textstat 1.0.0 → 1.0.1

data/lib/textstat/basic_stats.rb

@@ -14,6 +14,33 @@ module TextStat
   #   TextStat.syllable_count(text)      # => 6
   #   TextStat.sentence_count(text)      # => 2
   module BasicStats
+    # Frozen regex constants to avoid recompilation overhead
+    NON_ALPHA_REGEX = /[^a-zA-Z\s]/.freeze
+    SENTENCE_BOUNDARY_REGEX = /[.?!]['\\)\]]*[ |\n][A-Z]/.freeze
+
+    # Cache for Text::Hyphen instances to avoid recreating them for each call
+    @hyphenator_cache = {}
+
+    class << self
+      attr_accessor :hyphenator_cache
+
+      # Get or create a cached Text::Hyphen instance for the specified language
+      #
+      # @param language [String] language code
+      # @return [Text::Hyphen] cached hyphenator instance
+      # @private
+      def get_hyphenator(language)
+        @hyphenator_cache[language] ||= Text::Hyphen.new(language: language, left: 0, right: 0)
+      end
+
+      # Clear all cached hyphenators
+      #
+      # @return [Hash] empty cache
+      # @private
+      def clear_hyphenator_cache
+        @hyphenator_cache.clear
+      end
+    end
     # Count characters in text
     #
     # @param text [String] the text to analyze
@@ -36,7 +63,7 @@ module TextStat
     #   TextStat.lexicon_count("Hello, world!")       # => 2
     #   TextStat.lexicon_count("Hello, world!", false) # => 2
     def lexicon_count(text, remove_punctuation = true)
-      text = text.gsub(/[^a-zA-Z\s]/, '').squeeze(' ') if remove_punctuation
+      text = text.gsub(NON_ALPHA_REGEX, '').squeeze(' ') if remove_punctuation
       text.split.count
     end
 
@@ -44,7 +71,7 @@ module TextStat
     #
     # Uses the text-hyphen library for accurate syllable counting across
     # different languages. Supports 22 languages including English, Spanish,
-    # French, German, and more.
+    # French, German, and more. Hyphenator instances are cached for performance.
     #
     # @param text [String] the text to analyze
     # @param language [String] language code for hyphenation dictionary
@@ -58,11 +85,11 @@ module TextStat
       return 0 if text.empty?
 
       text = text.downcase
-      text.gsub(/[^a-zA-Z\s]/, '').squeeze(' ')
-      dictionary = Text::Hyphen.new(language: language, left: 0, right: 0)
+      text.gsub(NON_ALPHA_REGEX, '').squeeze(' ') # NOTE: not assigned back (matches original behavior)
+      hyphenator = BasicStats.get_hyphenator(language)
       count = 0
       text.split.each do |word|
-        word_hyphenated = dictionary.visualise(word)
+        word_hyphenated = hyphenator.visualise(word)
         count += word_hyphenated.count('-') + 1
       end
       count
@@ -79,7 +106,7 @@ module TextStat
     #   TextStat.sentence_count("Hello world! How are you?")  # => 2
     #   TextStat.sentence_count("Dr. Smith went to the U.S.A.") # => 1
     def sentence_count(text)
-      text.scan(/[\.\?!][\'\\)\]]*[ |\n][A-Z]/).map(&:strip).count + 1
+      text.scan(SENTENCE_BOUNDARY_REGEX).map(&:strip).count + 1
     end
 
     # Calculate average sentence length
@@ -139,16 +166,30 @@ module TextStat
 
     # Count polysyllabic words (3+ syllables)
     #
+    # Optimized to count syllables for all words in one pass using a cached hyphenator.
+    #
     # @param text [String] the text to analyze
     # @param language [String] language code for hyphenation dictionary
     # @return [Integer] number of polysyllabic words
     # @example
     #   TextStat.polysyllab_count("beautiful complicated")  # => 2
     def polysyllab_count(text, language = 'en_us')
+      return 0 if text.empty?
+
+      # Clean and split text once
+      cleaned_text = text.downcase.gsub(NON_ALPHA_REGEX, '').squeeze(' ')
+      words = cleaned_text.split
+      return 0 if words.empty?
+
+      # Use cached hyphenator for better performance
+      hyphenator = BasicStats.get_hyphenator(language)
       count = 0
-      text.split.each do |word|
-        w = syllable_count(word, language)
-        count += 1 if w >= 3
+      words.each do |word|
+        next if word.empty?
+
+        word_hyphenated = hyphenator.visualise(word)
+        syllables = word_hyphenated.count('-') + 1
+        count += 1 if syllables >= 3
       end
       count
     end

data/lib/textstat/dictionary_manager.rb

@@ -45,7 +45,8 @@ module TextStat
       #
       # Loads a language-specific dictionary from disk and caches it in memory
       # for subsequent calls. This provides significant performance improvements
-      # for repeated operations.
+      # for repeated operations. Uses optimized file reading with streaming for
+      # better performance and memory efficiency.
       #
       # @param language [String] language code (e.g., 'en_us', 'es', 'fr')
       # @return [Set] set of easy words for the specified language
@@ -63,8 +64,9 @@ module TextStat
         easy_words = Set.new
 
         if File.exist?(dictionary_file)
-          File.read(dictionary_file).each_line do |line|
-            easy_words << line.chomp
+          # Use foreach for streaming - efficient and memory-friendly for large files
+          File.foreach(dictionary_file, chomp: true) do |line|
+            easy_words << line
           end
         end
 
@@ -123,7 +125,7 @@ module TextStat
     # 1. Not being in the language's easy words dictionary
     # 2. Having more than one syllable
     #
-    # This method uses the cached dictionary system for optimal performance.
+    # This method uses the cached dictionary and hyphenator systems for optimal performance.
     #
     # @param text [String] the text to analyze
     # @param language [String] language code for dictionary selection
@@ -142,12 +144,22 @@ module TextStat
     def difficult_words(text, language = 'en_us', return_words = false)
       easy_words = DictionaryManager.load_dictionary(language)
 
+      # Clean and split text once
       text_list = text.downcase.gsub(/[^0-9a-z ]/i, '').split
+      return return_words ? Set.new : 0 if text_list.empty?
+
+      # Get cached hyphenator for syllable counting
+      hyphenator = BasicStats.get_hyphenator(language)
       diff_words_set = Set.new
-      text_list.each do |value|
-        next if easy_words.include? value
 
-        diff_words_set.add(value) if syllable_count(value, language) > 1
+      # Process each word once
+      text_list.each do |word|
+        next if easy_words.include?(word)
+
+        # Count syllables inline using cached hyphenator
+        word_hyphenated = hyphenator.visualise(word)
+        syllables = word_hyphenated.count('-') + 1
+        diff_words_set.add(word) if syllables > 1
       end
 
       return_words ? diff_words_set : diff_words_set.length

data/lib/textstat/readability_formulas.rb

@@ -344,11 +344,11 @@ module TextStat
     end
 
     # Calculate consensus grade from all collected grades
+    # Uses Ruby's built-in tally method for better performance
+    # Note: Requires Ruby 2.7+, which matches the gem's minimum requirement
     def calculate_consensus_grade(grade)
-      require_relative '../counter'
-      counter = Counter.new(grade)
-      most_common = counter.most_common(1)
-      most_common[0][0]
+      tallied = grade.tally
+      tallied.max_by { |_grade, count| count }[0]
     end
 
     # Format grade output based on float_output parameter

data/lib/textstat/version.rb

@@ -8,15 +8,14 @@
 module TextStat
   # Current version of the TextStat gem
   #
-  # Version 1.0.0 represents the first stable release with:
-  # - 36x performance improvement through dictionary caching
-  # - Modular architecture with separate modules for different functionality
-  # - Comprehensive test coverage (199 tests)
-  # - Support for 22 languages
-  # - Full backward compatibility with 0.1.x series
+  # Version 1.0.1 includes performance optimizations and bug fixes
+  # - Optimized dictionary caching with lazy loading
+  # - Improved text_standard performance
+  # - Reduced memory allocations
+  # - Code quality improvements (Rubocop compliance)
   #
   # @return [String] current version string
   # @example
-  #   TextStat::VERSION  # => \"1.0.0\"
-  VERSION = '1.0.0'.freeze
+  #   TextStat::VERSION  # => "1.0.1"
+  VERSION = '1.0.1'.freeze
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: textstat
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.0.1
 platform: ruby
 authors:
 - Jakub Polak
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2025-07-08 00:00:00.000000000 Z
+date: 2025-12-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: text-hyphen
@@ -16,14 +16,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.4.1
+        version: 1.5.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.4.1
+        version: 1.5.0
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -142,14 +142,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.31'
+        version: '3.8'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.31'
+        version: '3.8'
 - !ruby/object:Gem::Dependency
   name: rubocop-thread_safety
   requirement: !ruby/object:Gem::Requirement
@@ -240,14 +240,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '6.2'
+        version: '7.1'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '6.2'
+        version: '7.1'
 description:
 email:
 - jakub.polak.vz@gmail.com
@@ -255,7 +255,6 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- lib/counter.rb
 - lib/dictionaries/ca.txt
 - lib/dictionaries/cs.txt
 - lib/dictionaries/da.txt
@@ -264,8 +263,10 @@ files:
 - lib/dictionaries/en_us.txt
 - lib/dictionaries/es.txt
 - lib/dictionaries/et.txt
+- lib/dictionaries/eu.txt
 - lib/dictionaries/fi.txt
 - lib/dictionaries/fr.txt
+- lib/dictionaries/ga.txt
 - lib/dictionaries/hr.txt
 - lib/dictionaries/hu.txt
 - lib/dictionaries/id.txt

data/lib/counter.rb

@@ -1,37 +0,0 @@
-class Counter < Hash
-  def initialize(other = nil)
-    super(0)
-    other.each { |e| self[e] += 1 } if other.is_a? Array
-    other.each { |k, v| self[k] = v } if other.is_a? Hash
-    other.each_char { |e| self[e] += 1 } if other.is_a? String
-  end
-
-  def +(other)
-    raise TypeError, "cannot add #{other.class} to a Counter" unless other.is_a? Counter
-
-    result = Counter.new(self)
-    other.each { |k, v| result[k] += v }
-    result
-  end
-
-  def -(other)
-    raise TypeError, "cannot subtract #{other.class} to a Counter" unless other.is_a? Counter
-
-    result = Counter.new(self)
-    other.each { |k, v| result[k] -= v }
-    result
-  end
-
-  def most_common(n = nil)
-    s = sort_by { |_k, v| -v }
-    n ? s.take(n) : s
-  end
-
-  def to_s
-    "Counter(#{super})"
-  end
-
-  def inspect
-    to_s
-  end
-end