wordlist 1.0.0 → 1.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 98d7c15c0542442692f3ddd9eb1903b717ee9dc99c38744efa035140d3387c3b
-  data.tar.gz: 3a343f015e734d5b48caaaa0379cfab7b082235f21c14048de72bc7aba0658da
+  metadata.gz: 3648b45622323ff7c7c9a39d3cdb458d40388f1f0840fb80b917239df7ae995a
+  data.tar.gz: 8302f069d5a7dfd68103cfa106df8ade1b1d00f7f6755be7158dd7acd2a4bf0e
 SHA512:
-  metadata.gz: c6ad1af333afa7b2599729db8ff761d236ab7b70c37a0855f888debf547818fd1698b5efaa064742107f5003621fcab9efc6a3e101a8241c1ef7ea68b80344b6
-  data.tar.gz: 920e99dac9529db87d16394d94ccafcdefd45b64b6e8f9dc4664dc95846c6cfa5d5910d119cfa146249e1d46325e7a07a1471ea061d15f53f4b1b6736d4bd16e
+  metadata.gz: 01662d4d752294cca6da0809f7dfc0a953f7702259c448d73b4cfc796d214ce90797e4eedc80ebd48d005ec67039124ab5e974add35fadc8552f5cc9e6683de1
+  data.tar.gz: d29b36e5319a75bd9d88617451e6a7fda6c0cf4d0fe4cb43fd41b19da1e960135a57982b09f3ce93ff106668443ba03f26479a664c73737cc7721d8e2d0f26e5

data/.github/workflows/ruby.yml

@@ -12,6 +12,7 @@ jobs:
           - 2.6
           - 2.7
           - 3.0
+          - 3.1
           - jruby
           - truffleruby
     name: Ruby ${{ matrix.ruby }}

data/ChangeLog.md

@@ -1,3 +1,13 @@
+### 1.0.1 / 2023-07-17
+
+* Require Ruby >= 2.0.0.
+* Added `frozen_string_literal: true` magic comments.
+* Flush the output after each line is written in {Wordlist::Builder}.
+  This allows for watching the wordlist file grow using `tail -f`.
+* Fixed a bug in {Wordlist::Lexer#parse} where Unicode whitespace or other
+  Unicode characters caused an infinite loop.
+* Various documentation fixes.
+
 ### 1.0.0 / 2021-11-01
 
 * Redesigned the API.

data/Gemfile

@@ -7,7 +7,9 @@ group :development do
   gem 'rubygems-tasks', '~> 0.2'
   gem 'rspec',          '~> 3.0'
   gem 'simplecov',      '~> 0.20'
+
   gem 'kramdown'
+  gem 'redcarpet',       platform: :mri
   gem 'yard',           '~> 0.9'
   gem 'yard-spellcheck', require: false
 end

data/README.md

@@ -1,6 +1,7 @@
 # Wordlist
 
 [![CI](https://github.com/postmodern/wordlist.rb/actions/workflows/ruby.yml/badge.svg)](https://github.com/postmodern/wordlist.rb/actions/workflows/ruby.yml)
+[![Code Climate](https://codeclimate.com/github/postmodern/wordlist.rb.svg)](https://codeclimate.com/github/postmodern/wordlist.rb)
 [![Gem Version](https://badge.fury.io/rb/wordlist.svg)](https://badge.fury.io/rb/wordlist)
 
 * [Source](https://github.com/postmodern/wordlist.rb#readme)
@@ -9,8 +10,8 @@
 
 ## Description
 
-Wordlist is a Ruby library for reading, manipulating, and creating wordlists,
-efficiently.
+Wordlist is a Ruby library and CLI for reading, combining, mutating, and
+building wordlists, efficiently.
 
 ## Features
 
@@ -22,8 +23,9 @@ efficiently.
   * Can parse/skip digits, special characters, whole numbers, acronyms.
   * Can normalize case, apostrophes, and acronyms.
 * Supports wordlist operations for combining multiple wordlists together.
-* Supports wordlist manipulating to modify the words in the wordlist on the fly.
-* Fast-ish
+* Supports wordlist modify or mutating the words in the wordlist on the fly.
+* Also provides a `wordlist` [command](#synopsis).
+* [Fast-ish](#benchmarks)
 
 ## Examples
 
@@ -161,6 +163,13 @@ Performs every possible mutation of each word in a wordlist:
 wordlist.mutate(/[oae]/, {'o' => '0', 'a' => '@', 'e' => '3'}).each do |word|
   puts word
 end
+# dog
+# d0g
+# firefox
+# fir3fox
+# firef0x
+# fir3f0x
+# ...
 ```
 
 Enumerates over every possible case variation of every word in a wordlist:
@@ -169,6 +178,15 @@ Enumerates over every possible case variation of every word in a wordlist:
 wordlist.mutate_case.each do |word|
   puts word
 end
+# cat
+# Cat
+# cAt
+# caT
+# CAt
+# CaT
+# cAT
+# CAT
+# ...
 ```
 
