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

@@ -0,0 +1,26 @@
+name: Tests
+on:
+  # This can't yet run automatically, because tests fail because of
+  # different versions of chroma. Need to get the same one in my
+  # local env and in CI
+  workflow_dispatch:
+  push:
+permissions:
+  contents: read
+jobs:
+  build:
+    runs-on: ubuntu-22.04
+    steps:
+      - name: Download source
+        uses: actions/checkout@v4
+      - name: Install Crystal
+        uses: crystal-lang/install-crystal@v1
+      - name: Run tests
+        run: |
+          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
+          sudo mv chroma ~/.local/bin
+          shards install
+          crystal tool format --check
+          crystal spec -v

.github/workflows/coverage.yml

@@ -0,0 +1,30 @@
+name: Coverage
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: "0 1 * * *"
+permissions:
+  contents: read
+jobs:
+  build:
+    runs-on: ubuntu-22.04
+    steps:
+      - name: Download source
+        uses: actions/checkout@v4
+      - name: Install Crystal
+        uses: crystal-lang/install-crystal@v1
+      - name: Run tests using kcov
+        run: |
+          sudo apt update && sudo apt 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
+          sudo mv chroma ~/.local/bin
+          shards install
+          crystal build src/run_tests.cr
+          kcov --clean --include-path=./src $PWD/coverage ./run_tests
+          curl -Os https://uploader.codecov.io/latest/linux/codecov
+          chmod +x codecov
+          ./codecov -t ${CODECOV_TOKEN} -s coverage
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

.gitignore

@@ -7,3 +7,11 @@ chroma/
 pygments/
 shard.lock
 .vscode/
+.crystal/
+venv/
+.croupier
+coverage/
+run_tests
+
+# We use the internal crystal lexer
+lexers/crystal.xml

.md.rb

@@ -0,0 +1,3 @@
+exclude_rule 'MD033' # Inline HTML
+exclude_rule 'MD005' # 3-space indent for lists
+exclude_rule 'MD024' # Repeated headings

.mdlrc

@@ -0,0 +1 @@
+style ".md.rb"

.pre-commit-config.yaml

@@ -0,0 +1,35 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+
+repos:
+    - repo: https://github.com/pre-commit/pre-commit-hooks
+      rev: v4.6.0
+      hooks:
+          - id: trailing-whitespace
+          - id: end-of-file-fixer
+          - id: check-yaml
+          - id: check-added-large-files
+          - id: check-merge-conflict
+    - repo: https://github.com/jumanjihouse/pre-commit-hooks
+      rev: 3.0.0
+      hooks:
+          - id: shellcheck
+          - id: markdownlint
+            exclude: '^content'
+    - repo: https://github.com/mrtazz/checkmake
+      rev: 0.2.2
+      hooks:
+          - id: checkmake
+            exclude: lexers/makefile.xml
+    - repo: https://github.com/python-jsonschema/check-jsonschema
+      rev: 0.29.2
+      hooks:
+          - id: check-github-workflows
+    - repo: https://github.com/commitizen-tools/commitizen
+      rev: v3.29.0 # automatically updated by Commitizen
+      hooks:
+        - id: commitizen
+        - id: commitizen-branch
+          stages:
+            - post-commit
+            - push

CHANGELOG.md

@@ -0,0 +1,142 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+## [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
+- Git-cliff config
+- Started changelog
+- Force conventional commit messages
+- Force conventional commit messages
+- Updated pre-commit
+- *(ignore)* Fix tests
+- Added badges
+- Added badges
+- *(ignore)* Removed random file
+
+### Build
+
+- Switch from Makefile to Hacefile
+- Added do_release script
+- Fix markdown check
+
+### Bump
+
+- Release v0.6.4
+- Release v0.6.4
+
+## [0.6.1] - 2024-08-25
+
+### 📚 Documentation
+
+- Improve readme and help message
+
+<!-- generated by git-cliff -->

Hacefile.yml

@@ -0,0 +1,137 @@
+variables:
+  FLAGS: "-d --error-trace"
+  NAME: "tartrazine"
+
+tasks:
+  build:
+    default: true
+    dependencies:
+      - src
+      - shard.lock
+      - shard.yml
+      - Hacefile.yml
+      - lexers/*xml
+      - styles/*xml
+    outputs:
+      - bin/{{NAME}}
+    commands: |
+      shards build {{FLAGS}}
+
+  get-deps:
+    dependencies:
+      - shard.yml
+    outputs:
+      - shard.lock
+    commands: |
+      shards install
+
+  build-release:
+    phony: true
+    always_run: true
+    commands: |
+      hace build FLAGS="--release"
+
+  install:
+    phony: true
+    always_run: true
+    dependencies:
+      - bin/{{NAME}}
+    commands: |
+      rm ${HOME}/.local/bin/{{NAME}} -f
+      cp bin/{{NAME}} ${HOME}/.local/bin/{{NAME}}
+
+  static:
+    outputs:
+      - bin/{{NAME}}-static-linux-amd64
+      - bin/{{NAME}}-static-linux-arm64
+    commands: |
+      hace clean
+      ./build_static.sh
+
+  test:
+    dependencies:
+      - src
+      - spec
+      - shard.lock
+      - shard.yml
+    commands: |
+      crystal spec -v --error-trace
+    phony: true
+    always_run: true
+
+  lint:
+    dependencies:
+      - src
+      - spec
+      - shard.lock
+      - shard.yml
+    commands: |
+      crystal tool format src/*.cr spec/*.cr
+      ameba --fix
+    always_run: true
+    phony: true
+
+  docs:
+    dependencies:
+      - src
+      - shard.lock
+      - shard.yml
+      - README.md
+    commands: |
+      crystal docs
+    outputs:
+      - docs/index.html
+
+  pre-commit:
+    default: true
+    outputs:
+      - .git/hooks/commit-msg
+      - .git/hooks/pre-commit
+    dependencies:
+      - .pre-commit-config.yaml
+    commands: |
+      pre-commit install --hook-type commit-msg
+      pre-commit install
+
+  clean:
+    phony: true
+    always_run: true
+    commands: |
+      rm -rf shard.lock bin lib
+
+  coverage:
+    dependencies:
+      - src
+      - spec
+      - shard.lock
+      - shard.yml
+    commands: |
+      shards install
+      crystal build -o bin/run_tests src/run_tests.cr
+      rm -rf coverage/
+      mkdir coverage
+      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

Makefile

@@ -1,7 +0,0 @@
-build: $(wildcard src/**/*.cr) $(wildcard lexers/*xml) $(wildcard styles/*xml) shard.yml
-	shards build -Dstrict_multi_assign -Dno_number_autocast -d --error-trace
-release: $(wildcard src/**/*.cr) $(wildcard lexers/*xml) $(wildcard styles/*xml) shard.yml
-	shards build --release
-static: $(wildcard src/**/*.cr) $(wildcard lexers/*xml) $(wildcard styles/*xml) shard.yml
-	shards build --release --static
-	strip bin/tartrazine

README.md

@@ -1,45 +1,26 @@
 # TARTRAZINE
 
+[![Tests](https://github.com/ralsina/tartrazine/actions/workflows/ci.yml/badge.svg)](https://github.com/ralsina/tartrazine/actions/workflows/ci.yml)
+[![codecov](https://codecov.io/gh/ralsina/tartrazine/branch/main/graph/badge.svg?token=52XBPNL99F)](https://codecov.io/gh/ralsina/tartrazine)
+
 Tartrazine is a library to syntax-highlight code. It is
 a port of [Pygments](https://pygments.org/) to
-[Crystal](https://crystal-lang.org/). Kind of.
+[Crystal](https://crystal-lang.org/).
 
-It's not currently usable because it's not finished, but:
+It also provides a CLI tool which can be used to highlight many things in many styles.
 
-* The lexers work for the implemented languages
-* The provided styles work
-* There is a very very simple HTML formatter
-
-# A port of what? Why "kind of"?
-
-Because I did not read the Pygments code. And this is actually
-based on [Chroma](https://github.com/alecthomas/chroma) ...
-although I did not read that code either.
-
-Chroma has taken most of the Pygments lexers and turned them into
-XML descriptions. What I did was take those XML files from Chroma
-and a pile of test cases from Pygments, and I slapped them together
-until the tests passed and my code produced the same output as
-Chroma. Think of it as *extreme TDD*.
-
-Currently the pass rate for tests in the supported languages
-is `96.8%`, which is *not bad for a couple days hacking*.
-
-This only covers the RegexLexers, which are the most common ones,
-but it means the supported languages are a subset of Chroma's, which
-is a subset of Pygments'.
-
-Currently Tartrazine supports ... 241 languages.
-
-It has 331 themes (63 from Chroma, the rest are base16 themes via
-[Sixteen](https://github.com/ralsina/sixteen)
+Currently Tartrazine supports 247 languages and has 331 themes (63 from Chroma,
+the rest are base16 themes via [Sixteen](https://github.com/ralsina/sixteen)
 
 ## Installation
 
+If you are using Arch: Use yay or your favourite AUR helper, package name is `tartrazine`.
+
 From prebuilt binaries:
 
 Each release provides statically-linked binaries that should
-work on any Linux. Get them from the [releases page](https://github.com/ralsina/tartrazine/releases) and put them in your PATH.
+work on any Linux. Get them from the [releases page](https://github.com/ralsina/tartrazine/releases)
+and put them in your PATH.
 
 To build from source:
 
@@ -47,18 +28,132 @@ To build from source:
 2. Run `make` to build the `tartrazine` binary
 3. Copy the binary somewhere in your PATH.
 
-## Usage
+## Usage as a CLI tool
 
-This works:
+Show a syntax highlighted version of a C source file in your terminal:
+
+```shell
+tartrazine whatever.c -l c -t catppuccin-macchiato --line-numbers -f terminal
+```
+
+Generate a standalone HTML file from a C source file with the syntax highlighted:
+
+```shell
+$ tartrazine whatever.c -t catppuccin-macchiato --line-numbers \
+  --standalone -f html -o whatever.html
+```
+
+## Usage as a Library
+
+Add to your `shard.yml`:
+
+```yaml
+dependencies:
+  tartrazine:
+    github: ralsina/tartrazine
+```
+
+This is the high level API:
 
 ```crystal
 require "tartrazine"
 
-lexer = Tartrazine.lexer("crystal")
-theme = Tartrazine.theme("catppuccin-macchiato")
-puts Tartrazine::Html.new.format(File.read(ARGV[0]), lexer, theme)
+html = Tartrazine.to_html(
+  "puts \"Hello, world!\"",
+  language: "crystal",
+  theme: "catppuccin-macchiato",
+  standalone: true,
+  line_numbers: true
+)
 ```
 
+This does more or less the same thing, but more manually:
+
+```crystal
+lexer = Tartrazine.lexer("crystal")
+formatter = Tartrazine::Html.new(
+  theme: Tartrazine.theme("catppuccin-macchiato"),
+  line_numbers: true,
+  standalone: true,
+)
+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>)
@@ -69,4 +164,31 @@ puts Tartrazine::Html.new.format(File.read(ARGV[0]), lexer, theme)
 
 ## Contributors
 
-- [Roberto Alsina](https://github.com/ralsina) - creator and maintainer
+- [Roberto Alsina](https://github.com/ralsina) - creator and maintainer
+
+## A port of what, and why "kind of"
+
+Pygments is a staple of the Python ecosystem, and it's great.
+It lets you highlight code in many languages, and it has many
+themes. Chroma is "Pygments for Go", it's actually a port of
+Pygments to Go, and it's great too.
+
+I wanted that in Crystal, so I started this project. But I did
+not read much of the Pygments code. Or much of Chroma's.
+
+Chroma has taken most of the Pygments lexers and turned them into
+XML descriptions. What I did was take those XML files from Chroma
+and a pile of test cases from Pygments, and I slapped them together
+until the tests passed and my code produced the same output as
+Chroma. Think of it as [*extreme TDD*](https://ralsina.me/weblog/posts/tartrazine-reimplementing-pygments.html)
+
+Currently the pass rate for tests in the supported languages
+is `96.8%`, which is *not bad for a couple days hacking*.
+
+This only covers the RegexLexers, which are the most common ones,
+but it means the supported languages are a subset of Chroma's, which
+is a subset of Pygments' and DelegatingLexers (useful for things like template languages)
+
+Then performance was bad, so I hacked and hacked and made it significantly
+[faster than chroma](https://ralsina.me/weblog/posts/a-tale-of-optimization.html)
+which is fun.

