typo_checker 0.1.5 → 0.1.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7173dd0294a0f7645db2dde57c7fdd4dedd49643668ce2c7d59bc13d09d1d9f4
-  data.tar.gz: 37477c3e7eb020a7112fae39b9c30bdc3b78d8b4cb526da8ecab38a17e3ecfce
+  metadata.gz: 15d511455e488fe8175d4b8eb85f9d7a55647515d39450d1f627254ee90571a3
+  data.tar.gz: 3841f4796632094f9e8b17fb3ff9bdd219e5bb2b783ba11e1ec074788185f72e
 SHA512:
-  metadata.gz: 954a4e7a09375a52125d1db49ac0a5845ae8ef56867eb1e7c984244513ff0e801977a5f691ef181d8f7f91bb471af706fd94b04246c5bdc11a37aced5a6ffaf4
-  data.tar.gz: 38b377026a5433b5800517076afd009222e2a903cbd0df9b324b3e3c2ccd1fbf2e5b7679d7a505f5d073ccbf54bdad6061c2da3e056f4990e5de46cae74ec555
+  metadata.gz: a42eb16f7838b9e56e39a290d39682c4bb082c643526038d01b168b5f29a1a922fc8dfc6882d205684a906d0155ff96c610e4ccc9f8386b363cd560d781ef292
+  data.tar.gz: 7c097ec3e93767e28c12c414ec64cc439b06630c3d94983da15f8335ad53077938f3fbbcd240c89c482fd3e15cbeb8cafc077a85e8cd2428c3eba81208d13943

data/lib/data/typos.csv

@@ -44440,7 +44440,6 @@ falsde,false
 falsei,false
 falseley,falsely
 falsemounted,false
-falsey,false
 falsh,flash
 falshbacks,flashbacks
 falshed,flashed
@@ -112652,7 +112651,6 @@ unintuive,unintuitive
 uniomus,unanimous
 unionous,unanimous
 unioun,union
-uniq,unique
 uniqe,unique
 uniqely,uniquely
 uniqu,unique
@@ -114460,7 +114458,6 @@ uther,other
 uthor,author
 utiility,utility
 utiity,utility
-util,until
 utilaties,utilities
 utilaty,utility
 utiliatrian,utilitarian

data/lib/typo_checker/configuration.rb

@@ -0,0 +1,11 @@
+module TypoChecker
+  class Configuration
+    attr_reader :excludes, :skips, :stdoutput
+
+    def initialize(excludes = nil, skips = nil, stdoutput = true)
+      @excludes = excludes || []
+      @skips = (skips || []).map(&:downcase)
+      @stdoutput = stdoutput.nil? ? true : stdoutput
+    end
+  end
+end

data/lib/typo_checker/file_scanner.rb

@@ -0,0 +1,81 @@
+module TypoChecker
+  class FileScanner
+    def initialize(typos, stdoutput)
+      @typos = typos
+      @stdoutput = stdoutput
+    end
+
+    def scan_file(path, result)
+      File.foreach(path).with_index do |line, line_number|
+        words = line.split(/[^a-zA-Z0-9']+/)
+        check_words = words.map { |word| split_function_name(word) }.flatten
+        check_words.each do |word|
+          clean_word = word.gsub(/^[^\w]+|[^\w]+$/, '')
+          char_index = line.index(clean_word)
+          check_word(clean_word, path, line_number, char_index, result)
+        end
+      end
+    end
+
+    private
+
+    def check_word(word, file, line_num, char_index, result)
+      return unless @typos.key?(word.downcase)
+
+      corrected_word = corrected_word(word, @typos[word.downcase])
+      typo_details = { incorrect_word: word, correct_word: corrected_word }
+      typo_path = "#{file}:#{line_num + 1}:#{char_index + 1}"
+      path = file.sub(%r{^./}, '')
+
+      result[path] ||= {}
+      result[path][:typos] ||= []
+      line_entry = result[path][:typos].find { |entry| entry[:line] == line_num + 1 }
+
+      if line_entry
+        line_entry[:typos] << typo_details
+      else
+        result[path][:typos] << { line: line_num + 1, typos: [typo_details] }
+      end
+
+      stdout(typo_path, word, corrected_word)
+    end
+
+    def split_function_name(name)
+      # Split on capital letters or digit transitions.
+      # This handles cases like camelCase, PascalCase, and mixed cases with digits.
+      name.gsub(/([a-zA-Z])(\d)/, '\1 \2')    # Between letter and digit
+          .gsub(/(\d)([A-Z])/, '\1 \2')       # Between digit and capital letter
+          .gsub(/([a-z])([A-Z])/, '\1 \2')    # Between lowercase and uppercase
+          .split(/[\s_]+/)                    # Split on spaces and underscores
+    end
+
+    def corrected_word(word, typo_correct_word)
+      if word == word.capitalize
+        typo_correct_word.capitalize
+      elsif word == word.upcase
+        typo_correct_word.upcase
+      else
+        typo_correct_word
+      end
+    end
+
+    def stdout(typo_path, word, corrected_word)
+      return unless @stdoutput
+
+      puts "Typo found in #{colorize_light_blue(typo_path)}: " \
+            "#{colorize_red(word)} -> #{colorize_green(corrected_word)}"
+    end
+
+    def colorize_red(text)
+      "\e[31m#{text}\e[0m"
+    end
+
+    def colorize_green(text)
+      "\e[32m#{text}\e[0m"
+    end
+
+    def colorize_light_blue(text)
+      "\e[94m#{text}\e[0m"
+    end
+  end
+end

