rouge 0.2.15 → 0.3.0

data/Gemfile

@@ -12,6 +12,7 @@ gem 'redcarpet', :platforms => :ruby
 
 # for visual tests
 gem 'sinatra'
+gem 'shotgun'
 
 # docs
 gem 'yard'

data/lib/rouge/demos/gherkin

@@ -0,0 +1,17 @@
+# language: en
+Feature: Addition
+  In order to avoid silly mistakes
+  As a math idiot
+  I want to be told the sum of two numbers
+
+  Scenario Outline: Add two numbers
+    Given I have entered <input_1> into the calculator
+    And I have entered <input_2> into the calculator
+    When I press <button>
+    Then the result should be <output> on the screen
+
+  Examples:
+    | input_1 | input_2 | button | output |
+    | 20      | 30      | add    | 50     |
+    | 2       | 5       | add    | 7      |
+    | 0       | 40      | add    | 40     |

data/lib/rouge/demos/llvm

@@ -0,0 +1,20 @@
+; copied from http://llvm.org/docs/LangRef.html#module-structure
+; Declare the string constant as a global constant.
+@.str = private unnamed_addr constant [13 x i8] c"hello world\0A\00"
+
+; External declaration of the puts function
+declare i32 @puts(i8* nocapture) nounwind
+
+; Definition of main function
+define i32 @main() {   ; i32()*
+  ; Convert [13 x i8]* to i8  *...
+  %cast210 = getelementptr [13 x i8]* @.str, i64 0, i64 0
+
+  ; Call puts function to write out the string to stdout.
+  call i32 @puts(i8* %cast210)
+  ret i32 0
+}
+
+; Named metadata
+!1 = metadata !{i32 42}
+!foo = !{!1, null}

data/lib/rouge/demos/prolog

@@ -0,0 +1,9 @@
+diff(plus(A,B), X, plus(DA, DB))
+   <= diff(A, X, DA) and diff(B, X, DB).
+
+diff(times(A,B), X, plus(times(A, DB), times(DA, B)))
+   <= diff(A, X, DA) and diff(B, X, DB).
+
+equal(X, X).
+diff(X, X, 1).
+diff(Y, X, 0) <= not equal(Y, X).

data/lib/rouge/lexer.rb

@@ -89,6 +89,42 @@ module Rouge
         registry.values.uniq
       end
 
+      # Guess which lexer to use based on a hash of info.
+      #
+      # This accepts the same arguments as Lexer.guess, but will never throw
+      # an error.  It will return a (possibly empty) list of potential lexers
+      # to use.
+      def guesses(info={})
+        mimetype, filename, source = info.values_at(:mimetype, :filename, :source)
+        lexers = registry.values.uniq
+        total_size = lexers.size
+
+        lexers = filter_by_mimetype(lexers, mimetype) if mimetype
+        return lexers if lexers.size == 1
+
+        lexers = filter_by_filename(lexers, filename) if filename
+        return lexers if lexers.size == 1
+
+        if source
+          # If we're filtering against *all* lexers, we only use confident return
+          # values from analyze_text.  But if we've filtered down already, we can trust
+          # the analysis more.
+          source_threshold = lexers.size < total_size ? 0 : 0.5
+          return [best_by_source(lexers, source, source_threshold)].compact
+        end
+
+        []
+      end
+
+      class AmbiguousGuess < StandardError
+        attr_reader :alternatives
+        def initialize(alternatives); @alternatives = alternatives; end
+
+        def message
+          "Ambiguous guess: can't decide between #{alternatives.map(&:tag).inspect}"
+        end
+      end
+
       # Guess which lexer to use based on a hash of info.
       #
       # @option info :mimetype
@@ -101,41 +137,71 @@ module Rouge
       #   other hints.
       #
       # @see Lexer.analyze_text
+      # @see Lexer.multi_guess
       def guess(info={})
-        by_mimetype = guess_by_mimetype(info[:mimetype]) if info[:mimetype]
-        return by_mimetype if by_mimetype
-
-        by_filename = guess_by_filename(info[:filename]) if info[:filename]
-        return by_filename if by_filename
+        lexers = guesses(info)
 
