def test_extract_1(self):
html = \
"<h1>1</h1>" \
"<h1>2</h1>" \
"<h2>2.1</h2>" \
"<h2>2.2</h2>" \
"<h2>2.3</h2>" \
"<h2>2.4</h2>" \
"<h1>3</h1>" \
"<h1>4</h1>"
presentation = {'h1_1':set([PC('myclass1')]),
'h1_2':set([]),
'h1_3':set([]),
'h1_4':set([]),
'h2_1':set([]),
'h2_2':set([]),
'h2_3':set([]),
'h2_4':set([]),
'newrow_h1_1':set([NEWROW]),
'newcol_h1_1':set([NEWCOL]),
'newrow_h2_1':set([NEWROW]),
'newcol_h2_1':set([NEWCOL]),
'newcol_h2_2':set([NEWCOL]),
'newrow_h2_3':set([NEWROW]),
'newcol_h2_3':set([NEWCOL]),
'newcol_h2_4':set([NEWCOL, PC('myclass2')]),
'newrow_h1_3':set([NEWROW]),
'newcol_h1_3':set([NEWCOL]),
'newcol_h1_4':set([NEWCOL]),
}
combined = format_html(html, presentation)
pres2, html2 = extract_presentation(combined)
self.assertEqual(presentation, pres2)
def test_extract_2(self):
# Full featured, proper test
html = """
<div class="row columns3"><div class="column firstcolumn"><div class="myclass"><h1>Hello Jane</h1><p>Some fancy content, entered using WYMeditor</p><p>Another paragraph</p><p>Hello</p></div></div><div class="column doublewidth"><div><h1>Another <heading></h1><h2>this is a test</h2><h2>hello1</h2><h3>hello2</h3><h3>hello3</h3><h3>hello4</h3></div></div><div class="column lastcolumn"><div><h1>hello5</h1><h2>hello6</h2><p>asdasd</p><p>asdxx</p></div></div></div>
"""
pres = {'newrow_h1_1':set([NEWROW]),
'newcol_h1_1':set([NEWCOL, PC('myclass')]),
'h1_1':set(),
'newcol_h1_2':set([NEWCOL, PC('doublewidth', column_equiv=2)]),
'h1_2':set(),
'p_1': set(),
'p_2': set(),
'p_3': set(),
'h2_1':set(),
'h2_2':set(),
'h3_1':set(),
'h3_2':set(),
'h3_3':set(),
'newcol_h1_3':set([NEWCOL]),
'h1_3':set(),
'h2_3':set(),
'p_4': set(),
'p_5': set(),
}
pres2, html2 = extract_presentation(html)
self.assertEqual(pres, pres2)
def _handled():
pres, html = extract_presentation(data)
# Rewrite pres so that we can serialise it to JSON
pres2 = {}
for k, v in pres.items():
pres2[k] = [PI_to_dict(p) for p in v]
return dict(presentation=pres2, html=html)
def test_extract_presentation(self):
html = "<h1 class=\"foo\">Heading 1</h1><h2 class=\"bar baz\">Heading 2</h2><p class=\"whatsit\">Some paragraph</p>"
pres, html2 = extract_presentation(html)
self.assertEqual({'h1_1':set([PC('foo')]),
'h2_1':set([PC('bar'), PC('baz')]),
'p_1':set([PC('whatsit')]),
}, pres)
self.assertEqual("<h1 id=\"h1_1\">Heading 1</h1><h2 id=\"h2_1\">Heading 2</h2><p id=\"p_1\">Some paragraph</p>", html2)
def _handled():
pres, html = extract_presentation(data)
# Rewrite pres so that we can serialise it to JSON
pres2 = {}
for k, v in pres.items():
pres2[k] = [PI_to_dict(p) for p in v]
return dict(presentation=pres2,
html=html)
def test_div_extract_hack(self):
"""
Check that a div with class "div" is recognised and turned back into a 'p'
when extracting
"""
html = '<div class="div">Test</div>'
pres, html2 = extract_presentation(html)
self.assertEqual({'p_1':set([PC('div')])}, pres)
self.assertEqual('<p id="p_1">Test</p>', html2);
def test_extract_nested_layout(self):
"""
Tests that we can properly extract a layout created using inner rows/columns.
