pyLodStorage 0.2.12__tar.gz → 0.2.14__tar.gz

{pylodstorage-0.2.12/pylodstorage.egg-info → pylodstorage-0.2.14}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pylodstorage
-Version: 0.2.12
+Version: 0.2.14
 Summary: python List of Dict (Table) Storage library
 Home-page: https://github.com/WolfgangFahl/pyLodStorage
 Author: Wolfgang Fahl

{pylodstorage-0.2.12 → pylodstorage-0.2.14}/lodstorage/query.py

@@ -336,7 +336,7 @@ class Query(object):
             str: the "try it!" url for the given query
         '''
         # https://stackoverflow.com/a/9345102/1497139
-        quoted=urllib.parse.quote(self.query)
+        quoted=urllib.parse.quote(str(self.query))
         quoted=f"#{quoted}"
         url=f"{baseurl}/{quoted}"
         return url

{pylodstorage-0.2.12 → pylodstorage-0.2.14}/lodstorage/trulytabular.py

@@ -3,12 +3,34 @@ Created on 2022-04-14
 
 @author: wf
 '''
+import datetime
 from lodstorage.sparql import SPARQL
 from lodstorage.query import Query,QueryManager,YamlPath
+from pathlib import Path
 import os
 import textwrap
 import re
 
+class Variable:
+    '''
+    Variable e.g. name handling
+    '''
+    @classmethod
+    def validVarName(cls,varStr:str)->str:
+        '''
+        convert the given potential variable name string to a valid  
+        variable name
+        
+        see https://stackoverflow.com/a/3305731/1497139
+        
+        Args:
+            varStr(str): the string to convert
+            
+        Returns:
+            str: a valid variable name
+        '''
+        return re.sub('\W|^(?=\d)','_', varStr)
+    
 class WikidataProperty():
     '''
     a WikidataProperty
@@ -29,13 +51,13 @@ class WikidataProperty():
         get me as a Predicate
         '''
         reverseToken="^" if self.reverse else ""
-        pLabel=f"{reverseToken}wdt:{self.pid}"
-        return pLabel
+        plabel=f"{reverseToken}wdt:{self.pid}"
+        return plabel
     
     def __str__(self):
         text=self.pid
-        if hasattr(self, "label"):
-            text=f"{self.label} ({self.pid})"
+        if hasattr(self, "plabel"):
+            text=f"{self.plabel} ({self.pid})"
         return text
       
     @classmethod
@@ -115,9 +137,10 @@ SELECT ?property ?propertyLabel WHERE {
             url=record["property"]
             pid=re.sub(r"http://www.wikidata.org/entity/(.*)",r"\1",url)
             prop=WikidataProperty(pid)
-            prop.pLabel=record["propertyLabel"]
+            prop.plabel=record["propertyLabel"]
             prop.url=url
-            wdProperties[prop.pLabel]=prop
+            wdProperties[prop.plabel]=prop
+            prop.varname=Variable.validVarName(prop.plabel)
             pass
         return wdProperties
     
@@ -140,6 +163,7 @@ class WikidataItem:
         self.sparql=sparql
         if sparql is not None:
             self.qlabel,self.description=WikidataItem.getLabelAndDescription(sparql, self.qid, self.lang)
+            self.varname=Variable.validVarName(self.qlabel)
     
     def __str__(self):
         return self.asText(long=False)
@@ -238,6 +262,7 @@ WHERE {
             item=WikidataItem(qid)
             item.url=url
             item.qlabel=record["itemLabel"]
+            item.varname=Variable.validVarName(item.qlabel)
             item.description=record["itemDescription"]
             items.append(item)
         return items
@@ -274,6 +299,7 @@ class TrulyTabular(object):
         self.queryManager=TrulyTabular.getQueryManager(debug=self.debug)
         self.properties=WikidataProperty.getPropertiesByIds(self.sparql,propertyIds,lang)
         self.properties.update(WikidataProperty.getPropertiesByLabels(self.sparql, propertyLabels, lang))
+        self.isodate=datetime.datetime.now().isoformat()
         self.error=None
         
     def __str__(self):
@@ -342,6 +368,45 @@ WHERE
                 return qm
         return None
     
+    
+    def generateSparqlQuery(self,lang:str='en',naive:bool=True)->str:
+        '''
+        generate a SPARQL Query
+        '''
+        item=self.item
+        script=Path(__file__).name
+        naiveText="naive" if naive else "aggregate"
+        sparqlQuery=f"""# truly tabular {naiveText} query for 
+# {item.qid}:{item.qlabel}
+# generated by {script} on {self.isodate}
+PREFIX wd: <http://www.wikidata.org/entity/>
+PREFIX wdt: <http://www.wikidata.org/prop/direct/>
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
+SELECT ?{item.varname} ?{item.varname}Label"""
+        for wdProp in self.properties.values():
+            if naive:
+                sparqlQuery+=f"\n  ?{wdProp.varname}"
+            else:
+                sparqlQuery+=f"\n  (SAMPLE (?{wdProp.varname}) AS ?{wdProp.varname})"
+        sparqlQuery+=f"""
+WHERE {{
+  # instanceof {item.qid}:{item.qlabel}
+  ?{item.varname} wdt:P31 wd:{item.qid}.
+  # label
+  ?{item.varname} rdfs:label ?{item.varname}Label  
+  FILTER (LANG(?{item.varname}Label) = "{lang}").
+"""
+        for wdProp in self.properties.values():
+                sparqlQuery+=f"""  # {wdProp}
+  OPTIONAL {{ ?{item.varname} wdt:{wdProp.pid} ?{wdProp.varname}. }}
+"""                
+        # close where Clause
+        sparqlQuery+="""}\n"""
+        # optionally add Aggregate
+        if not naive:
+            sparqlQuery+=f"GROUP BY ?{item.varname} ?{item.varname}Label"
+        return sparqlQuery
+    
     def mostFrequentPropertiesQuery(self,whereClause:str=None):
         '''
         get the most frequently used properties
@@ -367,7 +432,7 @@ WHERE
             wdProperty(WikidataProperty): the property to analyze
             asFrequency(bool): if true do a frequency analysis
         '''
-        propertyLabel=wdProperty.pLabel
+        propertyLabel=wdProperty.plabel
         propertyId=wdProperty.pid
         # work around https://github.com/RDFLib/sparqlwrapper/issues/211
         if "described at" in propertyLabel:
@@ -436,7 +501,7 @@ ORDER BY DESC(?count)"""
             dict: a statistics row
         '''
         ntlod=self.noneTabular(wdProperty)
-        statsRow={"property":wdProperty.pLabel}
+        statsRow={"property":wdProperty.plabel}
         total=0
         nttotal=0
         maxCount=0

{pylodstorage-0.2.12 → pylodstorage-0.2.14}/lodstorage/version.py

@@ -9,7 +9,7 @@ class Version(object):
     Version handling for pyLoDStorage
     '''
     name="pylodstorage"
-    version='0.2.12'
+    version='0.2.14'
     date = '2020-09-10'
     updated = '2022-07-27'
     description='python List of Dict (Table) Storage library'

{pylodstorage-0.2.12 → pylodstorage-0.2.14/pylodstorage.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pylodstorage
-Version: 0.2.12
+Version: 0.2.14
 Summary: python List of Dict (Table) Storage library
 Home-page: https://github.com/WolfgangFahl/pyLodStorage
 Author: Wolfgang Fahl