From d5911d77ce952e3445de1ade19cd93f070f420b2 Mon Sep 17 00:00:00 2001 From: Anastasiia Khrapal Date: Mon, 12 Oct 2026 12:40:44 +0200 Subject: [PATCH 1/2] Fix website spellcheck and link-check false positives (uber.com, dspace.mit.edu, glossary terms) Ignore proper nouns, a code variable, and US-standard "dialogue" flagged on www glossary pages; exclude bot-protected uber.com and dspace.mit.edu from lychee. Co-Authored-By: Claude Opus 5.5 --- .github/workflows/links.yml | 4 ++-- .github/workflows/links_local.yml | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/.github/workflows/links.yml b/.github/workflows/links.yml index 87156ffcecf..f60ee47d8a1 100644 --- a/.github/workflows/links.yml +++ b/.github/workflows/links.yml @@ -133,7 +133,7 @@ jobs: --builtin clear,informal,en-GB_to_en-US \ --uri-ignore-words-list "*" \ --ignore-regex '\.alls\b' \ - --ignore-words-list "Ain't,grey,writeable,MENAT,Hart,wither,Bund,DED,AKS,VAs,RepResNet,iDenfy,Idenfy,WIT,Smoot,EHR,ROUGE,ALS,iTerm,Carmel,FPR,Hach,Calle,ore,COO,MOT,crate,nd,ned,strack,dota,ane,segway,fo,gool,winn,commend,bloc,nam,afterall,skelton,goin,tread,braket,corse,SoM,couldn't,couldn,wasn't,wasn,nin,cancelled,MapPin,cann,CANN,Vektor,MITRE,Confidencial,bale,HSI,VART,GES,Linz" \ + --ignore-words-list "Ain't,grey,writeable,MENAT,Hart,wither,Bund,DED,AKS,VAs,RepResNet,iDenfy,Idenfy,WIT,Smoot,EHR,ROUGE,ALS,iTerm,Carmel,FPR,Hach,Calle,ore,COO,MOT,crate,nd,ned,strack,dota,ane,segway,fo,gool,winn,commend,bloc,nam,afterall,skelton,goin,tread,braket,corse,SoM,couldn't,couldn,wasn't,wasn,nin,cancelled,MapPin,cann,CANN,Vektor,MITRE,Confidencial,bale,HSI,VART,GES,Linz,fpr,dialogue,dialogues,SME,redner,sEH,Mata,IST,DifferNet,Sclar,Centre" \ --skip "*.pt,*.pth,*.torchscript,*.onnx,*.tflite,*.pb,*.bin,*.param,*.mlmodel,*.engine,*.npy,*.data*,*.csv,*pnnx*,*venv*,*translat*,*lock*,__pycache__*,*.ico,*.jpg,*.png,*.mp4,*.mov,/runs,/.git,./docs/mkdocs_??.yml" \ 2>&1 || true) @@ -189,7 +189,7 @@ jobs: --insecure \ --accept 100..=103,200..=299,302,401,402,403,415,429,500..=599,999 \ --exclude-all-private \ - --exclude 'https?://([a-zA-Z0-9-]+\.)*(linkedin\.com|twitter\.com|x\.com|instagram\.com|kaggle\.com|tiktok\.com|fonts\.gstatic\.com|fonts\.googleapis\.com|url\.com|tesla\.com|wellfound\.com|fda\.gov|ftc\.gov|ieee\.org|sciencedirect\.com|mckinsey\.com|st\.com|adobe\.com|dhl\.com|avangrid\.com|bhp\.com|businesswire\.com|bmw\.in|intuit\.com|epo\.org|orangepi\.org|gdpr\.eu|mvtec\.com|cv-foundation\.org|ntrs\.nasa\.gov|elib\.dlr\.de|burrsettles\.com|biomecardio\.com|glaze\.cs\.uchicago\.edu|miquido\.com|forensicexpertinvestigation\.com|newspace\.co\.in|agriplanting\.com|revistafuera\.com|ravindersingal\.com|qsdca\.com\.au|videologicanalytics\.com|gitee\.com|chemistryworld\.com|aegistechnologies\.com)([:/?#]|$)' \ + --exclude 'https?://([a-zA-Z0-9-]+\.)*(linkedin\.com|twitter\.com|x\.com|instagram\.com|kaggle\.com|tiktok\.com|fonts\.gstatic\.com|fonts\.googleapis\.com|url\.com|tesla\.com|wellfound\.com|fda\.gov|ftc\.gov|ieee\.org|sciencedirect\.com|mckinsey\.com|st\.com|adobe\.com|dhl\.com|avangrid\.com|bhp\.com|businesswire\.com|bmw\.in|intuit\.com|epo\.org|orangepi\.org|gdpr\.eu|mvtec\.com|cv-foundation\.org|ntrs\.nasa\.gov|elib\.dlr\.de|burrsettles\.com|biomecardio\.com|glaze\.cs\.uchicago\.edu|miquido\.com|forensicexpertinvestigation\.com|newspace\.co\.in|agriplanting\.com|revistafuera\.com|ravindersingal\.com|qsdca\.com\.au|videologicanalytics\.com|gitee\.com|chemistryworld\.com|aegistechnologies\.com|uber\.com|dspace\.mit\.edu)([:/?#]|$)' \ --exclude '(\.run\.app|\.cloudfunctions\.net|0\.0\.0\.0:5543/predict/from_files)' \ --github-token ${{ secrets.GITHUB_TOKEN }} \ --header "User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.6478.183 Safari/537.36" \ diff --git a/.github/workflows/links_local.yml b/.github/workflows/links_local.yml index 8030a923d95..30e6f9f176b 100644 --- a/.github/workflows/links_local.yml +++ b/.github/workflows/links_local.yml @@ -55,7 +55,7 @@ jobs: --insecure \ --accept 100..=103,200..=299,302,401,402,403,415,429,500..=599,999 \ --exclude-all-private \ - --exclude 'https?://([a-zA-Z0-9-]+\.)*(linkedin\.com|twitter\.com|x\.com|instagram\.com|kaggle\.com|tiktok\.com|fonts\.gstatic\.com|fonts\.googleapis\.com|url\.com|tesla\.com|wellfound\.com|fda\.gov|ftc\.gov|ieee\.org|sciencedirect\.com|mckinsey\.com|st\.com|adobe\.com|dhl\.com|avangrid\.com|bhp\.com|businesswire\.com|bmw\.in|intuit\.com|epo\.org|orangepi\.org|gdpr\.eu|mvtec\.com|cv-foundation\.org|ntrs\.nasa\.gov|elib\.dlr\.de|burrsettles\.com|biomecardio\.com|glaze\.cs\.uchicago\.edu|miquido\.com|forensicexpertinvestigation\.com|newspace\.co\.in|agriplanting\.com|revistafuera\.com|ravindersingal\.com|qsdca\.com\.au|videologicanalytics\.com|gitee\.com|chemistryworld\.com|aegistechnologies\.com)([:/?#]|$)' \ + --exclude 'https?://([a-zA-Z0-9-]+\.)*(linkedin\.com|twitter\.com|x\.com|instagram\.com|kaggle\.com|tiktok\.com|fonts\.gstatic\.com|fonts\.googleapis\.com|url\.com|tesla\.com|wellfound\.com|fda\.gov|ftc\.gov|ieee\.org|sciencedirect\.com|mckinsey\.com|st\.com|adobe\.com|dhl\.com|avangrid\.com|bhp\.com|businesswire\.com|bmw\.in|intuit\.com|epo\.org|orangepi\.org|gdpr\.eu|mvtec\.com|cv-foundation\.org|ntrs\.nasa\.gov|elib\.dlr\.de|burrsettles\.com|biomecardio\.com|glaze\.cs\.uchicago\.edu|miquido\.com|forensicexpertinvestigation\.com|newspace\.co\.in|agriplanting\.com|revistafuera\.com|ravindersingal\.com|qsdca\.com\.au|videologicanalytics\.com|gitee\.com|chemistryworld\.com|aegistechnologies\.com|uber\.com|dspace\.mit\.edu)([:/?#]|$)' \ --exclude '(/\$|%7B|api\.indexnow\.org)' \ --github-token ${{ secrets.GITHUB_TOKEN }} \ --header "User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.6478.183 Safari/537.36" \ @@ -76,7 +76,7 @@ jobs: --insecure \ --accept 100..=103,200..=299,302,401,402,403,415,429,500..=599,999 \ --exclude-all-private \ - --exclude 'https?://([a-zA-Z0-9-]+\.)*(linkedin\.com|twitter\.com|x\.com|instagram\.com|kaggle\.com|tiktok\.com|fonts\.gstatic\.com|fonts\.googleapis\.com|url\.com|tesla\.com|wellfound\.com|fda\.gov|ftc\.gov|ieee\.org|sciencedirect\.com|mckinsey\.com|st\.com|adobe\.com|dhl\.com|avangrid\.com|bhp\.com|businesswire\.com|bmw\.in|intuit\.com|epo\.org|orangepi\.org|gdpr\.eu|mvtec\.com|cv-foundation\.org|ntrs\.nasa\.gov|elib\.dlr\.de|burrsettles\.com|biomecardio\.com|glaze\.cs\.uchicago\.edu|miquido\.com|forensicexpertinvestigation\.com|newspace\.co\.in|agriplanting\.com|revistafuera\.com|ravindersingal\.com|qsdca\.com\.au|videologicanalytics\.com|gitee\.com|chemistryworld\.com|aegistechnologies\.com)([:/?#]|$)' \ + --exclude 'https?://([a-zA-Z0-9-]+\.)*(linkedin\.com|twitter\.com|x\.com|instagram\.com|kaggle\.com|tiktok\.com|fonts\.gstatic\.com|fonts\.googleapis\.com|url\.com|tesla\.com|wellfound\.com|fda\.gov|ftc\.gov|ieee\.org|sciencedirect\.com|mckinsey\.com|st\.com|adobe\.com|dhl\.com|avangrid\.com|bhp\.com|businesswire\.com|bmw\.in|intuit\.com|epo\.org|orangepi\.org|gdpr\.eu|mvtec\.com|cv-foundation\.org|ntrs\.nasa\.gov|elib\.dlr\.de|burrsettles\.com|biomecardio\.com|glaze\.cs\.uchicago\.edu|miquido\.com|forensicexpertinvestigation\.com|newspace\.co\.in|agriplanting\.com|revistafuera\.com|ravindersingal\.com|qsdca\.com\.au|videologicanalytics\.com|gitee\.com|chemistryworld\.com|aegistechnologies\.com|uber\.com|dspace\.mit\.edu)([:/?#]|$)' \ --exclude '(/\$|%7B|api\.indexnow\.org)' \ --github-token ${{ secrets.GITHUB_TOKEN }} \ --header "User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.6478.183 Safari/537.36" \ From cf4777497468ff80f613d310388186c825f036ba Mon Sep 17 00:00:00 2001 From: Glenn Jocher Date: Mon, 12 Oct 2026 17:49:11 +0200 Subject: [PATCH 2/2] Keep link checks after repairing source URLs in CMS --- .github/workflows/links.yml | 2 +- .github/workflows/links_local.yml | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/.github/workflows/links.yml b/.github/workflows/links.yml index f60ee47d8a1..0f6cc8baf19 100644 --- a/.github/workflows/links.yml +++ b/.github/workflows/links.yml @@ -189,7 +189,7 @@ jobs: --insecure \ --accept 100..=103,200..=299,302,401,402,403,415,429,500..=599,999 \ --exclude-all-private \ - --exclude 'https?://([a-zA-Z0-9-]+\.)*(linkedin\.com|twitter\.com|x\.com|instagram\.com|kaggle\.com|tiktok\.com|fonts\.gstatic\.com|fonts\.googleapis\.com|url\.com|tesla\.com|wellfound\.com|fda\.gov|ftc\.gov|ieee\.org|sciencedirect\.com|mckinsey\.com|st\.com|adobe\.com|dhl\.com|avangrid\.com|bhp\.com|businesswire\.com|bmw\.in|intuit\.com|epo\.org|orangepi\.org|gdpr\.eu|mvtec\.com|cv-foundation\.org|ntrs\.nasa\.gov|elib\.dlr\.de|burrsettles\.com|biomecardio\.com|glaze\.cs\.uchicago\.edu|miquido\.com|forensicexpertinvestigation\.com|newspace\.co\.in|agriplanting\.com|revistafuera\.com|ravindersingal\.com|qsdca\.com\.au|videologicanalytics\.com|gitee\.com|chemistryworld\.com|aegistechnologies\.com|uber\.com|dspace\.mit\.edu)([:/?#]|$)' \ + --exclude 'https?://([a-zA-Z0-9-]+\.)*(linkedin\.com|twitter\.com|x\.com|instagram\.com|kaggle\.com|tiktok\.com|fonts\.gstatic\.com|fonts\.googleapis\.com|url\.com|tesla\.com|wellfound\.com|fda\.gov|ftc\.gov|ieee\.org|sciencedirect\.com|mckinsey\.com|st\.com|adobe\.com|dhl\.com|avangrid\.com|bhp\.com|businesswire\.com|bmw\.in|intuit\.com|epo\.org|orangepi\.org|gdpr\.eu|mvtec\.com|cv-foundation\.org|ntrs\.nasa\.gov|elib\.dlr\.de|burrsettles\.com|biomecardio\.com|glaze\.cs\.uchicago\.edu|miquido\.com|forensicexpertinvestigation\.com|newspace\.co\.in|agriplanting\.com|revistafuera\.com|ravindersingal\.com|qsdca\.com\.au|videologicanalytics\.com|gitee\.com|chemistryworld\.com|aegistechnologies\.com)([:/?#]|$)' \ --exclude '(\.run\.app|\.cloudfunctions\.net|0\.0\.0\.0:5543/predict/from_files)' \ --github-token ${{ secrets.GITHUB_TOKEN }} \ --header "User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.6478.183 Safari/537.36" \ diff --git a/.github/workflows/links_local.yml b/.github/workflows/links_local.yml index 30e6f9f176b..8030a923d95 100644 --- a/.github/workflows/links_local.yml +++ b/.github/workflows/links_local.yml @@ -55,7 +55,7 @@ jobs: --insecure \ --accept 100..=103,200..=299,302,401,402,403,415,429,500..=599,999 \ --exclude-all-private \ - --exclude 'https?://([a-zA-Z0-9-]+\.)*(linkedin\.com|twitter\.com|x\.com|instagram\.com|kaggle\.com|tiktok\.com|fonts\.gstatic\.com|fonts\.googleapis\.com|url\.com|tesla\.com|wellfound\.com|fda\.gov|ftc\.gov|ieee\.org|sciencedirect\.com|mckinsey\.com|st\.com|adobe\.com|dhl\.com|avangrid\.com|bhp\.com|businesswire\.com|bmw\.in|intuit\.com|epo\.org|orangepi\.org|gdpr\.eu|mvtec\.com|cv-foundation\.org|ntrs\.nasa\.gov|elib\.dlr\.de|burrsettles\.com|biomecardio\.com|glaze\.cs\.uchicago\.edu|miquido\.com|forensicexpertinvestigation\.com|newspace\.co\.in|agriplanting\.com|revistafuera\.com|ravindersingal\.com|qsdca\.com\.au|videologicanalytics\.com|gitee\.com|chemistryworld\.com|aegistechnologies\.com|uber\.com|dspace\.mit\.edu)([:/?