publication lookup edits post feedback startup refactor and constants sorted

mpanday-deakin · mpanday-deakin · commit df679209105b · 2025-02-12T18:42:47.000+11:00
diff --git a/pybliometrics/scival/publication_lookup.py b/pybliometrics/scival/publication_lookup.py
@@ -1,3 +1,4 @@
+"""Module with the PublicationLookup class."""
 from collections import namedtuple
 from typing import Union, Optional
 
@@ -14,51 +15,52 @@ def id(self) -> Optional[int]:
 
     @property
     def title(self) -> Optional[str]:
-        """Publication title"""
+        """Publication title."""
         return chained_get(self._json, ['publication', 'title'])
 
     @property
     def doi(self) -> Optional[str]:
-        """Digital Object Identifier (DOI)"""
+        """Digital Object Identifier (DOI)."""
         return chained_get(self._json, ['publication', 'doi'])
 
     @property
     def type(self) -> Optional[str]:
-        """Type of publication"""
+        """Type of publication."""
         return chained_get(self._json, ['publication', 'type'])
 
     @property
     def publication_year(self) -> Optional[int]:
-        """Year of publication"""
+        """Year of publication."""
         return make_int_if_possible(chained_get(self._json, ['publication', 'publicationYear']))
 
     @property
     def citation_count(self) -> Optional[int]:
-        """Count of citations"""
+        """Count of citations."""
         return make_int_if_possible(chained_get(self._json, ['publication', 'citationCount']))
 
     @property
     def source_title(self) -> Optional[str]:
-        """Title of source"""
+        """Title of source."""
         return chained_get(self._json, ['publication', 'sourceTitle'])
 
     @property
     def topic_id(self) -> Optional[int]:
-        """Topic id"""
+        """Topic id."""
         return make_int_if_possible(chained_get(self._json, ['publication', 'topicId']))
 
     @property
     def topic_cluster_id(self) -> Optional[int]:
-        """Topic cluster id"""
+        """Topic cluster id."""
         return make_int_if_possible(chained_get(self._json, ['publication', 'topicClusterId']))
 
     @property
     def link(self) -> Optional[str]:
-        """URL link"""
+        """URL link."""
         return chained_get(self._json, ['link', '@href'])
 
     @property
     def authors(self) -> Optional[list[namedtuple]]:
+        """Publication authors."""
         out = []
         fields = 'id name link'
         auth = namedtuple('Author', fields)
@@ -70,50 +72,49 @@ def authors(self) -> Optional[list[namedtuple]]:
 
     @property
     def institutions(self) -> Optional[list[namedtuple]]:
+        """Institutions linked to publication authors."""
         out = []
         fields = 'id name country country_code link'
         auth = namedtuple('Institution', fields)
         for item in chained_get(self._json, ['publication', 'institutions'], []):
-            new = auth(id=make_int_if_possible(item['id']), name=item.get('name'),
-                       country=item.get('country'), country_code=item.get('countryCode'),
-                       link=chained_get(item, ['link', '@href']))
+            new = auth(id=make_int_if_possible(item['id']), name=item.get('name'), country=item.get('country'),
+                       country_code=item.get('countryCode'), link=chained_get(item, ['link', '@href']))
             out.append(new)
         return out or None
 
     @property
     def sdgs(self) -> Optional[list[str]]:
-        """Sustainable Development Goals."""
+        """List of Sustainable Development Goals (SDG)."""
         return chained_get(self._json, ['publication', 'sdg'])
 
