v0.5.0

README.md

@@ -47,7 +47,14 @@ To build from source:
 2. Run `make` to build the `tartrazine` binary
 3. Copy the binary somewhere in your PATH.
 
-## Usage
+## Usage as a CLI tool
+
+```shell
+$ tartrazine whatever.c -l c -t catppuccin-macchiato --line-numbers \
+  --standalone -o whatever.html 
+```
+
+## Usage as a Library
 
 This works:
 

TODO.md

@@ -8,4 +8,5 @@
 * ✅ Implement lexer loader that respects aliases
 * ✅ Implement lexer loader by file extension
 * ✅ Add --line-numbers to terminal formatter
-* Implement lexer loader by mime type
+* Implement lexer loader by mime type
+* Implement Delegating lexers

shard.yml

@@ -1,5 +1,5 @@
 name: tartrazine
-version: 0.4.0
+version: 0.5.0
 
 authors:
   - Roberto Alsina <roberto.alsina@gmail.com>

spec/tartrazine_spec.cr

@@ -73,7 +73,8 @@ end
 # Helper that creates lexer and tokenizes
 def tokenize(lexer_name, text)
   lexer = Tartrazine.lexer(lexer_name)
-  lexer.tokenize(text)
+  tokenizer = Tartrazine::Tokenizer.new(lexer, text)
+  Tartrazine::Lexer.collapse_tokens(tokenizer.to_a)
 end
 
 # Helper that tokenizes using chroma to validate the lexer

src/actions.cr

@@ -8,19 +8,29 @@ require "./tartrazine"
 # perform a list of actions. These actions can emit tokens
 # or change the state machine.
 module Tartrazine
+  enum ActionType
+    Bygroups
+    Combined
+    Include
+    Pop
+    Push
+    Token
+    Using
+    Usingself
+  end
+
   struct Action
     property actions : Array(Action) = [] of Action
-    property type : String
 
     @depth : Int32 = 0
     @lexer_name : String = ""
     @states : Array(String) = [] of String
     @states_to_push : Array(String) = [] of String
     @token_type : String = ""
+    @type : ActionType = ActionType::Token
 
-    def initialize(@type : String, xml : XML::Node?)
-      known_types = %w(token push pop combined bygroups include using usingself)
-      raise Exception.new("Unknown action type: #{type}") unless known_types.includes? type
+    def initialize(t : String, xml : XML::Node?)
+      @type = ActionType.parse(t.capitalize)
 
       # Some actions may have actions in them, like this:
       # <bygroups>
@@ -37,18 +47,18 @@ module Tartrazine
       end
 
       # Prefetch the attributes we ned from the XML and keep them
-      case type
-      when "token"
+      case @type
+      when ActionType::Token
         @token_type = xml["type"]
-      when "push"
+      when ActionType::Push
         @states_to_push = xml.attributes.select { |attrib|
           attrib.name == "state"
         }.map &.content
-      when "pop"
+      when ActionType::Pop
         @depth = xml["depth"].to_i
-      when "using"
+      when ActionType::Using
         @lexer_name = xml["lexer"].downcase
-      when "combined"
+      when ActionType::Combined
         @states = xml.attributes.select { |attrib|
           attrib.name == "state"
         }.map &.content
@@ -56,28 +66,28 @@ module Tartrazine
     end
 
