Skip to content

Add normalize media wiki link tables (statistics) #356

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
loka1 merged 3 commits into from
May 31, 2024
Merged

Add normalize media wiki link tables (statistics) #356

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
2706bd8
update query of list_of_portals_by_number_of_articles
loka1 May 31, 2024
c593570
update query of list_of_contributors.py
loka1 May 31, 2024
05eb83a
update query of articles_in_which_there_is_a_link_to_user_pages
loka1 May 31, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions tasks/statistics/WikiProject/list_of_contributors.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,11 +5,12 @@
query = """select actor_name as "username", count(rev_actor) as "edit_count",
IF(actor_name in (

select replace(pl_title,"_"," ") from pagelinks
select replace(lt_title,"_"," ") from pagelinks
join page on page.page_id = pagelinks.pl_from
inner join linktarget ON lt_id = pl_target_id
where page.page_namespace in (4)
and page_title like "مشروع_ويكي_العراق/المساهمون"
and pl_namespace in (2)
and lt_namespace in (2)
and pl_from_namespace in (4)

), "YES", "NO") as "in_WikiProject"
Expand Down
39 changes: 27 additions & 12 deletions tasks/statistics/articles_in_which_there_is_a_link_to_user_pages.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,18 +1,33 @@
from tasks.statistics.module import UpdatePage, ArticleTables, index

# Set the parameters for the update
query = """select page.page_title as ll_page_title,pagelinks.pl_title as ll_page_to_title,pagelinks.pl_namespace as ll_pl_namespace
from page
inner join pagelinks
on pagelinks.pl_from = page.page_id
where pagelinks.pl_from_namespace = 0
and (pagelinks.pl_namespace = 2 or pagelinks.pl_namespace = 3)
and page.page_namespace = 0
and page.page_is_redirect = 0
and page.page_id not in (select templatelinks.tl_from from templatelinks
join linktarget on linktarget.lt_id = templatelinks.tl_target_id
where linktarget.lt_title in (select pl_title from pagelinks where pl_from = 9043549) and templatelinks.tl_from_namespace = 0 )
and page.page_title not in (select pl_title from pagelinks where pl_from = 9043549);"""
query = """SELECT page.page_title AS ll_page_title,
linktarget.lt_title AS ll_page_to_title,
linktarget.lt_namespace AS ll_pl_namespace
FROM page
INNER JOIN pagelinks ON pagelinks.pl_from = page.page_id
inner join linktarget ON lt_id = pl_target_id
WHERE pagelinks.pl_from_namespace = 0
AND (linktarget.lt_namespace = 2
OR linktarget.lt_namespace = 3)
AND page.page_namespace = 0
AND page.page_is_redirect = 0
AND page.page_id not in
(SELECT templatelinks.tl_from
FROM templatelinks
JOIN linktarget ON linktarget.lt_id = templatelinks.tl_target_id
WHERE linktarget.lt_title in
(SELECT lt_title
FROM pagelinks
inner join linktarget ON lt_id = pl_target_id
WHERE pl_from = 9043549)
AND templatelinks.tl_from_namespace = 0 )
AND page.page_title not in
(SELECT lt_title
FROM pagelinks
inner join linktarget ON lt_id = pl_target_id
WHERE pl_from = 9043549
);"""
file_path = 'stub/articles_in_which_there_is_a_link_to_user_pages.txt'
page_name = "ويكيبيديا:تقارير قاعدة البيانات/مقالات يوجد فيها وصلة إلى صفحات المستخدمين"

Expand Down
6 changes: 5 additions & 1 deletion tasks/statistics/list_of_portals_by_number_of_articles.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,11 @@

# Set the parameters for the update
query = """SELECT main.page_title as portal_name, COUNT(*) - 1 as sub_page_count,
(SELECT COUNT(*) FROM pagelinks WHERE pl_title = main.page_title and pl_from_namespace = 0 and pl_namespace = 100) as links_count
(
SELECT COUNT(*) FROM pagelinks
inner join linktarget ON lt_id = pl_target_id
WHERE lt_title = main.page_title and pl_from_namespace = 0 and lt_namespace = 100
) as links_count
FROM page AS p
INNER JOIN (
SELECT page_title
Expand Down