spellr 0.1.0

data/lib/spellr/reporter.rb

@@ -0,0 +1,27 @@
+# frozen_string_literal: true
+
+require_relative 'string_format'
+
+module Spellr
+  class Reporter
+    include Spellr::StringFormat
+
+    attr_accessor :total
+
+    def initialize
+      @total = 0
+    end
+
+    def finish(checked)
+      puts "\n"
+      puts "#{pluralize 'file', checked} checked"
+      puts "#{pluralize 'error', total} found"
+    end
+
+    def call(token)
+      puts "#{aqua token.location} #{token.line.highlight(token.char_range).strip}"
+
+      self.total += 1
+    end
+  end
+end

data/lib/spellr/string_format.rb

@@ -0,0 +1,43 @@
+# frozen_string_literal: true
+
+require_relative 'config'
+
+module Spellr
+  module StringFormat
+    module_function
+
+    def pluralize(word, count)
+      "#{count} #{word}#{'s' if count != 1}"
+    end
+
+    def color_enabled?
+      return $stdout.tty? if Spellr.config.color.nil?
+
+      Spellr.config.color
+    end
+
+    def aqua(text)
+      return text unless Spellr::StringFormat.color_enabled?
+
+      "\e[36m#{text}#{normal}"
+    end
+
+    def normal(text = '')
+      return text unless Spellr::StringFormat.color_enabled?
+
+      "\e[0m#{text}"
+    end
+
+    def bold(text)
+      return text unless Spellr::StringFormat.color_enabled?
+
+      "\e[1;39m#{text}#{normal}"
+    end
+
+    def red(text)
+      return text unless Spellr::StringFormat.color_enabled?
+
+      "\e[1;31m#{text}#{normal}"
+    end
+  end
+end

data/lib/spellr/token.rb

@@ -0,0 +1,83 @@
+# frozen_string_literal: true
+
+# frozen string_literal: true
+
+require_relative 'column_location'
+require_relative 'string_format'
+
+module Spellr
+  class Token < String
+    attr_reader :location, :line
+    def self.normalize(value)
+      return value.normalize if value.is_a?(Spellr::Token)
+
+      value.strip.downcase.unicode_normalize.tr('’', "'") + "\n"
+    end
+
+    def self.wrap(value)
+      return value if value.is_a?(Spellr::Token)
+
+      Spellr::Token.new(value || '')
+    end
+
+    def initialize(string, line: string, location: ColumnLocation.new)
+      @location = location
+      @line = line
+      super(string)
+    end
+
+    def strip
+      @strip ||= begin
+        lstripped = lstrip
+        new_column_location = lstripped_column_location(lstripped)
+        Token.new(lstripped.rstrip, line: line, location: new_column_location)
+      end
+    end
+
+    def lstripped_column_location(lstripped)
+      ColumnLocation.new(
+        byte_offset: bytesize - lstripped.bytesize,
+        char_offset: length - lstripped.length,
+        line_location: location.line_location
+      )
+    end
+
+    def normalize
+      @normalize ||= self.class.normalize(to_s)
+    end
+
+    def inspect
+      "#<#{self.class.name} #{to_s.inspect} @#{location}>"
+    end
+
+    def char_range
+      @char_range ||= location.char_offset...(location.char_offset + length)
+    end
+
+    def byte_range
+      @byte_range ||= location.byte_offset...(location.byte_offset + bytesize)
+    end
+
+    def coordinates
+      location.coordinates
+    end
+
+    def highlight(range = char_range)
+      "#{slice(0...(range.first))}#{Spellr::StringFormat.red slice(range)}#{slice(range.last..-1)}"
+    end
+
+    def replace(replacement)
+      ::File.open(file_name, 'r+') do |f|
+        body = f.read
+        body[location.absolute_char_offset...(location.absolute_char_offset + length)] = replacement
+        f.rewind
+        f.truncate(0)
+        f.write(body)
+      end
+    end
+
+    def file_name
+      location.file_name
+    end
+  end
+end

