rubocop-ast 0.0.2 → 0.4.0

data/lib/rubocop/ast/processed_source.rb

@@ -0,0 +1,285 @@
+# frozen_string_literal: true
+
+require 'digest/sha1'
+
+# rubocop:disable Metrics/ClassLength
+module RuboCop
+  module AST
+    # ProcessedSource contains objects which are generated by Parser
+    # and other information such as disabled lines for cops.
+    # It also provides a convenient way to access source lines.
+    class ProcessedSource
+      STRING_SOURCE_NAME = '(string)'
+
+      attr_reader :path, :buffer, :ast, :comments, :tokens, :diagnostics,
+                  :parser_error, :raw_source, :ruby_version
+
+      def self.from_file(path, ruby_version)
+        file = File.read(path, mode: 'rb')
+        new(file, ruby_version, path)
+      end
+
+      def initialize(source, ruby_version, path = nil)
+        # Defaults source encoding to UTF-8, regardless of the encoding it has
+        # been read with, which could be non-utf8 depending on the default
+        # external encoding.
+        source.force_encoding(Encoding::UTF_8) unless source.encoding == Encoding::UTF_8
+
+        @raw_source = source
+        @path = path
+        @diagnostics = []
+        @ruby_version = ruby_version
+        @parser_error = nil
+
+        parse(source, ruby_version)
+      end
+
+      def ast_with_comments
+        return if !ast || !comments
+
+        @ast_with_comments ||= Parser::Source::Comment.associate(ast, comments)
+      end
+
+      # Returns the source lines, line break characters removed, excluding a
+      # possible __END__ and everything that comes after.
+      def lines
+        @lines ||= begin
+          all_lines = @buffer.source_lines
+          last_token_line = tokens.any? ? tokens.last.line : all_lines.size
+          result = []
+          all_lines.each_with_index do |line, ix|
+            break if ix >= last_token_line && line == '__END__'
+
+            result << line
+          end
+          result
+        end
+      end
+
+      def [](*args)
+        lines[*args]
+      end
+
+      def valid_syntax?
+        return false if @parser_error
+
+        @diagnostics.none? { |d| %i[error fatal].include?(d.level) }
+      end
+
+      # Raw source checksum for tracking infinite loops.
+      def checksum
+        Digest::SHA1.hexdigest(@raw_source)
+      end
+
+      # @deprecated Use `comments.each`
+      def each_comment(&block)
+        comments.each(&block)
+      end
+
+      # @deprecated Use `comment_at_line`, `each_comment_in_lines`, or `comments.find`
+      def find_comment(&block)
+        comments.find(&block)
+      end
+
+      # @deprecated Use `tokens.each`
+      def each_token(&block)
+        tokens.each(&block)
+      end
+
+      # @deprecated Use `tokens.find`
+      def find_token(&block)
+        tokens.find(&block)
+      end
+
+      def file_path
+        buffer.name
+      end
+
+      def blank?
+        ast.nil?
+      end
+
+      # @return [Comment, nil] the comment at that line, if any.
+      def comment_at_line(line)
+        comment_index[line]
+      end
+
+      # @return [Boolean] if the given line number has a comment.
+      def line_with_comment?(line)
+        comment_index.include?(line)
+      end
+
+      # Enumerates on the comments contained with the given `line_range`
+      def each_comment_in_lines(line_range)
+        return to_enum(:each_comment_in_lines, line_range) unless block_given?
+
+        line_range.each do |line|
+          if (comment = comment_index[line])
+            yield comment
+          end
+        end
+      end
+
+      # @return [Boolean] if any of the lines in the given `source_range` has a comment.
+      # Consider using `each_comment_in_lines` instead
+      def contains_comment?(source_range)
+        each_comment_in_lines(source_range.line..source_range.last_line).any?
+      end
+      # @deprecated use contains_comment?
+      alias commented? contains_comment?
+
+      # @deprecated Use `each_comment_in_lines`
+      # Should have been called `comments_before_or_at_line`. Doubtful it has of any valid use.
+      def comments_before_line(line)
+        each_comment_in_lines(0..line).to_a
+      end
+
+      def start_with?(string)
+        return false if self[0].nil?
+
+        self[0].start_with?(string)
+      end
+
+      def preceding_line(token)
+        lines[token.line - 2]
+      end
+
+      def current_line(token)
+        lines[token.line - 1]
+      end
+
+      def following_line(token)
+        lines[token.line]
+      end
+
+      def line_indentation(line_number)
+        lines[line_number - 1]
+          .match(/^(\s*)/)[1]
+          .to_s
+          .length
+      end
+
+      def tokens_within(range_or_node)
+        begin_index = first_token_index(range_or_node)
+        end_index = last_token_index(range_or_node)
+        sorted_tokens[begin_index..end_index]
+      end
+
+      def first_token_of(range_or_node)
+        sorted_tokens[first_token_index(range_or_node)]
+      end
+
+      def last_token_of(range_or_node)
+        sorted_tokens[last_token_index(range_or_node)]
+      end
+
+      private
+
+      def comment_index
+        @comment_index ||= {}.tap do |hash|
+          comments.each { |c| hash[c.location.line] = c }
+        end
+      end
+
+      def parse(source, ruby_version)
+        buffer_name = @path || STRING_SOURCE_NAME
+        @buffer = Parser::Source::Buffer.new(buffer_name, 1)
+
+        begin
+          @buffer.source = source
+        rescue EncodingError => e
+          @parser_error = e
+          @ast = nil
+          @comments = []
+          @tokens = []
+          return
+        end
+
+        @ast, @comments, @tokens = tokenize(create_parser(ruby_version))
+      end
+
+      def tokenize(parser)
+        begin
+          ast, comments, tokens = parser.tokenize(@buffer)
+          ast ||= nil # force `false` to `nil`, see https://github.com/whitequark/parser/pull/722
+        rescue Parser::SyntaxError
+          # All errors are in diagnostics. No need to handle exception.
+          comments = []
+          tokens = []
+        end
+
+        ast&.complete!
+        tokens.map! { |t| Token.from_parser_token(t) }
+
+        [ast, comments, tokens]
+      end
+
+      # rubocop:disable Metrics/MethodLength
+      def parser_class(ruby_version)
+        case ruby_version
+        when 2.4
+          require 'parser/ruby24'
+          Parser::Ruby24
+        when 2.5
+          require 'parser/ruby25'
+          Parser::Ruby25
+        when 2.6
+          require 'parser/ruby26'
+          Parser::Ruby26
+        when 2.7
+          require 'parser/ruby27'
+          Parser::Ruby27
+        when 2.8
+          require 'parser/ruby28'
+          Parser::Ruby28
+        else
+          raise ArgumentError,
+                "RuboCop found unknown Ruby version: #{ruby_version.inspect}"
+        end
+      end
+      # rubocop:enable Metrics/MethodLength
+
+      def create_parser(ruby_version)
+        builder = RuboCop::AST::Builder.new
+
+        parser_class(ruby_version).new(builder).tap do |parser|
+          # On JRuby there's a risk that we hang in tokenize() if we
+          # don't set the all errors as fatal flag. The problem is caused by a bug
+          # in Racc that is discussed in issue #93 of the whitequark/parser
+          # project on GitHub.
+          parser.diagnostics.all_errors_are_fatal = (RUBY_ENGINE != 'ruby')
+          parser.diagnostics.ignore_warnings = false
+          parser.diagnostics.consumer = lambda do |diagnostic|
+            @diagnostics << diagnostic
+          end
+        end
+      end
+
+      def first_token_index(range_or_node)
+        begin_pos = source_range(range_or_node).begin_pos
+        sorted_tokens.bsearch_index { |token| token.begin_pos >= begin_pos }
+      end
+
+      def last_token_index(range_or_node)
+        end_pos = source_range(range_or_node).end_pos
+        sorted_tokens.bsearch_index { |token| token.end_pos >= end_pos }
+      end
+
+      # The tokens list is always sorted by token position, except for cases when heredoc
+      # is passed as a method argument. In this case tokens are interleaved by
+      # heredoc contents' tokens.
+      def sorted_tokens
+        @sorted_tokens ||= tokens.sort_by(&:begin_pos)
+      end
+
+      def source_range(range_or_node)
+        if range_or_node.respond_to?(:source_range)
+          range_or_node.source_range
+        else
+          range_or_node
+        end
+      end
+    end
+  end
+end
+# rubocop:enable Metrics/ClassLength