     def __str__(self):
         """Print a summary string."""
         authors = ', '.join(a.name for a in self.authors) if self.authors else "N/A"
         institutions = ', '.join(i.name for i in self.institutions) if self.institutions else "N/A"
         sdgs = ', '.join(self.sdgs) if self.sdgs else "N/A"
-        s = (
-            f"Publication Summary:\n"
-            f"- ID: {self.id or 'N/A'}\n"
-            f"- Title: {self.title or 'N/A'}\n"
-            f"- DOI: {self.doi or 'N/A'}\n"
-            f"- Type: {self.type or 'N/A'}\n"
-            f"- Year: {self.publication_year or 'N/A'}\n"
-            f"- Citation Count: {self.citation_count or 'N/A'}\n"
-            f"- Source Title: {self.source_title or 'N/A'}\n"
-            f"- Topic ID: {self.topic_id or 'N/A'}\n"
-            f"- Topic Cluster ID: {self.topic_cluster_id or 'N/A'}\n"
-            f"- Link: {self.link or 'N/A'}\n"
-            f"- Authors: {authors}\n"
-            f"- Institutions: {institutions}\n"
-            f"- SDGs: {sdgs}\n"
-        )
+        s = (f"Publication Summary:\n"
+             f"- ID: {self.id or 'N/A'}\n"
+             f"- Title: {self.title or 'N/A'}\n"
+             f"- DOI: {self.doi or 'N/A'}\n"
+             f"- Type: {self.type or 'N/A'}\n"
+             f"- Year: {self.publication_year or 'N/A'}\n"
+             f"- Citation Count: {self.citation_count or 'N/A'}\n"
+             f"- Source Title: {self.source_title or 'N/A'}\n"
+             f"- Topic ID: {self.topic_id or 'N/A'}\n"
+             f"- Topic Cluster ID: {self.topic_cluster_id or 'N/A'}\n"
+             f"- Link: {self.link or 'N/A'}\n"
+             f"- Authors: {authors}\n"
+             f"- Institutions: {institutions}\n"
+             f"- SDGs: {sdgs}\n")
         return s
 
-    def __init__(self,
-                 identifier: int = None,
-                 refresh: Union[bool, int] = False,
-                 **kwds: str
-                 ) -> None:
+    def __init__(self, identifier: int = None, refresh: Union[bool, int] = False, **kwds: str) -> None:
         """Interaction with the Publication Lookup API.
+        :param identifier: The Scopus ID of the object.
+        :param refresh: Whether to refresh the cached file if it exists. Default: `False`.
+        :param kwds: Keywords passed on to requests header.  Must contain
+                     fields and values specified in the respective
+                     API specification.
                 """
         self._view = ''
         self._refresh = refresh
diff --git a/pybliometrics/scival/tests/test_PublicationLookup.py b/pybliometrics/scival/tests/test_PublicationLookup.py
@@ -1,3 +1,5 @@
+"""Tests for the PublicationLookup() class."""
+
 from pybliometrics.scival import PublicationLookup
 from pybliometrics.utils import init
 
@@ -7,20 +9,50 @@
 pub1 = PublicationLookup(85036568406)
 
 
-def test_publication():
+def test_publication_id():
     assert pub1.id == 85036568406
+
+
+def test_publication_doi():
     assert pub1.doi == "10.1002/anie.201709271"
+
+
+def test_publication_type():
     assert pub1.type == "Article"
+
+
+def test_publication_year():
     assert pub1.publication_year == 2017
+
+
+def test_publication_source_title():
     assert pub1.source_title == 'Angewandte Chemie - International Edition'
+
+
+def test_publication_citation_count():
     assert pub1.citation_count > 0
+
+
+def test_publication_authors_count():
     assert len(pub1.authors) >= 7
+
+
+def test_publication_first_author():
     assert pub1.authors[0].id == 7404861905
     assert pub1.authors[0].name == "Lin, T.-E."
+
+
+def test_publication_institutions_count():
     assert len(pub1.institutions) >= 3
+
+
+def test_publication_first_institution():
     assert pub1.institutions[0].id == 217002
     assert pub1.institutions[0].name == "Chang Gung University"
     assert pub1.institutions[0].country == "Taiwan"
     assert pub1.institutions[0].country_code == "TWN"
+
+
+def test_publication_sdgs():
     assert len(pub1.sdgs) >= 1
-    assert pub1.sdgs[0] == 'SDG 3: Good Health and Well-being'
+    assert pub1.sdgs[0] == 'SDG 3: Good Health and Well-being'
diff --git a/pybliometrics/superclasses/retrieval.py b/pybliometrics/superclasses/retrieval.py
@@ -47,5 +47,7 @@ def __init__(self,
         self._cache_file_path = parent/self._view/stem
 
