fix: Fix issues with typing annotation and mypy (#18)

Author: xmnlab

.github/workflows/main.yaml

@@ -53,7 +53,7 @@ jobs:
         shell: bash -l {0}
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - uses: conda-incubator/setup-miniconda@v3
         with:
@@ -69,9 +69,19 @@ jobs:
         run: |
           poetry install
 
+      - name: Create .env file
+        env:
+          NCBI_API_KEY: ${{ secrets.NCBI_API_KEY }}
+          SERVICE_EMAIL: ${{ secrets.SERVICE_EMAIL }}
+        run: |
+          pushd tests
+          envsubst < .env.tpl > .env
+          popd
+
       - name: Run tests
         env:
           NCBI_API_KEY: ${{ secrets.NCBI_API_KEY }}
+          SERVICE_EMAIL: ${{ secrets.SERVICE_EMAIL }}
         run: makim tests.unittest
 
   linter-and-docs:

.pre-commit-config.yaml

@@ -46,13 +46,13 @@ repos:
         types:
           - python
 
-      # - id: mypy
-      #   name: mypy
-      #   entry: mypy .
-      #   language: system
-      #   pass_filenames: false
-      #   types:
-      #     - python
+      - id: mypy
+        name: mypy
+        entry: mypy .
+        language: system
+        pass_filenames: false
+        types:
+          - python
 
       - id: shellcheck
         name: shellcheck

pyproject.toml

@@ -108,13 +108,12 @@ quote-style = "double"
 
 [tool.mypy]
 python_version = "3.9"
-no_strict_optional = false
-# check_untyped_defs = true
-# strict = true
-# ignore_missing_imports = true
-# warn_unused_ignores = true
-# warn_redundant_casts = true
-# warn_unused_configs = true
+check_untyped_defs = true
+strict = true
+ignore_missing_imports = true
+warn_unused_ignores = true
+warn_redundant_casts = true
+warn_unused_configs = true
 exclude = [
   '^docs/$',
   '^examples/$',

src/pymedx/__init__.py

@@ -6,7 +6,7 @@
 from .api import PubMed, PubMedCentral
 
 
-def get_version():
+def get_version() -> str:
     """Return the program version."""
     try:
         return importlib_metadata.version(__name__)

src/pymedx/api.py

@@ -8,16 +8,16 @@
 import time
 
 from copy import copy
-from typing import Any, Dict, Generator, Iterable, Iterator, cast
+from typing import Any, Dict, Generator, Iterator, cast
 
 import requests
 
 from lxml import etree as xml
 from typeguard import typechecked
 
-from .article import PubMedArticle, PubMedCentralArticle
-from .book import PubMedBookArticle
-from .helpers import (
+from pymedx.article import PubMedArticle, PubMedCentralArticle
+from pymedx.book import PubMedBookArticle
+from pymedx.helpers import (
     arrange_query,
     batches,
     get_range_date_from_query,
@@ -248,7 +248,7 @@ def _get(
 
                 # Return the response
                 if output == "json":
-                    return response.json()
+                    return cast(Dict[str, Any], response.json())
                 else:
                     return response.text
 
@@ -262,7 +262,10 @@ def _get(
         )
 
     def _getArticleIdsMonth(
-        self, search_term, range_begin_date, range_end_date
+        self,
+        search_term: str,
+        range_begin_date: datetime.date,
+        range_end_date: datetime.date,
     ) -> list[str]:
         article_ids = []
         range_dates_month = get_range_months(range_begin_date, range_end_date)
@@ -500,7 +503,7 @@ def query(
         self,
         query: str,
         max_results: int = 100,
-    ) -> Iterable[PubMedArticle | PubMedBookArticle | PubMedCentralArticle]:
+    ) -> Iterator[PubMedArticle | PubMedBookArticle | PubMedCentralArticle]:
         """
         Execute a query agains the GraphQL schema.
 
@@ -631,16 +634,20 @@ def _getArticleIds(
 
     def _getArticles(
         self, article_ids: list[str]
-    ) -> Iterable[PubMedArticle | PubMedBookArticle | PubMedCentralArticle]:
+    ) -> Generator[
+        PubMedArticle | PubMedBookArticle | PubMedCentralArticle, None, None
+    ]:
         """Batch a list of article IDs and retrieves the content.
 