     # ameba:disable Metrics/CyclomaticComplexity
-    def emit(match : MatchData, lexer : Lexer, match_group = 0) : Array(Token)
-      case type
-      when "token"
+    def emit(match : MatchData, tokenizer : Tokenizer, match_group = 0) : Array(Token)
+      case @type
+      when ActionType::Token
         raise Exception.new "Can't have a token without a match" if match.empty?
         [Token.new(type: @token_type, value: String.new(match[match_group].value))]
-      when "push"
-        to_push = @states_to_push.empty? ? [lexer.state_stack.last] : @states_to_push
+      when ActionType::Push
+        to_push = @states_to_push.empty? ? [tokenizer.state_stack.last] : @states_to_push
         to_push.each do |state|
-          if state == "#pop" && lexer.state_stack.size > 1
+          if state == "#pop" && tokenizer.state_stack.size > 1
             # Pop the state
-            lexer.state_stack.pop
+            tokenizer.state_stack.pop
           else
             # Really push
-            lexer.state_stack << state
+            tokenizer.state_stack << state
           end
         end
         [] of Token
-      when "pop"
-        to_pop = [@depth, lexer.state_stack.size - 1].min
-        lexer.state_stack.pop(to_pop)
+      when ActionType::Pop
+        to_pop = [@depth, tokenizer.state_stack.size - 1].min
+        tokenizer.state_stack.pop(to_pop)
         [] of Token
-      when "bygroups"
+      when ActionType::Bygroups
         # FIXME: handle
         # ><bygroups>
         # <token type="Punctuation"/>
@@ -99,30 +109,35 @@ module Tartrazine
             # No match for this group
             next
           end
-          result += e.emit(match, lexer, i + 1)
+          result += e.emit(match, tokenizer, i + 1)
         end
         result
-      when "using"
+      when ActionType::Using
         # Shunt to another lexer entirely
         return [] of Token if match.empty?
-        Tartrazine.lexer(@lexer_name).tokenize(String.new(match[match_group].value), usingself: true)
-      when "usingself"
+        Tokenizer.new(
+          Tartrazine.lexer(@lexer_name),
+          String.new(match[match_group].value),
+          secondary: true).to_a
+      when ActionType::Usingself
         # Shunt to another copy of this lexer
         return [] of Token if match.empty?
-        new_lexer = lexer.copy
-        new_lexer.tokenize(String.new(match[match_group].value), usingself: true)
-      when "combined"
-        # Combine two states into one anonymous state
+        Tokenizer.new(
+          tokenizer.lexer,
+          String.new(match[match_group].value),
+          secondary: true).to_a
+      when ActionType::Combined
+        # Combine two or more states into one anonymous state
         new_state = @states.map { |name|
-          lexer.states[name]
+          tokenizer.lexer.states[name]
         }.reduce { |state1, state2|
           state1 + state2
         }
-        lexer.states[new_state.name] = new_state
-        lexer.state_stack << new_state.name
+        tokenizer.lexer.states[new_state.name] = new_state
+        tokenizer.state_stack << new_state.name
         [] of Token
       else
-        raise Exception.new("Unknown action type: #{type}")
+        raise Exception.new("Unknown action type: #{@type}")
       end
     end
   end

src/bytes_regex.cr

@@ -31,7 +31,6 @@ module BytesRegex
     end
 
     def match(str : Bytes, pos = 0) : Array(Match)
-      match = [] of Match
       rc = LibPCRE2.match(
         @re,
         str,
@@ -42,22 +41,23 @@ module BytesRegex
         nil)
       if rc > 0
         ovector = LibPCRE2.get_ovector_pointer(@match_data)
-        (0...rc).each do |i|
+        (0...rc).map do |i|
           m_start = ovector[2 * i]
-          m_size = ovector[2 * i + 1] - m_start
-          if m_size == 0
+          m_end = ovector[2 * i + 1]
+          if m_start == m_end
             m_value = Bytes.new(0)
           else
-            m_value = str[m_start...m_start + m_size]
+            m_value = str[m_start...m_end]
           end
-          match << Match.new(m_value, m_start, m_size)
+          Match.new(m_value, m_start, m_end - m_start)
         end
+      else
+        [] of Match
       end
-      match
     end
   end
 
-  class Match
+  struct Match
     property value : Bytes
     property start : UInt64
     property size : UInt64

src/formatters/ansi.cr

@@ -7,19 +7,39 @@ module Tartrazine
     def initialize(@theme : Theme = Tartrazine.theme("default-dark"), @line_numbers : Bool = false)
     end
 