         # Parse file contents
-        params = {'view': self._view, **kwds}
+        params = {**kwds}
+        if self._view:
+            params['view'] = self._view
         Base.__init__(self, params=params, url=url)
diff --git a/pybliometrics/utils/constants.py b/pybliometrics/utils/constants.py
@@ -26,21 +26,20 @@
     'AbstractRetrieval': BASE_PATH_SCOPUS / 'abstract_retrieval',
     'AffiliationRetrieval': BASE_PATH_SCOPUS / 'affiliation_retrieval',
     'AffiliationSearch': BASE_PATH_SCOPUS / 'affiliation_search',
+    'ArticleEntitlement': BASE_PATH_SCIENCEDIRECT / 'article_entitlement',
+    'ArticleMetadata': BASE_PATH_SCIENCEDIRECT / 'article_metadata / ',
+    'ArticleRetrieval': BASE_PATH_SCIENCEDIRECT / 'article_retrieval',
     'AuthorRetrieval': BASE_PATH_SCOPUS / 'author_retrieval',
     'AuthorSearch': BASE_PATH_SCOPUS / 'author_search',
     'CitationOverview': BASE_PATH_SCOPUS / 'citation_overview',
+    'PlumXMetrics': BASE_PATH_SCOPUS / 'plumx',
+    'PublicationLookup': BASE_PATH_SCIVAL / 'publication_lookup',
+    'ScDirSubjectClassifications': BASE_PATH_SCIENCEDIRECT / 'subject_classification',
+    'ScienceDirectSearch': BASE_PATH_SCIENCEDIRECT / 'science_direct_search',
     'ScopusSearch': BASE_PATH_SCOPUS / 'scopus_search',
     'SerialSearch': BASE_PATH_SCOPUS / 'serial_search',
     'SerialTitle': BASE_PATH_SCOPUS / 'serial_title',
-    'PlumXMetrics': BASE_PATH_SCOPUS / 'plumx',
     'SubjectClassifications': BASE_PATH_SCOPUS / 'subject_classification',
-    'ArticleEntitlement': BASE_PATH_SCIENCEDIRECT / 'article_entitlement',
-    'ArticleMetadata': BASE_PATH_SCIENCEDIRECT / 'article_metadata / ',
-    'ArticleRetrieval': BASE_PATH_SCIENCEDIRECT / 'article_retrieval',
-    'ScienceDirectSearch': BASE_PATH_SCIENCEDIRECT / 'science_direct_search',
-    'ScDirSubjectClassifications': BASE_PATH_SCIENCEDIRECT / 'subject_classification',
-
-    'PublicationLookup': BASE_PATH_SCIVAL / 'publication_lookup',
 }
 
 # URLs for all classes
@@ -53,66 +52,61 @@
     'AbstractRetrieval': RETRIEVAL_BASE + 'abstract/',
     'AffiliationRetrieval': RETRIEVAL_BASE + 'affiliation/affiliation_id/',
     'AffiliationSearch': SEARCH_BASE + 'affiliation',
+    'ArticleEntitlement': RETRIEVAL_BASE + 'article/entitlement/',
+    'ArticleMetadata': RETRIEVAL_BASE + 'metadata/article/',
+    'ArticleRetrieval': RETRIEVAL_BASE + 'article/',
     'AuthorRetrieval': RETRIEVAL_BASE + 'author/author_id/',
     'AuthorSearch': SEARCH_BASE + 'author',
     'CitationOverview': RETRIEVAL_BASE + 'abstract/citations/',
+    'PlumXMetrics': 'https://api.elsevier.com/analytics/plumx/',
+    'PublicationLookup': SCIVAL_BASE + 'publication/',
     'ScopusSearch': SEARCH_BASE + 'scopus',
+    'ScienceDirectSearch': SEARCH_BASE + 'sciencedirect/',
+    'ScDirSubjectClassifications': RETRIEVAL_BASE + 'subject/scidir/',
     'SerialSearch': RETRIEVAL_BASE + 'serial/title',
     'SerialTitle': RETRIEVAL_BASE + 'serial/title/issn/',
     'SubjectClassifications': RETRIEVAL_BASE + 'subject/scopus',
-    'PlumXMetrics': 'https://api.elsevier.com/analytics/plumx/',
-    'ArticleEntitlement': RETRIEVAL_BASE + 'article/entitlement/',
-    'ArticleMetadata': RETRIEVAL_BASE + 'metadata/article/',
-    'ArticleRetrieval': RETRIEVAL_BASE + 'article/',
-    'ScienceDirectSearch': SEARCH_BASE + 'sciencedirect/',
-    'ScDirSubjectClassifications': RETRIEVAL_BASE + 'subject/scidir/',
-
-    'PublicationLookup': SCIVAL_BASE + 'publication/',
-    'PublicationMetrics': SCIVAL_BASE + 'publication/metrics/'
 }
 
