kleene 0.7.0 → 0.9.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 674bbda22ddfbc6c4ec1624de621b96c24576cbe8aa656d228697e1d98549cdb
-  data.tar.gz: ddca6b95201b21359dd23c5d6b4d9591561e9045764ce90b470b6add1c4518b8
+  metadata.gz: 12f76babc39f4051cb6a1faf6dbcfbe03d3a52735c8fa2bd3b360b031ae9a0f8
+  data.tar.gz: c4bc2f26400e80aeca549fdba04c84ef863f1d04c047b885fbaa91668690a4cd
 SHA512:
-  metadata.gz: 9392d0b56aa48b8cef4f0337be625d6160d49c3fb0214b034f379a505ee3a142347e8bb5e62a82ad0cb982bb3ca00ad6f9b12f951e00cf48b0447a1b6fb78320
-  data.tar.gz: 1521365696f470bc249dac8aa77038bc9121ff60499dc9368aaf86224e64af14a06e092aef191bc9571d62d2dd63567a7051f4b07490e4f377eac8d24de83025
+  metadata.gz: 7501f2ad597e59333a792271333e981ffd1e20a4246b94a5f90d4063a311c32815b5c1413d2e9111a1d92da5a5d2eb6168f1c0e175a3a880b0ecf30530766897
+  data.tar.gz: e7acafe55b63f4d7f4a887af73490a05462be0394c575eedfa42048b454921c44282a17e7e336f2cf4f31831b7fea04fc3a04568b3d5cc2ede467f6e58b655d8

data/.rubocop.yml

@@ -0,0 +1,14 @@
+AllCops:
+  StyleGuideBaseURL: https://rubystyle.guide
+
+Layout/SpaceInsideBlockBraces:
+  SpaceBeforeBlockParameters: false
+
+Layout/LineLength:
+  Max: 160
+
+Style/AccessorGrouping:
+  EnforcedStyle: separated
+
+Style/Encoding:
+  Enabled: true

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    kleene (0.6.0)
+    kleene (0.8.0)
       activesupport (~> 7.1)
       regexp_parser (~> 2.8)
 
@@ -20,13 +20,13 @@ GEM
       tzinfo (~> 2.0)
     ast (2.4.2)
     backport (1.2.0)
-    base64 (0.1.1)
-    benchmark (0.2.1)
+    base64 (0.2.0)
+    benchmark (0.3.0)
     bigdecimal (3.1.4)
     concurrent-ruby (1.2.2)
     connection_pool (2.4.1)
     diff-lcs (1.5.0)
-    drb (2.1.1)
+    drb (2.2.0)
       ruby2_keywords
     e2mmap (0.1.0)
     i18n (1.14.1)
@@ -39,7 +39,7 @@ GEM
       kramdown (~> 2.0)
     language_server-protocol (3.17.0.3)
     minitest (5.20.0)
-    mutex_m (0.1.2)
+    mutex_m (0.2.0)
     nokogiri (1.15.4-x86_64-linux)
       racc (~> 1.4)
     parallel (1.23.0)

data/lib/kleene/kleene.rb

@@ -1,8 +1,8 @@
 # this is a port and extension of https://github.com/davidkellis/kleene/
 
-require_relative "./dsl"
-require_relative "./nfa"
-require_relative "./dfa"
+require_relative './dsl'
+require_relative './nfa'
+require_relative './dfa'
 
 module Kleene
   # The default alphabet consists of the following:
@@ -28,7 +28,6 @@ module Kleene
       State.new(final, true)
     end
 
-
     attr_reader :id # : Int32
     attr_accessor :final # : Bool
     attr_accessor :error # : Bool
@@ -76,13 +75,11 @@ module Kleene
     end
 
     def ==(other)
-      @string == other.string &&
-      @range == other.range
+      @string == other.string && @range == other.range
     end
 
     def eql?(other)
       self == other
     end
   end
-
 end

data/lib/kleene/naive_online_regex.rb

@@ -1,6 +1,5 @@
-require "set"
-require "stringio"
-require_relative "./kleene"
+require 'set'
+require_relative './kleene'
 
 module Kleene
   class NaiveOnlineRegex
@@ -12,52 +11,92 @@ module Kleene
     end
 
     def reset
-      @buffer = ""
-      @matches_per_regex = Hash.new   # Hash(Regexp, Set(MatchData))
+      @buffer = ''
+      @matches_per_regex = {} # Hash(Regexp, Set(OnlineMatch))
     end
 
     # #ingest(input) is the online-style matching interface
-    def ingest(input, debug = false) # : Set(OnlineMatch)
+    def ingest(input, _debug = false) # : Set(OnlineMatch)
       @buffer << input
       new_online_matches = Set.new
       @regexen.each do |regex|
         existing_matches_for_regex = (@matches_per_regex[regex] ||= Set.new)
-        scan_matches = @buffer.scan_matches(regex).to_set
-        new_matches = scan_matches - existing_matches_for_regex   # new_matches : Set(MatchData)
+        scan_matches = @buffer.scan_matches(regex)
+        scan_online_matches = scan_matches.map {|match_data| OnlineMatch.new(regex, match_data) }.to_set
+        new_matches = scan_online_matches - existing_matches_for_regex # new_matches : Set(OnlineMatch)
         existing_matches_for_regex.merge(new_matches)
-        new_online_matches.merge(new_matches.map {|match_data| OnlineMatch.new(regex, match_data) })
+        new_online_matches.merge(new_matches)
       end
       resize_buffer!
       new_online_matches
     end
 
-    def matches # Hash(Regexp, Set(MatchData))
+    def matches # Hash(Regexp, Set(OnlineMatch))
       @matches_per_regex
     end
 
-    def matches_for(regex) # Set(MatchData) | Nil
+    def matches_for(regex) # Set(OnlineMatch) | Nil
       @matches_per_regex[regex]
     end
 
     def resize_buffer!
-      if @buffer.size > @window_size
-        @buffer = @buffer[-@window_size..-1]
+      return unless @buffer.size > @window_size
+
+      number_of_chars_at_front_of_buffer_that_should_roll_off = @buffer.size - @window_size
+
+      @buffer = @buffer[-@window_size..-1]
+      drop_matches_that_have_rolled_off(number_of_chars_at_front_of_buffer_that_should_roll_off)
+    end
+
+    def drop_matches_that_have_rolled_off(number_of_chars_at_front_of_buffer_that_rolled_off)
+      @matches_per_regex.each do |regex, match_set|
+        match_set.reject! {|online_match| online_match.offsets.first < number_of_chars_at_front_of_buffer_that_rolled_off }
       end
     end
   end
 
   # A {Regexp, MatchData} pair
   class OnlineMatch
-    attr_reader :regex  # Regexp
-    attr_reader :match  # MatchData
+    # Regexp  # MatchData  # Array(Int) -> [start, end]    # excludes the end offset
+    attr_reader :regex
+    attr_reader :match
+    attr_reader :offsets # Regexp  # MatchData  # Array(Int) -> [start, end]    # excludes the end offset
+
     def initialize(regex, match)
-      @regex, @match = regex, match
+      @regex, @match, @offsets = regex, match
+      @offsets = match.offset(0)
     end
+
+    def identity
+      [@regex, @offsets, to_a]
+    end
+
+    def ==(other)
+      identity == other.identity
+    end
+
+    def eql?(other)
+      self == other
+    end
+
+    def hash
+      identity.hash
+    end
+
     def to_a
       @match.to_a
     end
+
     def to_h
-      {@regex => to_a}
+      { @regex => to_a, :offsets => @offsets }
+    end
+
+    def captures
+      @match.captures
+    end
+
+    def [](*args)
+      @match.method(:[]).call(*args)
     end
   end
 end

data/lib/kleene/patches.rb

@@ -12,14 +12,12 @@ module Enumerable
     ary = []
     each do |e|
       v = block.call(e)
-      unless v.nil?
-        ary << v
-      end
+      ary << v unless v.nil?
     end
     ary
   end
 
-  alias_method :includes?, :include?
+  alias includes? include?
 end
 
 class String

data/lib/kleene/version.rb

@@ -1,3 +1,3 @@
 module Kleene
-  VERSION = "0.7.0"
+  VERSION = "0.9.0"
 end

data/lib/kleene.rb

@@ -1,18 +1,18 @@
 # frozen_string_literal: true
 
-require "active_support"
-require "active_support/core_ext"
-require "regexp_parser"
-require_relative "kleene/version"
-require_relative "kleene/patches"
-require_relative "kleene/kleene"
-require_relative "kleene/dsl"
-require_relative "kleene/nfa"
-require_relative "kleene/dfa"
-require_relative "kleene/multi_match_dfa"
-require_relative "kleene/online_dfa"
-require_relative "kleene/naive_online_regex"
-require_relative "kleene/parser"
+require 'active_support'
+require 'active_support/core_ext'
+require 'regexp_parser'
+require_relative 'kleene/version'
+require_relative 'kleene/patches'
+require_relative 'kleene/kleene'
+require_relative 'kleene/dsl'
+require_relative 'kleene/nfa'
+require_relative 'kleene/dfa'
+require_relative 'kleene/multi_match_dfa'
+require_relative 'kleene/online_dfa'
+require_relative 'kleene/naive_online_regex'
+require_relative 'kleene/parser'
 
 module Kleene
   class Error < StandardError; end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: kleene
 version: !ruby/object:Gem::Version
-  version: 0.7.0
+  version: 0.9.0
 platform: ruby
 authors:
 - David Ellis
@@ -47,6 +47,7 @@ extensions: []
 extra_rdoc_files: []
 files:
 - ".rspec"
+- ".rubocop.yml"
 - Gemfile
 - Gemfile.lock
 - LICENSE