         Parameters
         ----------
-            - article_ids   List, article IDs.
+        article_ids: List
+            article IDs.
 
         Returns
         -------
-            - articles      List, article objects.
+        articles: List
+            article objects.
         """
         # Get the default parameters
         parameters = self.parameters.copy()

src/pymedx/article.py

@@ -5,7 +5,7 @@
 import datetime
 import json
 
-from typing import Any, Dict, List, Optional, Union, cast
+from typing import Any, Dict, List, Optional
 
 from lxml.etree import _Element
 from typeguard import typechecked
@@ -52,11 +52,11 @@ def __init__(
             for field in self.__slots__:
                 self.__setattr__(field, kwargs.get(field, None))
 
-    def _extractPubMedId(self, xml_element: _Element) -> Union[str, None, int]:
+    def _extractPubMedId(self, xml_element: _Element) -> Optional[str]:
         path = ".//PMID"
         return getContentUnique(element=xml_element, path=path)
 
-    def _extractTitle(self, xml_element: _Element) -> Union[str, None, int]:
+    def _extractTitle(self, xml_element: _Element) -> Optional[str]:
         path = ".//ArticleTitle"
         return getAllContent(element=xml_element, path=path)
 
@@ -68,35 +68,32 @@ def _extractKeywords(self, xml_element: _Element) -> List[Any]:
             if keyword is not None
         ]
 
-    def _extractJournal(self, xml_element: _Element) -> Union[str, None, int]:
+    def _extractJournal(self, xml_element: _Element) -> Optional[str]:
         path = ".//Journal/Title"
         return getContent(element=xml_element, path=path)
 
-    def _extractAbstract(self, xml_element: _Element) -> Union[str, None, int]:
+    def _extractAbstract(self, xml_element: _Element) -> Optional[str]:
         path = ".//AbstractText"
-        return getAbstract(element=xml_element, path=path)
+        abstract = getAbstract(element=xml_element, path=path)
+        return abstract
 
-    def _extractConclusions(
-        self, xml_element: _Element
-    ) -> Union[str, None, int]:
+    def _extractConclusions(self, xml_element: _Element) -> Optional[str]:
         path = ".//AbstractText[@Label='CONCLUSION']"
         return getContent(element=xml_element, path=path)
 
-    def _extractMethods(self, xml_element: _Element) -> Union[str, None, int]:
+    def _extractMethods(self, xml_element: _Element) -> Optional[str]:
         path = ".//AbstractText[@Label='METHOD']"
         return getContent(element=xml_element, path=path)
 
-    def _extractResults(self, xml_element: _Element) -> Union[str, None, int]:
+    def _extractResults(self, xml_element: _Element) -> Optional[str]:
         path = ".//AbstractText[@Label='RESULTS']"
         return getContent(element=xml_element, path=path)
 
-    def _extractCopyrights(
-        self, xml_element: _Element
-    ) -> Union[str, None, int]:
+    def _extractCopyrights(self, xml_element: _Element) -> Optional[str]:
         path = ".//CopyrightInformation"
         return getContent(element=xml_element, path=path)
 
-    def _extractDoi(self, xml_element: _Element) -> Union[str, None, int]:
+    def _extractDoi(self, xml_element: _Element) -> Optional[str]:
         path = ".//ArticleId[@IdType='doi']"
         return getContentUnique(element=xml_element, path=path)
 
