(whimsy) branch master updated: Default to showing transitive references separately

[sebb]

This is an automated email from the ASF dual-hosted git repository.

sebb pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/whimsy.git


The following commit(s) were added to refs/heads/master by this push:
     new 8bb0d446 Default to showing transitive references separately
8bb0d446 is described below

commit 8bb0d446c3516f76d376f22504cbfabc909b7763
Author: Sebb <s...@apache.org>
AuthorDate: Sat Apr 20 15:05:13 2024 +0100

    Default to showing transitive references separately
---
 www/members/page-scanner.cgi | 31 +++++++++++++++++++++++++++----
 1 file changed, 27 insertions(+), 4 deletions(-)

diff --git a/www/members/page-scanner.cgi b/www/members/page-scanner.cgi
index 0df899c8..6bda8d67 100755
--- a/www/members/page-scanner.cgi
+++ b/www/members/page-scanner.cgi
@@ -10,13 +10,14 @@ require_relative '../../tools/asf-site-check'
 
 print "Content-type: text/plain; charset=UTF-8\r\n\r\n"
 
-# puts ENV['REQUEST_URI']
+DIVIDER=' <= '
+
 qs = ENV['QUERY_STRING']
 if qs =~ %r{^url=(https?://[^&]+)(?:&(.+))?}
   url = $1
   option = $2
   # we only want full URLs
-  option = 'all' unless option == 'showurl'
+  option = 'allref' unless %w{all showurl}.include? option
   print "Checking the page #{url}\n\n"
   puts "The following references were found to hosts other than apache.org and 
apachecon.com"
   puts "The first column shows if the host is recognised as being under ASF 
control according to"
@@ -25,9 +26,31 @@ if qs =~ %r{^url=(https?://[^&]+)(?:&(.+))?}
   cmd = ['node', '/srv/whimsy/tools/scan-page.js', url, option]
   out, err, status = Open3.capture3(*cmd)
   if status.success?
+    if out == ''
+      puts "No external references found"
+    else
+      puts "Top-level references:"
+    end
+    extras = Hash.new {|h,k| h[k] = Hash.new}
     out.split("\n").each do |url|
-      print ASFDOMAIN.asfurl?(url) ? 'OK ' : 'NO '
-      puts url
+      p1, p2 = url.split(DIVIDER)
+      if p2
+        extras[p2][p1]=1
+      else
+        print ASFDOMAIN.asfurl?(url) ? 'OK ' : 'NO '
+        puts url
+      end
+    end
+    if extras.size > 0
+      puts ""
+      puts "Transitive references:"
+      extras.each do |k, v|
+        puts "Loaded by: "+k
+        v.each do |url,_|
+          print ASFDOMAIN.asfurl?(url) ? 'OK ' : 'NO '
+          puts url
+          end
+      end
     end
   else
     puts err.scan(/^Error:.+/).first || err # Show only the Error line if 
present