fix: Don't log when falling back to ruby, it breaks stuff

Conditional lexers and themes

.ameba.yml

@@ -1,9 +1,9 @@
 # This configuration file was generated by `ameba --gen-config`
-# on 2024-08-12 22:00:49 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: 2
+# Problems found: 3
 # Run `ameba --only Documentation/DocumentationAdmonition` for details
 Documentation/DocumentationAdmonition:
   Description: Reports documentation admonitions
@@ -18,104 +18,17 @@ Documentation/DocumentationAdmonition:
   Enabled: true
   Severity: Warning
 
-# Problems found: 22
-# Run `ameba --only Lint/MissingBlockArgument` for details
-Lint/MissingBlockArgument:
-  Description: Disallows yielding method definitions without block argument
-  Excluded:
-  - pygments/tests/examplefiles/cr/test.cr
-  Enabled: true
-  Severity: Warning
-
 # Problems found: 1
-# Run `ameba --only Lint/NotNil` for details
-Lint/NotNil:
-  Description: Identifies usage of `not_nil!` calls
+# Run `ameba --only Lint/SpecFilename` for details
+Lint/SpecFilename:
+  Description: Enforces spec filenames to have `_spec` suffix
   Excluded:
-  - pygments/tests/examplefiles/cr/test.cr
+  - spec/examples/crystal/hello.cr
+  IgnoredDirs:
+  - spec/support
+  - spec/fixtures
+  - spec/data
+  IgnoredFilenames:
+  - spec_helper
   Enabled: true
   Severity: Warning
-
-# Problems found: 34
-# Run `ameba --only Lint/ShadowingOuterLocalVar` for details
-Lint/ShadowingOuterLocalVar:
-  Description: Disallows the usage of the same name as outer local variables for block
-    or proc arguments
-  Excluded:
-  - pygments/tests/examplefiles/cr/test.cr
-  Enabled: true
-  Severity: Warning
-
-# Problems found: 1
-# Run `ameba --only Lint/UnreachableCode` for details
-Lint/UnreachableCode:
-  Description: Reports unreachable code
-  Excluded:
-  - pygments/tests/examplefiles/cr/test.cr
-  Enabled: true
-  Severity: Warning
-
-# Problems found: 6
-# Run `ameba --only Lint/UselessAssign` for details
-Lint/UselessAssign:
-  Description: Disallows useless variable assignments
-  ExcludeTypeDeclarations: false
-  Excluded:
-  - pygments/tests/examplefiles/cr/test.cr
-  Enabled: true
-  Severity: Warning
-
-# Problems found: 3
-# Run `ameba --only Naming/BlockParameterName` for details
-Naming/BlockParameterName:
-  Description: Disallows non-descriptive block parameter names
-  MinNameLength: 3
-  AllowNamesEndingInNumbers: true
-  Excluded:
-  - pygments/tests/examplefiles/cr/test.cr
-  AllowedNames:
-  - _
-  - e
-  - i
-  - j
-  - k
-  - v
-  - x
-  - y
-  - ex
-  - io
-  - ws
-  - op
-  - tx
-  - id
-  - ip
-  - k1
-  - k2
-  - v1
-  - v2
-  ForbiddenNames: []
-  Enabled: true
-  Severity: Convention
-
-# Problems found: 1
-# Run `ameba --only Naming/RescuedExceptionsVariableName` for details
-Naming/RescuedExceptionsVariableName:
-  Description: Makes sure that rescued exceptions variables are named as expected
-  Excluded:
-  - pygments/tests/examplefiles/cr/test.cr
-  AllowedNames:
-  - e
-  - ex
-  - exception
-  - error
-  Enabled: true
-  Severity: Convention
-
-# Problems found: 6
-# Run `ameba --only Naming/TypeNames` for details
-Naming/TypeNames:
-  Description: Enforces type names in camelcase manner
-  Excluded:
-  - pygments/tests/examplefiles/cr/test.cr
-  Enabled: true
-  Severity: Convention

.github/workflows/ci.yml

@@ -9,7 +9,7 @@ permissions:
   contents: read
 jobs:
   build:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-22.04
     steps:
       - name: Download source
         uses: actions/checkout@v4

.github/workflows/coverage.yml

@@ -7,7 +7,7 @@ permissions:
   contents: read
 jobs:
   build:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-22.04
     steps:
       - name: Download source
         uses: actions/checkout@v4
@@ -15,7 +15,7 @@ jobs:
         uses: crystal-lang/install-crystal@v1
       - name: Run tests using kcov
         run: |
-          sudo apt update && sudo apt install kcov
+          sudo apt update && sudo apt upgrade && sudo apt install -y kcov
           wget https://github.com/alecthomas/chroma/releases/download/v2.14.0/chroma-2.14.0-linux-amd64.tar.gz
           tar xzvf chroma-2.14.0*gz
           mkdir ~/.local/bin -p

.gitignore

@@ -12,3 +12,6 @@ venv/
 .croupier
 coverage/
 run_tests
+
+# We use the internal crystal lexer
+lexers/crystal.xml

CHANGELOG.md

@@ -2,17 +2,113 @@
 
 All notable changes to this project will be documented in this file.
 
-## [0.6.4] - 2024-08-28
+## [0.12.0] - 2025-01-21
+
+### 🚀 Features
+
+- Bumped to latest chroma release
+
+### ⚙️ Miscellaneous Tasks
+
+- Pin ubuntu version in CI
+- Mark more mcfunction tests as bad
+
+### Build
+
+- Automate AUR release
+
+## [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
+
+- Higher level API (`to_html` and `to_ansi`)
+- Use the native crystal highlighter
 
 ### 🐛 Bug Fixes
 
 - Ameba
 - Variable bame in Hacefile
+- Make it easier to import the Ansi formatter
+- Renamed BaseLexer to Lexer and Lexer to RegexLexer to make API nicer
+- Make install work
 
 ### 📚 Documentation
 
 - Mention AUR package
 
+### 🧪 Testing
+
+- Add CI workflows
+
 ### ⚙️ Miscellaneous Tasks
 
 - Pre-commit hooks
@@ -21,6 +117,10 @@ All notable changes to this project will be documented in this file.
 - Force conventional commit messages
 - Force conventional commit messages
 - Updated pre-commit
+- *(ignore)* Fix tests
+- Added badges
+- Added badges
+- *(ignore)* Removed random file
 
 ### Build
 
@@ -30,6 +130,7 @@ All notable changes to this project will be documented in this file.
 
 ### Bump
 
+- Release v0.6.4
 - Release v0.6.4
 
 ## [0.6.1] - 2024-08-25

Hacefile.yml

@@ -113,3 +113,25 @@ tasks:
       kcov --clean --include-path=./src ${PWD}/coverage ./bin/run_tests
     outputs:
       - coverage/index.html
+
+  loc:
+    phony: true
+    always_run: true
+    dependencies:
+      - src
+    commands: |
+      tokei src -e src/constants/
+
+  aur:
+    phony: true
+    always_run: true
+    commands: |
+      rm -rf aur-{{NAME}}
+      git clone ssh://aur@aur.archlinux.org/{{NAME}}.git aur-{{NAME}}
+      sed s/pkgver=.*/pkgver=$(shards version)/ -i aur-{{NAME}}/PKGBUILD
+      sed s/pkgrel=.*/pkgrel=1/ -i aur-{{NAME}}/PKGBUILD
+      cd aur-{{NAME}} && updpkgsums && makepkg --printsrcinfo > .SRCINFO
+      cd aur-{{NAME}} && makepkg -fsr
+      cd aur-{{NAME}} && git add PKGBUILD .SRCINFO
+      cd aur-{{NAME}} && git commit -a -m "Update to $(shards version)"
+      cd aur-{{NAME}} && git push

README.md

@@ -45,6 +45,14 @@ $ tartrazine whatever.c -t catppuccin-macchiato --line-numbers \
 
 ## Usage as a Library
 
+Add to your `shard.yml`:
+
+```yaml
+dependencies:
+  tartrazine:
+    github: ralsina/tartrazine
+```
+
 This is the high level API:
 
 ```crystal
@@ -63,7 +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,
@@ -74,6 +82,78 @@ 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.
+
+## Templates for standalone HTML output
+
+If you are using the HTML formatter, you can pass a template to use for the output. The template is a string where the following placeholders will be replaced:
+
+* `{{style_defs}}` will be replaced by the CSS styles needed for the theme
+* `{{code}}` will be replaced by the highlighted code
+
+This is an example template that changes the padding around the code:
+
+```jinja2
+<!DOCTYPE html>
+<html>
+  <head>
+    <style>
+      {{style_defs}}
+      pre {
+      padding: 1em;
+      }
+    </style>
+  </head>
+  <body>
+    {{body}}
+  </body>
+</html>
+```
+
+
 ## 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

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)"

lexers/atl.xml

@@ -0,0 +1,165 @@
+<lexer>
+  <config>
+    <name>ATL</name>
+    <alias>atl</alias>
+    <filename>*.atl</filename>
+    <mime_type>text/x-atl</mime_type>
+    <dot_all>true</dot_all>
+  </config>
+  <rules>
+    <state name="root">
+      <rule pattern="(--.*?)(\n)">
+        <bygroups>
+          <token type="CommentSingle" />
+          <token type="TextWhitespace" />
+        </bygroups>
+      </rule>
+      <rule pattern="(and|distinct|endif|else|for|foreach|if|implies|in|let|not|or|self|super|then|thisModule|xor)\b">
+        <token type="Keyword" />
+      </rule>
+      <rule pattern="(OclUndefined|true|false|#\w+)\b">
+        <token type="KeywordConstant" />
+      </rule>
+      <rule pattern="(module|query|library|create|from|to|uses)\b">
+         <token type="KeywordNamespace" />
+      </rule>
+      <rule pattern="(do)(\s*)({)">
+        <bygroups>
+          <token type="KeywordNamespace" />
+          <token type="TextWhitespace" />
+          <token type="Punctuation" />
+        </bygroups>
+      </rule>
+      <rule pattern="(abstract|endpoint|entrypoint|lazy|unique)(\s+)">
+        <bygroups>
+          <token type="KeywordDeclaration" />
+          <token type="TextWhitespace" />
+        </bygroups>
+      </rule>
+      <rule pattern="(rule)(\s+)">
+        <bygroups>
+          <token type="KeywordNamespace" />
+          <token type="TextWhitespace" />
+        </bygroups>
+      </rule>
+      <rule pattern="(helper)(\s+)">
+        <bygroups>
+          <token type="KeywordNamespace" />
+          <token type="TextWhitespace" />
+        </bygroups>
+      </rule>
+      <rule pattern="(context)(\s+)">
+        <bygroups>
+          <token type="KeywordNamespace" />
+          <token type="TextWhitespace" />
+        </bygroups>
+      </rule>
+      <rule pattern="(def)(\s*)(:)(\s*)">
+        <bygroups>
+          <token type="KeywordNamespace" />
+          <token type="TextWhitespace" />
+          <token type="Punctuation" />
+          <token type="TextWhitespace" />
+        </bygroups>
+      </rule>
+      <rule pattern="(Bag|Boolean|Integer|OrderedSet|Real|Sequence|Set|String|Tuple)">
+        <token type="KeywordType" />
+      </rule>
+      <rule pattern="(\w+)(\s*)(&lt;-|&lt;:=)">
+        <bygroups>
+          <token type="NameNamespace" />
+          <token type="TextWhitespace" />
+          <token type="Punctuation" />
+        </bygroups>
+      </rule>
+      <rule pattern="#&quot;">
+        <token type="KeywordConstant" />
+        <push state="quotedenumliteral" />
+      </rule>
+      <rule pattern="&quot;">
+        <token type="NameNamespace" />
+        <push state="quotedname" />
+      </rule>
+      <rule pattern="[^\S\n]+">
+        <token type="TextWhitespace" />
+      </rule>
+      <rule pattern="&#x27;">
+        <token type="LiteralString" />
+        <push state="string" />
+      </rule>
+      <rule
+        pattern="[0-9]*\.[0-9]+">
+        <token type="LiteralNumberFloat" />
+      </rule>
+      <rule pattern="0|[1-9][0-9]*">
+        <token type="LiteralNumberInteger" />
+      </rule>
+      <rule pattern="[*&lt;&gt;+=/-]">
+        <token type="Operator" />
+      </rule>
+      <rule pattern="([{}();:.,!|]|-&gt;)">
+        <token type="Punctuation" />
+      </rule>
+      <rule pattern="\n">
+        <token type="TextWhitespace" />
+      </rule>
+      <rule pattern="\w+">
+        <token type="NameNamespace" />
+      </rule>
+    </state>
+    <state name="string">
+      <rule pattern="[^\\&#x27;]+">
+        <token type="LiteralString" />
+      </rule>
+      <rule pattern="\\\\">
+        <token type="LiteralString" />
+      </rule>
+      <rule pattern="\\&#x27;">
+        <token type="LiteralString" />
+      </rule>
+      <rule pattern="\\">
+        <token type="LiteralString" />
+      </rule>
+      <rule pattern="&#x27;">
+        <token type="LiteralString" />
+        <pop depth="1" />
+      </rule>
+    </state>
+    <state name="quotedname">
+      <rule pattern="[^\\&quot;]+">
+        <token type="NameNamespace" />
+      </rule>
+      <rule pattern="\\\\">
+        <token type="NameNamespace" />
+      </rule>
+      <rule pattern="\\&quot;">
+        <token type="NameNamespace" />
+      </rule>
+      <rule pattern="\\">
+        <token type="NameNamespace" />
+      </rule>
+      <rule pattern="&quot;">
+        <token type="NameNamespace" />
+        <pop depth="1" />
+      </rule>
+    </state>
+    <state name="quotedenumliteral">
+      <rule pattern="[^\\&quot;]+">
+        <token type="KeywordConstant" />
+      </rule>
+      <rule pattern="\\\\">
+        <token type="KeywordConstant" />
+      </rule>
+      <rule pattern="\\&quot;">
+        <token type="KeywordConstant" />
+      </rule>
+      <rule pattern="\\">
+        <token type="KeywordConstant" />
+      </rule>
+      <rule pattern="&quot;">
+        <token type="KeywordConstant" />
+        <pop depth="1" />
+      </rule>
+    </state>
+  </rules>
+</lexer>

lexers/beef.xml

@@ -0,0 +1,120 @@
+<lexer>
+  <config>
+    <name>Beef</name>
+    <alias>beef</alias>
+    <filename>*.bf</filename>
+    <mime_type>text/x-beef</mime_type>
+    <dot_all>true</dot_all>
+    <ensure_nl>true</ensure_nl>
+  </config>
+  <rules>
+    <state name="root">
+      <rule pattern="^\s*\[.*?\]">
+        <token type="NameAttribute"/>
+      </rule>
+      <rule pattern="[^\S\n]+">
+        <token type="Text"/>
+      </rule>
+      <rule pattern="\\\n">
+        <token type="Text"/>
+      </rule>
+      <rule pattern="///[^\n\r]*">
+        <token type="CommentSpecial"/>
+      </rule>
+      <rule pattern="//[^\n\r]*">
+        <token type="CommentSingle"/>
+      </rule>
+      <rule pattern="/[*].*?[*]/">
+        <token type="CommentMultiline"/>
+      </rule>
+      <rule pattern="\n">
+        <token type="Text"/>
+      </rule>
+      <rule pattern="[~!%^&amp;*()+=|\[\]:;,.&lt;&gt;/?-]">
+        <token type="Punctuation"/>
+      </rule>
+      <rule pattern="[{}]">
+        <token type="Punctuation"/>
+      </rule>
+      <rule pattern="@&#34;(&#34;&#34;|[^&#34;])*&#34;">
+        <token type="LiteralString"/>
+      </rule>
+      <rule pattern="\$@?&#34;(&#34;&#34;|[^&#34;])*&#34;">
+        <token type="LiteralString"/>
+      </rule>
+      <rule pattern="&#34;(\\\\|\\&#34;|[^&#34;\n])*[&#34;\n]">
+        <token type="LiteralString"/>
+      </rule>
+      <rule pattern="&#39;\\.&#39;|&#39;[^\\]&#39;">
+        <token type="LiteralStringChar"/>
+      </rule>
+      <rule pattern="0[xX][0-9a-fA-F]+[Ll]?|\d[_\d]*(\.\d*)?([eE][+-]?\d+)?[flFLdD]?">
+        <token type="LiteralNumber"/>
+      </rule>
+      <rule pattern="#[ \t]*(if|endif|else|elif|define|undef|line|error|warning|region|endregion|pragma|nullable)\b">
+        <token type="CommentPreproc"/>
+      </rule>
+      <rule pattern="\b(extern)(\s+)(alias)\b">
+        <bygroups>
+          <token type="Keyword"/>
+          <token type="Text"/>
+          <token type="Keyword"/>
+        </bygroups>
+      </rule>
+      <rule pattern="(as|await|base|break|by|case|catch|checked|continue|default|delegate|else|event|finally|fixed|for|repeat|goto|if|in|init|is|let|lock|new|scope|on|out|params|readonly|ref|return|sizeof|stackalloc|switch|this|throw|try|typeof|unchecked|virtual|void|while|get|set|new|yield|add|remove|value|alias|ascending|descending|from|group|into|orderby|select|thenby|where|join|equals)\b">
+        <token type="Keyword"/>
+      </rule>
+      <rule pattern="(global)(::)">
+        <bygroups>
+          <token type="Keyword"/>
+          <token type="Punctuation"/>
+        </bygroups>
+      </rule>
+      <rule pattern="(abstract|async|const|enum|explicit|extern|implicit|internal|operator|override|partial|extension|private|protected|public|static|sealed|unsafe|volatile)\b">
+        <token type="KeywordDeclaration"/>
+      </rule>
+      <rule pattern="(bool|byte|char8|char16|char32|decimal|double|float|int|int8|int16|int32|int64|long|object|sbyte|short|string|uint|uint8|uint16|uint32|uint64|uint|let|var)\b\??">
+        <token type="KeywordType"/>
+      </rule>
+      <rule pattern="(true|false|null)\b">
+        <token type="KeywordConstant"/>
+      </rule>
+      <rule pattern="(class|struct|record|interface)(\s+)">
+        <bygroups>
+          <token type="Keyword"/>
+          <token type="Text"/>
+        </bygroups>
+        <push state="class"/>
+      </rule>
+      <rule pattern="(namespace|using)(\s+)">
+        <bygroups>
+          <token type="Keyword"/>
+          <token type="Text"/>
+        </bygroups>
+        <push state="namespace"/>
+      </rule>
+      <rule pattern="@?[_a-zA-Z]\w*">
+        <token type="Name"/>
+      </rule>
+    </state>
+    <state name="class">
+      <rule pattern="@?[_a-zA-Z]\w*">
+        <token type="NameClass"/>
+        <pop depth="1"/>
+      </rule>
+      <rule>
+        <pop depth="1"/>
+      </rule>
+    </state>
+    <state name="namespace">
+      <rule pattern="(?=\()">
+        <token type="Text"/>
+        <pop depth="1"/>
+      </rule>
+      <rule pattern="(@?[_a-zA-Z]\w*|\.)+">
+        <token type="NameNamespace"/>
+        <pop depth="1"/>
+      </rule>
+    </state>
+  </rules>
+</lexer>

lexers/csv.xml

@@ -0,0 +1,53 @@
+<!--
+Lexer for RFC-4180 compliant CSV subject to the following additions:
+- UTF-8 encoding is accepted (the RFC requires 7-bit ASCII)
+- The line terminator character can be LF or CRLF (the RFC allows CRLF only)
+
+Link to the RFC-4180 specification: https://tools.ietf.org/html/rfc4180
+
+Additions inspired by:
+https://github.com/frictionlessdata/datapackage/issues/204#issuecomment-193242077
+
+Future improvements:
+- Identify non-quoted numbers as LiteralNumber
+- Identify y as an error in "x"y. Currently it's identified as another string
+  literal.
+-->
+
+<lexer>
+    <config>
+        <name>CSV</name>
+        <alias>csv</alias>
+        <filename>*.csv</filename>
+        <mime_type>text/csv</mime_type>
+    </config>
+    <rules>
+        <state name="root">
+            <rule pattern="\r?\n">
+                <token type="Punctuation" />
+            </rule>
+            <rule pattern=",">
+                <token type="Punctuation" />
+            </rule>
+            <rule pattern="&quot;">
+                <token type="LiteralStringDouble" />
+                <push state="escaped" />
+            </rule>
+            <rule pattern="[^\r\n,]+">
+                <token type="LiteralString" />
+            </rule>
+        </state>
+        <state name="escaped">
+            <rule pattern="&quot;&quot;">
+                <token type="LiteralStringEscape"/>
+            </rule>
+            <rule pattern="&quot;">
+                <token type="LiteralStringDouble" />
+                <pop depth="1"/>
+            </rule>
+            <rule pattern="[^&quot;]+">
+                <token type="LiteralStringDouble" />
+            </rule>
+        </state>
+    </rules>
+</lexer>

lexers/groff.xml

@@ -3,7 +3,6 @@
     <name>Groff</name>
     <alias>groff</alias>
     <alias>nroff</alias>
-    <alias>roff</alias>
     <alias>man</alias>
     <filename>*.[1-9]</filename>
     <filename>*.1p</filename>

lexers/haskell.xml

@@ -95,19 +95,22 @@
       <rule pattern="[:!#$%&amp;*+.\\/&lt;=&gt;?@^|~-]+">
         <token type="Operator"/>
       </rule>
-      <rule pattern="\d+[eE][+-]?\d+">
+      <rule pattern="\d+_*[eE][+-]?\d+">
         <token type="LiteralNumberFloat"/>
       </rule>
-      <rule pattern="\d+\.\d+([eE][+-]?\d+)?">
