github-linguist 2.2.1 → 2.3.0

data/lib/linguist/tokenizer.rb

@@ -16,12 +16,15 @@ module Linguist
       new.extract_tokens(data)
     end
 
+    # Start state on token, ignore anything till the next newline
     SINGLE_LINE_COMMENTS = [
       '//', # C
       '#',  # Ruby
       '%',  # Tex
     ]
 
+    # Start state on opening token, ignore anything until the closing
+    # token is reached.
     MULTI_LINE_COMMENTS = [
       ['/*', '*/'],    # C
       ['<!--', '-->'], # XML
@@ -30,7 +33,7 @@ module Linguist
     ]
 
     START_SINGLE_LINE_COMMENT =  Regexp.compile(SINGLE_LINE_COMMENTS.map { |c|
-      "^\s*#{Regexp.escape(c)} "
+      "\s*#{Regexp.escape(c)} "
     }.join("|"))
 
     START_MULTI_LINE_COMMENT =  Regexp.compile(MULTI_LINE_COMMENTS.map { |c|
@@ -58,16 +61,16 @@ module Linguist
           end
 
         # Single line comment
-        elsif token = s.scan(START_SINGLE_LINE_COMMENT)
-          tokens << token.strip
+        elsif s.beginning_of_line? && token = s.scan(START_SINGLE_LINE_COMMENT)
+          # tokens << token.strip
           s.skip_until(/\n|\Z/)
 
         # Multiline comments
         elsif token = s.scan(START_MULTI_LINE_COMMENT)
-          tokens << token
+          # tokens << token
           close_token = MULTI_LINE_COMMENTS.assoc(token)[1]
           s.skip_until(Regexp.compile(Regexp.escape(close_token)))
-          tokens << close_token
+          # tokens << close_token
 
         # Skip single or double quoted strings
         elsif s.scan(/"/)

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: github-linguist
 version: !ruby/object:Gem::Version
-  version: 2.2.1
+  version: 2.3.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-08-07 00:00:00.000000000 Z
+date: 2012-08-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: charlock_holmes
@@ -50,7 +50,7 @@ dependencies:
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: '1.18'
+        version: '1.19'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -58,7 +58,7 @@ dependencies:
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: '1.18'
+        version: '1.19'
 - !ruby/object:Gem::Dependency
   name: pygments.rb
   requirement: !ruby/object:Gem::Requirement
@@ -137,8 +137,6 @@ files:
 - lib/linguist/language.rb
 - lib/linguist/languages.yml
 - lib/linguist/md5.rb
-- lib/linguist/mime.rb
-- lib/linguist/mimes.yml
 - lib/linguist/popular.yml
 - lib/linguist/repository.rb
 - lib/linguist/samples.json

data/lib/linguist/mime.rb

@@ -1,91 +0,0 @@
-require 'mime/types'
-require 'yaml'
-
-class MIME::Type
-  attr_accessor :override
-end
-
-# Register additional mime type extensions
-#
-# Follows same format as mime-types data file
-#   https://github.com/halostatue/mime-types/blob/master/lib/mime/types.rb.data
-File.read(File.expand_path("../mimes.yml", __FILE__)).lines.each do |line|
-  # Regexp was cargo culted from mime-types lib
-  next unless line =~ %r{^
-    #{MIME::Type::MEDIA_TYPE_RE}
-    (?:\s@([^\s]+))?
-    (?:\s:(#{MIME::Type::ENCODING_RE}))?
-  }x
-
-  mediatype  = $1
-  subtype    = $2
-  extensions = $3
-  encoding   = $4
-
-  # Lookup existing mime type
-  mime_type = MIME::Types["#{mediatype}/#{subtype}"].first ||
-    # Or create a new instance
-    MIME::Type.new("#{mediatype}/#{subtype}")
-
-  if extensions
-    extensions.split(/,/).each do |extension|
-      mime_type.extensions << extension
-    end
-  end
-
-  if encoding
-    mime_type.encoding = encoding
-  end
-
-  mime_type.override = true
-
-  # Kind of hacky, but we need to reindex the mime type after making changes
-  MIME::Types.add_type_variant(mime_type)
-  MIME::Types.index_extensions(mime_type)
-end
-
-module Linguist
-  module Mime
-    # Internal: Look up mime type for extension.
-    #
-    # ext - The extension String. May include leading "."
-    #
-    # Examples
-    #
-    #   Mime.mime_for('.html')
-    #   # => 'text/html'
-    #
-    #   Mime.mime_for('txt')
-    #   # => 'text/plain'
-    #
-    # Return mime type String otherwise falls back to 'text/plain'.
-    def self.mime_for(ext)
-      mime_type = lookup_mime_type_for(ext)
-      mime_type ? mime_type.to_s : 'text/plain'
-    end
-
-    # Internal: Lookup mime type for extension or mime type
-    #
-    # ext_or_mime_type - A file extension ".txt" or mime type "text/plain".
-    #
-    # Returns a MIME::Type
-    def self.lookup_mime_type_for(ext_or_mime_type)
-      ext_or_mime_type ||= ''
-
-      if ext_or_mime_type =~ /\w+\/\w+/
-        guesses = ::MIME::Types[ext_or_mime_type]
-      else
-        guesses = ::MIME::Types.type_for(ext_or_mime_type)
-      end
-
-      # Use custom override first
-      guesses.detect { |type| type.override } ||
-
-        # Prefer text mime types over binary
-        guesses.detect { |type| type.ascii? } ||
-
-        # Otherwise use the first guess
-        guesses.first
-    end
-  end
-end