 # Valid views for all classes
 VIEWS = {
-    "CitationOverview": ["STANDARD"],
     "AbstractRetrieval": ["META", "META_ABS", "FULL", "REF", "ENTITLED"],
     "AffiliationRetrieval": ["LIGHT", "STANDARD", "ENTITLED"],
     "AffiliationSearch": ["STANDARD"],
+    "ArticleEntitlement": ["FULL"],
+    "ArticleMetadata": ["STANDARD", "COMPLETE"],
+    "ArticleRetrieval": ["META", "META_ABS", "META_ABS_REF", "FULL", "ENTITLED"],
     "AuthorRetrieval": ["LIGHT", "STANDARD", "ENHANCED", "METRICS", "ENTITLED"],
     "AuthorSearch": ["STANDARD"],
+    "CitationOverview": ["STANDARD"],
     "PlumXMetrics": ["ENHANCED"],
+    "ScDirSubjectClassifications": [''],
+    "ScienceDirectSearch": ["STANDARD"],
     "ScopusSearch": ["STANDARD", "COMPLETE"],
     "SerialSearch": ["STANDARD", "ENHANCED", "CITESCORE"],
     "SerialTitle": ["STANDARD", "ENHANCED", "CITESCORE"],
     "SubjectClassifications": [''],
-    "ArticleEntitlement": ["FULL"],
-    "ArticleRetrieval": ["META", "META_ABS", "META_ABS_REF", "FULL", "ENTITLED"],
-    "ArticleMetadata": ["STANDARD", "COMPLETE"],
-    "ScienceDirectSearch": ["STANDARD"],
-    "ScDirSubjectClassifications": [''],
-
-    "PublicationLookup": ['']
 }
 
 # Throttling limits (in queries per second) // 0 = no limit
 RATELIMITS = {
     'AbstractRetrieval': 9,
     'AffiliationRetrieval': 9,
     'AffiliationSearch': 6,
+    'ArticleEntitlement': 0,
+    'ArticleMetadata': 6,
+    'ArticleRetrieval': 10,
     'AuthorRetrieval': 3,
     'AuthorSearch': 2,
     'CitationOverview': 4,
+    'PlumXMetrics': 6,
+    'PublicationLookup': 6,
+    'ScDirSubjectClassifications': 0,
+    'ScienceDirectSearch': 2,
     'ScopusSearch': 9,
     'SerialSearch': 6,
     'SerialTitle': 6,
-    'PlumXMetrics': 6,
     'SubjectClassifications': 0,
-    'ArticleEntitlement': 0,
-    'ArticleMetadata': 6,
-    'ArticleRetrieval': 10,
-    'ScienceDirectSearch': 2,
-    'ScDirSubjectClassifications': 0,
-
-    'PublicationLookup': 6
 }
 
 # Other API restrictions
diff --git a/pybliometrics/utils/startup.py b/pybliometrics/utils/startup.py
@@ -114,9 +114,13 @@ def check_keys_tokens() -> None:
 def create_cache_folders(config: Type[ConfigParser]) -> None:
     """Auxiliary function to create cache folders."""
     for api, path in config.items('Directories'):
-        for view in VIEWS[api]:
-            view_path = Path(path, view)
-            view_path.mkdir(parents=True, exist_ok=True)
+        base_dir = Path(path)
+        views = VIEWS.get(api, [])
+        if views:
+            for view in views:
+                (base_dir / view).mkdir(parents=True, exist_ok=True)
+        else:
+            base_dir.mkdir(parents=True, exist_ok=True)
 
 
 def get_config() -> Type[ConfigParser]:
