Merge pull request #17 from lozuponelab/async_optional

Make asynchronous download optional
lozuponelab · Jan 17, 2024 · 1f8e92c · 1f8e92c
2 parents 0039a66 + f1ed254
commit 1f8e92c
Show file tree

Hide file tree

Showing 3 changed files with 10 additions and 6 deletions.
diff --git a/KEGG_parser/__init__.py b/KEGG_parser/__init__.py
@@ -1 +1 @@
-__version__ = '0.0.7'
+__version__ = '0.0.8'
diff --git a/KEGG_parser/downloader.py b/KEGG_parser/downloader.py
@@ -72,8 +72,11 @@ def kegg_download_manager_synchronous(list_of_ids, wait=1):
     return [raw_record for raw_records in results for raw_record in raw_records.split('///')[:-1]]
 
 
+def get_from_kegg_api(loop, list_of_ids, parser, try_async=True):
+    if try_async == False:
+        print("KEGG parser will try to download data sequentially.")
+        return [parser(raw_record) for raw_record in kegg_download_manager_synchronous(list_of_ids)]
 
-def get_from_kegg_api(loop, list_of_ids, parser):
     try:
         return [parser(raw_record) for raw_record in loop.run_until_complete(kegg_download_manager(loop, list_of_ids))]
     except ValueError:
@@ -82,10 +85,11 @@ def get_from_kegg_api(loop, list_of_ids, parser):
         time.sleep(30)
         return [parser(raw_record) for raw_record in kegg_download_manager_synchronous(list_of_ids)]
 
-def get_kegg_record_dict(list_of_ids, parser, records_file_loc=None, verbose=False):
+
+def get_kegg_record_dict(list_of_ids, parser, records_file_loc=None, verbose=False, try_async=True):
     if records_file_loc is None:
         loop = asyncio.get_event_loop()
-        records = get_from_kegg_api(loop, list_of_ids, parser)
+        records = get_from_kegg_api(loop, list_of_ids, parser, try_async=try_async)
     else:
         records = get_from_kegg_flat_file(records_file_loc, list_of_ids, parser)
     if verbose:

diff --git a/KEGG_parser/parsers.py b/KEGG_parser/parsers.py
@@ -194,9 +194,9 @@ def split_module_reaction(current_dict, current_entry_name, current_entry_data):
     'COMPOUND': add_module_orthology, 'COMMENT': return_self, 'DBLINKS': add_nested_dict
 }
 
-NOT_CAPTURED_KO_FIELDS = ('REFERENCE', 'AUTHORS', 'TITLE', 'JOURNAL', 'SEQUENCE', 'BRITE', 'SYMBOL')
+NOT_CAPTURED_KO_FIELDS = ('REFERENCE', 'AUTHORS', 'TITLE', 'JOURNAL', 'SEQUENCE', 'BRITE', 'SYMBOL', 'REACTION')
 
-NOT_CAPTURED_RN_FIELDS = ('REFERENCE', 'AUTHORS', 'TITLE', 'JOURNAL')
+NOT_CAPTURED_RN_FIELDS = ('REFERENCE', 'AUTHORS', 'TITLE', 'JOURNAL', 'BRITE')
 
 NOT_CAPTURED_CO_FIELDS = ('BRITE', 'ATOM', 'BOND', 'BRACKET', 'ORIGINAL', 'REPEAT', 'NODE', 'EDGE', 'SEQUENCE',
                           'GENE', 'ORGANISM', 'TYPE', 'EFFICACY', 'PRODUCT', 'CLASS', 'DISEASE', 'TARGET',