refactor Lexer to be static class function

lib/liquid/lexer.rb

@@ -25,38 +25,37 @@ module Liquid
     COMPARISON_OPERATOR   = /==|!=|<>|<=?|>=?|contains(?=\s)/
     WHITESPACE_OR_NOTHING = /\s*/
 
-    def initialize(input)
-      @ss = StringScanner.new(input)
-    end
+    class << self
+      def tokenize(input)
+        ss = StringScanner.new(input)
+        output = []
 
-    def tokenize
-      @output = []
-
-      until @ss.eos?
-        @ss.skip(WHITESPACE_OR_NOTHING)
-        break if @ss.eos?
-        tok      = if (t = @ss.scan(COMPARISON_OPERATOR))
+        until ss.eos?
+          ss.skip(WHITESPACE_OR_NOTHING)
+          break if ss.eos?
+          tok      = if (t = ss.scan(COMPARISON_OPERATOR))
             [:comparison, t]
-        elsif (t = @ss.scan(STRING_LITERAL))
+          elsif (t = ss.scan(STRING_LITERAL))
             [:string, t]
-        elsif (t = @ss.scan(NUMBER_LITERAL))
+          elsif (t = ss.scan(NUMBER_LITERAL))
             [:number, t]
-        elsif (t = @ss.scan(IDENTIFIER))
+          elsif (t = ss.scan(IDENTIFIER))
             [:id, t]
-        elsif (t = @ss.scan(DOTDOT))
+          elsif (t = ss.scan(DOTDOT))
             [:dotdot, t]
           else
-          c     = @ss.getch
+            c     = ss.getch
             if (s = SPECIALS[c])
               [s, c]
             else
               raise SyntaxError, "Unexpected character #{c}"
             end
           end
-        @output << tok
+          output << tok
         end
 
-      @output << [:end_of_string]
+        output << [:end_of_string]
+      end
     end
   end
 
@@ -157,14 +156,11 @@ module Liquid
       table.freeze
     end
 
-    def initialize(input)
-      @input = input
-    end
-
     # rubocop:disable Metrics/BlockNesting
-    def tokenize
-      ss = StringScannerPool.pop(@input)
-      @output = []
+    class << self
+      def tokenize(input)
+        ss = StringScannerPool.pop(input)
+        output = []
 
         until ss.eos?
           ss.skip(WHITESPACE_OR_NOTHING)
@@ -179,22 +175,22 @@ module Liquid
             # Special case for ".."
             if special == DOT && ss.peek_byte == DOT_ORD
               ss.scan_byte
-            @output << DOTDOT
+              output << DOTDOT
             elsif special == DASH
               # Special case for negative numbers
               if (peeked_byte = ss.peek_byte) && NUMBER_TABLE[peeked_byte]
                 ss.pos -= 1
-              @output << [:number, ss.scan(NUMBER_LITERAL)]
+                output << [:number, ss.scan(NUMBER_LITERAL)]
               else
-              @output << special
+                output << special
               end
             else
-            @output << special
+              output << special
             end
           elsif (sub_table = TWO_CHARS_COMPARISON_JUMP_TABLE[peeked])
             ss.scan_byte
             if (peeked_byte = ss.peek_byte) && (found = sub_table[peeked_byte])
-            @output << found
+              output << found
               ss.scan_byte
             else
               raise_syntax_error(start_pos, ss)
@@ -202,17 +198,17 @@ module Liquid
           elsif (sub_table = COMPARISON_JUMP_TABLE[peeked])
             ss.scan_byte
             if (peeked_byte = ss.peek_byte) && (found = sub_table[peeked_byte])
-            @output << found
+              output << found
               ss.scan_byte
             else
-            @output << SINGLE_COMPARISON_TOKENS[peeked]
+              output << SINGLE_COMPARISON_TOKENS[peeked]
             end
           else
             type, pattern = NEXT_MATCHER_JUMP_TABLE[peeked]
 
             if type && (t = ss.scan(pattern))
               # Special case for "contains"
-            @output << if type == :id && t == "contains" && @output.last&.first != :dot
+              output << if type == :id && t == "contains" && output.last&.first != :dot
                 COMPARISON_CONTAINS
               else
                 [type, t]
@@ -223,8 +219,7 @@ module Liquid
           end
         end
         # rubocop:enable Metrics/BlockNesting
-
-      @output << EOS
+        output << EOS
       ensure
         StringScannerPool.release(ss)
       end
@@ -235,6 +230,7 @@ module Liquid
         raise SyntaxError, "Unexpected character #{ss.getch}"
       end
     end
+  end
 
   # Remove this once we can depend on strscan >= 3.1.1
   Lexer = StringScanner.instance_methods.include?(:scan_byte) ? Lexer2 : Lexer1

lib/liquid/parser.rb

@@ -3,8 +3,7 @@
 module Liquid
   class Parser
     def initialize(input)
-      l       = Lexer.new(input)
-      @tokens = l.tokenize
+      @tokens = Lexer.tokenize(input)
       @p      = 0 # pointer to current location
     end
 

lib/liquid/string_scanner_pool.rb

@@ -1,8 +1,10 @@
+# frozen_string_literal: true
+
 module Liquid
   class StringScannerPool
     class << self
       def pop(input)
-        @ss_pool ||= [StringScanner.new("")] * 5
+        @ss_pool ||= 5.times.each_with_object([]) { |_i, arr| arr << StringScanner.new("") }
 
         if @ss_pool.empty?
           StringScanner.new(input)
@@ -14,7 +16,6 @@ module Liquid
       end
 
       def release(ss)
-        binding.irb if ss.nil?
         @ss_pool ||= []
         @ss_pool << ss
       end

test/unit/lexer_unit_test.rb

@@ -134,6 +134,6 @@ class LexerUnitTest < Minitest::Test
   private
 
   def tokenize(input)
-    Lexer.new(input).tokenize
+    Lexer.tokenize(input)
   end
 end