TODO.md

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

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 && make static"
+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 && make static"
+docker run -ti --rm -v "$PWD":/app --platform linux/arm64 --user="$UID" tartrazine-builder /bin/sh -c "cd /app && rm -rf lib shard.lock && shards build --static --release && strip bin/tartrazine"
 mv bin/tartrazine bin/tartrazine-static-linux-arm64

cliff.toml

@@ -0,0 +1,79 @@
+# git-cliff ~ default configuration file
+# https://git-cliff.org/docs/configuration
+#
+# Lines starting with "#" are comments.
+# Configuration options are organized into tables and keys.
+# See documentation for more information on available options.
+
+[changelog]
+# template for the changelog header
+header = """
+# Changelog\n
+All notable changes to this project will be documented in this file.\n
+"""
+# template for the changelog body
+# https://keats.github.io/tera/docs/#introduction
+body = """
+{% if version %}\
+    ## [{{ version | trim_start_matches(pat="v") }}] - {{ timestamp | date(format="%Y-%m-%d") }}
+{% else %}\
+    ## [unreleased]
+{% endif %}\
+{% for group, commits in commits | group_by(attribute="group") %}
+    ### {{ group | striptags | trim | upper_first }}
+    {% for commit in commits %}
+        - {% if commit.scope %}*({{ commit.scope }})* {% endif %}\
+            {% if commit.breaking %}[**breaking**] {% endif %}\
+            {{ commit.message | upper_first }}\
+    {% endfor %}
+{% endfor %}\n
+"""
+# template for the changelog footer
+footer = """
+<!-- generated by git-cliff -->
+"""
+# remove the leading and trailing s
+trim = true
+# postprocessors
+postprocessors = [
+  # { pattern = '<REPO>', replace = "https://github.com/orhun/git-cliff" }, # replace repository URL
+]
+
+[git]
+# parse the commits based on https://www.conventionalcommits.org
+conventional_commits = true
+# filter out the commits that are not conventional
+filter_unconventional = true
+# process each line of a commit as an individual commit
+split_commits = false
+# regex for preprocessing the commit messages
+commit_preprocessors = [
+  # Replace issue numbers
+  #{ pattern = '\((\w+\s)?#([0-9]+)\)', replace = "([#${2}](<REPO>/issues/${2}))"},
+  # Check spelling of the commit with https://github.com/crate-ci/typos
+  # If the spelling is incorrect, it will be automatically fixed.
+  #{ pattern = '.*', replace_command = 'typos --write-changes -' },
+]
+# regex for parsing and grouping commits
+commit_parsers = [
+  { message = "^feat", group = "<!-- 0 -->🚀 Features" },
+  { message = "^fix", group = "<!-- 1 -->🐛 Bug Fixes" },
+  { message = "^doc", group = "<!-- 3 -->📚 Documentation" },
+  { message = "^perf", group = "<!-- 4 -->⚡ Performance" },
+  { message = "^refactor", group = "<!-- 2 -->🚜 Refactor" },
+  { message = "^style", group = "<!-- 5 -->🎨 Styling" },
+  { message = "^test", group = "<!-- 6 -->🧪 Testing" },
+  { message = "^chore\\(release\\): prepare for", skip = true },
+  { message = "^chore\\(deps.*\\)", skip = true },
+  { message = "^chore\\(pr\\)", skip = true },
+  { message = "^chore\\(pull\\)", skip = true },
+  { message = "^chore|^ci", group = "<!-- 7 -->⚙️ Miscellaneous Tasks" },
+  { body = ".*security", group = "<!-- 8 -->🛡️ Security" },
+  { message = "^revert", group = "<!-- 9 -->◀️ Revert" },
+]
+# filter out the commits that are not matched by commit parsers
+filter_commits = false
+# sort the tags topologically
+topo_order = false
+# sort the commits inside sections by oldest/newest order
+sort_commits = "oldest"

do_release.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+set e
+
+PKGNAME=$(basename "$PWD")
+VERSION=$(git cliff --bumped-version --unreleased |cut -dv -f2)
+
+sed "s/^version:.*$/version: $VERSION/g" -i shard.yml
+git add shard.yml
+hace lint test
+git cliff --bump -u -p CHANGELOG.md
+git commit -a -m "bump: Release v$VERSION"
+hace static
+git tag "v$VERSION"
+git push --tags
+gh release create "v$VERSION" "bin/$PKGNAME-static-linux-amd64" "bin/$PKGNAME-static-linux-arm64" --title "Release v$VERSION" --notes "$(git cliff -l -s all)"

lexers/LICENSE-heuristics

@@ -0,0 +1,22 @@
+Copyright (c) 2017 GitHub, Inc.
+
+Permission is hereby granted, free of charge, to any person
+obtaining a copy of this software and associated documentation
+files (the "Software"), to deal in the Software without
+restriction, including without limitation the rights to use,
+copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the
+Software is furnished to do so, subject to the following
+conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+OTHER DEALINGS IN THE SOFTWARE.

lexers/LiquidLexer.xml

@@ -0,0 +1,129 @@
+
+<lexer>
+  <config>
+    <name>liquid</name>
+    <alias>liquid</alias>
+    <filename>*.liquid</filename>
+  </config>
+  <rules>
+    <state name="root">
+      <rule pattern="[^{]+"><token type="Text"/></rule>
+      <rule pattern="(\{%)(\s*)"><bygroups><token type="Punctuation"/><token type="TextWhitespace"/></bygroups><push state="tag-or-block"/></rule>
+      <rule pattern="(\{\{)(\s*)([^\s}]+)"><bygroups><token type="Punctuation"/><token type="TextWhitespace"/><usingself state="generic"/></bygroups><push state="output"/></rule>
+      <rule pattern="\{"><token type="Text"/></rule>
+    </state>
+    <state name="tag-or-block">
+      <rule pattern="(if|unless|elsif|case)(?=\s+)"><token type="KeywordReserved"/><push state="condition"/></rule>
+      <rule pattern="(when)(\s+)"><bygroups><token type="KeywordReserved"/><token type="TextWhitespace"/></bygroups><combined state="end-of-block" state="whitespace" state="generic"/></rule>
+      <rule pattern="(else)(\s*)(%\})"><bygroups><token type="KeywordReserved"/><token type="TextWhitespace"/><token type="Punctuation"/></bygroups><pop depth="1"/></rule>
+      <rule pattern="(capture)(\s+)([^\s%]+)(\s*)(%\})"><bygroups><token type="NameTag"/><token type="TextWhitespace"/><usingself state="variable"/><token type="TextWhitespace"/><token type="Punctuation"/></bygroups><pop depth="1"/></rule>
+      <rule pattern="(comment)(\s*)(%\})"><bygroups><token type="NameTag"/><token type="TextWhitespace"/><token type="Punctuation"/></bygroups><push state="comment"/></rule>
+      <rule pattern="(raw)(\s*)(%\})"><bygroups><token type="NameTag"/><token type="TextWhitespace"/><token type="Punctuation"/></bygroups><push state="raw"/></rule>
+      <rule pattern="(end(case|unless|if))(\s*)(%\})"><bygroups><token type="KeywordReserved"/>None<token type="TextWhitespace"/><token type="Punctuation"/></bygroups><pop depth="1"/></rule>
+      <rule pattern="(end([^\s%]+))(\s*)(%\})"><bygroups><token type="NameTag"/>None<token type="TextWhitespace"/><token type="Punctuation"/></bygroups><pop depth="1"/></rule>
+      <rule pattern="(cycle)(\s+)(?:([^\s:]*)(:))?(\s*)"><bygroups><token type="NameTag"/><token type="TextWhitespace"/><usingself state="generic"/><token type="Punctuation"/><token type="TextWhitespace"/></bygroups><push state="variable-tag-markup"/></rule>
+      <rule pattern="([^\s%]+)(\s*)"><bygroups><token type="NameTag"/><token type="TextWhitespace"/></bygroups><push state="tag-markup"/></rule>
+    </state>
+    <state name="output">
+      <rule><include state="whitespace"/></rule>
+      <rule pattern="\}\}"><token type="Punctuation"/><pop depth="1"/></rule>
+      <rule pattern="\|"><token type="Punctuation"/><push state="filters"/></rule>
+    </state>
+    <state name="filters">
+      <rule><include state="whitespace"/></rule>
+      <rule pattern="\}\}"><token type="Punctuation"/><push state="#pop" state="#pop"/></rule>
+      <rule pattern="([^\s|:]+)(:?)(\s*)"><bygroups><token type="NameFunction"/><token type="Punctuation"/><token type="TextWhitespace"/></bygroups><push state="filter-markup"/></rule>
+    </state>
+    <state name="filter-markup">
+      <rule pattern="\|"><token type="Punctuation"/><pop depth="1"/></rule>
+      <rule><include state="end-of-tag"/></rule>
+      <rule><include state="default-param-markup"/></rule>
+    </state>
+    <state name="condition">
+      <rule><include state="end-of-block"/></rule>
+      <rule><include state="whitespace"/></rule>
+      <rule pattern="([^\s=!&gt;&lt;]+)(\s*)([=!&gt;&lt;]=?)(\s*)(\S+)(\s*)(%\})"><bygroups><usingself state="generic"/><token type="TextWhitespace"/><token type="Operator"/><token type="TextWhitespace"/><usingself state="generic"/><token type="TextWhitespace"/><token type="Punctuation"/></bygroups></rule>
+      <rule pattern="\b!"><token type="Operator"/></rule>
+      <rule pattern="\bnot\b"><token type="OperatorWord"/></rule>
+      <rule pattern="([\w.\&#x27;&quot;]+)(\s+)(contains)(\s+)([\w.\&#x27;&quot;]+)"><bygroups><usingself state="generic"/><token type="TextWhitespace"/><token type="OperatorWord"/><token type="TextWhitespace"/><usingself state="generic"/></bygroups></rule>
+      <rule><include state="generic"/></rule>
+      <rule><include state="whitespace"/></rule>
+    </state>
+    <state name="generic-value">
+      <rule><include state="generic"/></rule>
+      <rule><include state="end-at-whitespace"/></rule>
+    </state>
+    <state name="operator">
+      <rule pattern="(\s*)((=|!|&gt;|&lt;)=?)(\s*)"><bygroups><token type="TextWhitespace"/><token type="Operator"/>None<token type="TextWhitespace"/></bygroups><pop depth="1"/></rule>
+      <rule pattern="(\s*)(\bcontains\b)(\s*)"><bygroups><token type="TextWhitespace"/><token type="OperatorWord"/><token type="TextWhitespace"/></bygroups><pop depth="1"/></rule>
+    </state>
+    <state name="end-of-tag">
+      <rule pattern="\}\}"><token type="Punctuation"/><pop depth="1"/></rule>
+    </state>
+    <state name="end-of-block">
+      <rule pattern="%\}"><token type="Punctuation"/><push state="#pop" state="#pop"/></rule>
+    </state>
+    <state name="end-at-whitespace">
+      <rule pattern="\s+"><token type="TextWhitespace"/><pop depth="1"/></rule>
+    </state>
+    <state name="param-markup">
+      <rule><include state="whitespace"/></rule>
+      <rule pattern="([^\s=:]+)(\s*)(=|:)"><bygroups><token type="NameAttribute"/><token type="TextWhitespace"/><token type="Operator"/></bygroups></rule>
+      <rule pattern="(\{\{)(\s*)([^\s}])(\s*)(\}\})"><bygroups><token type="Punctuation"/><token type="TextWhitespace"/><usingself state="variable"/><token type="TextWhitespace"/><token type="Punctuation"/></bygroups></rule>
+      <rule><include state="string"/></rule>
+      <rule><include state="number"/></rule>
+      <rule><include state="keyword"/></rule>
+      <rule pattern=","><token type="Punctuation"/></rule>
+    </state>
+    <state name="default-param-markup">
+      <rule><include state="param-markup"/></rule>
+      <rule pattern="."><token type="Text"/></rule>
+    </state>
+    <state name="variable-param-markup">
+      <rule><include state="param-markup"/></rule>
+      <rule><include state="variable"/></rule>
+      <rule pattern="."><token type="Text"/></rule>
+    </state>
+    <state name="tag-markup">
+      <rule pattern="%\}"><token type="Punctuation"/><push state="#pop" state="#pop"/></rule>
+      <rule><include state="default-param-markup"/></rule>
+    </state>
+    <state name="variable-tag-markup">
+      <rule pattern="%\}"><token type="Punctuation"/><push state="#pop" state="#pop"/></rule>
+      <rule><include state="variable-param-markup"/></rule>
+    </state>
+    <state name="keyword">
+      <rule pattern="\b(false|true)\b"><token type="KeywordConstant"/></rule>
+    </state>
+    <state name="variable">
+      <rule pattern="[a-zA-Z_]\w*"><token type="NameVariable"/></rule>
+      <rule pattern="(?&lt;=\w)\.(?=\w)"><token type="Punctuation"/></rule>
+    </state>
+    <state name="string">
+      <rule pattern="&#x27;[^&#x27;]*&#x27;"><token type="LiteralStringSingle"/></rule>
+      <rule pattern="&quot;[^&quot;]*&quot;"><token type="LiteralStringDouble"/></rule>
+    </state>
+    <state name="number">
+      <rule pattern="\d+\.\d+"><token type="LiteralNumberFloat"/></rule>
+      <rule pattern="\d+"><token type="LiteralNumberInteger"/></rule>
+    </state>
+    <state name="generic">
+      <rule><include state="keyword"/></rule>
+      <rule><include state="string"/></rule>
+      <rule><include state="number"/></rule>
+      <rule><include state="variable"/></rule>
+    </state>
+    <state name="whitespace">
+      <rule pattern="[ \t]+"><token type="TextWhitespace"/></rule>
+    </state>
+    <state name="comment">
+      <rule pattern="(\{%)(\s*)(endcomment)(\s*)(%\})"><bygroups><token type="Punctuation"/><token type="TextWhitespace"/><token type="NameTag"/><token type="TextWhitespace"/><token type="Punctuation"/></bygroups><push state="#pop" state="#pop"/></rule>
+      <rule pattern="."><token type="Comment"/></rule>
+    </state>
+    <state name="raw">
+      <rule pattern="[^{]+"><token type="Text"/></rule>
+      <rule pattern="(\{%)(\s*)(endraw)(\s*)(%\})"><bygroups><token type="Punctuation"/><token type="TextWhitespace"/><token type="NameTag"/><token type="TextWhitespace"/><token type="Punctuation"/></bygroups><pop depth="1"/></rule>
+      <rule pattern="\{"><token type="Text"/></rule>
+    </state>
+  </rules>
+</lexer>

