diff options
| author | Terry Truong <terry06890@gmail.com> | 2022-06-08 00:19:38 +1000 |
|---|---|---|
| committer | Terry Truong <terry06890@gmail.com> | 2022-06-08 00:19:38 +1000 |
| commit | 88888983e59c5f0b19226573f06bd9dfca98d24c (patch) | |
| tree | 0c454cd1bfe3570084f9dcf26e8ddb16c88ee99a /backend/data/genEnwikiNameData.py | |
| parent | a530aa601336d8b5fd25fff14ff4cb3dae4d930b (diff) | |
Avoid some redundant enwiki-generated alt-names
Diffstat (limited to 'backend/data/genEnwikiNameData.py')
| -rwxr-xr-x | backend/data/genEnwikiNameData.py | 2 |
1 files changed, 1 insertions, 1 deletions
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") |
