diff options
| author | Terry Truong <terry06890@gmail.com> | 2022-08-30 12:27:42 +1000 |
|---|---|---|
| committer | Terry Truong <terry06890@gmail.com> | 2022-08-30 12:27:42 +1000 |
| commit | e8e58a3bb9dc233dacf573973457c5b48d369503 (patch) | |
| tree | 242500ca304c5afbb7e6506e61da4c4dfff0b175 /backend/tolData/dbpedia/genDescData.py | |
| parent | 930c12d33e1093f874a4beb4d6376621e464e8c0 (diff) | |
Add scripts for generating eol/enwiki mappings
- New data sources: OTOL taxonomy, EOL provider-ids, Wikidata dump
- Add 'node_iucn' table
- Remove 'redirected' field from 'wiki_ids' table
- Make 'eol_ids' table have 'name' as the primary key
- Combine name-generation scripts into genNameData.py
- Combine description-generation scripts into genDescData.py
Diffstat (limited to 'backend/tolData/dbpedia/genDescData.py')
| -rwxr-xr-x | backend/tolData/dbpedia/genDescData.py | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/backend/tolData/dbpedia/genDescData.py b/backend/tolData/dbpedia/genDescData.py index a23199d..8756a40 100755 --- a/backend/tolData/dbpedia/genDescData.py +++ b/backend/tolData/dbpedia/genDescData.py @@ -41,6 +41,7 @@ with bz2.open(labelsFile, mode='rt') as file: print("Reading/storing wiki page ids") dbCur.execute("CREATE TABLE ids (iri TEXT PRIMARY KEY, id INT)") +dbCur.execute("CREATE INDEX ids_idx ON ids(id)") idLineRegex = re.compile(r'<([^>]+)> <[^>]+> "(\d+)".*\n') lineNum = 0 with bz2.open(idsFile, mode='rt') as file: |