[FIX] website_multi: create sitemap by website

Before this commit, the first website which ask to generate
the sitemap (with 12h cache) will force his own domain, and page
was not filtered.

Now, genereate 1 sitemap by website, and the enumeration of page
take the website_id in consideration and use key instead of xml_id.

Author: JKE-be

website_multi/controllers/main.py

@@ -1,10 +1,12 @@
 import re
 
 import werkzeug
-
+import openerp
+import datetime
+from itertools import islice
 from openerp.addons.web import http
 from openerp.http import request
-from openerp.addons.website.controllers.main import Website
+from openerp.addons.website.controllers.main import Website, SITEMAP_CACHE_TIME, LOC_PER_SITEMAP
 
 
 class website_multi(Website):
@@ -42,3 +44,71 @@ def pagenew(self, path, noredirect=False, add_menu=None):
             return werkzeug.wrappers.Response(url, mimetype='text/plain')
 
         return werkzeug.utils.redirect(url)
+
+    @http.route()
+    def sitemap_xml_index(self):
+        cr, uid, context = request.cr, openerp.SUPERUSER_ID, request.context
+        current_website = request.website
+        ira = request.registry['ir.attachment']
+        iuv = request.registry['ir.ui.view']
+        mimetype ='application/xml;charset=utf-8'
+        content = None
+
+        def create_sitemap(url, content):
+            ira.create(cr, uid, dict(
+                datas=content.encode('base64'),
+                mimetype=mimetype,
+                type='binary',
+                name=url,
+                url=url,
+            ), context=context)
+
+        dom = [('url', '=' , '/sitemap-%d.xml' % current_website.id), ('type', '=', 'binary')]
+        sitemap = ira.search_read(cr, uid, dom, ('datas', 'create_date'), limit=1, context=context)
+
+        if sitemap:
+            # Check if stored version is still valid
+            server_format = openerp.tools.misc.DEFAULT_SERVER_DATETIME_FORMAT
+            create_date = datetime.datetime.strptime(sitemap[0]['create_date'], server_format)
+            delta = datetime.datetime.now() - create_date
+            if delta < SITEMAP_CACHE_TIME:
+                content = sitemap[0]['datas'].decode('base64')
+
+        if not content:
+            # Remove all sitemaps in ir.attachments as we're going to regenerated them
+            dom = [('type', '=', 'binary'), '|', ('url', '=like' , '/sitemap-%d-%%.xml' % current_website.id),
+                   ('url', '=' , '/sitemap-%d.xml' % current_website.id)]
+            sitemap_ids = ira.search(cr, uid, dom, context=context)
+            if sitemap_ids:
+                ira.unlink(cr, uid, sitemap_ids, context=context)
+
+            pages = 0
+            first_page = None
+            locs = current_website.sudo(user=current_website.user_id.id).enumerate_pages()
+            while True:
+                values = {
+                    'locs': islice(locs, 0, LOC_PER_SITEMAP),
+                    'url_root': request.httprequest.url_root[:-1],
+                }
+                urls = iuv.render(cr, uid, 'website.sitemap_locs', values, context=context)
+                if urls.strip():
+                    page = iuv.render(cr, uid, 'website.sitemap_xml', dict(content=urls), context=context)
+                    if not first_page:
+                        first_page = page
+                    pages += 1
+                    create_sitemap('/sitemap-%d-%d.xml' % (current_website.id, pages), page)
+                else:
+                    break
+            if not pages:
+                return request.not_found()
+            elif pages == 1:
+                content = first_page
+            else:
+                # Sitemaps must be split in several smaller files with a sitemap index
+                content = iuv.render(cr, uid, 'website.sitemap_index_xml', dict(
+                    pages=range(1, pages + 1),
+                    url_root=request.httprequest.url_root,
+                ), context=context)
+            create_sitemap('/sitemap-%d.xml' % current_website.id, content)
+
+        return request.make_response(content, [('Content-Type', mimetype)])

website_multi/models/website.py

@@ -4,7 +4,7 @@
 from openerp.addons.website.models.website import slugify
 from openerp.addons.web.http import request
 from werkzeug.exceptions import NotFound
-
+import werkzeug
 
 class website(orm.Model):
 
@@ -114,3 +114,29 @@ def _auth_method_public(self):
                 dummy, request.uid = self.pool['ir.model.data'].get_object_reference(request.cr, openerp.SUPERUSER_ID, 'base', 'public_user')
         else:
             request.uid = request.session.uid
+
+    def _get_converters(self):
+        converters = super(ir_http, self)._get_converters()
+        converters['page'] = PageMultiWebsiteConverter
+        return converters
+
+
+class PageMultiWebsiteConverter(werkzeug.routing.PathConverter):
+    def generate(self, cr, uid, query=None, args={}, context=None):
+        View = request.registry['ir.ui.view']
+        dom = [('page', '=', True), '|', ('website_id', '=', request.website.id), ('website_id', '=', False)]
+        views = View.search_read(cr, uid, dom, fields=['key', 'xml_id', 'priority','write_date'], order='name', context=context)
+
+        for view in views:
+            key = view['key'] or view['xml_id'] or ''
+            xid = key.startswith('website.') and key[8:] or key
+
+            if xid=='homepage': continue
+            if query and query.lower() not in xid.lower(): continue
+            record = {'loc': xid}
+            if view['priority'] != 16:
+                record['__priority'] = min(round(view['priority'] / 32.0, 1), 1)
+            if view['write_date']:
+                record['__lastmod'] = view['write_date'][:10]
+            yield record
+