Find violations in ERB templates

Gemfile.lock

@@ -1,8 +1,9 @@
 PATH
   remote: .
   specs:
-    query_packwerk (0.1.25)
+    query_packwerk (0.1.26)
       coderay
+      herb (>= 0.9)
       packwerk
       parse_packwerk
       rubocop
@@ -52,6 +53,12 @@ GEM
     diff-lcs (1.6.0)
     drb (2.2.1)
     erubi (1.13.1)
+    herb (0.11.0-aarch64-linux-gnu)
+    herb (0.11.0-aarch64-linux-musl)
+    herb (0.11.0-arm64-darwin)
+    herb (0.11.0-x86_64-darwin)
+    herb (0.11.0-x86_64-linux-gnu)
+    herb (0.11.0-x86_64-linux-musl)
     i18n (1.14.7)
       concurrent-ruby (~> 1.0)
     io-console (0.8.0)

lib/query_packwerk.rb

@@ -2,6 +2,7 @@
 # frozen_string_literal: true
 
 require 'sorbet-runtime'
+require 'herb'
 require 'parse_packwerk'
 require 'rubocop'
 

lib/query_packwerk/file_cache.rb

@@ -9,7 +9,9 @@ module QueryPackwerk
   class FileCache
     extend T::Sig
 
-    RUBY_FILE = T.let(/\.(rb|rake)\z/, Regexp)
+    # The files packwerk parses as Ruby, from Packwerk::Parsers::Factory
+    RUBY_FILE = T.let(/(\.(rb|rake|builder|gemspec|ru)|Gemfile|Rakefile)\z/, Regexp)
+    ERB_FILE = T.let(/\.erb\z/, Regexp)
 
     sig { void }
     def initialize
@@ -62,12 +64,18 @@ def set(cache_name, key:, value:)
 
     sig { params(file_name: String).returns(RuboCop::AST::Node) }
     def get_file_ast(file_name)
-      @file_ast_cache[file_name] ||= ast_from(get_file(file_name))
+      @file_ast_cache[file_name] ||= begin
+        source = processed_source(ruby_source(file_name))
+        warn_unparseable(file_name, source) unless source.valid_syntax?
+
+        # The AST is also nil for source with no code, like a template that's only HTML
+        source.ast || ast_from('x')
+      end
     end
 
     sig { params(file_name: String).returns(String) }
     def get_file(file_name)
-      @file_cache[file_name] ||= if RUBY_FILE.match?(file_name) && File.exist?(file_name)
+      @file_cache[file_name] ||= if (RUBY_FILE.match?(file_name) || ERB_FILE.match?(file_name)) && File.exist?(file_name)
                                    File.read(file_name)
                                  else
                                    'x'
@@ -84,7 +92,7 @@ def get_all_const_occurrences(file_name:, class_name:)
       absolute_const_node = ast_from(class_name)
       relative_const_node = ast_from(class_name.delete_prefix('::'))
 
-      @file_const_cache[const_key] = get_file_ast(file_name).each_descendant.select do |node|
+      @file_const_cache[const_key] = get_file_ast(file_name).each_node.select do |node|
         next false unless node.const_type?
 
         node == absolute_const_node || node == relative_const_node
@@ -133,10 +141,32 @@ def get_full_anonymous_sources(file_name:, class_name:)
 
     private
 
+    # Blanks out everything in an ERB template except its Ruby code, so line numbers still match the template
+    sig { params(file_name: String).returns(String) }
+    def ruby_source(file_name)
+      source = get_file(file_name)
+      return source unless ERB_FILE.match?(file_name)
+
+      Herb.extract_ruby(source, semicolons: true, comments: false, preserve_positions: true)
+    end
+
+    sig { params(string: String).returns(RuboCop::ProcessedSource) }
+    def processed_source(string)
+      RuboCop::ProcessedSource.new(string, RUBY_VERSION.to_f)
+    end
+
+    sig { params(file_name: String, source: RuboCop::ProcessedSource).void }
+    def warn_unparseable(file_name, source)
+      error = source.diagnostics.find { |diagnostic| diagnostic.level == :error }
+      location = error ? "#{file_name}:#{error.location.line} (#{error.message})" : file_name
+
+      warn "Could not parse #{location}, so its violations are not included"
+    end
+
     # Turns a string into a Ruby AST
     sig { params(string: String).returns(RuboCop::AST::Node) }
     def ast_from(string)
-      RuboCop::ProcessedSource.new(string, RUBY_VERSION.to_f).ast
+      processed_source(string).ast
     end
 
     # We can find a constant, but by going up its parents we can find the full call chain.

lib/query_packwerk/version.rb

@@ -2,5 +2,5 @@
 # frozen_string_literal: true
 
 module QueryPackwerk
-  VERSION = '0.1.25'
+  VERSION = '0.1.26'
 end

lib/query_packwerk/violation.rb

@@ -9,8 +9,6 @@ module QueryPackwerk
   class Violation
     extend T::Sig
 
-    # This does not play nicely with ERB files which may have violations
-    RUBY_FILE = T.let(/\.(rb|rake)\z/, Regexp)
     ALL_CAPS = T.let(/\A[A-Z_]+\z/, Regexp)
 
     sig { returns(QueryPackwerk::Package) }
@@ -168,13 +166,15 @@ def sources_with_contexts(start_offset: 3, end_offset: 3)
       load_cache!
 
       file_sources = files.flat_map do |file_name|
+        lines = @file_cache.get_file(file_name).lines
+
         @file_cache.get_full_sources(file_name: file_name, class_name: class_name).map do |s|
           line_number = s.loc.line
-          start_pos = line_number - start_offset
-          end_pos = line_number + end_offset
+          start_pos = [line_number - start_offset, 1].max
+          end_pos = [line_number + end_offset, lines.size].min
 
           location = "#{file_name}:#{s.loc.line} (L#{start_pos}..#{end_pos})"
-          context = @file_cache.get_file(file_name).lines.slice(start_pos..end_pos)
+          context = lines[(start_pos - 1)...end_pos]
           full_context = unindent((context || ['']).join)
 
           [@file_cache.anonymize_arguments(s.source), "> #{location}\n\n#{full_context}"]

lib/query_packwerk/violations.rb

@@ -192,7 +192,9 @@ def anonymous_sources_with_locations
     def sources_with_contexts(start_offset: 3, end_offset: 3)
       load_sources!
 
-      deep_merge_hash_groups(@original_collection) { |v| [v.class_name, v.sources_with_contexts] }
+      deep_merge_hash_groups(@original_collection) do |v|
+        [v.class_name, v.sources_with_contexts(start_offset:, end_offset:)]
+      end
     end
 
     sig { params(start_offset: Integer, end_offset: Integer).returns(String) }

query_packwerk.gemspec

@@ -34,6 +34,7 @@ Gem::Specification.new do |spec|
   spec.require_paths = ['lib']
 
   spec.add_dependency 'coderay'
+  spec.add_dependency 'herb', '>= 0.9'
   spec.add_dependency 'packwerk'
   spec.add_dependency 'parse_packwerk'
   spec.add_dependency 'rubocop'