pyLodStorage 0.4.2__tar.gz → 0.4.4__tar.gz

{pylodstorage-0.4.2/pylodstorage.egg-info → pylodstorage-0.4.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pylodstorage
-Version: 0.4.2
+Version: 0.4.4
 Summary: python List of Dict (Table) Storage library
 Home-page: https://github.com/WolfgangFahl/pyLodStorage
 Author: Wolfgang Fahl

{pylodstorage-0.4.2 → pylodstorage-0.4.4}/lodstorage/query.py

@@ -530,7 +530,7 @@ class QueryManager(object):
     @staticmethod
     def getQueries(queriesPath=None):
         '''
-        get the queries for thee given queries Path
+        get the queries for the given queries Path
         '''
         queriesPaths=YamlPath.getPaths("queries.yaml", queriesPath)
         queries={}

{pylodstorage-0.4.2 → pylodstorage-0.4.4}/lodstorage/trulytabular.py

@@ -4,9 +4,12 @@ Created on 2022-04-14
 @author: wf
 '''
 import datetime
+from typing import Union
+
 from lodstorage.sparql import SPARQL
 from lodstorage.query import Query,QueryManager,YamlPath,Endpoint
 from lodstorage.version import Version
+import logging
 from pathlib import Path
 import os
 import textwrap
@@ -141,6 +144,8 @@ SELECT ?property ?propertyLabel ?wbType WHERE {{
             prop.url=url
             wdProperties[prop.plabel]=prop
             prop.varname=Variable.validVarName(prop.plabel)
+            prop.valueVarname=f"{prop.varname}Item" if "WikibaseItem" in prop.wbtype else "" f"{prop.varname}"
+            prop.labelVarname=f"{prop.varname}"
             pass
         return wdProperties
     
@@ -166,6 +171,8 @@ class WikidataItem:
         if sparql is not None:
             self.qlabel,self.description=WikidataItem.getLabelAndDescription(sparql, self.qid, self.lang)
             self.varname=Variable.validVarName(self.qlabel)
+            self.itemVarname=f"{self.varname}Item"
+            self.labelVarname=f"{self.varname}"
     
