[CI] Fix link checking for all builds (#5551)

Author: chalin

.htmltest.yml

@@ -8,16 +8,16 @@ CheckMailto: false
 TestFilesConcurrently: true
 IgnoreDirs:
   # DO NOT EDIT! IgnoreDirs list is auto-generated from markdown file front matter.
-  # 2024-11-03 The following entry is for `en` pages only. Other locales do
-  # not currently require it.
-  - ^blog/(\d+/)?page/\d+
+  # Ignore blog index pages for all locales and in all blog sections (top-level and years)
+  - ^(../)?blog/(\d+/)?page/\d+
   # TODO drop next line after https://github.com/open-telemetry/opentelemetry.io/issues/5423 is fixed for ja pages:
   - ^ja/docs/concepts/instrumentation/libraries/
   # TODO drop next line after https://github.com/open-telemetry/opentelemetry.io/issues/5423 is fixed for pt pages:
   - ^pt/docs/concepts/instrumentation/libraries/
   # DO NOT EDIT! IgnoreDirs list is auto-generated from markdown file front matter.
 IgnoreInternalURLs: # list of paths
 IgnoreURLs: # list of regexs of paths or URLs to be ignored
+  - /index.xml$ # Ignore rel="alternative" links to RSS feeds
   - ^/api$
   - ^((/..)?/docs/languages/\w+|\.\.)/(api|examples|registry)/$
   - ^(/..)?/docs/collector/registry/$

content/en/blog/_index.md

@@ -8,8 +8,8 @@ redirects:
   - { from: 'index.xml', to: '2024/index.xml 301!' }
 outputs: [HTML, RSS]
 htmltest:
+  # 2024-11-07 DO NOT COPY the following IgnoreDirs to non-en pages because handles all locales.
   IgnoreDirs:
-    # 2024-11-03 The following entry is for `en` pages only. Other locales do
-    # not currently require it.
-    - ^blog/(\d+/)?page/\d+
+    # Ignore blog index pages for all locales and in all blog sections (top-level and years)
+    - ^(../)?blog/(\d+/)?page/\d+
 ---

layouts/partials/hooks/head-end.html

@@ -22,6 +22,6 @@
       {{ end -}}
     {{ end -}}
   {{ end -}}
-  <link rel="canonical" href="{{ $canonicalURL }}">
+  <link rel="canonical" href="{{ $canonicalURL }}" data-proofer-ignore>
 
 {{- end -}}

package.json

@@ -77,16 +77,14 @@
     "log:check:links": "npm run check:links | tee tmp/build-log.txt",
     "make:public": "make public ls-public",
     "netlify-build:preview": "npm run seq -- build:preview diff:check",
-    "netlify-build:production": "npm run build:production",
+    "netlify-build:production": "npm run seq -- build:production diff:check",
     "postget:submodule": "git submodule",
-    "postnetlify-build:production": "git restore .htmltest.yml && npm run diff:check",
     "prebuild:preview": "npm run _prebuild",
     "prebuild:production": "npm run _prebuild",
     "prebuild": "npm run _prebuild",
     "precheck:links:internal": "npm run build && npm run update:htmltest-config",
     "precheck:links": "npm run build && npm run update:htmltest-config",
     "prefix:submodules": "npm run update:submodule",
-    "prenetlify-build:production": "echo 'IgnoreTagAttribute: rel' >> .htmltest.yml",
     "prepare": "npm run seq -- get:submodule _prepare:docsy",
     "preserve:hugo": "npm run _prebuild",
     "preserve:netlify": "npm run seq -- _prebuild _install:netlify-cli",

scripts/htmltest-config.pl

@@ -42,11 +42,12 @@ sub extract_htmltest_config {
         return;
     }
 
-    shift @htmltest_config;
+    do {
+      shift @htmltest_config;
+    } until !@htmltest_config # No more config
+       || $htmltest_config[0] !~ /^\s*#/; # Non-comment line
 
-    if (@htmltest_config >= 1 && $htmltest_config[0] =~ /^IgnoreDirs:/i) {
-      return _extract_ignore_dirs($file_path, @htmltest_config)
-    }
+    return _extract_ignore_dirs($file_path, @htmltest_config) if $htmltest_config[0] =~ /^IgnoreDirs:/i;
 
     # TODO: Add support for `IgnoreURLs`.