CI: check external links (excluding GH)

Author: chalin

.htmltest.yml

@@ -1,28 +1,32 @@
 DirectoryPath: public
 IgnoreDirectoryMissingTrailingSlash: true
 IgnoreAltMissing: true
+IgnoreCanonicalBrokenLinks: false
 IgnoreInternalURLs: # list of paths
-IgnoreURLs: # list of regexs to paths or URLs
+IgnoreURLs: # list of regexs of paths or URLs to be ignored
   - ^/docs/instrumentation/\w+/(api|examples)/$
   - ^/docs/instrumentation/net/(metrics-api|traces-api)/
 
   - ^https?://localhost\b
-  - ^https?://(otel-demo|traefik).localhost
-  - ^https?://(www\.)?github\b
-  - ^https://mvnrepository.com # Always yields 403 Forbidden
-
-  # Temporary as we process external links incrementally:
-  - ^https?://[^a-o]
+  - ^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
 
   # TODO: drop after fix to https://github.com/rust-lang/crates.io/issues/788
-  - ^https://crates.io/crates
-  # Invalid certificate (x509) for daocloud.io:
-  - ^https://docs.daocloud.io
+  - ^https://crates\.io/crates
   # TODO: drop after fix to https://github.com/open-telemetry/opentelemetry-specification/pull/3217
-  - ^https://golang.org/pkg/runtime/debug/#Stack
+  - ^https://golang\.org/pkg/runtime/debug/#Stack
   # TODO: drop after fix to https://github.com/micrometer-metrics/micrometer-docs/issues/239
-  - ^https://micrometer.io/docs
+  - ^https://micrometer\.io/docs
   # TODO: drop after fix to https://github.com/google/docsy/issues/1337
-  - ^https://opentelemetry.io/
+  - ^https://opentelemetry\.io/
   # TODO: drop after fix to https://github.com/open-telemetry/opentelemetry.io/issues/2354
-  - ^https://open-telemetry.github.io/opentelemetry-python/benchmarks/
+  - ^https://open-telemetry\.github\.io/opentelemetry-python/benchmarks/
+  # TODO: drop after fix to https://github.com/open-telemetry/opentelemetry.io/issues/2361
+  - ^https://www\.jaegertracing\.io/docs/latest/opentelemetry
+  # TODO: drop after fix to https://github.com/open-telemetry/opentelemetry-specification/pull/3230
+  - ^https://wikipedia\.org/wiki/Double-precision_floating-point_format
+  # Ignore links into Netlify deploy-preview servers (because the preview might not be deployed when we check)
+  - ^https://deploy-preview-\d+--opentelemetry.netlify.app/

.prettierignore

@@ -34,5 +34,4 @@ content/en/docs/instrumentation/swift
 /data
 /resources
 /scripts
-/static
 /templates

Makefile

@@ -1,6 +1,11 @@
+# Set REFCACHE to another value to disable htmltest refcache-file manipulation
+REFCACHE?=refcache
 HTMLTEST_DIR=tmp
 HTMLTEST?=htmltest # Specify as make arg if different
 HTMLTEST_ARGS?=--skip-external
+LINK_CACHE_FILE?=refcache.json
+LINK_CACHE_FILE_DEST_DIR?=static
+LINK_CACHE_FILE_SRC_DIR?=$(HTMLTEST_DIR)/.htmltest
 OTEL_GEN_REPO?=../$(shell basename $(shell pwd)).g
 
 # Use $(HTMLTEST) in PATH, if available; otherwise, we'll get a copy
@@ -15,7 +20,29 @@ default:
 	@echo "Make what? Target list:\n"
 	@make -rpn | grep '^[a-z]\S*:' | sed 's/://' | sort
 
-check-links: $(GET_LINK_CHECKER_IF_NEEDED)
+$(LINK_CACHE_FILE_SRC_DIR):
+	mkdir -p $(LINK_CACHE_FILE_SRC_DIR)
+
+refcache-restore: $(LINK_CACHE_FILE_SRC_DIR)
+ifeq (refcache, $(REFCACHE))
+	cp $(LINK_CACHE_FILE_DEST_DIR)/$(LINK_CACHE_FILE) $(LINK_CACHE_FILE_SRC_DIR)/
+else
+	@echo "SKIPPING refcache-restore"
+endif
+
+refcache-save: $(LINK_CACHE_FILE_SRC_DIR)/$(LINK_CACHE_FILE)
+ifeq (refcache, $(REFCACHE))
+	cp $(LINK_CACHE_FILE_SRC_DIR)/$(LINK_CACHE_FILE) $(LINK_CACHE_FILE_DEST_DIR)/
+	npm run prettier:no-ignore -- \
+		--write $(LINK_CACHE_FILE_DEST_DIR)/$(LINK_CACHE_FILE)
+else
+	@echo "SKIPPING refcache-save"
+endif
+
+check-links: $(GET_LINK_CHECKER_IF_NEEDED) \
+	refcache-restore check-links-only refcache-save
+
+check-links-only:
 	$(HTMLTEST) $(HTMLTEST_ARGS)
 
 clean:

content/en/blog/2022/end-user-discussion-group-apac/index.md

@@ -5,50 +5,50 @@ date: 2022-12-06
 author: "[Reese Lee](https://github.com/reese-lee)"
 ---
 
-Since July, end users have been getting together to discuss their OpenTelemetry 
-adoption and implementation practices in a vendor-netural space known as the 
-[Monthly Discussion Groups](/community/end-user/discussion-group/) 
-(also referenced as the End User Discussion Groups). 
+Since July, end users have been getting together to discuss their OpenTelemetry
+adoption and implementation practices in a vendor-netural space known as the
+[Monthly Discussion Groups](/community/end-user/discussion-group/)
+(also referenced as the End User Discussion Groups).
 
