From 94a8ad9b067e5a2c442ce47ce72d1a53eb444160 Mon Sep 17 00:00:00 2001 From: Terry Truong Date: Mon, 23 Jan 2023 18:00:43 +1100 Subject: Clean up some docs and naming inconsistencies --- backend/tol_data/enwiki/gen_pageview_data.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'backend/tol_data/enwiki/gen_pageview_data.py') diff --git a/backend/tol_data/enwiki/gen_pageview_data.py b/backend/tol_data/enwiki/gen_pageview_data.py index ce3b674..8aee1cc 100755 --- a/backend/tol_data/enwiki/gen_pageview_data.py +++ b/backend/tol_data/enwiki/gen_pageview_data.py @@ -12,7 +12,7 @@ from collections import defaultdict import bz2, sqlite3 PAGEVIEW_FILES = glob.glob('./pageviews/pageviews-*-user.bz2') -DUMP_INDEX_DB = 'dumpIndex.db' +DUMP_INDEX_DB = 'dump_index.db' DB_FILE = 'pageview_data.db' def genData(pageviewFiles: list[str], dumpIndexDb: str, dbFile: str) -> None: @@ -42,6 +42,7 @@ def genData(pageviewFiles: list[str], dumpIndexDb: str, dbFile: str) -> None: if namespaceRegex.match(title) is not None: continue # Update map + title = title.replace('_', ' ') titleToViews[title] += viewCount print(f'Found {len(titleToViews)} titles') # -- cgit v1.2.3