lexers/VelocityLexer.xml

@@ -0,0 +1,54 @@
+
+<lexer>
+  <config>
+    <name>Velocity</name>
+    <alias>velocity</alias>
+    <filename>*.vm</filename>
+    <filename>*.fhtml</filename>
+    <dot_all>true</dot_all>
+  </config>
+  <rules>
+    <state name="root">
+      <rule pattern="[^{#$]+"><token type="Other"/></rule>
+      <rule pattern="(#)(\*.*?\*)(#)"><bygroups><token type="CommentPreproc"/><token type="Comment"/><token type="CommentPreproc"/></bygroups></rule>
+      <rule pattern="(##)(.*?$)"><bygroups><token type="CommentPreproc"/><token type="Comment"/></bygroups></rule>
+      <rule pattern="(#\{?)([a-zA-Z_]\w*)(\}?)(\s?\()"><bygroups><token type="CommentPreproc"/><token type="NameFunction"/><token type="CommentPreproc"/><token type="Punctuation"/></bygroups><push state="directiveparams"/></rule>
+      <rule pattern="(#\{?)([a-zA-Z_]\w*)(\}|\b)"><bygroups><token type="CommentPreproc"/><token type="NameFunction"/><token type="CommentPreproc"/></bygroups></rule>
+      <rule pattern="\$!?\{?"><token type="Punctuation"/><push state="variable"/></rule>
+    </state>
+    <state name="variable">
+      <rule pattern="[a-zA-Z_]\w*"><token type="NameVariable"/></rule>
+      <rule pattern="\("><token type="Punctuation"/><push state="funcparams"/></rule>
+      <rule pattern="(\.)([a-zA-Z_]\w*)"><bygroups><token type="Punctuation"/><token type="NameVariable"/></bygroups><push/></rule>
+      <rule pattern="\}"><token type="Punctuation"/><pop depth="1"/></rule>
+      <rule><pop depth="1"/></rule>
+    </state>
+    <state name="directiveparams">
+      <rule pattern="(&amp;&amp;|\|\||==?|!=?|[-&lt;&gt;+*%&amp;|^/])|\b(eq|ne|gt|lt|ge|le|not|in)\b"><token type="Operator"/></rule>
+      <rule pattern="\["><token type="Operator"/><push state="rangeoperator"/></rule>
+      <rule pattern="\b[a-zA-Z_]\w*\b"><token type="NameFunction"/></rule>
+      <rule><include state="funcparams"/></rule>
+    </state>
+    <state name="rangeoperator">
+      <rule pattern="\.\."><token type="Operator"/></rule>
+      <rule><include state="funcparams"/></rule>
+      <rule pattern="\]"><token type="Operator"/><pop depth="1"/></rule>
+    </state>
+    <state name="funcparams">
+      <rule pattern="\$!?\{?"><token type="Punctuation"/><push state="variable"/></rule>
+      <rule pattern="\s+"><token type="Text"/></rule>
+      <rule pattern="[,:]"><token type="Punctuation"/></rule>
+      <rule pattern="&quot;(\\\\|\\[^\\]|[^&quot;\\])*&quot;"><token type="LiteralStringDouble"/></rule>
+      <rule pattern="&#x27;(\\\\|\\[^\\]|[^&#x27;\\])*&#x27;"><token type="LiteralStringSingle"/></rule>
+      <rule pattern="0[xX][0-9a-fA-F]+[Ll]?"><token type="LiteralNumber"/></rule>
+      <rule pattern="\b[0-9]+\b"><token type="LiteralNumber"/></rule>
+      <rule pattern="(true|false|null)\b"><token type="KeywordConstant"/></rule>
+      <rule pattern="\("><token type="Punctuation"/><push/></rule>
+      <rule pattern="\)"><token type="Punctuation"/><pop depth="1"/></rule>
+      <rule pattern="\{"><token type="Punctuation"/><push/></rule>
+      <rule pattern="\}"><token type="Punctuation"/><pop depth="1"/></rule>
+      <rule pattern="\["><token type="Punctuation"/><push/></rule>
+      <rule pattern="\]"><token type="Punctuation"/><pop depth="1"/></rule>
+    </state>
+  </rules>
+</lexer>

lexers/abap.xml

@@ -151,4 +151,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/abnf.xml

@@ -63,4 +63,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/actionscript.xml

@@ -65,4 +65,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/actionscript_3.xml

@@ -160,4 +160,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/ada.xml

@@ -318,4 +318,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/agda.xml

@@ -63,4 +63,3 @@
     </state>
   </rules>
 </lexer>
-

lexers/al.xml

@@ -72,4 +72,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/alloy.xml

@@ -55,4 +55,3 @@
     </state>
   </rules>
 </lexer>
-

lexers/angular2.xml

@@ -105,4 +105,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/antlr.xml

@@ -314,4 +314,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/apacheconf.xml

@@ -71,4 +71,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/apl.xml

@@ -56,4 +56,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/applescript.xml

@@ -127,4 +127,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/arangodb_aql.xml

@@ -171,4 +171,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/arduino.xml

@@ -306,4 +306,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/armasm.xml

@@ -123,4 +123,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

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/autohotkey.xml

@@ -75,4 +75,3 @@
     </state>
   </rules>
 </lexer>
-

lexers/autoit.xml

@@ -67,4 +67,3 @@
     </state>
   </rules>
 </lexer>
-

lexers/awk.xml

@@ -92,4 +92,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/ballerina.xml

@@ -94,4 +94,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/bash.xml

@@ -217,4 +217,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/bash_session.xml

@@ -22,4 +22,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/batchfile.xml

@@ -657,4 +657,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/bbcode.xml

@@ -0,0 +1,21 @@
+
+<lexer>
+  <config>
+    <name>BBCode</name>
+    <alias>bbcode</alias>
+    <mime_type>text/x-bbcode</mime_type>
+  </config>
+  <rules>
+    <state name="root">
+      <rule pattern="[^[]+"><token type="Text"/></rule>
+      <rule pattern="\[/?\w+"><token type="Keyword"/><push state="tag"/></rule>
+      <rule pattern="\["><token type="Text"/></rule>
+    </state>
+    <state name="tag">
+      <rule pattern="\s+"><token type="Text"/></rule>
+      <rule pattern="(\w+)(=)(&quot;?[^\s&quot;\]]+&quot;?)"><bygroups><token type="NameAttribute"/><token type="Operator"/><token type="LiteralString"/></bygroups></rule>
+      <rule pattern="(=)(&quot;?[^\s&quot;\]]+&quot;?)"><bygroups><token type="Operator"/><token type="LiteralString"/></bygroups></rule>
+      <rule pattern="\]"><token type="Keyword"/><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/bibtex.xml

@@ -149,4 +149,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/bicep.xml

@@ -81,4 +81,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/blitzbasic.xml

@@ -138,4 +138,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/bnf.xml

@@ -25,4 +25,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/bqn.xml

@@ -80,4 +80,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/brainfuck.xml

@@ -48,4 +48,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/c#.xml

@@ -118,4 +118,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/c++.xml

@@ -328,4 +328,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/cap_n_proto.xml

@@ -119,4 +119,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/cassandra_cql.xml

@@ -134,4 +134,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/ceylon.xml

@@ -148,4 +148,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/cfstatement.xml

@@ -89,4 +89,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/chaiscript.xml

@@ -131,4 +131,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/chapel.xml

@@ -140,4 +140,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/cheetah.xml

@@ -52,4 +52,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/cmake.xml

@@ -87,4 +87,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/cobol.xml

@@ -87,4 +87,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/coffeescript.xml

@@ -207,4 +207,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/common_lisp.xml