 ### Building a Wordlist
@@ -203,6 +221,12 @@ Parsing a file's content:
 builder.parse_file(path)
 ```
 
+## Requirements
+
+* [ruby] >= 2.0.0
+
+[ruby]: https://www.ruby-lang.org/
+
 ## Install
 
 ```shell
@@ -239,18 +263,30 @@ Combining every word from one wordlist with another:
 
 ```shell
 $ wordlist sport_teams.txt -p beers.txt -p all_four_digits.txt
+coors0000
+coors0001
+coors0002
+coors0003
+...
 ```
 
 Combining every word from one wordlist with itself, N times:
 
 ```shell
-$ wordlist shakespeare.txt -P 3
+$ wordlist words.txt -P 3
 ```
 
 Mutating every word in a wordlist:
 
 ```shell
 $ wordlist passwords.txt -m o:0 -m e:3 -m a:@
+dog
+d0g
+firefox
+fir3fox
+firef0x
+fir3f0x
+...
 ```
 
 Executing a command on each word in the wordlist:

data/gemspec.yml

@@ -1,8 +1,9 @@
 name: wordlist
-summary: Ruby library for reading, manipulating, and creating wordlists.
+summary:
+  Ruby library and CLI for reading, combining, mutating, and building wordlists
 description:
-  Wordlist is a Ruby library for reading, manipulating, and creating wordlists,
-  efficiently.
+  Wordlist is a Ruby library and CLI for reading, combining, mutating, and
+  building wordlists, efficiently.
 
 license: MIT
 authors: Postmodern
@@ -10,7 +11,13 @@ email: postmodern.mod3@gmail.com
 homepage: https://github.com/postmodern/wordlist.rb
 has_yard: true
 
+metadata:
+  documentation_uri: https://rubydoc.info/gems/wordlist
+  source_code_uri:   https://github.com/postmodern/wordlist.rb
+  bug_tracker_uri:   https://github.com/postmodern/wordlist.rb/issues
+  changelog_uri:     https://github.com/postmodern/wordlist.rb/blob/master/ChangeLog.md
+
+required_ruby_version: ">= 2.0.0"
+
 development_dependencies:
-  rubygems-tasks: ~> 0.1
-  rspec: ~> 2.4
-  yard: ~> 0.8
+  bundler: ~> 2.0

data/lib/wordlist/abstract_wordlist.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/list_methods'
 
 module Wordlist

data/lib/wordlist/builder.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/format'
 require 'wordlist/lexer'
 require 'wordlist/unique_filter'
@@ -61,25 +62,25 @@ module Wordlist
     # @option kwargs [Array<String, Regexp>] :ignore_words
     #   Optional list of words to ignore. Can contain Strings or Regexps.
     #
-    # @option kwargs [Boolean] :digits
+    # @option kwargs [Boolean] :digits (true)
     #   Controls whether parsed words may contain digits or not.
     #
-    # @option kwargs [Array<String>] :special_chars
+    # @option kwargs [Array<String>] :special_chars (Lexer::SPCIAL_CHARS)
     #   The additional special characters allowed within words.
     #
-    # @option kwargs [Boolean] :numbers
+    # @option kwargs [Boolean] :numbers (false)
     #   Controls whether whole numbers will be parsed as words.
     #
-    # @option kwargs [Boolean] :acronyms
+    # @option kwargs [Boolean] :acronyms (true)
     #   Controls whether acronyms will be parsed as words.
     #
-    # @option kwargs [Boolean] :normalize_case
+    # @option kwargs [Boolean] :normalize_case (false)
     #   Controls whether to convert all words to lowercase.
     #
-    # @option kwargs [Boolean] :normalize_apostrophes
+    # @option kwargs [Boolean] :normalize_apostrophes (false)
     #   Controls whether apostrophes will be removed from the end of words.
     #
-    # @option kwargs [Boolean] :normalize_acronyms
+    # @option kwargs [Boolean] :normalize_acronyms (false)
     #   Controls whether acronyms will have `.` characters removed.
     #
     # @raise [ArgumentError]
@@ -258,6 +259,7 @@ module Wordlist
     #
     def write(line)
       @io.puts(line)
+      @io.flush
     end
 
