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

Author: tunetheweb

.github/linters/.python-lint

@@ -31,10 +31,6 @@ persistent=yes
 # Specify a configuration file.
 #rcfile=
 
-# When enabled, pylint would attempt to guess common misconfiguration and emit
-# user-friendly hints instead of false-positive error messages
-suggestion-mode=yes
-
 # Allow loading of arbitrary C extensions. Extensions are imported into the
 # active Python interpreter and may run arbitrary code.
 unsafe-load-any-extension=no
@@ -470,5 +466,6 @@ valid-metaclass-classmethod-first-arg=mcs
 [EXCEPTIONS]
 
 # Exceptions that will emit a warning when being caught. Defaults to
-# "Exception"
-overgeneral-exceptions=Exception
+# ["builtins.BaseException", "builtins.Exception"]
+overgeneral-exceptions = builtins.BaseException,
+                         builtins.Exception

.github/workflows/compress-images.yml

@@ -53,13 +53,14 @@ jobs:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           compressOnly: ${{ github.event_name != 'pull_request' }}
           jpegProgressive: true
+          minPctChange: '10.0'
       - name: Create Pull Request
         # If it's not a pull request then commit any changes as a new PR
         if: |
           github.event_name != 'pull_request' &&
           steps.calibre.outputs.markdown != ''
         id: cpr
-        uses: peter-evans/create-pull-request@v7
+        uses: peter-evans/create-pull-request@v8
         with:
           title: Auto Compress Images
           branch-suffix: timestamp

.github/workflows/predeploy.yml

@@ -67,7 +67,7 @@ jobs:
         npm run ebooks
     - name: Upload PDF artifact
       if: ${{ github.event.inputs.ebooks == 'true' }}
-      uses: actions/upload-artifact@v5
+      uses: actions/upload-artifact@v6
       with:
         name: pdfs
         path: ./src/static/pdfs/*.pdf
@@ -79,7 +79,7 @@ jobs:
         npm run timestamps
     - name: Create Pull Request
       id: cpr
-      uses: peter-evans/create-pull-request@v7
+      uses: peter-evans/create-pull-request@v8
       with:
         title: Pre-deploy Updates
         branch-suffix: timestamp

sql/.sqlfluff

@@ -28,7 +28,7 @@ exclude_rules = AL01,AL04,AL07,AL09,AM03,AM05,AM08,CP02,CP03,CV02,CV12,LT05,LT09
 # ST08 - Sometimes clearer to include brackets for complex COUNT(DISTINCT) cases
 # ST11 - Doesn't consider wildcards in SELECT. Issue: https://github.com/sqlfluff/sqlfluff/issues/6511
 
-large_file_skip_byte_limit = 40000
+large_file_skip_byte_limit = 1120000
 # CPU processes to use while linting.
 # If positive, just implies number of processes.
 # If negative or zero, implies number_of_cpus - specifed_number.
@@ -52,14 +52,13 @@ extended_capitalisation_policy = upper
 
 [sqlfluff:rules:convention.blocked_words]
 # Regex of blocked SQL that should not be used.
-# Can be overridden with `-- noqa: CV09` for those chapters using secondary pages
+# Can be overridden with `-- noqa: CV09` for those chapters using other dates
 # TABLESAMPLE - sometimes used for testing. Shouldn't be used in production as not random.
 # sample_data - sometimes used for testing. Shouldn't be used in production.
-# Block 2022_05_12 (contains secondary pages)
-# Block 2022_06_09 (contains secondary pages)
-# Block 2022_07_01 (probably forgot to update month to June for 2022)
-# Block 2021_06_01 (probably forgot to update month to July for 2021)
-blocked_regex = (TABLESAMPLE|sample_data|2022_?05_?12|2022_?06_?09|2022_?07_?01|2021_?06_?01)
+# The Web Almanac has run in different months due to timing or delays. This
+# means it's easy to use the wrong month by copying a previous query and only
+# updating the year and not the month. Block those months to warn about this.
+blocked_regex = (TABLESAMPLE|sample_data|2025-?08-?01|2025-?06-?01|2024-?08-?01|2024-?07-?01|2022-?08-?01|2022-?07-?01|2021-?06-?01|2021-?08-?01|2020-?07-?01)
 
 [sqlfluff:rules:convention.count_rows]
 prefer_count_0 = True

sql/2020/cms/core_web_vitals_distribution.sql

@@ -36,7 +36,7 @@ ON
   IF(device = 'desktop', 'desktop', 'mobile') = client
 WHERE
   # The CrUX 202008 dataset is not available until September 8.
-  date = '2020-07-01'
+  date = '2020-07-01' -- noqa: CV09
 GROUP BY
   client,
   cms

sql/2020/cms/core_web_vitals_passing.sql

@@ -61,7 +61,7 @@ ON
   IF(device = 'desktop', 'desktop', 'mobile') = client
 WHERE
   # The CrUX 202008 dataset is not available until September 8.
-  date = '2020-07-01'
+  date = '2020-07-01' -- noqa: CV09
 GROUP BY
   client,
   cms

sql/2021/media/video_source_types.sql

@@ -11,7 +11,7 @@ FROM
   UNNEST(REGEXP_EXTRACT_ALL(body, '(?i)(<video.*?</video>)')) AS video,
   UNNEST(REGEXP_EXTRACT_ALL(video, r'(?i)type\s*=\s*["\'](video/[^\'";?]*)')) AS video_type
 WHERE
-  date = '2021-08-01' AND
+  date = '2021-08-01' AND -- noqa: CV09
   firstHtml
 GROUP BY
   client,

sql/2021/media/video_tag_and_js_player.sql

@@ -43,7 +43,7 @@ FROM (
     FROM
       `httparchive.almanac.requests`
     WHERE
-      date = '2021-08-01' AND
+      date = '2021-08-01' AND -- noqa: CV09
       type = 'script'
     GROUP BY
       client,

sql/2022/accessibility/focus_outline_0.sql

@@ -59,7 +59,7 @@ FROM (
     `httparchive.almanac.parsed_css`,
     UNNEST(getFocusStylesOutline0(css)) AS sets_outline_0
   WHERE
-    date = '2022-07-01'
+    date = '2022-07-01' -- noqa: CV09
   GROUP BY
     client,
     page

sql/2022/accessibility/focus_visible.sql

@@ -73,7 +73,7 @@ FROM (
   LEFT JOIN
     UNNEST(getSelectorParts(css).pseudo_class) AS pseudo_class
   WHERE
-    date = '2022-07-01' AND
+    date = '2022-07-01' AND -- noqa: CV09
     # Limit the size of the CSS to avoid OOM crashes.
     LENGTH(css) < 0.1 * 1024 * 1024
   GROUP BY