reformats code

scripts/blackisort

@@ -0,0 +1,7 @@
+#!/bin/bash
+# WF 2024-01-10
+package=skg
+isort tests/*.py
+black tests/*.py
+isort $package/*.py
+black $package/*.py

skg/citeproc.py

@@ -1,114 +1,117 @@
-'''
+"""
 Created on 2022-12-21
 
 @author: wf
-'''
+"""
 import datetime
+
+
 class Citeproc:
     """
     see https://en.wikipedia.org/wiki/CiteProc
     """
-    
+
     @classmethod
-    def asScite(cls,meta_data:dict,retrieved_from:str)->str:
+    def asScite(cls, meta_data: dict, retrieved_from: str) -> str:
         """
         convert the given meta data to #Scite format
-        
+
         see https://github.com/SemanticMediaWiki/SemanticCite/blob/master/src/FilteredMetadata/BibliographicFilteredRecord.php
         Args:
             meta_data(dict): the citeproc compatible metadata dict to convert
             retrieved_from(str): the url the metadata was retrieved from
-            
+
         Returns:
             str: Semantic Mediawiki markup
         """
+
         def unlist(value):
-            if type(value)!=list:
+            if type(value) != list:
                 return value
-            text=""
-            delim=""
+            text = ""
+            delim = ""
             for item in value:
-                text+=f"{delim}{item}"
-                delim=";"
-            if len(value)>1:
-                text+="|+sep=;"
+                text += f"{delim}{item}"
+                delim = ";"
+            if len(value) > 1:
+                text += "|+sep=;"
             return text
-        
+
         def firstValue(value):
-            if type(value)!=list:
+            if type(value) != list:
                 return value
             else:
                 return value[0]
-        
-        def get_author(value)->str:
+
+        def get_author(value) -> str:
             """
             get the author markup
-            
+
             Args:
                 value(list): the list to disassemble
-                
+
             Returns:
                 str: Mediawiki markup
             """
-            author=""
-            delim=""
+            author = ""
+            delim = ""
             for arec in value:
                 if "given" in arec and "family" in arec:
-                    author+= f"""{delim}{arec["given"]} {arec["family"]}"""
-                    delim=";"
+                    author += f"""{delim}{arec["given"]} {arec["family"]}"""
+                    delim = ";"
                 elif "family" in arec:
-                    author+= f"""{delim}{arec["family"]}"""
-                    delim=";"
+                    author += f"""{delim}{arec["family"]}"""
+                    delim = ";"
                 else:
                     # incomplete author record ignored
                     pass
             return author
-        
-        timestamp=datetime.datetime.utcnow().strftime('%Y-%m-%d')
-        ref_type="journal-article"
-        title=meta_data["title"]
+
+        timestamp = datetime.datetime.utcnow().strftime("%Y-%m-%d")
+        ref_type = "journal-article"
+        title = meta_data["title"]
         if type(title) is list:
-            title=title[0]
-        title_2=title.lower()[:2]
-        author_lower=""
+            title = title[0]
+        title_2 = title.lower()[:2]
+        author_lower = ""
         if "author" in meta_data:
-            first_author=firstValue(meta_data["author"])
+            first_author = firstValue(meta_data["author"])
             if "family" in first_author:
-                family=firstValue(first_author["family"])
-                author_lower=family.lower()
+                family = firstValue(first_author["family"])
+                author_lower = family.lower()
             else:
                 # debug break point
                 pass
-        year=""
+        year = ""
         if "published-print" in meta_data:
-            year=meta_data["published-print"]["date-parts"][0][0]
+            year = meta_data["published-print"]["date-parts"][0][0]
         if not year and "issued" in meta_data:
-            year=meta_data["issued"]["date-parts"][0][0]
-        reference=f"{author_lower}{year}{title_2}"
-        markup=""
-        for skey,mkey,func in [
-            ("title","title",unlist),
-            ("subtitle","subtitle",unlist),
-            ("authors","author",get_author),
-            ("journal","container-title",unlist),
-            ("publisher","publisher",str),
-            ("issn","ISSN",unlist),
-            ("subject","subject",unlist),
-            ("volume","volume",str),
-            ("pages","page",str),
-            ("doi","DOI",str)
+            year = meta_data["issued"]["date-parts"][0][0]
+        reference = f"{author_lower}{year}{title_2}"
+        markup = ""
+        for skey, mkey, func in [
+            ("title", "title", unlist),
+            ("subtitle", "subtitle", unlist),
+            ("authors", "author", get_author),
+            ("journal", "container-title", unlist),
+            ("publisher", "publisher", str),
+            ("issn", "ISSN", unlist),
+            ("subject", "subject", unlist),
+            ("volume", "volume", str),
+            ("pages", "page", str),
+            ("doi", "DOI", str),
         ]:
             if mkey in meta_data:
-                value=meta_data[mkey]
+                value = meta_data[mkey]
                 if value:
-                    value=func(value)
-                    markup+=f"\n|{skey}={value}"
-        markup=f"""{{{{#scite:
+                    value = func(value)
+                    markup += f"\n|{skey}={value}"
+        markup = f"""{{{{#scite:
 |reference={reference}
 |type={ref_type}{markup}
 |year={year}
 |retrieved-from={retrieved_from}
 |retrieved-on={timestamp}
 }}}}"""
-        full_markup=f"{title}\n[[CiteRef::{reference}]]\n{markup}"
+        full_markup = f"{title}\n[[CiteRef::{reference}]]\n{markup}"
         return full_markup