     #

data/lib/wordlist/cli.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/file'
 require 'wordlist/builder'
 require 'wordlist/version'

data/lib/wordlist/file.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/abstract_wordlist'
 require 'wordlist/exceptions'
 require 'wordlist/format'
@@ -49,11 +50,11 @@ module Wordlist
       @format = format
 
       unless ::File.file?(@path)
-        raise(WordlistNotFound,"wordlist file does not exist: #{path.inspect}")
+        raise(WordlistNotFound,"wordlist file does not exist: #{@path.inspect}")
       end
 
       unless Format::FORMATS.include?(@format)
-        raise(UnknownFormat,"unknown format given: #{format.inspect}")
+        raise(UnknownFormat,"unknown format given: #{@format.inspect}")
       end
     end
 

data/lib/wordlist/format.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/exceptions'
 
 module Wordlist

data/lib/wordlist/lexer/lang.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Wordlist
   class Lexer
     #

data/lib/wordlist/lexer/stop_words.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/exceptions'
 
 module Wordlist

data/lib/wordlist/lexer.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/lexer/lang'
 require 'wordlist/lexer/stop_words'
 
@@ -13,8 +14,6 @@ module Wordlist
   #
   class Lexer
 
-    include Enumerable
-
     # Regexp to match acronyms.
     ACRONYM = /[[:alpha:]](?:\.[[:alpha:]])+\./
 
@@ -97,9 +96,11 @@ module Wordlist
       escaped_chars = Regexp.escape(@special_chars.join)
 
       @word = if @digits
-                /[[:alpha:]](?:[[:alnum:]#{escaped_chars}]*[[:alnum:]])?/
+                # allows numeric characters
+                /\p{L}(?:[\p{L}\p{Nd}#{escaped_chars}]*[\p{L}\p{Nd}])?/
               else
-                /[[:alpha:]](?:[[:alpha:]#{escaped_chars}]*[[:alpha:]])?/
+                # only allows alpha characters
+                /\p{L}(?:[\p{L}#{escaped_chars}]*\p{L})?/
               end
 
       skip_words = Regexp.union(
@@ -114,12 +115,14 @@ module Wordlist
       )
 
       if @numbers
-        @skip_word   = /(?:#{skip_words}[[:punct:]]*(?:\s+|$))+/i
+        # allows lexing whole numbers
+        @skip_word   = /(?:#{skip_words}[[:punct:]]*(?:[[:space:]]+|$))+/i
         @word        = /#{@word}|\d+/
-        @not_a_word  = /[\s[:punct:]]+/
+        @not_a_word  = /[^\p{L}\d]+/
       else
-        @skip_word   = /(?:(?:#{skip_words}|\d+)[[:punct:]]*(?:\s+|$))+/i
-        @not_a_word  = /[\s\d[:punct:]]+/
+        # skips whole numbers
+        @skip_word   = /(?:(?:#{skip_words}|\d+)[[:punct:]]*(?:[[:space:]]+|$))+/i
+        @not_a_word  = /[^\p{L}]+/
       end
     end
 

data/lib/wordlist/list_methods.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/operators'
 require 'wordlist/modifiers'
 
@@ -22,8 +23,8 @@ module Wordlist
     #   The lazily concatenated wordlists.
     #
     # @example
-    #   wordlist1 = Wordlist::List["foo", "bar", "baz"]
-    #   wordlist2 = Wordlist::List["abc", "xyz"]
+    #   wordlist1 = Wordlist::Words["foo", "bar", "baz"]
+    #   wordlist2 = Wordlist::Words["abc", "xyz"]
     #   (wordlist1 + wordlist2).each do |word|
     #     puts word
     #   end
@@ -52,8 +53,8 @@ module Wordlist
     #   The lazy subtraction of the two wordlists.
     #
     # @example
-    #   wordlist1 = Wordlist::List["foo", "bar", baz", "qux"]
-    #   wordlist2 = Wordlist::List["bar", "qux"]
+    #   wordlist1 = Wordlist::Words["foo", "bar", baz", "qux"]
+    #   wordlist2 = Wordlist::Words["bar", "qux"]
     #   (wordlist1 - wordlist2).each do |word|
     #     puts word
     #   end
@@ -78,8 +79,8 @@ module Wordlist
     #   The lazy product of the two wordlists.
     #
     # @example
-    #   wordlist1 = Wordlist::List["foo", "bar"]
-    #   wordlist2 = Wordlist::List["ABC", "XYZ"]
+    #   wordlist1 = Wordlist::Words["foo", "bar"]
+    #   wordlist2 = Wordlist::Words["ABC", "XYZ"]
     #   (wordlist1 * wordlist2).each do |word|
     #     puts word
     #   end
@@ -106,7 +107,7 @@ module Wordlist
     #   The lazy combination of the wordlist.
     #
     # @example
-    #   wordlist = Wordlist::List["foo", "bar"]
+    #   wordlist = Wordlist::Words["foo", "bar"]
     #   (wordlist ** 3).each do |word|
     #     puts word
     #   end
@@ -137,8 +138,8 @@ module Wordlist
     #   The lazy intersection of the two wordlists.
     #
     # @example
-    #   wordlist1 = Wordlist::List["foo", "bar", "baz", "qux"]
-    #   wordlist2 = Wordlist::List["xyz", "bar", "abc", "qux"]
+    #   wordlist1 = Wordlist::Words["foo", "bar", "baz", "qux"]
+    #   wordlist2 = Wordlist::Words["xyz", "bar", "abc", "qux"]
     #   (wordlist1 & wordlist2).each do |word|
     #     puts word
     #   end
@@ -164,8 +165,8 @@ module Wordlist
     #   The lazy union of the two wordlists.
     #
     # @example
-    #   wordlist1 = Wordlist::List["foo", "bar", "baz", "qux"]
-    #   wordlist2 = Wordlist::List["xyz", "bar", "abc", "qux"]
+    #   wordlist1 = Wordlist::Words["foo", "bar", "baz", "qux"]
+    #   wordlist2 = Wordlist::Words["xyz", "bar", "abc", "qux"]
     #   (wordlist1 | wordlist2).each do |word|
     #     puts word
     #   end
@@ -184,7 +185,6 @@ module Wordlist
 
