def setUp(self):
container = Container('samples/example.odt')
self.container = container
content_part = XmlPart(ODF_CONTENT, container)
self.annotation_element = (
content_part.get_element('//office:annotation[1]'))
self.paragraph_element = content_part.get_element('//text:p[1]')
def test_serialize(self):
container = self.container
content_bytes = container.get_part(ODF_CONTENT)
content_part = XmlPart(ODF_CONTENT, container)
# differences with lxml
serialized = content_part.serialize().replace(b"'", b"'")
self.assertEqual(content_bytes, serialized)
class ReplaceTestCase(TestCase):
def setUp(self):
self.container = Container('samples/span_style.odt')
self.content = XmlPart(ODF_CONTENT, self.container)
self.paragraph = self.content.get_element('//text:p')
self.span = self.paragraph.get_element('//text:span')
def test_count(self):
paragraph = self.paragraph
expected = paragraph.serialize()
count = paragraph.replace("ou")
self.assertEqual(count, 2)
# Ensure the orignal was not altered
self.assertEqual(paragraph.serialize(), expected)
def test_replace(self):
paragraph = self.paragraph
clone = paragraph.clone
count = clone.replace("moustache", "barbe")
self.assertEqual(count, 1)
expected = "Le Père Noël a une barbe rouge."
self.assertEqual(clone.text_recursive, expected)
# Ensure the orignal was not altered
self.assertNotEqual(clone.serialize(), paragraph.serialize())
def test_across_span(self):
paragraph = self.paragraph
count = paragraph.replace("moustache rouge")
self.assertEqual(count, 0)
def test_missing(self):
paragraph = self.paragraph
count = paragraph.replace("barbe")
self.assertEqual(count, 0)
class MatchTestCase(TestCase):
def setUp(self):
self.container = Container('samples/span_style.odt')
self.content = XmlPart(ODF_CONTENT, self.container)
self.paragraph = self.content.get_element('//text:p')
self.span = self.paragraph.get_element('//text:span')
def test_match_paragraph(self):
"""Match text in a paragraph.
"""
match = self.paragraph.match('ère')
return self.assertTrue(match)
def test_match_span(self):
"""Match text in a span.
"""
match = self.span.match('moust')
return self.assertTrue(match)
def test_match_inner_span(self):
"""Match text in a span from the parent paragraph.
"""
match = self.paragraph.match('roug')
return self.assertTrue(match)
def test_simple_regex(self):
"""Match a simple regex.
"""
match = self.paragraph.match('che roug')
return self.assertTrue(match)
def test_intermediate_regex(self):
"""Match an intermediate regex.
"""
match = self.paragraph.match('moustache (blanche|rouge)')
return self.assertTrue(match)
def test_complex_regex(self):
"""Match a complex regex.
"""
# The (?<=...) part is pointless as we don't try to get groups from
# a MatchObject. However, it's a valid regex expression.
match = self.paragraph.match(r'(?<=m)(ou)\w+(che) (blan\2|r\1ge)')
return self.assertTrue(match)
def test_compiled_regex(self):
"""Match with a compiled pattern.
"""
pattern = compile(r'moustache')
match = self.paragraph.match(pattern)
return self.assertTrue(match)
def test_failing_match(self):
"""Test a regex that doesn't match.
"""
match = self.paragraph.match('Le Père moustache')
return self.assertFalse(match)
def test_delete(self):
container = self.container
content = XmlPart(ODF_CONTENT, container)
paragraphs = content.get_elements("//text:p")
for paragraph in paragraphs:
content.delete_element(paragraph)
serialized = content.serialize()
self.assertEqual(serialized.count(b"<text:p"), 0)
class SearchTestCase(TestCase):
def setUp(self):
self.container = Container("samples/span_style.odt")
self.content = XmlPart(ODF_CONTENT, self.container)
self.paragraph = self.content.get_element("//text:p")
self.span = self.paragraph.get_element("//text:span")
def test_search_paragraph(self):
"""Search text in a paragraph."""
pos = self.paragraph.search("ère")
return self.assertEqual(pos, 4)
def test_match_span(self):
"""Search text in a span."""
pos = self.span.search("moust")
return self.assertEqual(pos, 0)
def test_match_inner_span(self):
"""Search text in a span from the parent paragraph."""
pos = self.paragraph.search("roug")
return self.assertEqual(pos, 29)
def test_simple_regex(self):
"""Search a simple regex."""
pos = self.paragraph.search("che roug")
return self.assertEqual(pos, 25)
def test_intermediate_regex(self):
"""Search an intermediate regex."""
pos = self.paragraph.search("moustache (blanche|rouge)")
return self.assertEqual(pos, 19)
def test_complex_regex(self):
"""Search a complex regex."""
# The (?<=...) part is pointless as we don't try to get groups from
# a MatchObject. However, it's a valid regex expression.
pos = self.paragraph.search(r"(?<=m)(ou)\w+(che) (blan\2|r\1ge)")
return self.assertEqual(pos, 20)
def test_compiled_regex(self):
"""Search with a compiled pattern."""
pattern = compile(r"moustache")
pos = self.paragraph.search(pattern)
return self.assertEqual(pos, 19)
def test_failing_match(self):
"""Test a regex that doesn't match."""
pos = self.paragraph.search("Le Père moustache")
return self.assertTrue(pos is None)
def test_root(self):
content = XmlPart(ODF_CONTENT, self.container)
root = content.root
self.assertTrue(isinstance(root, Element))
self.assertEqual(root.tag, "office:document-content")
self.assertNotEqual(content._XmlPart__root, None)
def test_tree(self):
# Testing a private but important method
content = XmlPart(ODF_CONTENT, self.container)
tree = content._XmlPart__get_tree()
self.assertTrue(isinstance(tree, _ElementTree))
self.assertNotEqual(content._XmlPart__tree, None)
def test_get_element_list(self):
content_part = XmlPart(ODF_CONTENT, self.container)
elements = content_part.get_elements("//text:p")
# The annotation paragraph is counted
self.assertEqual(len(elements), 8)
def setUp(self):
self.container = container = Container('samples/example.odt')
self.content_part = content_part = XmlPart(ODF_CONTENT, container)
self.paragraph_element = content_part.get_element('//text:p[1]')
query = '//style:style[@style:family="paragraph"][1]'
self.style_element = content_part.get_element(query)
def setUp(self):
self.container = Container('samples/span_style.odt')
self.content = XmlPart(ODF_CONTENT, self.container)
self.paragraph = self.content.get_element('//text:p')
self.span = self.paragraph.get_element('//text:span')
def setUp(self):
container = Container("samples/example.odt")
self.container = container
content_part = XmlPart(ODF_CONTENT, container)
self.paragraph_element = content_part.get_element("//text:p[1]")