"""
pres = {'newrow_h1_1':set([NEWROW]),
'newcol_h1_1':set([NEWCOL]),
'newcol_h1_2':set([NEWCOL]),
'innerrow_h1_3':set([NEWINNERROW]),
'innercol_h1_3':set([NEWINNERCOL]),
'innercol_h1_4':set([NEWINNERCOL]),
'newcol_h1_5':set([NEWCOL]),
'newrow_h1_6':set([NEWROW]),
'newcol_h1_6':set([NEWCOL]),
'newcol_h1_7':set([NEWCOL]),
'h1_1':set([]),
'h1_2':set([]),
'h1_3':set([]),
'h1_4':set([]),
'h1_5':set([]),
'h1_6':set([]),
'h1_7':set([]),
}
html = ('<div class="row columns3">'
'<div class="column firstcolumn">'
'<div><h1>1</h1></div>'
'</div>'
'<div class="column">'
'<div>'
'<h1>2</h1>'
'<div class="row columns2">'
'<div class="column firstcolumn">'
'<div><h1>3</h1></div>'
'</div>'
'<div class="column lastcolumn">'
'<div><h1>4</h1></div>'
'</div>'
'</div>'
'</div>'
'</div>'
'<div class="column lastcolumn">'
'<div><h1>5</h1></div>'
'</div>'
'</div>'
'<div class="row columns2">'
'<div class="column firstcolumn">'
'<div><h1>6</h1></div>'
'</div>'
'<div class="column lastcolumn">'
'<div><h1>7</h1></div>'
'</div>'
'</div>'
)
pres2, html2 = extract_presentation(html)
self.assertEqual(pres, pres2)
def test_extract_3(self):
# Tests some other boundary conditions e.g. 1 column row,
html = """
<div class="row"><div><div><h1>1</h1><h2>1.1</h2><h2>1.2</h2></div></div></div>
"""
pres = {'h1_1': set(),
'newrow_h1_1':set([NEWROW]),
'newcol_h1_1':set([NEWCOL]),
'h2_1': set(),
'h2_2': set(),
}
pres2, html2 = extract_presentation(html)
self.assertEqual(pres, pres2)
def test_extract_nested_layout_2(self):
"""
Issue 37
"""
pres = {'newrow_p_1':set([NEWROW]),
'newcol_p_1':set([NEWCOL]),
'innerrow_p_1':set([NEWINNERROW]),
'innercol_p_1':set([NEWINNERCOL]),
'innercol_p_2':set([NEWINNERCOL]),
'newcol_p_3':set([NEWCOL]),
'innerrow_p_3':set([NEWINNERROW]),
'innercol_p_3':set([NEWINNERCOL]),
'innercol_p_4':set([NEWINNERCOL]),
'p_1':set([]),
'p_2':set([]),
'p_3':set([]),
'p_4':set([]),
}
html = ('<div class="row columns2">'
'<div class="column firstcolumn">'
'<div>'
'<div class="row columns2">'
'<div class="column firstcolumn">'
'<div><p>col1</p></div>'
'</div>'
'<div class="column lastcolumn">'
'<div><p>col2</p></div>'
'</div>'
'</div>'
'</div>'
'</div>'
'<div class="column firstcolumn">'
'<div>'
'<div class="row columns2">'
'<div class="column firstcolumn">'
'<div><p>col3</p></div>'
'</div>'
'<div class="column lastcolumn">'
'<div><p>col4</p></div>'
'</div>'
'</div>'
'</div>'
'</div>'
'</div>'
)
pres2, html2 = extract_presentation(html)
self.assertEqual(pres, pres2)
def test_extract_no_inner_col_div_2(self):
# Tests that we can extract column structure if we don't have
# an inner column div.
# This is important for the case where LayoutDetails.use_inner_column_div = False
# Double col structure
html = """
<div class="row"><div class="column firstcolumn"><h1>1</h1></div><div class="column lastcolumn"><h2>1.1</h2></div></div>
"""
pres = {'h1_1': set(),
'newrow_h1_1':set([NEWROW]),
'newcol_h1_1':set([NEWCOL]),
'h2_1': set(),
'newcol_h2_1':set([NEWCOL])
}
pres2, html2 = extract_presentation(html)
self.assertEqual(pres, pres2)
def test_round_trip(self):
# Test the round trip of html -> extract_presentation -> format_html
stored_html = "<h1>Hello</h1>"
pres, simple_html = extract_presentation(stored_html)
formatted = format_html(simple_html, pres)
self.assertEqual(formatted, stored_html)
def test_format_pre(self):
html = "<pre>This\r\nis\r\na\r\ntest</pre>"
# check that format_html doesn't do anything nasty inside the pre
html2 = format_html(html, {})
pres, html3 = extract_presentation(html2)
self.assertEqual(html, html3)
def test_extract_empty(self):
pres, out_html = extract_presentation('')
self.assertEqual('', out_html)