From 8d1e3d06abae19598ce1bd854789327f56ef2536 Mon Sep 17 00:00:00 2001
From: niv-openerp <nicolas.vanhoren@openerp.com>
Date: Wed, 5 Sep 2012 17:32:12 +0200
Subject: [PATCH] [IMP] removed dependency to pyquery

bzr revid: nicolas.vanhoren@openerp.com-20120905153212-0gi1wjhf9m4xtnml
---
 openerp/tests/test_html_sanitize.py |  8 ++++++--
 openerp/tools/html_sanitize.py      | 21 +++++++++++++--------
 setup.py                            |  1 -
 3 files changed, 19 insertions(+), 11 deletions(-)

diff --git a/openerp/tests/test_html_sanitize.py b/openerp/tests/test_html_sanitize.py
index 90ccc88cc1d..cb46b325144 100755
--- a/openerp/tests/test_html_sanitize.py
+++ b/openerp/tests/test_html_sanitize.py
@@ -26,11 +26,15 @@ class TestSanitizer(unittest.TestCase):
     def test_simple(self):
         x = "yop"
         self.assertEqual(x, html_sanitize(x))
+        
+    def test_trailing_text(self):
+        x = 'lala<p>yop</p>xxx'
+        self.assertEqual(x, html_sanitize(x))
     
-    def test_test_case(self):
+    def test_no_exception(self):
         html_sanitize(test_case)
         
-    def test_crm(self):
+    def test_unicode(self):
         html_sanitize("Merci à l'intérêt pour notre produit.nous vous contacterons bientôt. Merci")
 
 if __name__ == '__main__':
diff --git a/openerp/tools/html_sanitize.py b/openerp/tools/html_sanitize.py
index 5164ceb276e..65f17be074f 100644
--- a/openerp/tools/html_sanitize.py
+++ b/openerp/tools/html_sanitize.py
@@ -1,17 +1,22 @@
 
-from pyquery import PyQuery as pq
+import lxml.html
 import re
 
 def html_sanitize(x):
     if not x:
         return x
-    root = pq("<div />")
     if type(x) == str:
         x = unicode(x, "utf8", "replace")
-    root.html(x)
-    result = handle_element(root[0])
-    new = pq(result)
-    return new.html()
+    root = lxml.html.fromstring("<div>%s</div>" % x)
+    result = handle_element(root)
+    res = ""
+    for el in children(result[0]):
+        if type(el) == str or type(el) == unicode:
+            res += el
+        else:
+            el.tail = ""
+            res += lxml.html.tostring(el)
+    return res
 
 to_remove = set(["script", "head", "meta", "title", "link", "img"])
 to_unwrap = set(["html", "body"])
@@ -33,7 +38,7 @@ def handle_element(el):
         return []
     if el.tag in to_unwrap:
         return reduce(lambda x,y: x+y, [handle_element(x) for x in children(el)])
-    new = pq("<%s />" % el.tag)[0]
+    new = lxml.html.fromstring("<%s />" % el.tag)
     for i in children(el):
         append_to(handle_element(i), new)
     if el.tag in special:
@@ -59,4 +64,4 @@ def append_to(new_ones, el):
             else:
                 children[-1].tail = i
         else:
-            el.append(i)
\ No newline at end of file
+            el.append(i)
diff --git a/setup.py b/setup.py
index a033921e70d..a26b74e255d 100755
--- a/setup.py
+++ b/setup.py
@@ -99,7 +99,6 @@ setuptools.setup(
           'mako',
           'psycopg2',
           'pydot',
-          'pyquery',
           'python-dateutil < 2',
           'python-ldap',
           'python-openid',