ruby-spellchecker 0.1.3 → 0.1.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 640ae53e5d025e1a9721991025c156f0572121defc5a0c12e8b3261ec0fae6ff
-  data.tar.gz: 504ac98dd3b4d985f910ad662f5e02b5feb54bb6986f9a50597cdee36893e97f
+  metadata.gz: ef027e0b01226b4df2d1ba0d4e4d63b9b28ee84070689d747f5573e52c94014b
+  data.tar.gz: 5daeaa089531bd755434545304c96a21501b0f2f5975611a9fc32f38cec92ee2
 SHA512:
-  metadata.gz: 495d4d161b1ebeebfb45086403fc00588098e9a9b7713627495a09f77ab367c7d77a29771c0c94f13704f7d104331fa364abd2b976043907662b49b3bb51d9e2
-  data.tar.gz: b0841b2ef09d09291da88cec2b4b8a871b78137db3b908c725cdcd3ff86d3d03cac2ffbd9aed9125f9316797c1684cadb7dd6ef651ce3bf9ad1c161b81e33cde
+  metadata.gz: 62237078c65b536f9ca986324f532ecf439f511184bf8ad738163b0681bb7f6cd66c783d5b1e63086d15802ea2c1ceb304ea35ddee9449fc6b3592c59b301d85
+  data.tar.gz: ff1bc1100afcdd792dcc600e8c42b696d2703bed837c2ea4fbccf2acdf8a7284bfb4b62341a72a3a675232a48e7131ebf025db4b3d32fb39aa0d7ff6cd629264

data/README.md

@@ -1,5 +1,7 @@
 # Ruby Spellchecker
 
+Fast ruby spelling and grammar checker that can be used for autocorrection. Used by [SiteInspector](http://github.com/siteinspector/siteinspector).
+
 ## Installation
 
 Add this line to your application's Gemfile:

data/dictionaries/ngrams.csv

@@ -693,7 +693,6 @@ corona virus,coronavirus
 cote chalonnaise,Côte Chalonnaise
 cote d'argent,Côte d'Argent
 cote d'azur,Côte d'Azur
-cote d'ivoire,Côte d'Ivoire
 cote d'opale,Côte d'Opale
 cote d'or,Côte d'Or
 cote d`argent,Côte d`Argent
@@ -2012,11 +2011,6 @@ salvador dali,Salvador Dalí
 sam elliot,Sam Elliott
 san luis potosi,San Luis Potosí
 sao paolo,São Paulo
-sao paulo,São Paulo
-sao tome and principe,São Tomé and Príncipe
-sao tome and príncipe,São Tomé and Príncipe
-sao tomé and principe,São Tomé and Príncipe
-sao tomé and príncipe,São Tomé and Príncipe
 sau paolo,São Paulo
 sau paulo,São Paulo
 saudia arabia,saudi Arabia

data/dictionaries/typos.csv

@@ -21157,7 +21157,6 @@ complexty,complexity
 complexy,complexity
 compliacted,complicate
 compliactions,complication
-compliancy,compliance
 complianed,compliance
 complians,complains
 compliants,complaints
@@ -89409,7 +89408,6 @@ reey,really
 refacted,refactored
 refactor's,refactored
 refactorig,refactoring
-refactorings,refactors
 refactorng,refactoring
 refactorsing,refactoring
 refarence,references

data/lib/spellchecker/detect_typo.rb

@@ -6,6 +6,9 @@ module Spellchecker
     ABBREVIATION_REGEXP = /\A(?:[A-Z]{2,4})|(?:[A-Z][a-z])\z/.freeze
 
     LENGTH_LIMIT = 2
+    ABBREVIATION_LENGTH = 2
+    NUMBER_SHORTENING_SUFFIX = 'th'
+    SHORTENINGS = Set.new(%w[ver]).freeze
 
     module_function
 
@@ -20,7 +23,7 @@ module Spellchecker
 
       return unless correction
       return if PROPER_NAME_REGEXP.match?(word)
-      return if ABBREVIATION_REGEXP.match?(word)
+      return if abbreviation?(token) || shortening?(token)
       return if Dictionaries::EnglishWords.include?(Utils.replace_quote(word))
 
       return if token.capital? && proper_noun?(word)
@@ -38,5 +41,25 @@ module Spellchecker
         Dictionaries::CompanyNames.include?(word) ||
         Dictionaries::UsToponyms.include?(word)
     end
+
+    # @param token [Spellchecker::Tokenizer::Token]
+    # @return [Boolean]
+    def abbreviation?(token)
+      return true if ABBREVIATION_REGEXP.match?(token.text)
+      return true if token.text.length <= ABBREVIATION_LENGTH &&
+                     !token.prev.word? && !token.next.word?
+
+      false
+    end
+
+    # @param token [Spellchecker::Tokenizer::Token]
+    # @return [Boolean]
+    def shortening?(token)
+      return true if token.text == NUMBER_SHORTENING_SUFFIX && token.prev.digit?
+      return true if SHORTENINGS.include?(token.downcased) &&
+                     (token.next.dot? || token.next.digit?)
+
+      false
+    end
   end
 end

data/lib/spellchecker/dictionaries/ngram_list.rb

@@ -11,7 +11,7 @@ module Spellchecker
       # @return [Hash<Array<String>, String>]
       def all
         @all || MUTEX.synchronize do
-          @all ||= CSV.parse(PATH.read).to_h.transform_keys { |e| e.split(' ') }
+          @all ||= CSV.parse(PATH.read).to_h.transform_keys(&:split)
         end
       end
 

data/lib/spellchecker/tokenizer.rb

@@ -16,7 +16,7 @@ module Spellchecker
     SIMPLE_POST = ['!', '?', ',', ':', ';', '.'].freeze
     PAIR_PRE = ['(', '{', '[', '<', '«', '„', '‘'].freeze
     PAIR_POST = [')', '}', ']', '>', '»', '“', '’'].freeze
-    PRE_N_POST = ['"', "'", '`'].freeze
+    PRE_N_POST = ['"', "'", '`', '*'].freeze
 
     SPLITTABLES = SIMPLE_PRE + SIMPLE_POST + PAIR_PRE + PAIR_POST + PRE_N_POST
 

data/lib/spellchecker/tokenizer/token.rb

@@ -43,6 +43,21 @@ module Spellchecker
         @capital ||= text.match?(/\A[A-Z]/)
       end
 
+      # @return [Boolean]
+      def word?
+        @word ||= text.length > 1 || text.match?(/\w/)
+      end
+
+      # @return [Boolean]
+      def digit?
+        @digit ||= text.match?(/\A\d+\z/)
+      end
+
+      # @return [Boolean]
+      def dot?
+        @dot ||= text == Tokenizer::DOT
+      end
+
       # @return [String]
       def downcased
         @downcased ||= text.downcase

data/lib/spellchecker/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Spellchecker
-  VERSION = '0.1.3'
+  VERSION = '0.1.4'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ruby-spellchecker
 version: !ruby/object:Gem::Version
-  version: 0.1.3
+  version: 0.1.4
 platform: ruby
 authors:
 - Pete Matsyburka
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-11-28 00:00:00.000000000 Z
+date: 2020-12-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec