destiny_sdk 0.2.0.post0__tar.gz → 0.2.3__tar.gz

destiny_sdk-0.2.3/.gitignore

@@ -0,0 +1,199 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+docs/html/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+cli/.env.*
+!/cli/.env.example
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# ruff
+.ruff_cache/
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# PyPI configuration file
+.pypirc
+
+# Terraform
+.terraform/
+
+# VS Code Workspace settings
+*.code-workspace
+.vscode/
+
+# Mac Finder config
+.DS_Store
+
+# MinIO presigned URLs
+.minio/presigned_urls.json
+
+# delete-me working files
+tmp-scripts.sh
+infra/app/*.py
+
+
+.certs
+
+libs/fake_data/*.jsonl

{destiny_sdk-0.2.0.post0 → destiny_sdk-0.2.3}/PKG-INFO

@@ -1,23 +1,19 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.4
 Name: destiny_sdk
-Version: 0.2.0.post0
+Version: 0.2.3
 Summary: A software development kit (sdk) to support interaction with the DESTINY repository
-License: Apache 2.0
-Author: Adam Hamilton
-Author-email: adam@futureevidence.org
-Requires-Python: >=3.12,<4.0
-Classifier: License :: Other/Proprietary License
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Requires-Dist: cachetools (>=5.5.2,<6.0.0)
-Requires-Dist: fastapi (>=0.115.12,<0.116.0)
-Requires-Dist: httpx (>=0.28.1,<0.29.0)
-Requires-Dist: pydantic (>=2.11.3,<3.0.0)
-Requires-Dist: pytest (>=8.4.0,<9.0.0)
-Requires-Dist: pytest-asyncio (>=1.0.0,<2.0.0)
-Requires-Dist: pytest-httpx (>=0.35.0,<0.36.0)
-Requires-Dist: python-jose (>=3.4.0,<4.0.0)
+Author-email: Adam Hamilton <adam@futureevidence.org>, Andrew Harvey <andrew@futureevidence.org>, Daniel Breves <daniel@futureevidence.org>, Jack Walmisley <jack@futureevidence.org>
+License-Expression: Apache-2.0
+License-File: LICENSE
+Requires-Python: ~=3.12
+Requires-Dist: cachetools<6,>=5.5.2
+Requires-Dist: fastapi<0.116,>=0.115.12
+Requires-Dist: httpx<0.29,>=0.28.1
+Requires-Dist: pydantic<3,>=2.11.3
+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
 Description-Content-Type: text/markdown
 
 # DESTINY SDK
@@ -35,7 +31,7 @@ pip install destiny-sdk
 ```
 
 ```sh
-poetry add destiny-sdk
+uv add destiny-sdk
 ```
 
 ## Development
@@ -43,21 +39,21 @@ poetry add destiny-sdk
 ### Dependencies
 
 ```sh
-poetry install
+uv install
 ```
 
 ### Tests
 
 ```sh
-poetry run pytest
+uv run pytest
 ```
 
 ### Installing as an editable package of another project
 
-Run the following command in the root folder of the other project (assuming poetry as a packaging framework). Pip also has an `--editable` option that you can use.
+Run the following command in the root folder of the other project (assuming uv as a packaging framework). Pip also has an `--editable` option that you can use.
 
 ```sh
-poetry add --editable ./PATH/TO/sdk/
+uv add --editable ./PATH/TO/sdk/
 ```
 
 or replace the dependency in `pyproject.toml` with
@@ -71,8 +67,8 @@ destiny-sdk = {path = "./PATH/TO/sdk/", develop = true}
 If you want to use a local build of the sdk `z.whl`, do
 
 ```sh
-poetry build
-poetry add ./PATH/TO/WHEEL.whl
+uv build
+uv add ./PATH/TO/WHEEL.whl
 ```
 
 ### Publishing
@@ -88,4 +84,3 @@ Given a version number `MAJOR.MINOR.PATCH`, increment the:
 - `MAJOR` version when you make incompatible API change
 - `MINOR` version when you add functionality in a backward compatible manner
 - `PATCH` version when you make backward compatible bug fixes
-

{destiny_sdk-0.2.0.post0 → destiny_sdk-0.2.3}/README.md

@@ -13,7 +13,7 @@ pip install destiny-sdk
 ```
 
 ```sh
-poetry add destiny-sdk
+uv add destiny-sdk
 ```
 
