CI: check non-resource & non-issue related links into GitHub (#2366)

Co-authored-by: Phillip Carter <pcarter@fastmail.com>

.htmltest.yml

@@ -1,3 +1,4 @@
+CacheExpires: 2200h # ~ 3 months
 DirectoryPath: public
 IgnoreDirectoryMissingTrailingSlash: true
 IgnoreAltMissing: true
@@ -14,9 +15,16 @@ IgnoreURLs: # list of regexs of paths or URLs to be ignored
   - ^https?://127\.0\.0\.1\b
   - ^https?://(otel-demo|traefik)\.localhost
 
-  - ^https?://(www\.)?github\b # TODO: process GitHub links too
-  - ^https?://(www\.)?linkedin\.com\b # Always yields 999 Request Denied
-  - ^https://mvnrepository\.com # Always yields 403 Forbidden
+  - ^https://(www\.)?linkedin\.com\b # Always yields 999 Request Denied
+  - ^https://(www\.)?mvnrepository\.com # Always yields 403 Forbidden
+
+  # Ignore Docsy-generated GitHub links:
+  - ^https?://github\.com/.*?/.*?/(new|edit)/ # view-page, edit-source etc
+  # TODO: drop after fix to https://github.com/google/docsy/issues/1432
+  - ^https://github.com/open-telemetry/opentelemetry.io/commit/ # last mod
+
+  # Ignore links to GH repo content for now.
+  - ^https?://github\.com/.*?/.*?/(blob|tree)/
 
   # TODO: drop after fix to https://github.com/rust-lang/crates.io/issues/788
   - ^https://crates\.io/crates

content/en/blog/2022/apisix/index.md

@@ -2,9 +2,7 @@
 title: Apache APISIX Integrates with OpenTelemetry to Collect Tracing Data
 linkTitle: Apache APISIX-Opentelemetry Integration
 date: 2022-03-26
-author: >-
-  [Haochao Zhuang](https://github.com/dmsolr),
-  [Fei Han](https://github.com/hf400159)
+author: "[Haochao Zhuang](https://github.com/dmsolr), Fei Han"
 canonical_url: https://apisix.apache.org/blog/2022/02/28/apisix-integration-opentelemetry-plugin/
 spelling: cSpell:ignore APISIX
 ---

content/en/docs/instrumentation/ruby/_index.md

@@ -14,11 +14,11 @@ weight: 24
 OpenTelemetry Ruby is in use by a number of companies, including:
 
 - [Heroku](https://heroku.com)
-- [GitHub](https://github.com/)
-- [Fulcrum](https://www.fulcrumapp.com/)
-- [Puppet](https://puppet.com/)
+- [GitHub](https://github.com)
+- [Fulcrum](https://www.fulcrumapp.com)
+- [Puppet](https://puppet.com)
 - [Shopify](https://shopify.com)
-- [TableCheck](https://www.tablecheck.com/)
+- [TableCheck](https://www.tablecheck.com)
 - [Dropbox DocSend](https://www.docsend.com)
 
 If you would like to add your name to this list, please feel free to submit a pull request.

package.json

@@ -30,7 +30,7 @@
     "clean": "make clean",
     "cp:spec": "./scripts/content-modules/cp-pages.sh",
     "diff:check": "git diff --name-only --exit-code || (echo; echo 'WARNING: the files above have not been committed'; echo)",
-    "diff:fail": "git diff --name-only --exit-code || (echo; echo 'ERROR: the files above have changed. Locally rerun `npm run test` and commit changes'; echo; exit 1)",
+    "diff:fail": "git diff --name-only --exit-code || (echo; echo 'ERROR: the files above have changed. Locally rerun `npm run test` and commit changes'; echo; git diff | head -100; exit 1)",
     "get:submodule": "npm run _get:${GET:-submodule}",
     "make:public": "make public ls-public",
     "postbuild:preview": "npm run _check:links",