chore(ignore): keep ci workflow just for manual running for now

.github/workflows/ci.yml

@@ -0,0 +1,22 @@
+name: Tests
+on:
+  # This can't yet run automatically, because tests fail because of
+  # different versions of chroma. Need to get the same one in my
+  # local env and in CI
+  workflow_dispatch:
+permissions:
+  contents: read
+jobs:
+  build:
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Download source
+        uses: actions/checkout@v4
+      - name: Install Crystal
+        uses: crystal-lang/install-crystal@v1
+      - name: Run tests
+        run: |
+          sudo apt-get update && sudo apt-get install golang-chroma -y
+          shards install
+          crystal tool format --check
+          crystal spec -v

.github/workflows/coverage.yml

@@ -0,0 +1,26 @@
+name: Coverage
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: "0 1 * * *"
+permissions:
+  contents: read
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Download source
+        uses: actions/checkout@v4
+      - name: Install Crystal
+        uses: crystal-lang/install-crystal@v1
+      - name: Run tests using kcov
+        run: |
+          sudo apt update && sudo apt install kcov
+          shards install
+          crystal build src/run_tests.cr
+          kcov --clean --include-path=./src coverage ./run_tests
+          curl -Os https://uploader.codecov.io/latest/linux/codecov
+          chmod +x codecov
+          ./codecov -t ${CODECOV_TOKEN} -s coverage
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

Hacefile.yml

@@ -35,7 +35,7 @@ tasks:
     phony: true
     always_run: true
     dependencies:
-      - bin/hace
+      - bin/tartrazine
     commands: |
       rm ${HOME}/.local/bin/{{name}}
       cp bin/hace ${HOME}/.local/bin/{{name}}

spec/tartrazine_spec.cr

@@ -73,7 +73,7 @@ end
 # Helper that creates lexer and tokenizes
 def tokenize(lexer_name, text)
   tokenizer = Tartrazine.lexer(lexer_name).tokenizer(text)
-  Tartrazine::Lexer.collapse_tokens(tokenizer.to_a)
+  Tartrazine::RegexLexer.collapse_tokens(tokenizer.to_a)
 end
 
 # Helper that tokenizes using chroma to validate the lexer
@@ -85,5 +85,5 @@ def chroma_tokenize(lexer_name, text)
     ["-f", "json", "-l", lexer_name],
     input: input, output: output
   )
-  Tartrazine::Lexer.collapse_tokens(Array(Tartrazine::Token).from_json(output.to_s))
+  Tartrazine::RegexLexer.collapse_tokens(Array(Tartrazine::Token).from_json(output.to_s))
 end

src/formatters/json.cr

@@ -12,7 +12,7 @@ module Tartrazine
 
     def format(text : String, lexer : BaseLexer, io : IO) : Nil
       tokenizer = lexer.tokenizer(text)
-      io << Tartrazine::Lexer.collapse_tokens(tokenizer.to_a).to_json
+      io << Tartrazine::RegexLexer.collapse_tokens(tokenizer.to_a).to_json
     end
   end
 end

src/lexer.cr

@@ -1,5 +1,6 @@
-require "baked_file_system"
 require "./constants/lexers"
+require "./heuristics"
+require "baked_file_system"
 
 module Tartrazine
   class LexerFiles
@@ -14,14 +15,14 @@ module Tartrazine
     return lexer_by_filename(filename) if filename
     return lexer_by_mimetype(mimetype) if mimetype
 
-    Lexer.from_xml(LexerFiles.get("/#{LEXERS_BY_NAME["plaintext"]}.xml").gets_to_end)
+    RegexLexer.from_xml(LexerFiles.get("/#{LEXERS_BY_NAME["plaintext"]}.xml").gets_to_end)
   end
 
   private def self.lexer_by_mimetype(mimetype : String) : BaseLexer
     lexer_file_name = LEXERS_BY_MIMETYPE.fetch(mimetype, nil)
     raise Exception.new("Unknown mimetype: #{mimetype}") if lexer_file_name.nil?
 
-    Lexer.from_xml(LexerFiles.get("/#{lexer_file_name}.xml").gets_to_end)
+    RegexLexer.from_xml(LexerFiles.get("/#{lexer_file_name}.xml").gets_to_end)
   end
 
   private def self.lexer_by_name(name : String) : BaseLexer
@@ -29,7 +30,7 @@ module Tartrazine
     return create_delegating_lexer(name) if lexer_file_name.nil? && name.includes? "+"
     raise Exception.new("Unknown lexer: #{name}") if lexer_file_name.nil?
 
-    Lexer.from_xml(LexerFiles.get("/#{lexer_file_name}.xml").gets_to_end)
+    RegexLexer.from_xml(LexerFiles.get("/#{lexer_file_name}.xml").gets_to_end)
   end
 
   private def self.lexer_by_filename(filename : String) : BaseLexer
@@ -52,7 +53,7 @@ module Tartrazine
       end
     end
 
-    Lexer.from_xml(LexerFiles.get("/#{lexer_file_name}.xml").gets_to_end)
+    RegexLexer.from_xml(LexerFiles.get("/#{lexer_file_name}.xml").gets_to_end)
   end
 
   private def self.lexer_by_content(fname : String) : String?
@@ -152,7 +153,9 @@ module Tartrazine
     end
   end
 
-  abstract class BaseLexer
+  alias BaseLexer = Lexer
+
+  abstract class Lexer
     property config = {
       name:             "",
       priority:         0.0,
@@ -174,7 +177,7 @@ module Tartrazine
   # For explanations on what actions and states do
   # the Pygments documentation is a good place to start.
   # https://pygments.org/docs/lexerdevelopment/
-  class Lexer < BaseLexer
+  class RegexLexer < BaseLexer
     # Collapse consecutive tokens of the same type for easier comparison
     # and smaller output
     def self.collapse_tokens(tokens : Array(Tartrazine::Token)) : Array(Tartrazine::Token)
@@ -198,7 +201,7 @@ module Tartrazine
     end
 
     def self.from_xml(xml : String) : Lexer
-      l = Lexer.new
+      l = RegexLexer.new
       lexer = XML.parse(xml).first_element_child
       if lexer
         config = lexer.children.find { |node|
@@ -263,7 +266,7 @@ module Tartrazine
   #
   # This is useful for things like template languages, where
   # you have Jinja + HTML or Jinja + CSS and so on.
-  class DelegatingLexer < BaseLexer
+  class DelegatingLexer < Lexer
     property language_lexer : BaseLexer
     property root_lexer : BaseLexer
 

src/main.cr

@@ -1,5 +1,5 @@
 require "docopt"
-require "./**"
+require "./tartrazine"
 
 HELP = <<-HELP
 tartrazine: a syntax highlighting tool

src/tartrazine.cr

@@ -1,5 +1,6 @@
 require "./actions"
 require "./formatter"
+require "./formatters/**"
 require "./rules"
 require "./styles"
 require "./tartrazine"