     alias | union
 
-    #
     #
     # Lazily enumerates over only the unique words in the wordlist, filtering
     # out duplicates.
@@ -193,7 +193,7 @@ module Wordlist
     #   The lazy uniqueness of the wordlist.
     #
     # @example
-    #   wordlist= Wordlist::List["foo", "bar", "baz", "qux"]
+    #   wordlist= Wordlist::Words["foo", "bar", "baz", "qux"]
     #   (wordlist + wordlist).uniq.each do |word|
     #     puts word
     #   end
@@ -225,7 +225,7 @@ module Wordlist
     #   The lazy `String#tr` modification of the wordlist.
     #
     # @example
-    #   wordlist = Wordlist::List["foo", "bar", "baz"]
+    #   wordlist = Wordlist::Words["foo", "bar", "baz"]
     #   wordlist.capitalize.each do |word|
     #     puts word
     #   end
@@ -259,7 +259,7 @@ module Wordlist
     #   The lazy `String#sub` modification of the wordlist.
     #
     # @example
-    #   wordlist = Wordlist::List["foo", "bar", "baz"]
+    #   wordlist = Wordlist::Words["foo", "bar", "baz"]
     #   wordlist.sub(/o/, '0').each do |word|
     #     puts word
     #   end
@@ -297,7 +297,7 @@ module Wordlist
     #   The lazy `String#gsub` modification of the wordlist.
     #
     # @example
-    #   wordlist = Wordlist::List["Foo", "BAR", "bAz"]
+    #   wordlist = Wordlist::Words["Foo", "BAR", "bAz"]
     #   wordlist.gsub(/o/,'0').each do |word|
     #     puts word
     #   end
@@ -322,7 +322,7 @@ module Wordlist
     #   The lazy `String#gsub` modification of the wordlist.
     #
     # @example
-    #   wordlist = Wordlist::List["foo", "bar", "baz"]
+    #   wordlist = Wordlist::Words["foo", "bar", "baz"]
     #   wordlist.capitalize.each do |word|
     #     puts word
     #   end
@@ -343,7 +343,7 @@ module Wordlist
     #   The lazy `String#gsub` modification of the wordlist.
     #
     # @example
-    #   wordlist = Wordlist::List["foo", "bar", "baz"]
+    #   wordlist = Wordlist::Words["foo", "bar", "baz"]
     #   wordlist.upcase.each do |word|
     #     puts word
     #   end
@@ -364,7 +364,7 @@ module Wordlist
     #   The lazy `String#gsub` modification of the wordlist.
     #
     # @example
-    #   wordlist = Wordlist::List["Foo", "BAR", "bAz"]
+    #   wordlist = Wordlist::Words["Foo", "BAR", "bAz"]
     #   wordlist.downcase.each do |word|
     #     puts word
     #   end
@@ -399,7 +399,7 @@ module Wordlist
     #   The lazy `String#gsub` modification of the wordlist.
     #
     # @example
-    #   wordlist = Wordlist::List["foo", "bar", "baz"]
+    #   wordlist = Wordlist::Words["foo", "bar", "baz"]
     #   wordlist.mutate(/[oa]/, {'o' => '0', 'a' => '@'}).each do |word|
     #     puts word
     #   end
@@ -429,7 +429,7 @@ module Wordlist
     #   The lazy `String#gsub` modification of the wordlist.
     #
     # @example
-    #   wordlist = Wordlist::List["foo", "bar"]
+    #   wordlist = Wordlist::Words["foo", "bar"]
     #   wordlist.mutate_case.each do |word|
     #     puts word
     #   end

data/lib/wordlist/modifiers/capitalize.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/modifiers/modifier'
 