skg/crossref.py

@@ -1,58 +1,63 @@
-'''
+"""
 Created on 17.11.2022
 
 @author: wf
-'''
-import skg
+"""
 import habanero
 import habanero.cn as cn
+
+import skg
 from skg.citeproc import Citeproc
 
+
 class Crossref:
     """
     Crossref access
     """
-    
-    def __init__(self,mailto=None,ua_string=None):
+
+    def __init__(self, mailto=None, ua_string=None):
         """
         constructor
         """
         if mailto is None:
-            mailto="[email protected]"
+            mailto = "[email protected]"
         if ua_string is None:
-            ua_string=f"pysotsog/{skg.__version__} (https://pypi.org/project/pysotsog/; mailto:{mailto})"
-        #self.cr = habanero.Crossref(mailto=mailto,ua_string=ua_string)  
-        self.cr = habanero.Crossref(ua_string="")  
-    
-    def doiMetaData(self, dois:list):
-        """ 
+            ua_string = f"pysotsog/{skg.__version__} (https://pypi.org/project/pysotsog/; mailto:{mailto})"
+        # self.cr = habanero.Crossref(mailto=mailto,ua_string=ua_string)
+        self.cr = habanero.Crossref(ua_string="")
+
+    def doiMetaData(self, dois: list):
+        """
         get the meta data for the given dois
-        
+
         Args:
             doi(list): a list of dois
         """
         metadata = None
         response = self.cr.works(ids=dois)
-        if 'status' in response and 'message' in response and response['status'] == 'ok':
-            metadata = response['message']
+        if (
+            "status" in response
+            and "message" in response
+            and response["status"] == "ok"
+        ):
+            metadata = response["message"]
         return metadata
-    
-    def doiBibEntry(self,dois:list):
+
+    def doiBibEntry(self, dois: list):
         """
         get bib entries for the given dois
         """
-        bibentry=cn.content_negotiation(ids = dois, format = "bibentry")
+        bibentry = cn.content_negotiation(ids=dois, format="bibentry")
         return bibentry
-    
-    def asScite(self,meta_data:dict)->str:
+
+    def asScite(self, meta_data: dict) -> str:
         """
         convert the given meta data to #Scite format
-        
+
         see https://github.com/SemanticMediaWiki/SemanticCite/blob/master/src/FilteredMetadata/BibliographicFilteredRecord.php
-        
+
         Returns:
             str: Semantic Mediawiki markup
         """
-        markup=Citeproc.asScite(meta_data,retrieved_from=self.cr.base_url)
+        markup = Citeproc.asScite(meta_data, retrieved_from=self.cr.base_url)
         return markup
-

skg/dblp.py

@@ -1,42 +1,51 @@
-'''
+"""
 Created on 2022-11-17
 
 @author: wf
-'''
+"""
 from lodstorage.sparql import SPARQL
+
 from skg.owl import Owl
 
