Changed order of methods in parser, added comments.

landingpage/landingpageapp/handle/cmip6parser.py

@@ -83,6 +83,14 @@ def get_errata_field_from_record(record):
 
 # Actual implementation and helpers
 
+def _get_title_from_record(record):
+    if is_file(record):
+        return get_filename_from_record(record)
+    elif is_dataset(record):
+        return get_drs_from_record(record)
+    else:
+        return None
+
 def _get_aggregation_level(record):
     return get_value_from_record(record, 'AGGREGATION_LEVEL')
 
@@ -94,23 +102,30 @@ def _is_dataset(record):
     if get_aggregation_level(record) == 'DATASET':
         return True
 
-def _get_title_from_record(record):
-    if is_file(record):
-        return get_filename_from_record(record)
-    elif is_dataset(record):
-        return get_drs_from_record(record)
-    else:
-        return None
-
 def _get_aggregation_field_from_record(record):
     field_string = get_value_from_record(record, 'IS_PART_OF')
     if field_string is None:
         field_string = get_value_from_record(record, 'PARENT') # TODO Remove once migration is done!
     return field_string
 
+def _get_list_of_aggregation_handles_from_record(record):
+    field_string = get_aggregation_field_from_record(record)
+    list_of_strings = field_string.split(';')
+    handles = []
+    for member in list_of_strings:
+        handles.append(_remove_hdl_from_handle(member))
+    return handles
+
 def _get_errata_field_from_record(record):
     return get_value_from_record(record, 'ERRATA_IDS')
 
+def _get_errata_list_from_record(record):
+    field_string = get_errata_field_from_record(record)
+    if field_string is not None:
+        return field_string.split(';')
+    else:
+        return None
+
 def _get_filename_from_record(record):
     return get_value_from_record(record, 'FILE_NAME')
 
@@ -131,6 +146,22 @@ def _get_urls_replicas_from_record(record):
     field_string = get_value_from_record(record, 'URL_REPLICAS')
     return _parse_urls_replicas_from_record(field_string)
 
+# Helpers:
+
+def _parse_urls_original_from_record(field_string):
+    parsed = _extract_url_info_from_field(field_string, 'href', 'host')
+    if parsed is not None:
+        parsed = _rename_href_to_url(parsed)
+        parsed = _remove_duplicate_urls(parsed)
+    return parsed
+
+def _parse_urls_replicas_from_record(field_string):
+    parsed = _extract_url_info_from_field(field_string, 'href', 'host')
+    if parsed is not None:
+        parsed = _rename_href_to_url(parsed)
+        parsed = _remove_duplicate_urls(parsed)
+    return parsed
+
 def _rename_href_to_url(list_of_dicts):
     ''' Helper for the list of dict that is the result of parsing
     a locations xml snippet.'''
@@ -154,34 +185,22 @@ def _remove_duplicate_urls(list_of_dicts):
             new_list_of_dicts.append(item)
     return new_list_of_dicts
 
-def _parse_urls_original_from_record(field_string):
-    parsed = _extract_url_info_from_field(field_string, 'href', 'host')
-    if parsed is not None:
-        parsed = _rename_href_to_url(parsed)
-        parsed = _remove_duplicate_urls(parsed)
-    return parsed
-
-def _get_errata_list_from_record(record):
-    field_string = get_errata_field_from_record(record)
-    if field_string is not None:
-        return field_string.split(';')
-    else:
+def _extract_url_info_from_field(field_string, *attributes):
+    if field_string is None:
         return None
+    else:
+        field_xml = ET.fromstring(field_string)
+        list_of_items = []
+        locations = field_xml.findall('location')
+        for location in locations:
+            temp = {}
+            for attr in attributes:
+                val = location.get(attr)
+                if val is not None:
+                    temp[attr] = val
+            list_of_items.append(temp)
+        return list_of_items
 
