From d845911e2e16734f1dffb9f5747bd87233824204 Mon Sep 17 00:00:00 2001 From: Giuseppe Bilotta Date: Tue, 6 Feb 2007 15:11:49 +0000 Subject: Optimizations to ircify_first_html_par --- lib/rbot/core/utils/utils.rb | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/lib/rbot/core/utils/utils.rb b/lib/rbot/core/utils/utils.rb index 52375334..11312e19 100644 --- a/lib/rbot/core/utils/utils.rb +++ b/lib/rbot/core/utils/utils.rb @@ -416,16 +416,18 @@ module ::Irc end end - # Try to grab and IRFify the first HTML par (

tag) in the given string. + H1_REGEX = /]*)?>(.*?)<\/h1>/im + PAR_REGEX = /]*)?>.*?<\/p>/im + # Try to grab and IRCify the first HTML par (

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>/im) + header_found = xml.match(H1_REGEX) txt = String.new if header_found debug "Found header: #{header_found[1].inspect}" while txt.empty? header_found = $' - candidate = header_found[/]*)?>.*?<\/p>/im] + candidate = header_found[PAR_REGEX] break unless candidate txt = candidate.ircify_html end @@ -435,7 +437,7 @@ module ::Irc if txt.empty? header_found = xml while txt.empty? - candidate = header_found[/]*)?>.*?<\/p>/im] + candidate = header_found[PAR_REGEX] break unless candidate txt = candidate.ircify_html header_found = $' -- cgit v1.2.3