+
 class Dblp:
     """
     Schloss Dagstuhl Dblp computer science bibliography
     """
-    
-    def __init__(self,endpoint:str="https://qlever.cs.uni-freiburg.de/api/dblp"):
+
+    def __init__(self, endpoint: str = "https://qlever.cs.uni-freiburg.de/api/dblp"):
         """
         constructor
-        
+
         Args:
             endpoint(str): the endpoint to use
         """
-        self.endpoint=endpoint
-        self.schema=Owl("dblp","https://dblp.org/rdf/schema", "Wolfgang Fahl","2022-11-19")
-        self.sparql=SPARQL(self.endpoint)
-
-
-    def get_paper_records(self,regex:str,prop_name:str="title",limit:int=100,debug:bool=False)->list:
+        self.endpoint = endpoint
+        self.schema = Owl(
+            "dblp", "https://dblp.org/rdf/schema", "Wolfgang Fahl", "2022-11-19"
+        )
+        self.sparql = SPARQL(self.endpoint)
+
+    def get_paper_records(
+        self,
+        regex: str,
+        prop_name: str = "title",
+        limit: int = 100,
+        debug: bool = False,
+    ) -> list:
         """
         get papers fitting the given regex
-        
+
         Args:
             prop_name(str): the property to filter
             regex(str): the regex to filter for
             limit(int): the maximum number of records to return
             debug(bool): if True show debug information
-            
+
         Returns:
             list: a list of dict of paper records
         """
-        sparql_query="""PREFIX dblp: <https://dblp.org/rdf/schema#>
+        sparql_query = """PREFIX dblp: <https://dblp.org/rdf/schema#>
 PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
 SELECT
   ?paper 
@@ -58,8 +67,8 @@ def get_paper_records(self,regex:str,prop_name:str="title",limit:int=100,debug:b
   ?paper dblp:yearOfPublication ?year.
   OPTIONAL { ?paper dblp:monthOfPublication ?month}.
 """
-        sparql_query+=f"""FILTER regex(?{prop_name}, "{regex}").\n"""
-        sparql_query+=f"""
+        sparql_query += f"""FILTER regex(?{prop_name}, "{regex}").\n"""
+        sparql_query += f"""
 }}
 GROUP BY 
   ?paper 
@@ -74,11 +83,11 @@ def get_paper_records(self,regex:str,prop_name:str="title",limit:int=100,debug:b
 LIMIT {limit}"""
         if debug:
             print(sparql_query)
-        records=self.sparql.queryAsListOfDicts(sparql_query)
+        records = self.sparql.queryAsListOfDicts(sparql_query)
         return records
-    
-    def get_random_papers(self,year:int=2020,limit:int=10):
-        sparql_query=f"""PREFIX dblp: <https://dblp.org/rdf/schema#>
+
+    def get_random_papers(self, year: int = 2020, limit: int = 10):
+        sparql_query = f"""PREFIX dblp: <https://dblp.org/rdf/schema#>
 SELECT 
   ?paper 
   (SAMPLE(?doi_o) as ?doi)
@@ -100,4 +109,3 @@ def get_random_papers(self,year:int=2020,limit:int=10):
 ORDER BY ?sortKey 
 LIMIT {limit}
         """
-

skg/dblp2wikidata.py

@@ -0,0 +1,26 @@
+"""
+Created on 2024-02-26
+
+@author: wf
+"""
+from argparse import Namespace
+
+class Dblp2Wikidata:
+    """
+    utility to transfering Dblp person entries to Wikidata
+    """
+
+    def __init__(self,debug:bool=False):
+        self.debug=debug
+        pass
+
+    def transfer(self, args:Namespace):
+        """
+        Main method to handle the transfer of DBLP entries to Wikidata.
+        
+        Args:
+            args(Namespace): Command line arguments.
+        """
+        search_term = getattr(args, 'dblp2wikidata', None)
+        if self.debug:
+            print(f"trying to transfer DBLP person entry for {search_term}")