From 58e8dac03848fe5d2406b4f265d5969b0d7b1654 Mon Sep 17 00:00:00 2001
From: Roberto Alsina <roberto.alsina@gmail.com>
Date: Thu, 15 Aug 2024 19:20:12 -0300
Subject: [PATCH] Make usingself MUCH cheaper, since it was called many times
 when parsing C

---
 src/actions.cr |  2 +-
 src/lexer.cr   | 13 +++++++++----
 2 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/src/actions.cr b/src/actions.cr
index 126fd47..6baf72b 100644
--- a/src/actions.cr
+++ b/src/actions.cr
@@ -109,7 +109,7 @@ module Tartrazine
       when "usingself"
         # Shunt to another copy of this lexer
         return [] of Token if match.empty?
-        new_lexer = Lexer.from_xml(lexer.xml)
+        new_lexer = lexer.copy
         new_lexer.tokenize(String.new(match[match_group].value), usingself: true)
       when "combined"
         # Combine two states into one anonymous state
diff --git a/src/lexer.cr b/src/lexer.cr
index b99c821..20f074a 100644
--- a/src/lexer.cr
+++ b/src/lexer.cr
@@ -56,10 +56,18 @@ module Tartrazine
       not_multiline:    false,
       ensure_nl:        false,
     }
-    property xml : String = ""
+    # property xml : String = ""
     property states = {} of String => State
     property state_stack = ["root"]
 
+    def copy : Lexer
+      new_lexer = Lexer.new
+      new_lexer.config = config
+      new_lexer.states = states
+      new_lexer.state_stack = state_stack[0..-1]
+      new_lexer
+    end
+
     # Turn the text into a list of tokens. The `usingself` parameter
     # is true when the lexer is being used to tokenize a string
     # from a larger text that is already being tokenized.
@@ -85,12 +93,10 @@ module Tartrazine
           if matched
             # Move position forward, save the tokens,
             # tokenize from the new position
-            # Log.trace { "MATCHED: #{rule.xml}" }
             pos = new_pos
             tokens += new_tokens
             break
           end
-          # Log.trace { "NOT MATCHED: #{rule.xml}" }
         end
         # If no rule matches, emit an error token
         unless matched
@@ -156,7 +162,6 @@ module Tartrazine
     # ameba:disable Metrics/CyclomaticComplexity
     def self.from_xml(xml : String) : Lexer
       l = Lexer.new
-      l.xml = xml
       lexer = XML.parse(xml).first_element_child
       if lexer
         config = lexer.children.find { |node|