     def __str__(self):
         return self.asText(long=False)
@@ -436,11 +443,11 @@ WHERE
 # {item.qid}:{item.qlabel}
 # generated by {script} version {Version.version} on {self.isodate}
 {WikidataItem.getPrefixes()}
-SELECT ?{item.varname} ?{item.varname}Label"""
+SELECT ?{item.itemVarname} ?{item.labelVarname}"""
         # loop over all properties
         for wdProp in self.properties.values():
             if naive:
-                sparqlQuery+=f"\n  ?{wdProp.varname}"
+                sparqlQuery+=f"\n  ?{wdProp.valueVarname}"
             else:
                 if wdProp.pid in genMap:
                     genList=genMap[wdProp.pid]
@@ -456,42 +463,44 @@ SELECT ?{item.varname} ?{item.varname}Label"""
                                     distinct="DISTINCT "
                                 aggregateFunc=aggregate.upper()
                                 aggregateParam=""
-                            sparqlQuery+=f"\n  ({aggregateFunc} ({distinct}?{wdProp.varname}{aggregateParam}) AS ?{wdProp.varname}_{aggregate})"
+                            sparqlQuery+=f"\n  ({aggregateFunc} ({distinct}?{wdProp.valueVarname}{aggregateParam}) AS ?{wdProp.valueVarname}_{aggregate})"
                         elif aggregate=="label":
-                            sparqlQuery+=f"\n  ?{wdProp.varname}Label"
-                        elif aggregate=="ignore":
-                            sparqlQuery+=f"\n  ?{wdProp.varname}"    
+                            sparqlQuery+=f"\n  ?{wdProp.labelVarname}"
+                        elif aggregate=="ignore" and not "label" in genList:
+                            sparqlQuery+=f"\n  ?{wdProp.valueVarname}"    
         sparqlQuery+=f"""
 WHERE {{
   # instanceof {item.qid}:{item.qlabel}
-  ?{item.varname} wdt:P31 wd:{item.qid}.
+  ?{item.itemVarname} wdt:P31 wd:{item.qid}.
   # label
-  ?{item.varname} rdfs:label ?{item.varname}Label.  
-  FILTER (LANG(?{item.varname}Label) = "{lang}").
+  ?{item.itemVarname} rdfs:label ?{item.labelVarname}.  
+  FILTER (LANG(?{item.labelVarname}) = "{lang}").
 """
         for wdProp in self.properties.values():
             sparqlQuery+=f"""  # {wdProp}
   OPTIONAL {{ 
-    ?{item.varname} wdt:{wdProp.pid} ?{wdProp.varname}. """
+    ?{item.itemVarname} wdt:{wdProp.pid} ?{wdProp.valueVarname}. """
             if wdProp.pid in genMap:
                 genList=genMap[wdProp.pid]
                 if "label" in genList:
-                    sparqlQuery+=f"""\n    ?{wdProp.varname} rdfs:label ?{wdProp.varname}Label."""
-                    sparqlQuery+=f"""\n    FILTER (LANG(?{wdProp.varname}Label) = "{lang}")."""
+                    sparqlQuery+=f"""\n    ?{wdProp.valueVarname} rdfs:label ?{wdProp.labelVarname}."""
+                    sparqlQuery+=f"""\n    FILTER (LANG(?{wdProp.labelVarname}) = "{lang}")."""
             sparqlQuery+="\n  }\n"
         # close where Clause
         sparqlQuery+="""}\n"""
         # optionally add Aggregate
         if not naive:
             sparqlQuery+=f"""GROUP BY
-  ?{item.varname} 
-  ?{item.varname}Label
+  ?{item.itemVarname} 
+  ?{item.labelVarname}
 """
             for wdProp in self.properties.values():
                 if wdProp.pid in genMap:
                     genList=genMap[wdProp.pid]
                     if "label" in genList:
-                        sparqlQuery+=f"\n  ?{wdProp.varname}Label"
+                        sparqlQuery+=f"\n  ?{wdProp.labelVarname}"
+                    if "ignore" in genList and not "label" in genList:
+                        sparqlQuery+=f"\n  ?{wdProp.valueVarname}"
             havingCount=0
             havingDelim="   "
             for wdProp in self.properties.values():
@@ -502,7 +511,7 @@ WHERE {{
                         if havingCount==1:
                             sparqlQuery+=f"\nHAVING ("
                             
-                        sparqlQuery+=f"\n  {havingDelim}COUNT(?{wdProp.varname})<=1"
+                        sparqlQuery+=f"\n  {havingDelim}COUNT(?{wdProp.valueVarname})<=1"
                         havingDelim="&& "
             if havingCount>0:
                 sparqlQuery+=f"\n)"
@@ -618,16 +627,24 @@ ORDER BY DESC(?count)"""
         '''
         query=self.noneTabularQuery(wdProperty)
         if self.debug:
-            print(query.query)
+            logging.info(query.query)
         qlod=self.sparql.queryAsListOfDicts(query.query)
         return qlod
     
-    def addStatsColWithPercent(self,m,col,value,total): 
+    def addStatsColWithPercent(self, m:dict, col:str, value:Union[int, float], total:Union[int, float]):
         '''
         add a statistics Column
+        Args:
+            m(dict):
+            col(str): name of the column
+            value: value
+            total: total value
         '''
         m[col]=value
-        m[f"{col}%"]=float(f"{value/total*100:.1f}") 
+        if total > 0:
+            m[f"{col}%"]=float(f"{value/total*100:.1f}")
+        else:
+            m[f"{col}%"] = None
         
     def genWdPropertyStatistic(self,wdProperty:WikidataProperty,itemCount:int,withQuery=True)->dict:
         '''

{pylodstorage-0.4.2 → pylodstorage-0.4.4}/lodstorage/version.py

@@ -9,7 +9,7 @@ class Version(object):
     Version handling for pyLoDStorage
     '''
     name="pylodstorage"
-    version='0.4.2'
+    version='0.4.4'
     date = '2020-09-10'
-    updated = '2022-08-03'
+    updated = '2022-08-04'
     description='python List of Dict (Table) Storage library'

{pylodstorage-0.4.2 → pylodstorage-0.4.4/pylodstorage.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pylodstorage
-Version: 0.4.2
+Version: 0.4.4
 Summary: python List of Dict (Table) Storage library
 Home-page: https://github.com/WolfgangFahl/pyLodStorage
 Author: Wolfgang Fahl