+    private def line_label(i : Int32) : String
+      "#{i + 1}".rjust(4).ljust(5)
+    end
+
     def format(text : String, lexer : Lexer) : String
+      tokenizer = Tokenizer.new(lexer, text)
+      i = 0
       output = String.build do |outp|
-        lexer.group_tokens_in_lines(lexer.tokenize(text)).each_with_index do |line, i|
-          label = line_numbers? ? "#{i + 1}".rjust(4).ljust(5) : ""
-          outp << label
-          line.each do |token|
-            outp << colorize(token[:value], token[:type])
+        outp << line_label(i) if line_numbers?
+        tokenizer.each do |token|
+          outp << colorize(token[:value], token[:type])
+          if token[:value].includes?("\n")
+            i += 1
+            outp << line_label(i) if line_numbers?
           end
         end
       end
       output
     end
 
+    # def format(text : String, lexer : Lexer) : String
+    #   output = String.build do |outp|
+    #     lexer.group_tokens_in_lines(lexer.tokenize(text)).each_with_index do |line, i|
+    #       label = line_numbers? ? "#{i + 1}".rjust(4).ljust(5) : ""
+    #       outp << label
+    #       line.each do |token|
+    #         outp << colorize(token[:value], token[:type])
+    #       end
+    #     end
+    #   end
+    #   output
+    # end
+
     def colorize(text : String, token : String) : String
       style = theme.styles.fetch(token, nil)
       return text if style.nil?

src/formatters/html.cr

@@ -54,21 +54,29 @@ module Tartrazine
       output
     end
 
+    private def line_label(i : Int32) : String
+      line_label = "#{i + 1}".rjust(4).ljust(5)
+      line_class = highlighted?(i + 1) ? "class=\"#{get_css_class("LineHighlight")}\"" : ""
+      line_id = linkable_line_numbers? ? "id=\"#{line_number_id_prefix}#{i + 1}\"" : ""
+      "<span #{line_id} #{line_class} style=\"user-select: none;\">#{line_label} </span>"
+    end
+
     def format_text(text : String, lexer : Lexer) : String
-      lines = lexer.group_tokens_in_lines(lexer.tokenize(text))
+      # lines = lexer.group_tokens_in_lines(lexer.tokenize(text))
+      tokenizer = Tokenizer.new(lexer, text)
+      i = 0
       output = String.build do |outp|
         if surrounding_pre?
           pre_style = wrap_long_lines? ? "style=\"white-space: pre-wrap; word-break: break-word;\"" : ""
           outp << "<pre class=\"#{get_css_class("Background")}\" #{pre_style}>"
         end
         outp << "<code class=\"#{get_css_class("Background")}\">"
-        lines.each_with_index(offset: line_number_start - 1) do |line, i|
-          line_label = line_numbers? ? "#{i + 1}".rjust(4).ljust(5) : ""
-          line_class = highlighted?(i + 1) ? "class=\"#{get_css_class("LineHighlight")}\"" : ""
-          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|
-            outp << "<span class=\"#{get_css_class(token[:type])}\">#{HTML.escape(token[:value])}</span>"
+        outp << line_label(i) if line_numbers?
+        tokenizer.each do |token|
+          outp << "<span class=\"#{get_css_class(token[:type])}\">#{HTML.escape(token[:value])}</span>"
+          if token[:value].ends_with? "\n"
+            i += 1
+            outp << line_label(i) if line_numbers?
           end
         end
         outp << "</code></pre>"

src/lexer.cr

@@ -4,7 +4,6 @@ require "./constants/lexers"
 module Tartrazine
   class LexerFiles
     extend BakedFileSystem
-
     bake_folder "../lexers", __DIR__
   end
 