-        by_source = guess_by_source(info[:source]) if info[:source]
-        return by_source if by_source
+        return Lexers::Text if lexers.empty?
+        return lexers[0] if lexers.size == 1
 
-        # guessing failed, just parse it as text
-        return Lexers::Text
+        raise AmbiguousGuess.new(lexers)
       end
 
       def guess_by_mimetype(mt)
-        registry.values.detect do |lexer|
-          lexer.mimetypes.include? mt
-        end
+        guess :mimetype => mt
       end
 
       def guess_by_filename(fname)
+        guess :filename => fname
+      end
+
+      def guess_by_source(source)
+        guess :source => source
+      end
+
+    private
+      def filter_by_mimetype(lexers, mt)
+        lexers.select { |lexer| lexer.mimetypes.include? mt }
+      end
+
+      # returns a list of lexers that match the given filename with
+      # equal specificity (i.e. number of wildcards in the pattern).
+      # This helps disambiguate between, e.g. the Nginx lexer, which
+      # matches `nginx.conf`, and the Conf lexer, which matches `*.conf`.
+      # In this case, nginx will win because the pattern has no wildcards,
+      # while `*.conf` has one.
+      def filter_by_filename(lexers, fname)
         fname = File.basename(fname)
-        registry.values.detect do |lexer|
-          lexer.filenames.any? do |pattern|
-            File.fnmatch?(pattern, fname, File::FNM_DOTMATCH)
+
+        out = []
+        best_seen = nil
+        lexers.each do |lexer|
+          score = lexer.filenames.map do |pattern|
+            if File.fnmatch?(pattern, fname, File::FNM_DOTMATCH)
+              # specificity is better the fewer wildcards there are
+              pattern.scan(/[*?\[]/).size
+            end
+          end.compact.min
+
+          next unless score
+
+          if best_seen.nil? || score < best_seen
+            best_seen = score
+            out = [lexer]
+          elsif score == best_seen
+            out << lexer
           end
         end
+
+        out
       end
 
-      def guess_by_source(source)
+      def best_by_source(lexers, source, threshold=0)
         assert_utf8!(source)
 
         source = TextAnalyzer.new(source)
 
-        best_result = 0
+        best_result = threshold
         best_match = nil
         registry.values.each do |lexer|
           result = lexer.analyze_text(source) || 0
@@ -150,11 +216,13 @@ module Rouge
         best_match
       end
 
+    protected
       # @private
       def register(name, lexer)
         registry[name.to_s] = lexer
       end
 
+    public
       # Used to specify or get the canonical name of this lexer class.
       #
       # @example
@@ -332,7 +400,8 @@ module Rouge
     #
     # Return a number between 0 and 1 indicating the likelihood that
     # the text given should be lexed with this lexer.  The default
-    # implementation returns 0.
+    # implementation returns 0.  Values under 0.5 will only be used
+    # to disambiguate filename or mimetype matches.
     #
     # @param [TextAnalyzer] text
     #   the text to be analyzed, with a couple of handy methods on it,

data/lib/rouge/lexers/csharp.rb

@@ -50,13 +50,13 @@ module Rouge
         rule /@"(\\.|.)*?"/, 'Literal.String'
         rule /"(\\.|.)*?["\n]/, 'Literal.String'
         rule /'(\\.|.)'/, 'Literal.String.Char'
+        rule /0x[0-9a-f]+[lu]?/i, 'Literal.Number'
         rule %r(
           [0-9]
           ([.][0-9]*)? # decimal
           (e[+-][0-9]+)? # exponent
-          [fld]? # type
+          [fldu]? # type
         )ix, 'Literal.Number'
-        rule /0x[0-9a-f]+l?/i, 'Literal.Number'
         rule /^#[ \t]*(#{cpp_keywords.join('|')})\b.*?\n/,
           'Comment.Preproc'
         rule /\b(#{keywords.join('|')})\b/, 'Keyword'

