nestedtext 0.1.0

data/lib/nestedtext/scanners.rb

@@ -0,0 +1,161 @@
+# frozen_string_literal: true
+
+require "nestedtext/errors"
+
+module NestedText
+  class LineScanner
+    def initialize(io)
+      @io = io
+      @next_line = nil
+      prepare_next_line
+    end
+
+    def empty?
+      @next_line.nil?
+    end
+
+    def read_next
+      raise Errors::LineScannerIsEmpty if empty?
+
+      line = @next_line
+      prepare_next_line
+      line.prev.prev = nil unless line.prev.nil? # GC: break the chain
+      line
+    end
+
+    def peek
+      @next_line
+    end
+
+    private
+
+    def prepare_next_line
+      line = nil
+      loop do
+        linestr = @io.gets&.chomp
+        lineno = @io.lineno - 1 # Be 0-based
+        line = linestr.nil? ? nil : Line.new(linestr, lineno, @next_line)
+        break if line.nil? || !%i[blank comment].include?(line.tag)
+      end
+      @next_line = line
+    end
+  end
+
+  class InlineScanner
+    attr_reader :line, :pos
+
+    def initialize(line)
+      @line = line
+      @pos = 0
+    end
+
+    def empty?
+      @pos >= @line.content.length
+    end
+
+    def remaining
+      @line.content[@pos..]
+    end
+
+    def read_next
+      raise Errors::InlineScannerIsEmpty if empty?
+
+      @pos += 1
+      @line.content[@pos - 1]
+    end
+
+    def peek
+      empty? ? nil : @line.content[@pos]
+    end
+  end
+
+  class Line
+    # Reference: https://nestedtext.org/en/latest/file_format.html
+    ALLOWED_LINE_TAGS = [
+      :comment, # a comment
+      :blank,
+      :list_item,  # - item
+      :dict_item,  # key: value (or value on next line)
+      :string_item, # > a string, can continue next line
+      :key_item,    # : key on a line
+      :inline_dict, # {key1: value1, key2: value2}
+      :inline_list, # [value1, value2]
+      :unrecognized # could not be determined
+    ]
+
+    attr_accessor :prev
+    attr_reader :tag, :content, :indentation, :attribs, :lineno
+
+    def initialize(content, lineno, prev_line)
+      @content = content
+      @lineno = lineno
+      @prev = prev_line
+      @attribs = Hash.new(nil)
+      @tag = nil
+      @indentation = 0
+      detect_line_tag_and_indentation
+    end
+
+    # def length
+    # @content.length
+    # end
+
+    # def [](index)
+    # @content[index]
+    # end
+
+    def tag=(tag)
+      @tag = tag
+      raise Errors::LineTagUnknown.new(self, tag) unless ALLOWED_LINE_TAGS.include?(@tag)
+    end
+
+    def to_s
+      "[##{@lineno}] #{" " * @indentation}#{@content}"
+    end
+
+    private
+
+    # TODO: this regex must  unit tested.
+    PATTERN_DICT_ITEM = /^
+             (?<key>[^\s].*?)   # Key must start with a non-whitespace character, and goes until first
+              \s*:              # first optional space, or :-separator
+              (?:               # Value part is optional
+                \p{Space}       # Must have a space after :-separator
+                (?<value>.*)    # Value is everything to the end of the line
+              )?
+              $/x
+
+    def detect_line_tag_and_indentation
+      @indentation += 1 while @indentation < @content.length && @content[@indentation] == " "
+      @content = @content[@indentation..]
+
+      if @content.length == 0
+        self.tag = :blank
+      elsif @content[0] == "#"
+        self.tag = :comment
+      elsif @content =~ /^:(?: |$)/
+        self.tag = :key_item
+        @attribs["key"] = @content[2..] || ""
+      elsif @content =~ /^-(?: |$)/
+        self.tag = :list_item
+        @attribs["value"] = @content[2..]
+      elsif @content =~ /^>(?: |$)/
+        self.tag = :string_item
+        @attribs["value"] = @content[2..] || ""
+      elsif @content[0] == "{"
+        self.tag = :inline_dict
+      elsif @content[0] == "["
+        # TODO: merge path of inline dict and list and just set :inline?
+        self.tag = :inline_list
+      elsif @content =~ PATTERN_DICT_ITEM
+        self.tag = :dict_item
+        @attribs["key"] = Regexp.last_match(:key)
+        @attribs["value"] = Regexp.last_match(:value)
+      else
+        # Don't raise error here, as this line might not have been consumed yet,
+        # thus could hide an error that we detect when parsing the previous line.
+        self.tag = :unrecognized
+      end
+    end
+  end
+end

data/lib/nestedtext/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module NestedText
+  VERSION = "0.1.0"
+end

data/lib/nestedtext.rb

@@ -0,0 +1,8 @@
+# frozen_string_literal: true
+
+require_relative "nestedtext/encode"
+require_relative "nestedtext/decode"
+require_relative "nestedtext/core_ext"
+
+module NestedText
+end

data/nestedtext.gemspec

@@ -0,0 +1,27 @@
+# frozen_string_literal: true
+
+require_relative "lib/nestedtext/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "nestedtext"
+  spec.version       = NestedText::VERSION
+  spec.authors       = ["Erik Westrup"]
+  spec.email         = ["erik.westrup@gmail.com"]
+
+  spec.summary       = "A ruby library for the human friendly data format NestedText https://nestedtext.org/"
+  spec.description   = "A ruby implementation the NestedText data format. There is support for decoding a NestedText file or string to Ruby data structures, as well as encoding Ruby objects to a NestedText file or string. Furthermore there is support for serialization and deserialization of custom classes. Support for v3.2.1 of the data format will all official tests passing."
+  spec.homepage      = "https://github.com/erikw/nestedtext-ruby/"
+  spec.license       = "MIT"
+  spec.required_ruby_version = [">= 3.0", "< 4"]
+
+  spec.metadata["homepage_uri"] = spec.homepage
+  spec.metadata["source_code_uri"] = "https://github.com/erikw/nestedtext-ruby/"
+  spec.metadata["changelog_uri"] = "https://github.com/erikw/nestedtext-ruby/blob/main/CHANGELOG.md"
+
+  spec.files = Dir.chdir(File.expand_path(__dir__)) do
+    `git ls-files -z`.split("\x0").reject do |f|
+      f.match(%r{\A(?:test/|script/|\.github/|\.gitmodules|Rakefile|TODO\.txt|\.codeclimate\.yml|\.vimlocal|\.simplecov)})
+    end
+  end
+  spec.require_paths = ["lib"]
+end

metadata

@@ -0,0 +1,77 @@
+--- !ruby/object:Gem::Specification
+name: nestedtext
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Erik Westrup
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2022-01-24 00:00:00.000000000 Z
+dependencies: []
+description: A ruby implementation the NestedText data format. There is support for
+  decoding a NestedText file or string to Ruby data structures, as well as encoding
+  Ruby objects to a NestedText file or string. Furthermore there is support for serialization
+  and deserialization of custom classes. Support for v3.2.1 of the data format will
+  all official tests passing.
+email:
+- erik.westrup@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".editorconfig"
+- ".gitignore"
+- ".rubocop.yml"
+- ".ruby-version"
+- CHANGELOG.md
+- CONTRIBUTING.md
+- Gemfile
+- LICENSE.txt
+- OSSMETADATA
+- README.md
+- SECURITY.md
+- lib/nestedtext.rb
+- lib/nestedtext/constants.rb
+- lib/nestedtext/core_ext.rb
+- lib/nestedtext/decode.rb
+- lib/nestedtext/dumper.rb
+- lib/nestedtext/encode.rb
+- lib/nestedtext/encode_helpers.rb
+- lib/nestedtext/errors.rb
+- lib/nestedtext/helpers.rb
+- lib/nestedtext/parser.rb
+- lib/nestedtext/scanners.rb
+- lib/nestedtext/version.rb
+- nestedtext.gemspec
+homepage: https://github.com/erikw/nestedtext-ruby/
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/erikw/nestedtext-ruby/
+  source_code_uri: https://github.com/erikw/nestedtext-ruby/
+  changelog_uri: https://github.com/erikw/nestedtext-ruby/blob/main/CHANGELOG.md
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '3.0'
+  - - "<"
+    - !ruby/object:Gem::Version
+      version: '4'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.3.3
+signing_key: 
+specification_version: 4
+summary: A ruby library for the human friendly data format NestedText https://nestedtext.org/
+test_files: []