def test_remove_insignificant_text_nodes():
html = dedent('''
<html>
<head />
<body>
<p>
one <em>two</em> <strong>three</strong>
</p>
<table>
<tr>
<td>stuff</td>
</tr>
</table>
</body>
</html>
''')
target_html = ('<p> one <em>two</em> <strong>three</strong> </p> '
'<table><tr><td>stuff</td></tr></table>')
dom = parse_minidom(html)
remove_insignificant_text_nodes(dom)
html = minidom_tostring(dom)
assert_equal(html, target_html)
# Check that it is idempotent.
dom = parse_minidom(html)
remove_insignificant_text_nodes(dom)
html = minidom_tostring(dom)
assert_equal(html, target_html)
def test_remove_insignificant_text_nodes():
html = dedent(
"""
<html>
<head />
<body>
<p>
one <em>two</em> <strong>three</strong>
</p>
<table>
<tr>
<td>stuff</td>
</tr>
</table>
</body>
</html>
"""
)
target_html = "<p> one <em>two</em> <strong>three</strong> </p> " "<table><tr><td>stuff</td></tr></table>"
dom = parse_minidom(html)
remove_insignificant_text_nodes(dom)
html = minidom_tostring(dom)
assert_equal(html, target_html)
# Check that it is idempotent.
dom = parse_minidom(html)
remove_insignificant_text_nodes(dom)
html = minidom_tostring(dom)
assert_equal(html, target_html)
def test(original, distributed):
original = parse_minidom(original)
distributed = parse_minidom(distributed)
node = get_location(original, [0])
distribute(node)
assert_html_equal(
minidom_tostring(original),
minidom_tostring(distributed),
)
def test(original, distributed):
original = parse_minidom(original)
distributed = parse_minidom(distributed)
node = get_location(original, [0])
distribute(node)
assert_html_equal(
minidom_tostring(original),
minidom_tostring(distributed),
)
def test_parse_comments():
assert_html_equal(
minidom_tostring(parse_minidom('<!-- -->')),
'',
)
assert_html_equal(
minidom_tostring(parse_minidom('<!--\n-->')),
'',
)
assert_html_equal(
minidom_tostring(parse_minidom('<p>stuff<!-- \n -->stuff</p>')),
'<p>stuffstuff</p>',
)
def diff(old_html, new_html, cutoff=0.0, plaintext=False, pretty=False):
"""Show the differences between the old and new html document, as html.
Return the document html with extra tags added to show changes. Add <ins>
tags around newly added sections, and <del> tags to show sections that have
been deleted.
"""
if plaintext:
old_dom = parse_text(old_html)
new_dom = parse_text(new_html)
else:
old_dom = parse_minidom(old_html)
new_dom = parse_minidom(new_html)
# If the two documents are not similar enough, don't show the changes.
if not check_text_similarity(old_dom, new_dom, cutoff):
return (
'<h2>The differences from the previous version are too large to '
'show concisely.</h2>')
dom = dom_diff(old_dom, new_dom)
# HTML-specific cleanup.
if not plaintext:
fix_lists(dom)
fix_tables(dom)
# Only return html for the document body contents.
body_elements = dom.getElementsByTagName('body')
if len(body_elements) == 1:
dom = body_elements[0]
return minidom_tostring(dom, pretty=pretty)
def diff(old_html, new_html, cutoff=0.0, plaintext=False, pretty=False):
"""Show the differences between the old and new html document, as html.
Return the document html with extra tags added to show changes. Add <ins>
tags around newly added sections, and <del> tags to show sections that have
been deleted.
"""
if plaintext:
old_dom = parse_text(old_html)
new_dom = parse_text(new_html)
else:
old_dom = parse_minidom(old_html)
new_dom = parse_minidom(new_html)
# If the two documents are not similar enough, don't show the changes.
if not check_text_similarity(old_dom, new_dom, cutoff):
return "<h2>The differences from the previous version are too large to " "show concisely.</h2>"
dom = dom_diff(old_dom, new_dom)
# HTML-specific cleanup.
if not plaintext:
fix_lists(dom)
fix_tables(dom)
# Only return html for the document body contents.
body_elements = dom.getElementsByTagName("body")
if len(body_elements) == 1:
dom = body_elements[0]
return minidom_tostring(dom, pretty=pretty)
def test_remove_insignificant_text_nodes_nbsp():
html = dedent(
"""
<table>
<tbody>
<tr>
<td> </td>
<td> </td>
<td> </td>
</tr>
</tbody>
</table>
"""
)
dom = parse_minidom(html)
remove_insignificant_text_nodes(dom)
html = minidom_tostring(dom)
assert_equal(html, ("<table><tbody><tr><td> </td><td> </td><td> </td>" "</tr></tbody></table>"))
def test_remove_insignificant_text_nodes_nbsp():
html = dedent('''
<table>
<tbody>
<tr>
<td> </td>
<td> </td>
<td> </td>
</tr>
</tbody>
</table>
''')
dom = parse_minidom(html)
remove_insignificant_text_nodes(dom)
html = minidom_tostring(dom)
assert_equal(
html,
('<table><tbody><tr><td> </td><td> </td><td> </td>'
'</tr></tbody></table>'),
)
def test():
dom = parse_minidom(old_html)
assert_equal(minidom_tostring(dom), target)
assert_equal(remove_xml_declaration(dom.toxml()), target_raw)
def test():
changes_dom = parse_minidom(changes, strict_xml=True)
fix_tables(changes_dom)
assert_html_equal(minidom_tostring(changes_dom), fixed_changes)
def test():
changes_dom = parse_minidom(changes)
fix_lists(changes_dom)
assert_html_equal(minidom_tostring(changes_dom), fixed_changes)
def strip_changes_new(html):
dom = parse_minidom(html)
_strip_changes_new(dom)
return minidom_tostring(dom)
def test():
dom = parse_minidom(old_html)
assert_equal(minidom_tostring(dom), target)
assert_equal(remove_xml_declaration(dom.toxml()), target_raw)
def html_patch(old_html, edit_script):
old_dom = parse_minidom(old_html)
split_text_nodes(old_dom)
runner = EditScriptRunner(old_dom, edit_script)
return minidom_tostring(runner.run_edit_script())
def strip_changes_new(html):
dom = parse_minidom(html)
_strip_changes_new(dom)
return minidom_tostring(dom)
def reverse_changes_html(changes):
dom = parse_minidom(changes)
reverse_changes(dom)
return minidom_tostring(dom)
def test_xml_diff():
for test_name, old_html, new_html, target in test_cases:
old_dom = parse_minidom(old_html, strict_xml=True)
new_dom = parse_minidom(new_html, strict_xml=True)
changes_xml = minidom_tostring(dom_diff(old_dom, new_dom))
assert_equal(changes_xml, target)
def remove_attributes(html):
dom = parse_minidom(html)
remove_dom_attributes(dom)
return minidom_tostring(dom)
def test_xml_diff():
for test_name, old_html, new_html, target in test_cases:
old_dom = parse_minidom(old_html, strict_xml=True)
new_dom = parse_minidom(new_html, strict_xml=True)
changes_xml = minidom_tostring(dom_diff(old_dom, new_dom))
assert_equal(changes_xml, target)
def test():
changes_dom = parse_minidom(changes)
fix_lists(changes_dom)
assert_html_equal(minidom_tostring(changes_dom), fixed_changes)
def html_patch(old_html, edit_script):
old_dom = parse_minidom(old_html)
split_text_nodes(old_dom)
runner = EditScriptRunner(old_dom, edit_script)
return minidom_tostring(runner.run_edit_script())
def test():
changes_dom = parse_minidom(changes, strict_xml=True)
fix_tables(changes_dom)
assert_html_equal(minidom_tostring(changes_dom), fixed_changes)
def remove_attributes(html):
dom = parse_minidom(html)
remove_dom_attributes(dom)
return minidom_tostring(dom)
def reverse_changes_html(changes):
dom = parse_minidom(changes)
reverse_changes(dom)
return minidom_tostring(dom)