From 282605a8fc061a1cc018384f83df623bf37f26d3 Mon Sep 17 00:00:00 2001
From: Martin Trigaux <mat@odoo.com>
Date: Wed, 21 Mar 2018 16:42:42 +0100
Subject: [PATCH 1/3] [FIX] website_blog: cut teaser after 150 chars

Space as word separator does not work in some non-latin languages like Japanese.
Cut arbitrarily after 150 chars

Closes #23219
---
 addons/website_blog/models/website_blog.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/addons/website_blog/models/website_blog.py b/addons/website_blog/models/website_blog.py
index 94c423b3153..3b41ae9a41d 100644
--- a/addons/website_blog/models/website_blog.py
+++ b/addons/website_blog/models/website_blog.py
@@ -165,7 +165,7 @@ class BlogPost(models.Model):
                 blog_post.teaser = blog_post.teaser_manual
             else:
                 content = html2plaintext(blog_post.content).replace('\n', ' ')
-                blog_post.teaser = ' '.join(filter(None, content.split(' '))[:50]) + '...'
+                blog_post.teaser = content[:150] + '...'
 
     @api.multi
     def _set_teaser(self):

From d39856dbe88b4492a6bf2d9b30923e58a945d692 Mon Sep 17 00:00:00 2001
From: Romain Derie <rde@odoo.com>
Date: Wed, 4 Apr 2018 18:19:29 +0200
Subject: [PATCH 2/3] [FIX] website_blog: prevent crawler on multiple blog tags
 page

Before this commit:
If a blog had multiple tags on the page, the crawler would click on every one
of them one after another until every tags combination got crawled.
With a lot of tags, this could result in million of URLs.

Now, we prevent URLs with more than one tag to be crawled.

Eg: With tags 'A', 'B', C':
/A
/A/B
/A/C
/A/B/C
/A/C/B

/B
/B/A
/B/C
/B/A/C
/B/C/A

/C
/C/A
/C/B
/C/A/B
/C/B/A
---
 addons/website_blog/views/website_blog_templates.xml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/addons/website_blog/views/website_blog_templates.xml b/addons/website_blog/views/website_blog_templates.xml
index 779ef067f95..513170dcf93 100644
--- a/addons/website_blog/views/website_blog_templates.xml
+++ b/addons/website_blog/views/website_blog_templates.xml
@@ -103,6 +103,7 @@
     <t t-call="website_blog.index">
         <t t-set="head">
             <link t-att-href="'/blog/%s/feed' % (blog.id)" type="application/atom+xml" rel="alternate" title="Atom Feed"/>
+            <meta t-if="len(active_tag_ids) > 1" name="robots" content="noindex, nofollow"/>
         </t>
         <div class="container">
             <t t-call="website.pager" >

From 27162b0e73a1887fc7178d6b79553c2301e1bac4 Mon Sep 17 00:00:00 2001
From: Romain Derie <rde@odoo.com>
Date: Thu, 5 Apr 2018 17:25:34 +0200
Subject: [PATCH 3/3] [FIX] website_blog: optimize crawler prevention

Commit d39856db prevents crawler to crawl and index blog tag URL which could
lead to possibly millions of URLs combinaison.

Still, it would crawl (but not index) second level of tags combinaison.

This commit ensure that crawling is prevented when already one tag on the URL.
---
 addons/website_blog/views/website_blog_templates.xml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/addons/website_blog/views/website_blog_templates.xml b/addons/website_blog/views/website_blog_templates.xml
index 513170dcf93..09123763676 100644
--- a/addons/website_blog/views/website_blog_templates.xml
+++ b/addons/website_blog/views/website_blog_templates.xml
@@ -103,7 +103,7 @@
     <t t-call="website_blog.index">
         <t t-set="head">
             <link t-att-href="'/blog/%s/feed' % (blog.id)" type="application/atom+xml" rel="alternate" title="Atom Feed"/>
-            <meta t-if="len(active_tag_ids) > 1" name="robots" content="noindex, nofollow"/>
+            <meta t-if="len(active_tag_ids) > 0" name="robots" t-attf-content="#{len(active_tag_ids) > 1 and 'noindex,'} nofollow"/>
         </t>
         <div class="container">
             <t t-call="website.pager" >