#]|$)' \ + --exclude 'https?://([a-zA-Z0-9-]+\.)*(linkedin\.com|twitter\.com|x\.com|instagram\.com|kaggle\.com|tiktok\.com|fonts\.gstatic\.com|fonts\.googleapis\.com|url\.com|tesla\.com|wellfound\.com|fda\.gov|ftc\.gov|ieee\.org|sciencedirect\.com|mckinsey\.com|st\.com|adobe\.com|dhl\.com|avangrid\.com|bhp\.com|businesswire\.com|bmw\.in|intuit\.com|epo\.org|orangepi\.org|gdpr\.eu|mvtec\.com|cv-foundation\.org|ntrs\.nasa\.gov|elib\.dlr\.de|burrsettles\.com|biomecardio\.com|glaze\.cs\.uchicago\.edu|miquido\.com|forensicexpertinvestigation\.com|newspace\.co\.in|agriplanting\.com|revistafuera\.com|ravindersingal\.com|qsdca\.com\.au|videologicanalytics\.com|gitee\.com|chemistryworld\.com|aegistechnologies\.com)([:/?#]|$)' \ --exclude '(/\$|%7B|api\.indexnow\.org)' \ --github-token ${{ secrets.GITHUB_TOKEN }} \ --header "User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.6478.183 Safari/537.36" \ @@ -76,7 +76,7 @@ jobs: --insecure \ --accept 100..=103,200..=299,302,401,402,403,415,429,500..=599,999 \ --exclude-all-private \ - --exclude 'https?://([a-zA-Z0-9-]+\.)*(linkedin\.com|twitter\.com|x\.com|instagram\.com|kaggle\.com|tiktok\.com|fonts\.gstatic\.com|fonts\.googleapis\.com|url\.com|tesla\.com|wellfound\.com|fda\.gov|ftc\.gov|ieee\.org|sciencedirect\.com|mckinsey\.com|st\.com|adobe\.com|dhl\.com|avangrid\.com|bhp\.com|businesswire\.com|bmw\.in|intuit\.com|epo\.org|orangepi\.org|gdpr\.eu|mvtec\.com|cv-foundation\.org|ntrs\.nasa\.gov|elib\.dlr\.de|burrsettles\.com|biomecardio\.com|glaze\.cs\.uchicago\.edu|miquido\.com|forensicexpertinvestigation\.com|newspace\.co\.in|agriplanting\.com|revistafuera\.com|ravindersingal\.com|qsdca\.com\.au|videologicanalytics\.com|gitee\.com|chemistryworld\.com|aegistechnologies\.com|uber\.com|dspace\.mit\.edu)([:/?#]|$)' \ + --exclude 'https?://([a-zA-Z0-9-]+\.)*(linkedin\.com|twitter\.com|x\.com|instagram\.com|kaggle\.com|tiktok\.com|fonts\.gstatic\.com|fonts\.googleapis\.com|url\.com|tesla\.com|wellfound\.com|fda\.gov|ftc\.gov|ieee\.org|sciencedirect\.com|mckinsey\.com|st\.com|adobe\.com|dhl\.com|avangrid\.com|bhp\.com|businesswire\.com|bmw\.in|intuit\.com|epo\.org|orangepi\.org|gdpr\.eu|mvtec\.com|cv-foundation\.org|ntrs\.nasa\.gov|elib\.dlr\.de|burrsettles\.com|biomecardio\.com|glaze\.cs\.uchicago\.edu|miquido\.com|forensicexpertinvestigation\.com|newspace\.co\.in|agriplanting\.com|revistafuera\.com|ravindersingal\.com|qsdca\.com\.au|videologicanalytics\.com|gitee\.com|chemistryworld\.com|aegistechnologies\.com)([:/?#]|$)' \ --exclude '(/\$|%7B|api\.indexnow\.org)' \ --github-token ${{ secrets.GITHUB_TOKEN }} \ --header "User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.6478.183 Safari/537.36" \