Skip to content

Commit a15be56

Browse files
onurglrtunetheweb
andauthored
CMS 2025 sql queries (#4343)
* updated 2025 cms sql queries * Switch to July * Correct years --------- Co-authored-by: Barry Pollard <barrypollard@google.com>
1 parent c3e9245 commit a15be56

18 files changed

Lines changed: 3327 additions & 0 deletions

sql/2025/cms/cms_adoption.sql

Lines changed: 161 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,161 @@
1+
#standardSQL
2+
# CMS adoption OVER time
3+
# cms_adoption.sql
4+
5+
SELECT
6+
client,
7+
2025 AS year,
8+
COUNT(DISTINCT page) AS freq,
9+
total,
10+
COUNT(DISTINCT page) / total AS pct
11+
FROM
12+
`httparchive.crawl.pages`,
13+
UNNEST(technologies) AS technologies,
14+
UNNEST(technologies.categories) AS cats
15+
JOIN (
16+
SELECT
17+
client,
18+
COUNT(0) AS total
19+
FROM
20+
`httparchive.crawl.pages`
21+
WHERE
22+
date = '2025-07-01' AND
23+
is_root_page
24+
GROUP BY
25+
client
26+
)
27+
USING (client)
28+
WHERE
29+
cats = 'CMS' AND
30+
date = '2025-07-01' AND
31+
is_root_page
32+
GROUP BY
33+
client,
34+
total
35+
UNION ALL
36+
SELECT
37+
client,
38+
2024 AS year,
39+
COUNT(DISTINCT page) AS freq,
40+
total,
41+
COUNT(DISTINCT page) / total AS pct
42+
FROM
43+
`httparchive.crawl.pages`,
44+
UNNEST(technologies) AS technologies,
45+
UNNEST(technologies.categories) AS cats
46+
JOIN (
47+
SELECT
48+
client,
49+
COUNT(0) AS total
50+
FROM
51+
`httparchive.crawl.pages`
52+
WHERE
53+
date = '2024-06-01' AND
54+
is_root_page
55+
GROUP BY
56+
client
57+
)
58+
USING (client)
59+
WHERE
60+
cats = 'CMS' AND
61+
date = '2024-06-01' AND
62+
is_root_page
63+
GROUP BY
64+
client,
65+
total
66+
UNION ALL
67+
SELECT
68+
client,
69+
2023 AS year,
70+
COUNT(DISTINCT page) AS freq,
71+
total,
72+
COUNT(DISTINCT page) / total AS pct
73+
FROM
74+
`httparchive.crawl.pages`,
75+
UNNEST(technologies) AS technologies,
76+
UNNEST(technologies.categories) AS cats
77+
JOIN (
78+
SELECT
79+
client,
80+
COUNT(0) AS total
81+
FROM
82+
`httparchive.crawl.pages`
83+
WHERE
84+
date = '2023-06-01' AND
85+
is_root_page
86+
GROUP BY
87+
client
88+
)
89+
USING (client)
90+
WHERE
91+
cats = 'CMS' AND
92+
date = '2023-06-01' AND
93+
is_root_page
94+
GROUP BY
95+
client,
96+
total
97+
UNION ALL
98+
SELECT
99+
client,
100+
2022 AS year,
101+
COUNT(DISTINCT page) AS freq,
102+
total,
103+
COUNT(DISTINCT page) / total AS pct
104+
FROM
105+
`httparchive.crawl.pages`,
106+
UNNEST(technologies) AS technologies,
107+
UNNEST(technologies.categories) AS cats
108+
JOIN (
109+
SELECT
110+
client,
111+
COUNT(0) AS total
112+
FROM
113+
`httparchive.crawl.pages`
114+
WHERE
115+
date = '2022-06-01' AND
116+
is_root_page
117+
GROUP BY
118+
client
119+
)
120+
USING (client)
121+
WHERE
122+
cats = 'CMS' AND
123+
date = '2022-06-01' AND
124+
is_root_page
125+
GROUP BY
126+
client,
127+
total
128+
UNION ALL
129+
SELECT
130+
client,
131+
2021 AS year,
132+
COUNT(DISTINCT page) AS freq,
133+
total,
134+
