aboutsummaryrefslogtreecommitdiff
path: root/backend/tolData/genPopData.py
diff options
context:
space:
mode:
authorTerry Truong <terry06890@gmail.com>2022-09-11 14:55:42 +1000
committerTerry Truong <terry06890@gmail.com>2022-09-11 15:04:14 +1000
commit5de5fb93e50fe9006221b30ac4a66f1be0db82e7 (patch)
tree2567c25c902dbb40d44419805cebb38171df47fa /backend/tolData/genPopData.py
parentdaccbbd9c73a5292ea9d6746560d7009e5aa666d (diff)
Add backend unit tests
- Add unit testing code in backend/tests/ - Change to snake-case for script/file/directory names - Use os.path.join() instead of '/' - Refactor script code into function defs and a main-guard - Make global vars all-caps Some fixes: - For getting descriptions, some wiki redirects weren't properly resolved - Linked images were sub-optimally propagated - Generation of reduced trees assumed a wiki-id association implied a description - Tilo.py had potential null dereferences by not always using a reduced node set - EOL image downloading didn't properly wait for all threads to end when finishing
Diffstat (limited to 'backend/tolData/genPopData.py')
-rwxr-xr-xbackend/tolData/genPopData.py39
1 files changed, 0 insertions, 39 deletions
diff --git a/backend/tolData/genPopData.py b/backend/tolData/genPopData.py
deleted file mode 100755
index 3bb1325..0000000
--- a/backend/tolData/genPopData.py
+++ /dev/null
@@ -1,39 +0,0 @@
-#!/usr/bin/python3
-
-import sqlite3
-
-import argparse
-parser = argparse.ArgumentParser(description="""
-Reads enwiki page view info from a database, and stores it
-as node popularity values in the database.
-""", formatter_class=argparse.RawDescriptionHelpFormatter)
-args = parser.parse_args()
-
-pageviewsDb = 'enwiki/pageviewData.db'
-dbFile = 'data.db'
-
-dbCon = sqlite3.connect(dbFile)
-dbCur = dbCon.cursor()
-
-print('Getting view counts')
-pdbCon = sqlite3.connect(pageviewsDb)
-pdbCur = pdbCon.cursor()
-nodeToViews: dict[str, int] = {} # Maps node names to counts
-iterNum = 0
-for wikiId, views in pdbCur.execute('SELECT id, views from views'):
- iterNum += 1
- if iterNum % 1e4 == 0:
- print(f'At iteration {iterNum}') # Reached 1.6e6
- #
- row = dbCur.execute('SELECT name FROM wiki_ids WHERE id = ?', (wikiId,)).fetchone()
- if row is not None:
- nodeToViews[row[0]] = views
-pdbCon.close()
-
-print(f'Writing {len(nodeToViews)} entries to db')
-dbCur.execute('CREATE TABLE node_pop (name TEXT PRIMARY KEY, pop INT)')
-for nodeName, views in nodeToViews.items():
- dbCur.execute('INSERT INTO node_pop VALUES (?, ?)', (nodeName, views))
-
-dbCon.commit()
-dbCon.close()