bump: Release v0.11.1

Conditional lexers and themes

.ameba.yml

@@ -1,9 +1,9 @@
 # This configuration file was generated by `ameba --gen-config`
-# on 2024-09-11 00:56:14 UTC using Ameba version 1.6.1.
+# on 2024-09-21 14:59:30 UTC using Ameba version 1.6.1.
 # The point is for the user to remove these configuration records
 # one by one as the reported problems are removed from the code base.
 
-# Problems found: 4
+# Problems found: 3
 # Run `ameba --only Documentation/DocumentationAdmonition` for details
 Documentation/DocumentationAdmonition:
   Description: Reports documentation admonitions
@@ -11,10 +11,24 @@ Documentation/DocumentationAdmonition:
   Excluded:
   - src/lexer.cr
   - src/actions.cr
-  - spec/examples/crystal/lexer_spec.cr
   Admonitions:
   - TODO
   - FIXME
   - BUG
   Enabled: true
   Severity: Warning
+
+# Problems found: 1
+# Run `ameba --only Lint/SpecFilename` for details
+Lint/SpecFilename:
+  Description: Enforces spec filenames to have `_spec` suffix
+  Excluded:
+  - spec/examples/crystal/hello.cr
+  IgnoredDirs:
+  - spec/support
+  - spec/fixtures
+  - spec/data
+  IgnoredFilenames:
+  - spec_helper
+  Enabled: true
+  Severity: Warning

CHANGELOG.md

@@ -2,6 +2,75 @@
 
 All notable changes to this project will be documented in this file.
 
+## [0.11.1] - 2024-10-14
+
+### 🐛 Bug Fixes
+
+- Support choosing lexers when used as a library
+
+## [0.11.0] - 2024-10-14
+
+### 🚀 Features
+
+- Support selecting only some themes
+
+## [0.10.0] - 2024-09-26
+
+### 🚀 Features
+
+- Optional conditional baking of lexers
+
+### 🐛 Bug Fixes
+
+- Strip binaries for release artifacts
+- Fix metadata to show crystal
+
+## [0.9.1] - 2024-09-22
+
+### 🐛 Bug Fixes
+
+- Terminal formatter was skipping things that it could highlight
+- Bug in high-level API for png formatter
+
+### 🧪 Testing
+
+- Added minimal tests for svg and png formatters
+
+## [0.9.0] - 2024-09-21
+
+### 🚀 Features
+
+- PNG writer based on Stumpy libs
+
+### ⚙️ Miscellaneous Tasks
+
+- Clean
+- Detect version bump in release script
+- Improve changelog handling
+
+## [0.8.0] - 2024-09-21
+
+### 🚀 Features
+
+- SVG formatter
+
+### 🐛 Bug Fixes
+
+- HTML formatter was setting bold wrong
+
+### 📚 Documentation
+
+- Added instructions to add as a dependency
+
+### 🧪 Testing
+
+- Add basic tests for crystal and delegating lexers
+- Added tests for CSS generation
+
+### ⚙ Miscellaneous Tasks
+
+- Fix example code in README
+
 ## [0.7.0] - 2024-09-10
 
 ### 🚀 Features

Hacefile.yml

@@ -113,3 +113,11 @@ tasks:
       kcov --clean --include-path=./src ${PWD}/coverage ./bin/run_tests
     outputs:
       - coverage/index.html
+
+  loc:
+    phony: true
+    always_run: true
+    dependencies:
+      - src
+    commands: |
+      tokei src -e src/constants/

README.md

@@ -71,7 +71,7 @@ This does more or less the same thing, but more manually:
 
 ```crystal
 lexer = Tartrazine.lexer("crystal")
-formatter = Tartrazine::Html.new (
+formatter = Tartrazine::Html.new(
   theme: Tartrazine.theme("catppuccin-macchiato"),
   line_numbers: true,
   standalone: true,
@@ -82,6 +82,51 @@ puts formatter.format("puts \"Hello, world!\"", lexer)
 The reason you may want to use the manual version is to reuse
 the lexer and formatter objects for performance reasons.
 
+## Choosing what Lexers you want
+
+By default Tartrazine will support all its lexers by embedding
+them in the binary. This makes the binary large. If you are
+using it as a library, you may want to just include a selection of lexers. To do that:
+
+* Pass the `-Dnolexers` flag to the compiler
+* Set the `TT_LEXERS` environment variable to a
+  comma-separated list of lexers you want to include.
+
+
+This builds a binary with only the python, markdown, bash and yaml lexers (enough to highlight this `README.md`):
+
+```bash
+> TT_LEXERS=python,markdown,bash,yaml shards build -Dnolexers -d --error-trace
+Dependencies are satisfied
+Building: tartrazine
+```
+
+## Choosing what themes you want
+
+Themes come from two places, tartrazine itself and [Sixteen](https://github.com/ralsina/sixteen).
+
+To only embed selected themes, build your project with the `-Dnothemes` option, and
+you can set two environment variables to control which themes are included:
+
+* `TT_THEMES` is a comma-separated list of themes to include from tartrazine (see the styles directory in the source)
+* `SIXTEEN_THEMES` is a comma-separated list of themes to include from Sixteen (see the base16 directory in the sixteen source)
+
+For example (using the tartrazine CLI as the project):
+
+```bash
+$ TT_THEMES=colorful,autumn SIXTEEN_THEMES=pasque,pico shards build -Dnothemes
+Dependencies are satisfied
+Building: tartrazine
+
+$ ./bin/tartrazine  --list-themes
+autumn
+colorful
+pasque
+pico
+```
+
+Be careful not to build without any themes at all, nothing will work.
+
 ## Contributing
 
 1. Fork it (<https://github.com/ralsina/tartrazine/fork>)

build_static.sh

@@ -7,10 +7,10 @@ docker run --rm --privileged \
 
 # Build for AMD64
 docker build . -f Dockerfile.static -t tartrazine-builder
-docker run -ti --rm -v "$PWD":/app --user="$UID" tartrazine-builder /bin/sh -c "cd /app && rm -rf lib shard.lock && shards build --static --release"
+docker run -ti --rm -v "$PWD":/app --user="$UID" tartrazine-builder /bin/sh -c "cd /app && rm -rf lib shard.lock && shards build --static --release && strip bin/tartrazine"
 mv bin/tartrazine bin/tartrazine-static-linux-amd64
 
 # Build for ARM64
 docker build . -f Dockerfile.static --platform linux/arm64 -t tartrazine-builder
-docker run -ti --rm -v "$PWD":/app --platform linux/arm64 --user="$UID" tartrazine-builder /bin/sh -c "cd /app && rm -rf lib shard.lock && shards build --static --release"
+docker run -ti --rm -v "$PWD":/app --platform linux/arm64 --user="$UID" tartrazine-builder /bin/sh -c "cd /app && rm -rf lib shard.lock && shards build --static --release && strip bin/tartrazine"
 mv bin/tartrazine bin/tartrazine-static-linux-arm64

cliff.toml

@@ -67,7 +67,6 @@ commit_parsers = [
   { message = "^chore\\(deps.*\\)", skip = true },
   { message = "^chore\\(pr\\)", skip = true },
   { message = "^chore\\(pull\\)", skip = true },
-  { message = "^chore\\(ignore\\)", skip = true },
   { message = "^chore|^ci", group = "<!-- 7 -->⚙️ Miscellaneous Tasks" },
   { body = ".*security", group = "<!-- 8 -->🛡️ Security" },
   { message = "^revert", group = "<!-- 9 -->◀️ Revert" },

do_release.sh

@@ -2,14 +2,14 @@
 set e
 
 PKGNAME=$(basename "$PWD")
-VERSION=$(git cliff --bumped-version |cut -dv -f2)
+VERSION=$(git cliff --bumped-version --unreleased |cut -dv -f2)
 
 sed "s/^version:.*$/version: $VERSION/g" -i shard.yml
 git add shard.yml
 hace lint test
-git cliff --bump -o
+git cliff --bump -u -p CHANGELOG.md
 git commit -a -m "bump: Release v$VERSION"
+hace static
 git tag "v$VERSION"
 git push --tags
-hace static
 gh release create "v$VERSION" "bin/$PKGNAME-static-linux-amd64" "bin/$PKGNAME-static-linux-arm64" --title "Release v$VERSION" --notes "$(git cliff -l -s all)"

scripts/lexer_metadata.py

@@ -38,6 +38,12 @@ for fname in glob.glob("lexers/*.xml"):
         lexer_by_filename[filename].add(lexer_name)
 
 with open("src/constants/lexers.cr", "w") as f:
+    # Crystal doesn't come from a xml file
+    lexer_by_name["crystal"] = "crystal"
+    lexer_by_name["cr"] = "crystal"
+    lexer_by_filename["*.cr"] = ["crystal"]
+    lexer_by_mimetype["text/x-crystal"] = "crystal"
+
     f.write("module Tartrazine\n")
     f.write("  LEXERS_BY_NAME = {\n")
     for k in sorted(lexer_by_name.keys()):

shard.yml

@@ -1,5 +1,5 @@
 name: tartrazine
-version: 0.7.0
+version: 0.11.1
 
 authors:
   - Roberto Alsina <roberto.alsina@gmail.com>
@@ -18,6 +18,10 @@ dependencies:
     github: ralsina/sixteen
   docopt:
     github: chenkovsky/docopt.cr
+  stumpy_utils:
+    github: stumpycr/stumpy_utils
+  stumpy_png:
+    github: stumpycr/stumpy_png
 
 crystal: ">= 1.13.0"
 

spec/css/manni.css

@@ -1 +1 @@
-.e {color: #aa0000;background-color: #ffaaaa;}.b {background-color: #f0f3f3;tab-size: 8;}.k {color: #006699;font-weight: bold;}.kp {font-weight: 600;}.kt {color: #007788;}.na {color: #330099;}.nb {color: #336666;}.nc {color: #00aa88;font-weight: bold;}.nc {color: #336600;}.nd {color: #9999ff;}.ne {color: #999999;font-weight: bold;}.ne {color: #cc0000;font-weight: bold;}.nf {color: #cc00ff;}.nl {color: #9999ff;}.nn {color: #00ccff;font-weight: bold;}.nt {color: #330099;font-weight: bold;}.nv {color: #003333;}.ls {color: #cc3300;}.lsd {font-style: italic;}.lse {color: #cc3300;font-weight: bold;}.lsi {color: #aa0000;}.lso {color: #cc3300;}.lsr {color: #33aaaa;}.lss {color: #ffcc33;}.ln {color: #ff6600;}.o {color: #555555;}.ow {color: #000000;font-weight: bold;}.c {color: #0099ff;font-style: italic;}.cs {font-weight: bold;}.cp {color: #009999;font-style: normal;}.gd {background-color: #ffcccc;border: 1px solid #cc0000;}.ge {font-style: italic;}.ge {color: #ff0000;}.gh {color: #003300;font-weight: bold;}.gi {background-color: #ccffcc;border: 1px solid #00cc00;}.go {color: #aaaaaa;}.gp {color: #000099;font-weight: bold;}.gs {font-weight: bold;}.gs {color: #003300;font-weight: bold;}.gt {color: #99cc66;}.gu {text-decoration: underline;}.tw {color: #bbbbbb;}.lh {}
+.e {color: #aa0000;background-color: #ffaaaa;}.b {background-color: #f0f3f3;tab-size: 8;}.k {color: #006699;font-weight: 600;}.kp {}.kt {color: #007788;}.na {color: #330099;}.nb {color: #336666;}.nc {color: #00aa88;font-weight: 600;}.nc {color: #336600;}.nd {color: #9999ff;}.ne {color: #999999;font-weight: 600;}.ne {color: #cc0000;font-weight: 600;}.nf {color: #cc00ff;}.nl {color: #9999ff;}.nn {color: #00ccff;font-weight: 600;}.nt {color: #330099;font-weight: 600;}.nv {color: #003333;}.ls {color: #cc3300;}.lsd {font-style: italic;}.lse {color: #cc3300;font-weight: 600;}.lsi {color: #aa0000;}.lso {color: #cc3300;}.lsr {color: #33aaaa;}.lss {color: #ffcc33;}.ln {color: #ff6600;}.o {color: #555555;}.ow {color: #000000;font-weight: 600;}.c {color: #0099ff;font-style: italic;}.cs {font-weight: 600;}.cp {color: #009999;font-style: normal;}.gd {background-color: #ffcccc;border: 1px solid #cc0000;}.ge {font-style: italic;}.ge {color: #ff0000;}.gh {color: #003300;font-weight: 600;}.gi {background-color: #ccffcc;border: 1px solid #00cc00;}.go {color: #aaaaaa;}.gp {color: #000099;font-weight: 600;}.gs {font-weight: 600;}.gs {color: #003300;font-weight: 600;}.gt {color: #99cc66;}.gu {text-decoration: underline;}.tw {color: #bbbbbb;}.lh {}

spec/css/vesper.css

@@ -1 +1 @@
-.b {color: #b7b7b7;background-color: #101010;font-weight: bold;tab-size: 8;}.lh {color: #8eaaaa;background-color: #232323;}.t {color: #b7b7b7;}.e {color: #de6e6e;}.c {color: #333333;}.cp {color: #876c4f;}.cpf {color: #5f8787;}.k {color: #d69094;}.kt {color: #de6e6e;}.na {color: #8eaaaa;}.nb {color: #de6e6e;}.nbp {color: #de6e6e;}.nc {color: #8eaaaa;}.nc {color: #dab083;}.nd {color: #dab083;}.nf {color: #8eaaaa;}.nn {color: #8eaaaa;}.nt {color: #d69094;}.nv {color: #8eaaaa;}.nvi {color: #de6e6e;}.ln {color: #dab083;}.o {color: #60a592;}.ow {color: #d69094;}.l {color: #5f8787;}.ls {color: #5f8787;}.lsi {color: #876c4f;}.lsr {color: #60a592;}.lss {color: #dab083;}
+.b {color: #b7b7b7;background-color: #101010;font-weight: 600;tab-size: 8;}.lh {color: #8eaaaa;background-color: #232323;}.t {color: #b7b7b7;}.e {color: #de6e6e;}.c {color: #333333;}.cp {color: #876c4f;}.cpf {color: #5f8787;}.k {color: #d69094;}.kt {color: #de6e6e;}.na {color: #8eaaaa;}.nb {color: #de6e6e;}.nbp {color: #de6e6e;}.nc {color: #8eaaaa;}.nc {color: #dab083;}.nd {color: #dab083;}.nf {color: #8eaaaa;}.nn {color: #8eaaaa;}.nt {color: #d69094;}.nv {color: #8eaaaa;}.nvi {color: #de6e6e;}.ln {color: #dab083;}.o {color: #60a592;}.ow {color: #d69094;}.l {color: #5f8787;}.ls {color: #5f8787;}.lsi {color: #876c4f;}.lsr {color: #60a592;}.lss {color: #dab083;}

spec/examples/crystal/hello.cr

@@ -0,0 +1 @@
+puts "Hello Crystal!"

spec/examples/crystal/hello.cr.json

@@ -0,0 +1 @@
+[{"type":"Text","value":"puts "},{"type":"LiteralString","value":"\"Hello Crystal!\""},{"type":"Text","value":"\n"}]

spec/examples/crystal/lexer.cr

@@ -1,413 +0,0 @@
-require "./constants/lexers"
-require "./heuristics"
-require "baked_file_system"
-require "crystal/syntax_highlighter"
-
-module Tartrazine
-  class LexerFiles
-    extend BakedFileSystem
-    bake_folder "../lexers", __DIR__
-  end
-
-  # Get the lexer object for a language name
-  # FIXME: support mimetypes
-  def self.lexer(name : String? = nil, filename : String? = nil, mimetype : String? = nil) : BaseLexer
-    return lexer_by_name(name) if name && name != "autodetect"
-    return lexer_by_filename(filename) if filename
-    return lexer_by_mimetype(mimetype) if mimetype
-
-    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?
-
-    RegexLexer.from_xml(LexerFiles.get("/#{lexer_file_name}.xml").gets_to_end)
-  end
-
-  private def self.lexer_by_name(name : String) : BaseLexer
-    return CrystalLexer.new if name == "crystal"
-    lexer_file_name = LEXERS_BY_NAME.fetch(name.downcase, nil)
-    return create_delegating_lexer(name) if lexer_file_name.nil? && name.includes? "+"
-    raise Exception.new("Unknown lexer: #{name}") if lexer_file_name.nil?
-
-    RegexLexer.from_xml(LexerFiles.get("/#{lexer_file_name}.xml").gets_to_end)
-  end
-
-  private def self.lexer_by_filename(filename : String) : BaseLexer
-    if filename.ends_with?(".cr")
-      return CrystalLexer.new
-    end
-
-    candidates = Set(String).new
-    LEXERS_BY_FILENAME.each do |k, v|
-      candidates += v.to_set if File.match?(k, File.basename(filename))
-    end
-
-    case candidates.size
-    when 0
-      lexer_file_name = LEXERS_BY_NAME["plaintext"]
-    when 1
-      lexer_file_name = candidates.first
-    else
-      lexer_file_name = self.lexer_by_content(filename)
-      begin
-        return self.lexer(lexer_file_name)
-      rescue ex : Exception
-        raise Exception.new("Multiple lexers match the filename: #{candidates.to_a.join(", ")}, heuristics suggest #{lexer_file_name} but there is no matching lexer.")
-      end
-    end
-
-    RegexLexer.from_xml(LexerFiles.get("/#{lexer_file_name}.xml").gets_to_end)
-  end
-
-  private def self.lexer_by_content(fname : String) : String?
-    h = Linguist::Heuristic.from_yaml(LexerFiles.get("/heuristics.yml").gets_to_end)
-    result = h.run(fname, File.read(fname))
-    case result
-    when Nil
-      raise Exception.new "No lexer found for #{fname}"
-    when String
-      result.as(String)
-    when Array(String)
-      result.first
-    end
-  end
-
-  private def self.create_delegating_lexer(name : String) : BaseLexer
-    language, root = name.split("+", 2)
-    language_lexer = lexer(language)
-    root_lexer = lexer(root)
-    DelegatingLexer.new(language_lexer, root_lexer)
-  end
-
-  # Return a list of all lexers
-  def self.lexers : Array(String)
-    LEXERS_BY_NAME.keys.sort!
-  end
-
-  # A token, the output of the tokenizer
-  alias Token = NamedTuple(type: String, value: String)
-
-  abstract class BaseTokenizer
-  end
-
-  class Tokenizer < BaseTokenizer
-    include Iterator(Token)
-    property lexer : BaseLexer
-    property text : Bytes
-    property pos : Int32 = 0
-    @dq = Deque(Token).new
-    property state_stack = ["root"]
-
-    def initialize(@lexer : BaseLexer, 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
-
-  alias BaseLexer = Lexer
-
-  abstract class Lexer
-    property config = {
-      name:             "",
-      priority:         0.0,
-      case_insensitive: false,
-      dot_all:          false,
-      not_multiline:    false,
-      ensure_nl:        false,
-    }
-    property states = {} of String => State
-
-    def tokenizer(text : String, secondary = false) : BaseTokenizer
-      Tokenizer.new(self, text, secondary)
-    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 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)
-      result = [] of Tartrazine::Token
-      tokens = tokens.reject { |token| token[:value] == "" }
-      tokens.each do |token|
-        if result.empty?
-          result << token
-          next
-        end
-        last = result.last
-        if last[:type] == token[:type]
-          new_token = {type: last[:type], value: last[:value] + token[:value]}
-          result.pop
-          result << new_token
-        else
-          result << token
-        end
-      end
-      result
-    end
-
-    def self.from_xml(xml : String) : Lexer
-      l = RegexLexer.new
-      lexer = XML.parse(xml).first_element_child
-      if lexer
-        config = lexer.children.find { |node|
-          node.name == "config"
-        }
-        if config
-          l.config = {
-            name:             xml_to_s(config, name) || "",
-            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",
-            case_insensitive: xml_to_s(config, case_insensitive) == "true",
-            ensure_nl:        xml_to_s(config, ensure_nl) == "true",
-          }
-        end
-
-        rules = lexer.children.find { |node|
-          node.name == "rules"
-        }
-        if rules
-          # Rules contains states 🤷
-          rules.children.select { |node|
-            node.name == "state"
-          }.each do |state_node|
-            state = State.new
-            state.name = state_node["name"]
-            if l.states.has_key?(state.name)
-              raise Exception.new("Duplicate state: #{state.name}")
-            else
-              l.states[state.name] = state
-            end
-            # And states contain rules 🤷
-            state_node.children.select { |node|
-              node.name == "rule"
-            }.each do |rule_node|
-              case rule_node["pattern"]?
-              when nil
-                if rule_node.first_element_child.try &.name == "include"
-                  rule = IncludeStateRule.new(rule_node)
-                else
-                  rule = UnconditionalRule.new(rule_node)
-                end
-              else
-                rule = Rule.new(rule_node,
-                  multiline: !l.config[:not_multiline],
-                  dotall: l.config[:dot_all],
-                  ignorecase: l.config[:case_insensitive])
-              end
-              state.rules << rule
-            end
-          end
-        end
-      end
-      l
-    end
-  end
-
-  # A lexer that takes two lexers as arguments. A root lexer
-  # and a language lexer. Everything is scalled using the
-  # language lexer, afterwards all `Other` tokens are lexed
-  # using the root lexer.
-  #
-  # This is useful for things like template languages, where
-  # you have Jinja + HTML or Jinja + CSS and so on.
-  class DelegatingLexer < Lexer
-    property language_lexer : BaseLexer
-    property root_lexer : BaseLexer
-
-    def initialize(@language_lexer : BaseLexer, @root_lexer : BaseLexer)
-    end
-
-    def tokenizer(text : String, secondary = false) : DelegatingTokenizer
-      DelegatingTokenizer.new(self, text, secondary)
-    end
-  end
-
-  # This Tokenizer works with a DelegatingLexer. It first tokenizes
-  # using the language lexer, and "Other" tokens are tokenized using
-  # the root lexer.
-  class DelegatingTokenizer < BaseTokenizer
-    include Iterator(Token)
-    @dq = Deque(Token).new
-    @language_tokenizer : BaseTokenizer
-
-    def initialize(@lexer : DelegatingLexer, 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
-      @language_tokenizer = @lexer.language_lexer.tokenizer(text, true)
-    end
-
-    def next : Iterator::Stop | Token
-      if @dq.size > 0
-        return @dq.shift
-      end
-      token = @language_tokenizer.next
-      if token.is_a? Iterator::Stop
-        return stop
-      elsif token.as(Token).[:type] == "Other"
-        root_tokenizer = @lexer.root_lexer.tokenizer(token.as(Token).[:value], true)
-        root_tokenizer.each do |root_token|
-          @dq << root_token
-        end
-      else
-        @dq << token.as(Token)
-      end
-      self.next
-    end
-  end
-
-  # 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.
-  struct State
-    property name : String = ""
-    property rules = [] of BaseRule
-
-    def +(other : State)
-      new_state = State.new
-      new_state.name = Random.base58(8)
-      new_state.rules = rules + other.rules
-      new_state
-    end
-  end
-
-  class CustomCrystalHighlighter < Crystal::SyntaxHighlighter
-    @tokens = [] of Token
-
-    def render_delimiter(&block)
-      @tokens << {type: "LiteralString", value: block.call.to_s}
-    end
-
-    def render_interpolation(&block)
-      @tokens << {type: "LiteralStringInterpol", value: "\#{"}
-      @tokens << {type: "Text", value: block.call.to_s}
-      @tokens << {type: "LiteralStringInterpol", value: "}"}
-    end
-
-    def render_string_array(&block)
-      @tokens << {type: "LiteralString", value: block.call.to_s}
-    end
-
-    # ameba:disable Metrics/CyclomaticComplexity
-    def render(type : TokenType, value : String)
-      case type
-      when .comment?
-        @tokens << {type: "Comment", value: value}
-      when .number?
-        @tokens << {type: "LiteralNumber", value: value}
-      when .char?
-        @tokens << {type: "LiteralStringChar", value: value}
-      when .symbol?
-        @tokens << {type: "LiteralStringSymbol", value: value}
-      when .const?
-        @tokens << {type: "NameConstant", value: value}
-      when .string?
-        @tokens << {type: "LiteralString", value: value}
-      when .ident?
-        @tokens << {type: "NameVariable", value: value}
-      when .keyword?, .self?
-        @tokens << {type: "NameKeyword", value: value}
-      when .primitive_literal?
-        @tokens << {type: "Literal", value: value}
-      when .operator?
-        @tokens << {type: "Operator", value: value}
-      when Crystal::SyntaxHighlighter::TokenType::DELIMITED_TOKEN, Crystal::SyntaxHighlighter::TokenType::DELIMITER_START, Crystal::SyntaxHighlighter::TokenType::DELIMITER_END
-        @tokens << {type: "LiteralString", value: value}
-      else
-        @tokens << {type: "Text", value: value}
-      end
-    end
-  end
-
-  class CrystalTokenizer < Tartrazine::BaseTokenizer
-    include Iterator(Token)
-    @hl = CustomCrystalHighlighter.new
-    @lexer : BaseLexer
-    @iter : Iterator(Token)
-
-    # delegate next, to: @iter
-
-    def initialize(@lexer : BaseLexer, 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
-      # Just do the tokenizing
-      @hl.highlight(text)
-      @iter = @hl.@tokens.each
-    end
-
-    def next : Iterator::Stop | Token
-      @iter.next
-    end
-  end
-
-  class CrystalLexer < BaseLexer
-    def tokenizer(text : String, secondary = false) : BaseTokenizer
-      CrystalTokenizer.new(self, text, secondary)
-    end
-  end
-end

spec/tartrazine_spec.cr

@@ -1,4 +1,5 @@
 require "./spec_helper"
+require "digest/sha1"
 
 # These are the testcases from Pygments
 testcases = Dir.glob("#{__DIR__}/tests/**/*txt").sort
@@ -103,6 +104,7 @@ describe Tartrazine do
       )
     end
   end
+
   describe "to_ansi" do
     it "should do basic highlighting" do
       ansi = Tartrazine.to_ansi("puts 'Hello, World!'", "ruby")
@@ -114,11 +116,29 @@ describe Tartrazine do
         )
       else
         ansi.should eq(
-          "\e[38;2;171;70;66mputs\e[0m\e[38;2;216;216;216m \e[0m'Hello, World!'"
+          "\e[38;2;171;70;66mputs\e[0m\e[38;2;216;216;216m \e[0m\e[38;2;161;181;108m'Hello, World!'\e[0m"
         )
       end
     end
   end
+
+  describe "to_svg" do
+    it "should do basic highlighting" do
+      svg = Tartrazine.to_svg("puts 'Hello, World!'", "ruby", standalone: false)
+      svg.should eq(
+        "<text x=\"0\" y=\"19\" xml:space=\"preserve\"><tspan fill=\"#ab4642\">puts</tspan><tspan fill=\"#d8d8d8\"> </tspan><tspan fill=\"#a1b56c\">&#39;Hello, World!&#39;</tspan></text>"
+      )
+    end
+  end
+
+  describe "to_png" do
+    it "should do basic highlighting" do
+      png = Digest::SHA1.hexdigest(Tartrazine.to_png("puts 'Hello, World!'", "ruby"))
+      png.should eq(
+        "62d419dcd263fffffc265a0f04c156dc2530c362"
+      )
+    end
+  end
 end
 
 # Helper that creates lexer and tokenizes

src/constants/lexers.cr

@@ -471,7 +471,7 @@ module Tartrazine
     "application/x-fennel"                        => "fennel",
     "application/x-fish"                          => "fish",
     "application/x-forth"                         => "forth",
-    "application/x-gdscript"                      => "gdscript",
+    "application/x-gdscript"                      => "gdscript3",
     "application/x-hcl"                           => "hcl",
     "application/x-hy"                            => "hy",
     "application/x-javascript"                    => "javascript",
@@ -594,7 +594,7 @@ module Tartrazine
     "text/x-fortran"                              => "fortran",
     "text/x-fsharp"                               => "fsharp",
     "text/x-gas"                                  => "gas",
-    "text/x-gdscript"                             => "gdscript",
+    "text/x-gdscript"                             => "gdscript3",
     "text/x-gherkin"                              => "gherkin",
     "text/x-gleam"                                => "gleam",
     "text/x-glslsrc"                              => "glsl",

src/formatter.cr

@@ -17,12 +17,19 @@ module Tartrazine
     end
 
     def format(text : String, lexer : Lexer) : String
-      raise Exception.new("Not implemented")
+      outp = String::Builder.new("")
+      format(text, lexer, outp)
+      outp.to_s
     end
 
     # Return the styles, if the formatter supports it.
     def style_defs : String
       raise Exception.new("Not implemented")
     end
+
+    # Is this line in the highlighted ranges?
+    def highlighted?(line : Int) : Bool
+      highlight_lines.any?(&.includes?(line))
+    end
   end
 end

src/formatters/ansi.cr

@@ -20,12 +20,6 @@ module Tartrazine
       "#{i + 1}".rjust(4).ljust(5)
     end
 
-    def format(text : String, lexer : BaseLexer) : String
-      outp = String::Builder.new("")
-      format(text, lexer, outp)
-      outp.to_s
-    end
-
     def format(text : String, lexer : BaseLexer, outp : IO) : Nil
       tokenizer = lexer.tokenizer(text)
       i = 0
@@ -40,8 +34,6 @@ module Tartrazine
     end
 
     def colorize(text : String, token : String) : String
-      style = theme.styles.fetch(token, nil)
-      return text if style.nil?
       if theme.styles.has_key?(token)
         s = theme.styles[token]
       else

src/formatters/html.cr

@@ -106,8 +106,7 @@ module Tartrazine
 
           # These are true/false/nil
           outp << "border: none;" if style.border == false
-          outp << "font-weight: bold;" if style.bold
+          outp << "font-weight: #{@weight_of_bold};" if style.bold
-          outp << "font-weight: #{@weight_of_bold};" if style.bold == false
           outp << "font-style: italic;" if style.italic
           outp << "font-style: normal;" if style.italic == false
           outp << "text-decoration: underline;" if style.underline
@@ -134,10 +133,5 @@ module Tartrazine
       end
       class_prefix + Abbreviations[token]
     end
-
-    # Is this line in the highlighted ranges?
-    def highlighted?(line : Int) : Bool
-      highlight_lines.any?(&.includes?(line))
-    end
   end
 end

src/formatters/png.cr

@@ -0,0 +1,117 @@
+require "../formatter"
+require "compress/gzip"
+require "digest/sha1"
+require "stumpy_png"
+require "stumpy_utils"
+
+module Tartrazine
+  def self.to_png(text : String, language : String,
+                  theme : String = "default-dark",
+                  line_numbers : Bool = false) : String
+    buf = IO::Memory.new
+
+    Tartrazine::Png.new(
+      theme: Tartrazine.theme(theme),
+      line_numbers: line_numbers
+    ).format(text, Tartrazine.lexer(name: language), buf)
+    buf.to_s
+  end
+
+  class FontFiles
+    extend BakedFileSystem
+    bake_folder "../../fonts", __DIR__
+  end
+
+  class Png < Formatter
+    include StumpyPNG
+    property? line_numbers : Bool = false
+    @font_regular : PCFParser::Font
+    @font_bold : PCFParser::Font
+    @font_oblique : PCFParser::Font
+    @font_bold_oblique : PCFParser::Font
+    @font_width = 15
+    @font_height = 24
+
+    def initialize(@theme : Theme = Tartrazine.theme("default-dark"), @line_numbers : Bool = false)
+      @font_regular = load_font("/courier-regular.pcf.gz")
+      @font_bold = load_font("/courier-bold.pcf.gz")
+      @font_oblique = load_font("/courier-oblique.pcf.gz")
+      @font_bold_oblique = load_font("/courier-bold-oblique.pcf.gz")
+    end
+
+    private def load_font(name : String) : PCFParser::Font
+      compressed = FontFiles.get(name)
+      uncompressed = Compress::Gzip::Reader.open(compressed) do |gzip|
+        gzip.gets_to_end
+      end
+      PCFParser::Font.new(IO::Memory.new uncompressed)
+    end
+
+    private def line_label(i : Int32) : String
+      "#{i + 1}".rjust(4).ljust(5)
+    end
+
+    def format(text : String, lexer : BaseLexer, outp : IO) : Nil
+      # Create canvas of correct size
+      lines = text.split("\n")
+      canvas_height = lines.size * @font_height
+      canvas_width = lines.max_of(&.size)
+      canvas_width += 5 if line_numbers?
+      canvas_width *= @font_width
+
+      bg_color = RGBA.from_hex("##{theme.styles["Background"].background.try &.hex}")
+      canvas = Canvas.new(canvas_width, canvas_height, bg_color)
+
+      tokenizer = lexer.tokenizer(text)
+      x = 0
+      y = @font_height
+      i = 0
+      if line_numbers?
+        canvas.text(x, y, line_label(i), @font_regular, RGBA.from_hex("##{theme.styles["Background"].color.try &.hex}"))
+        x += 5 * @font_width
+      end
+
+      tokenizer.each do |token|
+        font, color = token_style(token[:type])
+        # These fonts are very limited
+        t = token[:value].gsub(/[^[:ascii:]]/, "?")
+        canvas.text(x, y, t.rstrip("\n"), font, color)
+        if token[:value].includes?("\n")
+          x = 0
+          y += @font_height
+          i += 1
+          if line_numbers?
+            canvas.text(x, y, line_label(i), @font_regular, RGBA.from_hex("##{theme.styles["Background"].color.try &.hex}"))
+            x += 4 * @font_width
+          end
+        end
+
+        x += token[:value].size * @font_width
+      end
+
+      StumpyPNG.write(canvas, outp)
+    end
+
+    def token_style(token : String) : {PCFParser::Font, RGBA}
+      if theme.styles.has_key?(token)
+        s = theme.styles[token]
+      else
+        # 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.
+        s = theme.styles[theme.style_parents(token).reverse.find { |parent|
+          theme.styles.has_key?(parent)
+        }]
+      end
+
+      color = RGBA.from_hex("##{theme.styles["Background"].color.try &.hex}")
+      color = RGBA.from_hex("##{s.color.try &.hex}") if s.color
+
+      return {@font_bold_oblique, color} if s.bold && s.italic
+      return {@font_bold, color} if s.bold
+      return {@font_oblique, color} if s.italic
+      return {@font_regular, color}
+    end
+  end
+end

src/formatters/svg.cr

@@ -0,0 +1,129 @@
+require "../constants/token_abbrevs.cr"
+require "../formatter"
+require "html"
+
+module Tartrazine
+  def self.to_svg(text : String, language : String,
+                  theme : String = "default-dark",
+                  standalone : Bool = true,
+                  line_numbers : Bool = false) : String
+    Tartrazine::Svg.new(
+      theme: Tartrazine.theme(theme),
+      standalone: standalone,
+      line_numbers: line_numbers
+    ).format(text, Tartrazine.lexer(name: language))
+  end
+
+  class Svg < Formatter
+    property highlight_lines : Array(Range(Int32, Int32)) = [] of Range(Int32, Int32)
+    property line_number_id_prefix : String = "line-"
+    property line_number_start : Int32 = 1
+    property tab_width = 8
+    property? line_numbers : Bool = false
+    property? linkable_line_numbers : Bool = true
+    property? standalone : Bool = false
+    property weight_of_bold : Int32 = 600
+    property fs : Int32
+    property ystep : Int32
+
+    property theme : Theme
+
+    def initialize(@theme : Theme = Tartrazine.theme("default-dark"), *,
+                   @highlight_lines = [] of Range(Int32, Int32),
+                   @class_prefix : String = "",
+                   @line_number_id_prefix = "line-",
+                   @line_number_start = 1,
+                   @tab_width = 8,
+                   @line_numbers : Bool = false,
+                   @linkable_line_numbers : Bool = true,
+                   @standalone : Bool = false,
+                   @weight_of_bold : Int32 = 600,
+                   @font_family : String = "monospace",
+                   @font_size : String = "14px")
+      if font_size.ends_with? "px"
+        @fs = font_size[0...-2].to_i
+      else
+        @fs = font_size.to_i
+      end
+      @ystep = @fs + 5
+    end
+
+    def format(text : String, lexer : BaseLexer, io : IO) : Nil
+      pre, post = wrap_standalone
+      io << pre if standalone?
+      format_text(text, lexer, io)
+      io << post if standalone?
+    end
+
+    # Wrap text into a full HTML document, including the CSS for the theme
+    def wrap_standalone
+      output = String.build do |outp|
+        outp << %(<?xml version="1.0" encoding="utf-8"?>
+        <!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.0//EN" "http://www.w3.org/TR/2001/REC-SVG-20010904/DTD/svg10.dtd">
+        <svg xmlns="http://www.w3.org/2000/svg">
+        <g font-family="#{self.@font_family}" font-size="#{self.@font_size}">)
+      end
+      {output.to_s, "</g></svg>"}
+    end
+
+    private def line_label(i : Int32, x : Int32, y : Int32) : String
+      line_label = "#{i + 1}".rjust(4).ljust(5)
+      line_style = highlighted?(i + 1) ? "font-weight=\"#{@weight_of_bold}\"" : ""
+      line_id = linkable_line_numbers? ? "id=\"#{line_number_id_prefix}#{i + 1}\"" : ""
+      %(<text #{line_style} #{line_id}  x="#{4*ystep}" y="#{y}" text-anchor="end">#{line_label}</text>)
+    end
+
+    def format_text(text : String, lexer : BaseLexer, outp : IO)
+      x = 0
+      y = ystep
+      i = 0
+      line_x = x
+      line_x += 5 * ystep if line_numbers?
+      tokenizer = lexer.tokenizer(text)
+      outp << line_label(i, x, y) if line_numbers?
+      outp << %(<text x="#{line_x}" y="#{y}" xml:space="preserve">)
+      tokenizer.each do |token|
+        if token[:value].ends_with? "\n"
+          outp << "<tspan #{get_style(token[:type])}>#{HTML.escape(token[:value][0...-1])}</tspan>"
+          outp << "</text>"
+          x = 0
+          y += ystep
+          i += 1
+          outp << line_label(i, x, y) if line_numbers?
+          outp << %(<text x="#{line_x}" y="#{y}" xml:space="preserve">)
+        else
+          outp << "<tspan#{get_style(token[:type])}>#{HTML.escape(token[:value])}</tspan>"
+          x += token[:value].size * ystep
+        end
+      end
+      outp << "</text>"
+    end
+
+    # Given a token type, return the style.
+    def get_style(token : String) : String
+      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
+      output = String.build do |outp|
+        style = theme.styles[token]
+        outp << " fill=\"##{style.color.try &.hex}\"" if style.color
+        # No support for background color or border in SVG
+
+        outp << " font-weight=\"#{@weight_of_bold}\"" if style.bold
+        outp << " font-weight=\"normal\"" if style.bold == false
+        outp << " font-style=\"italic\"" if style.italic
+        outp << " font-style=\"normal\"" if style.italic == false
+        outp << " text-decoration=\"underline\"" if style.underline
+        outp << " text-decoration=\"none" if style.underline == false
+      end
+      output
+    end
+  end
+end

src/lexer.cr

@@ -6,11 +6,21 @@ require "crystal/syntax_highlighter"
 module Tartrazine
   class LexerFiles
     extend BakedFileSystem
-    bake_folder "../lexers", __DIR__
+
+    macro bake_selected_lexers
+      {% for lexer in env("TT_LEXERS").split "," %}
+      bake_file {{ lexer }}+".xml", {{ read_file "#{__DIR__}/../lexers/" + lexer + ".xml" }}
+      {% end %}
+    end
+
+    {% if flag?(:nolexers) %}
+      bake_selected_lexers
+    {% else %}
+      bake_folder "../lexers", __DIR__
+    {% end %}
   end
 
   # Get the lexer object for a language name
-  # FIXME: support mimetypes
   def self.lexer(name : String? = nil, filename : String? = nil, mimetype : String? = nil) : BaseLexer
     return lexer_by_name(name) if name && name != "autodetect"
     return lexer_by_filename(filename) if filename
@@ -33,6 +43,8 @@ module Tartrazine
     raise Exception.new("Unknown lexer: #{name}") if lexer_file_name.nil?
 
     RegexLexer.from_xml(LexerFiles.get("/#{lexer_file_name}.xml").gets_to_end)
+  rescue ex : BakedFileSystem::NoSuchFileError
+    raise Exception.new("Unknown lexer: #{name}")
   end
 
   private def self.lexer_by_filename(filename : String) : BaseLexer
@@ -84,7 +96,8 @@ module Tartrazine
 
   # Return a list of all lexers
   def self.lexers : Array(String)
-    LEXERS_BY_NAME.keys.sort!
+    file_map = LexerFiles.files.map(&.path)
+    LEXERS_BY_NAME.keys.select { |k| file_map.includes?("/#{k}.xml") }.sort!
   end
 
   # A token, the output of the tokenizer

src/main.cr

@@ -4,6 +4,10 @@ require "./tartrazine"
 HELP = <<-HELP
 tartrazine: a syntax highlighting tool
 
+You can use the CLI to generate HTML, terminal, JSON or SVG output
+from a source file using different themes.
+Keep in mind that not all formatters support all features.
+
 Usage:
   tartrazine (-h, --help)
   tartrazine FILE -f html [-t theme][--standalone][--line-numbers]
@@ -11,6 +15,10 @@ Usage:
   tartrazine -f html -t theme --css
   tartrazine FILE -f terminal [-t theme][-l lexer][--line-numbers]
                               [-o output]
+  tartrazine FILE -f svg  [-t theme][--standalone][--line-numbers]
+                          [-l lexer][-o output]
+  tartrazine FILE -f png  [-t theme][--line-numbers]
+                          [-l lexer][-o output]
   tartrazine FILE -f json [-o output]
   tartrazine --list-themes
   tartrazine --list-lexers
@@ -18,7 +26,7 @@ Usage:
   tartrazine --version
 
 Options:
-  -f <formatter>      Format to use (html, terminal, json)
+  -f <formatter>      Format to use (html, terminal, json, svg)
   -t <theme>          Theme to use, see --list-themes [default: default-dark]
   -l <lexer>          Lexer (language) to use, see --list-lexers. Use more than
                       one lexer with "+" (e.g. jinja+yaml) [default: autodetect]
@@ -71,6 +79,15 @@ if options["-f"]
     formatter.theme = theme
   when "json"
     formatter = Tartrazine::Json.new
+  when "svg"
+    formatter = Tartrazine::Svg.new
+    formatter.standalone = options["--standalone"] != nil
+    formatter.line_numbers = options["--line-numbers"] != nil
+    formatter.theme = theme
+  when "png"
+    formatter = Tartrazine::Png.new
+    formatter.line_numbers = options["--line-numbers"] != nil
+    formatter.theme = theme
   else
     puts "Invalid formatter: #{formatter}"
     exit 1

src/styles.cr

@@ -11,7 +11,20 @@ module Tartrazine
 
   struct ThemeFiles
     extend BakedFileSystem
-    bake_folder "../styles", __DIR__
+
+    macro bake_selected_themes
+      {% if env("TT_THEMES") %}
+      {% for theme in env("TT_THEMES").split "," %}
+      bake_file {{ theme }}+".xml", {{ read_file "#{__DIR__}/../styles/" + theme + ".xml" }}
+      {% end %}
+      {% end %}
+    end
+
+    {% if flag?(:nothemes) %}
+      bake_selected_themes
+    {% else %}
+      bake_folder "../styles", __DIR__
+    {% end %}
   end
 
   def self.theme(name : String) : Theme