tartrazine/lexers/heuristics.yml

914 lines
29 KiB
YAML
Raw Normal View History

2024-08-15 18:39:02 +00:00
# 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
2024-08-15 18:39:02 +00:00
and:
- named_pattern: mdoc-date
- named_pattern: mdoc-title
- named_pattern: mdoc-heading
- language: man
2024-08-15 18:39:02 +00:00
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
2024-08-15 18:39:02 +00:00
and:
- named_pattern: mdoc-date
- named_pattern: mdoc-title
- named_pattern: mdoc-heading
- language: man
2024-08-15 18:39:02 +00:00
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\([0-9a-zA-Z_]*, (?:[0-9a-zA-Z_]*|"[a-zA-Z]{1,3}"))\)'