@@ -181,4 +181,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/coq.xml

@@ -133,4 +133,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/crystal.xml

@@ -1,762 +0,0 @@
-<lexer>
-  <config>
-    <name>Crystal</name>
-    <alias>cr</alias>
-    <alias>crystal</alias>
-    <filename>*.cr</filename>
-    <mime_type>text/x-crystal</mime_type>
-    <dot_all>true</dot_all>
-  </config>
-  <rules>
-    <state name="pa-intp-string">
-      <rule pattern="\\[\(]">
-        <token type="LiteralStringOther"/>
-      </rule>
-      <rule pattern="\(">
-        <token type="LiteralStringOther"/>
-        <push/>
-      </rule>
-      <rule pattern="\)">
-        <token type="LiteralStringOther"/>
-        <pop depth="1"/>
-      </rule>
-      <rule>
-        <include state="string-intp-escaped"/>
-      </rule>
-      <rule pattern="[\\#()]">
-        <token type="LiteralStringOther"/>
-      </rule>
-      <rule pattern="[^\\#()]+">
-        <token type="LiteralStringOther"/>
-      </rule>
-    </state>
-    <state name="ab-regex">
-      <rule pattern="\\[\\&lt;&gt;]">
-        <token type="LiteralStringRegex"/>
-      </rule>
-      <rule pattern="&lt;">
-        <token type="LiteralStringRegex"/>
-        <push/>
-      </rule>
-      <rule pattern="&gt;[imsx]*">
-        <token type="LiteralStringRegex"/>
-        <pop depth="1"/>
-      </rule>
-      <rule>
-        <include state="string-intp"/>
-      </rule>
-      <rule pattern="[\\#&lt;&gt;]">
-        <token type="LiteralStringRegex"/>
-      </rule>
-      <rule pattern="[^\\#&lt;&gt;]+">
-        <token type="LiteralStringRegex"/>
-      </rule>
-    </state>
-    <state name="cb-regex">
-      <rule pattern="\\[\\{}]">
-        <token type="LiteralStringRegex"/>
-      </rule>
-      <rule pattern="\{">
-        <token type="LiteralStringRegex"/>
-        <push/>
-      </rule>
-      <rule pattern="\}[imsx]*">
-        <token type="LiteralStringRegex"/>
-        <pop depth="1"/>
-      </rule>
-      <rule>
-        <include state="string-intp"/>
-      </rule>
-      <rule pattern="[\\#{}]">
-        <token type="LiteralStringRegex"/>
-      </rule>
-      <rule pattern="[^\\#{}]+">
-        <token type="LiteralStringRegex"/>
-      </rule>
-    </state>
-    <state name="simple-backtick">
-      <rule>
-        <include state="string-intp-escaped"/>
-      </rule>
-      <rule pattern="[^\\`#]+">
-        <token type="LiteralStringBacktick"/>
-      </rule>
-      <rule pattern="[\\#]">
-        <token type="LiteralStringBacktick"/>
-      </rule>
-      <rule pattern="`">
-        <token type="LiteralStringBacktick"/>
-        <pop depth="1"/>
-      </rule>
-    </state>
-    <state name="string-intp">
-      <rule pattern="#\{">
-        <token type="LiteralStringInterpol"/>
-        <push state="in-intp"/>
-      </rule>
-    </state>
-    <state name="interpolated-regex">
-      <rule>
-        <include state="string-intp"/>
-      </rule>
-      <rule pattern="[\\#]">
-        <token type="LiteralStringRegex"/>
-      </rule>
-      <rule pattern="[^\\#]+">
-        <token type="LiteralStringRegex"/>
-      </rule>
-    </state>
-    <state name="cb-string">
-      <rule pattern="\\[\\{}]">
-        <token type="LiteralStringOther"/>
-      </rule>
-      <rule pattern="\{">
-        <token type="LiteralStringOther"/>
-        <push/>
-      </rule>
-      <rule pattern="\}">
-        <token type="LiteralStringOther"/>
-        <pop depth="1"/>
-      </rule>
-      <rule pattern="[\\#{}]">
-        <token type="LiteralStringOther"/>
-      </rule>
-      <rule pattern="[^\\#{}]+">
-        <token type="LiteralStringOther"/>
-      </rule>
-    </state>
-    <state name="in-macro-control">
-      <rule pattern="\{%">
-        <token type="LiteralStringInterpol"/>
-        <push/>
-      </rule>
-      <rule pattern="%\}">
-        <token type="LiteralStringInterpol"/>
-        <pop depth="1"/>
-      </rule>
-      <rule pattern="for\b|in\b">
-        <token type="Keyword"/>
-      </rule>
-      <rule>
-        <include state="root"/>
-      </rule>
-    </state>
-    <state name="interpolated-string">
-      <rule>
-        <include state="string-intp"/>
-      </rule>
-      <rule pattern="[\\#]">
-        <token type="LiteralStringOther"/>
-      </rule>
-      <rule pattern="[^\\#]+">
-        <token type="LiteralStringOther"/>
-      </rule>
-    </state>
-    <state name="in-macro-expr">
-      <rule pattern="\{\{">
-        <token type="LiteralStringInterpol"/>
-        <push/>
-      </rule>
-      <rule pattern="\}\}">
-        <token type="LiteralStringInterpol"/>
-        <pop depth="1"/>
-      </rule>
-      <rule>
-        <include state="root"/>
-      </rule>
-    </state>
-    <state name="simple-string">
-      <rule>
-        <include state="string-intp-escaped"/>
-      </rule>
-      <rule pattern="[^\\&#34;#]+">
-        <token type="LiteralStringDouble"/>
-      </rule>
-      <rule pattern="[\\#]">
-        <token type="LiteralStringDouble"/>
-      </rule>
-      <rule pattern="&#34;">
-        <token type="LiteralStringDouble"/>
-        <pop depth="1"/>
-      </rule>
-    </state>
-    <state name="cb-intp-string">
-      <rule pattern="\\[\{]">
-        <token type="LiteralStringOther"/>
-      </rule>
-      <rule pattern="\{">
-        <token type="LiteralStringOther"/>
-        <push/>
-      </rule>
-      <rule pattern="\}">
-        <token type="LiteralStringOther"/>
-        <pop depth="1"/>
-      </rule>
-      <rule>
-        <include state="string-intp-escaped"/>
-      </rule>
-      <rule pattern="[\\#{}]">
-        <token type="LiteralStringOther"/>
-      </rule>
-      <rule pattern="[^\\#{}]+">
-        <token type="LiteralStringOther"/>
-      </rule>
-    </state>
-    <state name="string-intp-escaped">
-      <rule>
-        <include state="string-intp"/>
-      </rule>
-      <rule>
-        <include state="string-escaped"/>
-      </rule>
-    </state>
-    <state name="sb-regex">
-      <rule pattern="\\[\\\[\]]">
-        <token type="LiteralStringRegex"/>
-      </rule>
-      <rule pattern="\[">
-        <token type="LiteralStringRegex"/>
-        <push/>
-      </rule>
-      <rule pattern="\][imsx]*">
-        <token type="LiteralStringRegex"/>
-        <pop depth="1"/>
-      </rule>
-      <rule>
-        <include state="string-intp"/>
-      </rule>
-      <rule pattern="[\\#\[\]]">
-        <token type="LiteralStringRegex"/>
-      </rule>
-      <rule pattern="[^\\#\[\]]+">
-        <token type="LiteralStringRegex"/>
-      </rule>
-    </state>
-    <state name="classname">
-      <rule pattern="[A-Z_]\w*">
-        <token type="NameClass"/>
-      </rule>
-      <rule pattern="(\()(\s*)([A-Z_]\w*)(\s*)(\))">
-        <bygroups>
-          <token type="Punctuation"/>
-          <token type="Text"/>
-          <token type="NameClass"/>
-          <token type="Text"/>
-          <token type="Punctuation"/>
-        </bygroups>
-      </rule>
-      <rule>
-        <pop depth="1"/>
-      </rule>
-    </state>
-    <state name="string-escaped">
-      <rule pattern="\\([\\befnstv#&#34;\&#39;]|x[a-fA-F0-9]{1,2}|[0-7]{1,3})">
-        <token type="LiteralStringEscape"/>
-      </rule>
-    </state>
-    <state name="sb-intp-string">
-      <rule pattern="\\[\[]">
-        <token type="LiteralStringOther"/>
-      </rule>
-      <rule pattern="\[">
-        <token type="LiteralStringOther"/>
-        <push/>
-      </rule>
-      <rule pattern="\]">
-        <token type="LiteralStringOther"/>
-        <pop depth="1"/>
-      </rule>
-      <rule>
-        <include state="string-intp-escaped"/>
-      </rule>
-      <rule pattern="[\\#\[\]]">
-        <token type="LiteralStringOther"/>
-      </rule>
-      <rule pattern="[^\\#\[\]]+">
-        <token type="LiteralStringOther"/>
-      </rule>
-    </state>
-    <state name="pa-regex">
-      <rule pattern="\\[\\()]">
-        <token type="LiteralStringRegex"/>
-      </rule>
-      <rule pattern="\(">
-        <token type="LiteralStringRegex"/>
-        <push/>
-      </rule>
-      <rule pattern="\)[imsx]*">
-        <token type="LiteralStringRegex"/>
-        <pop depth="1"/>
-      </rule>
-      <rule>
-        <include state="string-intp"/>
-      </rule>
-      <rule pattern="[\\#()]">
-        <token type="LiteralStringRegex"/>
-      </rule>
-      <rule pattern="[^\\#()]+">
-        <token type="LiteralStringRegex"/>
-      </rule>
-    </state>
-    <state name="in-attr">
-      <rule pattern="\[">
-        <token type="Operator"/>
-        <push/>
-      </rule>
-      <rule pattern="\]">
-        <token type="Operator"/>
-        <pop depth="1"/>
-      </rule>
-      <rule>
-        <include state="root"/>
-      </rule>
-    </state>
-    <state name="ab-intp-string">
-      <rule pattern="\\[&lt;]">
-        <token type="LiteralStringOther"/>
-      </rule>
-      <rule pattern="&lt;">
-        <token type="LiteralStringOther"/>
-        <push/>
-      </rule>
-      <rule pattern="&gt;">
-        <token type="LiteralStringOther"/>
-        <pop depth="1"/>
-      </rule>
-      <rule>
-        <include state="string-intp-escaped"/>
-      </rule>
-      <rule pattern="[\\#&lt;&gt;]">
-        <token type="LiteralStringOther"/>
-      </rule>
-      <rule pattern="[^\\#&lt;&gt;]+">
-        <token type="LiteralStringOther"/>
-      </rule>
-    </state>
-    <state name="in-intp">
-      <rule pattern="\{">
-        <token type="LiteralStringInterpol"/>
-        <push/>
-      </rule>
-      <rule pattern="\}">
-        <token type="LiteralStringInterpol"/>
-        <pop depth="1"/>
-      </rule>
-      <rule>
-        <include state="root"/>
-      </rule>
-    </state>
-    <state name="end-part">
-      <rule pattern=".+">
-        <token type="CommentPreproc"/>
-        <pop depth="1"/>
-      </rule>
-    </state>
-    <state name="root">
-      <rule pattern="#.*?$">
-        <token type="CommentSingle"/>
-      </rule>
-      <rule pattern="(instance_sizeof|pointerof|protected|abstract|require|private|include|unless|typeof|sizeof|return|extend|ensure|rescue|ifdef|super|break|begin|until|while|elsif|yield|next|when|else|then|case|with|end|asm|if|do|as|of)\b">
-        <token type="Keyword"/>
-      </rule>
-      <rule pattern="(false|true|nil)\b">
-        <token type="KeywordConstant"/>
-      </rule>
-      <rule pattern="(module|lib)(\s+)([a-zA-Z_]\w*(?:::[a-zA-Z_]\w*)*)">
-        <bygroups>
-          <token type="Keyword"/>
-          <token type="Text"/>
-          <token type="NameNamespace"/>
-        </bygroups>
-      </rule>
-      <rule pattern="(def|fun|macro)(\s+)((?:[a-zA-Z_]\w*::)*)">
-        <bygroups>
-          <token type="Keyword"/>
-          <token type="Text"/>
-          <token type="NameNamespace"/>
-        </bygroups>
-        <push state="funcname"/>
-      </rule>
-      <rule pattern="def(?=[*%&amp;^`~+-/\[&lt;&gt;=])">
-        <token type="Keyword"/>
-        <push state="funcname"/>
-      </rule>
-      <rule pattern="(class|struct|union|type|alias|enum)(\s+)((?:[a-zA-Z_]\w*::)*)">
-        <bygroups>
-          <token type="Keyword"/>
-          <token type="Text"/>
-          <token type="NameNamespace"/>
-        </bygroups>
-        <push state="classname"/>
-      </rule>
-      <rule pattern="(self|out|uninitialized)\b|(is_a|responds_to)\?">
-        <token type="KeywordPseudo"/>
-      </rule>
-      <rule pattern="(def_equals_and_hash|assert_responds_to|forward_missing_to|def_equals|property|def_hash|parallel|delegate|debugger|getter|record|setter|spawn|pp)\b">
-        <token type="NameBuiltinPseudo"/>
-      </rule>
-      <rule pattern="getter[!?]|property[!?]|__(DIR|FILE|LINE)__\b">
-        <token type="NameBuiltinPseudo"/>
-      </rule>
-      <rule pattern="(?&lt;!\.)(get_stack_top|StaticArray|Concurrent|with_color|Reference|Scheduler|read_line|Exception|at_exit|Pointer|Channel|Float64|sprintf|Float32|Process|Object|Struct|caller|UInt16|UInt32|UInt64|system|future|Number|printf|String|Symbol|Int32|Range|Slice|Regex|Mutex|sleep|Array|Class|raise|Tuple|Deque|delay|Float|Int16|print|abort|Value|UInt8|Int64|puts|Proc|File|Void|exit|fork|Bool|Char|gets|lazy|loop|main|rand|Enum|Int8|Time|Hash|Set|Box|Nil|Dir|Int|p)\b">
-        <token type="NameBuiltin"/>
-      </rule>
-      <rule pattern="(?&lt;!\w)(&lt;&lt;-?)([&#34;`\&#39;]?)([a-zA-Z_]\w*)(\2)(.*?\n)">
-        <token type="LiteralStringHeredoc"/>
-      </rule>
-      <rule pattern="(&lt;&lt;-?)(&#34;|\&#39;)()(\2)(.*?\n)">
-        <token type="LiteralStringHeredoc"/>
-      </rule>
-      <rule pattern="__END__">
-        <token type="CommentPreproc"/>
-        <push state="end-part"/>
-      </rule>
-      <rule pattern="(?:^|(?&lt;=[=&lt;&gt;~!:])|(?&lt;=(?:\s|;)when\s)|(?&lt;=(?:\s|;)or\s)|(?&lt;=(?:\s|;)and\s)|(?&lt;=\.index\s)|(?&lt;=\.scan\s)|(?&lt;=\.sub\s)|(?&lt;=\.sub!\s)|(?&lt;=\.gsub\s)|(?&lt;=\.gsub!\s)|(?&lt;=\.match\s)|(?&lt;=(?:\s|;)if\s)|(?&lt;=(?:\s|;)elsif\s)|(?&lt;=^when\s)|(?&lt;=^index\s)|(?&lt;=^scan\s)|(?&lt;=^sub\s)|(?&lt;=^gsub\s)|(?&lt;=^sub!\s)|(?&lt;=^gsub!\s)|(?&lt;=^match\s)|(?&lt;=^if\s)|(?&lt;=^elsif\s))(\s*)(/)">
-        <bygroups>
-          <token type="Text"/>
-          <token type="LiteralStringRegex"/>
-        </bygroups>
-        <push state="multiline-regex"/>
-      </rule>
-      <rule pattern="(?&lt;=\(|,|\[)/">
-        <token type="LiteralStringRegex"/>
-        <push state="multiline-regex"/>
-      </rule>
-      <rule pattern="(\s+)(/)(?![\s=])">
-        <bygroups>
-          <token type="Text"/>
-          <token type="LiteralStringRegex"/>
-        </bygroups>
-        <push state="multiline-regex"/>
-      </rule>
-      <rule pattern="(0o[0-7]+(?:_[0-7]+)*(?:_?[iu][0-9]+)?)\b(\s*)([/?])?">
-        <bygroups>
-          <token type="LiteralNumberOct"/>
-          <token type="Text"/>
-          <token type="Operator"/>
-        </bygroups>
-      </rule>
-      <rule pattern="(0x[0-9A-Fa-f]+(?:_[0-9A-Fa-f]+)*(?:_?[iu][0-9]+)?)\b(\s*)([/?])?">
-        <bygroups>
-          <token type="LiteralNumberHex"/>
-          <token type="Text"/>
-          <token type="Operator"/>
-        </bygroups>
-      </rule>
-      <rule pattern="(0b[01]+(?:_[01]+)*(?:_?[iu][0-9]+)?)\b(\s*)([/?])?">
-        <bygroups>
-          <token type="LiteralNumberBin"/>
-          <token type="Text"/>
-          <token type="Operator"/>
-        </bygroups>
-      </rule>
-      <rule pattern="((?:0(?![0-9])|[1-9][\d_]*)(?:\.\d[\d_]*)(?:e[+-]?[0-9]+)?(?:_?f[0-9]+)?)(\s*)([/?])?">
-        <bygroups>
-          <token type="LiteralNumberFloat"/>
-          <token type="Text"/>
-          <token type="Operator"/>
-        </bygroups>
-      </rule>
-      <rule pattern="((?:0(?![0-9])|[1-9][\d_]*)(?:\.\d[\d_]*)?(?:e[+-]?[0-9]+)(?:_?f[0-9]+)?)(\s*)([/?])?">
-        <bygroups>
-          <token type="LiteralNumberFloat"/>
-          <token type="Text"/>
-          <token type="Operator"/>
-        </bygroups>
-      </rule>
-      <rule pattern="((?:0(?![0-9])|[1-9][\d_]*)(?:\.\d[\d_]*)?(?:e[+-]?[0-9]+)?(?:_?f[0-9]+))(\s*)([/?])?">
-        <bygroups>
-          <token type="LiteralNumberFloat"/>
-          <token type="Text"/>
-          <token type="Operator"/>
-        </bygroups>
-      </rule>
-      <rule pattern="(0\b|[1-9][\d]*(?:_\d+)*(?:_?[iu][0-9]+)?)\b(\s*)([/?])?">
-        <bygroups>
-          <token type="LiteralNumberInteger"/>
-          <token type="Text"/>
-          <token type="Operator"/>
-        </bygroups>
-      </rule>
-      <rule pattern="@@[a-zA-Z_]\w*">
-        <token type="NameVariableClass"/>
-      </rule>
-      <rule pattern="@[a-zA-Z_]\w*">
-        <token type="NameVariableInstance"/>
-      </rule>
-      <rule pattern="\$\w+">
-        <token type="NameVariableGlobal"/>
-      </rule>
-      <rule pattern="\$[!@&amp;`\&#39;+~=/\\,;.&lt;&gt;_*$?:&#34;^-]">
-        <token type="NameVariableGlobal"/>
-      </rule>
-      <rule pattern="\$-[0adFiIlpvw]">
-        <token type="NameVariableGlobal"/>
-      </rule>
-      <rule pattern="::">
-        <token type="Operator"/>
-      </rule>
-      <rule>
-        <include state="strings"/>
-      </rule>
-      <rule pattern="\?(\\[MC]-)*(\\([\\befnrtv#&#34;\&#39;]|x[a-fA-F0-9]{1,2}|[0-7]{1,3})|\S)(?!\w)">
-        <token type="LiteralStringChar"/>
-      </rule>
-      <rule pattern="[A-Z][A-Z_]+\b">
-        <token type="NameConstant"/>
-      </rule>
-      <rule pattern="\{%">
-        <token type="LiteralStringInterpol"/>
-        <push state="in-macro-control"/>
-      </rule>
-      <rule pattern="\{\{">
-        <token type="LiteralStringInterpol"/>
-        <push state="in-macro-expr"/>
-      </rule>
-      <rule pattern="(@\[)(\s*)([A-Z]\w*)">
-        <bygroups>
-          <token type="Operator"/>
-          <token type="Text"/>
-          <token type="NameDecorator"/>
-        </bygroups>
-        <push state="in-attr"/>
-      </rule>
-      <rule pattern="(\.|::)(\[\]\?|&lt;=&gt;|===|\[\]=|&gt;&gt;|&amp;&amp;|\*\*|\[\]|\|\||&gt;=|=~|!~|&lt;&lt;|&lt;=|!=|==|&lt;|/|=|-|\+|&gt;|\*|&amp;|%|\^|!|\||~)">
-        <bygroups>
-          <token type="Operator"/>
-          <token type="NameOperator"/>
-        </bygroups>
-      </rule>
-      <rule pattern="(\.|::)([a-zA-Z_]\w*[!?]?|[*%&amp;^`~+\-/\[&lt;&gt;=])">
-        <bygroups>
-          <token type="Operator"/>
-          <token type="Name"/>
-        </bygroups>
-      </rule>
-      <rule pattern="[a-zA-Z_]\w*(?:[!?](?!=))?">
-        <token type="Name"/>
-      </rule>
-      <rule pattern="(\[|\]\??|\*\*|&lt;=&gt;?|&gt;=|&lt;&lt;?|&gt;&gt;?|=~|===|!~|&amp;&amp;?|\|\||\.{1,3})">
-        <token type="Operator"/>
-      </rule>
-      <rule pattern="[-+/*%=&lt;&gt;&amp;!^|~]=?">
-        <token type="Operator"/>
-      </rule>
-      <rule pattern="[(){};,/?:\\]">
-        <token type="Punctuation"/>
-      </rule>
-      <rule pattern="\s+">
-        <token type="Text"/>
-      </rule>
-    </state>
-    <state name="multiline-regex">
-      <rule>
-        <include state="string-intp"/>
-      </rule>
-      <rule pattern="\\\\">
-        <token type="LiteralStringRegex"/>
-      </rule>
-      <rule pattern="\\/">
-        <token type="LiteralStringRegex"/>
-      </rule>
-      <rule pattern="[\\#]">
-        <token type="LiteralStringRegex"/>
-      </rule>
-      <rule pattern="[^\\/#]+">
-        <token type="LiteralStringRegex"/>
-      </rule>
-      <rule pattern="/[imsx]*">
-        <token type="LiteralStringRegex"/>
-        <pop depth="1"/>
-      </rule>
-    </state>
-    <state name="ab-string">
-      <rule pattern="\\[\\&lt;&gt;]">
-        <token type="LiteralStringOther"/>
-      </rule>
-      <rule pattern="&lt;">
-        <token type="LiteralStringOther"/>
-        <push/>
-      </rule>
-      <rule pattern="&gt;">
-        <token type="LiteralStringOther"/>
-        <pop depth="1"/>
-      </rule>
-      <rule pattern="[\\#&lt;&gt;]">
-        <token type="LiteralStringOther"/>
-      </rule>
-      <rule pattern="[^\\#&lt;&gt;]+">
-        <token type="LiteralStringOther"/>
-      </rule>
-    </state>
-    <state name="pa-string">
-      <rule pattern="\\[\\()]">
-        <token type="LiteralStringOther"/>
-      </rule>
-      <rule pattern="\(">
-        <token type="LiteralStringOther"/>
-        <push/>
-      </rule>
-      <rule pattern="\)">
-        <token type="LiteralStringOther"/>
-        <pop depth="1"/>
-      </rule>
-      <rule pattern="[\\#()]">
-        <token type="LiteralStringOther"/>
-      </rule>
-      <rule pattern="[^\\#()]+">
-        <token type="LiteralStringOther"/>
-      </rule>
-    </state>
-    <state name="strings">
-      <rule pattern="\:@{0,2}[a-zA-Z_]\w*[!?]?">
-        <token type="LiteralStringSymbol"/>
-      </rule>
-      <rule pattern="\:@{0,2}(\[\]\?|&lt;=&gt;|===|\[\]=|&gt;&gt;|&amp;&amp;|\*\*|\[\]|\|\||&gt;=|=~|!~|&lt;&lt;|&lt;=|!=|==|&lt;|/|=|-|\+|&gt;|\*|&amp;|%|\^|!|\||~)">
-        <token type="LiteralStringSymbol"/>
-      </rule>
-      <rule pattern=":&#39;(\\\\|\\&#39;|[^&#39;])*&#39;">
-        <token type="LiteralStringSymbol"/>
-      </rule>
-      <rule pattern="&#39;(\\\\|\\&#39;|[^&#39;]|\\[^&#39;\\]+)&#39;">
-        <token type="LiteralStringChar"/>
-      </rule>
-      <rule pattern=":&#34;">
-        <token type="LiteralStringSymbol"/>
-        <push state="simple-sym"/>
-      </rule>
-      <rule pattern="([a-zA-Z_]\w*)(:)(?!:)">
-        <bygroups>
-          <token type="LiteralStringSymbol"/>
-          <token type="Punctuation"/>
-        </bygroups>
-      </rule>
-      <rule pattern="&#34;">
-        <token type="LiteralStringDouble"/>
-        <push state="simple-string"/>
-      </rule>
-      <rule pattern="(?&lt;!\.)`">
-        <token type="LiteralStringBacktick"/>
-        <push state="simple-backtick"/>
-      </rule>
-      <rule pattern="%\{">
-        <token type="LiteralStringOther"/>
-        <push state="cb-intp-string"/>
-      </rule>
-      <rule pattern="%[wi]\{">
-        <token type="LiteralStringOther"/>
-        <push state="cb-string"/>
-      </rule>
-      <rule pattern="%r\{">
-        <token type="LiteralStringRegex"/>
-        <push state="cb-regex"/>
-      </rule>
-      <rule pattern="%\[">
-        <token type="LiteralStringOther"/>
-        <push state="sb-intp-string"/>
-      </rule>
-      <rule pattern="%[wi]\[">
-        <token type="LiteralStringOther"/>
-        <push state="sb-string"/>
-      </rule>
-      <rule pattern="%r\[">
-        <token type="LiteralStringRegex"/>
-        <push state="sb-regex"/>
-      </rule>
-      <rule pattern="%\(">
-        <token type="LiteralStringOther"/>
-        <push state="pa-intp-string"/>
-      </rule>
-      <rule pattern="%[wi]\(">
-        <token type="LiteralStringOther"/>
-        <push state="pa-string"/>
-      </rule>
-      <rule pattern="%r\(">
-        <token type="LiteralStringRegex"/>
-        <push state="pa-regex"/>
-      </rule>
-      <rule pattern="%&lt;">
-        <token type="LiteralStringOther"/>
-        <push state="ab-intp-string"/>
-      </rule>
-      <rule pattern="%[wi]&lt;">
-        <token type="LiteralStringOther"/>
-        <push state="ab-string"/>
-      </rule>
-      <rule pattern="%r&lt;">
-        <token type="LiteralStringRegex"/>
-        <push state="ab-regex"/>
-      </rule>
-      <rule pattern="(%r([\W_]))((?:\\\2|(?!\2).)*)(\2[imsx]*)">
-        <token type="LiteralString"/>
-      </rule>
-      <rule pattern="(%[wi]([\W_]))((?:\\\2|(?!\2).)*)(\2)">
-        <token type="LiteralString"/>
-      </rule>
-      <rule pattern="(?&lt;=[-+/*%=&lt;&gt;&amp;!^|~,(])(\s*)(%([\t ])(?:(?:\\\3|(?!\3).)*)\3)">
-        <bygroups>
-          <token type="Text"/>
-          <token type="LiteralStringOther"/>
-          <token type="None"/>
-        </bygroups>
-      </rule>
-      <rule pattern="^(\s*)(%([\t ])(?:(?:\\\3|(?!\3).)*)\3)">
-        <bygroups>
-          <token type="Text"/>
-          <token type="LiteralStringOther"/>
-          <token type="None"/>
-        </bygroups>
-      </rule>
-      <rule pattern="(%([\[{(&lt;]))((?:\\\2|(?!\2).)*)(\2)">
-        <token type="LiteralString"/>
-      </rule>
-    </state>
-    <state name="sb-string">
-      <rule pattern="\\[\\\[\]]">
-        <token type="LiteralStringOther"/>
-      </rule>
-      <rule pattern="\[">
-        <token type="LiteralStringOther"/>
-        <push/>
-      </rule>
-      <rule pattern="\]">
-        <token type="LiteralStringOther"/>
-        <pop depth="1"/>
-      </rule>
-      <rule pattern="[\\#\[\]]">
-        <token type="LiteralStringOther"/>
-      </rule>
-      <rule pattern="[^\\#\[\]]+">
-        <token type="LiteralStringOther"/>
-      </rule>
-    </state>
-    <state name="funcname">
-      <rule pattern="(?:([a-zA-Z_]\w*)(\.))?([a-zA-Z_]\w*[!?]?|\*\*?|[-+]@?|[/%&amp;|^`~]|\[\]=?|&lt;&lt;|&gt;&gt;|&lt;=?&gt;|&gt;=?|===?)">
-        <bygroups>
-          <token type="NameClass"/>
-          <token type="Operator"/>
-          <token type="NameFunction"/>
-        </bygroups>
-        <pop depth="1"/>
-      </rule>
-      <rule>
-        <pop depth="1"/>
-      </rule>
-    </state>
-    <state name="simple-sym">
-      <rule>
-        <include state="string-escaped"/>
-      </rule>
-      <rule pattern="[^\\&#34;#]+">
-        <token type="LiteralStringSymbol"/>
-      </rule>
-      <rule pattern="[\\#]">
-        <token type="LiteralStringSymbol"/>
-      </rule>
-      <rule pattern="&#34;">
-        <token type="LiteralStringSymbol"/>
-        <pop depth="1"/>
-      </rule>
-    </state>
-  </rules>
-</lexer>

lexers/css.xml

@@ -320,4 +320,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</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/cython.xml

@@ -369,4 +369,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/d.xml

@@ -130,4 +130,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/dart.xml

@@ -210,4 +210,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/desktop_entry.xml

@@ -14,4 +14,4 @@
       <rule pattern="([-A-Za-z0-9]+)(\[[^\] \t=]+\])?([ \t]*)(=)([ \t]*)([^\n]*)([ \t\n]*\n)"><bygroups><token type="NameAttribute"/><token type="NameNamespace"/><token type="TextWhitespace"/><token type="Operator"/><token type="TextWhitespace"/><token type="LiteralString"/><token type="TextWhitespace"/></bygroups></rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/diff.xml

@@ -49,4 +49,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/django_jinja.xml

@@ -150,4 +150,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/docker.xml

@@ -54,4 +54,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/dtd.xml

@@ -165,4 +165,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/dylan.xml

@@ -173,4 +173,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/ebnf.xml

@@ -87,4 +87,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/elixir.xml

@@ -741,4 +741,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/elm.xml

@@ -116,4 +116,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/emacslisp.xml

@@ -129,4 +129,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/erlang.xml

@@ -163,4 +163,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/factor.xml

@@ -409,4 +409,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/fennel.xml

@@ -65,4 +65,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/fish.xml

@@ -156,4 +156,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/forth.xml

@@ -75,4 +75,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/fortranfixed.xml

@@ -68,4 +68,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/gherkin.xml

@@ -260,4 +260,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/glsl.xml

@@ -62,4 +62,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/gnuplot.xml

@@ -286,4 +286,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/go_template.xml

@@ -111,4 +111,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/graphql.xml

@@ -85,4 +85,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/groff.xml

@@ -87,4 +87,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/handlebars.xml

@@ -144,4 +144,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

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;">
@@ -269,4 +272,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/hcl.xml