 ## Development
@@ -21,21 +21,21 @@ poetry add destiny-sdk
 ### Dependencies
 
 ```sh
-poetry install
+uv install
 ```
 
 ### Tests
 
 ```sh
-poetry run pytest
+uv run pytest
 ```
 
 ### Installing as an editable package of another project
 
-Run the following command in the root folder of the other project (assuming poetry as a packaging framework). Pip also has an `--editable` option that you can use.
+Run the following command in the root folder of the other project (assuming uv as a packaging framework). Pip also has an `--editable` option that you can use.
 
 ```sh
-poetry add --editable ./PATH/TO/sdk/
+uv add --editable ./PATH/TO/sdk/
 ```
 
 or replace the dependency in `pyproject.toml` with
@@ -49,8 +49,8 @@ destiny-sdk = {path = "./PATH/TO/sdk/", develop = true}
 If you want to use a local build of the sdk `z.whl`, do
 
 ```sh
-poetry build
-poetry add ./PATH/TO/WHEEL.whl
+uv build
+uv add ./PATH/TO/WHEEL.whl
 ```
 
 ### Publishing

destiny_sdk-0.2.3/pyproject.toml

@@ -0,0 +1,43 @@
+[build-system]
+build-backend = "hatchling.build"
+requires = ["hatchling"]
+
+[dependency-groups]
+dev = [
+    "mypy>=1.15.0,<2",
+    "pre-commit>=4.2.0,<5",
+    "pytest-env>=1.1.5,<2",
+    "ruff>=0.11.5,<0.12",
+    "uvloop>=0.21.0,<0.22",
+]
+
+[project]
+authors = [
+    {email = "adam@futureevidence.org", name = "Adam Hamilton"},
+    {email = "andrew@futureevidence.org", name = "Andrew Harvey"},
+    {email = "daniel@futureevidence.org", name = "Daniel Breves"},
+    {email = "jack@futureevidence.org", name = "Jack Walmisley"},
+]
+dependencies = [
+    "cachetools>=5.5.2,<6",
+    "fastapi>=0.115.12,<0.116",
+    "httpx>=0.28.1,<0.29",
+    "pydantic>=2.11.3,<3",
+    "pytest-asyncio>=1.0.0,<2",
+    "pytest-httpx>=0.35.0,<0.36",
+    "pytest>=8.4.0,<9",
+    "python-jose>=3.4.0,<4",
+]
+description = "A software development kit (sdk) to support interaction with the DESTINY repository"
+license = "Apache-2.0"
+name = "destiny_sdk"
+readme = "README.md"
+requires-python = "~=3.12"
+version = "0.2.3"
+
+[tool.pytest.ini_options]
+addopts = ["--color=yes", "--import-mode=importlib", "--verbose"]
+env = ["ENV=test"]
+norecursedirs = ["tests/e2e"]
+pythonpath = "."
+testpaths = ["tests"]

{destiny_sdk-0.2.0.post0 → destiny_sdk-0.2.3}/src/destiny_sdk/core.py

@@ -4,6 +4,18 @@ from typing import Self
 
 from pydantic import BaseModel
 
+# 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.
+# Hence we replace each occurrence with standard new lines.
+_ESCAPED_NEW_LINE = "\\n"
+_UNSUPPORTED_NEWLINE_TRANSLATION = str.maketrans(
+    {
+        "\u0085": _ESCAPED_NEW_LINE,
+        "\u2028": _ESCAPED_NEW_LINE,
+        "\u2029": _ESCAPED_NEW_LINE,
+    }
+)
+
 
 class _JsonlFileInputMixIn(BaseModel):
     """
@@ -20,7 +32,9 @@ class _JsonlFileInputMixIn(BaseModel):
         :return: The JSONL string representation of the model.
         :rtype: str
         """
-        return self.model_dump_json(exclude_none=True)
+        return self.model_dump_json(exclude_none=True).translate(
+            _UNSUPPORTED_NEWLINE_TRANSLATION
+        )
 
     @classmethod
     def from_jsonl(cls, jsonl: str) -> Self:

{destiny_sdk-0.2.0.post0 → destiny_sdk-0.2.3}/src/destiny_sdk/enhancements.py

@@ -58,7 +58,7 @@ class Authorship(BaseModel):
     """
 
     display_name: str = Field(description="The display name of the author.")
-    orcid: str = Field(description="The ORCid of the author.")
+    orcid: str | None = Field(default=None, description="The ORCid of the author.")
     position: AuthorPosition = Field(
         description="The position of the author within the list of authors."
     )
@@ -105,7 +105,7 @@ other works have cited this work
 
 class AbstractProcessType(StrEnum):
     """
-    The process used to acquyire the abstract.
+    The process used to acquire the abstract.
 
     **Allowed values**:
     - `uninverted`

{destiny_sdk-0.2.0.post0 → destiny_sdk-0.2.3}/src/destiny_sdk/identifiers.py

@@ -27,13 +27,6 @@ class ExternalIdentifierType(StrEnum):
     OTHER = auto()
 
 
-def remove_doi_url(value: str) -> str:
-    """Remove the URL part of the DOI if it exists."""
-    return (
-        value.removeprefix("http://doi.org/").removeprefix("https://doi.org/").strip()
-    )
-
-
 class DOIIdentifier(BaseModel):
     """An external identifier representing a DOI."""
 
@@ -75,6 +68,16 @@ class OpenAlexIdentifier(BaseModel):
         ExternalIdentifierType.OPEN_ALEX, description="The type of identifier used."
     )
 
+    @field_validator("identifier", mode="before")
+    @classmethod
+    def remove_open_alex_url(cls, value: str) -> str:
+        """Remove the OpenAlex URL if it exists."""
+        return (
+            value.removeprefix("http://openalex.org/")
+            .removeprefix("https://openalex.org/")
+            .strip()
+        )
+
 
 class OtherIdentifier(BaseModel):
     """An external identifier not otherwise defined by the repository."""

destiny_sdk-0.2.3/src/destiny_sdk/parsers/__init__.py

@@ -0,0 +1,5 @@
+"""The parsers module contains the parsers for the Destiny SDK."""
+
+from destiny_sdk.parsers.eppi_parser import EPPIParser
+
+__all__ = ["EPPIParser"]

destiny_sdk-0.2.3/src/destiny_sdk/parsers/eppi_parser.py

@@ -0,0 +1,173 @@
+"""Parser for a EPPI JSON export file."""
+
+from typing import Any
+
+from destiny_sdk.enhancements import (
+    AbstractContentEnhancement,
+    AbstractProcessType,
+    AnnotationEnhancement,
+    AnnotationType,
+    AuthorPosition,
+    Authorship,
+    BibliographicMetadataEnhancement,
+    BooleanAnnotation,
+    EnhancementContent,
+    EnhancementFileInput,
+)
+from destiny_sdk.identifiers import (
+    DOIIdentifier,
+    ExternalIdentifier,
+    ExternalIdentifierType,
+)
+from destiny_sdk.references import ReferenceFileInput
+from destiny_sdk.visibility import Visibility
+
+
+class EPPIParser:
+    """
+    Parser for an EPPI JSON export file.
+
+    See example here: https://eppi.ioe.ac.uk/cms/Portals/35/Maps/Examples/example_orignal.json
+    """
+
+    version = "1.0"
+
+    def __init__(self, tags: list[str] | None = None) -> None:
+        """
+        Initialize the EPPIParser with optional tags.
+
+        Args:
+            tags (list[str] | None): Optional list of tags to annotate references.
+
+        """
+        self.tags = tags or []
+        self.parser_source = f"destiny_sdk.eppi_parser@{self.version}"
+
+    def _parse_identifiers(
+        self, ref_to_import: dict[str, Any]
+    ) -> list[ExternalIdentifier]:
+        identifiers = []
+        if doi := ref_to_import.get("DOI"):
+            identifiers.append(
+                DOIIdentifier(
+                    identifier=doi,
+                    identifier_type=ExternalIdentifierType.DOI,
+                )
+            )
+        return identifiers
+
+    def _parse_abstract_enhancement(
+        self, ref_to_import: dict[str, Any]
+    ) -> EnhancementContent | None:
+        if abstract := ref_to_import.get("Abstract"):
+            return AbstractContentEnhancement(
+                process=AbstractProcessType.OTHER,
+                abstract=abstract,
+            )
+        return None
+
+    def _parse_bibliographic_enhancement(
+        self, ref_to_import: dict[str, Any]
+    ) -> EnhancementContent | None:
+        title = ref_to_import.get("Title")
+        publication_year = (
+            int(year)
+            if (year := ref_to_import.get("Year")) and year.isdigit()
+            else None
+        )
+        publisher = ref_to_import.get("Publisher")
+        authors_string = ref_to_import.get("Authors")
+
+        authorships = []
+        if authors_string:
+            authors = [
+                author.strip() for author in authors_string.split(";") if author.strip()
+            ]
+            for i, author_name in enumerate(authors):
+                position = AuthorPosition.MIDDLE
+                if i == 0:
+                    position = AuthorPosition.FIRST
+                if i == len(authors) - 1 and i > 0:
+                    position = AuthorPosition.LAST
+
+                authorships.append(
+                    Authorship(
+                        display_name=author_name,
+                        position=position,
+                    )
+                )
+
+        if not title and not publication_year and not publisher and not authorships:
+            return None
+
+        return BibliographicMetadataEnhancement(
+            title=title,
+            publication_year=publication_year,
+            publisher=publisher,
+            authorship=authorships if authorships else None,
+        )
+
+    def _create_annotation_enhancement(self) -> EnhancementContent | None:
+        if not self.tags:
+            return None
+        annotations = [
+            BooleanAnnotation(
+                annotation_type=AnnotationType.BOOLEAN,
+                scheme=self.parser_source,
+                label=tag,
+                value=True,
+            )
+            for tag in self.tags
+        ]
+        return AnnotationEnhancement(
+            annotations=annotations,
+        )
+
+    def parse_data(
+        self, data: dict, source: str | None = None, robot_version: str | None = None
+    ) -> list[ReferenceFileInput]:
+        """
+        Parse an EPPI JSON export dict and return a list of ReferenceFileInput objects.
+
+        Args:
+            data (dict): Parsed EPPI JSON export data.
+            source (str | None): Optional source string for deduplication/provenance.
+            robot_version (str | None): Optional robot version string for provenance.
+            Defaults to parser version.
+
+        Returns:
+            list[ReferenceFileInput]: List of parsed references from the data.
+
+        """
+        parser_source = source if source is not None else self.parser_source
+        references = []
+        for ref_to_import in data.get("References", []):
+            enhancement_contents = [
+                content
+                for content in [
+                    self._parse_abstract_enhancement(ref_to_import),
+                    self._parse_bibliographic_enhancement(ref_to_import),
+                    self._create_annotation_enhancement(),
+                ]
+                if content
+            ]
+
+            enhancements = [
+                EnhancementFileInput(
+                    source=parser_source,
+                    visibility=Visibility.PUBLIC,
+                    content=content,
+                    enhancement_type=content.enhancement_type,
+                    robot_version=robot_version,
+                )
+                for content in enhancement_contents
+            ]
+
+            references.append(
+                ReferenceFileInput(
+                    visibility=Visibility.PUBLIC,
+                    identifiers=self._parse_identifiers(ref_to_import),
+                    enhancements=enhancements,
+                )
+            )
+        return references

destiny_sdk-0.2.3/tests/unit/conftest.py

@@ -0,0 +1,15 @@
+import asyncio
+import logging
+from typing import Any
+
+import pytest
+
+MIGRATION_TASK: asyncio.Task | None = None
+
+logging.getLogger("asyncio").setLevel("DEBUG")
+
+
+@pytest.fixture(scope="session", autouse=True)
+def anyio_backend() -> tuple[str, dict[str, Any]]:
+    """Specify the anyio backend for async tests."""
+    return "asyncio", {"use_uvloop": True}