From 059f917a709673d1d88f7056b45e86916de29ad4 Mon Sep 17 00:00:00 2001
From: Giuseppe Bilotta <giuseppe.bilotta@gmail.com>
Date: Tue, 6 Feb 2007 15:08:25 +0000
Subject: Move code to find and ircify first par from search plugin to utils

---
 lib/rbot/core/utils/utils.rb | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

(limited to 'lib')

diff --git a/lib/rbot/core/utils/utils.rb b/lib/rbot/core/utils/utils.rb
index fc89e1c3..52375334 100644
--- a/lib/rbot/core/utils/utils.rb
+++ b/lib/rbot/core/utils/utils.rb
@@ -415,5 +415,33 @@ module ::Irc
         }
       end
     end
+
+    # Try to grab and IRFify the first HTML par (<p> tag) in the given string.
+    # If possible, grab the one after the first h1 heading
+    def Utils.ircify_first_html_par(xml)
+      header_found = xml.match(/<h1(?:\s+[^>]*)?>(.*?)<\/h1>/im)
+      txt = String.new
+      if header_found
+        debug "Found header: #{header_found[1].inspect}"
+        while txt.empty? 
+          header_found = $'
+          candidate = header_found[/<p(?:\s+[^>]*)?>.*?<\/p>/im]
+          break unless candidate
+          txt = candidate.ircify_html
+        end
+      end
+      # If we haven't found a first par yet, try to get it from the whole
+      # document
+      if txt.empty?
+	header_found = xml
+        while txt.empty? 
+          candidate = header_found[/<p(?:\s+[^>]*)?>.*?<\/p>/im]
+          break unless candidate
+          txt = candidate.ircify_html
+          header_found = $'
+        end
+      end
+      return txt
+    end
   end
 end
-- 
cgit v1.2.3