whole process

.github/workflows/check-urls.yml

@@ -41,8 +41,24 @@ jobs:
         tmp=$(echo "${{ env.ignore_file_patterns }}" | tr '\n' ' ')
         echo "ignore_file_patterns=$tmp" >> $GITHUB_OUTPUT
 
-    - name: Checkout Repository
+    - name: Checkout Repo for PR branch
+      if: ${{ github.event_name == 'pull_request' }}
+      uses: actions/checkout@v4
+
+    - name: Checkout Repo for link check
+      if: ${{ github.event_name != 'pull_request' }}
       uses: actions/checkout@v4
+      with:
+        ref: 'sched-link-checks'
+
+    - name: Sync main to link check branch
+      if: ${{ github.event_name != 'pull_request' }}
+      run: | 
+        git config user.name 'github-actions'
+        git config user.email '[email protected]'
+        git fetch origin main
+        git merge origin/main --no-edit -X thiers
+        git push origin sched-link-checks
 
     - name: Get Changed Files (for PRs)
       if: ${{ github.event_name == 'pull_request' }}
@@ -62,7 +78,6 @@ jobs:
           echo "ignore_file_patterns=${{ steps.setup_vars.outputs.ignore_file_patterns }}" >> $GITHUB_OUTPUT
         fi
 
-      #exclude_patterns: ${{ steps.setup_vars.outputs.ignore_url_patterns }}
     - name: Check URLs in selected files
       run: |
         for f in ${{ steps.file_list.outputs.files }}; do
@@ -78,11 +93,27 @@ jobs:
             cat linkchecker.out >> linkchecker-all.out
         done
 
+    - name: Process log
+      run: |
+        python utils/LinkChecker/cklcresults.py ${{ github.event_name }}
+
+    - name: Finalize Check Status
+      if: ${{ github.event_name == 'pull_request' }}
+      run: |
+        [ $(wc -c utils/LinkChecker/bad_links.txt) -gt 0 ] && exit 1
+      
     - name: Upload artifact
+      if: always()
       uses: actions/upload-artifact@v4
       with:
-        name: my-artifact
-        path: linkchecker-all.out
+        name: bad-links
+        path: utils/LinkChecker/bad_links.txt
+
+    - name: Update link logs
+      if: ${{ github.event_name != 'pull_request' }}
+      run: |
+        git commit -m 'Update link logs'
+        git push origin sched-link-checks
 
 #
 # Keep the recurring failures and definitely bad lists in repo on
@@ -102,6 +133,7 @@ jobs:
 # Report success if definitely bad list is empty, otherwise failure
 # generate email with links or actual data
 #
+# you have to use file:// on command-line to checker
 
 # bare URLs in markdown are not actually links and will not be checked. Many
 # markdown renderers and browsers will recognize these and handle them as links

utils/LinkChecker/cklcresults.py

@@ -1,4 +1,4 @@
-import ast, datetime
+import ast, datetime, sys
 
 def AddEntryToRecord(cr, key, line):
     assert key not in cr.keys(), f"duplicate key {key}, {line}, {cr}"
@@ -18,15 +18,22 @@ def AddRecord(records, cr, key, line, now):
 def AppendLineToPreviousKey(cr, key, line):
     cr[key] += line
 
+#
+# Handle command-line args to this script
+ghEvent = ""
+if len(sys.argv) > 1:
+    ghEvent = sys.argv[1]
+
+#
 # Open log and read all lines into a python list object
 f = open('linkchecker-all.out','r')
 lines = f.readlines()
 f.close()
 
 #
-# Process contents of log, looking for groups of lines defining
-# each link tested and its results. Each link is its own dict
-# object (record) and we append each record to a list, records.
+# Process contents of linkchecker log, looking for groups of lines
+# defining each link tested and its results. Each link is its own dict
+# object (record) and we append each record to a list named records.
 #
 records = []
 currentRecord = {}
@@ -59,18 +66,20 @@ def AppendLineToPreviousKey(cr, key, line):
 # Open trouble_links.txt and read all contents
 #
 trouble_links = []
-with open('../../utils/LinkChecker/trouble_links.txt','r') as file:
-    for line in file:
-        trouble_links.append(ast.literal_eval(line.strip()))
+if ghEvent != "pull_request":
+    with open('../../utils/LinkChecker/trouble_links.txt','r') as file:
+        for line in file:
+            trouble_links.append(ast.literal_eval(line.strip()))
 trouble_links_original_size = len(trouble_links)
 
 #
 # Open bad_links.log 
 #
 bad_links = []
-with open('../../utils/LinkChecker/bad_links.txt','r') as file:
-    for line in file:
-        bad_links.append(ast.literal_eval(line.strip()))
+if ghEvent != "pull_request":
+    with open('../../utils/LinkChecker/bad_links.txt','r') as file:
+        for line in file:
+            bad_links.append(ast.literal_eval(line.strip()))
 bad_links_original_size = len(bad_links)
 
 #
@@ -91,6 +100,10 @@ def AppendLineToPreviousKey(cr, key, line):
         else:
             linkOK = False
 
+    if ghEvent == "pull_request" and not linkOK:
+        bad_links += [r]
+        continue
+
     prev_trouble_records = [x for x in trouble_links if x['URL'] == r['URL']]
 
     if linkOK:
@@ -118,7 +131,7 @@ def AppendLineToPreviousKey(cr, key, line):
 #
 # Update trouble_links file if modified
 #
-if len(trouble_links) != trouble_links_original_size:
+if ghEvent != "pull_request" and len(trouble_links) != trouble_links_original_size:
     with open('../../utils/LinkChecker/trouble_links.txt','w') as file:
         for rec in trouble_links:
             file.write(str(rec)+'\n')