COUNT(DISTINCT page) / total AS pct
135+
FROM
136+
`httparchive.crawl.pages`,
137+
UNNEST(technologies) AS technologies,
138+
UNNEST(technologies.categories) AS cats
139+
JOIN (
140+
SELECT
141+
client,
142+
COUNT(0) AS total
143+
FROM
144+
`httparchive.crawl.pages`
145+
WHERE
146+
date = '2021-07-01' AND
147+
is_root_page
148+
GROUP BY
149+
client
150+
)
151+
USING (client)
152+
WHERE
153+
cats = 'CMS' AND
154+
date = '2021-07-01' AND
155+
is_root_page
156+
GROUP BY
157+
client,
158+
total
159+
ORDER BY
160+
year DESC,
161+
pct DESC
Lines changed: 56 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,56 @@
1+
#standardSQL
2+
# All CMS popularity per geo
3+
# cms_adoption_by_geo.sql
4+
5+
WITH geo_summary AS (
6+
SELECT
7+
`chrome-ux-report`.experimental.GET_COUNTRY(country_code) AS geo,
8+
IF(device = 'desktop', 'desktop', 'mobile') AS client,
9+
origin,
10+
COUNT(DISTINCT origin) OVER (PARTITION BY country_code, IF(device = 'desktop', 'desktop', 'mobile')) AS total
11+
FROM
12+
`chrome-ux-report.materialized.country_summary`
13+
WHERE
14+
yyyymm = 202507
15+
)
16+
17+
SELECT
18+
*
19+
FROM (
20+
SELECT
21+
client,
22+
geo,
23+
COUNT(0) AS pages,
24+
ANY_VALUE(total) AS total,
25+
COUNT(0) / ANY_VALUE(total) AS pct
26+
FROM (
27+
SELECT DISTINCT
28+
geo,
29+
client,
30+
total,
31+
CONCAT(origin, '/') AS page
32+
FROM
33+
geo_summary
34+
)
35+
JOIN (
36+
SELECT
37+
client,
38+
page
39+
FROM
40+
`httparchive.crawl.pages`,
41+
UNNEST(technologies) AS technologies,
42+
UNNEST(technologies.categories) AS cats
43+
WHERE
44+
date = '2025-07-01' AND
45+
cats = 'CMS' AND
46+
is_root_page
47+
)
48+
USING (client, page)
49+
GROUP BY
50+
client,
51+
geo
52+
)
53+
WHERE
54+
pages > 1000
55+
ORDER BY
56+
pages DESC
Lines changed: 51 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,51 @@
1+
#standardSQL
2+
# CMS adoption per rank
3+
SELECT
4+
client,
5+
rank_grouping,
6+
CASE rank_grouping
7+
WHEN 1e8 THEN 'all'
8+
ELSE TRIM(CAST(rank_grouping AS STRING FORMAT '99,999,999'))
9+
END AS rank_grouping_text,
10+
COUNT(DISTINCT page) AS pages,
11+
MAX(total) AS total,
12+
COUNT(DISTINCT page) / MAX(total) AS pct
13+
FROM (
14+
SELECT
15+
client,
16+
page,
17+
rank_grouping
18+
FROM
19+
`httparchive.crawl.pages`,
20+
UNNEST(technologies) AS tech,
21+
UNNEST(tech.categories) AS category,
22+
UNNEST([1e3, 1e4, 1e5, 1e6, 1e7, 1e8]) AS rank_grouping
23+
WHERE
24+
date = '2025-07-01' AND
25+
rank <= rank_grouping AND
26+
is_root_page AND
27+
category = 'CMS'
28+
)
29+
JOIN (
30+
SELECT
31+
client,
32+
rank_grouping,
33+
COUNT(0) AS total
34+
FROM
35+
`httparchive.crawl.pages`,
36+
UNNEST([1e3, 1e4, 1e5, 1e6, 1e7, 1e8]) AS rank_grouping
37+
WHERE
38+
date = '2025-07-01' AND
39+
rank <= rank_grouping AND
40+
is_root_page
41+
GROUP BY
42+
client,
43+
rank_grouping
44+
)
45+
USING (client, rank_grouping)
46+
GROUP BY
47+
client,
48+
rank_grouping
49+
ORDER BY
50+
rank_grouping,
51+
pages DESC

0 commit comments

Comments
 (0)