From 5de5fb93e50fe9006221b30ac4a66f1be0db82e7 Mon Sep 17 00:00:00 2001 From: Terry Truong Date: Sun, 11 Sep 2022 14:55:42 +1000 Subject: 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 --- backend/tol_data/gen_pop_data.py | 45 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) create mode 100755 backend/tol_data/gen_pop_data.py (limited to 'backend/tol_data/gen_pop_data.py') diff --git a/backend/tol_data/gen_pop_data.py b/backend/tol_data/gen_pop_data.py new file mode 100755 index 0000000..e6a646e --- /dev/null +++ b/backend/tol_data/gen_pop_data.py @@ -0,0 +1,45 @@ +#!/usr/bin/python3 + +""" +Reads enwiki page view info from a database, and stores it +as node popularity values in the database. +""" + +import os, sqlite3 + +PAGEVIEWS_DB = os.path.join('enwiki', 'pageview_data.db') +DB_FILE = 'data.db' + +def genData(pageviewsDb: str, dbFile: str) -> None: + 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() + +if __name__ == '__main__': + import argparse + parser = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter) + args = parser.parse_args() + # + genData(PAGEVIEWS_DB, DB_FILE) -- cgit v1.2.3