lib/regex.rb in twitter-text-1.4.13 vs lib/regex.rb in twitter-text-1.4.14

@@ -104,18 +104,18 @@
 
     HASHTAG = /(#{HASHTAG_BOUNDARY})(#|＃)(#{HASHTAG_ALPHANUMERIC}*#{HASHTAG_ALPHA}#{HASHTAG_ALPHANUMERIC}*)/io
 
     REGEXEN[:auto_link_hashtags] = /#{HASHTAG}/io
     # Used in Extractor and Rewriter for final filtering
-    REGEXEN[:end_hashtag_match] = /^(?:[#＃]|:\/\/)/o
+    REGEXEN[:end_hashtag_match] = /\A(?:[#＃]|:\/\/)/o
 
     REGEXEN[:at_signs] = /[@＠]/
     REGEXEN[:extract_mentions] = /(^|[^a-zA-Z0-9_])#{REGEXEN[:at_signs]}([a-zA-Z0-9_]{1,20})/o
     REGEXEN[:extract_mentions_or_lists] = /(^|[^a-zA-Z0-9_])#{REGEXEN[:at_signs]}([a-zA-Z0-9_]{1,20})(\/[a-zA-Z][a-zA-Z0-9_\-]{0,24})?/o
     REGEXEN[:extract_reply] = /^(?:#{REGEXEN[:spaces]})*#{REGEXEN[:at_signs]}([a-zA-Z0-9_]{1,20})/o
     # Used in Extractor and Rewriter for final filtering
-    REGEXEN[:end_screen_name_match] = /^(?:#{REGEXEN[:at_signs]}|#{REGEXEN[:latin_accents]}|:\/\/)/o
+    REGEXEN[:end_screen_name_match] = /\A(?:#{REGEXEN[:at_signs]}|#{REGEXEN[:latin_accents]}|:\/\/)/o
 
     REGEXEN[:auto_link_usernames_or_lists] = /([^a-zA-Z0-9_]|^|RT:?)([@＠]+)([a-zA-Z0-9_]{1,20})(\/[a-zA-Z][a-zA-Z0-9_\-]{0,24})?/o
     REGEXEN[:auto_link_emoticon] = /(8\-\#|8\-E|\+\-\(|\`\@|\`O|\<\|:~\(|\}:o\{|:\-\[|\>o\<|X\-\/|\[:-\]\-I\-|\/\/\/\/Ö\\\\\\\\|\(\|:\|\/\)|∑:\*\)|\( \| \))/
 
     # URL related hash regex collection
@@ -123,11 +123,11 @@
 
     DOMAIN_VALID_CHARS = "[^[:punct:][:space:][:blank:][:cntrl:]#{INVALID_CHARACTERS.join('')}#{UNICODE_SPACES.join('')}]"
     REGEXEN[:valid_subdomain] = /(?:(?:#{DOMAIN_VALID_CHARS}(?:[_-]|#{DOMAIN_VALID_CHARS})*)?#{DOMAIN_VALID_CHARS}\.)/io
     REGEXEN[:valid_domain_name] = /(?:(?:#{DOMAIN_VALID_CHARS}(?:[-]|#{DOMAIN_VALID_CHARS})*)?#{DOMAIN_VALID_CHARS}\.)/io
 
-    REGEXEN[:valid_gTLD] = /(?:(?:aero|asia|biz|cat|com|coop|edu|gov|info|int|jobs|mil|mobi|museum|name|net|org|pro|tel|travel)(?=[^a-z]|$))/i
+    REGEXEN[:valid_gTLD] = /(?:(?:aero|asia|biz|cat|com|coop|edu|gov|info|int|jobs|mil|mobi|museum|name|net|org|pro|tel|travel|xxx)(?=[^a-z]|$))/i
     REGEXEN[:valid_ccTLD] = %r{
       (?:
         (?:ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|
         ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|
         gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|
@@ -148,11 +148,14 @@
     REGEXEN[:valid_ascii_domain] = /
       (?:(?:[A-Za-z0-9\-_]|#{REGEXEN[:latin_accents]})+\.)+
       (?:#{REGEXEN[:valid_gTLD]}|#{REGEXEN[:valid_ccTLD]}|#{REGEXEN[:valid_punycode]})
     /iox
 
+    # This is used in Extractor for stricter t.co URL extraction
+    REGEXEN[:valid_tco_url] = /^https?:\/\/t\.co\/[a-z0-9]+/i
+
     # This is used in Extractor to filter out unwanted URLs.
-    REGEXEN[:invalid_short_domain] = /^#{REGEXEN[:valid_domain_name]}#{REGEXEN[:valid_ccTLD]}$/io
+    REGEXEN[:invalid_short_domain] = /\A#{REGEXEN[:valid_domain_name]}#{REGEXEN[:valid_ccTLD]}\Z/io
 
     REGEXEN[:valid_port_number] = /[0-9]+/
 
     REGEXEN[:valid_general_url_path_chars] = /[a-z0-9!\*';:=\+\,\.\$\/%#\[\]\-_~&|#{LATIN_ACCENTS}]/io
     # Allow URL paths to contain balanced parens