aepp 0.4.0.post1__py3-none-any.whl → 0.4.0.post2__py3-none-any.whl

aepp/__version__.py

@@ -1 +1 @@
-__version__ = "0.4.0-1"
+__version__ = "0.4.0-2"

aepp/identity.py

@@ -218,6 +218,36 @@ class Identity:
             self.endpoint + path, headers=self.header, data=creation_dict
         )
         return res
+    
+    def getLinkedIdentities(self,xids:dict|list=None,projectionType:str="set",aam:bool=False,edgeMeta:bool=False,**kwargs)->dict:
+        """
+        Given set of identities, returns all linked identities in the graph corresponding to each identity.
+        Arguments:
+            xids : REQUIRED : A single or a list of xid composite such as: 
+                {'nsid':'mynsid','id':'myid','ns':'mynamespace'}
+            projectionType : OPTIONAL : This define the format returned. Default is "set". Possible : "graph"
+            aam : OPTIONAL : Boolean that cannot be used with graph type. Default False.
+            edgeMeta : OPTIONAL : This is and optional field that is used to add edge meta data in the response, such as dataset_ids and batch_ids. 
+                    It will only apply if the requested projection_type is graph.
+        """
+        if xids is None:
+            raise Exception("Cannot process the request without Xid")
+        if type(xids) == str:
+            xids = list(xids)
+        if self.loggingEnabled:
+            self.logger.debug(f"Starting getLinkedIdentities")
+        path = "/identity/v2/graph"
+        data = {}
+        data["composite_xid"] = xids
+        data['projection_type'] = projectionType
+        data['aam_properties'] = {'return_data_sources':aam}
+        data['require_edge_meta_data'] = edgeMeta
+        if len(kwargs)>0:
+            for key, value in kwargs.items():
+                if key in ['graph_type','traverse','filter']:
+                    data[key] = value
+        res = self.connector.postData(self.endpoint+path, data=data)
+        return res
 
     def updateIdentity(
         self,
@@ -290,117 +320,6 @@ class Identity:
         res = self.connector.getData(self.endpoint + path, headers=self.header)
         return res
 
-    def getClustersMembers(
-        self,
-        xid: str = None,
-        nsid: str = "411",
-        namespace: str = "adcloud",
-        id_value: str = None,
-        graphType: str = "private",
-    ) -> dict:
-        """
-        Given an XID return all XIDs, in the same or other namespaces, that are linked to it by the device graph type.
-        The related XIDs are considered to be part of the same cluster.
-        It is required to pass either xid or (namespace/nsid & id) pair to get cluster members.
-        Arguments:
-            xid : REQUIRED : Identity string returns by the getIdentity method.
-            nsid : OPTIONAL : namespace id (default : 411)
-            namespace : OPTIONAL : namespace code. (default : adcloud)
-            id_value : OPTIONAL : ID of the customer in given namespace.
-            graphType : OPTIONAL : Graph type (output type) you want to get the cluster from. (default private)
-        """
-        if self.loggingEnabled:
-            self.logger.debug(f"Starting getClustersMembers")
-        temp_header = deepcopy(self.header)
-        temp_header["Accept"] = "application/json"
-        temp_header["x-uis-cst-ctx"] = "stub"
-        path = "/identity/cluster/members"
-        params = {}
-        if xid is not None:
-            params["xid"] = xid
-            params["graph-type"] = graphType
-            res = self.connector.getData(
-                self.endpoint + path, params=params, headers=temp_header
-            )
-            return res
-        elif xid is None and id_value is not None:
-            params["nsid"] = nsid
-            params["namespace"] = namespace
-            params["id"] = id_value
-            params["graph-type"] = graphType
-            res = self.connector.getData(
-                self.endpoint + path, params=params, headers=temp_header
-            )
-            return res
-
-    def postClustersMembers(
-        self, xids: list = None, version: float = 1.0, graphType: str = "private"
-    ) -> dict:
-        """
-        Given set of identities, returns all linked identities in cluster corresponding to each identity.
-        Arguments:
-            xids : REQUIRED : list of identity as returned by getIdentity method.
-            version : OPTIONAL : Version of the clusterMembers (default 1.0)
-            graphType : OPTIONAL : Graph type (output type) you want to get the cluster from. (default private)
-        """
-        if self.loggingEnabled:
-            self.logger.debug(f"Starting postClustersMembers")
-        temp_header = deepcopy(self.header)
-        temp_header["Accept"] = "application/vnd.adobe.identity+json;version=1.2"
-        temp_header["x-uis-cst-ctx"] = "stub"
-        path = "/identity/cluster/members"
-        if type(xids) != list:
-            raise TypeError("xids must be of type list")
-        list_body = [
-            {"xid": [{"xid": xid}], "graph-type": graphType, "version": version}
-            for xid in xids
-        ]
-        res = self.connector.postData(
-            self.endpoint + path, data=list_body, headers=temp_header
-        )
-        return res
-
-    def getClusterHistory(
-        self,
-        xid: str = None,
-        nsid: int = 411,
-        namespace: str = "adcloud",
-        id_value: str = None,
-        graphType: str = "private",
-    ) -> dict:
-        """
-        Given an XID, return all cluster associations with that XID.
-        It is required to pass either xid or (namespace/nsid & id) pair to get cluster history.
-        Arguments:
-            xid : REQUIRED : Identity string returns by the getIdentity method.
-            nsid : OPTIONAL : namespace id (default : 411)
-            namespace : OPTIONAL : namespace code. (default : adcloud)
-            id_value : OPTIONAL : ID of the customer in given namespace.
-            graphType : OPTIONAL : Graph type (output type) you want to get the cluster from. (default private)
-        """
-        if self.loggingEnabled:
-            self.logger.debug(f"Starting getClusterHistory")
-        temp_header = deepcopy(self.header)
-        temp_header["Accept"] = "application/vnd.adobe.identity+json;version=1.2"
-        temp_header["x-uis-cst-ctx"] = "stub"
-        path = "/identity/cluster/history"
-        params = {}
-        if xid is not None:
-            params["xid"] = xid
-            params["graph-type"] = graphType
-            res = aepp._getData(
-                self.endpoint + path, params=params, headers=temp_header
-            )
-            return res
-        elif xid is None and id_value is not None:
-            params["nsid"] = nsid
-            params["namespace"] = namespace
-            params["id"] = id_value
-            params["graph-type"] = graphType
-            res = self.connector.getData(
-                self.endpoint + path, params=params, headers=temp_header
-            )
-            return res
 
     def getIdentityMapping(
         self,

aepp/queryservice.py

@@ -935,7 +935,7 @@ class InteractiveQuery:
     loggingEnabled = False
     logger = None
 
-    def __init__(self, conn_object: dict = None, loggingObject: dict = None):
+    def __init__(self, conn_object: dict = None, loggingObject: dict = None,config:ConnectObject=None):
         """
         Importing the pg (PyGreSQL) library and instantiating the connection via the conn_object pass over the instantiation method.
         Arguments:
@@ -946,6 +946,7 @@ class InteractiveQuery:
             raise AttributeError(
                 "You are missing the conn_object. Use the QueryService to retrieve the object."
             )
+        self.config = None
         self.dbname = conn_object["dbName"]
         self.host = conn_object["host"]
         self.port = conn_object["port"]
@@ -975,6 +976,17 @@ class InteractiveQuery:
                 streamHandler = logging.StreamHandler()
                 streamHandler.setFormatter(formatter)
                 self.logger.addHandler(streamHandler)
+        if config is not None:
+            self.config = config
+            from aepp import catalog, segmentation
+            self.mycat = catalog.Catalog(config=self.config)
+            self.myseg = segmentation.Segmentation(config=self.config)
+
+    def addConfig(self,config:ConnectObject)->None:
+        self.config = config
+        from aepp import catalog,segmentation
+        self.mycat = catalog.Catalog(config=self.config)
+        self.myseg = segmentation.Segmentation(config=self.config)
 
     def query(
         self, sql: str = None, output: str = "dataframe"
@@ -1003,6 +1015,57 @@ class InteractiveQuery:
             return df
         else:
             raise KeyError("You didn't specify a correct value.")
+    
+    def querySegmentPopulation(self,segmentId:str|list,extraFields:str|list=None,count:bool=False)->pd.DataFrame|object:
+        """
+        Retrieve the identities in the identityMap that are qualified to the segment ID passed. 
+        Arguments:
+            segmentId : REQUIRED : Single or list of segment Ids
+            extraFields : OPTIONAL : If you want to add more fields that are not in the IdentityMap
+            count : OPTIONAL : If you just want to get the count of the profiles and no details
+        """
+        if self.config is None:
+            raise Exception('Require to have a config available. Use addConfig method to add a configuration')
+        if type(extraFields) == str:
+            extraFields = [extraFields]
+        if type(segmentId) == list:
+            result = pd.DataFrame()
+            for segId in segmentId:
+                data = self.querySegmentPopulation(segId,count=count)
+                if result.empty:
+                    result = data.copy()
+                else:
+                    result = pd.concat([result,data],ignore_index=True)
+            return result
+        mysegment = self.myseg.getSegment(segmentId)
+        mergePolicyId = mysegment.get('mergePolicyId')
+        myProfileSnaphots = self.mycat.getProfileSnapshotDatasets()
+        table = None
+        for key, item in myProfileSnaphots.items():
+            tmp_ds_mergePolicyId = item['tags']['unifiedProfile']
+            if f"mergePolicyId:{mergePolicyId}" in tmp_ds_mergePolicyId:
+                table = item['tags']['adobe/pqs/table'][0]
+        if count == False:
+            strIdentity = ""
+            commaIdentity = ""
+            strIdentityFinal = ""
+            if extraFields is not None:
+                commaFields = ","
+                strFields = ','.join(extraFields)
+                minifyFields = [el.split('.').pop() for el in extraFields]
+                strFieldsFinal = ','.join(minifyFields)
+            queryTemplate = f"""
+                SELECT key, inline(value), '{segmentId}' segmentId {commaFields} {strFieldsFinal} FROM 
+                    (SELECT explode(identityMap) {commaFields} {strFields}
+                    FROM {table}
+                    WHERE segmentMembership['ups']['{segmentId}'].status = 'realized') LIMIT 0 
+            """
+            res = self.query(queryTemplate)
+            return res
+        else:
+            dict_data = [{'count':mysegment.get('metrics',{}).get('data',{}).get('totalProfiles','No Data Yet'),'segmentId':segmentId}]
+            df = pd.DataFrame(dict_data)
+            return df
 
     def transformToDataFrame(self, query: object = None) -> pd.DataFrame:
         """
@@ -1091,7 +1154,7 @@ class InteractiveQuery2:
     loggingEnabled = False
     logger = None
 
-    def __init__(self, conn_object: dict = None, loggingObject: dict = None,sslmode:str="allow"):
+    def __init__(self, conn_object: dict = None, loggingObject: dict = None,sslmode:str="allow",config:ConnectObject=None):
         """
         Importing the psycopg2 library and instantiating the connection via the conn_object pass over the instantiation method.
         Arguments:
@@ -1102,6 +1165,7 @@ class InteractiveQuery2:
             raise AttributeError(
                 "You are missing the conn_object. Use the QueryService to retrieve the object."
             )
+        self.config = None
         self.dbname = conn_object["dbName"]
         self.host = conn_object["host"]
         self.port = conn_object["port"]
@@ -1131,6 +1195,17 @@ class InteractiveQuery2:
                 streamHandler = logging.StreamHandler()
                 streamHandler.setFormatter(formatter)
                 self.logger.addHandler(streamHandler)
+        if config is not None:
+            self.config = config
+            from aepp import catalog, segmentation
+            self.mycat = catalog.Catalog(config=self.config)
+            self.myseg = segmentation.Segmentation(config=self.config)
+    
+    def addConfig(self,config:ConnectObject)->None:
+        self.config = config
+        from aepp import catalog,segmentation
+        self.mycat = catalog.Catalog(config=self.config)
+        self.myseg = segmentation.Segmentation(config=self.config)
 
     def query(
         self, sql: str = None, output: str = "dataframe"
@@ -1160,6 +1235,58 @@ class InteractiveQuery2:
         else:
             raise KeyError("You didn't specify a correct value.")
 
+    def querySegmentPopulation(self,segmentId:str|list,extraFields:str|list=None,count:bool=False)->pd.DataFrame|object:
+        """
+        Retrieve the identities in the identityMap that are qualified to the segment ID passed.
+        Arguments:
+            segmentId : REQUIRED : Single or list of segment Ids
+            extraFields : OPTIONAL : If you want to add more identities that are not in the IdentityMap
+            count : OPTIONAL : If you just want to get the population count of the segment IDs
+        """
+        if self.config is None:
+            raise Exception('Require to have a config available. Use addConfig method to add a configuration')
+        if type(extraFields) == str:
+            extraFields = [extraFields]
+        if type(segmentId) == list:
+            result = pd.DataFrame()
+            for segId in segmentId:
+                data = self.querySegmentPopulation(segId,count=count)
+                if result.empty:
+                    result = data.copy()
+                else:
+                    result = pd.concat([result,data],ignore_index=True)
+            return result
+        mysegment = self.myseg.getSegment(segmentId)
+        mergePolicyId = mysegment.get('mergePolicyId')
+        myProfileSnaphots = self.mycat.getProfileSnapshotDatasets()
+        table = None
+        for key, item in myProfileSnaphots.items():
+            tmp_ds_mergePolicyId = item['tags']['unifiedProfile']
+            if f"mergePolicyId:{mergePolicyId}" in tmp_ds_mergePolicyId:
+                table = item['tags']['adobe/pqs/table'][0]
+        if count == False:
+            strIdentity = ""
+            commaIdentity = ""
+            strIdentityFinal = ""
+            if extraFields is not None:
+                commaField = ","
+                strFields = ','.join(extraFields)
+                minifyFields = [el.split('.').pop() for el in extraFields]
+                strFieldsFinal = ','.join(minifyFields)
+            queryTemplate = f"""
+                SELECT key, inline(value), '{segmentId}' segmentId {commaField} {strFieldsFinal} FROM 
+                    (SELECT explode(identityMap) {commaField} {strFields}
+                    FROM {table}
+                    WHERE segmentMembership['ups']['{segmentId}'].status = 'realized') LIMIT 0 
+            """
+            res = self.query(queryTemplate)
+            return res
+        else:
+            dict_data = [{'count':mysegment.get('metrics',{}).get('data',{}).get('totalProfiles','No Data Yet'),'segmentId':segmentId}]
+            df = pd.DataFrame(dict_data)
+            return df
+
+
     def transformToDataFrame(self, query: object = None) -> pd.DataFrame:
         """
         Taking the raw output of the query method use with raw and returning a DataFrame

aepp/segmentation.py

@@ -771,6 +771,7 @@ class Segmentation:
         limit:int=100,
         name:str=None,
         sort:str=None,
+        entityType:str="_xdm.context.profile",
         prop:str=None,
         description:str=None,
         **kwargs)->list:
@@ -780,13 +781,14 @@ class Segmentation:
             name : OPTIONAL : Filter audiences that contains that string in the name, case unsensitive.
             limit : OPTIONAL : The number of audiences to be returned by pages (default: 100)
             sort : OPTIONAL : If you want to sort by a specific attribute (ex: "updateTime:desc")
+            entityType : OPTIONAL : The type of entity available, default "_xdm.context.profile".
             prop : If you want to test a specific property of the result to filter the data.
                     Ex: "audienceId==mytestAudienceId"
             description : OPTIONAL : Filter audiences that contains that string in the description, case unsensitive.
         """
         if self.loggingEnabled:
             self.logger.debug(f"Starting getAudiences")
-        params = {"limit":limit,"withMetrics":True}
+        params = {"limit":limit}
         path = "/audiences"
         if name is not None:
             params['name'] = name
@@ -796,8 +798,6 @@ class Segmentation:
             params['property'] = prop
         if description is not None:
             params['description'] = description
-        if kwargs.get('start',0) is not None:
-            params['start'] = kwargs.get('start')
         res = self.connector.getData(self.endpoint+path, params=params)
         data = res.get('children',[])
         nextStart = res.get('_page',{}).get('next',0)

{aepp-0.4.0.post1.dist-info → aepp-0.4.0.post2.dist-info}/METADATA

@@ -1,13 +1,13 @@
 Metadata-Version: 2.4
 Name: aepp
-Version: 0.4.0.post1
+Version: 0.4.0.post2
 Summary: Package to manage AEP API endpoint and some helper functions
 Home-page: https://github.com/adobe/aepp
 Author: Julien Piccini
 Author-email: piccini.julien@gmail.com
 Classifier: Programming Language :: Python :: 3
 Classifier: Operating System :: OS Independent
-Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
+Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Topic :: Utilities
 Classifier: Topic :: Internet
 Classifier: Topic :: Software Development :: Libraries

{aepp-0.4.0.post1.dist-info → aepp-0.4.0.post2.dist-info}/RECORD

@@ -1,5 +1,5 @@
 aepp/__init__.py,sha256=6Vx1MxvwnohShbXZgxQsB6Mg_dhx9AW7_fKGqoZhXHo,23409
-aepp/__version__.py,sha256=40YS1AO_IHn8Hsvg8yMW2rENEkTxRYiBd0zoWtQnnrg,23
+aepp/__version__.py,sha256=tvf97IPct6tqCNAfd_EVu0K-LUWG2ExY2zhh5Qo9630,23
 aepp/accesscontrol.py,sha256=PB3FcrO4bvDjdNxjHx7p_20hp4ahBXewoOSxuTGMXC8,17423
 aepp/catalog.py,sha256=hK9m3SAP0fhgkYqu14Tcfq14qBhw54tLCOF0mH31b1M,68237
 aepp/classmanager.py,sha256=xHcbgb9HkaAko2LxA0itfxR9tCYfVHW49_wlZH2zPtw,58380
@@ -19,22 +19,22 @@ aepp/exportDatasetToDataLandingZone.py,sha256=C6jg3XttFC-0mswa3ypZb6qx3MCQ8_A_3k
 aepp/fieldgroupmanager.py,sha256=FnRgbbilz69NVo8H51aTQsuocIH_Qs69Nnynp3RsYuw,92146
 aepp/flowservice.py,sha256=gVayD3vIMu7-d9TGpVtkbQ1r9iwAjJHWNRVtxKURWKc,107610
 aepp/hygiene.py,sha256=VEspnyu9eUlcK3wLeJYclaFaOWl5G5I5MRwmVA-RnUg,15385
-aepp/identity.py,sha256=_moM_YE0FOpRK5wu7O1_10XaPiFltGsZnBk7POdCwbo,24123
+aepp/identity.py,sha256=E9MCIgntScMssduqKZqehT6FqSfTjWHcq7E7wESj3Zc,20833
 aepp/ingestion.py,sha256=OamE7NDei2Ev5vXIDkMlzvdyBaN41nkIGmpAnUlQoZI,22372
 aepp/observability.py,sha256=bKe74nlXYB5E5syh7Lj4VqIgwUI3OjMxK383P05EdLU,9951
 aepp/policy.py,sha256=JbpvfCKJl2kE2McK2mn_ZI5HKd_6pTnrfMoUdyJesWQ,24924
 aepp/privacyservice.py,sha256=V6BkJeZG1LDBCyEQm9Gx0i68iRHG6uxSJiVnXzkHapI,8790
-aepp/queryservice.py,sha256=zt2o40iUCQz5jrOZnLeQNdaZkrLJz6CTFX27SFOSZrI,54821
+aepp/queryservice.py,sha256=HT_UoiBcLNERr_SCDtcGsPqrxQtu97cdXtSQMHkyRpc,61210
 aepp/sandboxes.py,sha256=UwlSFkO2OOmH--6ISz8rxwDu2LcLH1MPqoH7yOEAZHc,29363
 aepp/schema.py,sha256=JK1lOBYVFPC4Y8GTJsNWc0eoVCjoKoCRIBka26OdXk0,122004
 aepp/schemamanager.py,sha256=xSQQQw7cX67vopR7HXsWBnlI4FIV7_JBxnIeeEao5Hg,51103
-aepp/segmentation.py,sha256=Oi4VnGt0HHAw59rV309XGaBArzxGObssuKM58H8xsnc,42606
+aepp/segmentation.py,sha256=l-2MJuzV2eaO-RijWFdbELDLTAw1EHotFSzL343-up4,42636
 aepp/sensei.py,sha256=oYNy5BSWAEqsDkEexcQso6NfA6ntGGMnCOyHri0pJs8,7761
 aepp/som.py,sha256=JzNDQzGaHB9BRRv9zyY1B9Z1GZ-v1uioUZLxLtnf5vE,34206
 aepp/synchronizer.py,sha256=I32pSI0AVGIjtbbJiZq1qkeZKsIpMni-T72iqyAgo7c,58448
 aepp/tags.py,sha256=t2qBallTcWR4IOXcDBmrPpqjbSay1z3E2bcRijzVm1s,17641
 aepp/utils.py,sha256=tG-YVXylm38-bynqfp5N_Mzyo7mhlZj-dLo7wLoO4tM,1200
-aepp-0.4.0.post1.dist-info/licenses/LICENSE,sha256=HjYTlfne3BbS5gNHzNqJ5COCiTQLUdf87QkzRyFbE4Y,10337
+aepp-0.4.0.post2.dist-info/licenses/LICENSE,sha256=HjYTlfne3BbS5gNHzNqJ5COCiTQLUdf87QkzRyFbE4Y,10337
 tests/__init__.py,sha256=d6zWJsJFZrQd5wAYM7sezSxwXbuMMWfNPkK_vpaUzFA,623
 tests/catalog_test.py,sha256=O4kkG0C_dXk3E77pSzWIt1ewfyKjfZqgbJmBwWwx0po,2246
 tests/dataaccess_test.py,sha256=bnHwOjPPauTM8s1c6O7iUYC--gqt6tPzT94aEZHDC-c,1238
@@ -44,7 +44,7 @@ tests/exportDatasetToDatalandingZone_test.py,sha256=193AgQR8yhnQmRWV9pgYz1X2Hz-Y
 tests/flowservice_test.py,sha256=Y1mpYWbKYL_x-ZlIY-EuOuNvlzVV1ERlKseDO7gN3Ss,4208
 tests/schema_test.py,sha256=6UsgdsizKmii1hzREpBEKWvZouXdJMvU68UKSxlt1uk,2774
 tests/som_test.py,sha256=a4ut0pEg1HJVMTESaPITmj7YkF54eWCMzKxTMIS-VvM,12101
-aepp-0.4.0.post1.dist-info/METADATA,sha256=pWbPbXNv4xNcKqrPXsvPXQVUZlueJT7NWrAu01MbDPI,5490
-aepp-0.4.0.post1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-aepp-0.4.0.post1.dist-info/top_level.txt,sha256=Gn88pv1ywuEAgOvhmmXXhN4dosEfCrBNDskje3nqS34,11
-aepp-0.4.0.post1.dist-info/RECORD,,
+aepp-0.4.0.post2.dist-info/METADATA,sha256=oPqgxU1JDeP4eT3fHoy8IdstSYmINapk2G5TNEEQxMM,5476
+aepp-0.4.0.post2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+aepp-0.4.0.post2.dist-info/top_level.txt,sha256=Gn88pv1ywuEAgOvhmmXXhN4dosEfCrBNDskje3nqS34,11
+aepp-0.4.0.post2.dist-info/RECORD,,