+      <rule pattern="\d+(_+[\d]+)*\.\d+(_+[\d]+)*([eE][+-]?\d+)?">
         <token type="LiteralNumberFloat"/>
       </rule>
-      <rule pattern="0[oO][0-7]+">
+      <rule pattern="0[oO](_*[0-7])+">
         <token type="LiteralNumberOct"/>
       </rule>
-      <rule pattern="0[xX][\da-fA-F]+">
+      <rule pattern="0[xX](_*[\da-fA-F])+">
         <token type="LiteralNumberHex"/>
       </rule>
-      <rule pattern="\d+">
+      <rule pattern="0[bB](_*[01])+">
+        <token type="LiteralNumberBin"/>
+      </rule>
+      <rule pattern="\d+(_*[\d])*">
         <token type="LiteralNumberInteger"/>
       </rule>
       <rule pattern="&#39;">

lexers/json.xml

@@ -3,6 +3,7 @@
     <name>JSON</name>
     <alias>json</alias>
     <filename>*.json</filename>
+    <filename>*.jsonc</filename>
     <filename>*.avsc</filename>
     <mime_type>application/json</mime_type>
     <dot_all>true</dot_all>

lexers/jsonnet.xml

@@ -0,0 +1,137 @@
+
+<lexer>
+  <config>
+    <name>Jsonnet</name>
+    <alias>jsonnet</alias>
+    <filename>*.jsonnet</filename>
+    <filename>*.libsonnet</filename>
+  </config>
+  <rules>
+    <state name="_comments">
+      <rule pattern="(//|#).*\n"><token type="CommentSingle"/></rule>
+      <rule pattern="/\*\*([^/]|/(?!\*))*\*/"><token type="LiteralStringDoc"/></rule>
+      <rule pattern="/\*([^/]|/(?!\*))*\*/"><token type="Comment"/></rule>
+    </state>
+    <state name="root">
+      <rule><include state="_comments"/></rule>
+      <rule pattern="@&#x27;.*&#x27;"><token type="LiteralString"/></rule>
+      <rule pattern="@&quot;.*&quot;"><token type="LiteralString"/></rule>
+      <rule pattern="&#x27;"><token type="LiteralString"/><push state="singlestring"/></rule>
+      <rule pattern="&quot;"><token type="LiteralString"/><push state="doublestring"/></rule>
+      <rule pattern="\|\|\|(.|\n)*\|\|\|"><token type="LiteralString"/></rule>
+      <rule pattern="[+-]?[0-9]+(.[0-9])?"><token type="LiteralNumberFloat"/></rule>
+      <rule pattern="[!$~+\-&amp;|^=&lt;&gt;*/%]"><token type="Operator"/></rule>
+      <rule pattern="\{"><token type="Punctuation"/><push state="object"/></rule>
+      <rule pattern="\["><token type="Punctuation"/><push state="array"/></rule>
+      <rule pattern="local\b"><token type="Keyword"/><push state="local_name"/></rule>
+      <rule pattern="assert\b"><token type="Keyword"/><push state="assert"/></rule>
+      <rule pattern="(assert|else|error|false|for|if|import|importstr|in|null|tailstrict|then|self|super|true)\b"><token type="Keyword"/></rule>
+      <rule pattern="\s+"><token type="TextWhitespace"/></rule>
+      <rule pattern="function(?=\()"><token type="Keyword"/><push state="function_params"/></rule>
+      <rule pattern="std\.[^\W\d]\w*(?=\()"><token type="NameBuiltin"/><push state="function_args"/></rule>
+      <rule pattern="[^\W\d]\w*(?=\()"><token type="NameFunction"/><push state="function_args"/></rule>
+      <rule pattern="[^\W\d]\w*"><token type="NameVariable"/></rule>
+      <rule pattern="[\.()]"><token type="Punctuation"/></rule>
+    </state>
+    <state name="singlestring">
+      <rule pattern="[^&#x27;\\]"><token type="LiteralString"/></rule>
+      <rule pattern="\\."><token type="LiteralStringEscape"/></rule>
+      <rule pattern="&#x27;"><token type="LiteralString"/><pop depth="1"/></rule>
+    </state>
+    <state name="doublestring">
+      <rule pattern="[^&quot;\\]"><token type="LiteralString"/></rule>
+      <rule pattern="\\."><token type="LiteralStringEscape"/></rule>
+      <rule pattern="&quot;"><token type="LiteralString"/><pop depth="1"/></rule>
+    </state>
+    <state name="array">
+      <rule pattern=","><token type="Punctuation"/></rule>
+      <rule pattern="\]"><token type="Punctuation"/><pop depth="1"/></rule>
+      <rule><include state="root"/></rule>
+    </state>
+    <state name="local_name">
+      <rule pattern="[^\W\d]\w*(?=\()"><token type="NameFunction"/><push state="function_params"/></rule>
+      <rule pattern="[^\W\d]\w*"><token type="NameVariable"/></rule>
+      <rule pattern="\s+"><token type="TextWhitespace"/></rule>
+      <rule pattern="(?==)"><token type="TextWhitespace"/><push state="#pop" state="local_value"/></rule>
+    </state>
+    <state name="local_value">
+      <rule pattern="="><token type="Operator"/></rule>
+      <rule pattern=";"><token type="Punctuation"/><pop depth="1"/></rule>
+      <rule><include state="root"/></rule>
+    </state>
+    <state name="assert">
+      <rule pattern=":"><token type="Punctuation"/></rule>
+      <rule pattern=";"><token type="Punctuation"/><pop depth="1"/></rule>
+      <rule><include state="root"/></rule>
+    </state>
+    <state name="function_params">
+      <rule pattern="[^\W\d]\w*"><token type="NameVariable"/></rule>
+      <rule pattern="\("><token type="Punctuation"/></rule>
+      <rule pattern="\)"><token type="Punctuation"/><pop depth="1"/></rule>
+      <rule pattern=","><token type="Punctuation"/></rule>
+      <rule pattern="\s+"><token type="TextWhitespace"/></rule>
+      <rule pattern="="><token type="Operator"/><push state="function_param_default"/></rule>
+    </state>
+    <state name="function_args">
+      <rule pattern="\("><token type="Punctuation"/></rule>
+      <rule pattern="\)"><token type="Punctuation"/><pop depth="1"/></rule>
+      <rule pattern=","><token type="Punctuation"/></rule>
+      <rule pattern="\s+"><token type="TextWhitespace"/></rule>
+      <rule><include state="root"/></rule>
+    </state>
+    <state name="object">
+      <rule pattern="\s+"><token type="TextWhitespace"/></rule>
+      <rule pattern="local\b"><token type="Keyword"/><push state="object_local_name"/></rule>
+      <rule pattern="assert\b"><token type="Keyword"/><push state="object_assert"/></rule>
+      <rule pattern="\["><token type="Operator"/><push state="field_name_expr"/></rule>
+      <rule pattern="(?=[^\W\d]\w*)"><token type="Text"/><push state="field_name"/></rule>
+      <rule pattern="\}"><token type="Punctuation"/><pop depth="1"/></rule>
+      <rule pattern="&quot;"><token type="NameVariable"/><push state="double_field_name"/></rule>
+      <rule pattern="&#x27;"><token type="NameVariable"/><push state="single_field_name"/></rule>
+      <rule><include state="_comments"/></rule>
+    </state>
+    <state name="field_name">
+      <rule pattern="[^\W\d]\w*(?=\()"><token type="NameFunction"/><push state="field_separator" state="function_params"/></rule>
+      <rule pattern="[^\W\d]\w*"><token type="NameVariable"/><push state="field_separator"/></rule>
+    </state>
+    <state name="double_field_name">
+      <rule pattern="([^&quot;\\]|\\.)*&quot;"><token type="NameVariable"/><push state="field_separator"/></rule>
+    </state>
+    <state name="single_field_name">
+      <rule pattern="([^&#x27;\\]|\\.)*&#x27;"><token type="NameVariable"/><push state="field_separator"/></rule>
+    </state>
+    <state name="field_name_expr">
+      <rule pattern="\]"><token type="Operator"/><push state="field_separator"/></rule>
+      <rule><include state="root"/></rule>
+    </state>
+    <state name="function_param_default">
+      <rule pattern="(?=[,\)])"><token type="TextWhitespace"/><pop depth="1"/></rule>
+      <rule><include state="root"/></rule>
+    </state>
+    <state name="field_separator">
+      <rule pattern="\s+"><token type="TextWhitespace"/></rule>
+      <rule pattern="\+?::?:?"><token type="Punctuation"/><push state="#pop" state="#pop" state="field_value"/></rule>
+      <rule><include state="_comments"/></rule>
+    </state>
+    <state name="field_value">
+      <rule pattern=","><token type="Punctuation"/><pop depth="1"/></rule>
+      <rule pattern="\}"><token type="Punctuation"/><pop depth="2"/></rule>
+      <rule><include state="root"/></rule>
+    </state>
+    <state name="object_assert">
+      <rule pattern=":"><token type="Punctuation"/></rule>
+      <rule pattern=","><token type="Punctuation"/><pop depth="1"/></rule>
+      <rule><include state="root"/></rule>
+    </state>
+    <state name="object_local_name">
+      <rule pattern="[^\W\d]\w*"><token type="NameVariable"/><push state="#pop" state="object_local_value"/></rule>
+      <rule pattern="\s+"><token type="TextWhitespace"/></rule>
+    </state>
+    <state name="object_local_value">
+      <rule pattern="="><token type="Operator"/></rule>
+      <rule pattern=","><token type="Punctuation"/><pop depth="1"/></rule>
+      <rule pattern="\}"><token type="Punctuation"/><pop depth="2"/></rule>
+      <rule><include state="root"/></rule>
+    </state>
+  </rules>
+</lexer>

lexers/materialize_sql_dialect.xml

@@ -45,7 +45,7 @@
           </emitters>
         </usingbygroup>
       </rule>
-      <rule pattern="(ACCESS|ADD|ADDRESSES|AGGREGATE|ALIGNED|ALL|ALTER|ANALYSIS|AND|ANY|ARITY|ARN|ARRANGEMENT|ARRAY|AS|ASC|ASSERT|ASSUME|AT|AUCTION|AUTHORITY|AVAILABILITY|AVRO|AWS|BATCH|BEGIN|BETWEEN|BIGINT|BILLED|BODY|BOOLEAN|BOTH|BPCHAR|BROKEN|BROKER|BROKERS|BY|BYTES|CARDINALITY|CASCADE|CASE|CAST|CERTIFICATE|CHAIN|CHAINS|CHAR|CHARACTER|CHARACTERISTICS|CHECK|CLIENT|CLOSE|CLUSTER|CLUSTERS|COALESCE|COLLATE|COLUMN|COLUMNS|COMMENT|COMMIT|COMMITTED|COMPACTION|COMPATIBILITY|COMPRESSION|COMPUTE|COMPUTECTL|CONFIG|CONFLUENT|CONNECTION|CONNECTIONS|CONSTRAINT|COPY|COUNT|COUNTER|CREATE|CREATECLUSTER|CREATEDB|CREATEROLE|CREATION|CROSS|CSV|CURRENT|CURSOR|DATABASE|DATABASES|DATUMS|DAY|DAYS|DEALLOCATE|DEBEZIUM|DEBUG|DEBUGGING|DEC|DECIMAL|DECLARE|DECODING|DECORRELATED|DEFAULT|DEFAULTS|DELETE|DELIMITED|DELIMITER|DELTA|DESC|DETAILS|DISCARD|DISK|DISTINCT|DOC|DOT|DOUBLE|DROP|EAGER|ELEMENT|ELSE|ENABLE|END|ENDPOINT|ENFORCED|ENVELOPE|ERROR|ERRORS|ESCAPE|ESTIMATE|EVERY|EXCEPT|EXECUTE|EXISTS|EXPECTED|EXPLAIN|EXPOSE|EXPRESSIONS|EXTERNAL|EXTRACT|FACTOR|FALSE|FAST|FEATURES|FETCH|FIELDS|FILE|FILTER|FIRST|FIXPOINT|FLOAT|FOLLOWING|FOR|FOREIGN|FORMAT|FORWARD|FROM|FULL|FULLNAME|FUNCTION|GENERATOR|GRANT|GREATEST|GROUP|GROUPS|HAVING|HEADER|HEADERS|HISTORY|HOLD|HOST|HOUR|HOURS|HUMANIZED|ID|IDENTIFIERS|IDS|IF|IGNORE|ILIKE|IMPLEMENTATIONS|IMPORTED|IN|INCLUDE|INDEX|INDEXES|INFO|INHERIT|INLINE|INNER|INPUT|INSERT|INSIGHTS|INSPECT|INT|INTEGER|INTERNAL|INTERSECT|INTERVAL|INTO|INTROSPECTION|IS|ISNULL|ISOLATION|JOIN|JOINS|JSON|KAFKA|KEY|KEYS|LAST|LATERAL|LATEST|LEADING|LEAST|LEFT|LEGACY|LETREC|LEVEL|LIKE|LIMIT|LINEAR|LIST|LOAD|LOCAL|LOCALLY|LOG|LOGICAL|LOGIN|LOWERING|MANAGED|MANUAL|MAP|MARKETING|MATERIALIZE|MATERIALIZED|MAX|MECHANISMS|MEMBERSHIP|MESSAGE|METADATA|MINUTE|MINUTES|MODE|MONTH|MONTHS|MUTUALLY|MYSQL|NAME|NAMES|NATURAL|NEGATIVE|NEW|NEXT|NO|NOCREATECLUSTER|NOCREATEDB|NOCREATEROLE|NODE|NOINHERIT|NOLOGIN|NON|NONE|NOSUPERUSER|NOT|NOTICE|NOTICES|NULL|NULLIF|NULLS|OBJECTS|OF|OFFSET|ON|ONLY|OPERATOR|OPTIMIZED|OPTIMIZER|OPTIONS|OR|ORDER|ORDINALITY|OUTER|OVER|OWNED|OWNER|PARTITION|PARTITIONS|PASSWORD|PATH|PHYSICAL|PLAN|PLANS|PORT|POSITION|POSTGRES|PRECEDING|PRECISION|PREFIX|PREPARE|PRIMARY|PRIVATELINK|PRIVILEGES|PROGRESS|PROTOBUF|PROTOCOL|PUBLICATION|PUSHDOWN|QUERY|QUOTE|RAISE|RANGE|RATE|RAW|READ|REAL|REASSIGN|RECURSION|RECURSIVE|REDACTED|REFERENCE|REFERENCES|REFRESH|REGEX|REGION|REGISTRY|REHYDRATION|RENAME|REOPTIMIZE|REPEATABLE|REPLACE|REPLAN|REPLICA|REPLICAS|REPLICATION|RESET|RESPECT|RESTRICT|RETAIN|RETURN|RETURNING|REVOKE|RIGHT|ROLE|ROLES|ROLLBACK|ROTATE|ROUNDS|ROW|ROWS|SASL|SCALE|SCHEDULE|SCHEMA|SCHEMAS|SECOND|SECONDS|SECRET|SECRETS|SECURITY|SEED|SELECT|SEQUENCES|SERIALIZABLE|SERVICE|SESSION|SET|SHARD|SHOW|SINK|SINKS|SIZE|SMALLINT|SNAPSHOT|SOME|SOURCE|SOURCES|SSH|SSL|START|STDIN|STDOUT|STORAGE|STORAGECTL|STRATEGY|STRICT|STRING|STRONG|SUBSCRIBE|SUBSOURCE|SUBSOURCES|SUBSTRING|SUBTREE|SUPERUSER|SWAP|SYNTAX|SYSTEM|TABLE|TABLES|TAIL|TEMP|TEMPORARY|TEXT|THEN|TICK|TIES|TIME|TIMELINE|TIMEOUT|TIMESTAMP|TIMESTAMPTZ|TIMING|TO|TOKEN|TOPIC|TPCH|TRACE|TRAILING|TRANSACTION|TRANSACTIONAL|TRIM|TRUE|TUNNEL|TYPE|TYPES|UNBOUNDED|UNCOMMITTED|UNION|UNIQUE|UNKNOWN|UP|UPDATE|UPSERT|URL|USAGE|USER|USERNAME|USERS|USING|VALIDATE|VALUE|VALUES|VARCHAR|VARIADIC|VARYING|VERSION|VIEW|VIEWS|WARNING|WEBHOOK|WHEN|WHERE|WINDOW|WIRE|WITH|WITHIN|WITHOUT|WORK|WORKERS|WRITE|YEAR|YEARS|ZONE|ZONES)\b">
+      <rule pattern="(ACCESS|ADD|ADDRESSES|AGGREGATE|ALIGNED|ALL|ALTER|ANALYSIS|AND|ANY|ARITY|ARN|ARRANGEMENT|ARRAY|AS|ASC|ASSERT|ASSUME|AT|AUCTION|AUTHORITY|AVAILABILITY|AVRO|AWS|BATCH|BEGIN|BETWEEN|BIGINT|BILLED|BODY|BOOLEAN|BOTH|BPCHAR|BROKEN|BROKER|BROKERS|BY|BYTES|CARDINALITY|CASCADE|CASE|CAST|CERTIFICATE|CHAIN|CHAINS|CHAR|CHARACTER|CHARACTERISTICS|CHECK|CLASS|CLIENT|CLOCK|CLOSE|CLUSTER|CLUSTERS|COALESCE|COLLATE|COLUMN|COLUMNS|COMMENT|COMMIT|COMMITTED|COMPACTION|COMPATIBILITY|COMPRESSION|COMPUTE|COMPUTECTL|CONFIG|CONFLUENT|CONNECTION|CONNECTIONS|CONSTRAINT|CONTINUAL|COPY|COUNT|COUNTER|CREATE|CREATECLUSTER|CREATEDB|CREATEROLE|CREATION|CROSS|CSV|CURRENT|CURSOR|DATABASE|DATABASES|DATUMS|DAY|DAYS|DEALLOCATE|DEBEZIUM|DEBUG|DEBUGGING|DEC|DECIMAL|DECLARE|DECODING|DECORRELATED|DEFAULT|DEFAULTS|DELETE|DELIMITED|DELIMITER|DELTA|DESC|DETAILS|DISCARD|DISK|DISTINCT|DOC|DOT|DOUBLE|DROP|EAGER|ELEMENT|ELSE|ENABLE|END|ENDPOINT|ENFORCED|ENVELOPE|ERROR|ERRORS|ESCAPE|ESTIMATE|EVERY|EXCEPT|EXCLUDE|EXECUTE|EXISTS|EXPECTED|EXPLAIN|EXPOSE|EXPRESSIONS|EXTERNAL|EXTRACT|FACTOR|FALSE|FAST|FEATURES|FETCH|FIELDS|FILE|FILTER|FIRST|FIXPOINT|FLOAT|FOLLOWING|FOR|FOREIGN|FORMAT|FORWARD|FROM|FULL|FULLNAME|FUNCTION|FUSION|GENERATOR|GRANT|GREATEST|GROUP|GROUPS|HAVING|HEADER|HEADERS|HISTORY|HOLD|HOST|HOUR|HOURS|HUMANIZED|HYDRATION|ID|IDENTIFIERS|IDS|IF|IGNORE|ILIKE|IMPLEMENTATIONS|IMPORTED|IN|INCLUDE|INDEX|INDEXES|INFO|INHERIT|INLINE|INNER|INPUT|INSERT|INSIGHTS|INSPECT|INT|INTEGER|INTERNAL|INTERSECT|INTERVAL|INTO|INTROSPECTION|IS|ISNULL|ISOLATION|JOIN|JOINS|JSON|KAFKA|KEY|KEYS|LAST|LATERAL|LATEST|LEADING|LEAST|LEFT|LEGACY|LETREC|LEVEL|LIKE|LIMIT|LINEAR|LIST|LOAD|LOCAL|LOCALLY|LOG|LOGICAL|LOGIN|LOWERING|MANAGED|MANUAL|MAP|MARKETING|MATERIALIZE|MATERIALIZED|MAX|MECHANISMS|MEMBERSHIP|MESSAGE|METADATA|MINUTE|MINUTES|MODE|MONTH|MONTHS|MUTUALLY|MYSQL|NAME|NAMES|NATURAL|NEGATIVE|NEW|NEXT|NO|NOCREATECLUSTER|NOCREATEDB|NOCREATEROLE|NODE|NOINHERIT|NOLOGIN|NON|NONE|NOSUPERUSER|NOT|NOTICE|NOTICES|NULL|NULLIF|NULLS|OBJECTS|OF|OFFSET|ON|ONLY|OPERATOR|OPTIMIZED|OPTIMIZER|OPTIONS|OR|ORDER|ORDINALITY|OUTER|OVER|OWNED|OWNER|PARTITION|PARTITIONS|PASSWORD|PATH|PHYSICAL|PLAN|PLANS|PORT|POSITION|POSTGRES|PRECEDING|PRECISION|PREFIX|PREPARE|PRIMARY|PRIVATELINK|PRIVILEGES|PROGRESS|PROTOBUF|PROTOCOL|PUBLIC|PUBLICATION|PUSHDOWN|QUERY|QUOTE|RAISE|RANGE|RATE|RAW|READ|READY|REAL|REASSIGN|RECURSION|RECURSIVE|REDACTED|REDUCE|REFERENCE|REFERENCES|REFRESH|REGEX|REGION|REGISTRY|RENAME|REOPTIMIZE|REPEATABLE|REPLACE|REPLAN|REPLICA|REPLICAS|REPLICATION|RESET|RESPECT|RESTRICT|RETAIN|RETURN|RETURNING|REVOKE|RIGHT|ROLE|ROLES|ROLLBACK|ROTATE|ROUNDS|ROW|ROWS|SASL|SCALE|SCHEDULE|SCHEMA|SCHEMAS|SECOND|SECONDS|SECRET|SECRETS|SECURITY|SEED|SELECT|SEQUENCES|SERIALIZABLE|SERVICE|SESSION|SET|SHARD|SHOW|SINK|SINKS|SIZE|SMALLINT|SNAPSHOT|SOME|SOURCE|SOURCES|SSH|SSL|START|STDIN|STDOUT|STORAGE|STORAGECTL|STRATEGY|STRICT|STRING|STRONG|SUBSCRIBE|SUBSOURCE|SUBSOURCES|SUBSTRING|SUBTREE|SUPERUSER|SWAP|SYNTAX|SYSTEM|TABLE|TABLES|TAIL|TASK|TEMP|TEMPORARY|TEXT|THEN|TICK|TIES|TIME|TIMELINE|TIMEOUT|TIMESTAMP|TIMESTAMPTZ|TIMING|TO|TOKEN|TOPIC|TPCH|TRACE|TRAILING|TRANSACTION|TRANSACTIONAL|TRIM|TRUE|TUNNEL|TYPE|TYPES|UNBOUNDED|UNCOMMITTED|UNION|UNIQUE|UNKNOWN|UNNEST|UNTIL|UP|UPDATE|UPSERT|URL|USAGE|USER|USERNAME|USERS|USING|VALIDATE|VALUE|VALUES|VARCHAR|VARIADIC|VARYING|VERSION|VIEW|VIEWS|WAIT|WARNING|WEBHOOK|WHEN|WHERE|WINDOW|WIRE|WITH|WITHIN|WITHOUT|WORK|WORKERS|WORKLOAD|WRITE|YEAR|YEARS|YUGABYTE|ZONE|ZONES)\b">
         <token type="Keyword" />
       </rule>
       <rule pattern="[+*/&lt;&gt;=~!@#%^&amp;|`?-]+">

lexers/mcfunction.xml

@@ -1,182 +1,137 @@
+
 <lexer>
   <config>
-    <name>mcfunction</name>
+    <name>MCFunction</name>
     <alias>mcfunction</alias>
+    <alias>mcf</alias>
     <filename>*.mcfunction</filename>
-    <dot_all>true</dot_all>
-    <not_multiline>true</not_multiline>
+    <mime_type>text/mcfunction</mime_type>
   </config>
   <rules>
-    <state name="nbtobjectvalue">
-      <rule pattern="(&#34;(\\\\|\\&#34;|[^&#34;])*&#34;|[a-zA-Z0-9_]+)">
-        <token type="NameTag"/>
-        <push state="nbtobjectattribute"/>
-      </rule>
-      <rule pattern="\}">
-        <token type="Punctuation"/>
-        <pop depth="1"/>
-      </rule>
-    </state>
-    <state name="nbtarrayvalue">
-      <rule>
-        <include state="nbtvalue"/>
-      </rule>
-      <rule pattern=",">
-        <token type="Punctuation"/>
-      </rule>
-      <rule pattern="\]">
-        <token type="Punctuation"/>
-        <pop depth="1"/>
-      </rule>
-    </state>
-    <state name="nbtvalue">
-      <rule>
-        <include state="simplevalue"/>
-      </rule>
-      <rule pattern="\{">
-        <token type="Punctuation"/>
-        <push state="nbtobjectvalue"/>
-      </rule>
-      <rule pattern="\[">
-        <token type="Punctuation"/>
-        <push state="nbtarrayvalue"/>
-      </rule>
-    </state>
-    <state name="argumentvalue">
-      <rule>
-        <include state="simplevalue"/>
-      </rule>
-      <rule pattern=",">
-        <token type="Punctuation"/>
-        <pop depth="1"/>
-      </rule>
-      <rule pattern="[}\]]">
-        <token type="Punctuation"/>
-        <pop depth="2"/>
-      </rule>
-    </state>
-    <state name="argumentlist">
-      <rule pattern="(nbt)(={)">
-        <bygroups>
-          <token type="NameAttribute"/>
-          <token type="Punctuation"/>
-        </bygroups>
-        <push state="nbtobjectvalue"/>
-      </rule>
-      <rule pattern="([A-Za-z0-9/_!]+)(={)">
-        <bygroups>
-          <token type="NameAttribute"/>
-          <token type="Punctuation"/>
-        </bygroups>
-        <push state="argumentlist"/>
-      </rule>
-      <rule pattern="([A-Za-z0-9/_!]+)(=)">
-        <bygroups>
-          <token type="NameAttribute"/>
-          <token type="Punctuation"/>
-        </bygroups>
-        <push state="argumentvalue"/>
-      </rule>
-      <rule>
-        <include state="simplevalue"/>
-      </rule>
-      <rule pattern=",">
-        <token type="Punctuation"/>
-      </rule>
-      <rule pattern="[}\]]">
-        <token type="Punctuation"/>
-        <pop depth="1"/>
-      </rule>
-    </state>
     <state name="root">
-      <rule pattern="#.*?\n">
-        <token type="CommentSingle"/>
-      </rule>
-      <rule pattern="/?(geteduclientinfo|clearspawnpoint|defaultgamemode|transferserver|toggledownfall|immutableworld|detectredstone|setidletimeout|playanimation|classroommode|spreadplayers|testforblocks|setmaxplayers|setworldspawn|testforblock|worldbuilder|createagent|worldborder|camerashake|advancement|raytracefog|locatebiome|tickingarea|replaceitem|attributes|spawnpoint|difficulty|experience|scoreboard|whitelist|structure|playsound|stopsound|forceload|spectate|gamerule|function|schedule|wsserver|teleport|position|save-off|particle|setblock|datapack|mobevent|transfer|gamemode|save-all|bossbar|enchant|trigger|collect|execute|weather|teammsg|tpagent|banlist|dropall|publish|tellraw|testfor|save-on|destroy|ability|locate|summon|remove|effect|reload|ban-ip|recipe|pardon|detect|music|clear|clone|event|mixer|debug|title|ride|stop|list|turn|data|team|kick|loot|tell|help|give|flog|fill|move|time|seed|kill|save|item|deop|code|tag|ban|msg|say|tp|me|op|xp|w|place)\b">
-        <token type="KeywordReserved"/>
-      </rule>
-      <rule pattern="(@p|@r|@a|@e|@s|@c|@v)">
-        <token type="KeywordConstant"/>
-      </rule>
-      <rule pattern="\[">
-        <token type="Punctuation"/>
-        <push state="argumentlist"/>
-      </rule>
-      <rule pattern="{">
-        <token type="Punctuation"/>
-        <push state="nbtobjectvalue"/>
-      </rule>
-      <rule pattern="~">
-        <token type="NameBuiltin"/>
-      </rule>
-      <rule pattern="([a-zA-Z_]+:)?[a-zA-Z_]+\b">
-        <token type="Text"/>
-      </rule>
-      <rule pattern="([a-z]+)(\.)([0-9]+)\b">
-        <bygroups>
-          <token type="Text"/>
-          <token type="Punctuation"/>
-          <token type="LiteralNumber"/>
-        </bygroups>
-      </rule>
-      <rule pattern="([&lt;&gt;=]|&lt;=|&gt;=)">
-        <token type="Punctuation"/>
-      </rule>
-      <rule>
-        <include state="simplevalue"/>
-      </rule>
-      <rule pattern="\s+">
-        <token type="TextWhitespace"/>
-      </rule>
+      <rule><include state="names"/></rule>
+      <rule><include state="comments"/></rule>
+      <rule><include state="literals"/></rule>
+      <rule><include state="whitespace"/></rule>
+      <rule><include state="property"/></rule>
+      <rule><include state="operators"/></rule>
+      <rule><include state="selectors"/></rule>
     </state>
-    <state name="simplevalue">
-      <rule pattern="(true|false)">
-        <token type="KeywordConstant"/>
-      </rule>
-      <rule pattern="[01]b">
-        <token type="LiteralNumber"/>
-      </rule>
-      <rule pattern="-?(0|[1-9]\d*)(\.\d+[eE](\+|-)?\d+|[eE](\+|-)?\d+|\.\d+)">
-        <token type="LiteralNumberFloat"/>
-      </rule>
-      <rule pattern="(-?\d+)(\.\.)(-?\d+)">
-        <bygroups>
-          <token type="LiteralNumberInteger"/>
-          <token type="Punctuation"/>
-          <token type="LiteralNumberInteger"/>
-        </bygroups>
-      </rule>
-      <rule pattern="-?(0|[1-9]\d*)">
-        <token type="LiteralNumberInteger"/>
-      </rule>
-      <rule pattern="&#34;(\\\\|\\&#34;|[^&#34;])*&#34;">
-        <token type="LiteralStringDouble"/>
-      </rule>
-      <rule pattern="&#39;[^&#39;]+&#39;">
-        <token type="LiteralStringSingle"/>
-      </rule>
-      <rule pattern="([!#]?)(\w+)">
-        <bygroups>
-          <token type="Punctuation"/>
-          <token type="Text"/>
-        </bygroups>
-      </rule>
+    <state name="names">
+      <rule pattern="^(\s*)([a-z_]+)"><bygroups><token type="TextWhitespace"/><token type="NameBuiltin"/></bygroups></rule>
+      <rule pattern="(?&lt;=run)\s+[a-z_]+"><token type="NameBuiltin"/></rule>
+      <rule pattern="\b[0-9a-fA-F]+(?:-[0-9a-fA-F]+){4}\b"><token type="NameVariable"/></rule>
+      <rule><include state="resource-name"/></rule>
+      <rule pattern="[A-Za-z_][\w.#%$]+"><token type="KeywordConstant"/></rule>
+      <rule pattern="[#%$][\w.#%$]+"><token type="NameVariableMagic"/></rule>
     </state>
-    <state name="nbtobjectattribute">
-      <rule>
-        <include state="nbtvalue"/>
-      </rule>
-      <rule pattern=":">
-        <token type="Punctuation"/>
-      </rule>
-      <rule pattern=",">
-        <token type="Punctuation"/>
-        <pop depth="1"/>
-      </rule>
-      <rule pattern="\}">
-        <token type="Punctuation"/>
-        <pop depth="2"/>
-      </rule>
+    <state name="resource-name">
+      <rule pattern="#?[a-z_][a-z_.-]*:[a-z0-9_./-]+"><token type="NameFunction"/></rule>
+      <rule pattern="#?[a-z0-9_\.\-]+\/[a-z0-9_\.\-\/]+"><token type="NameFunction"/></rule>
+    </state>
+    <state name="whitespace">
+      <rule pattern="\s+"><token type="TextWhitespace"/></rule>
+    </state>
+    <state name="comments">
+      <rule pattern="^\s*(#[&gt;!])"><token type="CommentMultiline"/><push state="comments.block" state="comments.block.emphasized"/></rule>
+      <rule pattern="#.*$"><token type="CommentSingle"/></rule>
+    </state>
+    <state name="comments.block">
+      <rule pattern="^\s*#[&gt;!]"><token type="CommentMultiline"/><push state="comments.block.emphasized"/></rule>
+      <rule pattern="^\s*#"><token type="CommentMultiline"/><push state="comments.block.normal"/></rule>
+      <rule><pop depth="1"/></rule>
+    </state>
+    <state name="comments.block.normal">
+      <rule><include state="comments.block.special"/></rule>
+      <rule pattern="\S+"><token type="CommentMultiline"/></rule>
+      <rule pattern="\n"><token type="Text"/><pop depth="1"/></rule>
+      <rule><include state="whitespace"/></rule>
+    </state>
+    <state name="comments.block.emphasized">
+      <rule><include state="comments.block.special"/></rule>
+      <rule pattern="\S+"><token type="LiteralStringDoc"/></rule>
+      <rule pattern="\n"><token type="Text"/><pop depth="1"/></rule>
+      <rule><include state="whitespace"/></rule>
+    </state>
+    <state name="comments.block.special">
+      <rule pattern="@\S+"><token type="NameDecorator"/></rule>
+      <rule><include state="resource-name"/></rule>
+      <rule pattern="[#%$][\w.#%$]+"><token type="NameVariableMagic"/></rule>
+    </state>
+    <state name="operators">
+      <rule pattern="[\-~%^?!+*&lt;&gt;\\/|&amp;=.]"><token type="Operator"/></rule>
+    </state>
+    <state name="literals">
+      <rule pattern="\.\."><token type="Literal"/></rule>
+      <rule pattern="(true|false)"><token type="KeywordPseudo"/></rule>
+      <rule pattern="[A-Za-z_]+"><token type="NameVariableClass"/></rule>
+      <rule pattern="[0-7]b"><token type="LiteralNumberByte"/></rule>
+      <rule pattern="[+-]?\d*\.?\d+([eE]?[+-]?\d+)?[df]?\b"><token type="LiteralNumberFloat"/></rule>
+      <rule pattern="[+-]?\d+\b"><token type="LiteralNumberInteger"/></rule>
+      <rule pattern="&quot;"><token type="LiteralStringDouble"/><push state="literals.string-double"/></rule>
+      <rule pattern="&#x27;"><token type="LiteralStringSingle"/><push state="literals.string-single"/></rule>
+    </state>
+    <state name="literals.string-double">
+      <rule pattern="\\."><token type="LiteralStringEscape"/></rule>
+      <rule pattern="[^\\&quot;\n]+"><token type="LiteralStringDouble"/></rule>
+      <rule pattern="&quot;"><token type="LiteralStringDouble"/><pop depth="1"/></rule>
+    </state>
+    <state name="literals.string-single">
+      <rule pattern="\\."><token type="LiteralStringEscape"/></rule>
+      <rule pattern="[^\\&#x27;\n]+"><token type="LiteralStringSingle"/></rule>
+      <rule pattern="&#x27;"><token type="LiteralStringSingle"/><pop depth="1"/></rule>
+    </state>
+    <state name="selectors">
+      <rule pattern="@[a-z]"><token type="NameVariable"/></rule>
+    </state>
+    <state name="property">
+      <rule pattern="\{"><token type="Punctuation"/><push state="property.curly" state="property.key"/></rule>
+      <rule pattern="\["><token type="Punctuation"/><push state="property.square" state="property.key"/></rule>
+    </state>
+    <state name="property.curly">
+      <rule><include state="whitespace"/></rule>
+      <rule><include state="property"/></rule>
+      <rule pattern="\}"><token type="Punctuation"/><pop depth="1"/></rule>
+    </state>
+    <state name="property.square">
+      <rule><include state="whitespace"/></rule>
+      <rule><include state="property"/></rule>
+      <rule pattern="\]"><token type="Punctuation"/><pop depth="1"/></rule>
+      <rule pattern=","><token type="Punctuation"/></rule>
+    </state>
+    <state name="property.key">
+      <rule><include state="whitespace"/></rule>
+      <rule pattern="#?[a-z_][a-z_\.\-]*\:[a-z0-9_\.\-/]+(?=\s*\=)"><token type="NameAttribute"/><push state="property.delimiter"/></rule>
+      <rule pattern="#?[a-z_][a-z0-9_\.\-/]+"><token type="NameAttribute"/><push state="property.delimiter"/></rule>
+      <rule pattern="[A-Za-z_\-\+]+"><token type="NameAttribute"/><push state="property.delimiter"/></rule>
+      <rule pattern="&quot;"><token type="NameAttribute"/><push state="property.delimiter"/></rule>
+      <rule pattern="&#x27;"><token type="NameAttribute"/><push state="property.delimiter"/></rule>
+      <rule pattern="-?\d+"><token type="LiteralNumberInteger"/><push state="property.delimiter"/></rule>
+      <rule><pop depth="1"/></rule>
+    </state>
+    <state name="property.key.string-double">
+      <rule pattern="\\."><token type="LiteralStringEscape"/></rule>
+      <rule pattern="[^\\&quot;\n]+"><token type="NameAttribute"/></rule>
+      <rule pattern="&quot;"><token type="NameAttribute"/><pop depth="1"/></rule>
+    </state>
+    <state name="property.key.string-single">
+      <rule pattern="\\."><token type="LiteralStringEscape"/></rule>
+      <rule pattern="[^\\&#x27;\n]+"><token type="NameAttribute"/></rule>
+      <rule pattern="&#x27;"><token type="NameAttribute"/><pop depth="1"/></rule>
+    </state>
+    <state name="property.delimiter">
+      <rule><include state="whitespace"/></rule>
+      <rule pattern="[:=]!?"><token type="Punctuation"/><push state="property.value"/></rule>
+      <rule pattern=","><token type="Punctuation"/></rule>
+      <rule><pop depth="1"/></rule>
+    </state>
+    <state name="property.value">
+      <rule><include state="whitespace"/></rule>
+      <rule pattern="#?[a-z_][a-z_\.\-]*\:[a-z0-9_\.\-/]+"><token type="NameTag"/></rule>
+      <rule pattern="#?[a-z_][a-z0-9_\.\-/]+"><token type="NameTag"/></rule>
+      <rule><include state="literals"/></rule>
+      <rule><include state="property"/></rule>
+      <rule><pop depth="1"/></rule>
     </state>
   </rules>
 </lexer>

lexers/nix.xml

@@ -106,7 +106,7 @@
         </bygroups>
         <push state="interpol"/>
       </rule>
-      <rule pattern="(&amp;&amp;|&gt;=|&lt;=|\+\+|-&gt;|!=|\|\||//|==|@|!|\+|\?|&lt;|\.|&gt;|\*)">
+      <rule pattern="(&amp;&amp;|&gt;=|&lt;=|\+\+|-&gt;|!=|=|\|\||//|==|@|!|\+|\?|&lt;|\.|&gt;|\*)">
         <token type="Operator"/>
       </rule>
       <rule pattern="[;:]">

lexers/nsis.xml

@@ -0,0 +1,59 @@
+<lexer>
+  <config>
+    <name>NSIS</name>
+    <alias>nsis</alias>
+    <alias>nsi</alias>
+    <alias>nsh</alias>
+    <filename>*.nsi</filename>
+    <filename>*.nsh</filename>
+    <mime_type>text/x-nsis</mime_type>
+    <case_insensitive>true</case_insensitive>
+    <not_multiline>true</not_multiline>
+  </config>
+  <rules>
+    <state name="root">
+      <rule pattern="([;#].*)(\n)"><bygroups><token type="Comment"/><token type="TextWhitespace"/></bygroups></rule>
+      <rule pattern="&#x27;.*?&#x27;"><token type="LiteralStringSingle"/></rule>
+      <rule pattern="&quot;"><token type="LiteralStringDouble"/><push state="str_double"/></rule>
+      <rule pattern="`"><token type="LiteralStringBacktick"/><push state="str_backtick"/></rule>
+      <rule><include state="macro"/></rule>
+      <rule><include state="interpol"/></rule>
+      <rule><include state="basic"/></rule>
+      <rule pattern="\$\{[a-z_|][\w|]*\}"><token type="KeywordPseudo"/></rule>
+      <rule pattern="/[a-z_]\w*"><token type="NameAttribute"/></rule>
+      <rule pattern="\s+"><token type="TextWhitespace"/></rule>
+      <rule pattern="[\w.]+"><token type="Text"/></rule>
+    </state>
+    <state name="basic">
+      <rule pattern="(\n)(Function)(\s+)([._a-z][.\w]*)\b"><bygroups><token type="TextWhitespace"/><token type="Keyword"/><token type="TextWhitespace"/><token type="NameFunction"/></bygroups></rule>
+      <rule pattern="\b([_a-z]\w*)(::)([a-z][a-z0-9]*)\b"><bygroups><token type="KeywordNamespace"/><token type="Punctuation"/><token type="NameFunction"/></bygroups></rule>
+      <rule pattern="\b([_a-z]\w*)(:)"><bygroups><token type="NameLabel"/><token type="Punctuation"/></bygroups></rule>
+      <rule pattern="(\b[ULS]|\B)([!&lt;&gt;=]?=|\&lt;\&gt;?|\&gt;)\B"><token type="Operator"/></rule>
+      <rule pattern="[|+-]"><token type="Operator"/></rule>
+      <rule pattern="\\"><token type="Punctuation"/></rule>
+      <rule pattern="\b(Abort|Add(?:BrandingImage|Size)|Allow(?:RootDirInstall|SkipFiles)|AutoCloseWindow|BG(?:Font|Gradient)|BrandingText|BringToFront|Call(?:InstDLL)?|(?:Sub)?Caption|ChangeUI|CheckBitmap|ClearErrors|CompletedText|ComponentText|CopyFiles|CRCCheck|Create(?:Directory|Font|Shortcut)|Delete(?:INI(?:Sec|Str)|Reg(?:Key|Value))?|DetailPrint|DetailsButtonText|Dir(?:Show|Text|Var|Verify)|(?:Disabled|Enabled)Bitmap|EnableWindow|EnumReg(?:Key|Value)|Exch|Exec(?:Shell|Wait)?|ExpandEnvStrings|File(?:BufSize|Close|ErrorText|Open|Read(?:Byte)?|Seek|Write(?:Byte)?)?|Find(?:Close|First|Next|Window)|FlushINI|Function(?:End)?|Get(?:CurInstType|CurrentAddress|DlgItem|DLLVersion(?:Local)?|ErrorLevel|FileTime(?:Local)?|FullPathName|FunctionAddress|InstDirError|LabelAddress|TempFileName)|Goto|HideWindow|Icon|If(?:Abort|Errors|FileExists|RebootFlag|Silent)|InitPluginsDir|Install(?:ButtonText|Colors|Dir(?:RegKey)?)|Inst(?:ProgressFlags|Type(?:[GS]etText)?)|Int(?:CmpU?|Fmt|Op)|IsWindow|LangString(?:UP)?|License(?:BkColor|Data|ForceSelection|LangString|Text)|LoadLanguageFile|LockWindow|Log(?:Set|Text)|MessageBox|MiscButtonText|Name|Nop|OutFile|(?:Uninst)?Page(?:Ex(?:End)?)?|PluginDir|Pop|Push|Quit|Read(?:(?:Env|INI|Reg)Str|RegDWORD)|Reboot|(?:Un)?RegDLL|Rename|RequestExecutionLevel|ReserveFile|Return|RMDir|SearchPath|Section(?:Divider|End|(?:(?:Get|Set)(?:Flags|InstTypes|Size|Text))|Group(?:End)?|In)?|SendMessage|Set(?:AutoClose|BrandingImage|Compress(?:ionLevel|or(?:DictSize)?)?|CtlColors|CurInstType|DatablockOptimize|DateSave|Details(?:Print|View)|Error(?:s|Level)|FileAttributes|Font|OutPath|Overwrite|PluginUnload|RebootFlag|ShellVarContext|Silent|StaticBkColor)|Show(?:(?:I|Uni)nstDetails|Window)|Silent(?:Un)?Install|Sleep|SpaceTexts|Str(?:CmpS?|Cpy|Len)|SubSection(?:End)?|Uninstall(?:ButtonText|(?:Sub)?Caption|EXEName|Icon|Text)|UninstPage|Var|VI(?:AddVersionKey|ProductVersion)|WindowIcon|Write(?:INIStr|Reg(:?Bin|DWORD|(?:Expand)?Str)|Uninstaller)|XPStyle)\b"><token type="Keyword"/></rule>
+      <rule pattern="\b(CUR|END|(?:FILE_ATTRIBUTE_)?(?:ARCHIVE|HIDDEN|NORMAL|OFFLINE|READONLY|SYSTEM|TEMPORARY)|HK(CC|CR|CU|DD|LM|PD|U)|HKEY_(?:CLASSES_ROOT|CURRENT_(?:CONFIG|USER)|DYN_DATA|LOCAL_MACHINE|PERFORMANCE_DATA|USERS)|ID(?:ABORT|CANCEL|IGNORE|NO|OK|RETRY|YES)|MB_(?:ABORTRETRYIGNORE|DEFBUTTON[1-4]|ICON(?:EXCLAMATION|INFORMATION|QUESTION|STOP)|OK(?:CANCEL)?|RETRYCANCEL|RIGHT|SETFOREGROUND|TOPMOST|USERICON|YESNO(?:CANCEL)?)|SET|SHCTX|SW_(?:HIDE|SHOW(?:MAXIMIZED|MINIMIZED|NORMAL))|admin|all|auto|both|bottom|bzip2|checkbox|colored|current|false|force|hide|highest|if(?:diff|newer)|lastused|leave|left|listonly|lzma|nevershow|none|normal|off|on|pop|push|radiobuttons|right|show|silent|silentlog|smooth|textonly|top|true|try|user|zlib)\b"><token type="NameConstant"/></rule>
+    </state>
+    <state name="macro">
+      <rule pattern="\!(addincludedir(?:dir)?|addplugindir|appendfile|cd|define|delfilefile|echo(?:message)?|else|endif|error|execute|if(?:macro)?n?(?:def)?|include|insertmacro|macro(?:end)?|packhdr|search(?:parse|replace)|system|tempfilesymbol|undef|verbose|warning)\b"><token type="CommentPreproc"/></rule>
+    </state>
+    <state name="interpol">
+      <rule pattern="\$(R?[0-9])"><token type="NameBuiltinPseudo"/></rule>
+      <rule pattern="\$(ADMINTOOLS|APPDATA|CDBURN_AREA|COOKIES|COMMONFILES(?:32|64)|DESKTOP|DOCUMENTS|EXE(?:DIR|FILE|PATH)|FAVORITES|FONTS|HISTORY|HWNDPARENT|INTERNET_CACHE|LOCALAPPDATA|MUSIC|NETHOOD|PICTURES|PLUGINSDIR|PRINTHOOD|PROFILE|PROGRAMFILES(?:32|64)|QUICKLAUNCH|RECENT|RESOURCES(?:_LOCALIZED)?|SENDTO|SM(?:PROGRAMS|STARTUP)|STARTMENU|SYSDIR|TEMP(?:LATES)?|VIDEOS|WINDIR|\{NSISDIR\})"><token type="NameBuiltin"/></rule>
+      <rule pattern="\$(CMDLINE|INSTDIR|OUTDIR|LANGUAGE)"><token type="NameVariableGlobal"/></rule>
+      <rule pattern="\$[a-z_]\w*"><token type="NameVariable"/></rule>
+    </state>
+    <state name="str_double">
+      <rule pattern="&quot;"><token type="LiteralStringDouble"/><pop depth="1"/></rule>
+      <rule pattern="\$(\\[nrt&quot;]|\$)"><token type="LiteralStringEscape"/></rule>
+      <rule><include state="interpol"/></rule>
+      <rule pattern="[^&quot;]+"><token type="LiteralStringDouble"/></rule>
+    </state>
+    <state name="str_backtick">
+      <rule pattern="`"><token type="LiteralStringDouble"/><pop depth="1"/></rule>
+      <rule pattern="\$(\\[nrt&quot;]|\$)"><token type="LiteralStringEscape"/></rule>
+      <rule><include state="interpol"/></rule>
+      <rule pattern="[^`]+"><token type="LiteralStringDouble"/></rule>
+    </state>
+  </rules>
+</lexer>

lexers/ocaml.xml

@@ -41,6 +41,14 @@
       <rule pattern="\b(as|assert|begin|class|constraint|do|done|downto|else|end|exception|external|false|for|fun|function|functor|if|in|include|inherit|initializer|lazy|let|match|method|module|mutable|new|object|of|open|private|raise|rec|sig|struct|then|to|true|try|type|value|val|virtual|when|while|with)\b">
         <token type="Keyword"/>
       </rule>
+      <rule pattern="({([a-z_]*)\|)([\s\S]+?)(?=\|\2})(\|\2})">
+        <bygroups>
+          <token type="LiteralStringAffix"/>
+          <token type="Ignore"/>
+          <token type="LiteralString"/>
+          <token type="LiteralStringAffix"/>
+        </bygroups>
+      </rule>
       <rule pattern="(~|\}|\|]|\||\{&lt;|\{|`|_|]|\[\||\[&gt;|\[&lt;|\[|\?\?|\?|&gt;\}|&gt;]|&gt;|=|&lt;-|&lt;|;;|;|:&gt;|:=|::|:|\.\.|\.|-&gt;|-\.|-|,|\+|\*|\)|\(|&amp;&amp;|&amp;|#|!=)">
         <token type="Operator"/>
       </rule>

lexers/odin.xml

@@ -51,6 +51,20 @@
         <rule pattern = "\#[a-zA-Z_]+\b">
             <token type = "NameDecorator"/>
         </rule>
+        <rule pattern = "^\#\+\w+\s*$">
+            <token type = "NameAttribute"/>
+        </rule>
+        <rule pattern = "^(\#\+\w+)(\s+)(\!)?([A-Za-z0-9-_!]+)(?:(,)(\!)?([A-Za-z0-9-_!]+))*\s*$">
+            <bygroups>
+                <token type = "NameAttribute"/>
+                <token type = "TextWhitespace"/>
+                <token type = "Operator"/>
+                <token type = "Name"/>
+                <token type = "Punctuation"/>
+                <token type = "Operator"/>
+                <token type = "Name"/>
+            </bygroups>
+        </rule>
         <rule pattern = "\@(\([a-zA-Z_]+\b\s*.*\)|\(?[a-zA-Z_]+\)?)">
             <token type = "NameAttribute"/>
         </rule>

lexers/snbt.xml

@@ -0,0 +1,57 @@
+
+<lexer>
+  <config>
+    <name>SNBT</name>
+    <alias>snbt</alias>
+    <filename>*.snbt</filename>
+    <mime_type>text/snbt</mime_type>
+  </config>
+  <rules>
+    <state name="root">
+      <rule pattern="\{"><token type="Punctuation"/><push state="compound"/></rule>
+      <rule pattern="[^\{]+"><token type="Text"/></rule>
+    </state>
+    <state name="whitespace">
+      <rule pattern="\s+"><token type="TextWhitespace"/></rule>
+    </state>
+    <state name="operators">
+      <rule pattern="[,:;]"><token type="Punctuation"/></rule>
+    </state>
+    <state name="literals">
+      <rule pattern="(true|false)"><token type="KeywordConstant"/></rule>
+      <rule pattern="-?\d+[eE]-?\d+"><token type="LiteralNumberFloat"/></rule>
+      <rule pattern="-?\d*\.\d+[fFdD]?"><token type="LiteralNumberFloat"/></rule>
+      <rule pattern="-?\d+[bBsSlLfFdD]?"><token type="LiteralNumberInteger"/></rule>
+      <rule pattern="&quot;"><token type="LiteralStringDouble"/><push state="literals.string_double"/></rule>
+      <rule pattern="&#x27;"><token type="LiteralStringSingle"/><push state="literals.string_single"/></rule>
+    </state>
+    <state name="literals.string_double">
+      <rule pattern="\\."><token type="LiteralStringEscape"/></rule>
+      <rule pattern="[^\\&quot;\n]+"><token type="LiteralStringDouble"/></rule>
+      <rule pattern="&quot;"><token type="LiteralStringDouble"/><pop depth="1"/></rule>
+    </state>
+    <state name="literals.string_single">
+      <rule pattern="\\."><token type="LiteralStringEscape"/></rule>
+      <rule pattern="[^\\&#x27;\n]+"><token type="LiteralStringSingle"/></rule>
+      <rule pattern="&#x27;"><token type="LiteralStringSingle"/><pop depth="1"/></rule>
+    </state>
+    <state name="compound">
+      <rule pattern="[A-Z_a-z]+"><token type="NameAttribute"/></rule>
+      <rule><include state="operators"/></rule>
+      <rule><include state="whitespace"/></rule>
+      <rule><include state="literals"/></rule>
+      <rule pattern="\{"><token type="Punctuation"/><push/></rule>
+      <rule pattern="\["><token type="Punctuation"/><push state="list"/></rule>
+      <rule pattern="\}"><token type="Punctuation"/><pop depth="1"/></rule>
+    </state>
+    <state name="list">
+      <rule pattern="[A-Z_a-z]+"><token type="NameAttribute"/></rule>
+      <rule><include state="literals"/></rule>
+      <rule><include state="operators"/></rule>
+      <rule><include state="whitespace"/></rule>
+      <rule pattern="\["><token type="Punctuation"/><push/></rule>
+      <rule pattern="\{"><token type="Punctuation"/><push state="compound"/></rule>
+      <rule pattern="\]"><token type="Punctuation"/><pop depth="1"/></rule>
+    </state>
+  </rules>
+</lexer>

lexers/solidity.xml

@@ -157,8 +157,20 @@
       <rule pattern="(continue|returns|storage|memory|delete|return|throw|break|catch|while|else|from|new|try|for|if|is|as|do|in|_)\b">
         <token type="Keyword"/>
       </rule>
-      <rule pattern="assembly\b">
-        <token type="Keyword"/>
+      <rule pattern="(assembly)(\s+\()(.+)(\)\s+{)">
+        <bygroups>
+          <token type="Keyword"/>
+          <token type="Text"/>
+          <token type="LiteralString"/>
+          <token type="Text"/>
+        </bygroups>
+        <push state="assembly"/>
+      </rule>
+      <rule pattern="(assembly)(\s+{)">
+        <bygroups>
+          <token type="Keyword"/>
+          <token type="Text"/>
+        </bygroups>
         <push state="assembly"/>
       </rule>
       <rule pattern="(contract|interface|enum|event|struct)(\s+)([a-zA-Z_]\w*)">
@@ -235,7 +247,7 @@
         <token type="Punctuation"/>
         <pop depth="1"/>
       </rule>
-      <rule pattern="[(),]">
+      <rule pattern="[(),.]">
         <token type="Punctuation"/>
       </rule>
       <rule pattern=":=|=:">

lexers/typescript.xml

@@ -51,6 +51,22 @@
       </rule>
     </state>
     <state name="tag">
+      <rule>
+        <include state="jsx"/>
+      </rule>
+      <rule pattern=",">
+        <token type="Punctuation"/>
+      </rule>
+      <rule pattern="&#34;(\\\\|\\&#34;|[^&#34;])*&#34;">
+        <token type="LiteralStringDouble"/>
+      </rule>
+      <rule pattern="&#39;(\\\\|\\&#39;|[^&#39;])*&#39;">
+        <token type="LiteralStringSingle"/>
+      </rule>
+      <rule pattern="`">
+        <token type="LiteralStringBacktick"/>
+        <push state="interp"/>
+      </rule>
       <rule>
         <include state="commentsandwhitespace"/>
       </rule>
@@ -171,7 +187,7 @@
       </rule>
       <rule pattern="(?=/)">
         <token type="Text"/>
-        <push state="#pop" state="badregex"/>
+        <push state="badregex"/>
       </rule>
       <rule>
         <pop depth="1"/>

lexers/typst.xml

@@ -0,0 +1,107 @@
+
+<lexer>
+  <config>
+    <name>Typst</name>
+    <alias>typst</alias>
+    <filename>*.typ</filename>
+    <mime_type>text/x-typst</mime_type>
+  </config>
+  <rules>
+    <state name="root">
+      <rule><include state="markup"/></rule>
+    </state>
+    <state name="into_code">
+      <rule pattern="(\#let|\#set|\#show)\b"><token type="KeywordDeclaration"/><push state="inline_code"/></rule>
+      <rule pattern="(\#import|\#include)\b"><token type="KeywordNamespace"/><push state="inline_code"/></rule>
+      <rule pattern="(\#if|\#for|\#while|\#export)\b"><token type="KeywordReserved"/><push state="inline_code"/></rule>
+      <rule pattern="#\{"><token type="Punctuation"/><push state="code"/></rule>
+      <rule pattern="#\("><token type="Punctuation"/><push state="code"/></rule>
+      <rule pattern="(#[a-zA-Z_][a-zA-Z0-9_-]*)(\[)"><bygroups><token type="NameFunction"/><token type="Punctuation"/></bygroups><push state="markup"/></rule>
+      <rule pattern="(#[a-zA-Z_][a-zA-Z0-9_-]*)(\()"><bygroups><token type="NameFunction"/><token type="Punctuation"/></bygroups><push state="code"/></rule>
+      <rule pattern="(\#true|\#false|\#none|\#auto)\b"><token type="KeywordConstant"/></rule>
+      <rule pattern="#[a-zA-Z_][a-zA-Z0-9_]*"><token type="NameVariable"/></rule>
+      <rule pattern="#0x[0-9a-fA-F]+"><token type="LiteralNumberHex"/></rule>
+      <rule pattern="#0b[01]+"><token type="LiteralNumberBin"/></rule>
+      <rule pattern="#0o[0-7]+"><token type="LiteralNumberOct"/></rule>
+      <rule pattern="#[0-9]+[\.e][0-9]+"><token type="LiteralNumberFloat"/></rule>
+      <rule pattern="#[0-9]+"><token type="LiteralNumberInteger"/></rule>
+    </state>
+    <state name="markup">
+      <rule><include state="comment"/></rule>
+      <rule pattern="^\s*=+.*$"><token type="GenericHeading"/></rule>
+      <rule pattern="[*][^*]*[*]"><token type="GenericStrong"/></rule>
+      <rule pattern="_[^_]*_"><token type="GenericEmph"/></rule>
+      <rule pattern="\$"><token type="Punctuation"/><push state="math"/></rule>
+      <rule pattern="`[^`]*`"><token type="LiteralStringBacktick"/></rule>
+      <rule pattern="^(\s*)(-)(\s+)"><bygroups><token type="TextWhitespace"/><token type="Punctuation"/><token type="TextWhitespace"/></bygroups></rule>
+      <rule pattern="^(\s*)(\+)(\s+)"><bygroups><token type="TextWhitespace"/><token type="Punctuation"/><token type="TextWhitespace"/></bygroups></rule>
+      <rule pattern="^(\s*)([0-9]+\.)"><bygroups><token type="TextWhitespace"/><token type="Punctuation"/></bygroups></rule>
+      <rule pattern="^(\s*)(/)(\s+)([^:]+)(:)"><bygroups><token type="TextWhitespace"/><token type="Punctuation"/><token type="TextWhitespace"/><token type="NameVariable"/><token type="Punctuation"/></bygroups></rule>
+      <rule pattern="&lt;[a-zA-Z_][a-zA-Z0-9_-]*&gt;"><token type="NameLabel"/></rule>
+      <rule pattern="@[a-zA-Z_][a-zA-Z0-9_-]*"><token type="NameLabel"/></rule>
+      <rule pattern="\\#"><token type="Text"/></rule>
+      <rule><include state="into_code"/></rule>
+      <rule pattern="```(?:.|\n)*?```"><token type="LiteralStringBacktick"/></rule>
+      <rule pattern="https?://[0-9a-zA-Z~/%#&amp;=\&#x27;,;.+?]*"><token type="GenericEmph"/></rule>
+      <rule pattern="(\-\-\-|\\|\~|\-\-|\.\.\.)\B"><token type="Punctuation"/></rule>
+      <rule pattern="\\\["><token type="Punctuation"/></rule>
+      <rule pattern="\\\]"><token type="Punctuation"/></rule>
+      <rule pattern="\["><token type="Punctuation"/><push/></rule>
+      <rule pattern="\]"><token type="Punctuation"/><pop depth="1"/></rule>
+      <rule pattern="[ \t]+\n?|\n"><token type="TextWhitespace"/></rule>
+      <rule pattern="((?![*_$`&lt;@\\#\] ]|https?://).)+"><token type="Text"/></rule>
+    </state>
+    <state name="math">
+      <rule><include state="comment"/></rule>
+      <rule pattern="(\\_|\\\^|\\\&amp;)"><token type="Text"/></rule>
+      <rule pattern="(_|\^|\&amp;|;)"><token type="Punctuation"/></rule>
+      <rule pattern="(\+|/|=|\[\||\|\]|\|\||\*|:=|::=|\.\.\.|&#x27;|\-|=:|!=|&gt;&gt;|&gt;=|&gt;&gt;&gt;|&lt;&lt;|&lt;=|&lt;&lt;&lt;|\-&gt;|\|\-&gt;|=&gt;|\|=&gt;|==&gt;|\-\-&gt;|\~\~&gt;|\~&gt;|&gt;\-&gt;|\-&gt;&gt;|&lt;\-|&lt;==|&lt;\-\-|&lt;\~\~|&lt;\~|&lt;\-&lt;|&lt;&lt;\-|&lt;\-&gt;|&lt;=&gt;|&lt;==&gt;|&lt;\-\-&gt;|&gt;|&lt;|\~|:|\|)"><token type="Operator"/></rule>
+      <rule pattern="\\"><token type="Punctuation"/></rule>
+      <rule pattern="\\\$"><token type="Punctuation"/></rule>
+      <rule pattern="\$"><token type="Punctuation"/><pop depth="1"/></rule>
+      <rule><include state="into_code"/></rule>
+      <rule pattern="([a-zA-Z][a-zA-Z0-9-]*)(\s*)(\()"><bygroups><token type="NameFunction"/><token type="TextWhitespace"/><token type="Punctuation"/></bygroups></rule>
+      <rule pattern="([a-zA-Z][a-zA-Z0-9-]*)(:)"><bygroups><token type="NameVariable"/><token type="Punctuation"/></bygroups></rule>
+      <rule pattern="([a-zA-Z][a-zA-Z0-9-]*)"><token type="NameVariable"/></rule>
+      <rule pattern="[0-9]+(\.[0-9]+)?"><token type="LiteralNumber"/></rule>
+      <rule pattern="\.{1,3}|\(|\)|,|\{|\}"><token type="Punctuation"/></rule>
+      <rule pattern="&quot;[^&quot;]*&quot;"><token type="LiteralStringDouble"/></rule>
+      <rule pattern="[ \t\n]+"><token type="TextWhitespace"/></rule>
+    </state>
+    <state name="comment">
+      <rule pattern="//.*$"><token type="CommentSingle"/></rule>
+      <rule pattern="/[*](.|\n)*?[*]/"><token type="CommentMultiline"/></rule>
+    </state>
+    <state name="code">
+      <rule><include state="comment"/></rule>
+      <rule pattern="\["><token type="Punctuation"/><push state="markup"/></rule>
+      <rule pattern="\(|\{"><token type="Punctuation"/><push state="code"/></rule>
+      <rule pattern="\)|\}"><token type="Punctuation"/><pop depth="1"/></rule>
+      <rule pattern="&quot;[^&quot;]*&quot;"><token type="LiteralStringDouble"/></rule>
+      <rule pattern=",|\.{1,2}"><token type="Punctuation"/></rule>
+      <rule pattern="="><token type="Operator"/></rule>
+      <rule pattern="(and|or|not)\b"><token type="OperatorWord"/></rule>
+      <rule pattern="=&gt;|&lt;=|==|!=|&gt;|&lt;|-=|\+=|\*=|/=|\+|-|\\|\*"><token type="Operator"/></rule>
+      <rule pattern="([a-zA-Z_][a-zA-Z0-9_-]*)(:)"><bygroups><token type="NameVariable"/><token type="Punctuation"/></bygroups></rule>
+      <rule pattern="([a-zA-Z_][a-zA-Z0-9_-]*)(\()"><bygroups><token type="NameFunction"/><token type="Punctuation"/></bygroups><push state="code"/></rule>
+      <rule pattern="(as|break|export|continue|else|for|if|in|return|while)\b"><token type="KeywordReserved"/></rule>
+      <rule pattern="(import|include)\b"><token type="KeywordNamespace"/></rule>
+      <rule pattern="(auto|none|true|false)\b"><token type="KeywordConstant"/></rule>
+      <rule pattern="([0-9.]+)(mm|pt|cm|in|em|fr|%)"><bygroups><token type="LiteralNumber"/><token type="KeywordReserved"/></bygroups></rule>
+      <rule pattern="0x[0-9a-fA-F]+"><token type="LiteralNumberHex"/></rule>
+      <rule pattern="0b[01]+"><token type="LiteralNumberBin"/></rule>
+      <rule pattern="0o[0-7]+"><token type="LiteralNumberOct"/></rule>
+      <rule pattern="[0-9]+[\.e][0-9]+"><token type="LiteralNumberFloat"/></rule>
+      <rule pattern="[0-9]+"><token type="LiteralNumberInteger"/></rule>
+      <rule pattern="(let|set|show)\b"><token type="KeywordDeclaration"/></rule>
+      <rule pattern="([a-zA-Z_][a-zA-Z0-9_-]*)"><token type="NameVariable"/></rule>
+      <rule pattern="[ \t\n]+"><token type="TextWhitespace"/></rule>
+      <rule pattern=":"><token type="Punctuation"/></rule>
+    </state>
+    <state name="inline_code">
+      <rule pattern=";\b"><token type="Punctuation"/><pop depth="1"/></rule>
+      <rule pattern="\n"><token type="TextWhitespace"/><pop depth="1"/></rule>
+      <rule><include state="code"/></rule>
+    </state>
+  </rules>
+</lexer>

lexers/webvtt.xml

@@ -0,0 +1,283 @@
+<lexer>
+  <config>
+    <name>WebVTT</name>
+    <alias>vtt</alias>
+    <filename>*.vtt</filename>
+    <mime_type>text/vtt</mime_type>
+  </config>
+  <!--
+    The WebVTT spec refers to a WebVTT line terminator as either CRLF, CR or LF.
+    (https://www.w3.org/TR/webvtt1/#webvtt-line-terminator) However, with this
+    definition it is unclear whether CRLF is one line terminator (CRLF) or two
+    line terminators (CR and LF).
+
+    To work around this ambiguity, only CRLF and LF are considered as line terminators.
+    To my knowledge only classic Mac OS uses CR as line terminators, so the lexer should
+    still work for most files.
+  -->
+  <rules>
+    <!-- https://www.w3.org/TR/webvtt1/#webvtt-file-body -->
+    <state name="root">
+      <rule pattern="(\AWEBVTT)((?:[ \t][^\r\n]*)?(?:\r?\n){2,})">
+        <bygroups>
+          <token type="Keyword" />
+          <token type="Text" />
+        </bygroups>
+      </rule>
+      <rule pattern="(^REGION)([ \t]*$)">
+        <bygroups>
+          <token type="Keyword" />
+          <token type="Text" />
+        </bygroups>
+        <push state="region-settings-list" />
+      </rule>
+      <rule
+        pattern="(^STYLE)([ \t]*$)((?:(?!&#45;&#45;&gt;)[\s\S])*?)((?:\r?\n){2})">
+        <bygroups>
+          <token type="Keyword" />
+          <token type="Text" />
+          <using lexer="CSS" />
+          <token type="Text" />
+        </bygroups>
+      </rule>
+      <rule>
+        <include state="comment" />
+      </rule>
+      <rule
+        pattern="(?=((?![^\r\n]*&#45;&#45;&gt;)[^\r\n]*\r?\n)?(\d{2}:)?(?:[0-5][0-9]):(?:[0-5][0-9])\.\d{3}[ \t]+&#45;&#45;&gt;[ \t]+(\d{2}:)?(?:[0-5][0-9]):(?:[0-5][0-9])\.\d{3})"
+      >
+        <push state="cues" />
+      </rule>
+    </state>
+
+    <!-- https://www.w3.org/TR/webvtt1/#webvtt-region-settings-list -->
+    <state name="region-settings-list">
+      <rule pattern="(?: |\t|\r?\n(?!\r?\n))+">
+        <token type="Text" />
+      </rule>
+      <rule pattern="(?:\r?\n){2}">
+        <token type="Text" />
+        <pop depth="1" />
+      </rule>
+      <rule pattern="(id)(:)(?!&#45;&#45;&gt;)(\S+)">
+        <bygroups>
+          <token type="Keyword" />
+          <token type="Punctuation" />
+          <token type="Literal" />
+        </bygroups>
+      </rule>
+      <rule pattern="(width)(:)((?:[1-9]?\d|100)(?:\.\d+)?)(%)">
+        <bygroups>
+          <token type="Keyword" />
+          <token type="Punctuation" />
+          <token type="Literal" />
+          <token type="KeywordType" />
+        </bygroups>
+      </rule>
+      <rule pattern="(lines)(:)(\d+)">
+        <bygroups>
+          <token type="Keyword" />
+          <token type="Punctuation" />
+          <token type="Literal" />
+        </bygroups>
+      </rule>
+      <rule
+        pattern="(regionanchor|viewportanchor)(:)((?:[1-9]?\d|100)(?:\.\d+)?)(%)(,)((?:[1-9]?\d|100)(?:\.\d+)?)(%)">
+        <bygroups>
+          <token type="Keyword" />
+          <token type="Punctuation" />
+          <token type="Literal" />
+          <token type="KeywordType" />
+          <token type="Punctuation" />
+          <token type="Literal" />
+          <token type="KeywordType" />
+        </bygroups>
+      </rule>
+      <rule pattern="(scroll)(:)(up)">
+        <bygroups>
+          <token type="Keyword" />
+          <token type="Punctuation" />
+          <token type="KeywordConstant" />
+        </bygroups>
+      </rule>
+    </state>
+
+    <!-- https://www.w3.org/TR/webvtt1/#webvtt-comment-block -->
+    <state name="comment">
+      <rule
+        pattern="^NOTE( |\t|\r?\n)((?!&#45;&#45;&gt;)[\s\S])*?(?:(\r?\n){2}|\Z)">
+        <token type="Comment" />
+      </rule>
+    </state>
+
+    <!--
+      "Zero or more WebVTT cue blocks and WebVTT comment blocks separated from each other by one or more
+      WebVTT line terminators." (https://www.w3.org/TR/webvtt1/#file-structure)
+    -->
+    <state name="cues">
+      <rule
+        pattern="(?:((?!&#45;&#45;&gt;)[^\r\n]+)?(\r?\n))?((?:\d{2}:)?(?:[0-5][0-9]):(?:[0-5][0-9])\.\d{3})([ \t]+)(&#45;&#45;&gt;)([ \t]+)((?:\d{2}:)?(?:[0-5][0-9]):(?:[0-5][0-9])\.\d{3})([ \t]*)">
+        <bygroups>
+          <token type="Name" />
+          <token type="Text" />
+          <token type="LiteralDate" />
+          <token type="Text" />
+          <token type="Operator" />
+          <token type="Text" />
+          <token type="LiteralDate" />
+          <token type="Text" />
+        </bygroups>
+        <push state="cue-settings-list" />
+      </rule>
+      <rule>
+        <include state="comment" />
+      </rule>
+    </state>
+
+    <!-- https://www.w3.org/TR/webvtt1/#webvtt-cue-settings-list -->
+    <state name="cue-settings-list">
+      <rule pattern="[ \t]+">
+        <token type="Text" />
+      </rule>
+      <rule pattern="(vertical)(:)?(rl|lr)?">
+        <bygroups>
+          <token type="Keyword" />
+          <token type="Punctuation" />
+          <token type="KeywordConstant" />
+        </bygroups>
+      </rule>
+      <rule
+        pattern="(line)(:)?(?:(?:((?:[1-9]?\d|100)(?:\.\d+)?)(%)|(-?\d+))(?:(,)(start|center|end))?)?">
+        <bygroups>
+          <token type="Keyword" />
+          <token type="Punctuation" />
+          <token type="Literal" />
+          <token type="KeywordType" />
+          <token type="Literal" />
+          <token type="Punctuation" />
+          <token type="KeywordConstant" />
+        </bygroups>
+      </rule>
+      <rule
+        pattern="(position)(:)?(?:(?:((?:[1-9]?\d|100)(?:\.\d+)?)(%)|(-?\d+))(?:(,)(line-left|center|line-right))?)?">
+        <bygroups>
+          <token type="Keyword" />
+          <token type="Punctuation" />
+          <token type="Literal" />
+          <token type="KeywordType" />
+          <token type="Literal" />
+          <token type="Punctuation" />
+          <token type="KeywordConstant" />
+        </bygroups>
+      </rule>
+      <rule pattern="(size)(:)?(?:((?:[1-9]?\d|100)(?:\.\d+)?)(%))?">
+        <bygroups>
+          <token type="Keyword" />
+          <token type="Punctuation" />
+          <token type="Literal" />
+          <token type="KeywordType" />
+        </bygroups>
+      </rule>
+      <rule pattern="(align)(:)?(start|center|end|left|right)?">
+        <bygroups>
+          <token type="Keyword" />
+          <token type="Punctuation" />
+          <token type="KeywordConstant" />
+        </bygroups>
+      </rule>
+      <rule pattern="(region)(:)?((?![^\r\n]*&#45;&#45;&gt;(?=[ \t]+?))[^ \t\r\n]+)?">
+        <bygroups>
+          <token type="Keyword" />
+          <token type="Punctuation" />
+          <token type="Literal" />
+        </bygroups>
+      </rule>
+      <rule
+        pattern="(?=\r?\n)">
+        <push state="cue-payload" />
+      </rule>
+    </state>
+
+    <!-- https://www.w3.org/TR/webvtt1/#cue-payload -->
+    <state name="cue-payload">
+      <rule pattern="(\r?\n){2,}">
+        <token type="Text" />
+        <pop depth="2" />
+      </rule>
+      <rule pattern="[^&lt;&amp;]+?">
+        <token type="Text" />
+      </rule>
+      <rule pattern="&amp;(#\d+|#x[0-9A-Fa-f]+|[a-zA-Z0-9]+);">
+        <token type="Text" />
+      </rule>
+      <rule pattern="(?=&lt;)">
+        <token type="Text" />
+        <push state="cue-span-tag" />
+      </rule>
+    </state>
+    <state name="cue-span-tag">
+      <rule
+        pattern="&lt;(?=c|i|b|u|ruby|rt|v|lang|(?:\d{2}:)?(?:[0-5][0-9]):(?:[0-5][0-9])\.\d{3})">
+        <token type="Punctuation" />
+        <push state="cue-span-start-tag-name" />
+      </rule>
+      <rule pattern="(&lt;/)(c|i|b|u|ruby|rt|v|lang)">
+        <bygroups>
+          <token type="Punctuation" />
+          <token type="NameTag" />
+        </bygroups>
+      </rule>
+      <rule pattern="&gt;">
+        <token type="Punctuation" />
+        <pop depth="1" />
+      </rule>
+    </state>
+    <state name="cue-span-start-tag-name">
+      <rule pattern="(c|i|b|u|ruby|rt)|((?:\d{2}:)?(?:[0-5][0-9]):(?:[0-5][0-9])\.\d{3})">
+        <bygroups>
+          <token type="NameTag" />
+          <token type="LiteralDate" />
+        </bygroups>
+        <push state="cue-span-classes-without-annotations" />
+      </rule>
+      <rule pattern="v|lang">
+        <token type="NameTag" />
+        <push state="cue-span-classes-with-annotations" />
+      </rule>
+    </state>
+    <state name="cue-span-classes-without-annotations">
+      <rule>
+        <include state="cue-span-classes" />
+      </rule>
+      <rule pattern="(?=&gt;)">
+        <pop depth="2" />
+      </rule>
+    </state>
+    <state name="cue-span-classes-with-annotations">
+      <rule>
+        <include state="cue-span-classes" />
+      </rule>
+      <rule pattern="(?=[ \t])">
+        <push state="cue-span-start-tag-annotations" />
+      </rule>
+    </state>
+    <state name="cue-span-classes">
+      <rule pattern="(\.)([^ \t\n\r&amp;&lt;&gt;\.]+)">
+        <bygroups>
+          <token type="Punctuation" />
+          <token type="NameTag" />
+        </bygroups>
+      </rule>
+    </state>
+    <state name="cue-span-start-tag-annotations">
+      <rule
+        pattern="[ \t](?:[^\n\r&amp;&gt;]|&amp;(?:#\d+|#x[0-9A-Fa-f]+|[a-zA-Z0-9]+);)+">
+        <token type="Text" />
+      </rule>
+      <rule pattern="(?=&gt;)">
+        <token type="Text" />
+        <pop depth="3" />
+      </rule>
+    </state>
+  </rules>
+</lexer>

lexers/yaml.xml

@@ -53,7 +53,7 @@
         <bygroups>
           <token type="Punctuation"/>
           <token type="LiteralStringDoc"/>
-          <token type="TextWhitespace"/>
+          <token type="Ignore"/>
         </bygroups>
       </rule>
       <rule pattern="(false|False|FALSE|true|True|TRUE|null|Off|off|yes|Yes|YES|OFF|On|ON|no|No|on|NO|n|N|Y|y)\b">

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: 0.6.4
+version: 0.12.0
 
 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

@@ -0,0 +1 @@
+.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

@@ -0,0 +1 @@
+.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/jinja+python/funko.py.j2

@@ -0,0 +1,11 @@
+from flask import Flask, request
+
+app = Flask("{{name}}")
+
+@app.route('/')
+def handle():
+    return "Hello World from Flask!"
+
+@app.route('/ping')
+def ping():
+    return "OK"

spec/examples/jinja+python/funko.py.j2.json

@@ -0,0 +1 @@
+[{"type":"KeywordNamespace","value":"from"},{"type":"Text","value":" "},{"type":"NameNamespace","value":"flask"},{"type":"Text","value":" "},{"type":"KeywordNamespace","value":"import"},{"type":"Text","value":" "},{"type":"Name","value":"Flask"},{"type":"Punctuation","value":","},{"type":"Text","value":" "},{"type":"Name","value":"request"},{"type":"Text","value":"\n\n"},{"type":"Name","value":"app"},{"type":"Text","value":" "},{"type":"Operator","value":"="},{"type":"Text","value":" "},{"type":"Name","value":"Flask"},{"type":"Punctuation","value":"("},{"type":"LiteralStringDouble","value":"\""},{"type":"CommentPreproc","value":"{{"},{"type":"NameVariable","value":"name"},{"type":"CommentPreproc","value":"}}"},{"type":"LiteralStringDouble","value":"\")"},{"type":"Text","value":"\n\n"},{"type":"NameDecorator","value":"@app.route"},{"type":"Punctuation","value":"("},{"type":"LiteralStringSingle","value":"'/'"},{"type":"Punctuation","value":")"},{"type":"Text","value":"\n"},{"type":"Keyword","value":"def"},{"type":"Text","value":" "},{"type":"NameFunction","value":"handle"},{"type":"Punctuation","value":"():"},{"type":"Text","value":"\n    "},{"type":"Keyword","value":"return"},{"type":"Text","value":" "},{"type":"LiteralStringDouble","value":"\"Hello World from Flask!\""},{"type":"Text","value":"\n\n"},{"type":"NameDecorator","value":"@app.route"},{"type":"Punctuation","value":"("},{"type":"LiteralStringSingle","value":"'/ping'"},{"type":"Punctuation","value":")"},{"type":"Text","value":"\n"},{"type":"Keyword","value":"def"},{"type":"Text","value":" "},{"type":"NameFunction","value":"ping"},{"type":"Punctuation","value":"():"},{"type":"Text","value":"\n    "},{"type":"Keyword","value":"return"},{"type":"Text","value":" "},{"type":"LiteralStringDouble","value":"\"OK\""},{"type":"Text","value":"\n"}]

spec/tartrazine_spec.cr

@@ -1,8 +1,15 @@
 require "./spec_helper"
+require "digest/sha1"
 
 # These are the testcases from Pygments
 testcases = Dir.glob("#{__DIR__}/tests/**/*txt").sort
 
+# These are custom testcases
+examples = Dir.glob("#{__DIR__}/examples/**/*.*").reject(&.ends_with? ".json").sort!
+
+# CSS Stylesheets
+css_files = Dir.glob("#{__DIR__}/css/*.css")
+
 # These lexers don't load because of parsing issues
 failing_lexers = {
   "webgpu_shading_language",
@@ -40,8 +47,13 @@ known_bad = {
   "#{__DIR__}/tests/bash_session/test_newline_in_ls_no_ps2.txt",
   "#{__DIR__}/tests/bash_session/test_newline_in_ls_ps2.txt",
   "#{__DIR__}/tests/bash_session/test_virtualenv.txt",
+  "#{__DIR__}/tests/mcfunction/commenting.txt",
+  "#{__DIR__}/tests/mcfunction/coordinates.txt",
   "#{__DIR__}/tests/mcfunction/data.txt",
+  "#{__DIR__}/tests/mcfunction/difficult_1.txt",
+  "#{__DIR__}/tests/mcfunction/multiline.txt",
   "#{__DIR__}/tests/mcfunction/selectors.txt",
+  "#{__DIR__}/tests/mcfunction/simple.txt",
 }
 
 # Tests that fail because of a limitation in PCRE2
@@ -51,6 +63,14 @@ not_my_fault = {
 
 describe Tartrazine do
   describe "Lexer" do
+    examples.each do |example|
+      it "parses #{example}".split("/")[-2...].join("/") do
+        lexer = Tartrazine.lexer(name: File.basename(File.dirname(example)).downcase)
+        text = File.read(example)
+        expected = Array(Tartrazine::Token).from_json(File.read("#{example}.json"))
+        Tartrazine::RegexLexer.collapse_tokens(lexer.tokenizer(text).to_a).should eq expected
+      end
+    end
     testcases.each do |testcase|
       if known_bad.includes?(testcase)
         pending "parses #{testcase}".split("/")[-2...].join("/") do
@@ -70,6 +90,17 @@ describe Tartrazine do
     end
   end
 
+  describe "formatter" do
+    css_files.each do |css_file|
+      it "generates #{css_file}" do
+        css = File.read(css_file)
+        theme = Tartrazine.theme(File.basename(css_file, ".css"))
+        formatter = Tartrazine::Html.new(theme: theme)
+        formatter.style_defs.strip.should eq css.strip
+      end
+    end
+  end
+
   describe "to_html" do
     it "should do basic highlighting" do
       html = Tartrazine.to_html("puts 'Hello, World!'", "ruby", standalone: false)
@@ -78,6 +109,7 @@ describe Tartrazine do
       )
     end
   end
+
   describe "to_ansi" do
     it "should do basic highlighting" do
       ansi = Tartrazine.to_ansi("puts 'Hello, World!'", "ruby")
@@ -89,11 +121,29 @@ 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

@@ -28,6 +28,13 @@ module Tartrazine
     property? surrounding_pre : Bool = true
     property? wrap_long_lines : Bool = false
     property weight_of_bold : Int32 = 600
+    property template : String = <<-TEMPLATE
+<!DOCTYPE html><html><head><style>
+{{style_defs}}
+</style></head><body>
+{{body}}
+</body></html>
+TEMPLATE
 
     property theme : Theme
 
@@ -42,7 +49,8 @@ module Tartrazine
                    @standalone : Bool = false,
                    @surrounding_pre : Bool = true,
                    @wrap_long_lines : Bool = false,
-                   @weight_of_bold : Int32 = 600)
+                   @weight_of_bold : Int32 = 600,
+                   @template : String = @template)
     end
 
     def format(text : String, lexer : Lexer) : String
@@ -61,11 +69,15 @@ module Tartrazine
     # Wrap text into a full HTML document, including the CSS for the theme
     def wrap_standalone
       output = String.build do |outp|
-        outp << "<!DOCTYPE html><html><head><style>"
-        outp << style_defs
-        outp << "</style></head><body>"
+        if @template.includes? "{{style_defs}}"
+          outp << @template.split("{{style_defs}}")[0]
+          outp << style_defs
+          outp << @template.split("{{style_defs}}")[1].split("{{body}}")[0]
+        else
+          outp << @template.split("{{body}}")[0]
+        end
       end
-      {output.to_s, "</body></html>"}
+      {output.to_s, @template.split("{{body}}")[1]}
     end
 
     private def line_label(i : Int32) : String
@@ -106,8 +118,7 @@ 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 == false
+          outp << "font-weight: #{@weight_of_bold};" if style.bold
           outp << "font-style: italic;" if style.italic
           outp << "font-style: normal;" if style.italic == false
           outp << "text-decoration: underline;" if style.underline
@@ -134,10 +145,5 @@ 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
@@ -337,6 +350,13 @@ module Tartrazine
   class CustomCrystalHighlighter < Crystal::SyntaxHighlighter
     @tokens = [] of Token
 
+    def highlight(text)
+      super
+    rescue ex : Crystal::SyntaxException
+      # Fallback to Ruby highlighting
+      @tokens = Tartrazine.lexer("ruby").tokenizer(text).to_a
+    end
+
     def render_delimiter(&block)
       @tokens << {type: "LiteralString", value: block.call.to_s}
     end

src/main.cr

@@ -4,13 +4,21 @@ 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]
-                          [-l lexer][-o output]
+  tartrazine FILE -f html [-t theme][--standalone [--template file]]
+                          [--line-numbers][-l lexer][-o output]
   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]
@@ -27,6 +35,7 @@ Options:
                       all style information. If not given, it will generate just
                       a HTML fragment ready to include in your own page.
   --css               Generate a CSS file for the theme called <theme>.css
+  --template <file>   Use a custom template for the HTML output [default: none]
   --line-numbers      Include line numbers in the output
   -h, --help          Show this screen
   -v, --version       Show version number
@@ -56,6 +65,12 @@ if options["--list-formatters"]
 end
 
 theme = Tartrazine.theme(options["-t"].as(String))
+template = options["--template"].as(String)
+if template != "none" # Otherwise we will use the default template
+  template = File.open(template).gets_to_end
+else
+  template = nil
+end
 
 if options["-f"]
   formatter = options["-f"].as(String)
@@ -65,12 +80,22 @@ if options["-f"]
     formatter.standalone = options["--standalone"] != nil
     formatter.line_numbers = options["--line-numbers"] != nil
     formatter.theme = theme
+    formatter.template = template if template
   when "terminal"
     formatter = Tartrazine::Ansi.new
     formatter.line_numbers = options["--line-numbers"] != nil
     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/run_tests.cr

@@ -1 +1 @@
-require "../spec/**"
+require "../spec/tartrazine_spec.cr"

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
@@ -22,8 +35,8 @@ module Tartrazine
     end
     begin
       Theme.from_xml(ThemeFiles.get("/#{name}.xml").gets_to_end)
-    rescue
-      raise Exception.new("Theme #{name} not found")
+    rescue ex : Exception
+      raise Exception.new("Error loading theme #{name}: #{ex.message}")
     end
   end
 

styles/github.xml

@@ -1,44 +1,39 @@
 <style name="github">
-  <entry type="Error" style="#a61717 bg:#e3d2d2"/>
+  <entry type="Error" style="#f6f8fa bg:#82071e"/>
   <entry type="Background" style="bg:#ffffff"/>
-  <entry type="Keyword" style="bold #000000"/>
-  <entry type="KeywordType" style="bold #445588"/>
-  <entry type="NameAttribute" style="#008080"/>
-  <entry type="NameBuiltin" style="#0086b3"/>
-  <entry type="NameBuiltinPseudo" style="#999999"/>
-  <entry type="NameClass" style="bold #445588"/>
-  <entry type="NameConstant" style="#008080"/>
-  <entry type="NameDecorator" style="bold #3c5d5d"/>
-  <entry type="NameEntity" style="#800080"/>
-  <entry type="NameException" style="bold #990000"/>
-  <entry type="NameFunction" style="bold #990000"/>
+  <entry type="Keyword" style="#cf222e"/>
+  <entry type="KeywordType" style="#cf222e"/>
+  <entry type="NameAttribute" style="#1f2328"/>
+  <entry type="NameBuiltin" style="#6639ba"/>
+  <entry type="NameBuiltinPseudo" style="#6a737d"/>
+  <entry type="NameClass" style="#1f2328"/>
+  <entry type="NameConstant" style="#0550ae"/>
+  <entry type="NameDecorator" style="#0550ae"/>
+  <entry type="NameEntity" style="#6639ba"/>
+  <entry type="NameFunction" style="#6639ba"/>
   <entry type="NameLabel" style="bold #990000"/>
-  <entry type="NameNamespace" style="#555555"/>
-  <entry type="NameTag" style="#000080"/>
-  <entry type="NameVariable" style="#008080"/>
-  <entry type="NameVariableClass" style="#008080"/>
-  <entry type="NameVariableGlobal" style="#008080"/>
-  <entry type="NameVariableInstance" style="#008080"/>
-  <entry type="LiteralString" style="#dd1144"/>
-  <entry type="LiteralStringRegex" style="#009926"/>
-  <entry type="LiteralStringSymbol" style="#990073"/>
-  <entry type="LiteralNumber" style="#009999"/>
-  <entry type="Operator" style="bold #000000"/>
-  <entry type="Comment" style="italic #999988"/>
-  <entry type="CommentMultiline" style="italic #999988"/>
-  <entry type="CommentSingle" style="italic #999988"/>
-  <entry type="CommentSpecial" style="bold italic #999999"/>
-  <entry type="CommentPreproc" style="bold #999999"/>
-  <entry type="GenericDeleted" style="#000000 bg:#ffdddd"/>
-  <entry type="GenericEmph" style="italic #000000"/>
-  <entry type="GenericError" style="#aa0000"/>
-  <entry type="GenericHeading" style="#999999"/>
-  <entry type="GenericInserted" style="#000000 bg:#ddffdd"/>
-  <entry type="GenericOutput" style="#888888"/>
-  <entry type="GenericPrompt" style="#555555"/>
-  <entry type="GenericStrong" style="bold"/>
-  <entry type="GenericSubheading" style="#aaaaaa"/>
-  <entry type="GenericTraceback" style="#aa0000"/>
+  <entry type="NameNamespace" style="#24292e"/>
+  <entry type="NameOther" style="#1f2328"/>
+  <entry type="NameTag" style="#0550ae"/>
+  <entry type="NameVariable" style="#953800"/>
+  <entry type="NameVariableClass" style="#953800"/>
+  <entry type="NameVariableGlobal" style="#953800"/>
+  <entry type="NameVariableInstance" style="#953800"/>
+  <entry type="LiteralString" style="#0a3069"/>
+  <entry type="LiteralStringRegex" style="#0a3069"/>
+  <entry type="LiteralStringSymbol" style="#032f62"/>
+  <entry type="LiteralNumber" style="#0550ae"/>
+  <entry type="Operator" style="#0550ae"/>
+  <entry type="Comment" style="#57606a"/>
+  <entry type="CommentMultiline" style="#57606a"/>
+  <entry type="CommentSingle" style="#57606a"/>
+  <entry type="CommentSpecial" style="#57606a"/>
+  <entry type="CommentPreproc" style="#57606a"/>
+  <entry type="GenericDeleted" style="#82071e bg:#ffebe9"/>
+  <entry type="GenericEmph" style="#1f2328"/>
+  <entry type="GenericInserted" style="#116329 bg:#dafbe1"/>
+  <entry type="GenericOutput" style="#1f2328"/>
   <entry type="GenericUnderline" style="underline"/>
-  <entry type="TextWhitespace" style="#bbbbbb"/>
+  <entry type="Punctuation" style="#1f2328"/>
+  <entry type="TextWhitespace" style="#ffffff"/>
 </style>

styles/onesenterprise.xml

@@ -0,0 +1,10 @@
+<style name="onesenterprise">
+  <entry type="Keyword" style="#ff0000"/>
+  <entry type="Name" style="#0000ff"/>
+  <entry type="LiteralString" style="#000000"/>
+  <entry type="Operator" style="#ff0000"/>
+  <entry type="Punctuation" style="#ff0000"/>
+  <entry type="Comment" style="#008000"/>
+  <entry type="CommentPreproc" style="#963200"/>
+  <entry type="Text" style="#000000"/>
+</style>

styles/pygments.xml

@@ -0,0 +1,42 @@
+<style name="pygments">
+  <entry type="Error" style="border:#ff0000"/>
+  <entry type="Keyword" style="bold #008000"/>
+  <entry type="KeywordPseudo" style="nobold"/>
+  <entry type="KeywordType" style="nobold #b00040"/>
+  <entry type="NameAttribute" style="#7d9029"/>
+  <entry type="NameBuiltin" style="#008000"/>
+  <entry type="NameClass" style="bold #0000ff"/>
+  <entry type="NameConstant" style="#880000"/>
+  <entry type="NameDecorator" style="#aa22ff"/>
+  <entry type="NameEntity" style="bold #999999"/>
+  <entry type="NameException" style="bold #d2413a"/>
+  <entry type="NameFunction" style="#0000ff"/>
+  <entry type="NameLabel" style="#a0a000"/>
+  <entry type="NameNamespace" style="bold #0000ff"/>
+  <entry type="NameTag" style="bold #008000"/>
+  <entry type="NameVariable" style="#19177c"/>
+  <entry type="LiteralString" style="#ba2121"/>
+  <entry type="LiteralStringDoc" style="italic"/>
+  <entry type="LiteralStringEscape" style="bold #bb6622"/>
+  <entry type="LiteralStringInterpol" style="bold #bb6688"/>
+  <entry type="LiteralStringOther" style="#008000"/>
+  <entry type="LiteralStringRegex" style="#bb6688"/>
+  <entry type="LiteralStringSymbol" style="#19177c"/>
+  <entry type="LiteralNumber" style="#666666"/>
+  <entry type="Operator" style="#666666"/>
+  <entry type="OperatorWord" style="bold #aa22ff"/>
+  <entry type="Comment" style="italic #408080"/>
+  <entry type="CommentPreproc" style="noitalic #bc7a00"/>
+  <entry type="GenericDeleted" style="#a00000"/>
+  <entry type="GenericEmph" style="italic"/>
+  <entry type="GenericError" style="#ff0000"/>
+  <entry type="GenericHeading" style="bold #000080"/>
+  <entry type="GenericInserted" style="#00a000"/>
+  <entry type="GenericOutput" style="#888888"/>
+  <entry type="GenericPrompt" style="bold #000080"/>
+  <entry type="GenericStrong" style="bold"/>
+  <entry type="GenericSubheading" style="bold #800080"/>
+  <entry type="GenericTraceback" style="#0044dd"/>
+  <entry type="GenericUnderline" style="underline"/>
+  <entry type="TextWhitespace" style="#bbbbbb"/>
+</style>