@@ -140,4 +140,4 @@
       </rule>
     </state>
   </rules>
-</lexer>
+</lexer>

lexers/heuristics.yml

@@ -0,0 +1,913 @@
+# A collection of simple regexp-based rules that can be applied to content
+# to disambiguate languages with the same file extension.
+#
+# There are two top-level keys: disambiguations and named_patterns.
+#
+# disambiguations     - a list of disambiguation rules, one for each
+#                       extension or group of extensions.
+# extensions          - an array of file extensions that this block applies to.
+# rules               - list of rules that are applied in order to the content
+#                       of a file with a matching extension. Rules are evaluated
+#                       until one of them matches. If none matches, no language
+#                       is returned.
+# language            - Language to be returned if the rule matches.
+# pattern             - Ruby-compatible regular expression that makes the rule
+#                       match. If no pattern is specified, the rule always matches.
+#                       Pattern can be a string with a single regular expression
+#                       or an array of strings that will be merged in a single
+#                       regular expression (with union).
+# and                 - An and block merges multiple rules and checks that all of
+#                       them must match.
+# negative_pattern    - Same as pattern, but checks for absence of matches.
+# named_pattern       - A pattern can be reused by specifying it in the
+#                       named_patterns section and referencing it here by its
+#                       key.
+# named_patterns      - Key-value map of reusable named patterns.
+#
+# Please keep this list alphabetized.
+#
+---
+disambiguations:
+- extensions: ['.1', '.2', '.3', '.4', '.5', '.6', '.7', '.8', '.9']
+  rules:
+  - language: man
+    and:
+    - named_pattern: mdoc-date
+    - named_pattern: mdoc-title
+    - named_pattern: mdoc-heading
+  - language: man
+    and:
+    - named_pattern: man-title
+    - named_pattern: man-heading
+  - language: Roff
+    pattern: '^\.(?:[A-Za-z]{2}(?:\s|$)|\\")'
+- extensions: ['.1in', '.1m', '.1x', '.3in', '.3m', '.3p', '.3pm', '.3qt', '.3x', '.man', '.mdoc']
+  rules:
+  - language: man
+    and:
+    - named_pattern: mdoc-date
+    - named_pattern: mdoc-title
+    - named_pattern: mdoc-heading
+  - language: man
+    and:
+    - named_pattern: man-title
+    - named_pattern: man-heading
+  - language: Roff
+- extensions: ['.al']
+  rules:
+  # AL pattern source from https://github.com/microsoft/AL/blob/master/grammar/alsyntax.tmlanguage - keyword.other.applicationobject.al
+  - language: AL
+    and:
+    - pattern: '\b(?i:(CODEUNIT|PAGE|PAGEEXTENSION|PAGECUSTOMIZATION|DOTNET|ENUM|ENUMEXTENSION|VALUE|QUERY|REPORT|TABLE|TABLEEXTENSION|XMLPORT|PROFILE|CONTROLADDIN|REPORTEXTENSION|INTERFACE|PERMISSIONSET|PERMISSIONSETEXTENSION|ENTITLEMENT))\b'
+  # Open-ended fallback to Perl AutoLoader
+  - language: Perl
+- extensions: ['.app']
+  rules:
+  - language: Erlang
+    pattern: '^\{\s*(?:application|''application'')\s*,\s*(?:[a-z]+[\w@]*|''[^'']+'')\s*,\s*\[(?:.|[\r\n])*\]\s*\}\.[ \t]*$'
+- extensions: ['.as']
+  rules:
+  - language: ActionScript
+    pattern: '^\s*(?:package(?:\s+[\w.]+)?\s+(?:\{|$)|import\s+[\w.*]+\s*;|(?=.*?(?:intrinsic|extends))(intrinsic\s+)?class\s+[\w<>.]+(?:\s+extends\s+[\w<>.]+)?|(?:(?:public|protected|private|static)\s+)*(?:(?:var|const|local)\s+\w+\s*:\s*[\w<>.]+(?:\s*=.*)?\s*;|function\s+\w+\s*\((?:\s*\w+\s*:\s*[\w<>.]+\s*(,\s*\w+\s*:\s*[\w<>.]+\s*)*)?\)))'
+- extensions: ['.asc']
+  rules:
+  - language: Public Key
+    pattern: '^(----[- ]BEGIN|ssh-(rsa|dss)) '
+  - language: AsciiDoc
+    pattern: '^[=-]+\s|\{\{[A-Za-z]'
+  - language: AGS Script
+    pattern: '^(\/\/.+|((import|export)\s+)?(function|int|float|char)\s+((room|repeatedly|on|game)_)?([A-Za-z]+[A-Za-z_0-9]+)\s*[;\(])'
+- extensions: ['.asm']
+  rules:
+  - language: Motorola 68K Assembly
+    named_pattern: m68k
+- extensions: ['.asy']
+  rules:
+  - language: LTspice Symbol
+    pattern: '^SymbolType[ \t]'
+  - language: Asymptote
+- extensions: ['.bas']
+  rules:
+  - language: FreeBasic
+    pattern: '^[ \t]*#(?i)(?:define|endif|endmacro|ifn?def|include|lang|macro)(?:$|\s)'
+  - language: BASIC
+    pattern: '\A\s*\d'
+  - language: VBA
+    and:
+    - named_pattern: vb-module
+    - named_pattern: vba
+  - language: Visual Basic 6.0
+    named_pattern: vb-module
+- extensions: ['.bb']
+  rules:
+  - language: BlitzBasic
+    pattern: '(<^\s*; |End Function)'
+  - language: BitBake
+    pattern: '^(# |include|require|inherit)\b'
+  - language: Clojure
+    pattern: '\((def|defn|defmacro|let)\s'
+- extensions: ['.bf']
+  rules:
+  - language: Beef
+    pattern: '(?-m)^\s*using\s+(System|Beefy)(\.(.*))?;\s*$'
+  - language: HyPhy
+    pattern:
+    - '(?-m)^\s*#include\s+".*";\s*$'
+    - '\sfprintf\s*\('
+  - language: Brainfuck
+    pattern: '(>\+>|>\+<)'
+- extensions: ['.bi']
+  rules:
+  - language: FreeBasic
+    pattern: '^[ \t]*#(?i)(?:define|endif|endmacro|ifn?def|if|include|lang|macro)(?:$|\s)'
+- extensions: ['.bs']
+  rules:
+  - language: Bikeshed
+    pattern: '^(?i:<pre\s+class)\s*=\s*(''|\"|\b)metadata\b\1[^>\r\n]*>'
+  - language: BrighterScript
+    pattern:
+    - (?i:^\s*(?=^sub\s)(?:sub\s*\w+\(.*?\))|(?::\s*sub\(.*?\))$)
+    - (?i:^\s*(end\ssub)$)
+    - (?i:^\s*(?=^function\s)(?:function\s*\w+\(.*?\)\s*as\s*\w*)|(?::\s*function\(.*?\)\s*as\s*\w*)$)
+    - (?i:^\s*(end\sfunction)$)
+  - language: Bluespec BH
+    pattern: '^package\s+[A-Za-z_][A-Za-z0-9_'']*(?:\s*\(|\s+where)'
+- extensions: ['.builds']
+  rules:
+  - language: XML
+    pattern: '^(\s*)(?i:<Project|<Import|<Property|<?xml|xmlns)'
+- extensions: ['.ch']
+  rules:
+  - language: xBase
+    pattern: '^\s*#\s*(?i:if|ifdef|ifndef|define|command|xcommand|translate|xtranslate|include|pragma|undef)\b'
+- extensions: ['.cl']
+  rules:
+  - language: Common Lisp
+    pattern: '^\s*\((?i:defun|in-package|defpackage) '
+  - language: Cool
+    pattern: '^class'
+  - language: OpenCL
+    pattern: '\/\* |\/\/ |^\}'
+- extensions: ['.cls']
+  rules:
+  - language: Visual Basic 6.0
+    and:
+    - named_pattern: vb-class
+    - pattern: '^\s*BEGIN(?:\r?\n|\r)\s*MultiUse\s*=.*(?:\r?\n|\r)\s*Persistable\s*='
+  - language: VBA
+    named_pattern: vb-class
+  - language: TeX
+    pattern: '^\s*\\(?:NeedsTeXFormat|ProvidesClass)\{'
+  - language: ObjectScript
+    pattern: '^Class\s'
+- extensions: ['.cmp']
+  rules:
+  - language: Gerber Image
+    pattern: '^[DGMT][0-9]{2}\*(?:\r?\n|\r)'
+- extensions: ['.cs']
+  rules:
+  - language: Smalltalk
+    pattern: '![\w\s]+methodsFor: '
+  - language: 'C#'
+    pattern: '^\s*(using\s+[A-Z][\s\w.]+;|namespace\s*[\w\.]+\s*(\{|;)|\/\/)'
+- extensions: ['.csc']
+  rules:
+  - language: GSC
+    named_pattern: gsc
+- extensions: ['.csl']
+  rules:
+  - language: XML
+    pattern: '(?i:^\s*(<\?xml|xmlns))'
+  - language: Kusto
+    pattern: '(^\|\s*(where|extend|project|limit|summarize))|(^\.\w+)'
+- extensions: ['.d']
+  rules:
+  - language: D
+    # see http://dlang.org/spec/grammar
+    # ModuleDeclaration | ImportDeclaration | FuncDeclaration | unittest
+    pattern: '^module\s+[\w.]*\s*;|import\s+[\w\s,.:]*;|\w+\s+\w+\s*\(.*\)(?:\(.*\))?\s*\{[^}]*\}|unittest\s*(?:\(.*\))?\s*\{[^}]*\}'
+  - language: DTrace
+    # see http://dtrace.org/guide/chp-prog.html, http://dtrace.org/guide/chp-profile.html, http://dtrace.org/guide/chp-opt.html
+    pattern: '^(\w+:\w*:\w*:\w*|BEGIN|END|provider\s+|(tick|profile)-\w+\s+\{[^}]*\}|#pragma\s+D\s+(option|attributes|depends_on)\s|#pragma\s+ident\s)'
+  - language: Makefile
+    # path/target : dependency \
+    # target : \
+    #  : dependency
+    # path/file.ext1 : some/path/../file.ext2
+    pattern: '([\/\\].*:\s+.*\s\\$|: \\$|^[ %]:|^[\w\s\/\\.]+\w+\.\w+\s*:\s+[\w\s\/\\.]+\w+\.\w+)'
+- extensions: ['.dsp']
+  rules:
+  - language: Microsoft Developer Studio Project
+    pattern: '# Microsoft Developer Studio Generated Build File'
+  - language: Faust
+    pattern: '\bprocess\s*[(=]|\b(library|import)\s*\(\s*"|\bdeclare\s+(name|version|author|copyright|license)\s+"'
+- extensions: ['.e']
+  rules:
+  - language: E
+    pattern:
+    - '^\s*(def|var)\s+(.+):='
+    - '^\s*(def|to)\s+(\w+)(\(.+\))?\s+\{'
+    - '^\s*(when)\s+(\(.+\))\s+->\s+\{'
+  - language: Eiffel
+    pattern:
+    - '^\s*\w+\s*(?:,\s*\w+)*[:]\s*\w+\s'
+    - '^\s*\w+\s*(?:\(\s*\w+[:][^)]+\))?(?:[:]\s*\w+)?(?:--.+\s+)*\s+(?:do|local)\s'
+    - '^\s*(?:across|deferred|elseif|ensure|feature|from|inherit|inspect|invariant|note|once|require|undefine|variant|when)\s*$'
+  - language: Euphoria
+    named_pattern: euphoria
+- extensions: ['.ecl']
+  rules:
+  - language: ECLiPSe
+    pattern: '^[^#]+:-'
+  - language: ECL
+    pattern: ':='
+- extensions: ['.es']
+  rules:
+  - language: Erlang
+    pattern: '^\s*(?:%%|main\s*\(.*?\)\s*->)'
+  - language: JavaScript
+    pattern: '\/\/|("|'')use strict\1|export\s+default\s|\/\*(?:.|[\r\n])*?\*\/'
+- extensions: ['.ex']
+  rules:
+  - language: Elixir
+    pattern:
+    - '^\s*@moduledoc\s'
+    - '^\s*(?:cond|import|quote|unless)\s'
+    - '^\s*def(?:exception|impl|macro|module|protocol)[(\s]'
+  - language: Euphoria
+    named_pattern: euphoria
+- extensions: ['.f']
+  rules:
+  - language: Forth
+    pattern: '^: '
+  - language: Filebench WML
+    pattern: 'flowop'
+  - language: Fortran
+    named_pattern: fortran
+- extensions: ['.for']
+  rules:
+  - language: Forth
+    pattern: '^: '
+  - language: Fortran
+    named_pattern: fortran
+- extensions: ['.fr']
+  rules:
+  - language: Forth
+    pattern: '^(: |also |new-device|previous )'
+  - language: Frege
+    pattern: '^\s*(import|module|package|data|type) '
+  - language: Text
+- extensions: ['.frm']
+  rules:
+  - language: VBA
+    and:
+    - named_pattern: vb-form
+    - pattern: '^\s*Begin\s+\{[0-9A-Z\-]*\}\s?'
+  - language: Visual Basic 6.0
+    and:
+    - named_pattern: vb-form
+    - pattern: '^\s*Begin\s+VB\.Form\s+'
+- extensions: ['.fs']
+  rules:
+  - language: Forth
+    pattern: '^(: |new-device)'
+  - language: 'F#'
+    pattern: '^\s*(#light|import|let|module|namespace|open|type)'
+  - language: GLSL
+    pattern: '^\s*(#version|precision|uniform|varying|vec[234])'
+  - language: Filterscript
+    pattern: '#include|#pragma\s+(rs|version)|__attribute__'
+- extensions: ['.ftl']
+  rules:
+  - language: FreeMarker
+    pattern: '^(?:<|[a-zA-Z-][a-zA-Z0-9_-]+[ \t]+\w)|\$\{\w+[^\r\n]*?\}|^[ \t]*(?:<#--.*?-->|<#([a-z]+)(?=\s|>)[^>]*>.*?</#\1>|\[#--.*?--\]|\[#([a-z]+)(?=\s|\])[^\]]*\].*?\[#\2\])'
+  - language: Fluent
+    pattern: '^-?[a-zA-Z][a-zA-Z0-9_-]* *=|\{\$-?[a-zA-Z][-\w]*(?:\.[a-zA-Z][-\w]*)?\}'
+- extensions: ['.g']
+  rules:
+  - language: GAP
+    pattern: '\s*(Declare|BindGlobal|KeyDependentOperation|Install(Method|GlobalFunction)|SetPackageInfo)'
+  - language: G-code
+    pattern: '^[MG][0-9]+(?:\r?\n|\r)'
+- extensions: ['.gd']
+  rules:
+  - language: GAP
+    pattern: '\s*(Declare|BindGlobal|KeyDependentOperation)'
+  - language: GDScript
+    pattern: '\s*(extends|var|const|enum|func|class|signal|tool|yield|assert|onready)'
+- extensions: ['.gml']
+  rules:
+  - language: XML
+    pattern: '(?i:^\s*(<\?xml|xmlns))'
+  - language: Graph Modeling Language
+    pattern: '(?i:^\s*(graph|node)\s+\[$)'
+  - language: Gerber Image
+    pattern: '^[DGMT][0-9]{2}\*$'
+  - language: Game Maker Language
+- extensions: ['.gs']
+  rules:
+  - language: GLSL
+    pattern: '^#version\s+[0-9]+\b'
+  - language: Gosu
+    pattern: '^uses (java|gw)\.'
+  - language: Genie
+    pattern: '^\[indent=[0-9]+\]'
+- extensions: ['.gsc']
+  rules:
+  - language: GSC
+    named_pattern: gsc
+- extensions: ['.gsh']
+  rules:
+  - language: GSC
+    named_pattern: gsc
+- extensions: ['.gts']
+  rules:
+  - language: Gerber Image
+    pattern: '^G0.'
+  - language: Glimmer TS
+    negative_pattern: '^G0.'
+- extensions: ['.h']
+  rules:
+  - language: Objective-C
+    named_pattern: objectivec
+  - language: C++
+    named_pattern: cpp
+  - language: C
+- extensions: ['.hh']
+  rules:
+  - language: Hack
+    pattern: '<\?hh'
+- extensions: ['.html']
+  rules:
+  - language: Ecmarkup
+    pattern: '<emu-(?:alg|annex|biblio|clause|eqn|example|figure|gann|gmod|gprose|grammar|intro|not-ref|note|nt|prodref|production|rhs|table|t|xref)(?:$|\s|>)'
+  - language: HTML
+- extensions: ['.i']
+  rules:
+  - language: Motorola 68K Assembly
+    named_pattern: m68k
+  - language: SWIG
+    pattern: '^[ \t]*%[a-z_]+\b|^%[{}]$'
+- extensions: ['.ice']
+  rules:
+  - language: JSON
+    pattern: '\A\s*[{\[]'
+  - language: Slice
+- extensions: ['.inc']
+  rules:
+  - language: Motorola 68K Assembly
+    named_pattern: m68k
+  - language: PHP
+    pattern: '^<\?(?:php)?'
+  - language: SourcePawn
+    pattern:
+    - '^public\s+(?:SharedPlugin(?:\s+|:)__pl_\w+\s*=(?:\s*\{)?|(?:void\s+)?__pl_\w+_SetNTVOptional\(\)(?:\s*\{)?)'
+    - '^methodmap\s+\w+\s+<\s+\w+'
+    - '^\s*MarkNativeAsOptional\s*\('
+  - language: NASL
+    pattern:
+    - '^\s*include\s*\(\s*(?:"|'')[\\/\w\-\.:\s]+\.(?:nasl|inc)\s*(?:"|'')\s*\)\s*;'
+    - '^\s*(?:global|local)_var\s+(?:\w+(?:\s*=\s*[\w\-"'']+)?\s*)(?:,\s*\w+(?:\s*=\s*[\w\-"'']+)?\s*)*+\s*;'
+    - '^\s*namespace\s+\w+\s*\{'
+    - '^\s*object\s+\w+\s*(?:extends\s+\w+(?:::\w+)?)?\s*\{'
+    - '^\s*(?:public\s+|private\s+|\s*)function\s+\w+\s*\([\w\s,]*\)\s*\{'
+  - language: POV-Ray SDL
+    pattern: '^\s*#(declare|local|macro|while)\s'
+  - language: Pascal
+    pattern:
+    - '(?i:^\s*\{\$(?:mode|ifdef|undef|define)[ ]+[a-z0-9_]+\})'
+    - '^\s*end[.;]\s*$'
+  - language: BitBake
+    pattern: '^inherit(\s+[\w.-]+)+\s*$'
+- extensions: ['.json']
+  rules:
+  - language: OASv2-json
+    pattern: '"swagger":\s?"2.[0-9.]+"'
+  - language: OASv3-json
+    pattern: '"openapi":\s?"3.[0-9.]+"'
+  - language: JSON
+- extensions: ['.l']
+  rules:
+  - language: Common Lisp
+    pattern: '\(def(un|macro)\s'
+  - language: Lex
+    pattern: '^(%[%{}]xs|<.*>)'
+  - language: Roff
+    pattern: '^\.[A-Za-z]{2}(\s|$)'
+  - language: PicoLisp
+    pattern: '^\((de|class|rel|code|data|must)\s'
+- extensions: ['.lean']
+  rules:
+  - language: Lean
+    pattern: '^import [a-z]'
+  - language: Lean 4
+    pattern: '^import [A-Z]'
+- extensions: ['.ls']
+  rules:
+  - language: LoomScript
+    pattern: '^\s*package\s*[\w\.\/\*\s]*\s*\{'
+  - language: LiveScript
+- extensions: ['.lsp', '.lisp']
+  rules:
+  - language: Common Lisp
+    pattern: '^\s*\((?i:defun|in-package|defpackage) '
+  - language: NewLisp
+    pattern: '^\s*\(define '
+- extensions: ['.m']
+  rules:
+  - language: Objective-C
+    named_pattern: objectivec
+  - language: Mercury
+    pattern: ':- module'
+  - language: MUF
+    pattern: '^: '
+  - language: M
+    pattern: '^\s*;'
+  - language: Mathematica
+    and:
+      - pattern: '\(\*'
+      - pattern: '\*\)$'
+  - language: MATLAB
+    pattern: '^\s*%'
+  - language: Limbo
+    pattern: '^\w+\s*:\s*module\s*\{'
+- extensions: ['.m4']
+  rules:
+  - language: M4Sugar
+    pattern:
+    - 'AC_DEFUN|AC_PREREQ|AC_INIT'
+    - '^_?m4_'
+  - language: 'M4'
+- extensions: ['.mask']
+  rules:
+  - language: Unity3D Asset
+    pattern: 'tag:unity3d.com'
+- extensions: ['.mc']
+  rules:
+  - language: Win32 Message File
+    pattern: '(?i)^[ \t]*(?>\/\*\s*)?MessageId=|^\.$'
+  - language: M4
+    pattern: '^dnl|^divert\((?:-?\d+)?\)|^\w+\(`[^\r\n]*?''[),]'
+  - language: Monkey C
+    pattern: '\b(?:using|module|function|class|var)\s+\w'
+- extensions: ['.md']
+  rules:
+  - language: Markdown
+    pattern:
+    - '(^[-A-Za-z0-9=#!\*\[|>])|<\/'
+    - '\A\z'
+  - language: GCC Machine Description
+    pattern: '^(;;|\(define_)'
+  - language: Markdown
+- extensions: ['.ml']
+  rules:
+  - language: OCaml
+    pattern: '(^\s*module)|let rec |match\s+(\S+\s)+with'
+  - language: Standard ML
+    pattern: '=> |case\s+(\S+\s)+of'
+- extensions: ['.mod']
+  rules:
+  - language: XML
+    pattern: '<!ENTITY '
+  - language: NMODL
+    pattern: '\b(NEURON|INITIAL|UNITS)\b'
+  - language: Modula-2
+    pattern: '^\s*(?i:MODULE|END) [\w\.]+;'
+  - language: [Linux Kernel Module, AMPL]
+- extensions: ['.mojo']
+  rules:
+  - language: Mojo
+    pattern: '^\s*(alias|def|from|fn|import|struct|trait)\s'
+  - language: XML
+    pattern: '^\s*<\?xml'
+- extensions: ['.ms']
+  rules:
+  - language: Roff
+    pattern: '^[.''][A-Za-z]{2}(\s|$)'
+  - language: Unix Assembly
+    and:
+      - negative_pattern: '/\*'
+      - pattern: '^\s*\.(?:include\s|globa?l\s|[A-Za-z][_A-Za-z0-9]*:)'
+  - language: MAXScript
+- extensions: ['.n']
+  rules:
+  - language: Roff
+    pattern: '^[.'']'
+  - language: Nemerle
+    pattern: '^(module|namespace|using)\s'
+- extensions: ['.ncl']
+  rules:
+  - language: XML
+    pattern: '^\s*<\?xml\s+version'
+  - language: Gerber Image
+    pattern: '^[DGMT][0-9]{2}\*(?:\r?\n|\r)'
+  - language: Text
+    pattern: 'THE_TITLE'
+- extensions: ['.nl']
+  rules:
+  - language: NL
+    pattern: '^(b|g)[0-9]+ '
+  - language: NewLisp
+- extensions: ['.nu']
+  rules:
+  - language: Nushell
+    pattern: '^\s*(import|export|module|def|let|let-env) '
+  - language: Nu
+- extensions: ['.odin']
+  rules:
+  - language: Object Data Instance Notation
+    pattern: '(?:^|<)\s*[A-Za-z0-9_]+\s*=\s*<'
+  - language: Odin
+    pattern: 'package\s+\w+|\b(?:im|ex)port\s*"[\w:./]+"|\w+\s*::\s*(?:proc|struct)\s*\(|^\s*//\s'
+- extensions: ['.p']
+  rules:
+  - language: Gnuplot
+    pattern:
+    - '^s?plot\b'
+    - '^set\s+(term|terminal|out|output|[xy]tics|[xy]label|[xy]range|style)\b'
+  - language: OpenEdge ABL
+- extensions: ['.php']
+  rules:
+  - language: Hack
+    pattern: '<\?hh'
+  - language: PHP
+    pattern: '<\?[^h]'
+- extensions: ['.pkl']
+  rules:
+    - language: Pkl
+      pattern:
+      - '^\s*(module|import|amends|extends|local|const|fixed|abstract|open|class|typealias|@\w+)\b'
+      - '^\s*[a-zA-Z0-9_$]+\s*(=|{|:)|^\s*`[^`]+`\s*(=|{|:)|for\s*\(|when\s*\('
+    - language: Pickle
+- extensions: ['.pl']
+  rules:
+  - language: Prolog
+    pattern: '^[^#]*:-'
+  - language: Perl
+    and:
+      - negative_pattern: '^\s*use\s+v6\b'
+      - named_pattern: perl
+  - language: Raku
+    named_pattern: raku
+- extensions: ['.plist']
+  rules:
+  - language: XML Property List
+    pattern: '^\s*(?:<\?xml\s|<!DOCTYPE\s+plist|<plist(?:\s+version\s*=\s*(["''])\d+(?:\.\d+)?\1)?\s*>\s*$)'
+  - language: OpenStep Property List
+- extensions: ['.plt']
+  rules:
+  - language: Prolog
+    pattern: '^\s*:-'
+- extensions: ['.pm']
+  rules:
+  - language: Perl
+    and:
+      - negative_pattern: '^\s*use\s+v6\b'
+      - named_pattern: perl
+  - language: Raku
+    named_pattern: raku
+  - language: X PixMap
+    pattern: '^\s*\/\* XPM \*\/'
+- extensions: ['.pod']
+  rules:
+  - language: Pod 6
+    pattern: '^[\s&&[^\r\n]]*=(comment|begin pod|begin para|item\d+)'
+  - language: Pod
+- extensions: ['.pp']
+  rules:
+  - language: Pascal
+    pattern: '^\s*end[.;]'
+  - language: Puppet
+    pattern: '^\s+\w+\s+=>\s'
+- extensions: ['.pro']
+  rules:
+  - language: Proguard
+    pattern: '^-(include\b.*\.pro$|keep\b|keepclassmembers\b|keepattributes\b)'
+  - language: Prolog
+    pattern: '^[^\[#]+:-'
+  - language: INI
+    pattern: 'last_client='
+  - language: QMake
+    and:
+    - pattern: HEADERS
+    - pattern: SOURCES
+  - language: IDL
+    pattern: '^\s*(?i:function|pro|compile_opt) \w[ \w,:]*$'
+- extensions: ['.properties']
+  rules:
+  - language: INI
+    and:
+    - named_pattern: key_equals_value
+    - pattern: '^[;\[]'
+  - language: Java Properties
+    and:
+    - named_pattern: key_equals_value
+    - pattern: '^[#!]'
+  - language: INI
+    named_pattern: key_equals_value
+  - language: Java Properties
+    pattern: '^[^#!][^:]*:'
+- extensions: ['.q']
+  rules:
+  - language: q
+    pattern: '((?i:[A-Z.][\w.]*:\{)|^\\(cd?|d|l|p|ts?) )'
+  - language: HiveQL
+    pattern: '(?i:SELECT\s+[\w*,]+\s+FROM|(CREATE|ALTER|DROP)\s(DATABASE|SCHEMA|TABLE))'
+- extensions: ['.qs']
+  rules:
+  - language: Q#
+    pattern: '^((\/{2,3})?\s*(namespace|operation)\b)'
+  - language: Qt Script
+    pattern: '(\w+\.prototype\.\w+|===|\bvar\b)'
+- extensions: ['.r']
+  rules:
+  - language: Rebol
+    pattern: '(?i:\bRebol\b)'
+  - language: Rez
+    pattern: '(#include\s+["<](Types\.r|Carbon\/Carbon\.r)[">])|((resource|data|type)\s+''[A-Za-z0-9]{4}''\s+((\(.*\)\s+){0,1}){)'
+  - language: R
+    pattern: '<-|^\s*#'
+- extensions: ['.re']
+  rules:
+  - language: Reason
+    pattern:
+    - '^\s*module\s+type\s'
+    - '^\s*(?:include|open)\s+\w+\s*;\s*$'
+    - '^\s*let\s+(?:module\s\w+\s*=\s*\{|\w+:\s+.*=.*;\s*$)'
+  - language: C++
+    pattern:
+    - '^\s*#(?:(?:if|ifdef|define|pragma)\s+\w|\s*include\s+<[^>]+>)'
+    - '^\s*template\s*<'
+- extensions: ['.res']
+  rules:
+  - language: ReScript
+    pattern:
+    - '^\s*(let|module|type)\s+\w*\s+=\s+'
+    - '^\s*(?:include|open)\s+\w+\s*$'
+- extensions: ['.rno']
+  rules:
+  - language: RUNOFF
+    pattern: '(?i:^\.!|^\f|\f$|^\.end lit(?:eral)?\b|^\.[a-zA-Z].*?;\.[a-zA-Z](?:[; \t])|\^\*[^\s*][^*]*\\\*(?=$|\s)|^\.c;[ \t]*\w+)'
+  - language: Roff
+    pattern: '^\.\\" '
+- extensions: ['.rpy']
+  rules:
+  - language: Python
+    pattern: '^(import|from|class|def)\s'
+  - language: "Ren'Py"
+- extensions: ['.rs']
+  rules:
+  - language: Rust
+    pattern: '^(use |fn |mod |pub |macro_rules|impl|#!?\[)'
+  - language: RenderScript
+    pattern: '#include|#pragma\s+(rs|version)|__attribute__'
+  - language: XML
+    pattern: '^\s*<\?xml'
+- extensions: ['.s']
+  rules:
+  - language: Motorola 68K Assembly
+    named_pattern: m68k
+- extensions: ['.sc']
+  rules:
+  - language: SuperCollider
+    pattern: '(?i:\^(this|super)\.|^\s*~\w+\s*=\.)'
+  - language: Scala
+    pattern: '(^\s*import (scala|java)\.|^\s*class\b)'
+- extensions: ['.scd']
+  rules:
+  - language: SuperCollider
+    pattern: '(?i:\^(this|super)\.|^\s*(~\w+\s*=\.|SynthDef\b))'
+  - language: Markdown
+    # Markdown syntax for scdoc
+    pattern: '^#+\s+(NAME|SYNOPSIS|DESCRIPTION)'
+- extensions: ['.sol']
+  rules:
+  - language: Solidity
+    pattern: '\bpragma\s+solidity\b|\b(?:abstract\s+)?contract\s+(?!\d)[a-zA-Z0-9$_]+(?:\s+is\s+(?:[a-zA-Z0-9$_][^\{]*?)?)?\s*\{'
+  - language: Gerber Image
+    pattern: '^[DGMT][0-9]{2}\*(?:\r?\n|\r)'
+- extensions: ['.sql']
+  rules:
+   # Postgres
+  - language: PLpgSQL
+    pattern: '(?i:^\\i\b|AS\s+\$\$|LANGUAGE\s+''?plpgsql''?|BEGIN(\s+WORK)?\s*;)'
+  # IBM db2
+  - language: SQLPL
+    pattern: '(?i:ALTER\s+MODULE|MODE\s+DB2SQL|\bSYS(CAT|PROC)\.|ASSOCIATE\s+RESULT\s+SET|\bEND!\s*$)'
+  # Oracle
+  - language: PLSQL
+    pattern: '(?i:\$\$PLSQL_|XMLTYPE|systimestamp|\.nextval|CONNECT\s+BY|AUTHID\s+(DEFINER|CURRENT_USER)|constructor\W+function)'
+  # T-SQL
+  - language: TSQL
+    pattern: '(?i:^\s*GO\b|BEGIN(\s+TRY|\s+CATCH)|OUTPUT\s+INSERTED|DECLARE\s+@|\[dbo\])'
+  - language: SQL
+- extensions: ['.srt']
+  rules:
+  - language: SubRip Text
+    pattern: '^(\d{2}:\d{2}:\d{2},\d{3})\s*(-->)\s*(\d{2}:\d{2}:\d{2},\d{3})$'
+- extensions: ['.st']
+  rules:
+  - language: StringTemplate
+    pattern: '\$\w+[($]|(.)!\s*.+?\s*!\1|<!\s*.+?\s*!>|\[!\s*.+?\s*!\]|\{!\s*.+?\s*!\}'
+  - language: Smalltalk
+    pattern: '\A\s*[\[{(^"''\w#]|[a-zA-Z_]\w*\s*:=\s*[a-zA-Z_]\w*|class\s*>>\s*[a-zA-Z_]\w*|^[a-zA-Z_]\w*\s+[a-zA-Z_]\w*:|^Class\s*\{|if(?:True|False):\s*\['
+- extensions: ['.star']
+  rules:
+  - language: STAR
+    pattern: '^loop_\s*$'
+  - language: Starlark
+- extensions: ['.stl']
+  rules:
+  - language: STL
+    pattern: '\A\s*solid(?:$|\s)[\s\S]*^endsolid(?:$|\s)'
+- extensions: ['.sw']
+  rules:
+  - language: Sway
+    pattern: '^\s*(?:(?:abi|dep|fn|impl|mod|pub|trait)\s|#\[)'
+  - language: XML
+    pattern: '^\s*<\?xml\s+version'
+- extensions: ['.t']
+  rules:
+  - language: Perl
+    and:
+      - negative_pattern: '^\s*use\s+v6\b'
+      - named_pattern: perl
+  - language: Raku
+    pattern: '^\s*(?:use\s+v6\b|\bmodule\b|\bmy\s+class\b)'
+  - language: Turing
+    pattern: '^\s*%[ \t]+|^\s*var\s+\w+(\s*:\s*\w+)?\s*:=\s*\w+'
+- extensions: ['.tag']
+  rules:
+  - language: Java Server Pages
+    pattern: '<%[@!=\s]?\s*(taglib|tag|include|attribute|variable)\s'
+- extensions: ['.tlv']
+  rules:
+  - language: TL-Verilog
+    pattern: '^\\.{0,10}TLV_version'
+- extensions: ['.toc']
+  rules:
+  - language: World of Warcraft Addon Data
+    pattern: '^## |@no-lib-strip@'
+  - language: TeX
+    pattern: '^\\(contentsline|defcounter|beamer|boolfalse)'
+- extensions: ['.ts']
+  rules:
+  - language: XML
+    pattern: '<TS\b'
+  - language: TypeScript
+- extensions: ['.tst']
+  rules:
+  - language: GAP
+    pattern: 'gap> '
+  # Heads up - we don't usually write heuristics like this (with no regex match)
+  - language: Scilab
+- extensions: ['.tsx']
+  rules:
+  - language: TSX
+    pattern: '^\s*(import.+(from\s+|require\()[''"]react|\/\/\/\s*<reference\s)'
+  - language: XML
+    pattern: '(?i:^\s*<\?xml\s+version)'
+- extensions: ['.txt']
+  rules:
+    # The following RegExp is simply a collapsed and simplified form of the
+    # VIM_MODELINE pattern in `./lib/linguist/strategy/modeline.rb`.
+  - language: Vim Help File
+    pattern: '(?:(?:^|[ \t])(?:vi|Vi(?=m))(?:m[<=>]?[0-9]+|m)?|[ \t]ex)(?=:(?=[ \t]*set?[ \t][^\r\n:]+:)|:(?![ \t]*set?[ \t]))(?:(?:[ \t]*:[ \t]*|[ \t])\w*(?:[ \t]*=(?:[^\\\s]|\\.)*)?)*[ \t:](?:filetype|ft|syntax)[ \t]*=(help)(?=$|\s|:)'
+  - language: Adblock Filter List
+    pattern: |-
+      (?x)\A
+      \[
+      (?<version>
+        (?:
+          [Aa]d[Bb]lock
+          (?:[ \t][Pp]lus)?
+          |
+          u[Bb]lock
+          (?:[ \t][Oo]rigin)?
+          |
+          [Aa]d[Gg]uard
+        )
+        (?:[ \t] \d+(?:\.\d+)*+)?
+      )
+      (?:
+        [ \t]?;[ \t]?
+        \g<version>
+      )*+
+      \]
+    # HACK: This is a contrived use of heuristics needed to address
+    # an unusual edge-case. See https://git.io/JULye for discussion.
+  - language: Text
+- extensions: ['.typ']
+  rules:
+  - language: Typst
+    pattern: '^#(import|show|let|set)'
+  - language: XML
+- extensions: ['.url']
+  rules:
+  - language: INI
+    pattern: '^\[InternetShortcut\](?:\r?\n|\r)(?>[^\s\[][^\r\n]*(?:\r?\n|\r))*URL='
+- extensions: ['.v']
+  rules:
+  - language: Coq
+    pattern: '(?:^|\s)(?:Proof|Qed)\.(?:$|\s)|(?:^|\s)Require[ \t]+(Import|Export)\s'
+  - language: Verilog
+    pattern: '^[ \t]*module\s+[^\s()]+\s+\#?\(|^[ \t]*`(?:define|ifdef|ifndef|include|timescale)|^[ \t]*always[ \t]+@|^[ \t]*initial[ \t]+(begin|@)'
+  - language: V
+    pattern: '\$(?:if|else)[ \t]|^[ \t]*fn\s+[^\s()]+\(.*?\).*?\{|^[ \t]*for\s*\{'
+- extensions: ['.vba']
+  rules:
+  - language: Vim Script
+    pattern: '^UseVimball'
+  - language: VBA
+- extensions: ['.w']
+  rules:
+  - language: OpenEdge ABL
+    pattern: '&ANALYZE-SUSPEND _UIB-CODE-BLOCK _CUSTOM _DEFINITIONS'
+  - language: CWeb
+    pattern: '^@(<|\w+\.)'
+- extensions: ['.x']
+  rules:
+  - language: DirectX 3D File
+    pattern:  '^xof 030(2|3)(?:txt|bin|tzip|bzip)\b'
+  - language: RPC
+    pattern: '\b(program|version)\s+\w+\s*\{|\bunion\s+\w+\s+switch\s*\('
+  - language: Logos
+    pattern: '^%(end|ctor|hook|group)\b'
+  - language: Linker Script
+    pattern: 'OUTPUT_ARCH\(|OUTPUT_FORMAT\(|SECTIONS'
+- extensions: ['.yaml', '.yml']
+  rules:
+  - language: MiniYAML
+    pattern: '^\t+.*?[^\s:].*?:'
+    negative_pattern: '---'
+  - language: OASv2-yaml
+    pattern: 'swagger:\s?''?"?2.[0-9.]+''?"?'
+  - language: OASv3-yaml
+    pattern: 'openapi:\s?''?"?3.[0-9.]+''?"?'
+  - language: YAML
+- extensions: ['.yy']
+  rules:
+  - language: JSON
+    pattern: '\"modelName\"\:\s*\"GM'
+  - language: Yacc
+named_patterns:
+  cpp:
+  - '^\s*#\s*include <(cstdint|string|vector|map|list|array|bitset|queue|stack|forward_list|unordered_map|unordered_set|(i|o|io)stream)>'
+  - '^\s*template\s*<'
+  - '^[ \t]*(try|constexpr)'
+  - '^[ \t]*catch\s*\('
+  - '^[ \t]*(class|(using[ \t]+)?namespace)\s+\w+'
+  - '^[ \t]*(private|public|protected):$'
+  - '__has_cpp_attribute|__cplusplus >'
+  - 'std::\w+'
+  euphoria:
+  - '^\s*namespace\s'
+  - '^\s*(?:public\s+)?include\s'
+  - '^\s*(?:(?:public|export|global)\s+)?(?:atom|constant|enum|function|integer|object|procedure|sequence|type)\s'
+  fortran: '^(?i:[c*][^abd-z]|      (subroutine|program|end|data)\s|\s*!)'
+  gsc:
+  - '^\s*#\s*(?:using|insert|include|define|namespace)[ \t]+\w'
+  - '^\s*(?>(?:autoexec|private)\s+){0,2}function\s+(?>(?:autoexec|private)\s+){0,2}\w+\s*\('
+  - '\b(?:level|self)[ \t]+thread[ \t]+(?:\[\[[ \t]*(?>\w+\.)*\w+[ \t]*\]\]|\w+)[ \t]*\([^\r\n\)]*\)[ \t]*;'
+  - '^[ \t]*#[ \t]*(?:precache|using_animtree)[ \t]*\('
+  key_equals_value: '^[^#!;][^=]*='
+  m68k:
+  - '(?im)\bmoveq(?:\.l)?\s+#(?:\$-?[0-9a-f]{1,3}|%[0-1]{1,8}|-?[0-9]{1,3}),\s*d[0-7]\b'
+  - '(?im)^\s*move(?:\.[bwl])?\s+(?:sr|usp),\s*[^\s]+'
+  - '(?im)^\s*move\.[bwl]\s+.*\b[ad]\d'
+  - '(?im)^\s*movem\.[bwl]\b'
+  - '(?im)^\s*move[mp](?:\.[wl])?\b'
+  - '(?im)^\s*btst\b'
+  - '(?im)^\s*dbra\b'
+  man-heading:  '^[.''][ \t]*SH +(?:[^"\s]+|"[^"\s]+)'
+  man-title:    '^[.''][ \t]*TH +(?:[^"\s]+|"[^"]+") +"?(?:[1-9]|@[^\s@]+@)'
+  mdoc-date:    '^[.''][ \t]*Dd +(?:[^"\s]+|"[^"]+")'
+  mdoc-heading: '^[.''][ \t]*Sh +(?:[^"\s]|"[^"]+")'
+  mdoc-title:   '^[.''][ \t]*Dt +(?:[^"\s]+|"[^"]+") +"?(?:[1-9]|@[^\s@]+@)'
+  objectivec: '^\s*(@(interface|class|protocol|property|end|synchronised|selector|implementation)\b|#import\s+.+\.h[">])'
+  perl:
+  - '\buse\s+(?:strict\b|v?5\b)'
+  - '^\s*use\s+(?:constant|overload)\b'
+  - '^\s*(?:\*|(?:our\s*)?@)EXPORT\s*='
+  - '^\s*package\s+[^\W\d]\w*(?:::\w+)*\s*(?:[;{]|\sv?\d)'
+  - '[\s$][^\W\d]\w*(?::\w+)*->[a-zA-Z_\[({]'
+  raku: '^\s*(?:use\s+v6\b|\bmodule\b|\b(?:my\s+)?class\b)'
+  vb-class: '^[ ]*VERSION [0-9]\.[0-9] CLASS'
+  vb-form: '^[ ]*VERSION [0-9]\.[0-9]{2}'
+  vb-module: '^[ ]*Attribute VB_Name = '
+  vba:
+  - '\b(?:VBA|[vV]ba)(?:\b|[0-9A-Z_])'
+    # VBA7 new 64-bit features
+  - '^[ ]*(?:Public|Private)? Declare PtrSafe (?:Sub|Function)\b'
+  - '^[ ]*#If Win64\b'
+  - '^[ ]*(?:Dim|Const) [0-9a-zA-Z_]*[ ]*As Long(?:Ptr|Long)\b'
+  # Top module declarations unique to VBA
+  - '^[ ]*Option (?:Private Module|Compare (?:Database|Text|Binary))\b'
+  # General VBA libraries and objects
+  - '(?: |\()(?:Access|Excel|Outlook|PowerPoint|Visio|Word|VBIDE)\.\w'
+  - '\b(?:(?:Active)?VBProjects?|VBComponents?|Application\.(?:VBE|ScreenUpdating))\b'
+  # AutoCAD, Outlook, PowerPoint and Word objects
+  - '\b(?:ThisDrawing|AcadObject|Active(?:Explorer|Inspector|Window\.Presentation|Presentation|Document)|Selection\.(?:Find|Paragraphs))\b'
+  # Excel objects
+  - '\b(?:(?:This|Active)?Workbooks?|Worksheets?|Active(?:Sheet|Chart|Cell)|WorksheetFunction)\b'
+  - '\b(?:Range\(".*|Cells\([0-9a-zA-Z_]*, (?:[0-9a-zA-Z_]*|"[a-zA-Z]{1,3}"))\)'