@@ -38,80 +37,91 @@ module Tartrazine
     LEXERS_BY_NAME.keys.sort!
   end
 
+  # A token, the output of the tokenizer
+  alias Token = NamedTuple(type: String, value: String)
+
+  struct Tokenizer
+    include Iterator(Token)
+    property lexer : Lexer
+    property text : Bytes
+    property pos : Int32 = 0
+    @dq = Deque(Token).new
+    property state_stack = ["root"]
+
+    def initialize(@lexer : Lexer, text : String, secondary = false)
+      # Respect the `ensure_nl` config option
+      if text.size > 0 && text[-1] != '\n' && @lexer.config[:ensure_nl] && !secondary
+        text += "\n"
+      end
+      @text = text.to_slice
+    end
+
+    def next : Iterator::Stop | Token
+      if @dq.size > 0
+        return @dq.shift
+      end
+      if pos == @text.size
+        return stop
+      end
+
+      matched = false
+      while @pos < @text.size
+        @lexer.states[@state_stack.last].rules.each do |rule|
+          matched, new_pos, new_tokens = rule.match(@text, @pos, self)
+          if matched
+            @pos = new_pos
+            split_tokens(new_tokens).each { |token| @dq << token }
+            break
+          end
+        end
+        if !matched
+          if @text[@pos] == 10u8
+            @dq << {type: "Text", value: "\n"}
+            @state_stack = ["root"]
+          else
+            @dq << {type: "Error", value: String.new(@text[@pos..@pos])}
+          end
+          @pos += 1
+          break
+        end
+      end
+      self.next
+    end
+
+    # If a token contains a newline, split it into two tokens
+    def split_tokens(tokens : Array(Token)) : Array(Token)
+      split_tokens = [] of Token
+      tokens.each do |token|
+        if token[:value].includes?("\n")
+          values = token[:value].split("\n")
+          values.each_with_index do |value, index|
+            value += "\n" if index < values.size - 1
+            split_tokens << {type: token[:type], value: value}
+          end
+        else
+          split_tokens << token
+        end
+      end
+      split_tokens
+    end
+  end
+
   # This implements a lexer for Pygments RegexLexers as expressed
   # in Chroma's XML serialization.
   #
   # For explanations on what actions and states do
   # the Pygments documentation is a good place to start.
   # https://pygments.org/docs/lexerdevelopment/
-  class Lexer
+  struct Lexer
     property config = {
       name:             "",
-      aliases:          [] of String,
-      filenames:        [] of String,
-      mime_types:       [] of String,
       priority:         0.0,
       case_insensitive: false,
       dot_all:          false,
       not_multiline:    false,
       ensure_nl:        false,
     }
-    # 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.
-    # So, when it's true, we don't modify the text.
-    def tokenize(text : String, usingself = false) : Array(Token)
-      @state_stack = ["root"]
-      tokens = [] of Token
-      pos = 0
-      matched = false
-
-      # Respect the `ensure_nl` config option
-      if text.size > 0 && text[-1] != '\n' && config[:ensure_nl] && !usingself
-        text += "\n"
-      end
-
-      text_bytes = text.to_slice
-      # Loop through the text, applying rules
-      while pos < text_bytes.size
-        state = states[@state_stack.last]
-        # Log.trace { "Stack is #{@state_stack} State is #{state.name}, pos is #{pos}, text is #{text[pos..pos + 10]}" }
-        state.rules.each do |rule|
-          matched, new_pos, new_tokens = rule.match(text_bytes, pos, self)
-          if matched
-            # Move position forward, save the tokens,
-            # tokenize from the new position
-            pos = new_pos
-            tokens += new_tokens
-            break
-          end
-        end
-        # If no rule matches, emit an error token
-        unless matched
-          if text_bytes[pos] == 10u8
-            # at EOL, reset state to "root"
-            tokens << {type: "Text", value: "\n"}
-            @state_stack = ["root"]
-          else
-            tokens << {type: "Error", value: String.new(text_bytes[pos..pos])}
-          end
-          pos += 1
-        end
-      end
-      Lexer.collapse_tokens(tokens)
-    end
 
     # Collapse consecutive tokens of the same type for easier comparison
     # and smaller output
@@ -135,31 +145,6 @@ module Tartrazine
       result
     end
 
-    # Group tokens into lines, splitting them when a newline is found
-    def group_tokens_in_lines(tokens : Array(Token)) : Array(Array(Token))
-      split_tokens = [] of Token
-      tokens.each do |token|
-        if token[:value].includes?("\n")
-          values = token[:value].split("\n")
-          values.each_with_index do |value, index|
-            value += "\n" if index < values.size - 1
-            split_tokens << {type: token[:type], value: value}
-          end
-        else
-          split_tokens << token
-        end
-      end
-      lines = [Array(Token).new]
-      split_tokens.each do |token|
-        lines.last << token
-        if token[:value].includes?("\n")
-          lines << Array(Token).new
-        end
-      end
-      lines
-    end
-
-    # ameba:disable Metrics/CyclomaticComplexity
     def self.from_xml(xml : String) : Lexer
       l = Lexer.new
       lexer = XML.parse(xml).first_element_child
@@ -170,9 +155,6 @@ module Tartrazine
         if config
           l.config = {
             name:             xml_to_s(config, name) || "",
-            aliases:          xml_to_a(config, _alias) || [] of String,
-            filenames:        xml_to_a(config, filename) || [] of String,
-            mime_types:       xml_to_a(config, mime_type) || [] of String,
             priority:         xml_to_f(config, priority) || 0.0,
             not_multiline:    xml_to_s(config, not_multiline) == "true",
             dot_all:          xml_to_s(config, dot_all) == "true",
@@ -236,7 +218,4 @@ module Tartrazine
       new_state
     end
   end
-
-  # A token, the output of the tokenizer
-  alias Token = NamedTuple(type: String, value: String)
 end

src/rules.cr

@@ -16,10 +16,10 @@ module Tartrazine
   alias MatchData = Array(Match)
 
   abstract struct BaseRule
-    abstract def match(text : Bytes, pos, lexer) : Tuple(Bool, Int32, Array(Token))
+    abstract def match(text : Bytes, pos : Int32, tokenizer : Tokenizer) : Tuple(Bool, Int32, Array(Token))
     abstract def initialize(node : XML::Node)
 
-    property actions : Array(Action) = [] of Action
+    @actions : Array(Action) = [] of Action
 
     def add_actions(node : XML::Node)
       node.children.each do |child|
@@ -31,14 +31,13 @@ module Tartrazine
 
   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))
+    def match(text : Bytes, pos, tokenizer) : 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) }
+      return true, pos + match[0].size, @actions.flat_map(&.emit(match, tokenizer))
     end
 
     def initialize(node : XML::Node)
@@ -55,12 +54,11 @@ module Tartrazine
   # This rule includes another state. If any of the rules of the
   # included state matches, this rule matches.
   struct IncludeStateRule < BaseRule
-    property state : String = ""
+    @state : String = ""
 
-    def match(text, pos, lexer) : Tuple(Bool, Int32, Array(Token))
-      Log.trace { "Including state #{state} from #{lexer.state_stack.last}" }
-      lexer.states[state].rules.each do |rule|
-        matched, new_pos, new_tokens = rule.match(text, pos, lexer)
+    def match(text : Bytes, pos : Int32, tokenizer : Tokenizer) : Tuple(Bool, Int32, Array(Token))
+      tokenizer.@lexer.states[@state].rules.each do |rule|
+        matched, new_pos, new_tokens = rule.match(text, pos, tokenizer)
         return true, new_pos, new_tokens if matched
       end
       return false, pos, [] of Token
@@ -79,8 +77,8 @@ module Tartrazine
   struct UnconditionalRule < BaseRule
     NO_MATCH = [] of Match
 
-    def match(text, pos, lexer) : Tuple(Bool, Int32, Array(Token))
-      return true, pos, actions.flat_map { |action| action.emit(NO_MATCH, lexer) }
+    def match(text, pos, tokenizer) : Tuple(Bool, Int32, Array(Token))
+      return true, pos, @actions.flat_map(&.emit(NO_MATCH, tokenizer))
     end
 
     def initialize(node : XML::Node)

src/styles.cr

@@ -9,7 +9,7 @@ require "xml"
 module Tartrazine
   alias Color = Sixteen::Color
 
-  class ThemeFiles
+  struct ThemeFiles
     extend BakedFileSystem
     bake_folder "../styles", __DIR__
   end
@@ -39,7 +39,7 @@ module Tartrazine
     themes.to_a.sort!
   end
 
-  class Style
+  struct Style
     # These properties are tri-state.
     # true means it's set
     # false means it's not set
@@ -79,7 +79,7 @@ module Tartrazine
     end
   end
 
-  class Theme
+  struct Theme
     property name : String = ""
 
     property styles = {} of String => Style