data/lib/linguist/mimes.yml

@@ -1,62 +0,0 @@
-# Additional types to add to MIME::Types
-#
-# MIME types are used to set the Content-Type of raw binary blobs. All text
-# blobs are served as text/plain regardless of their type to ensure they
-# open in the browser rather than downloading.
-#
-# The encoding helps determine whether a file should be treated as plain
-# text or binary. By default, a mime type's encoding is base64 (binary).
-# These types will show a "View Raw" link. To force a type to render as
-# plain text, set it to 8bit for UTF-8. text/* types will be treated as
-# text by default.
-#
-#   <type> @<extensions> :<encoding>
-#
-# type       - mediatype/subtype
-# extensions - comma seperated extension list
-# encoding   - base64 (binary), 7bit (ASCII), 8bit (UTF-8), or
-#              quoted-printable (Printable ASCII).
-#
-# Follows same format as mime-types data file
-#   https://github.com/halostatue/mime-types/blob/master/lib/mime/types.rb.data
-#
-# Any additions or modifications (even trivial) should have corresponding
-# test change in `test/test_mime.rb`.
-
-# TODO: Lookup actual types
-application/octet-stream @a,blend,gem,graffle,ipa,lib,mcz,nib,o,ogv,otf,pfx,pigx,plgx,psd,sib,spl,sqlite3,swc,ucode,xpi
-
-# Please keep this list alphabetized
-application/java-archive @ear,war
-application/netcdf :8bit
-application/ogg @ogg
-application/postscript :base64
-application/vnd.adobe.air-application-installer-package+zip @air
-application/vnd.mozilla.xul+xml :8bit
-application/vnd.oasis.opendocument.presentation @odp
-application/vnd.oasis.opendocument.spreadsheet @ods
-application/vnd.oasis.opendocument.text @odt
-application/vnd.openofficeorg.extension @oxt
-application/vnd.openxmlformats-officedocument.presentationml.presentation @pptx
-application/x-chrome-extension @crx
-application/x-iwork-keynote-sffkey @key
-application/x-iwork-numbers-sffnumbers @numbers
-application/x-iwork-pages-sffpages @pages
-application/x-ms-xbap @xbap :8bit
-application/x-parrot-bytecode @pbc
-application/x-shockwave-flash @swf
-application/x-silverlight-app @xap
-application/x-supercollider @sc :8bit
-application/x-troff-ms :8bit
-application/x-wais-source :8bit
-application/xaml+xml @xaml :8bit
-application/xslt+xml @xslt :8bit
-image/x-icns @icns
-text/cache-manifest @manifest
-text/plain @cu,cxx
-text/x-logtalk @lgt
-text/x-nemerle @n
-text/x-nimrod @nim
-text/x-ocaml @ml,mli,mll,mly,sig,sml
-text/x-rust @rs,rc
-text/x-scheme @rkt,scm,sls,sps,ss