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
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
|
#!/usr/bin/env python3
"""epubgen - generate spec-perfect EPUB 3.3 files for testing readers and validators.
Two modes:
normal - a clean, readable EPUB that uses the full feature set
(cover, title page, TOC, landmarks, chapters, index, colophon,
EPUB2 NCX fallback, EPUB3 nav, CSS, metadata refinements).
torture - a technically valid EPUB with deliberately hostile syntax
(bidi overrides, combining chars, numeric char refs, deep nested
markup, unusual-but-valid xml:lang, weird filenames, ...).
Every XML file is re-parsed with xml.etree before zipping, so the output is
guaranteed well-formed. Zero dependencies beyond the Python standard library.
Usage:
python3 epubgen.py [options]
"""
import argparse
import html
import os
import random
import re
import struct
import sys
import uuid
import xml.etree.ElementTree as ET
import zipfile
import zlib
from datetime import datetime, timezone
from urllib.parse import quote
VERSION = "1.0"
HERE = os.path.dirname(os.path.abspath(__file__))
DEFAULT_FILE = os.path.join(HERE, "paragraphs.txt")
NS = 'xmlns="http://www.w3.org/1999/xhtml" xmlns:epub="http://www.idpf.org/2007/ops"'
# Hostile-but-valid Unicode (all fine in XML 1.0 / UTF-8)
COMBINING = "\u0300\u0301\u0308\u030a\u20dd\u20e3"
ZW = "\u200b\u200c\u200d\u200e\u200f"
SPACES = "\u00a0\u2009\u200a\u202f\u3000"
BIDI = "\u202a\u202b\u202d\u202e"
PRIV = "\ue000\ue100\uf8ff"
CJK = "\u6c49\u5b57\u6d4b\u8bd5\u30c6\u30b9\u30c8"
EMOJI = "\U0001f600\U0001f389\U0001f680\U0001f480\U0001f518\U0001f30d"
def esc(s):
"""XML-escape text (& < > and quotes; escaping '>' makes ']]>' impossible)."""
return html.escape(s, quote=True)
def xhtml(title, body, body_type=None, link_css=True):
"""Wrap body content in a spec-compliant XHTML5 document."""
head = f'<head><meta charset="utf-8"/><title>{esc(title)}</title>'
if link_css:
head += '<link rel="stylesheet" type="text/css" href="style.css"/>'
head += '</head>'
btype = f' epub:type="{body_type}"' if body_type else ''
return ('<?xml version="1.0" encoding="UTF-8"?>\n'
f'<html {NS} lang="en" xml:lang="en">{head}<body{btype}>{body}</body></html>')
def first_word(texts, rng):
t = rng.choice(texts)
m = re.search(r"[A-Za-z0-9]+", t)
return m.group(0) if m else "word"
# ---------------------------------------------------------------------------
# lorem ipsum generator
# ---------------------------------------------------------------------------
LOREM_WORDS = ("lorem ipsum dolor sit amet consectetur adipiscing elit sed do "
"eiusmod tempor incididunt ut labore et dolore magna aliqua enim ad "
"minim veniam quis nostrud exercitation ullamco laboris nisi aliquip "
"ex ea commodo consequat duis aute irure in reprehenderit in voluptate "
"velit esse cillum dolore eu fugiat nulla pariatur excepteur sint "
"occaecat cupidatat non proident sunt in culpa qui officia deserunt "
"mollit anim id est laborum").split()
def lorem_sentence(rng, min_w=8, max_w=20):
words = [rng.choice(LOREM_WORDS) for _ in range(rng.randint(min_w, max_w))]
words[0] = words[0].capitalize()
return " ".join(words) + "."
def lorem_paragraph(rng, min_s=3, max_s=7):
return " ".join(lorem_sentence(rng) for _ in range(rng.randint(min_s, max_s)))
def lorem_texts(rng, count):
return [lorem_paragraph(rng) for _ in range(count)]
# ---------------------------------------------------------------------------
# torture helpers
# ---------------------------------------------------------------------------
def torture_text(s, rng):
"""Inject combining marks, zero-width/bidi chars, exotic spaces, CJK/emoji/private-use."""
out = []
for ch in s:
out.append(ch)
if ch.isalnum() and rng.random() < 0.15:
out.append(rng.choice(COMBINING))
r = rng.random()
if r < 0.04:
out.append(rng.choice(ZW))
elif r < 0.05:
out.append(rng.choice(BIDI))
elif r < 0.055:
out.append(rng.choice(PRIV))
elif r < 0.06:
out.append(rng.choice(CJK + EMOJI))
s = "".join(out)
s = "".join(rng.choice(SPACES) if c == " " and rng.random() < 0.4 else c for c in s)
if len(s) > 40 and rng.random() < 0.3:
i = rng.randrange(0, len(s) - 20)
j = rng.randrange(i + 10, min(len(s), i + 60))
s = s[:i] + "\u202e" + s[i:j] + "\u202c" + s[j:]
return s
def torture_entities(s, rng):
"""Replace some chars with numeric character references (post-escaping, skips existing entities)."""
out, i, n = [], 0, len(s)
while i < n:
if s[i] == "&":
j = s.find(";", i)
if j != -1:
out.append(s[i:j + 1])
i = j + 1
continue
ch = s[i]
if (ch.isalnum() or ch == " ") and rng.random() < 0.12:
out.append(f"&#x{ord(ch):04x};")
else:
out.append(ch)
i += 1
return "".join(out)
def torture_para(rng, p, kid):
kind = rng.random()
if kind < 0.18:
body = '<pre xml:space="preserve">\n\t' + p + '\n</pre>'
elif kind < 0.30:
depth = rng.randint(3, 9)
inner = p
for d in range(depth):
inner = f'<span class="t{d}" data-x="{d}">{inner}</span>'
body = f'<p id="p{kid}" dir="auto" xml:lang="{rng.choice(["en-US", "de-AT-1901", "fr", "en"])}">{inner}</p>'
elif kind < 0.36:
body = f'<blockquote><p id="p{kid}">{p}</p></blockquote>'
else:
body = f'<p id="p{kid}">{p}</p>'
return body
def torture_extra(rng):
if rng.random() < 0.5:
cells = "".join(f"<tr><th>k{k}</th><td>{esc(str(rng.random()))}</td></tr>" for k in range(3))
return f"<table><caption>{esc('data')}</caption>{cells}</table>"
safe = "AZaz019()[]{}_"
return "<!--" + "".join(rng.choice(safe) for _ in range(rng.randint(10, 30))) + "-->"
# ---------------------------------------------------------------------------
# document builders
# ---------------------------------------------------------------------------
def container_xml():
return ('<?xml version="1.0" encoding="UTF-8"?>\n'
'<container version="1.0" xmlns="urn:oasis:names:tc:opendocument:xmlns:container">'
'<rootfiles><rootfile full-path="OEBPS/content.opf" media-type="application/oebps-package+xml"/>'
'</rootfiles></container>')
def cover_xhtml():
body = ('<section epub:type="cover">'
'<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" '
'version="1.1" width="100%" height="100%" viewBox="0 0 600 800">'
'<image width="600" height="800" xlink:href="cover.png"/></svg>'
'</section>')
return xhtml("Cover", body, link_css=False)
def title_xhtml(title, author):
body = ('<section epub:type="titlepage">'
f'<h1 class="book-title">{esc(title)}</h1>'
f'<p class="byline">{esc(author)}</p>'
'<p class="imprint">Test Press</p>'
'</section>')
return xhtml(title, body)
def chapter_xhtml(mode, rng, idx, total, npar, ctitle, texts):
ps = []
for k in range(1, npar + 1):
raw = rng.choice(texts)
if mode == "torture":
raw = torture_text(raw, rng)
p = esc(raw)
if mode == "torture":
p = torture_entities(p, rng)
ps.append(torture_para(rng, p, k))
else:
ps.append(f'<p id="p{k}">{p}</p>')
body = "\n".join(ps)
if mode == "torture":
body += "\n" + torture_extra(rng)
section = (f'<section epub:type="chapter"><h1>{esc(ctitle)}</h1>{body}'
f'<footer>{esc("Chapter %d of %d" % (idx, total))}</footer></section>')
return xhtml(ctitle, section, body_type="bodymatter chapter")
def nav_xhtml(first_href, chapters, back_hrefs):
def li(href, label):
return f'<li><a href="{href}">{esc(label)}</a></li>'
fl = "\n".join(li(h, l) for h, l in
[("cover.xhtml", "Cover"), ("title.xhtml", "Title page"), ("nav.xhtml", "Contents")])
cl = "\n".join(f'<li><a href="{h}">{esc(t)}</a></li>' for _, h, t in chapters)
bl = "\n".join(li(h, l) for h, l in back_hrefs)
toc = ('<nav epub:type="toc" id="toc">'
f'<h1>{esc("Table of Contents")}</h1><ol>'
f'<li><span>Front matter</span><ol>{fl}</ol></li>'
f'<li><span>Chapters</span><ol>{cl}</ol></li>'
f'<li><span>Back matter</span><ol>{bl}</ol></li>'
'</ol></nav>')
lms = "".join(f'<li><a href="{h}" epub:type="{t}">{esc(l)}</a></li>'
for h, t, l in [("cover.xhtml", "cover", "Cover"),
("title.xhtml", "titlepage", "Title page"),
