WIP: Test pattern for detecting and excluding duplicated gems

Just a rough estimate for how this could work using existing pattern. More to come...

Author: donoghuc

rakelib/artifacts.rake

@@ -82,6 +82,36 @@ namespace "artifact" do
     res
   end
 
+  def duplicated_gems_exclude_paths
+    shared_gems_path = 'vendor/jruby/lib/ruby/gems/shared/gems'
+    bundle_gems_path = 'vendor/bundle/jruby/*/gems'
+
+    exclusions = []
+    shared_gem_names = Dir.glob(File.join(shared_gems_path, '*')).map do |path|
+      match = File.basename(path).match(/^(.+?)-\d+/)
+      match ? match[1] : nil
+    end.compact
+
+    bundle_gem_names = Dir.glob(File.join(bundle_gems_path, '*')).map do |path|
+      match = File.basename(path).match(/^(.+?)-\d+/)
+      match ? match[1] : nil
+    end.compact
+
+    duplicates = shared_gem_names & bundle_gem_names
+    puts "Adding duplicate gems to exclude path: #{duplicates.sort.join(', ')}"
+
+    duplicates.each do |gem_name|
+      # remove contents as well as top level directory of bundled gems
+      gem_content_path = "vendor/jruby/lib/ruby/gems/shared/gems/#{gem_name}-*/**/*"
+      gem_path = "vendor/jruby/lib/ruby/gems/shared/gems/#{gem_name}-*"
+      spec_path = "vendor/jruby/lib/ruby/gems/shared/specifications/#{gem_name}-*.gemspec"
+      exclusions << gem_content_path
+      exclusions << gem_path
+      exclusions << spec_path
+    end
+    exclusions
+  end
+
   def default_exclude_paths
     return @exclude_paths if @exclude_paths
 
@@ -101,18 +131,8 @@ namespace "artifact" do
     @exclude_paths << 'vendor/**/gems/**/Gemfile.lock'
     @exclude_paths << 'vendor/**/gems/**/Gemfile'
 
-    @exclude_paths << 'vendor/jruby/lib/ruby/gems/shared/gems/rake-*'
-    # exclude ruby-maven-libs 3.3.9 jars until JRuby ships with >= 3.8.9
-    @exclude_paths << 'vendor/bundle/jruby/**/gems/ruby-maven-libs-3.3.9/**/*'
-
-    # remove this after JRuby includes rexml 3.3.x
-    @exclude_paths << 'vendor/jruby/lib/ruby/gems/shared/gems/rexml-3.2.5/**/*'
-    @exclude_paths << 'vendor/jruby/lib/ruby/gems/shared/specifications/rexml-3.2.5.gemspec'
-
-    # remove this after JRuby includes net-imap-0.2.4+
-    @exclude_paths << 'vendor/jruby/lib/ruby/gems/shared/specifications/net-imap-0.2.3.gemspec'
-    @exclude_paths << 'vendor/jruby/lib/ruby/gems/shared/gems/net-imap-0.2.3/**/*'
-
+    @exclude_paths.concat(duplicated_gems_exclude_paths)
+    puts "Full exclude_paths list: #{@exclude_paths}"
     @exclude_paths.freeze
   end