data/lib/rubocop/ast/token.rb

@@ -0,0 +1,116 @@
+# frozen_string_literal: true
+
+module RuboCop
+  module AST
+    # A basic wrapper around Parser's tokens.
+    class Token
+      attr_reader :pos, :type, :text
+
+      def self.from_parser_token(parser_token)
+        type, details = parser_token
+        text, range = details
+        new(range, type, text)
+      end
+
+      def initialize(pos, type, text)
+        @pos = pos
+        @type = type
+        # Parser token "text" may be an Integer
+        @text = text.to_s
+      end
+
+      def line
+        @pos.line
+      end
+
+      def column
+        @pos.column
+      end
+
+      def begin_pos
+        @pos.begin_pos
+      end
+
+      def end_pos
+        @pos.end_pos
+      end
+
+      def to_s
+        "[[#{line}, #{column}], #{type}, #{text.inspect}]"
+      end
+
+      # Checks if there is whitespace after token
+      def space_after?
+        pos.source_buffer.source.match(/\G\s/, end_pos)
+      end
+
+      # Checks if there is whitespace before token
+      def space_before?
+        position = begin_pos.zero? ? begin_pos : begin_pos - 1
+        pos.source_buffer.source.match(/\G\s/, position)
+      end
+
+      ## Type Predicates
+
+      def comment?
+        type == :tCOMMENT
+      end
+
+      def semicolon?
+        type == :tSEMI
+      end
+
+      def left_array_bracket?
+        type == :tLBRACK
+      end
+
+      def left_ref_bracket?
+        type == :tLBRACK2
+      end
+
+      def left_bracket?
+        %i[tLBRACK tLBRACK2].include?(type)
+      end
+
+      def right_bracket?
+        type == :tRBRACK
+      end
+
+      def left_brace?
+        type == :tLBRACE
+      end
+
+      def left_curly_brace?
+        type == :tLCURLY
+      end
+
+      def right_curly_brace?
+        type == :tRCURLY
+      end
+
+      def left_parens?
+        %i[tLPAREN tLPAREN2].include?(type)
+      end
+
+      def right_parens?
+        type == :tRPAREN
+      end
+
+      def comma?
+        type == :tCOMMA
+      end
+
+      def rescue_modifier?
+        type == :kRESCUE_MOD
+      end
+
+      def end?
+        type == :kEND
+      end
+
+      def equal_sign?
+        %i[tEQL tOP_ASGN].include?(type)
+      end
+    end
+  end
+end

data/lib/rubocop/ast/traversal.rb

@@ -19,21 +19,23 @@ module RuboCop
                              rational str sym regopt self lvar
                              ivar cvar gvar nth_ref back_ref cbase
                              arg restarg blockarg shadowarg
-                             kwrestarg zsuper lambda redo retry
+                             kwrestarg zsuper redo retry
                              forward_args forwarded_args
-                             match_var match_nil_pattern empty_else].freeze
+                             match_var match_nil_pattern empty_else
+                             forward_arg lambda procarg0 __ENCODING__].freeze
       ONE_CHILD_NODE    = %i[splat kwsplat block_pass not break next
                              preexe postexe match_current_line defined?
                              arg_expr pin match_rest if_guard unless_guard
                              match_with_trailing_comma].freeze
       MANY_CHILD_NODES  = %i[dstr dsym xstr regexp array hash pair
-                             mlhs masgn or_asgn and_asgn
+                             mlhs masgn or_asgn and_asgn rasgn mrasgn
                              undef alias args super yield or and
                              while_post until_post iflipflop eflipflop
                              match_with_lvasgn begin kwbegin return
                              in_match match_alt
                              match_as array_pattern array_pattern_with_tail
-                             hash_pattern const_pattern].freeze
+                             hash_pattern const_pattern find_pattern
+                             index indexasgn].freeze
       SECOND_CHILD_ONLY = %i[lvasgn ivasgn cvasgn gvasgn optarg kwarg
                              kwoptarg].freeze
 

data/lib/rubocop/ast/version.rb

@@ -3,7 +3,7 @@
 module RuboCop
   module AST
     module Version
-      STRING = '0.0.2'
+      STRING = '0.4.0'
     end
   end
 end

metadata

@@ -1,16 +1,16 @@
 --- !ruby/object:Gem::Specification
 name: rubocop-ast
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.4.0
 platform: ruby
 authors:
 - Bozhidar Batsov
 - Jonas Arvidsson
 - Yuji Nakayama
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-05-12 00:00:00.000000000 Z
+date: 2020-09-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: parser
@@ -18,14 +18,14 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 2.7.0.1
+        version: 2.7.1.4
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 2.7.0.1
+        version: 2.7.1.4
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -59,6 +59,8 @@ files:
 - lib/rubocop-ast.rb
 - lib/rubocop/ast.rb
 - lib/rubocop/ast/builder.rb
+- lib/rubocop/ast/ext/range.rb
+- lib/rubocop/ast/ext/set.rb
 - lib/rubocop/ast/node.rb
 - lib/rubocop/ast/node/alias_node.rb
 - lib/rubocop/ast/node/and_node.rb
@@ -69,6 +71,7 @@ files:
 - lib/rubocop/ast/node/case_match_node.rb
 - lib/rubocop/ast/node/case_node.rb
 - lib/rubocop/ast/node/class_node.rb
+- lib/rubocop/ast/node/const_node.rb
 - lib/rubocop/ast/node/def_node.rb
 - lib/rubocop/ast/node/defined_node.rb
 - lib/rubocop/ast/node/ensure_node.rb
@@ -77,8 +80,11 @@ files:
 - lib/rubocop/ast/node/forward_args_node.rb
 - lib/rubocop/ast/node/hash_node.rb
 - lib/rubocop/ast/node/if_node.rb
+- lib/rubocop/ast/node/index_node.rb
+- lib/rubocop/ast/node/indexasgn_node.rb
 - lib/rubocop/ast/node/int_node.rb
 - lib/rubocop/ast/node/keyword_splat_node.rb
+- lib/rubocop/ast/node/lambda_node.rb
 - lib/rubocop/ast/node/mixin/basic_literal_node.rb
 - lib/rubocop/ast/node/mixin/binary_operator_node.rb
 - lib/rubocop/ast/node/mixin/collection_node.rb
@@ -91,12 +97,13 @@ files:
 - lib/rubocop/ast/node/mixin/parameterized_node.rb
 - lib/rubocop/ast/node/mixin/predicate_operator_node.rb
 - lib/rubocop/ast/node/module_node.rb
+- lib/rubocop/ast/node/next_node.rb
 - lib/rubocop/ast/node/or_node.rb
 - lib/rubocop/ast/node/pair_node.rb
 - lib/rubocop/ast/node/range_node.rb
 - lib/rubocop/ast/node/regexp_node.rb
 - lib/rubocop/ast/node/resbody_node.rb
-- lib/rubocop/ast/node/retry_node.rb
+- lib/rubocop/ast/node/rescue_node.rb
 - lib/rubocop/ast/node/return_node.rb
 - lib/rubocop/ast/node/self_class_node.rb
 - lib/rubocop/ast/node/send_node.rb
@@ -107,13 +114,12 @@ files:
 - lib/rubocop/ast/node/when_node.rb
 - lib/rubocop/ast/node/while_node.rb
 - lib/rubocop/ast/node/yield_node.rb
+- lib/rubocop/ast/node_pattern.rb
+- lib/rubocop/ast/processed_source.rb
 - lib/rubocop/ast/sexp.rb
+- lib/rubocop/ast/token.rb
 - lib/rubocop/ast/traversal.rb
 - lib/rubocop/ast/version.rb
-- lib/rubocop/error.rb
-- lib/rubocop/node_pattern.rb
-- lib/rubocop/processed_source.rb
-- lib/rubocop/token.rb
 homepage: https://github.com/rubocop-hq/rubocop-ast
 licenses:
 - MIT
@@ -121,9 +127,9 @@ metadata:
   homepage_uri: https://www.rubocop.org/
   changelog_uri: https://github.com/rubocop-hq/rubocop-ast/blob/master/CHANGELOG.md
   source_code_uri: https://github.com/rubocop-hq/rubocop-ast/
-  documentation_uri: https://docs.rubocop.org/
+  documentation_uri: https://docs.rubocop.org/rubocop-ast/
   bug_tracker_uri: https://github.com/rubocop-hq/rubocop-ast/issues
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -139,7 +145,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubygems_version: 3.1.2
-signing_key: 
+signing_key:
 specification_version: 4
 summary: RuboCop tools to deal with Ruby code AST.
 test_files: []