@@ -128,7 +125,7 @@ def _extractPublicationDate(
 
     def _extractAuthors(
         self, xml_element: _Element
-    ) -> List[dict[str, Union[str, None, int]]]:
+    ) -> List[dict[str, Optional[str]]]:
         return [
             {
                 "lastname": getContent(author, ".//LastName", None),
@@ -145,15 +142,15 @@ def _initializeFromXML(self, xml_element: _Element) -> None:
         """Parse an XML element into an article object."""
         # Parse the different fields of the article
         self.pubmed_id = self._extractPubMedId(xml_element)
-        self.title = cast(str, self._extractTitle(xml_element))
+        self.title = self._extractTitle(xml_element)
         self.keywords = self._extractKeywords(xml_element)
-        self.journal = cast(str, self._extractJournal(xml_element))
-        self.abstract = cast(str, self._extractAbstract(xml_element) or "")
-        self.conclusions = cast(str, self._extractConclusions(xml_element))
-        self.methods = cast(str, self._extractMethods(xml_element))
-        self.results = cast(str, self._extractResults(xml_element))
-        self.copyrights = cast(str, self._extractCopyrights(xml_element))
-        self.doi = cast(str, self._extractDoi(xml_element))
+        self.journal = self._extractJournal(xml_element)
+        self.abstract = self._extractAbstract(xml_element) or ""
+        self.conclusions = self._extractConclusions(xml_element)
+        self.methods = self._extractMethods(xml_element)
+        self.results = self._extractResults(xml_element)
+        self.copyrights = self._extractCopyrights(xml_element)
+        self.doi = self._extractDoi(xml_element)
         self.publication_date = self._extractPublicationDate(xml_element)
         self.authors = self._extractAuthors(xml_element)
         self.xml = xml_element
@@ -230,11 +227,11 @@ def __init__(
             for field in self.__slots__:
                 self.__setattr__(field, kwargs.get(field, None))
 
-    def _extractPMCId(self, xml_element: _Element) -> Union[str, None, int]:
+    def _extractPMCId(self, xml_element: _Element) -> Optional[str]:
         path = ".//article-meta/article-id[@pub-id-type='pmc']"
         return getContentUnique(element=xml_element, path=path)
 
-    def _extractTitle(self, xml_element: _Element) -> Union[str, None, int]:
+    def _extractTitle(self, xml_element: _Element) -> Optional[str]:
         path = ".//title-group"
         return getAllContent(element=xml_element, path=path)
 
@@ -248,38 +245,38 @@ def _extractTitle(self, xml_element: _Element) -> Union[str, None, int]:
     #     ]
     # TODO: adapt the function for PubMed Central
     # def _extractJournal
-    # (self, xml_element: _Element) -> Union[str, None, int]:
+    # (self, xml_element: _Element) -> Optional[str]:
     #     path = ".//Journal/Title"
     #     return getContent(element=xml_element, path=path)
 
-    def _extractAbstract(self, xml_element: _Element) -> Union[str, None, int]:
+    def _extractAbstract(self, xml_element: _Element) -> Optional[str]:
         path = ".//abstract"
         return getAllContent(element=xml_element, path=path)
 
     # TODO: adapt the function for PubMed Central
     # def _extractConclusions(
     #     self, xml_element: _Element
-    # ) -> Union[str, None, int]:
+    # ) -> Optional[str]:
     #     path = ".//AbstractText[@Label='CONCLUSION']"
     #     return getContent(element=xml_element, path=path)
     # TODO: adapt the function for PubMed Central
     # def _extractMethods(self, xml_element: _Element)
-    # -> Union[str, None, int]:
+    # -> Optional[str]:
     #     path = ".//AbstractText[@Label='METHOD']"
     #     return getContent(element=xml_element, path=path)
     # TODO: adapt the function for PubMed Central
     # def _extractResults(self, xml_element: _Element)
-    # -> Union[str, None, int]:
+    # -> Optional[str]:
     #     path = ".//AbstractText[@Label='RESULTS']"
     #     return getContent(element=xml_element, path=path)
     # TODO: adapt the function for PubMed Central
     # def _extractCopyrights(
     #     self, xml_element: _Element
-    # ) -> Union[str, None, int]:
+    # ) -> Optional[str]:
     #     path = ".//CopyrightInformation"
     #     return getContent(element=xml_element, path=path)
 
-    def _extractDoi(self, xml_element: _Element) -> Union[str, None, int]:
+    def _extractDoi(self, xml_element: _Element) -> Optional[str]:
         path = ".//article-meta/article-id[@pub-id-type='doi']"
         return getContentUnique(element=xml_element, path=path)
 
@@ -318,7 +315,7 @@ def _extractPublicationDate(
 
     def _extractAuthors(
         self, xml_element: _Element
-    ) -> List[dict[str, Union[str, None, int]]]:
+    ) -> List[dict[str, Optional[str]]]:
         contrib_group = xml_element.findall(".//contrib-group")
         if contrib_group:
             return [