From 88888983e59c5f0b19226573f06bd9dfca98d24c Mon Sep 17 00:00:00 2001 From: Terry Truong Date: Wed, 8 Jun 2022 00:19:38 +1000 Subject: Avoid some redundant enwiki-generated alt-names --- backend/data/genEnwikiNameData.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'backend/data') diff --git a/backend/data/genEnwikiNameData.py b/backend/data/genEnwikiNameData.py index fd50338..b5d8670 100755 --- a/backend/data/genEnwikiNameData.py +++ b/backend/data/genEnwikiNameData.py @@ -41,7 +41,7 @@ for (nodeName, wikiId) in nodeToWikiId.items(): " INNER JOIN redirects r1 ON p1.id = r1.id" \ " INNER JOIN pages p2 ON r1.target = p2.title WHERE p2.id = ?" for (name,) in enwikiCur.execute(query, (wikiId,)): - if altNameRegex.fullmatch(name) != None: + if altNameRegex.fullmatch(name) != None and name.lower() != nodeName: nodeToAltNames[nodeName].add(name.lower()) numAltNames += 1 print(f"Found {numAltNames} alt-names") -- cgit v1.2.3