Import working for non-book pages

wagtailimportexport/exporting.py

@@ -17,10 +17,10 @@
 from wagtail.documents.models import Document
 
 
-def export_page(settings = {'root_page': None, 'export_unpublished': False, 
-    'export_documents': False, 'export_images': False, 'null_pk': True,
-    'null_fk': False, 'null_users': False
-    }):
+def export_page(settings={'root_page': None, 'export_unpublished': False,
+                          'export_documents': False, 'export_images': False, 'null_pk': True,
+                          'null_fk': False, 'null_users': False
+                          }):
     """
     Exports the root_page as well as its children (if the setting is set).
 
@@ -37,11 +37,11 @@ def export_page(settings = {'root_page': None, 'export_unpublished': False,
     # If root_page is not set, then set it the main directory as default.
     if not settings['root_page']:
         settings['root_page'] = Page.objects.filter(url_path='/').first()
-    
+
     # Get the list of the pages, (that are the descendant of the root_page).
     pages = Page.objects.descendant_of(
         settings['root_page'], inclusive=True).order_by('path').specific()
-    
+
     # Filter the pages if export_unpublished is set to false.
     if not settings['export_unpublished']:
         pages = pages.filter(live=True)
@@ -57,28 +57,29 @@ def export_page(settings = {'root_page': None, 'export_unpublished': False,
         # skip over pages whose parents haven't already been exported
         # (which means that export_unpublished is false and the parent was unpublished)
         if i == 0 or (parent_path in exported_paths):
-            
+
             # Turn page data to a dictionary.
             data = json.loads(page.to_json())
             locale = data['locale']
 
             # look up document titles
-            cover = functions.document_title(data['cover'])
-            title_image = functions.document_title(data['title_image'])
-            hi_res_pdf = functions.document_title(data['high_resolution_pdf'])
-            lo_res_pdf = functions.document_title(data['low_resolution_pdf'])
-            community_logo = functions.document_title(data['community_resource_logo'])
-            community_feature_link = functions.document_title(data['community_resource_feature_link'])
-
-            # Get list (and metadata) of images and documents to be exported.            
+            if page.content_type.model == 'book':
+                cover = functions.document_title(data['cover'])
+                title_image = functions.document_title(data['title_image'])
+                hi_res_pdf = functions.document_title(data['high_resolution_pdf'])
+                lo_res_pdf = functions.document_title(data['low_resolution_pdf'])
+                community_logo = functions.document_title(data['community_resource_logo'])
+                community_feature_link = functions.document_title(data['community_resource_feature_link'])
+
+            # Get list (and metadata) of images and documents to be exported.
             images = list_fileobjects(page, settings, Image) if settings['export_images'] else {}
             documents = list_fileobjects(page, settings, Document) if settings['export_documents'] else {}
 
-            #Remove FKs
+            # Remove FKs
             if settings['null_fk']:
                 functions.null_fks(page, data)
 
-            #Remove the owner of the page.
+            # Remove the owner of the page.
             if settings['null_users'] and not data.get('owner'):
                 data['owner'] = None
 
@@ -91,12 +92,13 @@ def export_page(settings = {'root_page': None, 'export_unpublished': False,
             data['pk'] = None
             data['locale'] = locale
             # add document titles to data
-            data['cover'] = cover
-            data['title_image'] = title_image
-            data['high_resolution_pdf'] = hi_res_pdf
-            data['low_resolution_pdf'] = lo_res_pdf
-            data['community_resource_logo'] = community_logo
-            data['community_resource_feature_link'] = community_feature_link
+            if page.content_type.model == 'book':
+                data['cover'] = cover
+                data['title_image'] = title_image
+                data['high_resolution_pdf'] = hi_res_pdf
+                data['low_resolution_pdf'] = lo_res_pdf
+                data['community_resource_logo'] = community_logo
+                data['community_resource_feature_link'] = community_feature_link
 
             # Export page data.
             page_data.append({
@@ -111,6 +113,7 @@ def export_page(settings = {'root_page': None, 'export_unpublished': False,
 
     return functions.zip_contents(page_data)
 
+
 def list_fileobjects(page, settings, objtype):
     """
     Returns a dict of all fields that has the related_model of objtype as well as their metadata.
@@ -149,22 +152,23 @@ def list_fileobjects(page, settings, objtype):
                         objects[field.name] = instance_to_data(instance, null_users=settings['null_users'])
 
                 except (FileNotFoundError, objtype.DoesNotExist):
-                    logging.error("File for "+str(field.name)+" is not found on the environment, skipping.")
+                    logging.error("File for " + str(field.name) + " is not found on the environment, skipping.")
                     objects[field.name] = None
 
             else:
                 objects[field.name] = None
-    
+
     return objects
 
+
 def instance_to_data(instance, null_users=False):
     """
     A utility to create JSON-able data from a model instance.
 
     Arguments:
     instance -- objects.get() object instance.
     null_users -- Whether to null user references.
-    
+
     Returns:
     A dictionary of metadata of instance.
     """

wagtailimportexport/functions.py

@@ -9,6 +9,7 @@
 from django.core.serializers.json import DjangoJSONEncoder
 from django.db.models.fields.related import ForeignKey
 from django.db.models.fields.reverse_related import ManyToOneRel
+from django.contrib.contenttypes.models import ContentType
 
 from wagtail.core.fields import StreamField
 from wagtail.documents.models import Document
@@ -25,7 +26,7 @@ def null_pks(page, data):
     Returns:
     N/A. Overwrites the argument.
     """
-    
+
     # Nullify the main ID
     data['id'] = None
     data['pk'] = None
@@ -34,11 +35,12 @@ def null_pks(page, data):
     for field_name, field_val in data.items():
         if type(field_val) != list:
             continue
-        
+
         for i, sub_item in enumerate(field_val):
             if 'pk' in sub_item:
                 data[field_name][i]['pk'] = None
 
+
 def find_null_child_blocks(subfield, location, data):
     """
     Recursive function to find all children blocks
@@ -65,9 +67,10 @@ def find_null_child_blocks(subfield, location, data):
             if isinstance(field_val, ForeignKey):
                 # TODO: Implement overwriting.
                 pass
-            
+
             # Recursive Calls
-            find_null_child_blocks(field_val, location+[field_key], data)
+            find_null_child_blocks(field_val, location + [field_key], data)
+
 
 def find_null_child_relations(subfield, location, data):
     """
@@ -95,13 +98,14 @@ def find_null_child_relations(subfield, location, data):
             if isinstance(field, ForeignKey):
                 if not location[0] in data:
                     continue
-                
+
                 for i, value in enumerate(data[location[0]]):
                     if not field.name in data[location[0]][i]:
                         continue
-                    
+
                     data[location[0]][i][field.name] = None
 
+
 def null_fks(page, data):
     """
     Nullifies foreign keys within all supplied fields.
@@ -116,11 +120,11 @@ def null_fks(page, data):
 
     # Loop through all fields.
     for field in page._meta.get_fields():
-        
+
         # Check whether the field is a ForeignKey.
         # By nature, owner, content_type, live_revision
         # are foreign keys defined by wagtail core pages.
-        if(isinstance(field, ForeignKey)):
+        if (isinstance(field, ForeignKey)):
             data[field.name] = None
 
         # StreamFields often have foreign keys associated with them.
@@ -130,7 +134,8 @@ def null_fks(page, data):
         # # Many to One relations often have foreign keys associated with them.
         # if(isinstance(field, ManyToOneRel)):
         #     find_null_child_relations(field, [field.name], data)
-
+
+
 def zip_contents(page_contents):
     """
     Creates and returns a zip archive of all supplied items.
@@ -158,42 +163,42 @@ def zip_contents(page_contents):
                 'content.json',
                 json.dumps(page_contents, indent=2, cls=DjangoJSONEncoder)
             )
-            
+
             # Loop through pages to explore all used images and documents.
             for page in page_contents:
 
                 # Export all the images.
                 for image_def in page['images'].values():
                     if not image_def:
                         continue
-                    
+
                     filename = image_def['file']['name']
 
                     try:
                         with file_storage.open(filename, 'rb') as f:
                             zf.writestr(filename, f.read())
                     except FileNotFoundError:
-                        logging.error("File "+str(filename)+" is not found on local file storage and was not exported.")
+                        logging.error("File " + str(filename) + " is not found on local file storage and was not exported.")
 
-
                 # Export all the documents.
                 for doc_def in page['documents'].values():
                     if not doc_def:
                         continue
-                    
+
                     filename = doc_def['file']['name']
 
                     try:
                         with file_storage.open(filename, 'rb') as f:
                             zf.writestr(filename, f.read())
                     except FileNotFoundError:
-                        logging.error("File "+str(filename)+" is not found on local file storage and was not exported.")
-        
+                        logging.error("File " + str(filename) + " is not found on local file storage and was not exported.")
+
         with open(zfname, 'rb') as zf:
             fd = zf.read()
 
     return io.BytesIO(fd)
 
+
 def unzip_contents(zip_contents):
     """
     Extracts all items in the zip archive and returns a mapping
@@ -213,7 +218,7 @@ def unzip_contents(zip_contents):
     zip_contents.extractall(tempdir)
 
     # Return the mapping of all extracted members.
-    return {member: tempdir+'/'+member for member in zip_contents.namelist()}
+    return {member: tempdir + '/' + member for member in zip_contents.namelist()}
 
 
 def document_title(doc_pk):
@@ -230,3 +235,11 @@ def document_id(doc_title):
         return None
     else:
         return doc[0].pk
+
+
+def content_type_by_model(model):
+    content_type = ContentType.objects.all().filter(model=model)
+    if not content_type:
+        return None
+    else:
+        return str(content_type[0].pk)

wagtailimportexport/importing.py

@@ -1,6 +1,7 @@
 import io
 import json
 import logging
+import traceback
 from zipfile import ZipFile
 
 from django.apps import apps
@@ -66,10 +67,12 @@ def import_page(uploaded_archive, parent_page, overwrites={}):
                 for (i, page_record) in enumerate(contents):
 
                     new_field_datas = {}
+                    content_type = functions.content_type_by_model(page_record['model'])
+                    #content_type = page_record['content']['content_type']
 
                     # Skip the existing pages.
                     if i in existing_pages:
-                        error_msg = 'Duplicate slug'
+                        error_msg = 'Import stopped. Duplicate slug: ' + str(page_record['content']['slug'])
                         continue
 
                     # Reassign image IDs.
@@ -96,13 +99,14 @@ def import_page(uploaded_archive, parent_page, overwrites={}):
                     for (field, new_value) in overwrites.items():
                         page_record['content'][field] = new_value
 
-                    # look up document ids
-                    page_record['content']['cover'] = functions.document_id(page_record['content']['cover'])
-                    page_record['content']['title_image'] = functions.document_id(page_record['content']['title_image'])
-                    page_record['content']['high_resolution_pdf'] = functions.document_id(page_record['content']['high_resolution_pdf'])
-                    page_record['content']['low_resolution_pdf'] = functions.document_id(page_record['content']['low_resolution_pdf'])
-                    page_record['content']['community_resource_logo'] = functions.document_id(page_record['content']['community_resource_logo'])
-                    page_record['content']['community_resource_feature_link'] = functions.document_id(page_record['content']['community_resource_feature_link'])
+                    if page_record['model'] == 'book':
+                        # look up document ids
+                        page_record['content']['cover'] = functions.document_id(page_record['content']['cover'])
+                        page_record['content']['title_image'] = functions.document_id(page_record['content']['title_image'])
+                        page_record['content']['high_resolution_pdf'] = functions.document_id(page_record['content']['high_resolution_pdf'])
+                        page_record['content']['low_resolution_pdf'] = functions.document_id(page_record['content']['low_resolution_pdf'])
+                        page_record['content']['community_resource_logo'] = functions.document_id(page_record['content']['community_resource_logo'])
+                        page_record['content']['community_resource_feature_link'] = functions.document_id(page_record['content']['community_resource_feature_link'])
 
                     # set page.pk to null if pk already exists
                     pages = Page.objects.all()
@@ -111,6 +115,7 @@ def import_page(uploaded_archive, parent_page, overwrites={}):
                             page_record['content']['pk'] = None
                             break
 
+                    page_record['content']['content_type'] = content_type
                     # Create page instance.
                     page = Page.from_serializable_data(page_record['content'])
 
@@ -165,6 +170,7 @@ def import_page(uploaded_archive, parent_page, overwrites={}):
             # If content.json does not exist, then return the error,
             # and terminate the import_page.
             logging.error("Importing file failed because file does not exist: " + str(e))
+            traceback.print_exception(type(e), e, e.__traceback__)
             return (0, 1, "File does not exist: " + str(e))
 
     return (0, 1, "")