about summary refs log tree commit diff
path: root/config
diff options
context:
space:
mode:
authorThibG <thib@sitedethib.com>2020-01-11 02:15:25 +0100
committerEugen Rochko <eugen@zeonfederated.com>2020-01-11 02:15:25 +0100
commitea436b355bd844c86a4f4ddfd204b9bf15a1db6c (patch)
treec33fd5501bf295573665740481a6d749a57bab35 /config
parente9ea09d17398763ead69ca845c7aefebf266d373 (diff)
Add support for linking XMPP URIs in toots (#12709)
* Fix wrong grouping in Twitter valid_url regex

* Add support for xmpp URIs

Fixes #9776

The difficult part is autolinking, because Twitter-text's extractor does
some pretty ad-hoc stuff to find things that “look like” URLs, and XMPP
URIs do not really match the assumptions of that lib, so it doesn't sound
wise to try to shoehorn it into the existing regex.

This is why I used a specific regex (very close, although slightly more
permissive than the RFC), and a specific scan function (a simplified version
of the generalized one from Twitter).

* Remove leading “xmpp:” from auto-linked text
Diffstat (limited to 'config')
-rw-r--r--config/initializers/twitter_regex.rb51
1 files changed, 50 insertions, 1 deletions
diff --git a/config/initializers/twitter_regex.rb b/config/initializers/twitter_regex.rb
index 0ddbbee98..87815d458 100644
--- a/config/initializers/twitter_regex.rb
+++ b/config/initializers/twitter_regex.rb
@@ -29,7 +29,7 @@ module Twitter
       (                                                                                     #   $1 total match
         (#{REGEXEN[:valid_url_preceding_chars]})                                            #   $2 Preceding character
         (                                                                                   #   $3 URL
-          ((https?|dat|dweb|ipfs|ipns|ssb|gopher):\/\/)?                                    #   $4 Protocol (optional)
+          ((?:https?|dat|dweb|ipfs|ipns|ssb|gopher):\/\/)?                                  #   $4 Protocol (optional)
           (#{REGEXEN[:valid_domain]})                                                       #   $5 Domain(s)
           (?::(#{REGEXEN[:valid_port_number]}))?                                            #   $6 Port number (optional)
           (/#{REGEXEN[:valid_url_path]}*)?                                                  #   $7 URL Path and anchor
@@ -37,5 +37,54 @@ module Twitter
         )
       )
     }iox
+    REGEXEN[:validate_nodeid] = /(?:
+      #{REGEXEN[:validate_url_unreserved]}|
+      #{REGEXEN[:validate_url_pct_encoded]}|
+      [!$()*+,;=]
+    )/iox
+    REGEXEN[:validate_resid] = /(?:
+      #{REGEXEN[:validate_url_unreserved]}|
+      #{REGEXEN[:validate_url_pct_encoded]}|
+      #{REGEXEN[:validate_url_sub_delims]}
+    )/iox
+    REGEXEN[:valid_xmpp_uri] = %r{
+      (                                                                                     #   $1 total match
+        (#{REGEXEN[:valid_url_preceding_chars]})                                            #   $2 Preceding character
+        (                                                                                   #   $3 URL
+          ((?:xmpp):)                                                                       #   $4 Protocol
+          (//#{REGEXEN[:validate_nodeid]}+@#{REGEXEN[:valid_domain]}/)?                     #   $5 Authority (optional)
+          (#{REGEXEN[:validate_nodeid]}+@)?                                                 #   $6 Username in path (optional)
+          (#{REGEXEN[:valid_domain]})                                                       #   $7 Domain in path
+          (/#{REGEXEN[:validate_resid]}+)?                                                  #   $8 Resource in path (optional)
+          (\?#{REGEXEN[:valid_url_query_chars]}*#{REGEXEN[:valid_url_query_ending_chars]})? #   $9 Query String
+        )
+      )
+    }iox
+  end
+
+  module Extractor
+    # Extracts a list of all XMPP URIs included in the Tweet <tt>text</tt> along
+    # with the indices. If the <tt>text</tt> is <tt>nil</tt> or contains no
+    # XMPP URIs an empty array will be returned.
+    #
+    # If a block is given then it will be called for each XMPP URI.
+    def extract_xmpp_uris_with_indices(text, options = {}) # :yields: uri, start, end
+      return [] unless text && text.index(":")
+      urls = []
+
+      text.to_s.scan(Twitter::Regex[:valid_xmpp_uri]) do
+        valid_uri_match_data = $~
+
+        start_position = valid_uri_match_data.char_begin(3)
+        end_position = valid_uri_match_data.char_end(3)
+
+        urls << {
+          :url => valid_uri_match_data[3],
+          :indices => [start_position, end_position]
+        }
+      end
+      urls.each{|url| yield url[:url], url[:indices].first, url[:indices].last} if block_given?
+      urls
+    end
   end
 end