # for them still lives in the TSV cache, just not in the SSSOM.
             continue
+        # mapping_date and subject/object_source_version are semantically
+        # distinct SSSOM fields: a release version (e.g. ChEBI's "183") is
+        # never a date, and must never end up in mapping_date or vice versa.
+        # Override both from first_seen_*, not whatever the snapshot's own
+        # (last-seen) values were.
         row_fields["mapping_date"] = fields.get("first_seen_date") or None
+        first_seen_version = fields.get("first_seen_version") or None
+        row_fields["subject_source_version"] = first_seen_version
+        row_fields["object_source_version"] = first_seen_version
         row_fields["record_id"] = f"{record_namespace}{version_label}/consolidate/{pair_key}"
         mappings.append(SSSOMMapping(**row_fields))
 
@@ -257,7 +267,7 @@ def build_consolidated_mapping_set(
         mapping_set_description=mapping_set_metadata.get("mapping_set_description"),
         license=mapping_set_metadata.get("license"),
     )
-    mapping_set.compute_cardinalities()
+    mapping_set._compute_cardinalities(on=cardinality_on)
     return mapping_set
 
 
@@ -268,6 +278,7 @@ def write_consolidated_sssom(
     mapping_set_class: type[Any],
     record_namespace: str,
     mapping_set_metadata: Mapping[str, Any],
+    cardinality_on: str = "id",
 ) -> Path:
     """Build and save the companion SSSOM mapping set next to the cache file.
 
@@ -278,6 +289,8 @@ def write_consolidated_sssom(
         record_namespace: Base IRI namespace for rebuilt ``record_id`` values.
         mapping_set_metadata: ``mapping_set_id``/``curie_map``/``license``/...
             metadata for the resulting mapping set.
+        cardinality_on: ``"id"`` or ``"label"``, see
+            :func:`build_consolidated_mapping_set`.
 
     Returns:
         Path to the written SSSOM TSV (see :func:`sssom_output_path`).
@@ -290,6 +303,7 @@ def write_consolidated_sssom(
         mapping_set_class=mapping_set_class,
         record_namespace=record_namespace,
         mapping_set_metadata=mapping_set_metadata,
+        cardinality_on=cardinality_on,
     )
     output_path = sssom_output_path(cache_path)
     mapping_set.save("sssom", output_path)
@@ -341,9 +355,9 @@ def consolidate_by_release(
         try:
             mapping_set = run_one_version(v)
             release_date = resolve_release_date(v)
-            # Empty (not the version label v) when no real release date is
-            # resolvable -- v is a version, not a date, and isn't always
-            # date-shaped (e.g. ChEBI's plain release numbers).
+            # Empty when no real release date resolves. v is a version, not
+            # a date, and isn't always date-shaped (e.g. ChEBI's plain
+            # release numbers), so don't store it as one.
             date_str = release_date.date().isoformat() if release_date else ""
 
             for m in mapping_set.mappings or []:

{mapkgsutils-0.0.3 → mapkgsutils-0.0.4}/src/mapkgsutils/context.py

@@ -1,18 +1,13 @@
-"""Disambiguate ambiguous secondary with context: label, id, and xref evidence.
+"""Disambiguate ambiguous mappings with context: label, id, and xref evidence.
 
 :class:`ContextSpec` describes a per-row piece of evidence that can
 be used to decide which of those two entities a given ambiguous cell actually
 means:
 
-* ``label``: an alias/synonym string.
+* ``label``: a label string.
 * ``id``    : a related/foreign identifier string.
 * ``xref``  : a cross-reference token (e.g. an Ensembl ID) resolved through
   an independent :class:`XrefMapping` crosswalk table.
-
-All three are resolved the same way: confirm *secondary usage* (the evidence
-points to the mapping's target), confirm *primary usage* (the evidence points
-to the token's own current identity), or leave the cell unresolved. Every
-attempt can be recorded as a :class:`DecisionRecord` for an auditable TSV log.
 """
 
 from __future__ import annotations
@@ -35,8 +30,8 @@ class XrefRecord:
 
     Args:
         subject_id: The cross-reference token, e.g. ``"ENSG00000197471"``.
-        object_id: The target primary id, e.g. ``"HGNC:11249"``.
-        object_label: The target primary label, e.g. ``"SPN"``.
+        object_id: The target id, e.g. ``"HGNC:11249"``.
+        object_label: The target label, e.g. ``"SPN"``.
         predicate_id: The equivalence predicate, e.g. ``"skos:exactMatch"``.
             ``None`` when the source table carries no predicate column.
     """
@@ -93,8 +88,8 @@ def load_xref_mapping(
     Args:
         path: Path to the crosswalk file.
         subject_col: Column with the cross-reference token.
-        object_col: Column with the target primary id.
-        object_label_col: Column with the target primary label (optional).
+        object_col: Column with the target id.
+        object_label_col: Column with the target label (optional).
         predicate_col: Column with the equivalence predicate (optional).
         sep: Field delimiter.
 
@@ -257,13 +252,12 @@ def resolve_ambiguous_with_xref(
     """Attempt to resolve an ambiguous token using a cross-reference token.
 
     Args:
-        token: The ambiguous label or ID (appears both as a current primary
-            entry and as a secondary one pointing elsewhere).
+        token: The ambiguous label or ID.
         xref_token: The row's cross-reference token, e.g. an Ensembl ID.
-        lkp: ``{secondary_token: resolved_token}`` lookup.
+        lkp: ``{token: resolved_token}`` lookup.
         xref_index: ``{xref_token: [XrefRecord, ...]}`` (see
             :meth:`XrefMapping.by_subject`).
-        token_to_id: ``{primary_token: primary_id}``. ``None`` when *token*
+        token_to_id: ``{token: id}``. ``None`` when *token*
             is already a CURIE (ID mode).
         accepted_predicates: Equivalence predicates to accept. ``None``
             accepts any predicate.

{mapkgsutils-0.0.3 → mapkgsutils-0.0.4}/src/mapkgsutils/parsers/base.py

@@ -48,7 +48,7 @@ class DistributionEra:
     format: str | None = None
     from_version: str | None = None
     to_version: str | None = None
-    wayback: bool = False  # declarative only for now -- no resolver yet
+    wayback: bool = False  # declarative only for now, no resolver yet
 
 
 @dataclass
@@ -124,8 +124,6 @@ class DatasourceConfig:
     xref_sources: list[XrefSource] = field(default_factory=list)
     # Species this datasource publishes
     species: dict[str, Any] = field(default_factory=dict)
-    # Genome assembly/build metadata.
-    genome_build: dict[str, Any] = field(default_factory=dict)
     # Compound/entry subset this datasource publishes (e.g. ChEBI's
     # 3star/complete). Generic, config-driven counterpart to `species`.
     subset: dict[str, Any] = field(default_factory=dict)
@@ -299,7 +297,6 @@ def get_datasource_config(datasource_name: str, *, config_package: str) -> Datas
         distribution_eras=eras,
         xref_sources=xref_sources,
         species=raw.get("species") or {},
-        genome_build=raw.get("genome_build") or {},
         subset=raw.get("subset") or {},
         mappingset_metadata=raw.get("mappingset", {}),
         mapping_metadata=raw.get("mapping", {}),
@@ -507,16 +504,16 @@ def pair_hash(pri: str, sec: str) -> str:
     """Version-independent 16-hex-char digest for a (pri, sec) pair.
 
     The same pair always hashes identically, regardless of release/version
-    or product (species/subset). This is the join key a cross-release
-    consolidation layer uses to match a mapping across releases (to discover
-    when it first/last appeared) -- *not* what ends up in the ``record_id``
-    field (see :func:`mint_record_id`).
+    or product (species/subset). A cross-release consolidation layer uses
+    this as the join key to match a mapping across releases and discover
+    when it first/last appeared. It is not what ends up in the
+    ``record_id`` field; see :func:`mint_record_id` for that.
     """
     return hashlib.sha256(f"{pri}|{sec}".encode()).hexdigest()[:16]
 
 
 def mint_record_id(pri: str, sec: str, *, namespace: str) -> str:
-    """Mint a row's ``record_id`` -- the row's OWL Axiom IRI in SSSOM's RDF/OWL output.
+    """Mint a row's ``record_id``, the row's OWL Axiom IRI in SSSOM's RDF/OWL output.
 
     Scoped to *namespace* (typically a release- and product-specific prefix,
     see :meth:`BaseParser._record_namespace`), so the same (pri, sec) pair
@@ -528,7 +525,7 @@ def mint_record_id(pri: str, sec: str, *, namespace: str) -> str:
     confidence, ...) under the same IRI.
 
     The trailing 16 hex characters are always :func:`pair_hash`'s
-    version-independent digest -- use that function directly (not this one)
+    version-independent digest. Use that function directly, not this one,
     for cross-release matching/lookups.
     """
     return f"{namespace}{pair_hash(pri, sec)}"
@@ -1278,12 +1275,6 @@ class BaseParser(ABC):
         """
         self.version = version
         self.show_progress = show_progress
-        # Genome assembly/build for the SSSOM ``*_source_version`` fields.
-        # Default ``None`` -> resolved from config per species, or left to
-        # fall back to ``self.version``. Parsers that read a build straight
-        # from the data (e.g. an Ensembl-style ``mapping_session``) may set
-        # this, or override per mapping row.
-        self.genome_build: str | None = None
         # Release date of the source data, used for the SSSOM ``mapping_date``.
         # Set by the download layer to the upstream release date; falls back
         # to the version when that is an ISO date (e.g. quarterly
@@ -1370,7 +1361,7 @@ class BaseParser(ABC):
 
         ``None`` for most parsers (one release == one product). Override
         when a parser option selects a genuinely different dataset rather
-        than just a different output mode -- e.g. a species selector for a
+        than just a different output mode, e.g. a species selector for a
         multi-species datasource, where the same release number produces a
         disjoint set of mappings per species. Folded into ``mapping_set_id``
         and :meth:`_record_namespace` so two runs that differ only in this
@@ -1384,8 +1375,8 @@ class BaseParser(ABC):
         Mirrors ``mapping_set_id``'s ``{base}/{version}/{slug}`` ordering
         (see :meth:`create_mapping_set`) so a mapping's ``record_id`` is
         scoped to the same release/product as the mapping *set* it's
-        asserted in -- use this (instead of reading
-        ``mapping_metadata()["record_id"]`` directly) when building
+        asserted in. Use this, instead of reading
+        ``mapping_metadata()["record_id"]`` directly, when building
         per-row ``record_id`` values.
         """
         base = str(self.get_mapping_metadata().get("record_id") or "")
@@ -1717,74 +1708,13 @@ class BaseParser(ABC):
             return str(self.version)
         return date.today().isoformat()
 
-    def _species_build(self) -> str | None:
-        """Return the configured genome build for this run's species, if any.
-
-        Reads ``species.available[<species>].build`` from config.
-        ``self.species`` may be a canonical taxon ID (single-species runs)
-        or a datasource token (all-species runs), so both the ``available``
-        key and each entry's ``token`` are matched.
-
-        Returns:
-            The per-species build string, or ``None`` when not configured.
-        """
-        cfg = self._config
-        species = getattr(self, "species", None)
-        if not cfg or species is None:
-            return None
-        available = (cfg.species or {}).get("available") or {}
-        entry = available.get(species) or available.get(str(species))
-        if entry is None:
-            for value in available.values():
-                if isinstance(value, dict) and str(value.get("token")) == str(species):
-                    entry = value
-                    break
-        if isinstance(entry, dict) and entry.get("build"):
-            return str(entry["build"])
-        return None
-
-    def _genome_build(self) -> str | None:
-        """Resolve the genome assembly/build for the source-version fields.
-
-        The mapping set's release is already explicit in
-        ``mapping_set_version`` / ``mapping_set_id``, so
-        ``subject_source_version`` / ``object_source_version`` carry the
-        genome build (e.g. ``"GRCh38"``) rather than repeating the release.
-        Resolution order:
-
-        1. an explicit :attr:`genome_build` override (e.g. a build a parser
-           discovered straight from the data);
-        2. the per-species build from ``species.available[<species>].build``;
-        3. the datasource-wide ``genome_build.default`` -- but *only* for
-           single-build datasources (those with no ``species.available`` map,
-           e.g. a human-only datasource). A multi-species datasource never
-           falls through to ``default``, so it can't stamp one build (say
-           GRCh38) onto a non-human species; an uncurated species is left to
-           fall back to the release instead.
-
-        Returns:
-            The resolved build, or ``None`` when none is configured (e.g.
-            ChEBI), so callers fall back to :attr:`version`.
-        """
-        if self.genome_build:
-            return self.genome_build
-        species_build = self._species_build()
-        if species_build:
-            return species_build
-        cfg = self._config
-        if not cfg or (cfg.species or {}).get("available"):
-            return None
-        default = (cfg.genome_build or {}).get("default")
-        return str(default) if default else None
-
     def _source_version(self) -> str | None:
         """Return the value for the set-level SSSOM ``*_source_version`` fields.
 
-        The genome build when one is resolvable (see :meth:`_genome_build`),
-        otherwise the release :attr:`version` (unchanged behaviour for
-        datasources without a genome build, e.g. ChEBI).
+        Always the analyzed release, :attr:`version`. The same field means
+        the same thing across every datasource's mapping set.
         """
-        return self._genome_build() or self.version
+        return self.version
 
     def create_mapping_set(
         self,

{mapkgsutils-0.0.3 → mapkgsutils-0.0.4}/src/mapkgsutils/version.py

@@ -12,7 +12,7 @@ __all__ = [
     "get_version",
 ]
 
-VERSION = "0.0.3"
+VERSION = "0.0.4"
 
 
 def get_git_hash() -> str: