destiny_sdk 0.5.1__tar.gz → 0.6.0__tar.gz

{destiny_sdk-0.5.1 → destiny_sdk-0.6.0}/.gitignore

@@ -198,3 +198,8 @@ infra/app/*.py
 .certs
 
 libs/fake_data/*.jsonl
+
+.data
+.env.*
+!.env.example
+.idea/

{destiny_sdk-0.5.1 → destiny_sdk-0.6.0}/PKG-INFO

@@ -1,8 +1,8 @@
 Metadata-Version: 2.4
 Name: destiny_sdk
-Version: 0.5.1
+Version: 0.6.0
 Summary: A software development kit (sdk) to support interaction with the DESTINY repository
-Author-email: Adam Hamilton <adam@futureevidence.org>, Andrew Harvey <andrew@futureevidence.org>, Daniel Breves <daniel@futureevidence.org>, Jack Walmisley <jack@futureevidence.org>
+Author-email: Adam Hamilton <adam@futureevidence.org>, Andrew Harvey <andrew@futureevidence.org>, Daniel Breves <daniel@futureevidence.org>, Jack Walmisley <jack@futureevidence.org>, Tim Repke <tim.repke@pik-potsdam.de>
 License-Expression: Apache-2.0
 License-File: LICENSE
 Requires-Python: ~=3.12
@@ -14,6 +14,7 @@ Requires-Dist: pytest-asyncio<2,>=1.0.0
 Requires-Dist: pytest-httpx<0.36,>=0.35.0
 Requires-Dist: pytest<9,>=8.4.0
 Requires-Dist: python-jose<4,>=3.4.0
+Provides-Extra: labs
 Description-Content-Type: text/markdown
 
 # DESTINY SDK
@@ -34,6 +35,13 @@ pip install destiny-sdk
 uv add destiny-sdk
 ```
 
+Some labs functionality may require extra dependencies - these can be installed by:
+
+```sh
+pip install destiny-sdk[labs]
+uv add destiny-sdk --extra labs
+```
+
 ## Development
 
 ### Dependencies

{destiny_sdk-0.5.1 → destiny_sdk-0.6.0}/README.md

@@ -16,6 +16,13 @@ pip install destiny-sdk
 uv add destiny-sdk
 ```
 
+Some labs functionality may require extra dependencies - these can be installed by:
+
+```sh
+pip install destiny-sdk[labs]
+uv add destiny-sdk --extra labs
+```
+
 ## Development
 
 ### Dependencies

{destiny_sdk-0.5.1 → destiny_sdk-0.6.0}/pyproject.toml

@@ -17,6 +17,7 @@ authors = [
     {email = "andrew@futureevidence.org", name = "Andrew Harvey"},
     {email = "daniel@futureevidence.org", name = "Daniel Breves"},
     {email = "jack@futureevidence.org", name = "Jack Walmisley"},
+    {email = "tim.repke@pik-potsdam.de", name = "Tim Repke"},
 ]
 dependencies = [
     "cachetools>=5.5.2,<6",
@@ -33,7 +34,10 @@ license = "Apache-2.0"
 name = "destiny_sdk"
 readme = "README.md"
 requires-python = "~=3.12"
-version = "0.5.1"
+version = "0.6.0"
+
+[project.optional-dependencies]
+labs = []
 
 [tool.pytest.ini_options]
 addopts = ["--color=yes", "--import-mode=importlib", "--verbose"]

{destiny_sdk-0.5.1 → destiny_sdk-0.6.0}/src/destiny_sdk/__init__.py

@@ -8,6 +8,7 @@ from . import (
     imports,
     references,
     robots,
+    search,
     visibility,
 )
 
@@ -19,5 +20,6 @@ __all__ = [
     "imports",
     "references",
     "robots",
+    "search",
     "visibility",
 ]

{destiny_sdk-0.5.1 → destiny_sdk-0.6.0}/src/destiny_sdk/core.py

@@ -2,7 +2,9 @@
 
 from typing import Self
 
-from pydantic import BaseModel
+from pydantic import BaseModel, Field
+
+from destiny_sdk.search import SearchResultPage, SearchResultTotal
 
 # These are non-standard newline characters that are not escaped by model_dump_json().
 # We want jsonl files to have empirical new lines so they can be streamed line by line.
@@ -47,3 +49,14 @@ class _JsonlFileInputMixIn(BaseModel):
         :rtype: Self
         """
         return cls.model_validate_json(jsonl)
+
+
+class SearchResultMixIn(BaseModel):
+    """A mixin class for models that represent search results."""
+
+    total: SearchResultTotal = Field(
+        description="The total number of results matching the search criteria.",
+    )
+    page: SearchResultPage = Field(
+        description="Information about the page of results.",
+    )

destiny_sdk-0.6.0/src/destiny_sdk/labs/__init__.py

@@ -0,0 +1,10 @@
+"""
+Experimental DESTINY SDK.
+
+The DESTINY SDK-labs provides experimental features
+for interacting with DESTINY repository.
+"""
+
+from . import references
+
+__all__ = ["references"]

destiny_sdk-0.6.0/src/destiny_sdk/labs/references.py

@@ -0,0 +1,154 @@
+"""
+Extended Reference SDK.
+
+Extended Reference class for the Destiny SDK
+with added experimental convenience methods and properties.
+"""
+
+from collections.abc import Generator
+from typing import cast
+
+from pydantic import BaseModel, Field
+
+from destiny_sdk.enhancements import (
+    Annotation,
+    AnnotationType,
+    BibliographicMetadataEnhancement,
+    EnhancementType,
+)
+from destiny_sdk.identifiers import ExternalIdentifierType
+from destiny_sdk.references import Reference
+
+
+class LabsReference(BaseModel):
+    """Experimental presenter class for Reference with added convenience methods."""
+
+    reference: Reference = Field(
+        ...,
+        description="The core Reference object",
+    )
+
+    def _get_id(self, identifier_type: ExternalIdentifierType) -> str | int | None:
+        """Fetch an identifier matching the given identifier_type."""
+        for identifier in self.reference.identifiers or []:
+            if identifier.identifier_type == identifier_type:
+                return identifier.identifier
+        return None
+
+    @property
+    def openalex_id(self) -> str | None:
+        """Return an OpenAlex ID for the reference."""
+        return cast(
+            str | None, self._get_id(identifier_type=ExternalIdentifierType.OPEN_ALEX)
+        )
+
+    @property
+    def doi(self) -> str | None:
+        """Return a DOI for the reference."""
+        return cast(
+            str | None, self._get_id(identifier_type=ExternalIdentifierType.DOI)
+        )
+
+    @property
+    def pubmed_id(self) -> int | None:
+        """Return a pubmed ID for the reference."""
+        return cast(
+            int | None, self._get_id(identifier_type=ExternalIdentifierType.PM_ID)
+        )
+
+    @property
+    def abstract(self) -> str | None:
+        """Return an abstract for the reference."""
+        for enhancement in self.reference.enhancements or []:
+            if enhancement.content.enhancement_type == EnhancementType.ABSTRACT:
+                return enhancement.content.abstract
+        return None
+
+    @property
+    def publication_year(self) -> int | None:
+        """Return a publication year for the reference."""
+        for meta in self.it_bibliographics():
+            if meta.publication_year is not None:
+                return meta.publication_year
+        return None
+
+    @property
+    def title(self) -> str | None:
+        """The title of the reference. If multiple are present, return first one."""
+        for meta in self.it_bibliographics():
+            if meta.title is not None:
+                return meta.title
+        return None
+
+    def it_bibliographics(
+        self,
+    ) -> Generator[BibliographicMetadataEnhancement, None, None]:
+        """Iterate bibliographic enhancements."""
+        for enhancement in self.reference.enhancements or []:
+            if enhancement.content.enhancement_type == EnhancementType.BIBLIOGRAPHIC:
+                yield enhancement.content
+
+    def it_annotations(
+        self,
+        source: str | None = None,
+        annotation_type: AnnotationType | None = None,
+        scheme: str | None = None,
+        label: str | None = None,
+    ) -> Generator[Annotation, None, None]:
+        """
+        Iterate annotation enhancements for the given filters.
+
+        :param source: Optional filter for Enhancement.source
+        :param annotation_type: Optional filter for
+                                AnnotationEnhancement.annotation_type
+        :param scheme: Optional filter for Annotation.scheme
+        :param label: Optional filter for Annotation.label
+        """
+        for enhancement in self.reference.enhancements or []:
+            if enhancement.content.enhancement_type == EnhancementType.ANNOTATION:
+                if source is not None and enhancement.source != source:
+                    continue
+                for annotation in enhancement.content.annotations:
+                    if (
+                        annotation_type is not None
+                        and annotation.annotation_type != annotation_type
+                    ):
+                        continue
+                    if scheme is not None and annotation.scheme != scheme:
+                        continue
+                    if label is not None and annotation.label != label:
+                        continue
+                    yield annotation
+
+    def has_bool_annotation(
+        self,
+        source: str | None = None,
+        scheme: str | None = None,
+        label: str | None = None,
+        expected_value: bool = True,  # noqa: FBT001, FBT002
+    ) -> bool | None:
+        """
+        Check if a specific annotation exists and is true.
+
+        :param source: Optional filter for Enhancement.source
+        :param scheme: Optional filter for Annotation.scheme
+        :param label: Optional filter for Annotation.label
+        :param expected_value: Specify expected boolean annotation value
+        :return: Returns the boolean value for the first annotation matching
+                 the filters or None if nothing is found.
+        """
+        if scheme is None and label is None:
+            msg = "Please use at least one of the optional scheme or label filters."
+            raise AssertionError(msg)
+
+        found_annotation = False
+        for annotation in self.it_annotations(
+            source=source,
+            annotation_type=AnnotationType.BOOLEAN,
+            scheme=scheme,
+            label=label,
+        ):
+            if annotation.value == expected_value:
+                return True
+            found_annotation = True
+        return False if found_annotation else None

{destiny_sdk-0.5.1 → destiny_sdk-0.6.0}/src/destiny_sdk/references.py

@@ -4,7 +4,7 @@ from typing import Self
 
 from pydantic import UUID4, BaseModel, Field, TypeAdapter
 
-from destiny_sdk.core import _JsonlFileInputMixIn
+from destiny_sdk.core import SearchResultMixIn, _JsonlFileInputMixIn
 from destiny_sdk.enhancements import Enhancement, EnhancementFileInput
 from destiny_sdk.identifiers import ExternalIdentifier
 from destiny_sdk.visibility import Visibility
@@ -65,3 +65,11 @@ class ReferenceFileInput(_JsonlFileInputMixIn, BaseModel):
         default=None,
         description="A list of enhancements for the reference",
     )
+
+
+class ReferenceSearchResult(SearchResultMixIn, BaseModel):
+    """A search result for references."""
+
+    references: list[Reference] = Field(
+        description="The references returned by the search.",
+    )

destiny_sdk-0.6.0/src/destiny_sdk/search.py

@@ -0,0 +1,52 @@
+"""Models for search queries and results."""
+
+from pydantic import BaseModel, Field
+
+
+class SearchResultTotal(BaseModel):
+    """Information about the total number of search results."""
+
+    count: int = Field(
+        description="The total number of results matching the search criteria.",
+    )
+    is_lower_bound: bool = Field(
+        description="Whether the count is a lower bound (true) or exact (false).",
+    )
+
+
+class SearchResultPage(BaseModel):
+    """Information about the page of search results."""
+
+    count: int = Field(
+        description="The number of results on this page.",
+    )
+    number: int = Field(
+        description="The page number of results returned, indexed from 1.",
+    )
+
+
+class AnnotationFilter(BaseModel):
+    """An annotation filter for search queries."""
+
+    scheme: str = Field(
+        description="The annotation scheme to filter by.",
+    )
+    label: str | None = Field(
+        None,
+        description="The annotation label to filter by.",
+    )
+    score: float | None = Field(
+        None,
+        description="The minimum score for the annotation filter.",
+        ge=0.0,
+        le=1.0,
+    )
+
+    def serialize(self) -> str:
+        """Serialize the annotation filter to a string."""
+        annotation = self.scheme
+        if self.label:
+            annotation += f"/{self.label}"
+        if self.score is not None:
+            annotation += f"@{self.score}"
+        return annotation

destiny_sdk-0.6.0/tests/unit/labs/test_references.py

@@ -0,0 +1,144 @@
+"""Tests for the experimental Reference class."""
+
+import json
+from pathlib import Path
+
+from destiny_sdk.labs.references import LabsReference
+from destiny_sdk.references import Reference
+
+
+def _read_references():
+    test_data_path = Path(__file__).parent.parent / "test_data/destiny_references.jsonl"
+    with test_data_path.open() as test_references_file:
+        for line in test_references_file:
+            yield LabsReference(reference=Reference.from_es(json.loads(line)))
+
+
+def test_annotations():
+    """Test that the parse_data method returns the expected output."""
+
+    expected = [
+        (
+            {"scheme": "inclusion:destiny"},
+            [True, None, True, False, False, True, True, True, False, True],
+        ),
+        (
+            {"scheme": "inclusion:destiny", "label": "Included in DESTINY domain"},
+            [True, None, True, False, False, True, True, True, False, True],
+        ),
+        (
+            {
+                "scheme": "inclusion:destiny",
+                "label": "Included in DESTINY domain",
+                "expected_value": False,
+            },
+            [False, None, False, True, True, False, False, False, True, False],
+        ),
+        (
+            {
+                "scheme": "classifier:taxonomy:Context",
+                "label": "Coastal socioecological systems",
+            },
+            [None, None, None, None, None, False, False, False, False, False],
+        ),
+        (
+            {"scheme": "classifier:taxonomy:Context"},
+            [None, None, None, None, None, True, True, True, True, True],
+        ),
+        (
+            {"scheme": "classifier:taxonomy:Context", "expected_value": False},
+            [None, None, None, None, None, True, True, True, True, True],
+        ),
+    ]
+
+    for params, expected_values in expected:
+        for ref, expected_value in zip(
+            _read_references(), expected_values, strict=False
+        ):
+            assert expected_value == ref.has_bool_annotation(**params)
+
+
+def test_titles():
+    """Test that the parse_data method returns the expected output."""
+    expected = [
+        "Makro Ekonomik Zihin Teori, Politika, Dinamikler",
+        "Analysis of parental beliefs and practices leading to excessive screen "
+        "time in early childhood",
+        "Exploring the link between A Body Shape Index and abdominal aortic "
+        "calcification in chronic kidney disease: a cross-sectional analysis from "
+        "2013–2014 National Health and Nutrition Examination Survey",  # noqa: RUF001
+        "Microbiological Evaluation of Biodegradation Processes of Solid Waste in "
+        "Reclaimed Landfills",
+        "Wave-Structure Interactions of a Floating FPSO-Shaped Body",
+        "Function and public awareness of sustainable development and population "
+        "health projects in Montreal, Canada: a logic model and survey of the "
+        "Quartiers 21 Program",
+        "NGOs’ responses to the challenges faced by orphans and "  # noqa: RUF001
+        "vulnerable children (OVC) in Chegutu, Zimbabwe",
+        "Climate change-related health hazards in daycare centers in Munich, Germany: "
+        "risk perception and adaptation measures",
+        None,
+        "Association of Placenta Praevia with Previous Cesarean Section in "
+        "Rajshahi Medical College Hospital",
+    ]
+    for ref, expected_value in zip(_read_references(), expected, strict=False):
+        assert expected_value == ref.title
+
+
+def test_biblio():
+    """Test that the parse_data method returns the expected output."""
+    expected = {
+        "doi": [
+            "10.58830/ozgur.pub782",
+            None,
+            "10.1080/0886022x.2025.2517403",
+            "10.54740/ros.2025.028",
+            "10.31814/stce.huce2025-19(2)-11",
+            "10.1016/s0140-6736(14)61878-x",
+            "10.1111/issj.12473",
+            "10.1007/s10113-023-02136-w",
+            "10.3390/diseases11040157",
+            "10.36347/sasjs.2023.v09i10.007",
+        ],
+        "publication_year": [
+            2025,
+            None,
+            2025,
+            2025,
+            2025,
+            None,
+            2023,
+            2023,
+            2023,
+            None,
+        ],
+        "openalex_id": [
+            "W4411634280",
+            "W4411634320",
+            "W4411634759",
+            "W4411698874",
+            "W4411698892",
+            "W1965074043",
+            "W4388230581",
+            "W4388231242",
+            "W4388231278",
+            "W4388232129",
+        ],
+        "pubmed_id": [
+            None,
+            40562693,
+            40562394,
+            None,
+            None,
+            None,
+            None,
+            None,
+            37987268,
+            None,
+        ],
+    }
+    for prop, expected_values in expected.items():
+        for ref, expected_value in zip(
+            _read_references(), expected_values, strict=False
+        ):
+            assert expected_value == getattr(ref, prop)