From e48e20ad6b79ab08a6b0bcb1c2c176f67f9986ac Mon Sep 17 00:00:00 2001
From: j <0x006A@0x2620.org>
Date: Wed, 29 Dec 2010 16:19:34 +0530
Subject: [PATCH] add new file

---
 pandora/annotaion/utils.py | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)
 create mode 100644 pandora/annotaion/utils.py

diff --git a/pandora/annotaion/utils.py b/pandora/annotaion/utils.py
new file mode 100644
index 0000000..133d874
--- /dev/null
+++ b/pandora/annotaion/utils.py
@@ -0,0 +1,36 @@
+# -*- coding: utf-8 -*-
+# ci:si:et:sw=4:sts=4:ts=4
+
+def html_parser(text, nofollow=True):
+    text = text.replace('<i>', '__i__').replace('</i>', '__/i__')
+    text = text.replace('<b>', '__b__').replace('</b>', '__/b__')
+    #truns links into wiki links, make sure to only take http links
+    text = re.sub('<a .*?href="(http.*?)".*?>(.*?)</a>', '[\\1 \\2]', text)
+    text = escape(text)
+    text = text.replace('__i__', '<i>').replace('__/i__', '</i>')
+    text = text.replace('__b__', '<b>').replace('__/b__', '</b>')
+    if nofollow:
+        nofollow_rel = ' rel="nofollow"'
+    else:
+        nofollow_rel = ''
+    
+    links = re.compile('(\[(http.*?) (.*?)\])').findall(text)
+    for t, link, txt in links:
+        link = link.replace('http', '__LINK__').replace('.', '__DOT__')
+        ll = '<a href="%s"%s>%s</a>' % (link, nofollow_rel, txt)
+        text = text.replace(t, ll)
+    links = re.compile('(\[(http.*?)\])').findall(text)
+    for t, link in links:
+        link = link.replace('http', '__LINK__').replace('.', '__DOT__')
+        ll = '<a href="%s"%s>%s</a>' % (link, nofollow_rel, link)
+        text = text.replace(t, ll)
+    
+    text = urlize(text, nofollow=nofollow)
+
+    #inpage links
+    text = re.sub('\[(/.+?) (.+?)\]', '<a href="\\1">\\2</a>', text)
+
+    text = text.replace('__LINK__', 'http').replace('__DOT__', '.')
+    text = text.replace("\n", '<br />')
+    return text
+