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

Author: tunetheweb

.github/workflows/add-to-release-notes.yml

@@ -16,6 +16,6 @@ jobs:
     if: github.repository == 'HTTPArchive/almanac.httparchive.org'
     steps:
     - name: Update release notes
-      uses: release-drafter/release-drafter@v6.1.1
+      uses: release-drafter/release-drafter@v6.2.0
       env:
         GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/linter.yml

@@ -34,6 +34,7 @@ jobs:
         uses: super-linter/super-linter/slim@v8
         env:
           DEFAULT_BRANCH: main
+          ENABLE_GITHUB_PULL_REQUEST_SUMMARY_COMMENT: false
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           VALIDATE_BASH: true
           VALIDATE_CSS: true

.github/workflows/test_website.yml

@@ -42,6 +42,7 @@ jobs:
     - name: Lint Generated HTML
       uses: super-linter/super-linter/slim@v8
       env:
+        ENABLE_GITHUB_PULL_REQUEST_SUMMARY_COMMENT: false
         FILTER_REGEX_INCLUDE: src/static/html/.*
         GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         LOG_LEVEL: DEBUG

sql/2025/webassembly/counts.sql

@@ -7,15 +7,16 @@ WITH wasmRequests AS (
     page,
     root_page,
     url,
-    REGEXP_EXTRACT(url, r'([^/]+)$') AS filename -- lowercase & extract filename between last `/` and `.` or `?`
+    REGEXP_EXTRACT(url, r'([^/]+)$') AS filename, -- lowercase & extract filename between last `/` and `.` or `?`
+    SAFE_CAST(JSON_VALUE(summary.respBodySize) AS INT64) AS respBodySize
   FROM
     `httparchive.crawl.requests`
   WHERE
-    date IN ('2021-07-01', '2022-06-01', '2024-06-01', '2025-07-01') AND
+    date IN ('2021-07-01', '2022-06-01', '2023-06-01', '2024-06-01', '2025-07-01') AND
     (
       (date IN ('2024-06-01', '2025-07-01') AND type = 'wasm') -- wasm type was added in Jan 2024
       OR
-      (date IN ('2021-07-01', '2022-06-01') AND (JSON_VALUE(summary.mimeType) = 'application/wasm' OR JSON_VALUE(summary.ext) = 'wasm'))
+      (date IN ('2021-07-01', '2022-06-01', '2023-06-01') AND (JSON_VALUE(summary.mimeType) = 'application/wasm' OR JSON_VALUE(summary.ext) = 'wasm'))
     )
 ),
 
@@ -28,7 +29,7 @@ totals AS (
   FROM
     `httparchive.crawl.requests`
   WHERE
-    date IN ('2021-07-01', '2022-06-01', '2024-06-01', '2025-07-01')
+    date IN ('2021-07-01', '2022-06-01', '2023-06-01', '2024-06-01', '2025-07-01')
   GROUP BY
     date,
     client
@@ -37,8 +38,12 @@ totals AS (
 SELECT
   date,
   client,
-  COUNT(0) AS total_wasm,
-  COUNT(DISTINCT filename) AS unique_wasm,
+  COUNT(0) AS total_wasm_requests,
+  COUNT(DISTINCT filename) AS unique_filenames,
+  -- NEW: Distinct based on full URL
+  COUNT(DISTINCT url) AS unique_urls,
+  -- NEW: Distinct based on Name + Size
+  COUNT(DISTINCT CONCAT(filename, '-', CAST(respBodySize AS STRING))) AS unique_wasm_by_size,
   COUNT(DISTINCT root_page) AS sites,
   total_sites,
   COUNT(DISTINCT root_page) / total_sites AS pct_sites,