[FIX] whitespace/indent lost by RTE

Didn't manage to find RTE settings to avoid losing leading whitespace of
lines, so reindeint arch after doing all integration, right before saving back
to view's field.

* html.fromstring(parser=HTMLParser(remove_blank_text=True) does not seem to
  work, so serialize to XML, and parse back with
  remove_blank_text. remove_blank_text necessary for lxml's pretty_print to
  work correctly.

* pretty_print only & always uses 2 spaces/indent level. Our files (and the
  HTML editor's Format button) uses 4 spaces -> need a second pass to double
  indents.

bzr revid: xmo@openerp.com-20140227125934-q8j3z440px2ic6kx

diff --git a/addons/website/models/ir_ui_view.py b/addons/website/models/ir_ui_view.py
index 27af033..857b99d 100644 (file)
--- a/addons/website/models/ir_ui_view.py
+++ b/addons/website/models/ir_ui_view.py
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 import copy
+import re
 import simplejson
 import werkzeug
 
@@ -158,6 +159,29 @@ class view(osv.osv):
 
         return super(view, self).render(cr, uid, id_or_xml_id, values=values, engine=engine, context=context)
 
+    def _pretty_arch(self, arch):
+        # remove_blank_string does not seem to work on HTMLParser, and
+        # pretty-printing with lxml more or less requires stripping
+        # whitespace: http://lxml.de/FAQ.html#why-doesn-t-the-pretty-print-option-reformat-my-xml-output
+        # so serialize to XML, parse as XML (remove whitespace) then serialize
+        # as XML (pretty print)
+        arch_no_whitespace = etree.fromstring(
+            etree.tostring(arch, encoding='utf-8'),
+            parser=etree.XMLParser(encoding='utf-8', remove_blank_text=True))
+        arch_pretty_indent_2 = etree.tostring(
+            arch_no_whitespace, encoding='unicode', pretty_print=True)
+
+        # pretty_print uses a fixed indent level of 2, we want an indent of 4,
+        # double up leading spaces.
+        def repl(m):
+            indent = len(m.group(0)) / 2
+            return u' ' * 4 * indent
+        # FIXME: If py2.7 only, can use re.M in sub and don't have to do replacement line by line
+        return u'\n'.join(
+            re.sub(ur'^((?:  )+)', repl, line)
+            for line in arch_pretty_indent_2.split(u'\n')
+        )
+
     def save(self, cr, uid, res_id, value, xpath=None, context=None):
         """ Update a view section. The view section may embed fields to write
 
@@ -183,5 +207,5 @@ class view(osv.osv):
 
         arch = self.replace_arch_section(cr, uid, res_id, xpath, arch_section, context=context)
         self.write(cr, uid, res_id, {
-            'arch': etree.tostring(arch, encoding='utf-8').decode('utf-8')
+            'arch': self._pretty_arch(arch)
         }, context=context)

diff --git a/addons/website/tests/test_views.py b/addons/website/tests/test_views.py
index 8041a7e..1adb117 100644 (file)
--- a/addons/website/tests/test_views.py
+++ b/addons/website/tests/test_views.py
@@ -13,8 +13,8 @@ class TestViewSaving(common.TransactionCase):
     def eq(self, a, b):
         self.assertEqual(a.tag, b.tag)
         self.assertEqual(a.attrib, b.attrib)
-        self.assertEqual(a.text, b.text)
-        self.assertEqual(a.tail, b.tail)
+        self.assertEqual((a.text or '').strip(), (b.text or '').strip())
+        self.assertEqual((a.tail or '').strip(), (b.tail or '').strip())
         for ca, cb in itertools.izip_longest(a, b):
             self.eq(ca, cb)