classifier 1.4.4 → 2.1.0

data/lib/classifier/storage/base.rb

@@ -0,0 +1,50 @@
+# rbs_inline: enabled
+
+# Author::    Lucas Carlson  (mailto:lucas@rufy.com)
+# Copyright:: Copyright (c) 2005 Lucas Carlson
+# License::   LGPL
+
+module Classifier
+  module Storage
+    # Abstract base class for storage backends.
+    # Implement this protocol to create custom storage (Redis, PostgreSQL, etc.)
+    #
+    # Example:
+    #   class RedisStorage < Classifier::Storage::Base
+    #     def initialize(redis:, key:)
+    #       @redis, @key = redis, key
+    #     end
+    #
+    #     def write(data) = @redis.set(@key, data)
+    #     def read = @redis.get(@key)
+    #     def delete = @redis.del(@key)
+    #     def exists? = @redis.exists?(@key)
+    #   end
+    #
+    class Base
+      # Save classifier data
+      # @rbs (String) -> void
+      def write(data)
+        raise NotImplementedError, "#{self.class}#write must be implemented"
+      end
+
+      # Load classifier data
+      # @rbs () -> String?
+      def read
+        raise NotImplementedError, "#{self.class}#read must be implemented"
+      end
+
+      # Delete classifier data
+      # @rbs () -> void
+      def delete
+        raise NotImplementedError, "#{self.class}#delete must be implemented"
+      end
+
+      # Check if data exists
+      # @rbs () -> bool
+      def exists?
+        raise NotImplementedError, "#{self.class}#exists? must be implemented"
+      end
+    end
+  end
+end

data/lib/classifier/storage/file.rb

@@ -0,0 +1,51 @@
+# rbs_inline: enabled
+
+# Author::    Lucas Carlson  (mailto:lucas@rufy.com)
+# Copyright:: Copyright (c) 2005 Lucas Carlson
+# License::   LGPL
+
+require_relative 'base'
+
+module Classifier
+  module Storage
+    # File-based storage backend.
+    #
+    # Example:
+    #   bayes = Classifier::Bayes.new('Spam', 'Ham')
+    #   bayes.storage = Classifier::Storage::File.new(path: "/var/models/spam.json")
+    #   bayes.train_spam("Buy now!")
+    #   bayes.save
+    #
+    class File < Base
+      # @rbs @path: String
+
+      attr_reader :path
+
+      # @rbs (path: String) -> void
+      def initialize(path:)
+        super()
+        @path = path
+      end
+
+      # @rbs (String) -> Integer
+      def write(data)
+        ::File.write(@path, data)
+      end
+
+      # @rbs () -> String?
+      def read
+        exists? ? ::File.read(@path) : nil
+      end
+
+      # @rbs () -> void
+      def delete
+        ::File.delete(@path) if exists?
+      end
+
+      # @rbs () -> bool
+      def exists?
+        ::File.exist?(@path)
+      end
+    end
+  end
+end

data/lib/classifier/storage/memory.rb

@@ -0,0 +1,49 @@
+# rbs_inline: enabled
+
+# Author::    Lucas Carlson  (mailto:lucas@rufy.com)
+# Copyright:: Copyright (c) 2005 Lucas Carlson
+# License::   LGPL
+
+require_relative 'base'
+
+module Classifier
+  module Storage
+    # In-memory storage for testing and ephemeral use.
+    #
+    # Example:
+    #   bayes = Classifier::Bayes.new('Spam', 'Ham')
+    #   bayes.storage = Classifier::Storage::Memory.new
+    #   bayes.train_spam("Buy now!")
+    #   bayes.save
+    #
+    class Memory < Base
+      # @rbs @data: String?
+
+      # @rbs () -> void
+      def initialize
+        super
+        @data = nil
+      end
+
+      # @rbs (String) -> String
+      def write(data)
+        @data = data
+      end
+
+      # @rbs () -> String?
+      def read
+        @data
+      end
+
+      # @rbs () -> void
+      def delete
+        @data = nil
+      end
+
+      # @rbs () -> bool
+      def exists?
+        !@data.nil?
+      end
+    end
+  end
+end

data/lib/classifier/storage.rb

@@ -0,0 +1,9 @@
+# rbs_inline: enabled
+
+# Author::    Lucas Carlson  (mailto:lucas@rufy.com)
+# Copyright:: Copyright (c) 2005 Lucas Carlson
+# License::   LGPL
+
+require_relative 'storage/base'
+require_relative 'storage/memory'
+require_relative 'storage/file'

data/lib/classifier.rb

@@ -25,6 +25,8 @@
 # License::   LGPL
 
 require 'rubygems'
+require 'classifier/errors'
+require 'classifier/storage'
 require 'classifier/extensions/string'
 require 'classifier/extensions/vector'
 require 'classifier/bayes'

data/sig/vendor/fast_stemmer.rbs

@@ -0,0 +1,9 @@
+# Type stubs for fast-stemmer gem and classifier extensions
+class String
+  def stem: () -> String
+  def prepare_category_name: () -> Symbol
+end
+
+class Symbol
+  def prepare_category_name: () -> Symbol
+end

data/sig/vendor/gsl.rbs

@@ -0,0 +1,27 @@
+# Type stubs for optional GSL gem
+module GSL
+  class Vector
+    def self.alloc: (untyped) -> Vector
+    def to_a: () -> Array[Float]
+    def normalize: () -> Vector
+    def sum: () -> Float
+    def each: () { (Float) -> void } -> void
+    def []: (Integer) -> Float
+    def []=: (Integer, Float) -> Float
+    def size: () -> Integer
+    def row: () -> Vector
+    def col: () -> Vector
+    def *: (untyped) -> untyped
+    def collect: () { (Float) -> Float } -> Vector
+  end
+
+  class Matrix
+    def self.alloc: (*untyped) -> Matrix
+    def self.diag: (untyped) -> Matrix
+    def trans: () -> Matrix
+    def *: (untyped) -> Matrix
+    def size: () -> [Integer, Integer]
+    def column: (Integer) -> Vector
+    def SV_decomp: () -> [Matrix, Matrix, Vector]
+  end
+end

data/sig/vendor/json.rbs

@@ -0,0 +1,4 @@
+module JSON
+  def self.parse: (String source, ?symbolize_names: bool) -> untyped
+  def self.generate: (untyped obj) -> String
+end

data/sig/vendor/matrix.rbs

@@ -0,0 +1,26 @@
+# Type stubs for matrix gem
+class Vector[T]
+  EPSILON: Float
+
+  def self.[]: [T] (*T) -> Vector[T]
+  def size: () -> Integer
+  def []: (Integer) -> T
+  def magnitude: () -> Float
+  def normalize: () -> Vector[T]
+  def each: () { (T) -> void } -> void
+  def collect: [U] () { (T) -> U } -> Vector[U]
+  def to_a: () -> Array[T]
+  def *: (untyped) -> untyped
+end
+
+class Matrix[T]
+  def self.rows: [T] (Array[Array[T]]) -> Matrix[T]
+  def self.[]: [T] (*Array[T]) -> Matrix[T]
+  def self.diag: (untyped) -> Matrix[untyped]
+  def trans: () -> Matrix[T]
+  def *: (untyped) -> untyped
+  def row_size: () -> Integer
+  def column_size: () -> Integer
+  def column: (Integer) -> Vector[T]
+  def SV_decomp: () -> [Matrix[T], Matrix[T], untyped]
+end

data/sig/vendor/mutex_m.rbs

@@ -0,0 +1,16 @@
+# Type stubs for mutex_m gem
+module Mutex_m
+  def mu_initialize: () -> void
+  def mu_lock: () -> void
+  def mu_unlock: () -> void
+  def mu_synchronize: [T] () { () -> T } -> T
+  def mu_try_lock: () -> bool
+  def mu_locked?: () -> bool
+
+  # Aliases
+  alias lock mu_lock
+  alias unlock mu_unlock
+  alias synchronize mu_synchronize
+  alias try_lock mu_try_lock
+  alias locked? mu_locked?
+end

data/test/test_helper.rb

@@ -1,5 +1,17 @@
-$:.unshift(File.dirname(__FILE__) + '/../lib')
+require 'simplecov'
+SimpleCov.start do
+  add_filter '/test/'
+  add_filter '/vendor/'
+  add_group 'Bayes', 'lib/classifier/bayes.rb'
+  add_group 'LSI', 'lib/classifier/lsi'
+  add_group 'Extensions', 'lib/classifier/extensions'
+  enable_coverage :branch
+end
+
+$LOAD_PATH.unshift("#{File.dirname(__FILE__)}/../lib")
 
 require 'minitest'
 require 'minitest/autorun'
+require 'tmpdir'
+require 'json'
 require 'classifier'

metadata

@@ -1,14 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: classifier
 version: !ruby/object:Gem::Version
-  version: 1.4.4
+  version: 2.1.0
 platform: ruby
 authors:
 - Lucas Carlson
-autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-07-31 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: fast-stemmer
@@ -52,6 +51,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: matrix
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: minitest
   requirement: !ruby/object:Gem::Requirement
@@ -66,6 +79,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: rbs-inline
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rdoc
   requirement: !ruby/object:Gem::Requirement
@@ -80,31 +107,66 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: rake-compiler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 description: A general classifier module to allow Bayesian and other types of classifications.
 email: lucas@rufy.com
 executables: []
-extensions: []
+extensions:
+- ext/classifier/extconf.rb
 extra_rdoc_files: []
 files:
+- CLAUDE.md
 - LICENSE
+- README.md
 - bin/bayes.rb
 - bin/summarize.rb
+- ext/classifier/classifier_ext.c
+- ext/classifier/extconf.rb
+- ext/classifier/linalg.h
+- ext/classifier/matrix.c
+- ext/classifier/svd.c
+- ext/classifier/vector.c
 - lib/classifier.rb
 - lib/classifier/bayes.rb
+- lib/classifier/errors.rb
 - lib/classifier/extensions/string.rb
 - lib/classifier/extensions/vector.rb
-- lib/classifier/extensions/vector_serialize.rb
 - lib/classifier/extensions/word_hash.rb
 - lib/classifier/lsi.rb
 - lib/classifier/lsi/content_node.rb
 - lib/classifier/lsi/summary.rb
 - lib/classifier/lsi/word_list.rb
+- lib/classifier/storage.rb
+- lib/classifier/storage/base.rb
+- lib/classifier/storage/file.rb
+- lib/classifier/storage/memory.rb
+- sig/vendor/fast_stemmer.rbs
+- sig/vendor/gsl.rbs
+- sig/vendor/json.rbs
+- sig/vendor/matrix.rbs
+- sig/vendor/mutex_m.rbs
 - test/test_helper.rb
-homepage: https://github.com/cardmagic/classifier
+homepage: https://rubyclassifier.com
 licenses:
 - LGPL
-metadata: {}
-post_install_message:
+metadata:
+  documentation_uri: https://rubyclassifier.com/docs
+  source_code_uri: https://github.com/cardmagic/classifier
+  bug_tracker_uri: https://github.com/cardmagic/classifier/issues
+  changelog_uri: https://github.com/cardmagic/classifier/releases
 rdoc_options: []
 require_paths:
 - lib
@@ -119,8 +181,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.9
-signing_key:
+rubygems_version: 4.0.3
 specification_version: 4
 summary: A general classifier module to allow Bayesian and other types of classifications.
 test_files: []

data/lib/classifier/extensions/vector_serialize.rb

@@ -1,18 +0,0 @@
-module GSL
-  class Vector
-    def _dump(_v)
-      Marshal.dump(to_a)
-    end
-
-    def self._load(arr)
-      arry = Marshal.load(arr)
-      GSL::Vector.alloc(arry)
-    end
-  end
-
-  class Matrix
-    class << self
-      alias diag diagonal
-    end
-  end
-end