destiny_sdk 0.7.5__py3-none-any.whl → 0.7.6__py3-none-any.whl

destiny_sdk/client.py

@@ -213,8 +213,8 @@ class OAuthMiddleware(httpx.Auth):
 
         auth = OAuthMiddleware(
             azure_client_id="client-id",
-            azure_application_id="login-url",
-            azure_tenant_id="tenant-id",
+            azure_application_id="application-id",
+            azure_login_url="login-url",
         )
 
     **Confidential Client Application (client credentials)**
@@ -260,11 +260,9 @@ class OAuthMiddleware(httpx.Auth):
         """
         Initialize the auth middleware.
 
-        :param tenant_id: The OAuth2 tenant ID.
-        :type tenant_id: str
-        :param client_id: The OAuth2 client ID.
-        :type client_id: str
-        :param application_id: The application ID for the Destiny API.
+        :param azure_client_id: The OAuth2 client ID.
+        :type azure_client_id: str
+        :param azure_application_id: The application ID for the Destiny API.
         :type application_id: str
         :param azure_login_url: The Azure login URL.
         :type azure_login_url: str

destiny_sdk/enhancements.py

@@ -5,7 +5,7 @@ import json
 from enum import StrEnum, auto
 from typing import Annotated, Any, Literal, Self
 
-from pydantic import UUID4, BaseModel, Field, HttpUrl, model_validator
+from pydantic import UUID4, BaseModel, Field, HttpUrl, field_validator, model_validator
 
 from destiny_sdk.core import _JsonlFileInputMixIn
 from destiny_sdk.identifiers import Identifier
@@ -70,6 +70,42 @@ class Authorship(BaseModel):
     )
 
 
+class Pagination(BaseModel):
+    """
+    Pagination information for journal articles.
+
+    Maps to OpenAlex's work.biblio object. All fields are strings to match
+    OpenAlex's format, which may include non-numeric values like "Spring" or "A1".
+    """
+
+    volume: str | None = Field(
+        default=None,
+        description="The volume number of the journal/publication.",
+    )
+    issue: str | None = Field(
+        default=None,
+        description="The issue number of the journal/publication.",
+    )
+    first_page: str | None = Field(
+        default=None,
+        description="The first page number of the reference in the publication.",
+    )
+    last_page: str | None = Field(
+        default=None,
+        description="The last page number of the reference in the publication.",
+    )
+
+    @field_validator("volume", "issue", "first_page", "last_page", mode="before")
+    @classmethod
+    def normalize_pagination_string(cls, value: str | None) -> str | None:
+        """Normalize pagination strings: NBSP to space, strip, empty to None."""
+        if isinstance(value, str):
+            # Replace NBSP with space, then strip
+            value = value.replace("\u00a0", " ").strip()
+            return value if value else None
+        return value
+
+
 class BibliographicMetadataEnhancement(BaseModel):
     """
     An enhancement which is made up of bibliographic metadata.
@@ -111,6 +147,10 @@ other works have cited this work
         description="The name of the entity which published the version of record.",
     )
     title: str | None = Field(default=None, description="The title of the reference.")
+    pagination: Pagination | None = Field(
+        default=None,
+        description="Pagination info (volume, issue, pages).",
+    )
 
     @property
     def fingerprint(self) -> str:

destiny_sdk/identifiers.py

@@ -1,10 +1,24 @@
 """Identifier classes for the Destiny SDK."""
 
+import re
+import unicodedata
 import uuid
 from enum import StrEnum, auto
 from typing import Annotated, Literal, Self
 
-from pydantic import UUID4, BaseModel, Field, TypeAdapter, field_validator
+from pydantic import UUID4, BaseModel, Field, PositiveInt, TypeAdapter, field_validator
+
+# Case-insensitive patterns for DOI URL prefix stripping
+_DOI_URL_PREFIX_RE = re.compile(r"^(?:https?://)?(?:dx\.)?doi\.org/", re.IGNORECASE)
+_DOI_SCHEME_RE = re.compile(r"^doi:\s*", re.IGNORECASE)
+
+# Translation table for DOI canonicalization (extensible for future characters)
+_DOI_CHAR_TRANSLATION = str.maketrans(
+    {
+        "\u00a0": " ",  # NBSP -> space
+        "\u2010": "-",  # Unicode hyphen -> ASCII hyphen
+    }
+)
 
 
 class ExternalIdentifierType(StrEnum):
@@ -24,7 +38,7 @@ class ExternalIdentifierType(StrEnum):
     PM_ID = auto()
     """A PubMed ID which is a unique identifier for a document in PubMed."""
     PRO_QUEST = auto()
-    """A ProQuest ID which is a unqiue identifier for a document in ProQuest."""
+    """A ProQuest ID which is a unique identifier for a document in ProQuest."""
     OPEN_ALEX = auto()
     """An OpenAlex ID which is a unique identifier for a document in OpenAlex."""
     OTHER = auto()
@@ -35,8 +49,13 @@ class DOIIdentifier(BaseModel):
     """An external identifier representing a DOI."""
 
     identifier: str = Field(
-        description="The DOI of the reference.",
-        pattern=r"^10\.\d{4,9}/[-._;()/:a-zA-Z0-9%<>\[\]+&]+$",
+        description=(
+            "The DOI of the reference. "
+            "Format: '10.<registrant>/<suffix>' where registrant is 4-9 digits "
+            "and suffix is any non-whitespace characters. "
+            "Examples: 10.1000/journal.pone.0001, 10.18730/9WQ$D, 10.1000/édition"
+        ),
+        pattern=r"^10\.\d{4,9}/\S+$",
     )
     identifier_type: Literal[ExternalIdentifierType.DOI] = Field(
         ExternalIdentifierType.DOI, description="The type of identifier used."
@@ -44,23 +63,33 @@ class DOIIdentifier(BaseModel):
 
     @field_validator("identifier", mode="before")
     @classmethod
-    def remove_doi_url(cls, value: str) -> str:
-        """Remove the URL part of the DOI if it exists."""
-        return (
-            value.removeprefix("http://")
-            .removeprefix("https://")
-            .removeprefix("doi.org/")
-            .removeprefix("dx.doi.org/")
-            .removeprefix("doi:")
-            .strip()
-        )
+    def canonicalize_doi(cls, value: str) -> str:
+        """
+        Canonicalize DOI: strip URL prefixes and normalize Unicode.
+
+        - NFC Unicode normalization
+        - Translate special characters (NBSP, Unicode hyphen) via translation table
+        - Case-insensitive URL/scheme prefix stripping
+        """
+        # NFC normalization first
+        value = unicodedata.normalize("NFC", str(value))
+        # Translate special characters and strip
+        value = value.translate(_DOI_CHAR_TRANSLATION).strip()
+        # Strip URL prefixes (case-insensitive)
+        value = _DOI_URL_PREFIX_RE.sub("", value)
+        value = _DOI_SCHEME_RE.sub("", value)
+        return value.strip()
 
 
 class ProQuestIdentifier(BaseModel):
     """An external identifier representing a ProQuest ID."""
 
     identifier: str = Field(
-        description="The ProQuest id of the reference", pattern=r"[0-9]+$"
+        description=(
+            "The ProQuest ID of the reference. "
+            "Format: numeric digits only. Example: 12345678"
+        ),
+        pattern=r"[0-9]+$",
     )
     identifier_type: Literal[ExternalIdentifierType.PRO_QUEST] = Field(
         ExternalIdentifierType.PRO_QUEST, description="The type of identifier used."
@@ -84,12 +113,16 @@ class ERICIdentifier(BaseModel):
     """
     An external identifier representing an ERIC Number.
 
-    An ERIC Number is defined as a unqiue identifiying number preceeded by
-    EJ (for a journal article) or ED (for a non-journal document).
+    An ERIC Number is defined as a unique identifying number preceded by
+    ED (for a non-journal document) or EJ (for a journal article).
     """
 
     identifier: str = Field(
-        description="The ERIC Number of the reference.", pattern=r"E[D|J][0-9]+$"
+        description=(
+            "The ERIC Number. "
+            "Format: 'ED' or 'EJ' followed by digits. Example: ED123456 or EJ789012"
+        ),
+        pattern=r"E[D|J][0-9]+$",
     )
     identifier_type: Literal[ExternalIdentifierType.ERIC] = Field(
         ExternalIdentifierType.ERIC, description="The type of identifier used."
@@ -112,7 +145,9 @@ class ERICIdentifier(BaseModel):
 class PubMedIdentifier(BaseModel):
     """An external identifier representing a PubMed ID."""
 
-    identifier: int = Field(description="The PubMed ID of the reference.")
+    identifier: PositiveInt = Field(
+        description="The PubMed ID (PMID) of the reference. Example: 12345678",
+    )
     identifier_type: Literal[ExternalIdentifierType.PM_ID] = Field(
         ExternalIdentifierType.PM_ID, description="The type of identifier used."
     )
@@ -122,7 +157,11 @@ class OpenAlexIdentifier(BaseModel):
     """An external identifier representing an OpenAlex ID."""
 
     identifier: str = Field(
-        description="The OpenAlex ID of the reference.", pattern=r"^W\d+$"
+        description=(
+            "The OpenAlex ID of the reference. "
+            "Format: 'W' followed by digits. Example: W2741809807"
+        ),
+        pattern=r"^W\d+$",
     )
     identifier_type: Literal[ExternalIdentifierType.OPEN_ALEX] = Field(
         ExternalIdentifierType.OPEN_ALEX, description="The type of identifier used."

{destiny_sdk-0.7.5.dist-info → destiny_sdk-0.7.6.dist-info}/METADATA

@@ -1,19 +1,16 @@
 Metadata-Version: 2.4
 Name: destiny_sdk
-Version: 0.7.5
+Version: 0.7.6
 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>, Tim Repke <tim.repke@pik-potsdam.de>
 License-Expression: Apache-2.0
 License-File: LICENSE
-Requires-Python: ~=3.12
+Requires-Python: <4,>=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: msal>=1.34.0
 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
 Provides-Extra: labs
 Description-Content-Type: text/markdown

{destiny_sdk-0.7.5.dist-info → destiny_sdk-0.7.6.dist-info}/RECORD

@@ -1,9 +1,9 @@
 destiny_sdk/__init__.py,sha256=NdSlsPQyDF3TW30_JzbvYMRBRA9iT677iTRWWCMdYOA,382
 destiny_sdk/auth.py,sha256=bY72ywZEcG_67YBd9PrwgWTXkCf58rhLvVEXrtXbWtA,6247
-destiny_sdk/client.py,sha256=XJi4LXrG6C_0aWSiEE27Ehmq17dE9MdaEOidb1ki_nY,21979
+destiny_sdk/client.py,sha256=Hrsw_ofThHTy-WkmDYO2C0DLwXx4_4dEBEROXSl00dk,21925
 destiny_sdk/core.py,sha256=E0Wotu9psggK1JRJxbvx3Jc7WEGE6zaz2R2awvRrLz8,2023
-destiny_sdk/enhancements.py,sha256=79-lXOowRPC3EdM3PZPkcbnVIj5Bnbp_GIlVuEYhLkM,15707
-destiny_sdk/identifiers.py,sha256=JoJvRBzK4pGTRB03mCaGPyjd32tqZLT5hnRgc9Yi95Q,9828
+destiny_sdk/enhancements.py,sha256=oqkDu7slpQxJYBYO_xbZ8-wWmAmm5tMjYRD9NFCRY-o,17123
+destiny_sdk/identifiers.py,sha256=0D2FTR0SO_WJNfWgXVg8M1T0VmtvHGxdIsWSiuQim7U,11215
 destiny_sdk/imports.py,sha256=b-rh-dt3NsyLGxqmVzIzKaHiXhbw-3wtAaBN-ZW-i1E,5940
 destiny_sdk/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 destiny_sdk/references.py,sha256=3Y8gBMTSyZY35S3pB1bnVHMai9RRiGeoGZysNvSo7kk,2553
@@ -15,7 +15,7 @@ destiny_sdk/labs/references.py,sha256=iZisRgGZ5c7X7uTFoe6Q0AwwFMa4yJbIoPUVv_hvOi
 destiny_sdk/parsers/__init__.py,sha256=d5gS--bXla_0I7e_9wTBnGWMXt2U8b-_ndeprTPe1hk,149
 destiny_sdk/parsers/eppi_parser.py,sha256=_1xnAT0F0o1HKpMWOGQbVS3VPOrhPqyzHDWR3CosWwk,9484
 destiny_sdk/parsers/exceptions.py,sha256=0Sc_M4j560Nqh4SjeP_YrgOUVagdIwWwRz24E6YlZ1k,573
-destiny_sdk-0.7.5.dist-info/METADATA,sha256=fgalMU_UB56EZrHU-emwsc5QuSunDO0f1QEl5iMSlcU,2685
-destiny_sdk-0.7.5.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-destiny_sdk-0.7.5.dist-info/licenses/LICENSE,sha256=6QURU4gvvTjVZ5rfp5amZ6FtFvcpPhAGUjxF5WSZAHI,9138
-destiny_sdk-0.7.5.dist-info/RECORD,,
+destiny_sdk-0.7.6.dist-info/METADATA,sha256=F1diRhYTbom-cL9sROdIiItvf4v4ACm0h7rLAgP18hs,2574
+destiny_sdk-0.7.6.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+destiny_sdk-0.7.6.dist-info/licenses/LICENSE,sha256=6QURU4gvvTjVZ5rfp5amZ6FtFvcpPhAGUjxF5WSZAHI,9138
+destiny_sdk-0.7.6.dist-info/RECORD,,