 module Wordlist
@@ -22,7 +23,7 @@ module Wordlist
       #   If no block is given, an Enumerator object will be returned.
       #
       # @example
-      #   wordlist = Wordlist::List["foo", "bar", "baz"]
+      #   wordlist = Wordlist::Words["foo", "bar", "baz"]
       #   wordlist.capitalize.each do |word|
       #     puts word
       #   end

data/lib/wordlist/modifiers/downcase.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/modifiers/modifier'
 
 module Wordlist
@@ -22,7 +23,7 @@ module Wordlist
       #   If no block is given, an Enumerator object will be returned.
       #
       # @example
-      #   wordlist = Wordlist::List["Foo", "BAR", "bAz"]
+      #   wordlist = Wordlist::Words["Foo", "BAR", "bAz"]
       #   wordlist.downcase.each do |word|
       #     puts word
       #   end

data/lib/wordlist/modifiers/gsub.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/modifiers/sub'
 
 module Wordlist
@@ -22,7 +23,7 @@ module Wordlist
       #   If no block is given, an Enumerator object will be returned.
       #
       # @example
-      #   wordlist = Wordlist::List["Foo", "BAR", "bAz"]
+      #   wordlist = Wordlist::Words["Foo", "BAR", "bAz"]
       #   wordlist.gsub(/o/,'0').each do |word|
       #     puts word
       #   end

data/lib/wordlist/modifiers/mutate.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/modifiers/sub'
 
 module Wordlist
@@ -23,7 +24,7 @@ module Wordlist
       #   If no block is given, an Enumerator object will be returned.
       #
       # @example
-      #   wordlist = Wordlist::List["foo", "bar", "baz"]
+      #   wordlist = Wordlist::Words["foo", "bar", "baz"]
       #   wordlist.mutate(/[oa]/, {'o' => '0', 'a' => '@'}).each do |word|
       #     puts word
       #   end

data/lib/wordlist/modifiers/mutate_case.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/modifiers/mutate'
 
 module Wordlist

data/lib/wordlist/modifiers/sub.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/modifiers/modifier'
 
 module Wordlist
@@ -68,7 +69,7 @@ module Wordlist
       #   If no block is given, an Enumerator object will be returned.
       #
       # @example
-      #   wordlist = Wordlist::List["foo", "bar", "baz"]
+      #   wordlist = Wordlist::Words["foo", "bar", "baz"]
       #   wordlist.sub(/o/, '0').each do |word|
       #     puts word
       #   end

data/lib/wordlist/modifiers/tr.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/modifiers/modifier'
 
 module Wordlist
@@ -48,7 +49,7 @@ module Wordlist
       #   If no block is given, an Enumerator object will be returned.
       #
       # @example
-      #   wordlist = Wordlist::List["foo", "bar", "baz"]
+      #   wordlist = Wordlist::Words["foo", "bar", "baz"]
       #   wordlist.tr("oa", "0@").each do |word|
       #     puts word
       #   end

data/lib/wordlist/modifiers/upcase.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/modifiers/modifier'
 
 module Wordlist
@@ -22,7 +23,7 @@ module Wordlist
       #   If no block is given, an Enumerator object will be returned.
       #
       # @example
-      #   wordlist = Wordlist::List["foo", "bar", "baz"]
+      #   wordlist = Wordlist::Words["foo", "bar", "baz"]
       #   wordlist.upcase.each do |word|
       #     puts word
       #   end

data/lib/wordlist/modifiers.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/modifiers/tr'
 require 'wordlist/modifiers/sub'
 require 'wordlist/modifiers/gsub'

data/lib/wordlist/operators/binary_operator.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/operators/operator'
 
 module Wordlist

data/lib/wordlist/operators/concat.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/operators/binary_operator'
 
 module Wordlist
@@ -22,8 +23,8 @@ module Wordlist
       #   If no block is given, an Enumerator object will be returned.
       #
       # @example
-      #   wordlist1 = Wordlist::List["foo", "bar", "baz"]
-      #   wordlist2 = Wordlist::List["abc", "xyz"]
+      #   wordlist1 = Wordlist::Words["foo", "bar", "baz"]
+      #   wordlist2 = Wordlist::Words["abc", "xyz"]
       #   (wordlist1 + wordlist2).each do |word|
       #     puts word
       #   end

data/lib/wordlist/operators/intersect.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/operators/binary_operator'
 require 'wordlist/unique_filter'
 
@@ -24,8 +25,8 @@ module Wordlist
       #   If no block is given, an Enumerator object will be returned.
       #
       # @example
-      #   wordlist1 = Wordlist::List["foo", "bar", "baz", "qux"]
-      #   wordlist2 = Wordlist::List["xyz", "bar", "abc", "qux"]
+      #   wordlist1 = Wordlist::Words["foo", "bar", "baz", "qux"]
+      #   wordlist2 = Wordlist::Words["xyz", "bar", "abc", "qux"]
       #   (wordlist1 & wordlist2).each do |word|
       #     puts word
       #   end

data/lib/wordlist/operators/power.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/operators/binary_operator'
 require 'wordlist/operators/product'
 
