[Lxml-checkins] r52960 - in lxml/trunk: . src/lxml/html src/lxml/html/tests

Wed Mar 26 17:54:49 CET 2008

Author: ianb
Date: Wed Mar 26 17:54:46 2008
New Revision: 52960

Modified:
   lxml/trunk/CHANGES.txt
   lxml/trunk/src/lxml/html/diff.py
   lxml/trunk/src/lxml/html/tests/test_diff.txt
Log:
Fix empty tags (e.g., <br>) in diffs.

Modified: lxml/trunk/CHANGES.txt
==============================================================================

--- lxml/trunk/CHANGES.txt	(original)
+++ lxml/trunk/CHANGES.txt	Wed Mar 26 17:54:46 2008
@@ -29,6 +29,9 @@
 * Default encoding for plain text serialisation was different from
   that of XML serialisation (UTF-8 instead of ASCII).
 
+* ``lxml.html.diff`` didn't treat empty tags properly (e.g.,
+  ``<br>``).
+
 Other changes
 -------------
 

Modified: lxml/trunk/src/lxml/html/diff.py
==============================================================================
--- lxml/trunk/src/lxml/html/diff.py	(original)
+++ lxml/trunk/src/lxml/html/diff.py	Wed Mar 26 17:54:46 2008
@@ -139,6 +139,8 @@
 ############################################################
 
 def htmldiff(old_html, new_html):
+    ## FIXME: this should take parsed documents too, and use their body
+    ## or other content.
     """ Do a diff of the old and new document.  The documents are HTML
     *fragments* (str/UTF8 or unicode), they are not complete documents
     (i.e., no <html> tag).
@@ -310,8 +312,6 @@
         endtag = chunk[1] == '/'
         name = chunk.split()[0].strip('<>/')
         if name in empty_tags:
-            assert not endtag, (
-                "Empty tag %r should have no end tag" % chunk)
             balanced.append(chunk)
             continue
         if endtag:
@@ -669,7 +669,7 @@
             yield ('img', el.attrib['src'], start_tag(el))
         else:
             yield start_tag(el)
-    if el.tag in empty_tags and not el.text and not len(el):
+    if el.tag in empty_tags and not el.text and not len(el) and not el.tail:
         return
     start_words = split_words(el.text)
     for word in start_words:

Modified: lxml/trunk/src/lxml/html/tests/test_diff.txt
==============================================================================
--- lxml/trunk/src/lxml/html/tests/test_diff.txt	(original)
+++ lxml/trunk/src/lxml/html/tests/test_diff.txt	Wed Mar 26 17:54:46 2008
@@ -66,6 +66,11 @@
     >>> pdiff('<a href="http://yahoo.com">search</a>', '<a href="http://yahoo.com">search</a>')
     <a href="http://yahoo.com">search</a>
 
+A test of empty elements:
+
+    >>> pdiff('some <br> text', 'some <br> test')
+    some <ins><br> test</ins> <del><br> text</del>
+
 The sixteen combinations::
 
 First "insert start" (del start/middle/end/none):
@@ -177,8 +182,8 @@
     >>> panno('<p>Hi <img src="/foo"> You</p>',
     ...       '<p>Hi You</p>',
     ...       '<p>Hi You <img src="/bar"></p>')
-    <p><span version="0">Hi</span> <span version="1">You</span> <span
-    version="2"><img src="/bar"></span></p>
+    <p><span version="0">Hi You</span> <span version="2"><img
+    src="/bar"></span></p>
     >>> panno('<p><a href="/foo">Hey</a></p>',
     ...       '<p><a href="/bar">Hey</a></p>')
     <p><a href="/bar"><span version="0">Hey</span></a></p>
