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
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
|
import io
import logging
import os
import zipfile
import six
if six.PY3:
from pathlib import Path
else:
from pathlib2 import Path
import pytest
import ebooklib
from ebooklib import epub
from ebooklib.plugins import booktype, sourcecode, standard
from ebooklib.utils import parse_html_string, parse_string
logger = logging.getLogger(__name__)
@pytest.mark.usefixtures("session_temp_dir")
class TestEbook:
def _create_basic_book(self, ncx=True):
book = epub.EpubBook()
book.set_identifier("test123456")
book.set_title("Test book")
book.set_language("en")
book.add_author("Test Author")
book.set_cover("image.jpg", b"fake image data")
doc1 = epub.EpubHtml(uid="chap_1", file_name="test.xhtml")
doc1.set_content(
"""<body><h1>Title</h1><p>lorum ipsum.<a epub:type="noteref" href="#fn01">1</a></p>
<aside epub:type="footnote" id="fn01">
<p>These have been corrected in this EPUB3 edition.</p>
</aside>
</body>"""
)
doc2 = epub.EpubHtml(uid="chap_2", file_name="test2.xhtml")
doc2.set_content(
""""<body><h1>Title2</h1><p>lorum ipsum.<a epub:type="noteref" href="#en01">1</a></p>
<aside epub:type="endnote">
<p>These have been corrected in this EPUB3 edition.</p>
</aside>
</body>"""
)
css1 = epub.EpubItem(
uid="style",
file_name="style.css",
media_type="text/css",
content="BODY { color: black; }",
)
book.add_item(css1)
book.add_item(doc1)
book.add_item(doc2)
book.toc = (
doc1,
(epub.Section("Section"), (doc2,)),
)
if ncx:
book.add_item(epub.EpubNcx())
book.add_item(epub.EpubNav())
book.spine = ["nav", doc1, doc2]
return book
def _test_basic_book(self, book):
assert len(book.toc) == 2
assert type(book.toc[0]) is epub.Link
assert type(book.toc[1]) is tuple
assert type(book.toc[1][0]) is epub.Section
assert type(book.toc[1][1]) is list
assert book.spine == [("nav", "yes"), ("chap_1", "yes"), ("chap_2", "yes")]
assert book.get_item_with_id("chap_1") is not None
assert book.get_item_with_id("style") is not None
assert book.get_item_with_href("test.xhtml") is not None
assert book.get_item_with_href("style.css") is not None
assert len(list(book.get_items_of_type(ebooklib.ITEM_DOCUMENT))) == 4
assert len(list(book.get_items_of_type(ebooklib.ITEM_NAVIGATION))) == 1
assert len(list(book.get_items_of_type(ebooklib.ITEM_STYLE))) == 1
assert len(list(book.get_items_of_type(ebooklib.ITEM_COVER))) == 1
assert book.get_metadata("DC", "title") == [("Test book", {})]
assert book.get_metadata("DC", "identifier") == [("test123456", {"id": "id"})]
assert book.get_metadata("DC", "language") == [("en", {})]
def test_basic_bytes(self):
book = self._create_basic_book()
# Write to
f = io.BytesIO()
epub.write_epub(f, book, {})
f.seek(0)
self._test_basic_book(epub.read_epub(f))
def test_basic_file(self, session_temp_dir):
book = self._create_basic_book()
epub.write_epub(os.path.join(str(session_temp_dir), "test_basic.epub"), book, {})
self._test_basic_book(epub.read_epub(os.path.join(str(session_temp_dir), "test_basic.epub")))
def test_basic_read_options(self):
book = self._create_basic_book()
book.toc = []
# Write to
f = io.BytesIO()
epub.write_epub(f, book)
f.seek(0)
bk = epub.read_epub(f, {"ignore_ncx": False})
assert type(bk.toc) is epub.Link
bk = epub.read_epub(f, {"ignore_ncx": True})
assert len(bk.toc) == 0
def test_basic_file_raise_exceptions(self):
book = self._create_basic_book()
class FakeFile:
def write(self, content):
raise OSError
def writestr(self, filename, content, compress_type):
raise OSError
def close(self):
pass
def tell(self):
return 0
def seek(self, offset, whence=0):
return 0
with pytest.raises(IOError):
epub.write_epub(FakeFile(), book, {"raise_exceptions": True})
assert epub.write_epub(FakeFile(), book, {"raise_exceptions": False}) is False
def test_basic_file_save_options(self, session_temp_dir):
book = self._create_basic_book()
book.guide = [{"href": "test.xhtml", "title": "Introduction", "type": "bodymatter"}]
book.set_direction("ltr")
epub.write_epub(
os.path.join(str(session_temp_dir), "test_basic_on.epub"),
book,
{
"epub2_guide": True,
"epub3_landmark": True,
"epub3_pages": True,
"landmark_title": "My Guide",
"pages_title": "My Pages",
"spine_direction": True,
"package_direction": True,
"play_order": {"enabled": True, "start_from": 1},
},
)
epub.write_epub(
os.path.join(str(session_temp_dir), "test_basic_off.epub"),
book,
{
"epub2_guide": False,
"epub3_landmark": False,
"epub3_pages": False,
"spine_direction": False,
"package_direction": False,
},
)
# Everything turned off
zf_off = zipfile.ZipFile(
os.path.join(str(session_temp_dir), "test_basic_off.epub"),
"r",
compression=zipfile.ZIP_DEFLATED,
allowZip64=True,
)
content_off = parse_string(zf_off.read("EPUB/content.opf"))
nav_off = parse_string(zf_off.read("EPUB/nav.xhtml"))
toc_off = parse_string(zf_off.read("EPUB/toc.ncx"))
assert content_off.find("{%s}%s" % (epub.NAMESPACES["OPF"], "guide")) is None # noqa
landmarks = nav_off.find(
'.//{%s}nav[@{%s}type="landmarks"]' % (epub.NAMESPACES["XHTML"], epub.NAMESPACES["EPUB"]) # noqa
)
assert landmarks is None
page_list = nav_off.find(
'.//{%s}nav[@{%s}type="page-list"]' % (epub.NAMESPACES["XHTML"], epub.NAMESPACES["EPUB"]) # noqa
)
assert page_list is None
assert content_off.find(".//{%s}spine" % epub.NAMESPACES["OPF"]).get("page-progression-direction") is None # noqa
assert content_off.getroot().get("dir") is None
nav_points = toc_off.findall(".//{%s}navPoint" % epub.NAMESPACES["DAISY"]) # noqa
assert len(nav_points) > 0
for _n, nav_point in enumerate(nav_points, 1):
assert "playOrder" not in nav_point.attrib
zf_off.close()
# Everything turned onn
zf_on = zipfile.ZipFile(
os.path.join(str(session_temp_dir), "test_basic_on.epub"),
"r",
compression=zipfile.ZIP_DEFLATED,
allowZip64=True,
)
content_on = parse_string(zf_on.read("EPUB/content.opf"))
nav_on = parse_string(zf_on.read("EPUB/nav.xhtml"))
toc_on = parse_string(zf_on.read("EPUB/toc.ncx"))
guide = content_on.find("{%s}%s" % (epub.NAMESPACES["OPF"], "guide")) # noqa
references = list(guide)
print("\n\n\n\n\n", zf_on.read("EPUB/nav.xhtml"), "\n\n\n\n\n")
assert guide is not None
assert len(references) == 1
assert references[0] is not None
assert references[0].get("href") == "test.xhtml"
assert references[0].get("title") == "Introduction"
assert references[0].get("type") == "bodymatter"
landmarks = nav_on.find(
'.//{%s}nav[@{%s}type="landmarks"]' % (epub.NAMESPACES["XHTML"], epub.NAMESPACES["EPUB"]) # noqa
)
assert landmarks is not None
assert landmarks.find(".//{%s}h2" % epub.NAMESPACES["XHTML"]).text == "My Guide" # noqa
page_list = nav_on.find(
'.//{%s}nav[@{%s}type="page-list"]' % (epub.NAMESPACES["XHTML"], epub.NAMESPACES["EPUB"]) # noqa
)
assert page_list is not None
assert page_list.find(".//{%s}h2" % epub.NAMESPACES["XHTML"]).text == "My Pages" # noqa
assert (
page_list.find(".//{%s}ol" % epub.NAMESPACES["XHTML"]) # noqa
.find(".//{%s}li" % epub.NAMESPACES["XHTML"]) # noqa
.find(".//{%s}a" % epub.NAMESPACES["XHTML"]) # noqa
.get("href")
== "test.xhtml#fn01"
)
assert (
page_list.find(".//{%s}ol" % epub.NAMESPACES["XHTML"]) # noqa
.find(".//{%s}li" % epub.NAMESPACES["XHTML"]) # noqa
.find(".//{%s}a" % epub.NAMESPACES["XHTML"]) # noqa
.text
== "fn01"
)
assert content_on.find(".//{%s}spine" % epub.NAMESPACES["OPF"]).get("page-progression-direction") == "ltr" # noqa
assert content_on.getroot().get("dir") == "ltr"
nav_points = toc_on.findall(".//{%s}navPoint" % epub.NAMESPACES["DAISY"]) # noqa
assert len(nav_points) > 0
for n, nav_point in enumerate(nav_points, 1):
assert "playOrder" in nav_point.attrib
assert nav_point.get("playOrder") == str(n)
zf_on.close()
def test_syntax_plugin(self):
book = self._create_basic_book()
doc1 = epub.EpubHtml(uid="chap_syntax", file_name="syntax.xhtml")
doc1.set_content(
"<body><h1>Title</h1><p>Wrong<p>Correct <a href='document.xhtml'"
" onclick='javascript:something();'>link</a></p></body>"
)
book.add_item(doc1)
# create epub file
f = io.BytesIO()
epub.write_epub(f, book, {"plugins": [standard.SyntaxPlugin()]})
f.seek(0)
book2 = epub.read_epub(f)
chapter1 = book2.get_item_with_id("chap_syntax")
html_tree = parse_html_string(chapter1.get_content())
body = html_tree.find("body")
link = body.xpath(".//a")
assert len(link) == 1
# Make sure plugin erases unwanted attributes
assert link[0].attrib.get("onclick") is None
def test_booktype_plugin(self):
book = self._create_basic_book()
doc1 = epub.EpubHtml(uid="chap_syntax", file_name="syntax.xhtml")
doc1.set_content(
"""<body><h1>Title</h1><p>Wrong<p>Correct <a name="test01" href="../test01" """
""">link</a><a name="test02"href="test02#something">test 02 link</a></p>"""
"""<p><span id="InsertNoteID_1_marker1" class="InsertNoteMarker"><sup><a href="#InsertNoteID_1">"""
"""1</a></sup>"""
"""</span></p><p><ol id="InsertNote_NoteList"><li id="InsertNoteID_1">prvi footnote """
"""<span id="InsertNoteID_1_LinkBacks"><sup>"""
"""<a href="#InsertNoteID_1_marker1">^</a></sup></span></li>"""
"""</ol></p>"""
"""</body>"""
)
book.add_item(doc1)
# create epub file
f = io.BytesIO()
epub.write_epub(
f,
book,
{
"plugins": [
booktype.BooktypeLinks(book),
booktype.BooktypeFootnotes(book),
]
},
)
f.seek(0)
book2 = epub.read_epub(f)
chapter1 = book2.get_item_with_id("chap_syntax")
html_tree = parse_html_string(chapter1.get_content())
body = html_tree.find("body")
link01 = body.xpath(".//a[@id='test01']")[0]
link02 = body.xpath(".//a[@id='test02']")[0]
assert link01.attrib.get("href") == "../test01.xhtml"
assert link02.attrib.get("href") == "test02.xhtml#something"
link_noteref = body.xpath(".//a[@href='#InsertNoteID_1']")[0]
assert link_noteref.attrib.get("href") == "#InsertNoteID_1"
assert link_noteref.text == "1"
aside = body.xpath(".//aside[@id='InsertNoteID_1']")[0]
assert aside.find("p").text == "prvi footnote "
def test_sourcecode_plugin(self):
book = self._create_basic_book()
doc1 = epub.EpubHtml(uid="chap_syntax", file_name="syntax.xhtml")
doc1.set_content(
"<body><h1>Title</h1><p>Wrong</p><pre class='source-python'>print('Hello, world!')</pre></body>"
)
book.add_item(doc1)
# create epub file
f = io.BytesIO()
epub.write_epub(f, book, {"plugins": [sourcecode.SourceHighlighter()]})
f.seek(0)
book2 = epub.read_epub(f)
chapter1 = book2.get_item_with_id("chap_syntax")
html_tree = parse_html_string(chapter1.get_content())
body = html_tree.find("body")
highlight_div = body.xpath(".//div[@class='highlight']")
assert len(highlight_div) == 1
def _test_metadata(self, book):
assert book.get_metadata("DC", "subject") == [("Fiction", None)]
assert book.get_metadata("DC", "contributor") == [("Editor", {"role": "edt"})]
assert book.get_metadata(None, "meta") == [
("", {"name": "cover", "content": "cover-img"}),
("", {"name": "key", "content": "value"}),
("", {"name": "key2", "content": "value2"}),
]
def test_epubbook_add_metadata(self):
book = self._create_basic_book()
book.add_metadata("DC", "subject", "Fiction")
book.add_metadata("DC", "contributor", "Editor", {"role": "edt"})
book.add_metadata(None, "meta", "", {"name": "key", "content": "value"})
book.add_metadata(None, "meta", "", {"name": "key2", "content": "value2"})
self._test_metadata(book)
def _test_epubbook(self, name):
# TODO:
# - add other roles here besides creator
book = epub.read_epub(name)
assert book.get_metadata("DC", "identifier") == [("sample123456", {"id": "id"})]
assert book.uid == "sample123456"
assert book.get_metadata("DC", "title") == [("Sample book", {})]
assert book.get_metadata("DC", "language") == [("en", {})]
assert book.language == "en"
assert book.get_metadata("DC", "creator") == [("Aleksandar Erkalovic", {"id": "creator"})]
assert len(list(book.get_items())) == 6
def test_epubbook_read_epub_as_filepath(self):
if six.PY2:
self._test_epubbook(os.path.join(os.path.dirname(__file__), "resources", "test01.epub"))
else:
self._test_epubbook(Path(__file__).parent / "resources" / "test01.epub")
def test_epubbook_read_epub_as_string(self):
self._test_epubbook(os.path.join(os.path.dirname(__file__), "resources", "test01.epub"))
def test_epubbook_read_epub_as_bytes(self):
self._test_epubbook(io.BytesIO((Path(__file__).parent / "resources" / "test01.epub").open("rb").read()))
|
