From a3a7b5bd9a4039864569885824960680dc5e4ce1 Mon Sep 17 00:00:00 2001
From: Roberto Alsina <roberto.alsina@gmail.com>
Date: Thu, 15 Aug 2024 21:10:25 -0300
Subject: [PATCH] Many cleanups

---
 src/formatters/html.cr | 23 +++++++--------
 src/lexer.cr           |  4 +--
 src/rules.cr           | 63 +++++++++++++++++++++---------------------
 3 files changed, 46 insertions(+), 44 deletions(-)

diff --git a/src/formatters/html.cr b/src/formatters/html.cr
index 715d793..b6037cc 100644
--- a/src/formatters/html.cr
+++ b/src/formatters/html.cr
@@ -68,8 +68,7 @@ module Tartrazine
           line_id = linkable_line_numbers? ? "id=\"#{line_number_id_prefix}#{i + 1}\"" : ""
           outp << "<span #{line_id} #{line_class} style=\"user-select: none;\">#{line_label} </span>"
           line.each do |token|
-            fragment = "<span class=\"#{get_css_class(token[:type])}\">#{HTML.escape(token[:value])}</span>"
-            outp << fragment
+            outp << "<span class=\"#{get_css_class(token[:type])}\">#{HTML.escape(token[:value])}</span>"
           end
         end
         outp << "</code></pre>"
@@ -105,15 +104,17 @@ module Tartrazine
 
     # Given a token type, return the CSS class to use.
     def get_css_class(token : String) : String
-      return class_prefix + Abbreviations[token] if theme.styles.has_key?(token)
-
-      # Themes don't contain information for each specific
-      # token type. However, they may contain information
-      # for a parent style. Worst case, we go to the root
-      # (Background) style.
-      class_prefix + Abbreviations[theme.style_parents(token).reverse.find { |parent|
-        theme.styles.has_key?(parent)
-      }]
+      if !theme.styles.has_key? token
+        # Themes don't contain information for each specific
+        # token type. However, they may contain information
+        # for a parent style. Worst case, we go to the root
+        # (Background) style.
+        parent = theme.style_parents(token).reverse.find { |dad|
+          theme.styles.has_key?(dad)
+        }
+        theme.styles[token] = theme.styles[parent]
+      end
+      class_prefix + Abbreviations[token]
     end
 
     # Is this line in the highlighted ranges?
diff --git a/src/lexer.cr b/src/lexer.cr
index 20f074a..1f8c924 100644
--- a/src/lexer.cr
+++ b/src/lexer.cr
@@ -225,9 +225,9 @@ module Tartrazine
   # A Lexer state. A state has a name and a list of rules.
   # The state machine has a state stack containing references
   # to states to decide which rules to apply.
-  class State
+  struct State
     property name : String = ""
-    property rules = [] of Rule
+    property rules = [] of BaseRule
 
     def +(other : State)
       new_state = State.new
diff --git a/src/rules.cr b/src/rules.cr
index 632eec1..4de1d61 100644
--- a/src/rules.cr
+++ b/src/rules.cr
@@ -15,30 +15,12 @@ module Tartrazine
   alias Match = BytesRegex::Match
   alias MatchData = Array(Match)
 
-  class Rule
-    property pattern : Regex = Regex.new ""
+  abstract struct BaseRule
+    abstract def match(text : Bytes, pos, lexer) : Tuple(Bool, Int32, Array(Token))
+    abstract def initialize(node : XML::Node)
+
     property actions : Array(Action) = [] of Action
 
-    def match(text : Bytes, pos, lexer) : Tuple(Bool, Int32, Array(Token))
-      match = pattern.match(text, pos)
-      # We don't match if the match doesn't move the cursor
-      # because that causes infinite loops
-      return false, pos, [] of Token if match.empty? || match[0].size == 0
-      tokens = [] of Token
-      actions.each do |action|
-        tokens += action.emit(match, lexer)
-      end
-      return true, pos + match[0].size, tokens
-    end
-
-    def initialize(node : XML::Node, multiline, dotall, ignorecase)
-      @xml = node.to_s
-      pattern = node["pattern"]
-      pattern = "(?m)" + pattern if multiline
-      @pattern = Regex.new(pattern, multiline, dotall, ignorecase, true)
-      add_actions(node)
-    end
-
     def add_actions(node : XML::Node)
       node.children.each do |child|
         next unless child.element?
@@ -47,9 +29,32 @@ module Tartrazine
     end
   end
 
+  struct Rule < BaseRule
+    property pattern : Regex = Regex.new ""
+    property actions : Array(Action) = [] of Action
+
+    def match(text : Bytes, pos, lexer) : Tuple(Bool, Int32, Array(Token))
+      match = pattern.match(text, pos)
+
+      # No match
+      return false, pos, [] of Token if match.size == 0
+      return true, pos + match[0].size, actions.flat_map { |action| action.emit(match, lexer) }
+    end
+
+    def initialize(node : XML::Node)
+    end
+
+    def initialize(node : XML::Node, multiline, dotall, ignorecase)
+      pattern = node["pattern"]
+      pattern = "(?m)" + pattern if multiline
+      @pattern = Regex.new(pattern, multiline, dotall, ignorecase, true)
+      add_actions(node)
+    end
+  end
+
   # This rule includes another state. If any of the rules of the
   # included state matches, this rule matches.
-  class IncludeStateRule < Rule
+  struct IncludeStateRule < BaseRule
     property state : String = ""
 
     def match(text, pos, lexer) : Tuple(Bool, Int32, Array(Token))
@@ -62,7 +67,6 @@ module Tartrazine
     end
 
     def initialize(node : XML::Node)
-      @xml = node.to_s
       include_node = node.children.find { |child|
         child.name == "include"
       }
@@ -72,17 +76,14 @@ module Tartrazine
   end
 
   # This rule always matches, unconditionally
-  class UnconditionalRule < Rule
+  struct UnconditionalRule < BaseRule
+    NO_MATCH = [] of Match
+
     def match(text, pos, lexer) : Tuple(Bool, Int32, Array(Token))
-      tokens = [] of Token
-      actions.each do |action|
-        tokens += action.emit([] of Match, lexer)
-      end
-      return true, pos, tokens
+      return true, pos, actions.flat_map { |action| action.emit(NO_MATCH, lexer) }
     end
 
     def initialize(node : XML::Node)
-      @xml = node.to_s
       add_actions(node)
     end
   end