-def _parse_urls_replicas_from_record(field_string):
-    parsed = _extract_url_info_from_field(field_string, 'href', 'host')
-    if parsed is not None:
-        parsed = _rename_href_to_url(parsed)
-        parsed = _remove_duplicate_urls(parsed)
-    return parsed
-
-def _get_list_of_aggregation_handles_from_record(record):
-    field_string = get_aggregation_field_from_record(record)
-    list_of_strings = field_string.split(';')
-    handles = []
-    for member in list_of_strings:
-        handles.append(_remove_hdl_from_handle(member))
-    return handles
 
 # Retrieve info on parent dataset from handle system:
 
@@ -202,26 +221,10 @@ def _get_list_of_aggregation_records_from_record(list_of_aggregation_handles):
 
     return list_to_be_returned, any_replaced
 
-def _extract_url_info_from_field(field_string, *attributes):
-    if field_string is None:
-        return None
-    else:
-        field_xml = ET.fromstring(field_string)
-        list_of_items = []
-        locations = field_xml.findall('location')
-        for location in locations:
-            temp = {}
-            for attr in attributes:
-                val = location.get(attr)
-                if val is not None:
-                    temp[attr] = val
-            list_of_items.append(temp)
-        return list_of_items
-
-def _extract_info_on_one_aggregation_record(handle):
+def _extract_info_on_one_aggregation_record(parenthandle):
         
     # Retrieve handle:
-    record = retrieval.get_handle_record_json(handle)
+    record = retrieval.get_handle_record_json(parenthandle)
 
     # Get info:
     aggregation_level = get_aggregation_level(record)
@@ -229,12 +232,12 @@ def _extract_info_on_one_aggregation_record(handle):
     vers_num = get_version_number_from_record(record)
     newer_version = get_replaced_by_from_record(record)
     replaced = False
-    if newer_version is not None and not newer_version == handle:
+    if newer_version is not None and not newer_version == parenthandle:
         replaced = True
 
     # Assemble info:
     info_to_return = dict(
-        handle = handle,
+        handle = parenthandle,
         level = aggregation_level.lower(),
         title = drs_id,
         version = vers_num,
@@ -267,6 +270,12 @@ def _get_hosts_replicas_from_record(record):
     parsed = _extract_url_info_from_field(field_string, 'host')
     return parsed
 
+def _get_parts_field_from_record(record):
+    field_string = get_value_from_record(record, 'HAS_PARTS')
+    if field_string is None:
+        field_string = get_value_from_record(record, 'CHILDREN') # TODO Remove once migration is done!
+    return field_string
+
 def _get_list_of_parts_handles_from_record(record):
     field_string = _get_parts_field_from_record(record)
     list_of_strings = field_string.split(';')
@@ -275,6 +284,8 @@ def _get_list_of_parts_handles_from_record(record):
         handles.append(_remove_hdl_from_handle(string))
     return handles
 
+# Retrieve info on child files from handle system:
+
 def _get_list_of_parts_records_from_record(record):
     list_of_parts_handles = _get_list_of_parts_handles_from_record(record)
     list_to_be_returned = []
@@ -312,13 +323,7 @@ def _extract_info_on_one_part_record(handle):
 
     return info_to_return, replaced
 
-
-def _get_parts_field_from_record(record):
-    field_string = get_value_from_record(record, 'HAS_PARTS')
-    if field_string is None:
-        field_string = get_value_from_record(record, 'CHILDREN') # TODO Remove once migration is done!
-    return field_string
-
+# Parsing helpers
 
 def get_value_from_record(record, key):
     ''' Returns the first occurrence as value.'''
@@ -357,7 +362,7 @@ def _get_all_entries_as_dict(record, include_special_types=True):
             record_dict[key] = str(get_value_from_record(record, key))
     return record_dict
 
-# Helper
+# Handle helper
 
 def _remove_hdl_from_handle(handle):
     if handle is not None: