Merge branch 'main' of github.com:HTTPArchive/almanac.httparchive.org into production

Author: tunetheweb

sql/2024/seo/outgoing_links_by_rank -2024.sql

@@ -1,76 +1,70 @@
 #standardSQL
 # Internal and external link metrics by quantile and rank
-
-CREATE TEMPORARY FUNCTION getOutgoingLinkMetrics(payload STRING)
-RETURNS STRUCT<
-  same_site INT64,
-  same_property INT64,
-  other_property INT64
-> LANGUAGE js AS '''
-var result = {same_site: 0,
-              same_property: 0,
-              other_property: 0};
-
-try {
-    var $ = JSON.parse(payload);
-    var wpt_bodies  = JSON.parse($._wpt_bodies);
-
-    if (!wpt_bodies){
-        return result;
-    }
-
-    var anchors = wpt_bodies.anchors;
-
-    if (anchors){
-      result.same_site = anchors.rendered.same_site;
-      result.same_property = anchors.rendered.same_property;
-      result.other_property = anchors.rendered.other_property;
-    }
-
-} catch (e) {}
-
-return result;
-''';
-
 WITH page_metrics AS (
   SELECT
     client,
     page,
-    getOutgoingLinkMetrics(payload) AS outgoing_link_metrics,
-    JSON_EXTRACT_SCALAR(JSON_EXTRACT_SCALAR(payload, '$._wpt_bodies'), '$.is_root_page') AS is_root_page
-  FROM
-    `httparchive.all.pages`
+    is_root_page,
+    IF(rank <= rank_bucket, rank_bucket, NULL) AS rank,
+    ANY_VALUE(custom_metrics.wpt_bodies.anchors) AS anchors
+  FROM httparchive.crawl.pages,
+    UNNEST([1000, 10000, 100000, 1000000, 10000000, 100000000]) AS rank_bucket
   WHERE
-    DATE = '2024-06-01'
+    date = '2024-06-01'
+  GROUP BY
+    client,
+    page,
+    is_root_page,
+    rank
+  HAVING rank IS NOT NULL
+), metric_details AS (
+  SELECT
+    client,
+    is_root_page,
+    percentile,
+    rank,
+    APPROX_QUANTILES(INT64(anchors.rendered.same_site), 1000)[OFFSET(percentile * 10)] AS outgoing_links_same_site,
+    APPROX_QUANTILES(INT64(anchors.rendered.same_property), 1000)[OFFSET(percentile * 10)] AS outgoing_links_same_property,
+    APPROX_QUANTILES(INT64(anchors.rendered.other_property), 1000)[OFFSET(percentile * 10)] AS outgoing_links_other_property
+  FROM page_metrics,
+    UNNEST([10, 25, 50, 75, 90, 100]) AS percentile
+  GROUP BY
+    client,
+    is_root_page,
+    rank,
+    percentile
+  ORDER BY
+    client,
+    is_root_page,
+    rank,
+    percentile
+), page_counts AS (
+  SELECT
+    client,
+    is_root_page,
+    rank,
+    COUNT(DISTINCT page) AS total_pages
+  FROM page_metrics
+  GROUP BY
+    client,
+    is_root_page,
+    rank
 )
 
 SELECT
   client,
-  CASE
-    WHEN is_root_page = 'false' THEN 'Secondary Page'
-    ELSE 'Homepage'
-  END AS page_type,
+  is_root_page,
+  rank,
+  total_pages,
   percentile,
-  rank_grouping,
-  CASE
-    WHEN rank_grouping = 100000000 THEN 'all'
-    ELSE FORMAT("%'d", rank_grouping)
-  END AS ranking,
-  COUNT(DISTINCT page) AS pages,
-  APPROX_QUANTILES(outgoing_link_metrics.same_site, 1000)[OFFSET(percentile * 10)] AS outgoing_links_same_site,
-  APPROX_QUANTILES(outgoing_link_metrics.same_property, 1000)[OFFSET(percentile * 10)] AS outgoing_links_same_property,
-  APPROX_QUANTILES(outgoing_link_metrics.other_property, 1000)[OFFSET(percentile * 10)] AS outgoing_links_other_property
-FROM
-  page_metrics,
-  UNNEST([10, 25, 50, 75, 90, 100]) AS percentile,
-  UNNEST([1000, 10000, 100000, 1000000, 10000000, 100000000]) AS rank_grouping
-GROUP BY
-  client,
-  page_type,
-  rank_grouping,
-  percentile
+  outgoing_links_same_site,
+  outgoing_links_same_property,
+  outgoing_links_other_property
+FROM metric_details
+LEFT JOIN page_counts
+USING (client, is_root_page, rank)
 ORDER BY
   client,
-  page_type,
-  rank_grouping,
+  is_root_page,
+  rank,
   percentile

src/config/contributors.json

@@ -626,11 +626,13 @@
   },
   "b_atish": {
     "name": "Beatriz González Mellídez",
+    "avatar_url": "756480",
     "teams": {
       "2024": [
         "reviewers"
       ]
     },
+    "github": "bgonzalez",
     "twitter": "b_atish",
     "linkedin": "beatrizgonzalezm",
     "website": "https://medium.com/@b_atish"
@@ -1985,8 +1987,7 @@
         "analysts",
         "authors"
       ]
-    },
-    "twitter": "SilentJMA"
+    }
   },
   "jroakes": {
     "avatar_url": "10191545",
@@ -3047,6 +3048,9 @@
       ],
       "2022": [
         "designers"
+      ],
+      "2024": [
+        "designers"
       ]
     }
   },
@@ -3088,6 +3092,7 @@
     "avatar_url": "116832",
     "github": "mgifford",
     "linkedin": "mgifford",
+    "bluesky": "mgifford.bsky.social",
     "mastodon": "https://mastodon.social/@mgifford",
     "name": "Mike Gifford",
     "teams": {

src/config/last_updated.json

@@ -758,8 +758,8 @@
   },
   "en/2024/chapters/cdn.html": {
     "date_published": "2024-11-11T00:00:00.000Z",
-    "date_modified": "2024-11-11T00:00:00.000Z",
-    "hash": "65d8d20990cc3ff5ab6975659151646b"
+    "date_modified": "2024-11-13T00:00:00.000Z",
+    "hash": "a518330b7083e972202dcdfcfe34fbad"
   },
   "en/2024/chapters/cms.html": {
     "date_published": "2024-11-11T00:00:00.000Z",

src/content/en/2024/cdn.md

@@ -9,7 +9,7 @@ analysts: [pgjaiganesh, AlexMoening]
 translators: []
 results: https://docs.google.com/spreadsheets/d/15YXQQjyoQ0Bnfw9KNSz_YuGDiCfW978_WKEHvDXjdm4/
 joeviggiano_bio: Joe Viggiano is a Principal Solutions Architect at Amazon Web Services helping Media & Entertainment customers deliver media content at scale.
-pgjaiganesh_bio: Jaiganesh Girinathan is a Principal Edge Solutions Architect at Amazon Web Services.
+pgjaiganesh_bio: Jaiganesh Girinathan is a Principal Solutions Architect at Amazon Web Services with the mission to help customers deliver a fast and secure digital experience.
 AlexMoening_bio: Alex Moening is a Senior Edge Solutions Architect at Amazon Web Services.
 featured_quote: The benefits of utilizing CDNs have expanded beyond simple performance improvements. In 2024, CDNs play a crucial role in enabling global scalability, enhancing security postures, and facilitating the deployment of complex, distributed applications. By pushing more logic to the edge, businesses can create more responsive and personalized user experiences while reducing the load on origin servers.
 featured_stat_1: 70%