-Previously, they were only available in the EMEA and AMER regions; the End User 
-Working Group is pleased to announce that **APAC sessions will now be available, 
-starting in January 2023**! 
+Previously, they were only available in the EMEA and AMER regions; the End User
+Working Group is pleased to announce that **APAC sessions will now be available,
+starting in January 2023**!
 
 ## The what
-As mentioned above, these Discussion Groups are monthly meetings for end users 
-to discuss the challenges they're facing in their OTel implementations and to 
-learn from each other, as well as to talk about the project itself and what is 
-working, what isn't, and what they'd like to see. 
+As mentioned above, these Discussion Groups are monthly meetings for end users
+to discuss the challenges they're facing in their OTel implementations and to
+learn from each other, as well as to talk about the project itself and what is
+working, what isn't, and what they'd like to see.
 
-We encourage you to attend and ask questions to learn how other users have 
-implemented OpenTelemetry in their organizations, resolved common issues, and 
-more. Example topics that have been discussed include tail sampling, collector 
-scaling, and OpAMP; there really is no limit to the topics! We simply ask that 
-you be respectful and abide by the [Chatham House Rule](https://www.chathamhouse.org/about-us/chatham-house-rule#:~:text=The%20Rule%20reads%20as%20follows,other%20participant%2C%20may%20be%20revealed.).
+We encourage you to attend and ask questions to learn how other users have
+implemented OpenTelemetry in their organizations, resolved common issues, and
+more. Example topics that have been discussed include tail sampling, collector
+scaling, and OpAMP; there really is no limit to the topics! We simply ask that
+you be respectful and abide by the [Chatham House Rule](https://www.chathamhouse.org/about-us/chatham-house-rule).
 
 ## The why
-This group started as a result of direct feedback from end users in the community! 
-Past participants have shared with us that these have been helpful and valuable 
-for them as they migrate their observability instrumentation to OpenTelemetry. 
+This group started as a result of direct feedback from end users in the community!
+Past participants have shared with us that these have been helpful and valuable
+for them as they migrate their observability instrumentation to OpenTelemetry.
 
-Additionally, the End User Working Group is also improving the process to share 
-any collected user feedback\* with the appropriate project maintainers to help 
-improve the user experience and increase adoption. 
+Additionally, the End User Working Group is also improving the process to share
+any collected user feedback\* with the appropriate project maintainers to help
+improve the user experience and increase adoption.
 
-\*Information shared in the groups can be discussed publicly, but **not** the 
-identity of the person who said it or their affiliation. 
+\*Information shared in the groups can be discussed publicly, but **not** the
+identity of the person who said it or their affiliation.
 
 ## The when
-If this is your first time hearing about these meetings, you are invited to 
-participate in any of the upcoming sessions that fit your schedule. Look for 
-the meetings by filtering them in one of the community's publicly available 
-[calendars](https://github.com/open-telemetry/community#calendar), and duplicate 
-the event to your own. There will also be periodic reminders in the general CNCF 
-Slack `#opentelemetry` channel. 
+If this is your first time hearing about these meetings, you are invited to
+participate in any of the upcoming sessions that fit your schedule. Look for
+the meetings by filtering them in one of the community's publicly available
+[calendars](https://github.com/open-telemetry/community#calendar), and duplicate
+the event to your own. There will also be periodic reminders in the general CNCF
+Slack `#opentelemetry` channel.
 
 Upcoming sessions:
 
-* **EMEA**: every third Tuesday of the month at 11AM CET (GMT +1), join [here](https://us06web.zoom.us/j/85691064809?pwd=c0VCejh) 
+* **EMEA**: every third Tuesday of the month at 11AM CET (GMT +1), join [here](https://us06web.zoom.us/j/85691064809?pwd=c0VCejh)
   * December 20, 2022
   * January 17, 2023
 * **APAC**: every third Wednesday of the month at 11AM IST (GMT +5.5), join [here](https://us06web.zoom.us/j/82702918447?pwd=WllKc0hmdTNuelhFdlhMM1Q3TktSQT09)
@@ -58,4 +58,4 @@ Upcoming sessions:
   * December 15, 2022
   * January 19, 2023
 
-See y'all soon! 
+See y'all soon!