data/lib/spellr/tokenizer.rb

@@ -0,0 +1,72 @@
+# frozen_string_literal: true
+
+require_relative '../spellr'
+require_relative 'token'
+require_relative 'column_location'
+require_relative 'line_location'
+require_relative 'line_tokenizer'
+
+module Spellr
+  class Tokenizer
+    attr_reader :file
+    attr_reader :start_at
+
+    attr_accessor :disabled
+    alias_method :disabled?, :disabled
+
+    def initialize(file, start_at: nil, skip_uri: true, skip_key: true)
+      # $stderr.puts start_at if start_at
+      @start_at = start_at || ColumnLocation.new(line_location: LineLocation.new(file))
+      @file = file.is_a?(StringIO) || file.is_a?(IO) ? file : ::File.new(file)
+      @file.pos = @start_at.line_location.byte_offset
+
+      @line_tokenizer = LineTokenizer.new(skip_uri: skip_uri, skip_key: skip_key)
+    end
+
+    def terms
+      enum_for(:each_term).to_a
+    end
+
+    def map(&block)
+      enum_for(:each_token).map(&block)
+    end
+
+    def each_term(&block)
+      each_line_with_offset do |line, line_number|
+        prepare_tokenizer_for_line(line, line_number).each_term(&block)
+      end
+    end
+
+    def each_token(&block) # rubocop:disable Metrics/AbcSize
+      char_offset = @start_at.line_location.char_offset
+      byte_offset = @start_at.line_location.byte_offset
+
+      each_line_with_offset do |line, line_number|
+        line_location = LineLocation.new(file, line_number, byte_offset: byte_offset, char_offset: char_offset)
+        char_offset += line.length
+        byte_offset += line.bytesize
+        line = Token.new(line, location: ColumnLocation.new(line_location: line_location))
+        prepare_tokenizer_for_line(line, line_number).each_token(&block)
+      end
+    end
+
+    def normalized_terms
+      enum_for(:each_term).lazy.map { |t| Token.normalize(t) }.uniq.sort
+    end
+
+    private
+
+    attr_reader :line_tokenizer
+
+    def each_line_with_offset(&block)
+      file.each_line.with_index(@start_at.line_number, &block)
+    end
+
+    def prepare_tokenizer_for_line(line, _line_number)
+      line_tokenizer.string = line
+      line_tokenizer.pos = 0
+      # line_tokenizer.pos = @start_at.byte_offset if line_number == @start_at.line_number
+      line_tokenizer
+    end
+  end
+end

data/lib/spellr/version.rb

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

data/lib/spellr/wordlist.rb

@@ -0,0 +1,100 @@
+# frozen_string_literal: true
+
+require 'pathname'
+require_relative '../spellr'
+require_relative 'token'
+
+module Spellr
+  class Wordlist
+    class NotFound < Spellr::Error; end
+
+    include Enumerable
+
+    attr_reader :path, :name
+
+    def initialize(file, name: file)
+      path = @file = file
+      @path = Pathname.pwd.join('.spellr_wordlists').join(path).expand_path
+      @name = name
+    end
+
+    def each(&block)
+      raise_unless_exists?
+
+      @path.each_line(&block)
+    end
+
+    def inspect
+      "#<#{self.class.name}:#{@path}>"
+    end
+
+    # significantly faster than default Enumerable#include?
+    # requires terms to be sorted
+    def include?(term)
+      include_cache[Spellr::Token.normalize(term)]
+    end
+
+    def include_cache
+      @include_cache ||= Hash.new do |cache, term|
+        cache[term] = to_a.bsearch do |value|
+          term <=> value
+        end
+      end
+    end
+
+    def to_a
+      @to_a ||= super
+    end
+
+    def clean(file = @path)
+      require_relative 'tokenizer'
+      write(Spellr::Tokenizer.new(file, skip_uri: false, skip_key: false).normalized_terms.join)
+    end
+
+    def write(content)
+      @path.write(content)
+
+      clear_cache
+    end
+
+    def read
+      raise_unless_exists?
+
+      @path.read
+    end
+
+    def clear_cache
+      @to_a = nil
+      @include = nil
+    end
+
+    def exist?
+      @path.exist?
+    end
+
+    def add(term)
+      touch
+      term = Spellr::Token.normalize(term)
+      include_cache[term] = true
+      to_a << term
+      to_a.sort!
+      write(@to_a.join)
+      Spellr.config.clear_cache if to_a.length == 1
+    end
+
+    private
+
+    def touch
+      return if exist?
+
+      @path.dirname.mkpath
+      @path.write('')
+    end
+
+    def raise_unless_exists?
+      return if exist?
+
+      raise Spellr::Wordlist::NotFound, "Wordlist file #{@file} doesn't exist at #{@path}"
+    end
+  end
+end

data/lib/spellr/wordlist_reporter.rb

@@ -0,0 +1,21 @@
+# frozen_string_literal: true
+
+require 'set'
+
+module Spellr
+  class WordlistReporter
+    attr_reader :words
+
+    def initialize
+      @words = Set.new
+    end
+
+    def finish(_checked)
+      puts words.sort.join
+    end
+
+    def call(token)
+      words << token.normalize
+    end
+  end
+end

