Merge branch 'main' of github.com:ralsina/tartrazine

spec/tartrazine_spec.cr

@@ -42,7 +42,6 @@ known_bad = {
   "#{__DIR__}/tests/mcfunction/selectors.txt",
   "#{__DIR__}/tests/php/anonymous_class.txt",
   "#{__DIR__}/tests/html/javascript_unclosed.txt",
-
 }
 
 # Tests that fail because of a limitation in PCRE2

src/formatters/html.cr

@@ -30,7 +30,7 @@ module Tartrazine
                    @standalone : Bool = false,
                    @surrounding_pre : Bool = true,
                    @wrap_long_lines : Bool = false,
-                   @weight_of_bold : Int32 = 600,)
+                   @weight_of_bold : Int32 = 600)
     end
 
     def format(text : String, lexer : Lexer) : String

src/lexer.cr

@@ -94,8 +94,13 @@ module Tartrazine
         end
         # If no rule matches, emit an error token
         unless matched
-          # Log.trace { "Error at #{pos}" }
+          if text[pos] == "\n"
-          tokens << {type: "Error", value: "#{text[pos]}"}
+            # at EOL, reset state to "root"
+            tokens << {type: "TextWhitespace", value: "\n"}
+            @state_stack = ["root"]
+          else
+            tokens << {type: "Error", value: text[pos..pos]}
+          end
           pos += 1
         end
       end

src/rules.cr

@@ -19,7 +19,7 @@ module Tartrazine
       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.nil? || match.end == 0
+      return false, pos, [] of Token if match.nil? || match.size == 0
       # Log.trace { "#{match}, #{pattern.inspect}, #{text}, #{pos}" }
       tokens = [] of Token
       # Emit the tokens