content/en/blog/2022/otel-demo-app-nomad/index.md

@@ -10,7 +10,7 @@ Y’all… I’m so excited, because I finally got to work on an item on my tech
 bucket list. Last week, I began the process of translating
 [OpenTelemetry (OTel) Demo App](https://github.com/open-telemetry/opentelemetry-demo)’s
 [Helm Charts](https://github.com/open-telemetry/opentelemetry-helm-charts/tree/main/charts/opentelemetry-demo)
-to [HashiCorp](https://hashicorp.com) [Nomad](https://nomadproject.io) job
+to [HashiCorp](https://hashicorp.com) [Nomad][] job
 specs. Today I’ll be talking about how to run the OpenTelemetry Demo App on
 Nomad, using my favorite Hashi-in-a-box tool,
 [HashiQube](https://rubiksqube.com/#/).
@@ -25,7 +25,7 @@ Let’s do this!
 
 Before we move on, I am assuming that you have a basic understanding of:
 
-- **[Nomad](https://nomadproject.io)**. If not, head on over to my
+- **[Nomad][]**. If not, head on over to my
   [Nomad intro post](https://storiesfromtheherd.com/just-in-time-nomad-80f57cd403ca).
   [This blog post](https://danielabaron.me/blog/nomad-tips-and-tricks/) by
   [Daniela Baron](https://danielabaron.me) is also great.
@@ -53,7 +53,7 @@ Below are the repos that we’ll be using for today’s tutorial:
 ### HashiQube Setup
 
 Before you start, just a friendly reminder that HashiQube by default runs
-[Nomad](https://nomadproject.io), [Vault](http://vaultproject.io), and
+[Nomad][], [Vault](https://www.vaultproject.io), and
 [Consul](https://consul.io) on Docker. In addition, we’ll be deploying 21 job
 specs to Nomad. This means that we’ll need a decent amount of CPU and RAM, so
 please make sure that you have enough resources allocated in your Docker
@@ -372,3 +372,5 @@ The OpenTelemetry community is always looking for contributions!
 [Join us](https://github.com/open-telemetry/community)! If you're on Mastodon,
 be sure to follow
 [OpenTelemetry on Mastodon](https://fosstodon.org/@opentelemetry)
+
+[Nomad]: https://www.nomadproject.io

package.json

@@ -6,9 +6,10 @@
     "That is, from the command line, you can use, e.g.: npm run s <arguments>."
   ],
   "scripts": {
+    "__check:links": "make --keep-going check-links",
     "_build": "hugo --cleanDestinationDir -e dev -DFE",
-    "_check:links:all": "HTMLTEST_ARGS='--log-level 1' make check-links",
-    "_check:links": "make check-links",
+    "_check:links": "HTMLTEST_ARGS='--log-level 1' npm run __check:links",
+    "_check:links:internal": "npm run __check:links",
     "_get:no": "echo SKIPPING get operation",
     "_get:submodule:non-lang": "npm run _get:submodule -- content-modules/opentelemetry-specification themes/docsy",
     "_get:submodule": "set -x && git submodule update --init ${DEPTH:- --depth 1}",
@@ -23,8 +24,8 @@
     "cd:public": "cd public &&",
     "check": "npm run all -- check:*",
     "check:formatting": "npx prettier --check .",
-    "check:links:all": "npm run _check:links:all",
     "check:links": "npm run _check:links",
+    "check:links:internal": "npm run _check:links:internal",
     "clean": "make clean",
     "cp:spec": "./scripts/content-modules/cp-pages.sh",
     "get:submodule": "npm run _get:${GET:-submodule}",
@@ -34,8 +35,8 @@
     "prebuild:preview": "run-s _prebuild check:formatting",
     "prebuild:production": "run-s _prebuild check:formatting",
     "prebuild": "npm run _prebuild",
-    "precheck:links:all": "npm run build",
     "precheck:links": "npm run build",
+    "precheck:links:internal": "npm run build",
     "prepare": "run-s get:submodule _prepare:docsy",
     "preserve:hugo": "npm run _prebuild",
     "prettier:no-ignore": "npx prettier --ignore-path ''",

static/favicons/site.webmanifest

@@ -1,19 +1,19 @@
 {
-    "name": "OpenTelemetry.io",
-    "short_name": "OTel site",
-    "icons": [
-        {
-            "src": "android-chrome-192x192.png",
-            "sizes": "192x192",
-            "type": "image/png"
-        },
-        {
-            "src": "android-chrome-512x512.png",
-            "sizes": "512x512",
-            "type": "image/png"
-        }
-    ],
-    "theme_color": "#4f62ad",
-    "background_color": "#4f62ad",
-    "display": "standalone"
+  "name": "OpenTelemetry.io",
+  "short_name": "OTel site",
+  "icons": [
+    {
+      "src": "android-chrome-192x192.png",
+      "sizes": "192x192",
+      "type": "image/png"
+    },
+    {
+      "src": "android-chrome-512x512.png",
+      "sizes": "512x512",
+      "type": "image/png"
+    }
+  ],
+  "theme_color": "#4f62ad",
+  "background_color": "#4f62ad",
+  "display": "standalone"
 }