From 4cd0ce6857e57ee684da075954eb7a667234e221 Mon Sep 17 00:00:00 2001 From: Francesco Casalegno Date: Fri, 25 Feb 2022 15:09:01 +0100 Subject: [PATCH 1/2] Log info on processed batch (arxiv topic-extract) --- src/bluesearch/database/topic.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/src/bluesearch/database/topic.py b/src/bluesearch/database/topic.py index c0d714411..1da143f15 100644 --- a/src/bluesearch/database/topic.py +++ b/src/bluesearch/database/topic.py @@ -359,6 +359,9 @@ def get_topics_for_arxiv_articles( ids = list(id_2_path.keys()) article_topics = {} for i_start in range(0, len(ids), batch_size): + logger.info( + f"Processing batch {i_start//batch_size} out of {len(ids)//batch_size}" + ) # Get a slice of arXiv ids i_end = i_start + batch_size id_list = ids[i_start:i_end] From 9d7ba97021f7684ae00a15fd63b1f01ba52bafb1 Mon Sep 17 00:00:00 2001 From: Francesco Casalegno Date: Fri, 25 Feb 2022 15:39:43 +0100 Subject: [PATCH 2/2] Extra info if logging is -vv --- src/bluesearch/database/topic.py | 1 + 1 file changed, 1 insertion(+) diff --git a/src/bluesearch/database/topic.py b/src/bluesearch/database/topic.py index 1da143f15..a17bcbfe8 100644 --- a/src/bluesearch/database/topic.py +++ b/src/bluesearch/database/topic.py @@ -371,6 +371,7 @@ def get_topics_for_arxiv_articles( "id_list": ",".join(id_list), "max_results": str(batch_size), } + logger.debug(f"Requesting topic info on arxiv ids: {id_list}") res = requests.get(base_url, params) res.raise_for_status()