data/spellr.gemspec

@@ -0,0 +1,35 @@
+# frozen_string_literal: true
+
+lib = ::File.expand_path('lib', __dir__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'spellr/version'
+
+Gem::Specification.new do |spec|
+  spec.name = 'spellr'
+  spec.version = Spellr::VERSION
+  spec.authors = ['Dana Sherson']
+  spec.email = ['robot@dana.sh']
+
+  spec.summary = 'Spell check your source code'
+  spec.homepage = 'http://github.com/robotdana/spellr'
+  spec.license = 'MIT'
+
+  # Specify which files should be added to the gem when it is released.
+  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
+  spec.files = Dir.chdir(::File.expand_path(__dir__)) do
+    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  end
+  spec.bindir = 'exe'
+  spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ['lib']
+
+  spec.add_development_dependency 'bundler', '~> 1.17'
+  spec.add_development_dependency 'pry'
+  spec.add_development_dependency 'rake', '~> 10.0'
+  spec.add_development_dependency 'rspec', '~> 3.0'
+  spec.add_development_dependency 'rspec-eventually'
+  spec.add_development_dependency 'rubocop'
+  spec.add_development_dependency 'rubocop-rspec'
+  spec.add_dependency 'fast_ignore'
+  spec.add_dependency 'parallel'
+end

data/wordlist

@@ -0,0 +1,2 @@
+bar
+foo

data/wordlists/dockerfile.txt

@@ -0,0 +1,21 @@
+add
+arg
+as
+cmd
+copy
+docker
+dockerfile
+entrypoint
+env
+expose
+from
+healthcheck
+label
+maintainer
+onbuild
+run
+shell
+stopsignal
+user
+volume
+workdir

data/wordlists/html.txt

@@ -0,0 +1,340 @@
+a
+abbr
+accept
+accesskey
+acronym
+action
+activedescendant
+address
+alert
+alertdialog
+align
+allow
+alt
+applet
+application
+area
+aria
+article
+aside
+async
+atomic
+audio
+autocapitalize
+autocomplete
+autofocus
+autoplay
+b
+banner
+base
+basefont
+bdi
+bdo
+bgcolor
+bgsound
+big
+blink
+blockquote
+body
+br
+buffered
+busy
+button
+canvas
+caption
+cell
+center
+challenge
+charset
+checkbox
+checked
+cite
+class
+code
+codebase
+col
+colcount
+colgroup
+colindex
+color
+cols
+colspan
+columnheader
+combobox
+command
+complementary
+content
+contenteditable
+contentinfo
+contextmenu
+controls
+coords
+crossorigin
+csp
+current
+data
+datalist
+datetime
+dd
+decoding
+default
+defer
+definition
+del
+describedby
+details
+dfn
+dialog
+dir
+directory
+dirname
+disabled
+div
+dl
+document
+download
+draggable
+dropeffect
+dropzone
+dt
+element
+em
+embed
+enctype
+equiv
+errormessage
+expanded
+feed
+fieldset
+figcaption
+figure
+flowto
+font
+footer
+for
+form
+formaction
+frame
+frameset
+grabbed
+grid
+gridcell
+group
+h
+haspopup
+head
+header
+headers
+heading
+height
+hgroup
+hidden
+high
+hr
+href
+hreflang
+html
+http
+i
+icon
+id
+iframe
+image
+img
+importance
+input
+ins
+integrity
+invalid
+isindex
+ismap
+itemprop
+kbd
+keygen
+keyshortcuts
+keytype
+kind
+label
+labelledby
+lang
+language
+lazyload
+legend
+level
+li
+link
+list
+listbox
+listing
+listitem
+live
+log
+loop
+low
+main
+manifest
+map
+mark
+marquee
+math
+max
+maxlength
+media
+menu
+menubar
+menuitem
+menuitemcheckbox
+menuitemradio
+meta
+meter
+method
+min
+minlength
+modal
+multicol
+multiline
+multiple
+multiselectable
+muted
+name
+nav
+navigation
+nextid
+nobr
+noembed
+noframes
+none
+noscript
+note
+novalidate
+object
+ol
+open
+optgroup
+optimum
+option
+orientation
+output
+owns
+p
+param
+pattern
+picture
+ping
+placeholder
+plaintext
+posinset
+poster
+pre
+preload
+presentation
+pressed
+progress
+progressbar
+q
+radio
+radiogroup
+rb
+readonly
+referrerpolicy
+region
+rel
+relevant
+required
+reversed
+role
+roledescription
+row
+rowcount
+rowgroup
+rowheader
+rowindex
+rows
+rowspan
+rp
+rt
+rtc
+ruby
+s
+samp
+sandbox
+scope
+scoped
+script
+scrollbar
+search
+searchbox
+section
+select
+selected
+separator
+setsize
+shadow
+shape
+size
+sizes
+slider
+slot
+small
+sort
+source
+spacer
+span
+spellcheck
+spinbutton
+src
+srcdoc
+srclang
+srcset
+start
+status
+step
+strike
+strong
+style
+sub
+summary
+sup
+switch
+tab
+tabindex
+table
+tablist
+tabpanel
+target
+tbody
+td
+template
+term
+textarea
+textbox
+tfoot
+th
+thead
+time
+timer
+title
+toolbar
+tooltip
+tr
+track
+translate
+tree
+treegrid
+treeitem
+tt
+type
+u
+ul
+usemap
+value
+valuemax
+valuemin
+valuenow
+valuetext
+var
+video
+wbr
+width
+wrap
+xmp