spellr 0.5.2 → 0.5.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ffa5cd50771c2305c4e4f3e14d6905b40be8b337c6ebbddc2b2d8a82649cfb55
-  data.tar.gz: 51d07400d834a8c5e4e4432a5ecb95017bd4fb9896addb39753a7490bb4793f5
+  metadata.gz: 6ab2e491fac49775163c74ab18787f8abed0b46f96de0bbcb2fa00d02c3ebe89
+  data.tar.gz: b6fcd62fb1a090e9f82e6d7b591eb44156f0a000ef1f7e74417a6d0cef9b8e8f
 SHA512:
-  metadata.gz: 0fb135cb1f8368c65372e10af566b5a8553f926aa0ac6443f047be7042fd1c2d07a7ae0e451995430048b22241c266d40826306b58f5aa9665dd2ec624ca0ca7
-  data.tar.gz: e18d571c9269875bfede005247266a9c39dff4611f76a3327adf19dda08e400b9c9066adf6cdc05580e7282f39a23549a3d0b436616ecc868c763bc6a4979a2a
+  metadata.gz: be574430d9bd37fb857670e4e555e5c90559a62749e788af6e844c24a56f4c08aaeee5b7498f10c3a7edce39cf0393927e9439871ae59569e46e84f719569467
+  data.tar.gz: b711c144f99e37d96bf789caa3dcabb36273218f6b02c02f368c2164575a41e99a0b32c2382c66679f3583ffc6ca85f1600e4aff59690de42af7f858f0aea929

data/CHANGELOG.md

@@ -1,3 +1,7 @@
+# v0.5.3
+- update fast_ignore requirement. it's slightly faster.
+- misc other performance improvements
+
 # v0.5.2
 - require Parallel dependency in gemspec (oops)
 

data/README.md

@@ -1,5 +1,6 @@
 # Spellr
 
+[![Gem Version](https://badge.fury.io/rb/spellr.svg)](https://rubygems.org/gems/spellr)
 [![Build Status](https://travis-ci.org/robotdana/spellr.svg?branch=master)](https://travis-ci.org/robotdana/spellr)
 
 Spell check your source code for fun and occasionally finding bugs

data/lib/.spellr.yml

@@ -29,6 +29,8 @@ excludes: # this list is parsed with the .gitignore format
 languages:
   english:
     locale: US # options US, CA, AU, GBs (GB with -ise endings), GBz (GB with -ize endings)
+  spellr:
+    addable: false
   ruby:
     includes: # Filtered using gitignore format
       - '*.rb'

data/lib/spellr/backports.rb

@@ -12,6 +12,10 @@ class Array
   end
 end
 
+class Regexp
+  alias_method :match?, :match unless RUBY_VERSION >= '2.4'
+end
+
 class String
   alias_method :match?, :match unless RUBY_VERSION >= '2.4'
 end

data/lib/spellr/check.rb

@@ -6,6 +6,7 @@ require_relative 'token'
 require_relative 'column_location'
 require_relative 'line_location'
 require_relative 'output_stubbed'
+require_relative 'backports'
 
 require 'parallel'
 

data/lib/spellr/config.rb

@@ -61,7 +61,7 @@ module Spellr
 
     def languages
       @languages ||= @config[:languages].map do |key, args|
-        Spellr::Language.new(key, args)
+        Spellr::Language.new(key, **args)
       end
     end
 
@@ -89,14 +89,18 @@ module Spellr
     private
 
     def only_has_one_key_per_language
-      conflicting_languages = languages.group_by(&:key).values.select { |g| g.length > 1 }
-
-      conflicting_languages.each do |conflicts|
+      languages_with_conflicting_keys.each do |conflicts|
         errors << "Error: #{conflicts.map(&:name).join(' & ')} share the same language key "\
         "(#{conflicts.first.key}). Please define one to be different with `key:`"
       end
     end
 