data/lib/typo_checker/repository_scanner.rb

@@ -0,0 +1,58 @@
+require 'find'
+
+module TypoChecker
+  class RepositoryScanner
+    def initialize(repo_path, configuration)
+      @repo_path = repo_path
+      @configuration = configuration
+      @file_scanner = FileScanner.new(load_typos, configuration.stdoutput)
+    end
+
+    def scan
+      result = {}
+      Find.find(@repo_path) do |path|
+        next if exclude_path?(path)
+
+        @file_scanner.scan_file(path, result) if File.file?(path) && text_file?(path)
+      end
+      result.map do |path, data|
+        data[:typos].map do |entry|
+          { path: path, line: entry[:line], typos: entry[:typos] }
+        end
+      end.flatten
+    end
+
+    private
+
+    def exclude_path?(path)
+      exclude_patterns.any? { |pattern| path.match?(pattern) }
+    end
+
+    def exclude_patterns
+      @exclude_patterns ||= @configuration.excludes + [
+        %r{\.git/.*},        # Skip all files and directories inside .git
+        %r{node_modules/.*}, # Skip all files and directories inside node_modules
+        %r{vendor/.*},       # Skip all files and directories inside vendor
+        %r{tmp/.*}           # Skip all files and directories inside tmp
+      ]
+    end
+
+    def text_file?(path)
+      excluded_extensions = %w[.log]
+
+      return false if excluded_extensions.include?(File.extname(path))
+
+      %w[
+        .rb .txt .md .html .css .js .py .java .php .go .swift .ts .scala .c .cpp .csharp .h .lua .pl .rs .kt
+        .d .r .m .sh .bash .bat .json .yaml .xml .scss .tsv .vb .ps1 .clj .elixir .f# .vhdl .verilog
+        .ada .ml .lisp .prolog .tcl .rexx .awk .sed .coffee .groovy .dart .haxe .zig .nim .crystal .reason .ocaml
+        .forth .v .xhtml .julia .racket .scheme .rust .graphql
+      ].include? File.extname(path)
+    end
+
+    def load_typos
+      csv_file = File.expand_path('../data/typos.csv', __dir__)
+      TyposLoader.new(@configuration.skips).load_typos(csv_file)
+    end
+  end
+end

data/lib/typo_checker/typos_loader.rb

@@ -0,0 +1,19 @@
+require 'csv'
+
+module TypoChecker
+  class TyposLoader
+    def initialize(skips)
+      @skips = skips
+    end
+
+    def load_typos(file_path)
+      typos = {}
+      CSV.foreach(file_path, headers: false) do |row|
+        next if @skips.include?(row[0])
+
+        typos[row[0]] = row[1]
+      end
+      typos
+    end
+  end
+end

data/lib/typo_checker/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module TypoChecker
-  VERSION = '0.1.5'
+  VERSION = '0.1.6'
 end

data/lib/typo_checker.rb

@@ -3,134 +3,20 @@
 require 'csv'
 require 'find'
 require 'fileutils'
+require_relative 'typo_checker/configuration'
+require_relative 'typo_checker/typos_loader'
+require_relative 'typo_checker/file_scanner'
+require_relative 'typo_checker/repository_scanner'
 
 module TypoChecker
   class Checker
-    attr_reader :typos, :excludes, :skips, :stdoutput
-
     def initialize(excludes = [], skips = [], stdoutput = true)
-      @excludes = excludes
-      @skips = skips.map(&:downcase)
-      @typos = load_typos
-      @stdoutput = stdoutput
+      @configuration = Configuration.new(excludes, skips, stdoutput)
     end
 
