pyLodStorage 0.2.14__tar.gz → 0.3.0__tar.gz

{pylodstorage-0.2.14/pylodstorage.egg-info → pylodstorage-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pylodstorage
-Version: 0.2.14
+Version: 0.3.0
 Summary: python List of Dict (Table) Storage library
 Home-page: https://github.com/WolfgangFahl/pyLodStorage
 Author: Wolfgang Fahl

{pylodstorage-0.2.14 → pylodstorage-0.3.0}/lodstorage/trulytabular.py

@@ -6,11 +6,13 @@ Created on 2022-04-14
 import datetime
 from lodstorage.sparql import SPARQL
 from lodstorage.query import Query,QueryManager,YamlPath
+from lodstorage.version import Version
 from pathlib import Path
 import os
 import textwrap
 import re
 
+
 class Variable:
     '''
     Variable e.g. name handling
@@ -368,43 +370,81 @@ WHERE
                 return qm
         return None
     
-    
-    def generateSparqlQuery(self,lang:str='en',naive:bool=True)->str:
+    def generateSparqlQuery(self,genMap:dict,listSeparator:str="⇹",naive:bool=True,lang:str='en')->str:
         '''
         generate a SPARQL Query
+        
+        Args:
+            genMap(dict): a dictionary of generation items aggregates/ignores/labels
+            listSeparator(str): the symbole to use as a list separator for GROUP_CONCAT
+            naive(bool): if True - generate a naive straight forward SPARQL query
+                if False generate a proper truly tabular aggregate query
+            lang(str): the language to generate for
+            
+        Returns:
+            str: the generated SPARQL Query
         '''
+        # The Wikidata item to generate the query for
         item=self.item
+        # the name of this script
         script=Path(__file__).name
+        # the mode of generation
         naiveText="naive" if naive else "aggregate"
+        # start with th preamble and PREFIX section
+        # select the item and it's label
         sparqlQuery=f"""# truly tabular {naiveText} query for 
 # {item.qid}:{item.qlabel}
-# generated by {script} on {self.isodate}
+# generated by {script} version {Version.version} 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"""
+        # loop over all properties
         for wdProp in self.properties.values():
             if naive:
                 sparqlQuery+=f"\n  ?{wdProp.varname}"
             else:
-                sparqlQuery+=f"\n  (SAMPLE (?{wdProp.varname}) AS ?{wdProp.varname})"
+                if wdProp.pid in genMap:
+                    genList=genMap[wdProp.pid]
+                    for aggregate in genList:
+                        if not aggregate in ["ignore","label"]:
+                            if aggregate=="list": 
+                                aggregateFunc="GROUP_CONCAT"
+                                aggregateParam=f';SEPARATOR="{listSeparator}"'
+                            else:
+                                aggregateFunc=aggregate.upper()
+                                aggregateParam=""
+                            sparqlQuery+=f"\n  ({aggregateFunc} (?{wdProp.varname}{aggregateParam}) AS ?{wdProp.varname}_{aggregate})"
+                        elif aggregate=="label":
+                            sparqlQuery+=f"\n  ?{wdProp.varname}Label"
         sparqlQuery+=f"""
 WHERE {{
   # instanceof {item.qid}:{item.qlabel}
   ?{item.varname} wdt:P31 wd:{item.qid}.
   # label
-  ?{item.varname} rdfs:label ?{item.varname}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}. }}
-"""                
+            sparqlQuery+=f"""  # {wdProp}
+  OPTIONAL {{ 
+    ?{item.varname} wdt:{wdProp.pid} ?{wdProp.varname}. """
+            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+="\n  }\n"
         # close where Clause
         sparqlQuery+="""}\n"""
         # optionally add Aggregate
         if not naive:
             sparqlQuery+=f"GROUP BY ?{item.varname} ?{item.varname}Label"
+            for wdProp in self.properties.values():
+                if wdProp.pid in genMap:
+                    genList=genMap[wdProp.pid]
+                    if "ignore" in genList:
+                        sparqlQuery+=f"\nHAVING (COUNT(?{wdProp.varname})=1)"
         return sparqlQuery
     
     def mostFrequentPropertiesQuery(self,whereClause:str=None):

{pylodstorage-0.2.14 → pylodstorage-0.3.0}/lodstorage/version.py

@@ -9,7 +9,7 @@ class Version(object):
     Version handling for pyLoDStorage
     '''
     name="pylodstorage"
-    version='0.2.14'
+    version='0.3.0'
     date = '2020-09-10'
-    updated = '2022-07-27'
+    updated = '2022-07-28'
     description='python List of Dict (Table) Storage library'

{pylodstorage-0.2.14 → pylodstorage-0.3.0/pylodstorage.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pylodstorage
-Version: 0.2.14
+Version: 0.3.0
 Summary: python List of Dict (Table) Storage library
 Home-page: https://github.com/WolfgangFahl/pyLodStorage
 Author: Wolfgang Fahl