github-linguist 7.11.0 → 7.13.0

data/grammars/text.xml.xsl.json

@@ -1,88 +1 @@
-{
-  "name": "XSL",
-  "scopeName": "text.xml.xsl",
-  "patterns": [
-    {
-      "name": "meta.tag.xml.template",
-      "begin": "(\u003c)(xsl)((:))(template)",
-      "end": "(\u003e)",
-      "patterns": [
-        {
-          "match": " (?:([-_a-zA-Z0-9]+)((:)))?([a-zA-Z-]+)",
-          "captures": {
-            "1": {
-              "name": "entity.other.attribute-name.namespace.xml"
-            },
-            "2": {
-              "name": "entity.other.attribute-name.xml"
-            },
-            "3": {
-              "name": "punctuation.separator.namespace.xml"
-            },
-            "4": {
-              "name": "entity.other.attribute-name.localname.xml"
-            }
-          }
-        },
-        {
-          "include": "#doublequotedString"
-        },
-        {
-          "include": "#singlequotedString"
-        }
-      ],
-      "captures": {
-        "1": {
-          "name": "punctuation.definition.tag.xml"
-        },
-        "2": {
-          "name": "entity.name.tag.namespace.xml"
-        },
-        "3": {
-          "name": "entity.name.tag.xml"
-        },
-        "4": {
-          "name": "punctuation.separator.namespace.xml"
-        },
-        "5": {
-          "name": "entity.name.tag.localname.xml"
-        }
-      }
-    },
-    {
-      "include": "text.xml"
-    }
-  ],
-  "repository": {
-    "doublequotedString": {
-      "name": "string.quoted.double.xml",
-      "begin": "\"",
-      "end": "\"",
-      "beginCaptures": {
-        "0": {
-          "name": "punctuation.definition.string.begin.xml"
-        }
-      },
-      "endCaptures": {
-        "0": {
-          "name": "punctuation.definition.string.end.xml"
-        }
-      }
-    },
-    "singlequotedString": {
-      "name": "string.quoted.single.xml",
-      "begin": "'",
-      "end": "'",
-      "beginCaptures": {
-        "0": {
-          "name": "punctuation.definition.string.begin.xml"
-        }
-      },
-      "endCaptures": {
-        "0": {
-          "name": "punctuation.definition.string.end.xml"
-        }
-      }
-    }
-  }
-}
+{"name":"XSL","scopeName":"text.xml.xsl","patterns":[{"name":"meta.tag.xml.template","begin":"(\u003c)(xsl)((:))(template)","end":"(\u003e)","patterns":[{"match":" (?:([-_a-zA-Z0-9]+)((:)))?([a-zA-Z-]+)","captures":{"1":{"name":"entity.other.attribute-name.namespace.xml"},"2":{"name":"entity.other.attribute-name.xml"},"3":{"name":"punctuation.separator.namespace.xml"},"4":{"name":"entity.other.attribute-name.localname.xml"}}},{"include":"#doublequotedString"},{"include":"#singlequotedString"}],"captures":{"1":{"name":"punctuation.definition.tag.xml"},"2":{"name":"entity.name.tag.namespace.xml"},"3":{"name":"entity.name.tag.xml"},"4":{"name":"punctuation.separator.namespace.xml"},"5":{"name":"entity.name.tag.localname.xml"}}},{"include":"text.xml"}],"repository":{"doublequotedString":{"name":"string.quoted.double.xml","begin":"\"","end":"\"","beginCaptures":{"0":{"name":"punctuation.definition.string.begin.xml"}},"endCaptures":{"0":{"name":"punctuation.definition.string.end.xml"}}},"singlequotedString":{"name":"string.quoted.single.xml","begin":"'","end":"'","beginCaptures":{"0":{"name":"punctuation.definition.string.begin.xml"}},"endCaptures":{"0":{"name":"punctuation.definition.string.end.xml"}}}}}

data/grammars/text.zone_file.json

@@ -1,67 +1 @@
-{
-  "name": "Bind Zone Files",
-  "scopeName": "text.zone_file",
-  "patterns": [
-    {
-      "name": "comment.line.semicolon.zone_file",
-      "match": ";.*"
-    },
-    {
-      "name": "keyword.directive.zone_file",
-      "match": "@"
-    },
-    {
-      "name": "keyword.directive.zone_file",
-      "match": "\\$(ORIGIN|origin|TTL|ttl|INCLUDE|include)\\s*([^;]*)(;.*)?",
-      "captures": {
-        "2": {
-          "name": "variable.other.directive.zone_file"
-        },
-        "3": {
-          "name": "comment.line.semicolon.zone_file"
-        }
-      }
-    },
-    {
-      "name": "variable.other.timeunit.zone_file",
-      "match": "\\d+(H|h|D|d|W|w|M|m|Y|y)"
-    },
-    {
-      "name": "string.quoted.single.address.zone_file",
-      "begin": "([A-Za-z0-9_.-]*)\\s+(?:([0-9A-Za-z]*)\\s+)?([I|i][N|n]\\s+[A-Za-z0-9]+)\\s+(.*)\\(",
-      "end": "\\)",
-      "patterns": [
-        {
-          "name": "comment.line.semicolon.zone_file",
-          "match": ";.*"
-        }
-      ],
-      "beginCaptures": {
-        "2": {
-          "name": "variable.other.timeunit.zone_file"
-        },
-        "3": {
-          "name": "keyword.resourcetype.zone_file"
-        },
-        "4": {
-          "name": "string.quoted.single.resource.address.zone_file"
-        }
-      }
-    },
-    {
-      "name": "string.quoted.single.address.zone_file",
-      "match": "([A-Za-z0-9_.-]*)\\s+(?:([0-9A-Za-z]*)\\s+)?([I|i][N|n]\\s+[A-Za-z0-9]+)\\s+(.*)",
-      "captures": {
-        "2": {
-          "name": "variable.other.timeunit.zone_file"
-        },
-        "3": {
-          "name": "keyword.resourcetype.zone_file"
-        },
-        "4": {
-          "name": "string.quoted.single.resource.address.zone_file"
-        }
-      }
-    }
-  ]
-}
+{"name":"Bind Zone Files","scopeName":"text.zone_file","patterns":[{"name":"comment.line.semicolon.zone_file","match":";.*"},{"name":"keyword.directive.zone_file","match":"@"},{"name":"keyword.directive.zone_file","match":"\\$(ORIGIN|origin|TTL|ttl|INCLUDE|include)\\s*([^;]*)(;.*)?","captures":{"2":{"name":"variable.other.directive.zone_file"},"3":{"name":"comment.line.semicolon.zone_file"}}},{"name":"variable.other.timeunit.zone_file","match":"\\d+(H|h|D|d|W|w|M|m|Y|y)"},{"name":"string.quoted.single.address.zone_file","begin":"([A-Za-z0-9_.-]*)\\s+(?:([0-9A-Za-z]*)\\s+)?([I|i][N|n]\\s+[A-Za-z0-9]+)\\s+(.*)\\(","end":"\\)","patterns":[{"name":"comment.line.semicolon.zone_file","match":";.*"}],"beginCaptures":{"2":{"name":"variable.other.timeunit.zone_file"},"3":{"name":"keyword.resourcetype.zone_file"},"4":{"name":"string.quoted.single.resource.address.zone_file"}}},{"name":"string.quoted.single.address.zone_file","match":"([A-Za-z0-9_.-]*)\\s+(?:([0-9A-Za-z]*)\\s+)?([I|i][N|n]\\s+[A-Za-z0-9]+)\\s+(.*)","captures":{"2":{"name":"variable.other.timeunit.zone_file"},"3":{"name":"keyword.resourcetype.zone_file"},"4":{"name":"string.quoted.single.resource.address.zone_file"}}}]}

data/grammars/version

@@ -1 +1 @@
-7.11.0
+7.13.0

data/lib/linguist/VERSION

@@ -1 +1 @@
-7.11.0
+7.13.0

data/lib/linguist/classifier.rb

@@ -39,7 +39,11 @@ module Linguist
     # Set LINGUIST_DEBUG=1 or =2 to see probabilities per-token or
     # per-language.  See also #dump_all_tokens, below.
     def self.train!(db, language, data)
-      tokens = Tokenizer.tokenize(data)
+      tokens = data
+      tokens = Tokenizer.tokenize(tokens) if tokens.is_a?(String)
+
+      counts = Hash.new(0)
+      tokens.each { |tok| counts[tok] += 1 }
 
       db['tokens_total'] ||= 0
       db['languages_total'] ||= 0
@@ -47,13 +51,13 @@ module Linguist
       db['language_tokens'] ||= {}
       db['languages'] ||= {}
 
-      tokens.each do |token|
+      counts.each do |token, count|
         db['tokens'][language] ||= {}
         db['tokens'][language][token] ||= 0
-        db['tokens'][language][token] += 1
+        db['tokens'][language][token] += count
         db['language_tokens'][language] ||= 0
-        db['language_tokens'][language] += 1
-        db['tokens_total'] += 1
+        db['language_tokens'][language] += count
+        db['tokens_total'] += count
       end
       db['languages'][language] ||= 0
       db['languages'][language] += 1
@@ -87,6 +91,7 @@ module Linguist
       @tokens          = db['tokens']
       @language_tokens = db['language_tokens']
       @languages       = db['languages']
+      @unknown_logprob = Math.log(1 / db['tokens_total'].to_f)
     end
 
     # Internal: Guess language of data
@@ -103,9 +108,12 @@ module Linguist
 
       debug_dump_all_tokens(tokens, languages) if verbosity >= 2
 
+      counts = Hash.new(0)
+      tokens.each { |tok| counts[tok] += 1 }
+
       languages.each do |language|
-        scores[language] = tokens_probability(tokens, language) + language_probability(language)
-        debug_dump_probabilities(tokens, language, scores[language]) if verbosity >= 1
+        scores[language] = tokens_probability(counts, language) + language_probability(language)
+        debug_dump_probabilities(counts, language, scores[language]) if verbosity >= 1
       end
 
       scores.sort { |a, b| b[1] <=> a[1] }.map { |score| [score[0], score[1]] }
@@ -117,23 +125,27 @@ module Linguist
     # language - Language to check.
     #
     # Returns Float between 0.0 and 1.0.
-    def tokens_probability(tokens, language)
-      tokens.inject(0.0) do |sum, token|
-        sum += Math.log(token_probability(token, language))
+    def tokens_probability(counts, language)
+      sum = 0
+      counts.each do |token, count|
+        sum += count * token_probability(token, language)
       end
+      sum
     end
 
-    # Internal: Probably of token in language occurring - P(F | C)
+    # Internal: Log-probability of token in language occurring - P(F | C)
     #
     # token    - String token.
     # language - Language to check.
     #
-    # Returns Float between 0.0 and 1.0.
+    # Returns Float.
     def token_probability(token, language)
-      if @tokens[language][token].to_f == 0.0
-        1 / @tokens_total.to_f
+      count = @tokens[language][token]
+      if count.nil? || count == 0
+        # This is usually the most common case, so we cache the result.
+        @unknown_logprob
       else
-        @tokens[language][token].to_f / @language_tokens[language].to_f
+        Math.log(count.to_f / @language_tokens[language].to_f)
       end
     end
 
@@ -178,12 +190,11 @@ module Linguist
         token_map.sort.each { |tok, count|
           arr = languages.map { |lang| [lang, token_probability(tok, lang)] }
           min = arr.map { |a,b| b }.min
-          minlog = Math.log(min)
           if !arr.inject(true) { |result, n| result && n[1] == arr[0][1] }
             printf "%#{maxlen}s%5d", tok, count
 
             puts arr.map { |ent|
-              ent[1] == min ? "         -" : sprintf("%10.3f", count * (Math.log(ent[1]) - minlog))
+              ent[1] == min ? "         -" : sprintf("%10.3f", count * (ent[1] - min))
             }.join
           end
         }

data/lib/linguist/generated.rb

@@ -83,6 +83,7 @@ module Linguist
       generated_apache_thrift? ||
       generated_jni_header? ||
       vcr_cassette? ||
+      generated_antlr? ||
       generated_module? ||
       generated_unity3d_meta? ||
       generated_racc? ||
@@ -98,7 +99,8 @@ module Linguist
       generated_gimp? ||
       generated_visualstudio6? ||
       generated_haxe? ||
-      generated_jooq?
+      generated_jooq? ||
+      generated_pascal_tlb?
     end
 
     # Internal: Is the blob an Xcode file?
@@ -240,7 +242,7 @@ module Linguist
     #
     # Returns true or false
     def generated_net_designer_file?
-      name.downcase =~ /\.designer\.(cs|vb)$/
+      !!name.match(/\.designer\.(cs|vb)$/i)
     end
 
     # Internal: Is this a codegen file for Specflow feature file?
@@ -251,7 +253,7 @@ module Linguist
     #
     # Returns true or false
     def generated_net_specflow_feature_file?
-      name.downcase =~ /\.feature\.cs$/
+      !!name.match(/\.feature\.cs$/i)
     end
 
     # Internal: Is the blob of JS a parser generated by PEG.js?
@@ -441,6 +443,14 @@ module Linguist
       return lines[-2].include?("recorded_with: VCR")
     end
 
+    # Is this a generated ANTLR file?
+    #
+    # Returns true or false
+    def generated_antlr?
+      return false unless extname == '.g'
+      return lines[1].include?("generated by Xtest")
+    end
+
     # Internal: Is this a compiled C/C++ file from Cython?
     #
     # Cython-compiled C/C++ files typically contain:
@@ -708,6 +718,16 @@ module Linguist
       lines.first(2).any? { |l| l.include? 'This file is generated by jOOQ.' }
     end
 
+    # Internal: Is this a generated Delphi Interface file for a type library?
+    #
+    # Delphi Type Library Import tool generates *_TLB.pas files based on .ridl files.
+    # They are not meant to be altered by humans.
+    #
+    # Returns true or false
+    def generated_pascal_tlb?
+      !!name.match(/_tlb\.pas$/i)
+    end
+
     # Internal: Extract a Hash of name/content pairs from an HTML <meta> tag
     def extract_html_meta(match)
       (match.last.sub(/\/\Z/, "").strip.scan(/

data/lib/linguist/generic.yml

@@ -0,0 +1,18 @@
+# This is a list of file extensions considered too common to safely associate
+# with only the formats Linguist recognises. In addition to the stipulated
+# extension requirement, candidate matches must also satisfy a heuristic
+# (or some other strategy) in order to be identified as any one language.
+
+---
+extensions:
+- ".1"
+- ".2"
+- ".3"
+- ".4"
+- ".5"
+- ".6"
+- ".7"
+- ".8"
+- ".9"
+- ".cmp"
+- ".sol"

data/lib/linguist/heuristics.yml

@@ -28,27 +28,35 @@
 #
 ---
 disambiguations:
-- extensions: ['.1', '.1in', '.1m', '.1x', '.2', '.3', '.3in', '.3m', '.3p', '.3pm', '.3qt', '.3x', '.4', '.5', '.6', '.7', '.8', '.9', '.man', '.mdoc']
+- extensions: ['.1', '.2', '.3', '.4', '.5', '.6', '.7', '.8', '.9']
   rules:
-  # Document which uses mdoc(7) macros
   - language: Roff Manpage
     and:
-    - pattern: '^[.''][ \t]*Dd +(?:[^"\s]+|"[^"]+")'
-    - pattern: '^[.''][ \t]*Dt +(?:[^"\s]+|"[^"]+") +"?(?:[1-9]|@[^\s@]+@)'
-    - pattern: '^[.''][ \t]*Sh +(?:[^"\s]|"[^"]+")'
-
-  # Document which uses man(7) macros
+    - named_pattern: mdoc-date
+    - named_pattern: mdoc-title
+    - named_pattern: mdoc-heading
   - language: Roff Manpage
     and:
-    - pattern: '^[.''][ \t]*TH +(?:[^"\s]+|"[^"]+") +"?(?:[1-9]|@[^\s@]+@)'
-    - pattern: '^[.''][ \t]*SH +(?:[^"\s]+|"[^"\s]+)'
-
-  # Open-ended fallback to unrendered Roff source
+    - named_pattern: man-title
+    - named_pattern: man-heading
+  - language: Roff
+    pattern: '^\.(?:[A-Za-z]{2}(?:\s|$)|\\")'
+- extensions: ['.1in', '.1m', '.1x', '.3in', '.3m', '.3p', '.3pm', '.3qt', '.3x', '.man', '.mdoc']
+  rules:
+  - language: Roff Manpage
+    and:
+    - named_pattern: mdoc-date
+    - named_pattern: mdoc-title
+    - named_pattern: mdoc-heading
+  - language: Roff Manpage
+    and:
+    - named_pattern: man-title
+    - named_pattern: man-heading
   - language: Roff
 - extensions: ['.al']
   rules:
-  # AL Code pattern source from https://github.com/microsoft/AL/blob/master/grammar/alsyntax.tmlanguage - keyword.other.applicationobject.al
-  - language: AL Code
+  # AL pattern source from https://github.com/microsoft/AL/blob/master/grammar/alsyntax.tmlanguage - keyword.other.applicationobject.al
+  - language: AL
     and:
     - pattern: '\b(?i:(CODEUNIT|PAGE|PAGEEXTENSION|PAGECUSTOMIZATION|DOTNET|ENUM|ENUMEXTENSION|VALUE|QUERY|REPORT|TABLE|TABLEEXTENSION|XMLPORT|PROFILE|CONTROLADDIN))\b'
   # Open-ended fallback to Perl AutoLoader
@@ -56,8 +64,7 @@ disambiguations:
 - extensions: ['.as']
   rules:
   - language: ActionScript
-    pattern: '^\s*(package\s+[a-z0-9_\.]+|import\s+[a-zA-Z0-9_\.]+;|class\s+[A-Za-z0-9_]+\s+extends\s+[A-Za-z0-9_]+)'
-  - language: AngelScript
+    pattern: '^\s*(?:package(?:\s+[\w.]+)?\s+(?:{|$)|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
@@ -103,6 +110,10 @@ disambiguations:
     pattern: '\\\w+{'
   - language: ObjectScript
     pattern: '^Class\s'
+- extensions: ['.cmp']
+  rules:
+  - language: Gerber Image
+    pattern: '^[DGMT][0-9]{2}\*\r?\n'
 - extensions: ['.cs']
   rules:
   - language: Smalltalk
@@ -186,14 +197,16 @@ disambiguations:
   - language: Graph Modeling Language
     pattern: '(?i:^\s*(graph|node)\s+\[$)'
   - language: Gerber Image
-    pattern: '\*\%$'
+    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\.'
+    pattern: '^uses (java|gw)\.'
+  - language: Genie
+    pattern: '^\[indent=[0-9]+\]'
 - extensions: ['.h']
   rules:
   - language: Objective-C
@@ -271,6 +284,13 @@ disambiguations:
     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
@@ -316,6 +336,8 @@ disambiguations:
   rules:
   - language: XML
     pattern: '^\s*<\?xml\s+version'
+  - language: Gerber Image
+    pattern: '^[DGMT][0-9]{2}\*\r?\n'
   - language: Text
     pattern: 'THE_TITLE'
 - extensions: ['.nl']
@@ -431,6 +453,12 @@ disambiguations:
     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
@@ -448,6 +476,8 @@ disambiguations:
     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
@@ -463,7 +493,7 @@ disambiguations:
   - 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: '^G75\*'
+    pattern: '^[DGMT][0-9]{2}\*\r?\n'
 - extensions: ['.sql']
   rules:
    # Postgres
@@ -488,7 +518,7 @@ disambiguations:
   - language: Perl
     named_pattern: perl5
   - language: Raku
-    named_pattern: perl6
+    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: ['.toc']
@@ -519,16 +549,16 @@ disambiguations:
     # 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: '(?:(?:\s|^)vi(?:m[<=>]?\d+|m)?|\sex)(?=:(?=\s*set?\s[^\n:]+:)|:(?!\s* set?\s))(?:(?:\s|\s*:\s*)\w*(?:\s*=(?:[^\\\s]|\\.)*)?)*[\s:](?:filetype|ft|syntax)\s*=help(?=\s|:|$)'
+    pattern: '(?:(?:[ \t]|^)vi(?:m[<=>]?\d+|m)?|[ \t]ex)(?=:(?=[ \t]*set?[ \t][^\n:]+:)|:(?![ \t]* set?[ \t]))(?:(?:[ \t]|[ \t]*:[ \t]*)\w*(?:[ \t]*=(?:[^\\[ \t]]|\\.)*)?)*[[ \t]:](?:filetype|ft|syntax)[ \t]*=help(?=[ \t]|:|$)'
     # 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: ['.v']
   rules:
   - language: Coq
-    pattern: '\(\*.*?\*\)|(?:^|\s)(?:Proof|Qed)\.(?:$|\s)|(?:^|\s)Require[ \t]+Import\s'
+    pattern: '(?:^|\s)(?:Proof|Qed)\.(?:$|\s)|(?:^|\s)Require[ \t]+(Import|Export)\s'
   - language: Verilog
-    pattern: '^[ \t]*module\s+[^\s()]+\s+\#?\(|^[ \t]*`(?:ifdef|timescale)\s|^[ \t]*always[ \t]+@'
+    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']
@@ -576,6 +606,11 @@ named_patterns:
   - '(?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[">])'
   perl5: '\buse\s+(?:strict\b|v?5\.)'
   perl6: '^\s*(?:use\s+v6\b|\bmodule\b|\b(?:my\s+)?class\b)'