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
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
|
# coding=utf-8
from __future__ import unicode_literals
from nose.tools import istest, assert_equal
from .testing import test_path
import mammoth
@istest
def docx_containing_one_paragraph_is_converted_to_single_p_element():
with open(test_path("single-paragraph.docx"), "rb") as fileobj:
result = mammoth.convert_to_html(fileobj=fileobj)
assert_equal("<p>Walking on imported air</p>", result.value)
assert_equal([], result.messages)
@istest
def can_read_xml_files_with_utf8_bom():
with open(test_path("utf8-bom.docx"), "rb") as fileobj:
result = mammoth.convert_to_html(fileobj=fileobj)
assert_equal("<p>This XML has a byte order mark.</p>", result.value)
assert_equal([], result.messages)
@istest
def empty_paragraphs_are_ignored_by_default():
with open(test_path("empty.docx"), "rb") as fileobj:
result = mammoth.convert_to_html(fileobj=fileobj)
assert_equal("", result.value)
assert_equal([], result.messages)
@istest
def empty_paragraphs_are_preserved_if_ignore_empty_paragraphs_is_false():
with open(test_path("empty.docx"), "rb") as fileobj:
result = mammoth.convert_to_html(fileobj=fileobj, ignore_empty_paragraphs=False)
assert_equal("<p></p>", result.value)
assert_equal([], result.messages)
@istest
def inline_images_are_included_in_output():
with open(test_path("tiny-picture.docx"), "rb") as fileobj:
result = mammoth.convert_to_html(fileobj=fileobj)
assert_equal("""<p><img src="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAIAAAACUFjqAAAAAXNSR0IArs4c6QAAAAlwSFlzAAAOvgAADr4B6kKxwAAAABNJREFUKFNj/M+ADzDhlWUYqdIAQSwBE8U+X40AAAAASUVORK5CYII=" /></p>""", result.value)
assert_equal([], result.messages)
@istest
def images_stored_outside_of_document_are_included_in_output():
with open(test_path("external-picture.docx"), "rb") as fileobj:
result = mammoth.convert_to_html(fileobj=fileobj)
assert_equal("""<p><img src="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAIAAAACUFjqAAAAAXNSR0IArs4c6QAAAAlwSFlzAAAOvgAADr4B6kKxwAAAABNJREFUKFNj/M+ADzDhlWUYqdIAQSwBE8U+X40AAAAASUVORK5CYII=" /></p>""", result.value)
assert_equal([], result.messages)
@istest
def simple_list_is_converted_to_list_elements():
with open(test_path("simple-list.docx"), "rb") as fileobj:
result = mammoth.convert_to_html(fileobj=fileobj)
assert_equal([], result.messages)
assert_equal("<ul><li>Apple</li><li>Banana</li></ul>", result.value)
@istest
def word_tables_are_converted_to_html_tables():
expected_html = ("<p>Above</p>" +
"<table>" +
"<tr><td><p>Top left</p></td><td><p>Top right</p></td></tr>" +
"<tr><td><p>Bottom left</p></td><td><p>Bottom right</p></td></tr>" +
"</table>" +
"<p>Below</p>")
with open(test_path("tables.docx"), "rb") as fileobj:
result = mammoth.convert_to_html(fileobj=fileobj)
assert_equal([], result.messages)
assert_equal(expected_html, result.value)
@istest
def footnotes_are_appended_to_text():
# TODO: don't duplicate footnotes with multiple references
expected_html = ('<p>Ouch' +
'<sup><a href="#doc-42-footnote-1" id="doc-42-footnote-ref-1">[1]</a></sup>.' +
'<sup><a href="#doc-42-footnote-2" id="doc-42-footnote-ref-2">[2]</a></sup></p>' +
'<ol><li id="doc-42-footnote-1"><p> A tachyon walks into a bar. <a href="#doc-42-footnote-ref-1">↑</a></p></li>' +
'<li id="doc-42-footnote-2"><p> Fin. <a href="#doc-42-footnote-ref-2">↑</a></p></li></ol>')
with open(test_path("footnotes.docx"), "rb") as fileobj:
result = mammoth.convert_to_html(fileobj=fileobj, id_prefix="doc-42")
assert_equal([], result.messages)
assert_equal(expected_html, result.value)
@istest
def endnotes_are_appended_to_text():
expected_html = ('<p>Ouch' +
