regex.rb in twitter-text-1.1.4

- old
+ new

@@ -1,5 +1,6 @@
+# coding: UTF-8
 
 module Twitter
   # A collection of regular expressions for parsing Tweet text. The regular expression
   # list is frozen at load time to ensure immutability. These reular expressions are
   # used throughout the <tt>Twitter</tt> classes. Special care has been taken to make
@@ -28,38 +29,47 @@
 
     REGEXEN[:at_signs] = /[@＠]/
     REGEXEN[:extract_mentions] = /(^|[^a-zA-Z0-9_])#{REGEXEN[:at_signs]}([a-zA-Z0-9_]{1,20})(?=(.|$))/o
     REGEXEN[:extract_reply] = /^(?:#{REGEXEN[:spaces]})*#{REGEXEN[:at_signs]}([a-zA-Z0-9_]{1,20})/o
 
-    REGEXEN[:list_name] = /^[a-zA-Z\x80-\xff].{0,79}$/
+    REGEXEN[:list_name] = /^[a-zA-Z\u0080-\u00ff].{0,79}$/
 
     # Latin accented characters (subtracted 0xD7 from the range, it's a confusable multiplication sign. Looks like "x")
     LATIN_ACCENTS = [(0xc0..0xd6).to_a, (0xd8..0xf6).to_a, (0xf8..0xff).to_a].flatten.pack('U*').freeze
     REGEXEN[:latin_accents] = /[#{LATIN_ACCENTS}]+/o
 
     # Characters considered valid in a hashtag but not at the beginning, where only a-z and 0-9 are valid.
     HASHTAG_CHARACTERS = /[a-z0-9_#{LATIN_ACCENTS}]/io
     REGEXEN[:auto_link_hashtags] = /(^|[^0-9A-Z&\/]+)(#|＃)([0-9A-Z_]*[A-Z_]+#{HASHTAG_CHARACTERS}*)/io
-    REGEXEN[:auto_link_usernames_or_lists] = /([^a-zA-Z0-9_]|^)([@＠]+)([a-zA-Z0-9_]{1,20})(\/[a-zA-Z][a-zA-Z0-9\x80-\xff\-]{0,79})?/
+    REGEXEN[:auto_link_usernames_or_lists] = /([^a-zA-Z0-9_]|^)([@＠]+)([a-zA-Z0-9_]{1,20})(\/[a-zA-Z][a-zA-Z0-9\u0080-\u00ff\-]{0,79})?/
     REGEXEN[:auto_link_emoticon] = /(8\-\#|8\-E|\+\-\(|\`\@|\`O|\&lt;\|:~\(|\}:o\{|:\-\[|\&gt;o\&lt;|X\-\/|\[:-\]\-I\-|\/\/\/\/Ö\\\\\\\\|\(\|:\|\/\)|∑:\*\)|\( \| \))/
 
     # URL related hash regex collection
     REGEXEN[:valid_preceding_chars] = /(?:[^\/"':!=]|^|\:)/
     REGEXEN[:valid_domain] = /(?:[^[:punct:]\s][\.-](?=[^[:punct:]\s])|[^[:punct:]\s]){1,}\.[a-z]{2,}(?::[0-9]+)?/i
-    REGEXEN[:valid_url_path_chars] = /[\.\,]?[a-z0-9!\*'\(\);:=\+\$\/%#\[\]\-_,~@]/i
+
+    # Allow URL paths to contain balanced parens
+    #  1. Used in Wikipedia URLs like /Primer_(film)
+    #  2. Used in IIS sessions like /S(dfd346)/
+    REGEXEN[:wikipedia_disambiguation] = /(?:\([^\)]+\))/i
+    REGEXEN[:valid_url_path_chars] = /(?:
+      #{REGEXEN[:wikipedia_disambiguation]}|
+      [\.\,]?[a-z0-9!\*';:=\+\$\/%#\[\]\-_,~@]
+    )/ix
     # Valid end-of-path chracters (so /foo. does not gobble the period).
-    #   1. Allow ) for Wikipedia URLs.
-    #   2. Allow =&# for empty URL parameters and other URL-join artifacts
-    REGEXEN[:valid_url_path_ending_chars] = /[a-z0-9\)=#\/]/i
+    #   1. Allow =&# for empty URL parameters and other URL-join artifacts
+    REGEXEN[:valid_url_path_ending_chars] = /[a-z0-9=#\/]/i
     REGEXEN[:valid_url_query_chars] = /[a-z0-9!\*'\(\);:&=\+\$\/%#\[\]\-_\.,~]/i
     REGEXEN[:valid_url_query_ending_chars] = /[a-z0-9_&=#]/i
     REGEXEN[:valid_url] = %r{
       (                                                                                     #   $1 total match
         (#{REGEXEN[:valid_preceding_chars]})                                                #   $2 Preceeding chracter
         (                                                                                   #   $3 URL
           (https?:\/\/|www\.)                                                               #   $4 Protocol or beginning
           (#{REGEXEN[:valid_domain]})                                                       #   $5 Domain(s) and optional post number
-          (/#{REGEXEN[:valid_url_path_chars]}*#{REGEXEN[:valid_url_path_ending_chars]}?)?   #   $6 URL Path
+          (/#{REGEXEN[:valid_url_path_chars]}*
+            #{REGEXEN[:valid_url_path_ending_chars]}?
+          )?                                                                                #   $6 URL Path
           (\?#{REGEXEN[:valid_url_query_chars]}*#{REGEXEN[:valid_url_query_ending_chars]})? #   $7 Query String
         )
       )
     }iox;
 