feature: check dead links in doc CI (#2460)

* feature: one liner to check dead links

* fix: check rate limit after build

* fix: rate error

* fix: ignore intel.com links

* fix: remove ignored checks

* fix: fix broken links

* fix: fix dead link in ipynb files

* fix: fix broken links

* fix: format and add comment

Author: yuejiaointel

doc/build-doc.sh

@@ -53,3 +53,6 @@ if [[ "$*" == *"--gh-pages"* ]]; then
 else
     make html
 fi
+
+#Run the link-checker after build avoid rate limit errors
+sphinx-build -b linkcheck -j auto $SPHINXOPTS sources _build/linkcheck

doc/sources/conf.py

@@ -30,6 +30,7 @@
 # documentation root, use os.path.abspath to make it absolute, like shown here.
 #
 import os
+import re
 import sys
 
 # sys.path.insert(0, os.path.abspath("../"))
@@ -263,3 +264,13 @@ def setup(app):
 # not found 404 page
 
 notfound_urls_prefix = "/scikit-learn-intelex/"
+
+# Any link matching these regexes will be skipped by linkcheck
+linkcheck_ignore = [
+    re.compile(r"https://github\.com/.+"),  # Avoid rate error
+    re.compile(r"https://.*intel\.com/.+"),  # Avoid permission error
+]
+
+# Speed up link-check and fail faster
+linkcheck_timeout = 10
+linkcheck_workers = 8

doc/sources/daal4py.rst

@@ -1042,7 +1042,7 @@ Parameters and semantics are described in |onedal-dg-sorting|_.
 .. _onedal-dg-k-means-clustering: https://uxlfoundation.github.io/oneDAL/daal/algorithms/kmeans/k-means-clustering.html
 
 .. |onedal-dg-lbfgs| replace:: |onedal| LBFGS
-.. _onedal-dg-lbfgs: https://uxlfoundation.github.io/oneDAL/daal/algorithms/optimization-solvers/solvers/limited-memory-broyden-fletcher-goldfarb-shanno-algorithm.html
+.. _onedal-dg-lbfgs: https://uxlfoundation.github.io/oneDAL/daal/algorithms/optimization-solvers/solvers/lbfgs.html
 
 .. |onedal-dg-naive-bayes| replace:: |onedal| Naive Bayes
 .. _onedal-dg-naive-bayes: https://uxlfoundation.github.io/oneDAL/daal/algorithms/naive_bayes/naive-bayes-classifier.html

examples/notebooks/svc_adult.ipynb

@@ -92,7 +92,7 @@
    "id": "6bb14ac8",
    "metadata": {},
    "source": [
-    "Extension for Scikit-learn patching affects performance of specific Scikit-learn functionality. Refer to the [list of supported algorithms and parameters](https://uxlfoundation.github.io/scikit-learn-intelex/algorithms.html) for details. In cases when unsupported parameters are used, the package fallbacks into original Scikit-learn. If the patching does not cover your scenarios, [submit an issue on GitHub](https://github.com/uxlfoundation/scikit-learn-intelex/issues)."
+    "Extension for Scikit-learn patching affects performance of specific Scikit-learn functionality. Refer to the [list of supported algorithms and parameters](https://uxlfoundation.github.io/scikit-learn-intelex/latest/algorithms.html) for details. In cases when unsupported parameters are used, the package fallbacks into original Scikit-learn. If the patching does not cover your scenarios, [submit an issue on GitHub](https://github.com/uxlfoundation/scikit-learn-intelex/issues)."
    ]
   },
   {

examples/notebooks/tsne.ipynb

@@ -86,7 +86,7 @@
    "id": "6bb14ac8",
    "metadata": {},
    "source": [
-    "Extension for Scikit-learn patching affects performance of specific Scikit-learn functionality. Refer to the [list of supported algorithms and parameters](https://uxlfoundation.github.io/scikit-learn-intelex/algorithms.html) for details. In cases when unsupported parameters are used, the package fallbacks into original Scikit-learn. If the patching does not cover your scenarios, [submit an issue on GitHub](https://github.com/uxlfoundation/scikit-learn-intelex/issues)."
+    "Extension for Scikit-learn patching affects performance of specific Scikit-learn functionality. Refer to the [list of supported algorithms and parameters](https://uxlfoundation.github.io/scikit-learn-intelex/latest/algorithms.html) for details. In cases when unsupported parameters are used, the package fallbacks into original Scikit-learn. If the patching does not cover your scenarios, [submit an issue on GitHub](https://github.com/uxlfoundation/scikit-learn-intelex/issues)."
    ]
   },
   {