xref: /trunk/test/aoo-test/tests/selftest/test_foreign.py (revision 2cb6d6f119bbe2f78742f1c5c8538cb0d4e72ede) 
1################################################################
2#
3#  Licensed to the Apache Software Foundation (ASF) under one
4#  or more contributor license agreements.  See the NOTICE file
5#  distributed with this work for additional information
6#  regarding copyright ownership.  The ASF licenses this file
7#  to you under the Apache License, Version 2.0 (the
8#  "License"); you may not use this file except in compliance
9#  with the License.  You may obtain a copy of the License at
10#
11#    http://www.apache.org/licenses/LICENSE-2.0
12#
13#  Unless required by applicable law or agreed to in writing,
14#  software distributed under the License is distributed on an
15#  "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
16#  KIND, either express or implied.  See the License for the
17#  specific language governing permissions and limitations
18#  under the License.
19#
20################################################################
21
22"""foreign.strip_foreign(): removal of foreign elements and attributes (ODF 1.2 Part 1 2.2.2 B.1, 3.17)."""
23import os
24
25import pytest
26
27from aootest.checkers import foreign
28
29pytestmark = pytest.mark.selftest
30
31HDR = ('<office:text xmlns:office="urn:oasis:names:tc:opendocument:xmlns:office:1.0" xmlns:text="urn:oasis:names:tc:opendocument:xmlns:text:1.0" '
32       'xmlns:draw="urn:oasis:names:tc:opendocument:xmlns:drawing:1.0" xmlns:foo="urn:foo" xmlns:dc="http://purl.org/dc/elements/1.1/" '
33       'xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xf="http://www.w3.org/2002/xforms"')
34CASES = [
35    ("foreign attribute removed", '<text:p foo:x="1" text:style-name="a">t</text:p>', '<text:p text:style-name="a">t</text:p>'),
36    ("foreign element outside a paragraph dropped with its content", '<foo:x>stuff<text:p>q</text:p></foo:x><text:p>t</text:p>', '<text:p>t</text:p>'),
37    ("foreign element in a paragraph: tags removed, content kept", '<text:p>a<foo:x>b<text:span>c</text:span></foo:x>d</text:p>', '<text:p>ab<text:span>c</text:span>d</text:p>'),
38    ("foreign element in a span in a paragraph: tags removed", '<text:p><text:span>a<foo:x>b</foo:x></text:span></text:p>', '<text:p><text:span>ab</text:span></text:p>'),
39    ("foreign element below a frame (no character data): dropped", '<text:p><draw:frame><foo:x>b</foo:x></draw:frame></text:p>', '<text:p><draw:frame></draw:frame></text:p>'),
40    ("namespace declared on an unwrapped element is kept for its children",
41     '<text:p><foo:x xmlns:t2="urn:oasis:names:tc:opendocument:xmlns:text:1.0"><t2:span>a</t2:span></foo:x></text:p>',
42     '<text:p><t2:span xmlns:t2="urn:oasis:names:tc:opendocument:xmlns:text:1.0">a</t2:span></text:p>'),
43    ("elements and attributes of table 4 namespaces kept", '<text:p xlink:href="u"><dc:title>t</dc:title></text:p>', '<text:p xlink:href="u"><dc:title>t</dc:title></text:p>'),
44    ("content below a table 4 element kept (wildcard content)", '<xf:model><foo:data><bar/></foo:data></xf:model>', '<xf:model><foo:data><bar></bar></foo:data></xf:model>'),
45    ("text is escaped again", '<text:p>a &amp; b &lt; c</text:p>', '<text:p>a &amp; b &lt; c</text:p>'),
46]
47
48
49@pytest.fixture(scope="module")
50def mixed(schema_dir):
51    return foreign.mixed_elements(os.path.join(schema_dir, "OpenDocument-v1.2-os-schema.rng"))
52
53
54@pytest.mark.parametrize("src, want", [pytest.param(s, w, id=n) for n, s, w in CASES])
55def test_strip_foreign(src, want, mixed):
56    got = foreign.strip_foreign(HDR + ">" + src + "</office:text>", mixed).split("\n", 1)[1].strip()
57    inner = got[got.index(">") + 1:-len("</office:text>")] if got.startswith("<office:text") else got
58    assert inner == want
59