@@ -48,7 +49,7 @@ module Wordlist
       #   If no block is given, an Enumerator object will be returned.
       #
       # @example
-      #   wordlist = Wordlist::List["foo", "bar"]
+      #   wordlist = Wordlist::Words["foo", "bar"]
       #   (wordlist ** 3).each do |word|
       #     puts word
       #   end

data/lib/wordlist/operators/product.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/operators/binary_operator'
 
 module Wordlist
@@ -23,8 +24,8 @@ module Wordlist
       #   If no block is given, an Enumerator object will be returned.
       #
       # @example
-      #   wordlist1 = Wordlist::List["foo", "bar"]
-      #   wordlist2 = Wordlist::List["ABC", "XYZ"]
+      #   wordlist1 = Wordlist::Words["foo", "bar"]
+      #   wordlist2 = Wordlist::Words["ABC", "XYZ"]
       #   (wordlist1 * wordlist2).each do |word|
       #     puts word
       #   end

data/lib/wordlist/operators/subtract.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/operators/binary_operator'
 require 'wordlist/unique_filter'
 
@@ -25,8 +26,8 @@ module Wordlist
       #   If no block is given, an Enumerator object will be returned.
       #
       # @example
-      #   wordlist1 = Wordlist::List["foo", "bar", baz", "qux"]
-      #   wordlist2 = Wordlist::List["bar", "qux"]
+      #   wordlist1 = Wordlist::Words["foo", "bar", baz", "qux"]
+      #   wordlist2 = Wordlist::Words["bar", "qux"]
       #   (wordlist1 - wordlist2).each do |word|
       #     puts word
       #   end

data/lib/wordlist/operators/unary_operator.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/operators/operator'
 
 module Wordlist

data/lib/wordlist/operators/union.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/operators/binary_operator'
 require 'wordlist/unique_filter'
 
@@ -25,8 +26,8 @@ module Wordlist
       #   If no block is given, an Enumerator object will be returned.
       #
       # @example
-      #   wordlist1 = Wordlist::List["foo", "bar", "baz", "qux"]
-      #   wordlist2 = Wordlist::List["xyz", "bar", "abc", "qux"]
+      #   wordlist1 = Wordlist::Words["foo", "bar", "baz", "qux"]
+      #   wordlist2 = Wordlist::Words["xyz", "bar", "abc", "qux"]
       #   (wordlist1 | wordlist2).each do |word|
       #     puts word
       #   end

data/lib/wordlist/operators/unique.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/operators/unary_operator'
 require 'wordlist/unique_filter'
 
@@ -24,7 +25,7 @@ module Wordlist
       #   If no block is given, an Enumerator object will be returned.
       #
       # @example
-      #   wordlist= Wordlist::List["foo", "bar", "baz", "qux"]
+      #   wordlist= Wordlist::Words["foo", "bar", "baz", "qux"]
       #   (wordlist + wordlist).uniq.each do |word|
       #     puts word
       #   end

data/lib/wordlist/operators.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/operators/concat'
 require 'wordlist/operators/subtract'
 require 'wordlist/operators/product'

data/lib/wordlist/unique_filter.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'set'
 
 module Wordlist

data/lib/wordlist/version.rb

@@ -1,4 +1,6 @@
+# frozen_string_literal: true
+
 module Wordlist
-  # Word version
-  VERSION = '1.0.0'
+  # wordlist version
+  VERSION = '1.0.1'
 end

data/lib/wordlist/words.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require "wordlist/abstract_wordlist"
 
 module Wordlist

data/lib/wordlist.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'wordlist/words'
 require 'wordlist/file'
 require 'wordlist/builder'
@@ -30,7 +31,7 @@ module Wordlist
   # @param [Hash{Symbol => Object}] kwargs
   #   Additional keyword arguments for {Wordlist::File#initialize}.
   #
-  # @option [:txt, :bzip, :bzip2, :xz] :format
+  # @option kwargs [:txt, :bzip, :bzip2, :xz] :format
   #   Specifies the format of the wordlist. If no format is given, the format
   #   will be inferred from the path's file extension.
   #

data/spec/cli_spec.rb

@@ -100,14 +100,15 @@ Please report the following text to: #{Regexp.escape(described_class::BUG_REPORT
     end
 
     context "when the file does not exist" do
-      let(:path) { 'does/not/exist.txt' }
+      let(:path)          { 'does/not/exist.txt'   }
+      let(:absolute_path) { File.expand_path(path) }
 
       it "must print an error and exit with -1" do
         expect(subject).to receive(:exit).with(-1)
 
         expect {
           subject.open_wordlist(path)
-        }.to output("#{described_class::PROGRAM_NAME}: wordlist file does not exist: #{path.inspect}#{$/}").to_stderr
+        }.to output("#{described_class::PROGRAM_NAME}: wordlist file does not exist: #{absolute_path.inspect}#{$/}").to_stderr
       end
     end
   end
@@ -617,7 +618,7 @@ Please report the following text to: #{Regexp.escape(described_class::BUG_REPORT
         context "when given #{flag}" do
           let(:argv) { [flag] }
 
-          it "must append to #modifiers" do
+          it "must print the program name and the Wordlist::VERSION" do
             expect(subject).to receive(:exit)
 
             expect {
@@ -631,7 +632,7 @@ Please report the following text to: #{Regexp.escape(described_class::BUG_REPORT
         context "when given #{flag}" do
           let(:argv) { [flag] }
 
-          it "must append to #modifiers" do
+          it "must print the option paresr --help output" do
             expect(subject).to receive(:exit)
 
             expect {

data/spec/file_spec.rb

@@ -20,6 +20,17 @@ describe Wordlist::File do
           described_class.new(path)
         }.to raise_error(Wordlist::WordlistNotFound,"wordlist file does not exist: #{path.inspect}")
       end
+
+      context "and the path is relative" do
+        let(:path)          { 'does/not/exist.txt'   }
+        let(:absolute_path) { File.expand_path(path) }
+
+        it "must include the absolute path in the exception message" do
+          expect {
+            described_class.new(path)
+          }.to raise_error(Wordlist::WordlistNotFound,"wordlist file does not exist: #{absolute_path.inspect}")
+        end
+      end
     end
 
     context "when given a relative path" do

data/spec/lexer_spec.rb

@@ -4,10 +4,6 @@ require 'wordlist/lexer'
 describe Wordlist::Lexer do
   let(:text) { "foo bar baz qux" }
 
-  it do
-    expect(described_class).to include(Enumerable)
-  end
-
   describe "#initialize" do
     let(:default_lang) { Wordlist::Lexer::Lang.default }
 
@@ -153,6 +149,86 @@ describe Wordlist::Lexer do
         }.to yield_successive_args(*expected_words)
       end
 
+      context "and when the text is empty" do
+        let(:text) { '' }
+
+        it "must not yield any words" do
+          expect { |b|
+            subject.parse(text,&b)
+          }.to_not yield_control
+        end
+      end
+
+      context "and when the text is only whitespace" do
+        let(:text) { " \t\r\n" }
+
+        it "must not yield any words" do
+          expect { |b|
+            subject.parse(text,&b)
+          }.to_not yield_control
+        end
+      end
+
+      context "and when the text contains newlines" do
+        let(:text) { expected_words.join("\n") }
+
+        it "must parse each line" do
+          expect { |b|
+            subject.parse(text,&b)
+          }.to yield_successive_args(*expected_words)
+        end
+      end
+
+      context "and when the text is only unicode whitespace" do
+        let(:text) { "\u{a0}" }
+
+        it "must not yield any words" do
+          expect { |b|
+            subject.parse(text,&b)
+          }.to_not yield_control
+        end
+      end
+
+      context "and when the text is only unicode symbols" do
+        let(:text) { "©" }
+
+        it "must not yield any words" do
+          expect { |b|
+            subject.parse(text,&b)
+          }.to_not yield_control
+        end
+      end
+
+      context "and when the words are separated by unicode whitespace" do
+        let(:text) { expected_words.join("\u{a0}") }
+
+        it "must skip the unicode whitespace and yield the words" do
+          expect { |b|
+            subject.parse(text,&b)
+          }.to yield_successive_args(*expected_words)
+        end
+      end
+
+      context "and when the text contains unicode symbols" do
+        let(:text) { "© #{super()}" }
+
+        it "must skip any unicode symbols and yield the words" do
+          expect { |b|
+            subject.parse(text,&b)
+          }.to yield_successive_args(*expected_words)
+        end
+      end
+
+      context "when the words contain unicode letters" do
+        let(:expected_words) { %w[Hervé Schäfer Ålesund] }
+
+        it "must parse words containing unicode letters" do
+          expect { |b|
+            subject.parse(text,&b)
+          }.to yield_successive_args(*expected_words)
+        end
+      end
+
       context "when the words contain uppercase letters" do
         let(:expected_words) { %w[foo Bar baZ QUX] }
 
