marshal-parser 0.1.0 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 54bc27a08a2e25692ac3b0ccf449b6db7df3af095eff14a2c94c91545502721f
-  data.tar.gz: 0b803be1bde2b3d51d5023c51db1042b9b41eebc341f1d9c29e9c7c2e39e9aa8
+  metadata.gz: 84d834a71863bd08ec4f6a4027ddac9603dd83bf5cfa7c0f7c81b540e43950b9
+  data.tar.gz: b2327a3176bc5b31db011b61d79d13aa2b973a98596bd9a5586376617a1407cb
 SHA512:
-  metadata.gz: fca493db638e427e393d252b32e01a7be43bc4f9e2090d2b23492e5997c3b671d3734534054039dee19aeb8667b9291e74e098d4c85a3a1bbefaf79df7037fd4
-  data.tar.gz: cc2bcab736f4a53aec056e7d52dbe282100223641c8b57bff64e8fba3ea00995fddbdcfb3a8c5e1c848a148ebe784fb90937e8dff9b7bb3f9948d16e5b317528
+  metadata.gz: 505dd53a7648131070bb260a26c1c86a38d057f0e9c84539dd02bef8571f828f7b48e42a463fdb75d9eb0088379f7725c8432748bdf8b829023cf07587638194
+  data.tar.gz: 22bce0b7a72769507db2d612d179a2d82fb0376319f63d062ff41a1ce907cb7bfcf1cadc141355e33ad3ab863284d07611c030053f1f1a4c6e094636fcbdf824

data/CHANGELOG.md

@@ -1,5 +1,17 @@
 ## [Unreleased]
 
+## [0.2.0] - 2023-12-20
+
+### Added
+
+- Added `--hex` flag to print tokens in hexadecimal encoding
+- Added `-r`/`--require` option to load Ruby source file
+
+### Fixed
+
+- Fixed parsing of a Hash with default value
+- Fixed parsing of a Regexp with options
+
 ## [0.1.0] - 2023-02-27
 
-- Initial release
+Initial release

data/README.md

@@ -31,7 +31,7 @@ Ruby object.
 
 The Marshal format is described here <https://ruby-doc.org/core-3.1.0/doc/marshal_rdoc.html>.
 
-There are also a lot of useful articles, for instance:
+There are also a lot of articles that could be useful, for instance:
 - <https://shopify.engineering/caching-without-marshal-part-one>
 - <https://iliabylich.github.io/2016/01/25/ruby-marshalling-from-a-to-z.html>
 - <http://jakegoulding.com/blog/categories/marshal/>
@@ -160,7 +160,7 @@ lexer.run
 parser = MarshalParser::Parser.new(lexer)
 ast = parser.parse
 
-puts ast
+pp ast
 ```
 
 This will output:
@@ -171,11 +171,11 @@ This will output:
 
 ## Limitations
 
-- Only supports current format version 4.8
-- Does not support a deprecated node 'M' (that represents Class or Module)
+- Supports only the current Marshal format version (4.8)
+- Does not support a deprecated node 'M' (that represents 'Class or Module')
 - Does not support a 'd' node (Data object, that represents wrapped pointers from Ruby extensions)
 - Doesn't print in annotations object indices (because Ruby is not consistent here and object indices assigning order may
-vary depending on dumped class)
+vary depending on a class of a dumped object)
 
 ## Similar projects
 

data/lib/marshal-parser/cli/commands.rb

@@ -11,9 +11,15 @@ module MarshalParser
         desc "Parse a dump and print tokens. By default reads dump from the stdin."
         option :file,     type: :string,  aliases: ["-f"], desc: "Read a dump from file with provided name"
         option :evaluate, type: :string,  aliases: ["-e"], desc: "Ruby expression to dump"
+        option :require,  type: :string,  aliases: ["-r"], desc: "Load the library using require. It is useful when -e is specified"
         option :annotate, type: :boolean, aliases: ["-a"], desc: "Print a table with annonated tokens"
+        option :hex,      type: :boolean, aliases: ["-x"], desc: "Print tokens in a hexadecimal encoding"
 
         def call(**options)
+          if options[:require]
+            require options[:require]
+          end
+
           dump = \
             if options[:file]
               File.read(options[:file])
@@ -28,9 +34,9 @@ module MarshalParser
 
           formatter = \
             if options[:annotate]
-              MarshalParser::Formatters::Tokens::WithDescription.new(lexer.tokens, dump)
+              MarshalParser::Formatters::Tokens::WithDescription.new(lexer.tokens, dump, hex: options[:hex])
             else
-              MarshalParser::Formatters::Tokens::OneLine.new(lexer.tokens, dump)
+              MarshalParser::Formatters::Tokens::OneLine.new(lexer.tokens, dump, hex: options[:hex])
             end
 
           puts formatter.string
@@ -41,6 +47,7 @@ module MarshalParser
         desc "Parse a dump and print AST. By default reads dump from the stdin and uses S-expressions format."
         option :file,          type: :string,  aliases: ["-f"], desc: "Read a dump from file with provided name"
         option :evaluate,      type: :string,  aliases: ["-e"], desc: "Ruby expression to dump"
+        option :require,       type: :string,  aliases: ["-r"], desc: "Load the library using require. It is useful when -e is specified"
         option :"only-tokens", type: :boolean, aliases: ["-o"], desc: "Print only tokens"
         option :annotate,      type: :boolean, aliases: ["-a"], desc: "Print annotations"
         option :width,         type: :string,  aliases: ["-w"],
@@ -49,6 +56,10 @@ module MarshalParser
         option :compact,       type: :boolean, aliases: ["-c"], desc: "Don't print node attributes"
 
         def call(**options)
+          if options[:require]
+            require options[:require]
+          end
+
           dump = \
             if options[:file]
               File.read(options[:file])

data/lib/marshal-parser/formatters/tokens/one_line.rb

@@ -4,16 +4,24 @@ module MarshalParser
   module Formatters
     module Tokens
       class OneLine
-        def initialize(tokens, source_string)
+        def initialize(tokens, source_string, hex: nil)
           @tokens = tokens
           @source_string = source_string
+          @hex = hex
         end
 
         def string
-          @tokens.map do |token|
-            string = @source_string[token.index, token.length]
-            string =~ /[^[:print:]]/ ? string.dump : string
-          end.join(" ")
+          unless @hex
+            @tokens.map do |token|
+              string = @source_string[token.index, token.length]
+              string =~ /[^[:print:]]/ ? string.dump : string
+            end.join(" ")
+          else
+            @tokens.map do |token|
+              string = @source_string[token.index, token.length]
+              string = string.bytes.map { |b| "%02X" % b }.join(" ")
+            end.join("  ")
+          end
         end
       end
     end

data/lib/marshal-parser/formatters/tokens/with_description.rb

@@ -4,14 +4,15 @@ module MarshalParser
   module Formatters
     module Tokens
       class WithDescription
-        def initialize(tokens, source_string)
+        def initialize(tokens, source_string, hex: nil)
           @tokens = tokens
           @source_string = source_string
+          @hex = hex
         end
 
         def string
           @tokens.map do |token|
-            string = @source_string[token.index, token.length].dump
+            string = token_to_string(token)
             description = self.class.token_description(token.id)
             value = token.value ? " (#{token.value})" : ""
 
@@ -19,6 +20,15 @@ module MarshalParser
           end.join("\n")
         end
 
+        private def token_to_string(token)
+          unless @hex
+            @source_string[token.index, token.length].dump
+          else
+            string = @source_string[token.index, token.length]
+            string.bytes.map { |b| "%02X" % b }.join(" ")
+          end
+        end
+
         def self.token_description(token)
           case token
           when Lexer::VERSION                           then "Version"
@@ -28,7 +38,7 @@ module MarshalParser
           when Lexer::OBJECT_WITH_MARSHAL_DUMP_PREFIX   then "Object with #marshal_dump and #marshal_load"
           when Lexer::STRING_PREFIX                     then "String beginning"
           when Lexer::HASH_PREFIX                       then "Hash beginning"
-          when Lexer::HASH_WITH_DEFAULT_VALUE_PREFIX    then "Hash beginning (with defaul value)"
+          when Lexer::HASH_WITH_DEFAULT_VALUE_PREFIX    then "Hash beginning (with default value)"
           when Lexer::REGEXP_PREFIX                     then "Regexp beginning"
           when Lexer::STRUCT_PREFIX                     then "Struct beginning"
           when Lexer::TRUE                              then "true"
@@ -48,6 +58,7 @@ module MarshalParser
           when Lexer::FLOAT                             then "Float string representation"
           when Lexer::INTEGER                           then "Integer encoded"
           when Lexer::BIG_INTEGER                       then "Big Integer encoded"
+          when Lexer::BYTE                              then "Byte"
           when Lexer::STRING                            then "String characters"
           when Lexer::SYMBOL                            then "Symbol characters"
           when Lexer::PLUS_SIGN                         then "Sign '+'"

data/lib/marshal-parser/lexer.rb

@@ -30,6 +30,7 @@ module MarshalParser
       FLOAT,
       INTEGER,
       BIG_INTEGER,
+      BYTE,
       STRING,
       SYMBOL,
       PLUS_SIGN,
@@ -147,6 +148,12 @@ module MarshalParser
       elements = (1..count).map { read }
     end
 
+    def read_byte
+      value = @dump[@index].ord
+      @index += 1
+      @tokens << Token.new(BYTE, @index - 1, 1, value)
+    end
+
     def read_integer
       index_base = @index
 
@@ -266,7 +273,7 @@ module MarshalParser
 
     def read_regexp
       read_string # read Regexp's source
-      read_integer # read flags
+      read_byte # read flags
     end
 
     def read_struct

data/lib/marshal-parser/parser.rb

@@ -130,7 +130,6 @@ module MarshalParser
         end
 
         default_value_node = build_ast_node
-        assert_node_type default_value_node, IntegerNode
 
         HashWithDefaultValueNode.new(token, size, key_and_value_nodes, default_value_node)
 
@@ -649,7 +648,7 @@ module MarshalParser
         assert_token_type prefix, Lexer::REGEXP_PREFIX
         assert_token_type string_length, Lexer::INTEGER
         assert_token_type string, Lexer::STRING
-        assert_token_type options, Lexer::INTEGER
+        assert_token_type options, Lexer::BYTE
 
         @prefix = prefix
         @string_length = string_length

data/lib/marshal-parser/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module MarshalParser
-  VERSION = "0.1.0"
+  VERSION = "0.2.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: marshal-parser
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors:
 - Andrew Konchin
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-04-06 00:00:00.000000000 Z
+date: 2023-12-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: dry-cli
@@ -78,7 +78,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.4.6
+rubygems_version: 3.4.10
 signing_key:
 specification_version: 4
 summary: Parser of the Ruby Marshal format