github-linguist 2.3.3 → 2.3.4

data/lib/linguist/blob_helper.rb

@@ -204,7 +204,31 @@ module Linguist
     #
     # Returns an Array of lines
     def lines
-      @lines ||= (viewable? && data) ? data.split("\n", -1) : []
+      @lines ||=
+        if viewable? && data
+          data.split(line_split_character, -1)
+        else
+          []
+        end
+    end
+
+    # Character used to split lines. This is almost always "\n" except when Mac
+    # Format is detected in which case it's "\r".
+    #
+    # Returns a split pattern string.
+    def line_split_character
+      @line_split_character ||= (mac_format?? "\r" : "\n")
+    end
+
+    # Public: Is the data in ** Mac Format **. This format uses \r (0x0d) characters
+    # for line ends and does not include a \n (0x0a).
+    #
+    # Returns true when mac format is detected.
+    def mac_format?
+      return if !viewable?
+      if pos = data[0, 4096].index("\r")
+        data[pos + 1] != ?\n
+      end
     end
 
     # Public: Get number of lines of code
@@ -278,7 +302,7 @@ module Linguist
       if defined?(@data) && @data.is_a?(String)
         data = @data
       else
-        data = lambda { binary_mime_type? ? "" : self.data }
+        data = lambda { (binary_mime_type? || binary?) ? "" : self.data }
       end
 
       @language = Language.detect(name.to_s, data, mode)

data/lib/linguist/language.rb

@@ -84,7 +84,9 @@ module Linguist
 
       if possible_languages.length > 1
         data = data.call() if data.respond_to?(:call)
-        if result = Classifier.classify(Samples::DATA, data, possible_languages.map(&:name)).first
+        if data.nil? || data == ""
+          nil
+        elsif result = Classifier.classify(Samples::DATA, data, possible_languages.map(&:name)).first
           Language[result[0]]
         end
       else

data/lib/linguist/languages.yml

@@ -367,6 +367,14 @@ Ecere Projects:
   extensions:
   - .epj
 
+Ecl:
+  type: programming
+  color: "#8a1267"
+  primary_extension: .ecl
+  lexer: ECL
+  extensions:
+  - .eclxml
+
 Eiffel:
   type: programming
   lexer: Text only

data/lib/linguist/samples.json

@@ -17,11 +17,11 @@
       ".h"
     ],
     "C++": [
-      ".h",
-      ".hpp",
-      ".cu",
+      ".cc",
       ".cpp",
-      ".cc"
+      ".cu",
+      ".h",
+      ".hpp"
     ],
     "Ceylon": [
       ".ceylon"
@@ -41,6 +41,9 @@
     "Diff": [
       ".patch"
     ],
+    "Ecl": [
+      ".ecl"
+    ],
     "Emacs Lisp": [
       ".el"
     ],
@@ -48,11 +51,11 @@
       ".s"
     ],
     "Gosu": [
+      ".gs",
       ".gsp",
       ".gst",
       ".gsx",
-      ".vark",
-      ".gs"
+      ".vark"
     ],
     "Groovy": [
       ".gradle",
@@ -75,9 +78,9 @@
       ".script!"
     ],
     "JSON": [
+      ".json",
       ".maxhelp",
-      ".maxpat",
-      ".json"
+      ".maxpat"
     ],
     "Julia": [
       ".jl"
@@ -130,14 +133,14 @@
       ".pir"
     ],
     "Perl": [
-      ".pm",
       ".pl",
-      ".t",
-      ".script!"
+      ".pm",
+      ".script!",
+      ".t"
     ],
     "PHP": [
-      ".php",
-      ".module"
+      ".module",
+      ".php"
     ],
     "PowerShell": [
       ".ps1",
@@ -154,17 +157,17 @@
       ".R"
     ],
     "Racket": [
-      ".script!",
-      ".scrbl"
+      ".scrbl",
+      ".script!"
     ],
     "Rebol": [
       ".r"
     ],
     "Ruby": [
-      ".rb",
-      ".script!",
       ".rabl",
-      ".rake"
+      ".rake",
+      ".rb",
+      ".script!"
     ],
     "Rust": [
       ".rs"
@@ -180,17 +183,17 @@
       ".sps"
     ],
     "Scilab": [
-      ".sci",
       ".sce",
+      ".sci",
       ".tst"
     ],
     "SCSS": [
       ".scss"
     ],
     "Shell": [
+      ".bash",
       ".script!",
       ".sh",
-      ".bash",
       ".zsh"
     ],
     "Standard ML": [
@@ -257,7 +260,7 @@
       ".gemrc"
     ]
   },
-  "tokens_total": 270906,
+  "tokens_total": 271187,
   "languages_total": 275,
   "tokens": {
     "Apex": {
@@ -9157,6 +9160,84 @@
       "d472341..8ad9ffb": 1,
       "+": 3
     },
+    "Ecl": {
+      "#option": 1,
+      "(": 32,
+      "true": 1,
+      ")": 32,
+      ";": 23,
+      "namesRecord": 4,
+      "RECORD": 1,
+      "string20": 1,
+      "surname": 1,
+      "string10": 2,
+      "forename": 1,
+      "integer2": 5,
+      "age": 2,
+      "dadAge": 1,
+      "mumAge": 1,
+      "END": 1,
+      "namesRecord2": 3,
+      "record": 1,
+      "extra": 1,
+      "end": 1,
+      "namesTable": 11,
+      "dataset": 2,
+      "FLAT": 2,
+      "namesTable2": 9,
+      "aveAgeL": 3,
+      "l": 1,
+      "l.dadAge": 1,
+      "+": 16,
+      "l.mumAge": 1,
+      "/2": 2,
+      "aveAgeR": 4,
+      "r": 1,
+      "r.dadAge": 1,
+      "r.mumAge": 1,
+      "output": 9,
+      "join": 11,
+      "left": 2,
+      "right": 3,
+      "//Several": 1,
+      "simple": 1,
+      "examples": 1,
+      "of": 1,
+      "sliding": 2,
+      "syntax": 1,
+      "left.age": 8,
+      "right.age": 12,
+      "-": 5,
+      "and": 10,
+      "<": 1,
+      "between": 7,
+      "//Same": 1,
+      "but": 1,
+      "on": 1,
+      "strings.": 1,
+      "Also": 1,
+      "includes": 1,
+      "to": 1,
+      "ensure": 1,
+      "sort": 1,
+      "is": 1,
+      "done": 1,
+      "by": 1,
+      "non": 1,
+      "before": 1,
+      "sliding.": 1,
+      "left.surname": 2,
+      "right.surname": 4,
+      "[": 4,
+      "]": 4,
+      "all": 1,
+      "//This": 1,
+      "should": 1,
+      "not": 1,
+      "generate": 1,
+      "a": 1,
+      "self": 1
+    },
     "Emacs Lisp": {
       "(": 1,
       "print": 1,
@@ -27671,6 +27752,7 @@
     "Dart": 68,
     "Delphi": 30,
     "Diff": 16,
+    "Ecl": 281,
     "Emacs Lisp": 3,
     "GAS": 133,
     "Gosu": 413,
@@ -27741,6 +27823,7 @@
     "Dart": 1,
     "Delphi": 1,
     "Diff": 1,
+    "Ecl": 1,
     "Emacs Lisp": 1,
     "GAS": 1,
     "Gosu": 5,
@@ -27761,7 +27844,7 @@
     "Nemerle": 1,
     "Nimrod": 1,
     "Nu": 1,
-    "Objective-C": 20,
+    "Objective-C": 19,
     "OCaml": 1,
     "Opa": 2,
     "OpenCL": 1,
@@ -27798,5 +27881,5 @@
     "XSLT": 1,
     "YAML": 1
   },
-  "md5": "73937d71c79ba8a2f9e085431017cb2d"
+  "md5": "8591cfa68ab6fe3b3dacbcb885be70d0"
 }

data/lib/linguist/samples.rb

@@ -76,12 +76,14 @@ module Linguist
           db['extnames'][language_name] ||= []
           if !db['extnames'][language_name].include?(sample[:extname])
             db['extnames'][language_name] << sample[:extname]
+            db['extnames'][language_name].sort!
           end
         end
 
         if sample[:filename]
           db['filenames'][language_name] ||= []
           db['filenames'][language_name] << sample[:filename]
+          db['filenames'][language_name].sort!
         end
 
         data = File.read(sample[:path])

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: github-linguist
 version: !ruby/object:Gem::Version
-  version: 2.3.3
+  version: 2.3.4
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-09-04 00:00:00.000000000 Z
+date: 2012-09-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: charlock_holmes
@@ -181,7 +181,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.24
+rubygems_version: 1.8.23
 signing_key: 
 specification_version: 3
 summary: GitHub Language detection