diff --git a/README.md b/README.md index b758a3b..5c42e6f 100644 --- a/README.md +++ b/README.md @@ -154,6 +154,18 @@ e.g. write to `neo4j://localhost:7687`: python -m dblp_crawler -k video -k edge -p 27d5dc70280c8628f181a7f8881912025f808256 -a 1681457 neo4j --uri neo4j://localhost:7687 ``` +#### Tips + +Without index, NEO4J query will be very very slow. So before you start, you should add some index: + +```cql +CREATE INDEX publication_title_hash_index FOR (p:Publication) ON (p.title_hash); +CREATE INDEX publication_dblp_key_index FOR (p:Publication) ON (p.dblp_key); +CREATE INDEX publication_paper_id_index FOR (p:Publication) ON (p.paperId); +CREATE INDEX person_author_id_index FOR (p:Person) ON (p.authorId); +CREATE INDEX person_dblp_pid_index FOR (p:Person) ON (p.dblp_pid); +``` + ### Get initial paper list or author list from a Neo4J database ```sh diff --git a/setup.py b/setup.py index d8c12c4..96e07b6 100644 --- a/setup.py +++ b/setup.py @@ -15,7 +15,7 @@ setup( name='citation_crawler', - version='2.5.3', + version='2.7', author='yindaheng98', author_email='yindaheng98@gmail.com', url='https://github.com/yindaheng98/citation-crawler',