+    def languages_with_conflicting_keys
+      languages.select(&:addable?).group_by(&:key).values.select do |g|
+        g.length > 1
+      end
+    end
+
     def keys_are_single_characters
       bad_languages = languages.select { |l| l.key.length > 1 }
 

data/lib/spellr/file_list.rb

@@ -14,6 +14,8 @@ module Spellr
 
     def each
       fast_ignore.each do |file|
+        next unless cli_patterns_ignore.allowed?(file)
+
         file = Spellr::File.new(file)
 
         yield(file)
@@ -41,9 +43,13 @@ module Spellr
     def fast_ignore
       FastIgnore.new(
         ignore_rules: Spellr.config.excludes,
-        include_rules: Spellr.config.includes + cli_patterns,
+        include_rules: Spellr.config.includes,
         gitignore: gitignore_path
       )
     end
+
+    def cli_patterns_ignore
+      @cli_patterns_ignore ||= FastIgnore.new(include_rules: cli_patterns, gitignore: false)
+    end
   end
 end

data/lib/spellr/interactive_add.rb

@@ -19,14 +19,18 @@ module Spellr
       @languages ||= Spellr.config.languages_for(token.location.file.to_path)
     end
 
+    def addable_languages
+      languages.select(&:addable?)
+    end
+
     def language_keys
-      @language_keys ||= @languages.map(&:key)
+      @language_keys ||= addable_languages.map(&:key)
     end
 
     def ask_wordlist
       puts "Add #{red(token)} to wordlist:"
 
-      languages.each do |language|
+      addable_languages.each do |language|
         puts "[#{language.key}] #{language.name}"
       end
 
@@ -50,7 +54,7 @@ module Spellr
     end
 
     def add_to_wordlist(choice)
-      wordlist = languages.find { |w| w.key == choice }.project_wordlist
+      wordlist = addable_languages.find { |w| w.key == choice }.project_wordlist
       wordlist << token
       reporter.increment(:total_added)
       puts "Added #{red(token)} to #{wordlist.name} wordlist"

data/lib/spellr/key_tuner/naive_bayes.rb

@@ -11,10 +11,10 @@ class NaiveBayes
 
   def initialize(path = YAML_PATH)
     load_from_yaml(path) if File.exist?(path)
+    @key = {}
   end
 
   def key?(string)
-    @key ||= {}
     @key.fetch(string) do
       @key[string] = classify(PossibleKey.new(string).features).start_with?('key')
     end
@@ -92,7 +92,7 @@ class NaiveBayes
   # value: the value of the feature for which we are finding the probability
   # class_name: name of the class in consideration
   def feature_probability(feature, value, class_name)
-    Stats.gaussian_probability(value, feature_set[class_name][feature])
+    Stats.gaussian_probability(value, **feature_set[class_name][feature])
   end
 
   # multiply together the feature probabilities for all of the
@@ -103,12 +103,16 @@ class NaiveBayes
     end
   end
 
+  def heuristic_weight
+    @heuristic_weight ||= 10**Spellr.config.key_heuristic_weight
+  end
+
   # this is where we compute the final naive Bayesian probability
   # for a given set of features being a part of a given class.
   def class_probability(features, class_name)
     class_fraction = 1.0 / num_classes
     feature_bayes = feature_multiplication(features, class_name)
-    feature_bayes *= (10**Spellr.config.key_heuristic_weight) if class_name.start_with?('key_')
+    feature_bayes *= heuristic_weight if class_name.start_with?('key_')
     feature_bayes * class_fraction
   end
 

data/lib/spellr/language.rb

@@ -7,12 +7,17 @@ module Spellr
     attr_reader :name
     attr_reader :key
 
-    def initialize(name, key: name[0], includes: [], hashbangs: [], locale: [])
+    def initialize(name, key: name[0], includes: [], hashbangs: [], locale: [], addable: true) # rubocop:disable Metrics/ParameterLists, Metrics/MethodLength
       @name = name
       @key = key
       @includes = includes
       @hashbangs = hashbangs
       @locales = Array(locale)
+      @addable = addable
+    end
+
+    def addable?
+      @addable
     end
 
     def matches?(file)

data/lib/spellr/token.rb

@@ -4,8 +4,9 @@ require_relative 'column_location'
 require_relative 'string_format'
 
 class String
+  @@spellr_normalize = {} # rubocop:disable Style/ClassVars # I want to share this with subclasses
+
   def spellr_normalize
-    @@spellr_normalize ||= {} # rubocop:disable Style/ClassVars # I want to share this with subclasses
     @@spellr_normalize.fetch(to_s) do |term|
       @@spellr_normalize[term] = "#{term.strip.downcase.unicode_normalize.tr('’', "'")}\n"
     end

data/lib/spellr/tokenizer.rb

@@ -19,7 +19,7 @@ module Spellr
       @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_key: skip_key)
+      @line_tokenizer = LineTokenizer.new('', skip_key: skip_key)
     end
 
     def terms
@@ -34,6 +34,8 @@ module Spellr
       file.each_line do |line|
         prepare_tokenizer_for_line(line).each_term(&block)
       end
+    ensure
+      file.close
     end
 
     def each_token(skip_term_proc: nil) # rubocop:disable Metrics/MethodLength
@@ -64,6 +66,8 @@ module Spellr
         char_offset += line.length
         byte_offset += line.bytesize
       end
+    ensure
+      file.close
     end
 
     def normalized_terms

data/lib/spellr/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Spellr
-  VERSION = '0.5.2'
+  VERSION = '0.5.3'
 end

data/lib/spellr/wordlist.rb

@@ -14,6 +14,7 @@ module Spellr
       path = @file = file
       @path = Pathname.pwd.join('.spellr_wordlists').join(path).expand_path
       @name = name
+      @include = {}
     end
 
     def each(&block)
@@ -29,20 +30,24 @@ module Spellr
     # significantly faster than default Enumerable#include?
     # requires terms to have been sorted
     def include?(term)
-      include_cache[term.spellr_normalize]
+      term = term.spellr_normalize
+      @include.fetch(term) do
+        @include[term] = words.bsearch { |value| term <=> value }
+      end
     end
 
     def <<(term)
       term = term.spellr_normalize
       touch
-      include_cache[term] = true
+      @include[term] = true
       insert_sorted(term)
-      @path.write(to_a.join) # we don't need to clear the cache
+      @path.write(words.join) # we don't need to clear the cache
     end
 
-    def to_a
-      @to_a ||= super
+    def words
+      @words ||= (exist? ? @path.readlines : [])
     end
+    alias_method :to_a, :words
 
     def clean(file = @path)
       require_relative 'tokenizer'
@@ -78,21 +83,13 @@ module Spellr
     private
 
     def insert_sorted(term)
-      insert_at = to_a.bsearch_index { |value| value >= term }
-      insert_at ? to_a.insert(insert_at, term) : to_a.push(term)
-    end
-
-    def include_cache
-      @include_cache ||= Hash.new do |cache, term|
-        cache[term] = to_a.bsearch do |value|
-          term <=> value
-        end
-      end
+      insert_at = words.bsearch_index { |value| value >= term }
+      insert_at ? words.insert(insert_at, term) : words.push(term)
     end
 
     def clear_cache
-      @to_a = nil
-      @include = nil
+      @words = nil
+      @include = {}
       remove_instance_variable(:@exist) if defined?(@exist)
     end
 

data/spellr.gemspec

@@ -34,6 +34,6 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency 'rubocop-rspec'
   spec.add_development_dependency 'terminal-table'
   spec.add_development_dependency 'tty_string'
-  spec.add_dependency 'fast_ignore', '~> 0.4.0'
+  spec.add_dependency 'fast_ignore', '~> 0.5.1'
   spec.add_dependency 'parallel', '~> 1.0'
 end

data/wordlists/spellr.txt

@@ -0,0 +1,17 @@
+disable
+enable
+excludes
+generated
+hashbangs
+heuristic
+includes
+key
+languages
+length
+locale
+minimum
+robotdana
+spellr
+weight
+word
+wordlists

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: spellr
 version: !ruby/object:Gem::Version
-  version: 0.5.2
+  version: 0.5.3
 platform: ruby
 authors:
 - Dana Sherson
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2019-10-30 00:00:00.000000000 Z
+date: 2020-02-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -142,14 +142,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.4.0
+        version: 0.5.1
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.4.0
+        version: 0.5.1
 - !ruby/object:Gem::Dependency
   name: parallel
   requirement: !ruby/object:Gem::Requirement
@@ -228,6 +228,7 @@ files:
 - wordlists/javascript.txt
 - wordlists/ruby.txt
 - wordlists/shell.txt
+- wordlists/spellr.txt
 homepage: http://github.com/robotdana/spellr
 licenses:
 - MIT