'<sup><a href="#doc-42-endnote-2" id="doc-42-endnote-ref-2">[1]</a></sup>.' +
'<sup><a href="#doc-42-endnote-3" id="doc-42-endnote-ref-3">[2]</a></sup></p>' +
'<ol><li id="doc-42-endnote-2"><p> A tachyon walks into a bar. <a href="#doc-42-endnote-ref-2">↑</a></p></li>' +
'<li id="doc-42-endnote-3"><p> Fin. <a href="#doc-42-endnote-ref-3">↑</a></p></li></ol>')
with open(test_path("endnotes.docx"), "rb") as fileobj:
result = mammoth.convert_to_html(fileobj=fileobj, id_prefix="doc-42")
assert_equal([], result.messages)
assert_equal(expected_html, result.value)
@istest
def relationships_are_handled_properly_in_footnotes():
expected_html = (
'<p><sup><a href="#doc-42-footnote-1" id="doc-42-footnote-ref-1">[1]</a></sup></p>' +
'<ol><li id="doc-42-footnote-1"><p> <a href="http://www.example.com">Example</a> <a href="#doc-42-footnote-ref-1">↑</a></p></li></ol>')
with open(test_path("footnote-hyperlink.docx"), "rb") as fileobj:
result = mammoth.convert_to_html(fileobj=fileobj, id_prefix="doc-42")
assert_equal([], result.messages)
assert_equal(expected_html, result.value)
@istest
def text_boxes_are_read():
with open(test_path("text-box.docx"), "rb") as fileobj:
result = mammoth.convert_to_html(fileobj=fileobj)
assert_equal('<p>Datum plane</p>', result.value)
@istest
def underline_is_ignored_by_defualt():
with open(test_path("underline.docx"), "rb") as fileobj:
result = mammoth.convert_to_html(fileobj=fileobj)
assert_equal('<p><strong>The </strong><strong>Sunset</strong><strong> Tree</strong></p>', result.value)
@istest
def underline_can_be_configured_with_convert_underline_option():
with open(test_path("underline.docx"), "rb") as fileobj:
result = mammoth.convert_to_html(fileobj=fileobj, convert_underline=mammoth.underline.element("em"))
assert_equal('<p><strong>The </strong><strong><em>Sunset</em></strong><strong> Tree</strong></p>', result.value)
@istest
def underline_can_be_configured_with_style_mapping():
with open(test_path("underline.docx"), "rb") as fileobj:
result = mammoth.convert_to_html(fileobj=fileobj, style_map="u => em")
assert_equal('<p><strong>The </strong><strong><em>Sunset</em></strong><strong> Tree</strong></p>', result.value)
@istest
def strikethrough_is_converted_to_s_element_by_default():
with open(test_path("strikethrough.docx"), "rb") as fileobj:
result = mammoth.convert_to_html(fileobj=fileobj)
assert_equal("<p><s>Today's Special: Salmon</s> Sold out</p>", result.value)
@istest
def strikethrough_conversion_can_be_configured_with_style_mapping():
with open(test_path("strikethrough.docx"), "rb") as fileobj:
result = mammoth.convert_to_html(fileobj=fileobj, style_map="strike => del")
assert_equal("<p><del>Today's Special: Salmon</del> Sold out</p>", result.value)
@istest
def transform_document_is_applied_to_document_before_conversion():
def transform_document(document):
document.children[0].style_id = "Heading1"
return document
with open(test_path("single-paragraph.docx"), "rb") as fileobj:
result = mammoth.convert_to_html(fileobj=fileobj, transform_document=transform_document)
assert_equal("<h1>Walking on imported air</h1>", result.value)
assert_equal([], result.messages)
@istest
def docx_containing_one_paragraph_can_be_converted_to_markdown():
with open(test_path("single-paragraph.docx"), "rb") as fileobj:
result = mammoth.convert_to_markdown(fileobj=fileobj)
assert_equal("Walking on imported air\n\n", result.value)
assert_equal([], result.messages)
@istest
def can_extract_raw_text():
with open(test_path("simple-list.docx"), "rb") as fileobj:
result = mammoth.extract_raw_text(fileobj=fileobj)
assert_equal([], result.messages)
assert_equal("Apple\n\nBanana\n\n", result.value)
|
