From 7f98f5516eeee56a374eeb371603ce21fea6c75b Mon Sep 17 00:00:00 2001
From: Rushabh Mehta <rmehta@gmail.com>
Date: Thu, 21 Jul 2011 10:02:59 +0530
Subject: [PATCH] fixes for sitemp.xml

---
 cgi-bin/webnotes/utils/sitemap.py     | 15 ++++++----
 cgi-bin/webnotes/widgets/page_body.py | 41 +++++----------------------
 2 files changed, 17 insertions(+), 39 deletions(-)

diff --git a/cgi-bin/webnotes/utils/sitemap.py b/cgi-bin/webnotes/utils/sitemap.py
index fd489f6d64..916aaa1eb1 100644
--- a/cgi-bin/webnotes/utils/sitemap.py
+++ b/cgi-bin/webnotes/utils/sitemap.py
@@ -16,19 +16,24 @@ def generate_xml(conn, site_prefix):
 	max_items = 1000
 	
 	site_map = ''
+	page_list = []
 	
 	if site_prefix:
-		# list of all Guest pages (static content)
-		for r in conn.sql("SELECT name, modified FROM tabPage WHERE ifnull(publish,0)=1 ORDER BY modified DESC"):
-			page_url = site_prefix + '#!' + urllib.quote(r[0])
-			site_map += link_xml % (page_url, r[1].strftime('%Y-%m-%d'))
-		
 		# list of all Records that are viewable by guests (Blogs, Articles etc)
 		try:
 			from startup.event_handlers import get_sitemap_items
 			for i in get_sitemap_items(site_prefix):
 				site_map += link_xml % (i[0], i[1])
+				('/' in i[0]) and page_list.append(i[0].split('/')[1]) or i[0]
 		except ImportError, e:
 			pass
 
+		# list of all Guest pages (static content)
+		for r in conn.sql("SELECT name, modified FROM tabPage WHERE ifnull(publish,0)=1 ORDER BY modified DESC"):
+			#check for double
+			if r[0] not in page_list:
+				page_url = site_prefix + '#!' + urllib.quote(r[0])
+				site_map += link_xml % (page_url, r[1].strftime('%Y-%m-%d'))
+		
+
 	return frame_xml % site_map
diff --git a/cgi-bin/webnotes/widgets/page_body.py b/cgi-bin/webnotes/widgets/page_body.py
index f221511209..8e19ad0716 100644
--- a/cgi-bin/webnotes/widgets/page_body.py
+++ b/cgi-bin/webnotes/widgets/page_body.py
@@ -90,12 +90,10 @@ def scrub_ids(content):
 	
 	return content
 
-#
-# load the page content and meta tags
-#
 def get_page_content(page):
 	"""
-	   Gets the HTML content from `static_content` or `content` property of a `Page`
+		Gets the HTML content from `static_content` or `content` property of a `Page`
+		and loads it in global `page_properties`
 	"""
 	from webnotes.model.code import get_code
 	from webnotes.model.doc import Document
@@ -125,9 +123,6 @@ def get_page_content(page):
 	except:
 		pass
 
-#
-# load metatags
-#
 def load_page_metatags(doc):
 	global page_properties
 
@@ -143,25 +138,6 @@ def load_page_metatags(doc):
 	page_properties['add_in_head'] = getattr(startup, 'add_in_head', '')
 	page_properties['add_in_body'] = getattr(startup, 'add_in_body', '')
 
-#
-# load the form as page (deprecated)
-#
-def get_doc_content(dt, dn):
-	"""
-	   Gets the HTML content of a document record by using the overridden or standard :method: `doclist.to_html`
-	"""
-	import webnotes.model.code
-	
-	if dt in webnotes.user.get_read_list():
-		# generate HTML
-		do = webnotes.model.code.get_obj(dt, dn, with_children = 1)
-		if hasattr(do, 'to_html'):
-			return dn, do.to_html()
-		else:
-			import webnotes.model.doclist
-			return dn, webnotes.model.doclist.to_html(do.doclist)
-	else:
-		return 'Forbidden - 404', '<h1>Forbidden - 404</h1>'
 
 # find the page to load as static
 # -------------------------------
@@ -171,17 +147,14 @@ def load_properties():
 	import urllib
 
 	page_url = webnotes.form_dict.get('_escaped_fragment_', webnotes.form_dict.get('page', ''))
+
+	if pag_url and page_url.lower().startswith('page/'): 
+		page_url = page_url[5:]
 	
 	if page_url:
-		if page_url.startswith('Page/'): 
-			page_url = page_url[5:]
-		page_url = ['Page', urllib.unquote(page_url)]
+		get_page_content(urllib.unquote(page_url))
 	else:
-		page_url = ['Page', webnotes.user.get_home_page()]
-		
-	# load content
-	# -----------------	
-	get_page_content(page_url[1])
+		get_page_content(webnotes.user.get_home_page())
 
 # generate the page
 # -----------------