Changeset 5847 for TI01-discovery/branches/ingestAutomation-upgrade/OAIBatch/Utilities.py

Timestamp:

20/10/09 11:35:29 (11 years ago)

Author:

sdonegan

Message:

fixed bug in getting latest revision date & distinguishing from creation date

File:

• TI01-discovery/branches/ingestAutomation-upgrade/OAIBatch/Utilities.py (modified) (3 diffs)

TI01-discovery/branches/ingestAutomation-upgrade/OAIBatch/Utilities.py

@@ -75 +75 @@
                         
                         self.paths = self.appendNameSpace(self.URLpaths())
+
+                        for path in self.paths:
                         
-                        for path in self.paths:
-                                
                                 nodes = self.root.findall(path)
-                                
+
                                 for node in nodes:
-                                        
                                         currentURL = urllib.quote(node.text)
-                                        
                                         redirectURL = self.redirectBaseURL + currentURL + '&docID=' + urllib.quote(docID) + '&docTitle=' + urllib.quote(docTitle)               
-                                        
                                         node.text = redirectURL
-                                        
+                
                 except:
-                        
+                        print "Cannot perform identityTransform to rewrite ndg redirect urls!"
                         logging.warn("Cannot perform identityTransform to rewrite ndg redirect urls!")
 
@@ -123 +120 @@
         '''method to handle xpath to title for acceptable formats'''
         def datasetTitle(self):
-                if (self.format == 'DIF') | (self.format == 'dif'):
+                if self.format == 'DIF':
                         return ['Entry_Title']
-                elif (self.format == 'MDIP') | (self.format =='mdip'):
+                elif self.format == 'MDIP':
                         return ['Title']
 
         '''method to handle xpath for id if for reqd format '''
         def getIdPath(self):
-                if (self.format == 'DIF') | (self.format == 'dif'):
+                if self.format == 'DIF':
                         return ['Entry_ID']
-                elif (self.format == 'MDIP') | (self.format =='mdip'):
+                elif self.format == 'MDIP':
                         return ['DatasetIdentifier']
 
         '''method to handle xpath for expected URLS if for reqd format '''
         def URLpaths(self):
-                if (self.format == 'DIF') | (self.format == 'dif'):
-                        return ['Related_URL/URL','Data_Center/Data_Center_URL', 'Data_Set_Citation/Online_Resource']
-                elif (self.format == 'MDIP') | (self.format =='mdip'):
+                if self.format == 'DIF':
+                        return ['Related_URL/URL','Data_Center/Data_Center_URL']
+                elif self.format == 'MDIP':
                         return ['OnlineResource','Distributor/Web']
 
         '''method to handle default namespaces for reqd format '''
         def returnNS(self):
-                if (self.format == 'DIF') | (self.format == 'dif'):
+                if self.format == 'DIF':
                         return '{http://gcmd.gsfc.nasa.gov/Aboutus/xml/dif/}' #Note that ns has to be encapsulated in {}'s!
-                elif (self.format == 'MDIP') | (self.format =='mdip'):
+                elif self.format == 'MDIP':
                         return '{http://www.oceannet.org/mdip/xml}'
 
@@ -267 +264 @@
             self.datasetID=helper.getText(et,'Entry_ID')
             self.datasetName = helper.getText(et,'Data_Set_Citation/Dataset_Title')
-            self.datacentreName = helper.getText(et,'Data_Center/Data_Center_Name/Short_Name')
-            self.metadataCreationDate=helper.getText(et,'DIF_Creation_Date')
+            self.datacentreName = helper.getText(et,'Data_Center/Data_Center_Name/Short_Name')            
             self.datasetStartDateNom = helper.getText(et,'Temporal_Coverage/Start_Date')
             self.datasetEndDateNom = helper.getText(et,'Temporal_Coverage/Stop_Date')
             
+            #need to make sure that latest date, eother from creation or last revision is present.
+            if helper.getText(et,'Last_DIF_Revision_Date') != '':
+                self.metadataCreationDate=helper.getText(et,'Last_DIF_Revision_Date')                
+            else:                
+                self.metadataCreationDate=helper.getText(et,'DIF_Creation_Date')
+                
             #Fudge to get around some DC's using "entry_title" and others "dataset_title".  grrr.
-            if self.datasetName == '':             
-             self.datasetName = helper.getText(et,'Entry_Title')
-                
+            if self.datasetName == '':
+             self.datasetName == helper.getText(et,'Entry_Title')
+                
             #TODO amend this - just a fudge to ingest records from crappy badc/neodc whilst pipeline down;..
             if self.datasetEndDateNom == '':
              self.datasetEndDateNom = helper.getText(et,'Temporal_Coverage/End_Date')                       
             
-        elif ((self._datacentre_format == 'MDIP') or (self._datacentre_format == 'mdip')):
-                
+        elif self._datacentre_format == 'MDIP':
             #return helper.getText(self.tree,'DatasetIdentifier')
             self.datasetID=helper.getText(et,'DatasetIdentifier')