     def scan_repo(repo_path = Dir.pwd)
-      result = {}
-      Find.find(repo_path) do |path|
-        next if exclude_path?(path)
-
-        scan_file(path, result) if File.file?(path) && text_file?(path)
-      end
-
-      result.map do |path, data|
-        data[:typos].map do |entry|
-          { path: path, line: entry[:line], typos: entry[:typos] }
-        end
-      end.flatten
-    end
-
-    private
-
-    def exclude_path?(path)
-      exclude_patterns.any? { |pattern| path.match?(pattern) }
-    end
-
-    def exclude_patterns
-      @exclude_patterns ||= excludes + [
-        %r{\.git/.*},        # Skip all files and directories inside .git
-        %r{node_modules/.*}, # Skip all files and directories inside node_modules
-        %r{vendor/.*},       # Skip all files and directories inside vendor
-        %r{tmp/.*}           # Skip all files and directories inside tmp
-      ]
-    end
-
-    def load_typos
-      typos = {}
-      csv_file = File.expand_path('data/typos.csv', __dir__)
-      CSV.foreach(csv_file, headers: false) do |row|
-        next if skips.include?(row[0])
-
-        typos[row[0]] = row[1]
-      end
-      typos
-    end
-
-    def text_file?(path)
-      excluded_extensions = %w[.log]
-
-      return false if excluded_extensions.include?(File.extname(path))
-
-      %w[
-        .rb .txt .md .html .css .js .py .java .php .go .swift .ts .scala .c .cpp .csharp .h .lua .pl .rs .kt
-        .d .r .m .sh .bash .bat .json .yaml .xml .scss .tsv .vb .ps1 .clj .elixir .f# .vhdl .verilog
-        .ada .ml .lisp .prolog .tcl .rexx .awk .sed .coffee .groovy .dart .haxe .zig .nim .crystal .reason .ocaml
-        .forth .v .xhtml .julia .racket .scheme .rust .graphql
-      ].include? File.extname(path)
-    end
-
-    def scan_file(path, result)
-      File.foreach(path).with_index do |line, line_number|
-        words = line.split(/[^a-zA-Z0-9']+/)
-        check_words = words.map { |word| split_function_name(word) }.flatten
-        check_words.each do |word|
-          clean_word = word.gsub(/^[^\w]+|[^\w]+$/, '')
-          char_index = line.index(clean_word)
-          check_word(clean_word, path, line_number, char_index, result)
-        end
-      end
-    end
-
-    def check_word(word, file, line_num, char_index, result)
-      return unless typos.key?(word.downcase)
-
-      corrected_word = corrected_word(word, typos[word.downcase])
-      typo_details = { incorrect_word: word, correct_word: corrected_word }
-      typo_path = "#{file}:#{line_num + 1}:#{char_index + 1}"
-      path = file.sub(%r{^./}, '')
-
-      result[path] ||= {}
-      result[path][:typos] ||= []
-      line_entry = result[path][:typos].find { |entry| entry[:line] == line_num + 1 }
-
-      if line_entry
-        line_entry[:typos] << typo_details
-      else
-        result[path][:typos] << { line: line_num + 1, typos: [typo_details] }
-      end
-
-      stdout(typo_path, word, corrected_word) if stdoutput
-    end
-
-    def split_function_name(name)
-      name.gsub(/([a-z])([A-Z])/, '\1 \2').split(/[\s_]+/)
-    end
-
-    def corrected_word(word, typo_correct_word)
-      if word == word.capitalize
-        typo_correct_word.capitalize
-      elsif word == word.upcase
-        typo_correct_word.upcase
-      else
-        typo_correct_word
-      end
-    end
-
-    def stdout(typo_path, word, corrected_word)
-      puts "Typo found in #{colorize_light_blue(typo_path)}: " \
-            "#{colorize_red(word)} -> #{colorize_green(corrected_word)}"
-    end
-
-    def colorize_red(text)
-      "\e[31m#{text}\e[0m"
-    end
-
-    def colorize_green(text)
-      "\e[32m#{text}\e[0m"
-    end
-
-    def colorize_light_blue(text)
-      "\e[94m#{text}\e[0m"
+      repository_scanner = RepositoryScanner.new(repo_path, @configuration)
+      repository_scanner.scan
     end
   end
 end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: typo_checker
 version: !ruby/object:Gem::Version
-  version: 0.1.5
+  version: 0.1.6
 platform: ruby
 authors:
 - datpmt
 bindir: bin
 cert_chain: []
-date: 2025-01-06 00:00:00.000000000 Z
+date: 2025-01-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: thor
@@ -39,6 +39,10 @@ files:
 - lib/data/typos.csv
 - lib/typo_checker.rb
 - lib/typo_checker/cli.rb
+- lib/typo_checker/configuration.rb
+- lib/typo_checker/file_scanner.rb
+- lib/typo_checker/repository_scanner.rb
+- lib/typo_checker/typos_loader.rb
 - lib/typo_checker/version.rb
 homepage: https://rubygems.org/gems/typo_checker
 licenses: