pymetadata 0.6.2__tar.gz → 0.6.4__tar.gz

{pymetadata-0.6.2 → pymetadata-0.6.4}/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.6.2"
+current_version = "0.6.4"
 commit = true
 parse = "(?P<major>\\d+)\\.(?P<minor>\\d+)\\.(?P<patch>\\d+)"
 serialize = ["{major}.{minor}.{patch}"]

{pymetadata-0.6.2 → pymetadata-0.6.4}/.github/workflows/ci-cd.yml

@@ -26,7 +26,7 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest, windows-latest, macos-latest]
-        python-version: ["3.11", "3.12", "3.13", "3.14"]
+        python-version: ["3.11", "3.12", "3.13", "3.14", "3.15"]
         # linux covers the full range, windows and macos only the newest version
         exclude:
           - os: windows-latest
@@ -35,12 +35,16 @@ jobs:
             python-version: "3.12"
           - os: windows-latest
             python-version: "3.13"
+          - os: windows-latest
+            python-version: "3.14"
           - os: macos-latest
             python-version: "3.11"
           - os: macos-latest
             python-version: "3.12"
           - os: macos-latest
             python-version: "3.13"
+          - os: macos-latest
+            python-version: "3.14"
 
     steps:
     - uses: actions/checkout@v7
@@ -48,7 +52,7 @@ jobs:
         persist-credentials: false
     - name: Install uv and set the python version
       # astral-sh/setup-uv publishes no floating major tag beyond v7
-      uses: astral-sh/setup-uv@v10.0.1
+      uses: astral-sh/setup-uv@v10.1.0
       with:
         python-version: ${{ matrix.python-version }}
         enable-cache: true
@@ -88,7 +92,7 @@ jobs:
       with:
         persist-credentials: false
     - name: Install uv
-      uses: astral-sh/setup-uv@v10.0.1
+      uses: astral-sh/setup-uv@v10.1.0
       with:
         python-version: "3.14"
         enable-cache: true

{pymetadata-0.6.2 → pymetadata-0.6.4}/.github/workflows/docs.yml

@@ -29,7 +29,7 @@ jobs:
       - name: Configure GitHub Pages
         uses: actions/configure-pages@v6
       - name: Install uv and set the python version
-        uses: astral-sh/setup-uv@v10.0.1
+        uses: astral-sh/setup-uv@v10.1.0
         with:
           python-version: "3.14"
           enable-cache: true

{pymetadata-0.6.2 → pymetadata-0.6.4}/.github/workflows/ty.yml

@@ -26,7 +26,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Install uv and set the python version
-        uses: astral-sh/setup-uv@v10.0.1
+        uses: astral-sh/setup-uv@v10.1.0
         with:
           python-version: "3.14"
           enable-cache: true

{pymetadata-0.6.2 → pymetadata-0.6.4}/CITATION.cff

@@ -8,7 +8,7 @@ authors:
     given-names: "Matthias"
     orcid: "https://orcid.org/0000-0003-1725-179X"
     affiliation: "Humboldt-University Berlin, Faculty of Life Science, Institute for Biology, Biology, Berlin; University Lübeck; University Hospital Schleswig-Holstein, Campus Lübeck, First Department of Medicine, Germany"
-version: "0.6.2"
+version: "0.6.4"
 date-released: "2026-09-07"
 doi: "10.5281/zenodo.5308801"
 license: MIT

{pymetadata-0.6.2 → pymetadata-0.6.4}/CLAUDE.md

@@ -22,7 +22,7 @@ uv run pre-commit install
 pytest                          # all tests
 pytest tests/test_omex.py       # single file
 pytest tests/test_omex.py::test_entry_from_dict   # single test
-tox r -e py3.14                 # single tox env (py3.11-3.14 available)
+tox r -e py3.15                 # single tox env (py3.11-3.15 available)
 tox run-parallel                # full matrix + ty
 
 # lint / format / types

{pymetadata-0.6.2 → pymetadata-0.6.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: pymetadata
-Version: 0.6.2
+Version: 0.6.4
 Summary: pymetadata are python utilities for working with metadata.
 Project-URL: Homepage, https://matthiaskoenig.github.io/pymetadata
 Project-URL: Documentation, https://matthiaskoenig.github.io/pymetadata
@@ -20,6 +20,7 @@ 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 :: 3.15
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Topic :: Scientific/Engineering
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
@@ -37,7 +38,7 @@ Requires-Dist: pytest>=9.1.1; extra == 'dev'
 Requires-Dist: ruff>=0.16.6; extra == 'dev'
 Requires-Dist: tox>=4.61.2; extra == 'dev'
 Requires-Dist: ty>=0.0.78; extra == 'dev'
-Requires-Dist: zensical>=0.0.59; extra == 'dev'
+Requires-Dist: zensical>=0.0.60; extra == 'dev'
 Provides-Extra: ontology
 Requires-Dist: pronto>=2.7.3; extra == 'ontology'
 Description-Content-Type: text/markdown

{pymetadata-0.6.2 → pymetadata-0.6.4}/docs/annotations.md

@@ -51,6 +51,14 @@ RDFAnnotation(qualifier=BQB.IS, resource="https://en.wikipedia.org/wiki/Cytosol"
 
 `resource_normalized` returns `https://identifiers.org/<prefix>:<accession>`. For namespaces which embed their prefix in the identifier (GO, CHEBI, SBO, BTO) the prefix is already part of the term and is not added a second time.
 
+The normalization never changes what a resource says: `resource_normalized` is a URL, and parsing it again gives the same `collection` and `term`. A collection which is not in the identifiers.org registry, or a term which does not carry the prefix of its collection, cannot be written as a compact identifier and is returned as `https://identifiers.org/<collection>/<term>`:
+
+```python
+annotation = RDFAnnotation(qualifier=BQB.IS, resource="urn:miriam:sabiork:1406")
+print(annotation.resource_normalized)
+# https://identifiers.org/sabiork/1406
+```
+
 ## Validation
 
 Validation answers two questions: is the qualifier a real MIRIAM qualifier, and does the term match the pattern the identifiers.org registry defines for its collection?

{pymetadata-0.6.2 → pymetadata-0.6.4}/docs/development.md

@@ -27,7 +27,7 @@ A pull request can only be merged once the four required checks are green:
 
 | check   | workflow      | content                                                              |
 | ------- | ------------- | -------------------------------------------------------------------- |
-| `tests` | `ci-cd.yml`   | the test matrix, linux, macos and windows with python 3.11 to 3.14    |
+| `tests` | `ci-cd.yml`   | the test matrix, linux, macos and windows with python 3.11 to 3.15    |
 | `ruff`  | `ruff.yml`    | `ruff check` and `ruff format --check`                                |
 | `ty`    | `ty.yml`      | `tox r -e ty`                                                         |
 | `docs`  | `docs.yml`    | the zensical build including the api reference and the agent files    |
@@ -118,16 +118,16 @@ From now on every commit is checked with ruff (lint and format) and ty, i.e., th
 
 The tests are written with pytest, tox runs them against every supported python version.
 
-The tox environments are named after the interpreter (`py3.11` to `py3.14`, see `envlist` in `tox.ini`), a single one is run with
+The tox environments are named after the interpreter (`py3.11` to `py3.15`, see `envlist` in `tox.ini`), a single one is run with
 ```bash
-tox r -e py3.14
+tox r -e py3.15
 ```
 and the complete matrix, including the `ty` environment, in parallel with
 ```bash
 tox run-parallel
 ```
 
-This needs the interpreters to be available, which uv installs with `uv python install 3.11 3.12 3.13 3.14`. Continuous integration runs the same environments as `uvx --with tox-uv tox -e py3.14`.
+This needs the interpreters to be available, which uv installs with `uv python install 3.11 3.12 3.13 3.14 3.15`. Continuous integration runs the same environments as `uvx --with tox-uv tox -e py3.15`.
 
 To run the tests directly against the development environment use
 

{pymetadata-0.6.2 → pymetadata-0.6.4}/docs/installation.md

@@ -1,6 +1,6 @@
 # Installation
 
-`pymetadata` requires python >= 3.11 and is available from [pypi](https://pypi.python.org/pypi/pymetadata). It is pure python without compiled dependencies, so the installation is the same on Linux, macOS and Windows.
+`pymetadata` requires python >= 3.11 and is available from [pypi](https://pypi.python.org/pypi/pymetadata). It is pure python and tested with python 3.11 to 3.15 on Linux, macOS and Windows. The only compiled dependency is `pydantic-core`, which comes with [pydantic](https://docs.pydantic.dev/) and is installed from a wheel; for python 3.15 these wheels are part of pydantic 2.14, with an older pydantic it is built from source, which requires a Rust toolchain.
 
 ## With uv
 

{pymetadata-0.6.2 → pymetadata-0.6.4}/pyproject.toml

@@ -24,6 +24,7 @@ classifiers = [
 	"Programming Language :: Python :: 3.12",
     "Programming Language :: Python :: 3.13",
     "Programming Language :: Python :: 3.14",
+    "Programming Language :: Python :: 3.15",
 	"Programming Language :: Python :: Implementation :: CPython",
 	"Topic :: Scientific/Engineering",
 	"Topic :: Scientific/Engineering :: Bio-Informatics",
@@ -57,7 +58,7 @@ dev = [
     "tox>=4.61.2",
     "pytest>=9.1.1",
     "pytest-cov>=7.1.0",
-    "zensical>=0.0.59",
+    "zensical>=0.0.60",
     "mkdocstrings-python>=2.0.8",
 ]
 

pymetadata-0.6.4/release-notes/0.6.3.md

@@ -0,0 +1,16 @@
+# Release notes for pymetadata 0.6.3
+![pymetadata](./docs/images/favicon/pymetadata-100x100-300dpi.png)
+
+We are pleased to release the next version of pymetadata including the
+following changes:
+
+## Features
+- support for python 3.15, which is part of the test matrix and the tox environments
+
+## Fixes
+- `UnichemQuery` works with the current UniChem web service again, which changed the fields of a source (`lastChecked` and `srcLastUpdated` are new, `lastUpdated`, `srcReleaseDate` and `srcReleaseNumber` were removed). Only `sourceID` and `name` of a `UnichemSource` are required now and `UnichemSource.from_dict` ignores unknown fields, so such a change, or a cache written by an older version, no longer breaks the queries
+
+## Development
+- the development environment requires zensical 0.0.60, the version the documentation is built with
+
+Your pymetadata team

pymetadata-0.6.4/release-notes/0.6.4.md

@@ -0,0 +1,13 @@
+# Release notes for pymetadata 0.6.4
+![pymetadata](./docs/images/favicon/pymetadata-100x100-300dpi.png)
+
+We are pleased to release the next version of pymetadata including the
+following changes:
+
+## Fixes
+- `Omex.from_directory`, and with it `Omex.from_omex` and `Omex.from_url`, add the entries in the order of the manifest, followed by the files which the manifest does not list, sorted by their location. The entries were added in the order of `os.walk`, which is the order of the file system, so `manifest.entries` and `entries_by_format` of the same archive differed between machines
+- `RDFAnnotation.resource_normalized` keeps the collection and the term of every resource: the result is a URL, and parsing it again gives the same `collection` and `term`. A collection which is not in the identifiers.org registry (`http://identifiers.org/sabiork/1406`, `urn:miriam:foo:bar`) was reduced to the bare term, and a term which does not match the pattern of its collection (`http://identifiers.org/chebi/000000035`) lost its collection. Both are now returned as `https://identifiers.org/<collection>/<term>`, and the compact identifier of a prefix which is not in the registry stays the URL `https://identifiers.org/CMO:0000012` (#81)
+- identifiers.org URLs of a prefix with a hyphen or an underscore, like `ec-code`, `pdb-ccd` or `go_ref`, are parsed into collection and term instead of being kept as an arbitrary URL (#81)
+- the collection of a MIRIAM URN and of the `collection/term` notation is lowercased, as it already was for URLs, so `TAXONOMY/9606` is the collection `taxonomy` (#81)
+
+Your pymetadata team

{pymetadata-0.6.2 → pymetadata-0.6.4}/src/pymetadata/__init__.py

@@ -7,7 +7,7 @@ from pathlib import Path
 logging.getLogger(__name__).addHandler(logging.NullHandler())
 
 __author__ = "Matthias Koenig"
-__version__ = "0.6.2"
+__version__ = "0.6.4"
 
 
 program_name: str = "pymetadata"

{pymetadata-0.6.2 → pymetadata-0.6.4}/src/pymetadata/core/annotation.py

@@ -48,11 +48,13 @@ def get_ols_query() -> OLSQuery:
 
 
 IDENTIFIERS_ORG_PREFIX: Final = "https://identifiers.org"
+# prefixes of the registry consist of letters, digits, `.`, `_` and `-`,
+# e.g., `ec-code` or `go_ref`
 IDENTIFIERS_ORG_PATTERN_COMPACT: Final = re.compile(
-    r"^https?://identifiers.org/([a-zA-Z0-9.]+):(.+)"
+    r"^https?://identifiers.org/([a-zA-Z0-9._-]+):(.+)"
 )
 IDENTIFIERS_ORG_PATTERN_CLASSIC: Final = re.compile(
-    r"^https?://identifiers.org/([a-zA-Z0-9.]+)/(.+)"
+    r"^https?://identifiers.org/([a-zA-Z0-9._-]+)/(.+)"
 )
 
 BIOREGISTRY_PREFIX: Final = "https://bioregistry.io"
@@ -167,21 +169,15 @@ class RDFAnnotation:
             match3 = MIRIAM_URN_PATTERN.match(resource)
             if match3:
                 tokens = match3.group(1).split(":")
-                self.collection = tokens[0]
+                self.collection = tokens[0].lower()
                 self.term = ":".join(tokens[1:]).replace("%3A", ":")
                 self.provider = ProviderType.IDENTIFIERS_ORG
 
-                logger.warning(
-                    "Deprecated urn pattern `%s` updated: %s",
-                    resource,
-                    self.resource_normalized,
-                )
-
         else:
             # handle short notation
             tokens = resource.split("/")
             if len(tokens) > 1:
-                self.collection = tokens[0]
+                self.collection = tokens[0].lower()
                 self.term = "/".join(tokens[1:])
                 self.provider = ProviderType.IDENTIFIERS_ORG
             elif len(tokens) == 1 and ":" in tokens[0]:
@@ -209,6 +205,13 @@ class RDFAnnotation:
         if self.collection in self.replaced_collections:
             self.collection = self.replaced_collections[self.collection]
 
+        if resource.startswith("urn:miriam:"):
+            logger.warning(
+                "Deprecated urn pattern `%s` updated: %s",
+                resource,
+                self.resource_normalized,
+            )
+
         if validate:
             self.validate()
 
@@ -244,21 +247,33 @@ class RDFAnnotation:
         `https://identifiers.org/<prefix>:<accession>`. If the namespace is
         embedded in the LUI the prefix is already part of the term, otherwise
         the prefix of the identifiers.org registry is prepended.
+
+        The normalization never changes what the resource says: the result is
+        an url, and parsing it again yields the same `collection` and `term`.
+        A collection which is not in the registry, or a term which does not
+        carry the prefix of its collection, can not be written as a compact
+        identifier and is returned as
+        `https://identifiers.org/<collection>/<term>`. Whether the term is
+        valid does not matter here, this is the task of `validate`.
+
+        Resources without a collection, i.e., arbitrary urls, are returned
+        unchanged.
         """
         if not self.term:
             return None
 
-        if (
-            self.provider == ProviderType.IDENTIFIERS_ORG
-            and self.collection is not None
-        ):
-            namespace = get_registry().ns_dict.get(self.collection, None)
-            if namespace:
-                if namespace.namespaceEmbeddedInLui:
-                    return f"{IDENTIFIERS_ORG_PREFIX}/{self.term}"
-                return f"{IDENTIFIERS_ORG_PREFIX}/{self.collection}:{self.term}"
+        if self.provider != ProviderType.IDENTIFIERS_ORG or self.collection is None:
+            return self.term
+
+        namespace = get_registry().ns_dict.get(self.collection, None)
+        if namespace and not namespace.namespaceEmbeddedInLui:
+            return f"{IDENTIFIERS_ORG_PREFIX}/{self.collection}:{self.term}"
+
+        # the term is only a compact identifier if its prefix is the collection
+        if self.term.lower().startswith(f"{self.collection}:"):
+            return f"{IDENTIFIERS_ORG_PREFIX}/{self.term}"
 
-        return self.term
+        return f"{IDENTIFIERS_ORG_PREFIX}/{self.collection}/{self.term}"
 
     def __repr__(self) -> str:
         """Get representation string."""

{pymetadata-0.6.2 → pymetadata-0.6.4}/src/pymetadata/omex.py

@@ -743,6 +743,10 @@ class Omex:
         `Omex.guess_format`; SED-ML files added this way get `master=True`,
         as they are the entry point of a simulation study.
 
+        The entries are in the order of the manifest, followed by the files
+        which the manifest does not list, sorted by their location. The order
+        does not depend on the file system.
+
         Args:
             directory: directory with the content of the archive
 
@@ -785,7 +789,8 @@ class Omex:
         # new archive
         omex = Omex()
 
-        # iterate over all locations and add entry
+        # locations of all files
+        file_paths: dict[str, str] = {}
         for root, _dirs, files in os.walk(str(directory)):
             for file in files:
                 file_path = os.path.join(root, file)
@@ -795,32 +800,46 @@ class Omex:
                 if location == "./manifest.xml":
                     # manifest is created from the internal manifest entries
                     continue
+                file_paths[location] = file_path
+
+        # The order of `os.walk` is the order of the file system, which differs
+        # between machines: the entries are added in the order of the manifest,
+        # followed by the files which the manifest does not list, by location.
+        positions: dict[str, int] = {}
+        if manifest:
+            positions = {e.location: k for k, e in enumerate(manifest.entries)}
+        locations = sorted(
+            file_paths, key=lambda loc: (positions.get(loc, len(positions)), loc)
+        )
 
-                logger.debug("'%s' -> '%s'", file_path, location)
-                entry: ManifestEntry
-                if manifest and location in manifest:
-                    # use entry from existing manifest
-                    entry = manifest[location]
-                else:
-                    if manifest and location not in manifest:
-                        logger.warning(
-                            "Entry with location missing in manifest.xml: '%s'",
-                            location,
-                        )
-
-                    format = Omex.guess_format(Path(file_path))
-                    master = False
-                    if format and ManifestEntry.is_format(
-                        format_key="sedml", format=format
-                    ):
-                        master = True
-                    entry = ManifestEntry(
-                        location=location,
-                        format=format,
-                        master=master,
+        # iterate over all locations and add entry
+        for location in locations:
+            file_path = file_paths[location]
+            logger.debug("'%s' -> '%s'", file_path, location)
+            entry: ManifestEntry
+            if manifest and location in manifest:
+                # use entry from existing manifest
+                entry = manifest[location]
+            else:
+                if manifest and location not in manifest:
+                    logger.warning(
+                        "Entry with location missing in manifest.xml: '%s'",
+                        location,
                     )
 
-                omex.add_entry(entry_path=Path(file_path), entry=entry)
+                format = Omex.guess_format(Path(file_path))
+                master = False
+                if format and ManifestEntry.is_format(
+                    format_key="sedml", format=format
+                ):
+                    master = True
+                entry = ManifestEntry(
+                    location=location,
+                    format=format,
+                    master=master,
+                )
+
+            omex.add_entry(entry_path=Path(file_path), entry=entry)
 
         return omex
 

{pymetadata-0.6.2 → pymetadata-0.6.4}/src/pymetadata/webservices/unichem.py

@@ -17,9 +17,9 @@ See <https://www.ebi.ac.uk/unichem/info/webservices>.
 import contextlib
 import logging
 import urllib.parse
-from dataclasses import dataclass, field
+from dataclasses import dataclass, field, fields
 from pathlib import Path
-from typing import ClassVar
+from typing import Any, ClassVar
 
 import pymetadata
 from pymetadata.cache import (
@@ -37,34 +37,62 @@ logger = logging.getLogger(__name__)
 
 @dataclass
 class UnichemSource:
-    """Unichem source.
-
-    src_id (the src_id for this source),
-    src_url (the main home page of the source),
-    name (the unique name for the source in UniChem, always lower case),
-    name_long (the full name of the source, as defined by the source),
-    name_label (A name for the source suitable for use as a 'label' for the source within a web-page. Correct case setting for source, and always less than 30 characters),
-    description (a description of the content of the source),
-    base_id_url_available (an flag indicating whether this source provides a valid base_id_url for creating cpd-specific links [1=yes, 0=no]).
-    base_id_url (the base url for constructing hyperlinks to this source [append an identifier from this source to the end of this url to create a valid url to a specific page for this cpd], unless aux_for_url=1),
-    aux_for_url (A flag to indicate whether the aux_src field should be used to create hyperlinks instead of the src_compound_id [1=yes, 0=no]
+    """Database known to UniChem, see the `sources` endpoint of the web service.
+
+    Only `sourceID` and `name` are required. UniChem adds and removes the
+    descriptive fields without notice, so they are optional, and
+    `UnichemSource.from_dict` ignores fields which are not declared here.
+
+    Attributes:
+        sourceID: id of the source in UniChem
+        name: unique name of the source in UniChem, always lower case
+        nameLabel: name suitable as label of the source, in the case used by
+            the source
+        nameLong: full name of the source, as defined by the source
+        srcUrl: home page of the source
+        baseIdUrl: base url for links to a compound in the source; the
+            identifier of the compound is appended or replaces `{$id}`
+        description: description of the content of the source
+        UCICount: number of UniChem compound identifiers in the source
+        created: date the source was added to UniChem
+        lastChecked: date UniChem checked the source for an update
+        srcLastUpdated: date of the last update of the source
+        srcDetails: details on the source
+        updateComments: comments on the update of the source
+        private: the source is not public
     """
 
     sourceID: int
-    srcUrl: str
     name: str
-    nameLabel: str = field(repr=False)
-    nameLong: str = field(repr=False)
-    UCICount: int = field(repr=False)
-    baseIdUrl: str = field(repr=False)
-    description: str = field(repr=False)
-    created: str = field(repr=False)
-    lastUpdated: str = field(repr=False)
-    srcDetails: str = field(repr=False)
-    srcReleaseDate: str = field(repr=False)
-    srcReleaseNumber: int = field(repr=False)
-    updateComments: str = field(repr=False)
-    private: bool = field(repr=False)
+    nameLabel: str | None = field(default=None, repr=False)
+    nameLong: str | None = field(default=None, repr=False)
+    srcUrl: str | None = None
+    baseIdUrl: str | None = field(default=None, repr=False)
+    description: str | None = field(default=None, repr=False)
+    UCICount: int | None = field(default=None, repr=False)
+    created: str | None = field(default=None, repr=False)
+    lastChecked: str | None = field(default=None, repr=False)
+    srcLastUpdated: str | None = field(default=None, repr=False)
+    srcDetails: str | None = field(default=None, repr=False)
+    updateComments: str | None = field(default=None, repr=False)
+    private: bool | None = field(default=None, repr=False)
+
+    @classmethod
+    def from_dict(cls, data: dict[str, Any]) -> "UnichemSource":
+        """Create a source from a source of the web service or of the cache.
+
+        Args:
+            data: fields of the source, fields unknown to `UnichemSource` are
+                ignored
+
+        Returns:
+            The source.
+        """
+        names = {f.name for f in fields(cls)}
+        unknown = sorted(set(data) - names)
+        if unknown:
+            logger.debug("Ignored fields of UniChem source: %s", unknown)
+        return cls(**{k: v for k, v in data.items() if k in names})
 
 
 class UnichemQuery:
@@ -117,7 +145,7 @@ class UnichemQuery:
                 data = read_json_cache(
                     unichem_sources_path, max_age=CACHE_DURATION_ONTOLOGY
                 )
-                return {int(k): UnichemSource(**v) for k, v in data.items()}
+                return {int(k): UnichemSource.from_dict(v) for k, v in data.items()}
 
         url = "https://www.ebi.ac.uk/unichem/api/v1/sources/"
         try:
@@ -131,11 +159,13 @@ class UnichemQuery:
                     unichem_sources_path, reason=str(err)
                 )
                 if fallback is not None:
-                    return {int(k): UnichemSource(**v) for k, v in fallback.items()}
+                    return {
+                        int(k): UnichemSource.from_dict(v) for k, v in fallback.items()
+                    }
             raise
 
         sources_list: list[UnichemSource] = [
-            UnichemSource(**v) for v in data["sources"]
+            UnichemSource.from_dict(v) for v in data["sources"]
         ]
         sources = {source.sourceID: source for source in sources_list}
 
@@ -219,9 +249,6 @@ class UnichemQuery:
                 accession = item["src_compound_id"]
                 if source.baseIdUrl:
                     # create and clean url
-                    if not source.baseIdUrl:
-                        continue
-
                     url = f"{source.baseIdUrl}{accession}"
 
                     url_accession = urllib.parse.quote(accession)

{pymetadata-0.6.2 → pymetadata-0.6.4}/tests/core/test_annotation.py

@@ -227,3 +227,82 @@ def test_resource_normalized(resource: str, expected: str) -> None:
     """Test normalization to identifiers.org compact identifiers."""
     a = RDFAnnotation(qualifier=BQB.IS, resource=resource)
     assert a.resource_normalized == expected
+
+
+resource_kept_data = [
+    # collection which is not in the registry (see #81)
+    ("http://identifiers.org/sabiork/1406", "https://identifiers.org/sabiork/1406"),
+    ("urn:miriam:foo:bar", "https://identifiers.org/foo/bar"),
+    ("foo/bar", "https://identifiers.org/foo/bar"),
+    # collection which is not in the registry, term with a prefix of its own
+    (
+        "http://identifiers.org/unit/UO:0000040",
+        "https://identifiers.org/unit/UO:0000040",
+    ),
+    # compact identifier of a prefix which is not in the registry
+    ("https://identifiers.org/CMO:0000012", "https://identifiers.org/CMO:0000012"),
+    ("CMO:0000012", "https://identifiers.org/CMO:0000012"),
+    # term which does not match the pattern of its collection
+    (
+        "http://identifiers.org/chebi/000000035",
+        "https://identifiers.org/chebi/000000035",
+    ),
+    ("taxonomy/abc", "https://identifiers.org/taxonomy:abc"),
+    # prefix with a hyphen or an underscore
+    ("urn:miriam:ec-code:1.1.1.1", "https://identifiers.org/ec-code:1.1.1.1"),
+    (
+        "https://identifiers.org/ec-code/1.1.1.1",
+        "https://identifiers.org/ec-code:1.1.1.1",
+    ),
+    ("go_ref/GO_REF:0000041", "https://identifiers.org/GO_REF:0000041"),
+    (
+        "https://identifiers.org/GO_REF:0000041",
+        "https://identifiers.org/GO_REF:0000041",
+    ),
+    # prefixes are case insensitive
+    ("urn:miriam:CHEBI:CHEBI%3A33699", "https://identifiers.org/CHEBI:33699"),
+    ("TAXONOMY/9606", "https://identifiers.org/taxonomy:9606"),
+]
+
+
+def assert_resource_kept(resource: str) -> None:
+    """Assert that the normalized resource is a url with the same meaning."""
+    a = RDFAnnotation(qualifier=BQB.IS, resource=resource, validate=False)
+    normalized = a.resource_normalized
+    assert normalized
+    assert normalized.startswith("https://")
+
+    b = RDFAnnotation(qualifier=BQB.IS, resource=normalized, validate=False)
+    assert (b.collection, b.term) == (a.collection, a.term)
+    assert b.resource_normalized == normalized
+
+
+@pytest.mark.parametrize("resource,expected", resource_kept_data)
+def test_resource_normalized_keeps_resource(resource: str, expected: str) -> None:
+    """Test that collection and term survive the normalization, see #81."""
+    a = RDFAnnotation(qualifier=BQB.IS, resource=resource, validate=False)
+    assert a.resource_normalized == expected
+    assert_resource_kept(resource)
+
+
+@pytest.mark.parametrize(
+    "resource", [resource for resource, _ in resource_normalized_data]
+)
+def test_resource_normalized_roundtrip(resource: str) -> None:
+    """Test that the normalized resource parses to the same annotation."""
+    assert_resource_kept(resource)
+
+
+def test_resource_normalized_registry() -> None:
+    """Test the normalization with the sample of every registry namespace."""
+    from pymetadata.webservices.registry import get_registry
+
+    for prefix, namespace in get_registry().ns_dict.items():
+        sample_id = namespace.sampleId
+        if not sample_id:
+            continue
+        for resource in [
+            f"https://identifiers.org/{prefix}/{sample_id}",
+            f"urn:miriam:{prefix}:{sample_id.replace(':', '%3A')}",
+        ]:
+            assert_resource_kept(resource)