data/lib/rouge/lexers/gherkin.rb

@@ -0,0 +1,130 @@
+# -*- coding: utf-8 -*- #
+
+module Rouge
+  module Lexers
+    class Gherkin < RegexLexer
+      tag 'gherkin'
+      aliases 'cucumber'
+
+      filenames '*.feature'
+      mimetypes 'text/x-gherkin'
+
+      def self.analyze_text(text)
+        return 1 if text.shebang? 'cucumber'
+      end
+
+      # self-modifying method that loads the keywords file
+      def self.keywords
+        load Pathname.new(__FILE__).dirname.join('gherkin/keywords.rb')
+        keywords
+      end
+
+      def self.step_regex
+        # in Gherkin's config, keywords that end in < don't
+        # need word boundaries at the ends - all others do.
+        @step_regex ||= Regexp.new(
+          keywords[:step].map do |w|
+            if w.end_with? '<'
+              Regexp.escape(w.chop)
+            else
+              "#{Regexp.escape(w)}\\b"
+            end
+          end.join('|')
+        )
+      end
+
+      rest_of_line = /.*?(?=[#\n])/
+
+      state :basic do
+        rule %r(#.*$), 'Comment'
+        rule /[ \r\t]+/, 'Text'
+      end
+
+      state :root do
+        mixin :basic
+        rule %r(\n), 'Text'
+        rule %r(""".*?""")m, 'Literal.String'
+        rule %r(@[^\s@]+), 'Name.Tag'
+        mixin :has_table
+        mixin :has_examples
+      end
+
+      state :has_scenarios do
+        rule %r((.*?)(:)) do |m|
+          reset_stack
+
+          keyword = m[1]
+          if self.class.keywords[:element].include? keyword
+            group 'Keyword.Namespace'; push :description
+          elsif self.class.keywords[:feature].include? keyword
+            group 'Keyword.Declaration'; push :feature_description
+          elsif self.class.keywords[:examples].include? keyword
+            group 'Name.Namespace'; push :example_description
+          else
+            group 'Error'
+          end
+
+          group 'Punctuation'
+        end
+      end
+
+      state :has_examples do
+        mixin :has_scenarios
+        rule Gherkin.step_regex, 'Name.Function' do
+          token 'Name.Function'
+          reset_stack; push :step
+        end
+      end
+
+      state :has_table do
+        rule(/(?=[|])/) { push :table_header }
+      end
+
+      state :table_header do
+        rule /[^|\s]+/, 'Name.Variable'
+        rule /\n/ do
+          token 'Text'
+          pop!; push :table
+        end
+        mixin :table
+      end
+
+      state :table do
+        rule(/^(?=\s*[^\s|])/) { reset_stack }
+        mixin :basic
+        rule /[|]/, 'Punctuation'
+        rule /[^|\s]+/, 'Name'
+      end
+
+      state :description do
+        mixin :basic
+        mixin :has_examples
+        rule /\n/, 'Text'
+        rule rest_of_line, 'Text'
+      end
+
+      state :feature_description do
+        mixin :basic
+        mixin :has_scenarios
+        rule /\n/, 'Text'
+        rule rest_of_line, 'Text'
+      end
+
+      state :example_description do
+        mixin :basic
+        mixin :has_table
+        rule /\n/, 'Text'
+        rule rest_of_line, 'Text'
+      end
+
+      state :step do
+        mixin :basic
+        rule /<.*?>/, 'Name.Variable'
+        rule /".*?"/, 'Literal.String'
+        rule /\S+/, 'Text'
+        rule rest_of_line, 'Text', :pop!
+      end
+    end
+  end
+end
+

data/lib/rouge/lexers/gherkin/keywords.rb

@@ -0,0 +1,14 @@
+# -*- coding: utf-8 -*- #
+# automatically generated by `rake builtins:gherkin`
+module Rouge
+  module Lexers
+    def Gherkin.keywords
+      @keywords ||= {}.tap do |k|
+        k[:feature] = Set.new ["Ability", "Ahoy matey!", "Arwedd", "Aspekt", "Business Need", "Caracteristica", "Característica", "Egenskab", "Egenskap", "Eiginleiki", "Feature", "Fitur", "Fonctionnalité", "Funcionalidade", "Funcionalitat", "Functionalitate", "Functionaliteit", "Funcţionalitate", "Funcționalitate", "Fungsi", "Funkcia", "Funkcionalitāte", "Funkcionalnost", "Funkcja", "Funktionalität", "Funktionalitéit", "Funzionalità", "Fīča", "Jellemző", "Mogucnost", "Mogućnost", "OH HAI", "Omadus", "Ominaisuus", "Osobina", "Potrzeba biznesowa", "Požadavek", "Požiadavka", "Pretty much", "Savybė", "Trajto", "Tính năng", "Vlastnosť", "Właściwość", "Özellik", "Могућност", "Мөмкинлек", "Особина", "Свойство", "Функционал", "Функционалност", "Функция", "Функціонал", "Үзенчәлеклелек", "תכונה", "خاصية", "وِیژگی", "रूप लेख", "గుణము", "フィーチャ", "功能", "機能", "기능"]
+        k[:element] = Set.new ["Abstract Scenario", "Abstrakt Scenario", "Achtergrond", "All y'all", "Antecedentes", "Antecedents", "Atburðarás", "Awww, look mate", "B4", "Background", "Baggrund", "Bakgrund", "Bakgrunn", "Bakgrunnur", "Bối cảnh", "Cefndir", "Cenario", "Cenario de Fundo", "Cenário", "Cenário de Fundo", "Contesto", "Context", "Contexte", "Contexto", "Dasar", "Delineacao do Cenario", "Delineação do Cenário", "Dis is what went down", "Escenari", "Escenario", "Esquema de l'escenari", "Esquema del escenario", "Esquema do Cenario", "Esquema do Cenário", "First off", "Fono", "Forgatókönyv", "Forgatókönyv vázlat", "Fundo", "Geçmiş", "Grundlage", "Hannergrond", "Heave to", "Háttér", "Khung kịch bản", "Khung tình huống", "Koncept", "Kontekst", "Kontekstas", "Konteksts", "Kontext", "Konturo de la scenaro", "Kịch bản", "Latar Belakang", "Lýsing Atburðarásar", "Lýsing Dæma", "MISHUN", "MISHUN SRSLY", "Menggariskan Senario ", "Náčrt Scenára", "Náčrt Scenáru", "Náčrt Scénáře", "Osnova", "Osnova Scenára", "Osnova scénáře", "Plan du Scénario", "Plan du scénario", "Plang vum Szenario", "Pozadie", "Pozadina", "Pozadí", "Primer", "Raamstsenaarium", "Reckon it's like", "Rerefons", "Scenarie", "Scenarij", "Scenarijaus šablonas", "Scenarijus", "Scenario", "Scenario Amlinellol", "Scenario Outline", "Scenario Template", "Scenariomal", "Scenariomall", "Scenariu", "Scenariusz", "Scenaro", "Scenár", "Scenārijs", "Scenārijs pēc parauga", "Schema dello scenario", "Scénario", "Scénář", "Senario", "Senaryo", "Senaryo taslağı", "Shiver me timbers", "Situācija", "Skenario", "Skenario konsep", "Skica", "Structura scenariu", "Structură scenariu", "Struktura scenarija", "Stsenaarium", "Szablon scenariusza", "Szenario", "Szenariogrundriss", "Tapaus", "Tapausaihio", "Taust", "Tausta", "The thing of it is", "Tình huống", "Wharrimean is", "Yo-ho-ho", "Założenia", "Кереш", "Контекст", "Концепт", "Основа", "Передумова", "Позадина", "Предистория", "Предыстория", "Пример", "Рамка на сценарий", "Скица", "Структура сценария", "Структура сценарија", "Структура сценарію", "Сценарий", "Сценарий структураси", "Сценарийның төзелеше", "Сценарио", "Сценарій", "Тарих", "רקע", "תבנית תרחיש", "תרחיש", "الخلفية", "الگوی سناریو", "زمینه", "سناریو", "سيناريو", "سيناريو مخطط", "परिदृश्य", "परिदृश्य रूपरेखा", "पृष्ठभूमि", "కథనం", "నేపథ్యం", "సన్నివేశం", "シナリオ", "シナリオアウトライン", "シナリオテンプレ", "シナリオテンプレート", "テンプレ", "剧本", "剧本大纲", "劇本", "劇本大綱", "场景", "场景大纲", "場景", "場景大綱", "背景", "배경", "시나리오", "시나리오 개요"]
+        k[:examples] = Set.new ["Atburðarásir", "Beispiele", "Beispiller", "Cenarios", "Cenários", "Contoh", "Contoh ", "Dead men tell no tales", "Dæmi", "Dữ liệu", "EXAMPLZ", "Ejemplos", "Eksempler", "Ekzemploj", "Enghreifftiau", "Esempi", "Examples", "Exempel", "Exemple", "Exemples", "Exemplos", "Juhtumid", "Paraugs", "Pavyzdžiai", "Piemēri", "Primeri", "Primjeri", "Przykłady", "Príklady", "Példák", "Příklady", "Scenarijai", "Scenariji", "Scenarios", "Tapaukset", "Variantai", "Voorbeelden", "You'll wanna", "Örnekler", "Мисаллар", "Мисоллар", "Приклади", "Примери", "Примеры", "Сценарији", "Үрнәкләр", "דוגמאות", "امثلة", "نمونه ها", "उदाहरण", "ఉదాహరణలు", "サンプル", "例", "例子", "예"]
+        k[:step] = Set.new ["*", "A", "A taktiež", "A také", "A tiež", "A zároveň", "AN", "Aber", "Adott", "Ak", "Akkor", "Ale", "Aleshores", "Ali", "Allora", "Alors", "Als", "Ama", "Amennyiben", "Amikor", "An", "And", "And y'all", "Angenommen", "Anrhegedig a", "Apabila", "Atesa", "Atunci", "Atès", "Avast!", "Aye", "BUT", "Bagi", "Bet", "Biết", "Blimey!", "Buh", "But", "But at the end of the day I reckon", "But y'all", "Cal", "Cand", "Cho", "Cuando", "Când", "DEN", "Dada", "Dadas", "Dado", "Dados", "Dan", "Dann", "Dar", "Dat fiind", "Data", "Date", "Date fiind", "Dati", "Dati fiind", "Dato", "Daţi fiind", "Dați fiind", "De", "Den youse gotta", "Dengan", "Diyelim ki", "Do", "Donada", "Donat", "Donitaĵo", "Dun", "Duota", "E", "Eeldades", "Ef", "En", "Entao", "Entonces", "Então", "Et", "Etant donné", "Etant donnée", "Etant données", "Etant donnés", "Eğer ki", "Fakat", "Gangway!", "Gdy", "Gegeben sei", "Gegeven", "Gitt", "Given", "Given y'all", "Givet", "Givun", "Ha", "I", "I CAN HAZ", "Ir", "It's just unbelievable", "Ja", "Jeśli", "Jeżeli", "Kad", "Kada", "Kai", "Kaj", "Když", "Kemudian", "Ketika", "Keď", "Khi", "Kiedy", "Kui", "Kuid", "Kun", "Let go and haul", "Lorsqu'<", "Lorsque", "Ma", "Maar", "Mais", "Majd", "Mając", "Maka", "Mas", "Men", "Mutta", "Nhưng", "Niin", "När", "Når", "O zaman", "Och", "Og", "Oletetaan", "Ond", "Onda", "Oraz", "Pak", "Pero", "Però", "Pokiaľ", "Pokud", "Potom", "Pryd", "Quan", "Quand", "Quando", "Se", "Sed", "Si", "Siis", "Soit", "Stel", "Så", "Tad", "Tada", "Tak", "Tapi", "Tetapi", "Then", "Then y'all", "Thì", "Too right", "Un", "Und", "Ve", "Và", "WEN", "Wenn", "When", "When y'all", "Wtedy", "Wun", "Y", "Y'know", "Yeah nah", "Yna", "Youse know like when", "Youse know when youse got", "Za predpokladu", "Za předpokladu", "Zadan", "Zadani", "Zadano", "Zadate", "Zadato", "Zakładając", "Zatati", "a", "an", "awer", "dann", "mä", "ugeholl", "wann", "És", "Étant donné", "Étant donnée", "Étant données", "Étant donnés", "Þegar", "Þá", "Şi", "Și", "І", "А", "А також", "Агар", "Але", "Али", "Аммо", "Бирок", "Ва", "Вә", "Дадено", "Дано", "Допустим", "Если", "Задате", "Задати", "Задато", "И", "К тому же", "Кад", "Када", "Когато", "Когда", "Коли", "Лекин", "Ләкин", "Нехай", "Но", "Нәтиҗәдә", "Онда", "Припустимо", "Припустимо, що", "Пусть", "Та", "Также", "То", "Тогда", "Тоді", "Унда", "Якщо", "Һәм", "Әгәр", "Әйтик", "Әмма", "אבל", "אז", "אזי", "בהינתן", "וגם", "כאשר", "آنگاه", "اذاً", "اما", "با فرض", "بفرض", "ثم", "عندما", "لكن", "متى", "هنگامی", "و", "अगर", "और", "चूंकि", "जब", "तथा", "तब", "पर", "यदि", "అప్పుడు", "ఈ పరిస్థితిలో", "కాని", "చెప్పబడినది", "మరియు", "かつ<", "しかし<", "ただし<", "ならば<", "もし<", "並且<", "但し<", "但是<", "假如<", "假定<", "假設<", "假设<", "前提<", "同时<", "同時<", "并且<", "当<", "當<", "而且<", "那么<", "那麼<", "그러면<", "그리고<", "단<", "만약<", "만일<", "먼저<", "조건<", "하지만<"]
+      end
+    end
+  end
+end

data/lib/rouge/lexers/html.rb

@@ -3,7 +3,7 @@ module Rouge
     class HTML < RegexLexer
       desc "HTML, the markup language of the web"
       tag 'html'
-      filenames '*.htm', '*.html', '*.xhtml', '*.xslt'
+      filenames '*.htm', '*.html', '*.xhtml'
       mimetypes 'text/html', 'application/xhtml+xml'
 
       def self.analyze_text(text)

data/lib/rouge/lexers/llvm.rb

@@ -0,0 +1,81 @@
+module Rouge
+  module Lexers
+    class LLVM < RegexLexer
+      desc 'The LLVM Compiler Infrastructure (http://llvm.org/)'
+      tag 'llvm'
+
+      filenames '*.ll'
+      mimetypes 'text/x-llvm'
+
+      def self.analyze_text(text)
+        return 0.1 if text =~ /\A%\w+\s=\s/
+      end
+
+      string = /"[^"]*?"/
+      identifier = /([-a-zA-Z$._][-a-zA-Z$._0-9]*|#{string})/
+
+      state :basic do
+        rule /;.*?$/, 'Comment.Single'
+        rule /\s+/, 'Text'
+
+        rule /#{identifier}\s*:/, 'Literal.Name.Label'
+
+        rule /@(#{identifier}|\d+)/, 'Name.Variable.Global'
+        rule /(%|!)#{identifier}/, 'Name.Variable'
+        rule /(%|!)\d+/, 'Name.Variable.Anonymous'
+
+        rule /c?#{string}/, 'Literal.String'
+
+        rule /0[xX][a-fA-F0-9]+/, 'Literal.Number'
+        rule /-?\d+(?:[.]\d+)?(?:[eE][-+]?\d+(?:[.]\d+)?)?/, 'Literal.Number'
+
+        rule /[=<>{}\[\]()*.,!]|x/, 'Punctuation'
+      end
+
+      builtin_types = %w(
+        void float double half x86_fp80 x86mmx fp128 ppc_fp128 label metadata
+      )
+
+      state :types do
+        rule /i[1-9]\d*/, 'Keyword.Type'
+        rule /#{builtin_types.join('|')}/, 'Keyword.Type'
+      end
+
+      builtin_keywords = %w(
+        begin end true false declare define global constant personality private
+        landingpad linker_private internal available_externally linkonce_odr
+        linkonce weak weak_odr appending dllimport dllexport common default
+        hidden protected extern_weak external thread_local zeroinitializer
+        undef null to tail target triple datalayout volatile nuw nsw nnan ninf
+        nsz arcp fast exact inbounds align addrspace section alias module asm
+        sideeffect gc dbg ccc fastcc coldcc x86_stdcallcc x86_fastcallcc
+        arm_apcscc arm_aapcscc arm_aapcs_vfpcc ptx_device ptx_kernel cc
+        c signext zeroext inreg sret nounwind noreturn noalias nocapture byval
+        nest readnone readonly inlinehint noinline alwaysinline optsize ssp
+        sspreq noredzone noimplicitfloat naked type opaque eq ne slt sgt sle
+        sge ult ugt ule uge oeq one olt ogt ole oge ord uno unnamed_addr ueq
+        une uwtable x
+      )
+
+      builtin_instructions = %w(
+        add fadd sub fsub mul fmul udiv sdiv fdiv urem srem frem shl lshr ashr
+        and or xor icmp fcmp phi call catch trunc zext sext fptrunc fpext
+        uitofp sitofp fptoui fptosi inttoptr ptrtoint bitcast select va_arg ret
+        br switch invoke unwind unreachable malloc alloca free load store
+        getelementptr extractelement insertelement shufflevector getresult
+        extractvalue insertvalue cleanup resume
+      )
+
+      state :keywords do
+        rule /#{builtin_instructions.join('|')}/, 'Keyword'
+        rule /#{builtin_keywords.join('|')}/, 'Keyword'
+      end
+
+      state :root do
+        mixin :basic
+        mixin :keywords
+        mixin :types
+      end
+    end
+  end
+end

data/lib/rouge/lexers/make.rb

@@ -8,7 +8,7 @@ module Rouge
       mimetypes 'text/x-makefile'
 
       def self.analyze_text(text)
-        return 0.2 if text =~ /^\.PHONY:/
+        return 0.6 if text =~ /^\.PHONY:/
       end
 
       bsd_special = %w(

data/lib/rouge/lexers/nginx.rb

@@ -1,6 +1,7 @@
 module Rouge
   module Lexers
     class Nginx < RegexLexer
+      desc 'configuration files for the nginx web server (nginx.org)'
       tag 'nginx'
       mimetypes 'text/x-nginx-conf'
       filenames 'nginx.conf'

data/lib/rouge/lexers/perl.rb

@@ -11,7 +11,7 @@ module Rouge
 
       def self.analyze_text(text)
         return 1 if text.shebang? 'perl'
-        return 0.9 if text.include? 'my $'
+        return 0.4 if text.include? 'my $'
       end
 
       keywords = %w(

data/lib/rouge/lexers/prolog.rb

@@ -0,0 +1,61 @@
+module Rouge
+  module Lexers
+    class Prolog < RegexLexer
+      desc "The Prolog programming language (http://en.wikipedia.org/wiki/Prolog)"
+      tag 'prolog'
+      aliases 'prolog'
+      filenames '*.pro', '*.P', '*.prolog', '*.pl'
+      mimetypes 'text/x-prolog'
+
+      def self.analyze_text(text)
+        return 0.1 if text =~ /\A\w+(\(\w+\,\s*\w+\))*\./
+        return 0.1 if text.include? ':-'
+      end
+
+      state :basic do
+        rule /\s+/, 'Text'
+        rule /^#.*/, 'Comment.Single'
+        rule /\/\*/, 'Comment.Multiline', :nested_comment
+
+        rule /[\[\](){}|.,;!]/, 'Punctuation'
+        rule /:-|-->/, 'Punctuation'
+
+        rule /"[^"]*"/, 'Literal.String.Double'
+
+        rule /\d+\.\d+/, 'Literal.Number.Float'
+        rule /\d+/, 'Literal.Number'
+      end
+
+      state :atoms do
+        rule /[[:lower:]]([_[:lower:][:digit:]])*/, 'Literal.String.Symbol'
+        rule /'[^']*'/, 'Literal.String.Symbol'
+      end
+
+      state :operators do
+        rule /(<|>|=<|>=|==|=:=|=|\/|\/\/|\*|\+|-)(?=\s|[a-zA-Z0-9\[])/,
+          'Operator'
+        rule /is/, 'Operator'
+        rule /(mod|div|not)/, 'Operator'
+        rule /[#&*+-.\/:<=>?@^~]+/, 'Operator'
+      end
+
+      state :variables do
+        rule /[A-Z]+\w*/, 'Name.Variable'
+        rule /_[[:word:]]*/, 'Name.Variable'
+      end
+
+      state :root do
+        mixin :basic
+        mixin :atoms
+        mixin :variables
+        mixin :operators
+      end
+
+      state :nested_comment do
+        rule /\/\*/, 'Comment.Multiline', :push
+        rule /\s*\*[^*\/]+/, 'Comment.Multiline'
+        rule /\*\//, 'Comment.Multiline', :pop!
+      end
+    end
+  end
+end

data/lib/rouge/lexers/xml.rb

@@ -13,9 +13,11 @@ module Rouge
       )
 
       def self.analyze_text(text)
-        return 0.5 if text.doctype?
-        return 0.5 if text[0..1000] =~ %r(<.+?>.*?</.+?>)m
+        return 0.9 if text.doctype?
         return 0.8 if text =~ /\A<\?xml\b/
+        start = text[0..1000]
+        return 0.6 if start =~ %r(<xml\b)
+        return 0.3 if start =~ %r(<.+?>.*?</.+?>)m
       end
 
       state :root do

data/lib/rouge/version.rb

@@ -1,5 +1,5 @@
 module Rouge
   def self.version
-    "0.2.15"
+    "0.3.0"
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: rouge
 version: !ruby/object:Gem::Version
-  version: 0.2.15
+  version: 0.3.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-03-03 00:00:00.000000000 Z
+date: 2013-03-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   type: :runtime
@@ -61,6 +61,7 @@ files:
 - lib/rouge/lexers/csharp.rb
 - lib/rouge/lexers/php/builtins.rb
 - lib/rouge/lexers/nginx.rb
+- lib/rouge/lexers/llvm.rb
 - lib/rouge/lexers/perl.rb
 - lib/rouge/lexers/groovy.rb
 - lib/rouge/lexers/sed.rb
@@ -78,6 +79,7 @@ files:
 - lib/rouge/lexers/php.rb
 - lib/rouge/lexers/tcl.rb
 - lib/rouge/lexers/tex.rb
+- lib/rouge/lexers/gherkin.rb
 - lib/rouge/lexers/rust.rb
 - lib/rouge/lexers/ini.rb
 - lib/rouge/lexers/scss.rb
@@ -94,6 +96,7 @@ files:
 - lib/rouge/lexers/erb.rb
 - lib/rouge/lexers/literate_haskell.rb
 - lib/rouge/lexers/c.rb
+- lib/rouge/lexers/gherkin/keywords.rb
 - lib/rouge/lexers/io.rb
 - lib/rouge/lexers/lua/builtins.rb
 - lib/rouge/lexers/python.rb
@@ -101,6 +104,7 @@ files:
 - lib/rouge/lexers/sql.rb
 - lib/rouge/lexers/haskell.rb
 - lib/rouge/lexers/markdown.rb
+- lib/rouge/lexers/prolog.rb
 - lib/rouge/lexers/conf.rb
 - lib/rouge.rb
 - bin/rougify
@@ -117,6 +121,7 @@ files:
 - lib/rouge/demos/shell
 - lib/rouge/demos/perl
 - lib/rouge/demos/text
+- lib/rouge/demos/prolog
 - lib/rouge/demos/viml
 - lib/rouge/demos/haskell
 - lib/rouge/demos/css
@@ -126,6 +131,7 @@ files:
 - lib/rouge/demos/io
 - lib/rouge/demos/c
 - lib/rouge/demos/scss
+- lib/rouge/demos/llvm
 - lib/rouge/demos/literate_coffeescript
 - lib/rouge/demos/python
 - lib/rouge/demos/make
@@ -138,6 +144,7 @@ files:
 - lib/rouge/demos/groovy
 - lib/rouge/demos/nginx
 - lib/rouge/demos/toml
+- lib/rouge/demos/gherkin
 - lib/rouge/demos/rust
 - lib/rouge/demos/json
 - lib/rouge/demos/markdown