1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
|
from nose.tools import istest, assert_equal
from mammoth import documents, results
from mammoth.docx.xmlparser import element as xml_element, text as xml_text
from mammoth.docx.document_xml import read_document_xml_element
from mammoth.docx.numbering_xml import Numbering, NumberingLevel
@istest
class ReadXmlElementTests(object):
@istest
def text_from_text_element_is_read(self):
element = _text_element("Hello!")
assert_equal(documents.Text("Hello!"), _read_and_get_document_xml_element(element))
@istest
def can_read_text_within_run(self):
element = _run_element_with_text("Hello!")
assert_equal(
documents.run([documents.Text("Hello!")]),
_read_and_get_document_xml_element(element)
)
@istest
def can_read_text_within_paragraph(self):
element = _paragraph_element_with_text("Hello!")
assert_equal(
documents.paragraph([documents.run([documents.Text("Hello!")])]),
_read_and_get_document_xml_element(element)
)
@istest
def can_read_text_within_document(self):
element = _document_element_with_text("Hello!")
assert_equal(
documents.Document([documents.paragraph([documents.run([documents.Text("Hello!")])])]),
_read_and_get_document_xml_element(element)
)
@istest
def paragraph_has_no_style_if_it_has_no_properties(self):
element = xml_element("w:p")
assert_equal(None, _read_and_get_document_xml_element(element).style_name)
@istest
def paragraph_has_style_name_read_from_paragraph_properties_if_present(self):
style_xml = xml_element("w:pStyle", {"w:val": "Heading1"})
properties_xml = xml_element("w:pPr", {}, [style_xml])
paragraph_xml = xml_element("w:p", {}, [properties_xml])
paragraph = _read_and_get_document_xml_element(paragraph_xml)
assert_equal("Heading1", paragraph.style_name)
@istest
def paragraph_has_no_numbering_if_it_has_no_numbering_properties(self):
element = xml_element("w:p")
assert_equal(None, _read_and_get_document_xml_element(element).numbering)
@istest
def paragraph_has_numbering_properties_from_paragraph_properties_if_present(self):
numbering_properties_xml = xml_element("w:numPr", {}, [
xml_element("w:ilvl", {"w:val": "1"}),
xml_element("w:numId", {"w:val": "42"}),
])
properties_xml = xml_element("w:pPr", {}, [numbering_properties_xml])
paragraph_xml = xml_element("w:p", {}, [properties_xml])
numbering = Numbering({"42": {"1": NumberingLevel("1", True)}})
paragraph = _read_and_get_document_xml_element(paragraph_xml, numbering=numbering)
assert_equal("1", paragraph.numbering.level_index)
assert_equal(True, paragraph.numbering.is_ordered)
@istest
def run_has_no_style_if_it_has_no_properties(self):
element = xml_element("w:r")
assert_equal(None, _read_and_get_document_xml_element(element).style_name)
@istest
def run_has_style_name_read_from_run_properties_if_present(self):
style_xml = xml_element("w:rStyle", {"w:val": "Emphasis"})
run = self._read_run_with_properties([style_xml])
assert_equal("Emphasis", run.style_name)
@istest
def run_is_not_bold_if_bold_element_is_not_present(self):
run = self._read_run_with_properties([])
assert_equal(False, run.is_bold)
@istest
def run_is_bold_if_bold_element_is_present(self):
run = self._read_run_with_properties([xml_element("w:b")])
assert_equal(True, run.is_bold)
@istest
def run_is_not_italic_if_italic_element_is_not_present(self):
run = self._read_run_with_properties([])
assert_equal(False, run.is_italic)
@istest
def run_is_italic_if_italic_element_is_present(self):
run = self._read_run_with_properties([xml_element("w:i")])
assert_equal(True, run.is_italic)
def _read_run_with_properties(self, properties):
properties_xml = xml_element("w:rPr", {}, properties)
run_xml = xml_element("w:r", {}, [properties_xml])
return _read_and_get_document_xml_element(run_xml)
@istest
def can_read_tab_element(self):
element = xml_element("w:tab")
tab = _read_and_get_document_xml_element(element)
assert_equal(documents.tab(), tab)
@istest
def children_of_w_ins_are_converted_normally(self):
element = xml_element("w:p", {}, [
xml_element("w:ins", {}, [
xml_element("w:r")
])
])
assert_equal(
documents.paragraph([documents.run([])]),
_read_and_get_document_xml_element(element)
)
@istest
def ignored_elements_are_ignored_without_message(self):
element = xml_element("w:bookmarkStart")
result = read_document_xml_element(element)
assert_equal(None, result.value)
assert_equal([], result.messages)
@istest
def unrecognised_elements_emit_warning(self):
element = xml_element("w:huh", {}, [])
result = read_document_xml_element(element)
expected_warning = results.warning("An unrecognised element was ignored: w:huh")
assert_equal([expected_warning], result.messages)
@istest
def unrecognised_elements_are_ignored(self):
element = xml_element("w:huh", {}, [])
assert_equal(None, _read_and_get_document_xml_element(element))
@istest
def unrecognised_children_are_ignored(self):
element = xml_element("w:r", {}, [_text_element("Hello!"), xml_element("w:huh", {}, [])])
assert_equal(
documents.run([documents.Text("Hello!")]),
_read_and_get_document_xml_element(element)
)
def _read_and_get_document_xml_element(*args, **kwargs):
return read_document_xml_element(*args, **kwargs).value
def _document_element_with_text(text):
return xml_element("w:document", {}, [
xml_element("w:body", {}, [_paragraph_element_with_text(text)])
])
def _paragraph_element_with_text(text):
return xml_element("w:p", {}, [_run_element_with_text(text)])
def _run_element_with_text(text):
return xml_element("w:r", {}, [_text_element(text)])
def _text_element(value):
return xml_element("w:t", {}, [xml_text(value)])
|