@@ -200,16 +276,6 @@ describe Wordlist::Lexer do
         end
       end
 
-      context "and when the text contains newlines" do
-        let(:text) { expected_words.join("\n") }
-
-        it "must parse each line" do
-          expect { |b|
-            subject.parse(text,&b)
-          }.to yield_successive_args(*expected_words)
-        end
-      end
-
       context "and when the text contains punctuation" do
         let(:text) { expected_words.join(", ") + '.' }
 

data/spec/modifiers/sub_spec.rb

@@ -53,7 +53,7 @@ describe Wordlist::Modifiers::Sub do
     end
 
     context "when a block is given" do
-      subject { described_class.new(wordlist,pattern,replace,&block) }
+      subject { described_class.new(wordlist,pattern,&block) }
 
       it "must set #block" do
         expect(subject.block).to eq(block)

data/spec/operators/unary_operator_spec.rb

@@ -0,0 +1,14 @@
+require 'spec_helper'
+require 'wordlist/operators/unary_operator'
+
+describe Wordlist::Operators::UnaryOperator do
+  let(:wordlist) { %w[foo bar] }
+
+  subject { described_class.new(wordlist) }
+
+  describe "#initialize" do
+    it "must set #wordlist" do
+      expect(subject.wordlist).to eq(wordlist)
+    end
+  end
+end

data/spec/unique_filter_spec.rb

@@ -53,8 +53,8 @@ describe Wordlist::UniqueFilter do
 
     before { subject.add(word) }
 
-    context "when the unique filter contains the String's hash" do
-      it "must return nil" do
+    context "when the unique filter already contains the String's hash" do
+      it "must return false" do
         expect(subject.add?(word)).to be(false)
       end
     end
@@ -62,7 +62,7 @@ describe Wordlist::UniqueFilter do
     context "when the unqiue filter does not contain the String's hash" do
       let(:new_word) { "bar" }
 
-      it "must return nil" do
+      it "must return true" do
         expect(subject.add?(new_word)).to be(true)
       end
     end

data/wordlist.gemspec

@@ -20,6 +20,7 @@ Gem::Specification.new do |gem|
   gem.authors     = Array(gemspec['authors'])
   gem.email       = gemspec['email']
   gem.homepage    = gemspec['homepage']
+  gem.metadata    = gemspec['metadata'] if gemspec['metadata']
 
   glob = lambda { |patterns| gem.files & Dir[*patterns] }
 

metadata

@@ -1,59 +1,31 @@
 --- !ruby/object:Gem::Specification
 name: wordlist
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.0.1
 platform: ruby
 authors:
 - Postmodern
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-11-02 00:00:00.000000000 Z
+date: 2023-07-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: rubygems-tasks
+  name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.1'
+        version: '2.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.1'
-- !ruby/object:Gem::Dependency
-  name: rspec
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '2.4'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '2.4'
-- !ruby/object:Gem::Dependency
-  name: yard
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.8'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.8'
-description: Wordlist is a Ruby library for reading, manipulating, and creating wordlists,
-  efficiently.
+        version: '2.0'
+description: Wordlist is a Ruby library and CLI for reading, combining, mutating,
+  and building wordlists, efficiently.
 email: postmodern.mod3@gmail.com
 executables:
 - wordlist
@@ -158,8 +130,6 @@ files:
 - spec/abstract_list_spec.rb
 - spec/builder_examples.rb
 - spec/builder_spec.rb
-- spec/classes/parser_class.rb
-- spec/classes/test_list.rb
 - spec/cli_spec.rb
 - spec/compression/reader_spec.rb
 - spec/compression/writer_spec.rb
@@ -194,6 +164,7 @@ files:
 - spec/operators/power_spec.rb
 - spec/operators/product_spec.rb
 - spec/operators/subtract_spec.rb
+- spec/operators/unary_operator_spec.rb
 - spec/operators/union_spec.rb
 - spec/operators/unique_spec.rb
 - spec/spec_helper.rb
@@ -207,7 +178,11 @@ files:
 homepage: https://github.com/postmodern/wordlist.rb
 licenses:
 - MIT
-metadata: {}
+metadata:
+  documentation_uri: https://rubydoc.info/gems/wordlist
+  source_code_uri: https://github.com/postmodern/wordlist.rb
+  bug_tracker_uri: https://github.com/postmodern/wordlist.rb/issues
+  changelog_uri: https://github.com/postmodern/wordlist.rb/blob/master/ChangeLog.md
 post_install_message:
 rdoc_options: []
 require_paths:
@@ -216,15 +191,15 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 2.0.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.22
+rubygems_version: 3.4.10
 signing_key:
 specification_version: 4
-summary: Ruby library for reading, manipulating, and creating wordlists.
+summary: Ruby library and CLI for reading, combining, mutating, and building wordlists
 test_files: []

data/spec/classes/parser_class.rb

@@ -1,7 +0,0 @@
-require 'wordlist/parsers'
-
-class ParserClass
-
-  include Wordlist::Parsers
-
-end

data/spec/classes/test_list.rb

@@ -1,9 +0,0 @@
-require 'wordlist/list'
-
-class TestList < Wordlist::List
-
-  def each_word
-    yield 'omg.hackers'
-  end
-
-end