("nav.xhtml", "toc", "Table of contents"),
(first_href, "bodymatter", "Start"),
("index.xhtml", "index", "Index")])
landmarks = f'<nav epub:type="landmarks" id="landmarks"><h2>{esc("Guide")}</h2><ol>{lms}</ol></nav>'
return xhtml("Contents", toc + landmarks, body_type="frontmatter")
def ncx_xml(mode, rng, title, chapters, uid):
po = [0]
def point(pid, href, label, children=""):
po[0] += 1
return (f'<navPoint id="{pid}" playOrder="{po[0]}"><navLabel><text>{esc(label)}</text></navLabel>'
f'<content src="{href}"/>{children}</navPoint>')
cover = point("npx", "cover.xhtml", "Cover")
cps = "\n".join(point(f"np{i}", h, t) for i, (_, h, t) in enumerate(chapters))
if mode == "torture":
cps = point("npWrap", chapters[0][1], rng.choice(["Chapters", "Contents", "Edição"]), cps)
navmap = f"<navMap>{cover}{cps}</navMap>"
head = (f'<head><meta name="dtb:uid" content="{uid}"/>'
'<meta name="dtb:depth" content="1"/>'
'<meta name="dtb:totalPageCount" content="0"/>'
'<meta name="dtb:maxPageNumber" content="0"/></head>')
doctype = ''
if mode == "normal":
doctype = '<!DOCTYPE ncx PUBLIC "-//NISO//DTD ncx 2005-1//EN" "http://www.dtd-helper.com/ncx/ncx-2005-1.dtd">\n'
return ('<?xml version="1.0" encoding="UTF-8"?>\n' + doctype +
'<ncx xmlns="http://www.daisy.org/z3986/2005/ncx/" version="2005-1" xml:lang="en">'
f'{head}<docTitle><text>{esc(title)}</text></docTitle>{navmap}</ncx>')
def opf_xml(mode, rng, title, author, uid, now, chapters, ncx):
meta = [
f'<dc:identifier id="pub-id">{uid}</dc:identifier>',
f'<dc:title id="t1">{esc(title)}</dc:title>',
'<meta refines="#t1" property="title-type">main</meta>',
f'<dc:creator id="c1">{esc(author)}</dc:creator>',
'<meta refines="#c1" property="role" scheme="marc:relators">aut</meta>',
'<dc:language>en</dc:language>',
'<meta property="dcterms:conformsTo">EPUB 3.3</meta>',
'<dc:publisher>Test Press</dc:publisher>',
f'<dc:date>{now}</dc:date>',
f'<meta property="dcterms:modified">{now}</meta>',
'<dc:rights>Public domain test text.</dc:rights>',
]
if mode == "torture":
meta += [
f'<dc:creator id="c2">{esc(rng.choice(["A. Nonymous", "Écrivain", "テスト作者"]))}</dc:creator>',
'<meta refines="#c2" property="role" scheme="marc:relators">edt</meta>',
'<meta property="schema:accessMode">textual</meta>',
'<meta property="schema:accessibilityFeature">readingOrder</meta>',
'<dc:subject>testing, books, epub, torture</dc:subject>',
f'<dc:description>{esc(torture_text("A book for testing parsers.", rng))}</dc:description>',
]
metadata = f'<metadata xmlns:dc="http://purl.org/dc/elements/1.1/">{"".join(meta)}</metadata>'
manifest = [
'<item id="cover" href="cover.png" media-type="image/png" properties="cover-image"/>',
'<item id="cover-page" href="cover.xhtml" media-type="application/xhtml+xml" properties="svg"/>',
'<item id="title-page" href="title.xhtml" media-type="application/xhtml+xml"/>',
'<item id="nav" href="nav.xhtml" media-type="application/xhtml+xml" properties="nav"/>',
'<item id="css" href="style.css" media-type="text/css"/>',
'<item id="index" href="index.xhtml" media-type="application/xhtml+xml"/>',
'<item id="colophon" href="colophon.xhtml" media-type="application/xhtml+xml"/>',
]
if ncx:
manifest.append('<item id="ncx" href="toc.ncx" media-type="application/x-dtbncx+xml"/>')
for i, (_, h, _) in enumerate(chapters):
manifest.append(f'<item id="chap{i}" href="{h}" media-type="application/xhtml+xml"/>')
manifest_xml = f'<manifest>{"".join(manifest)}</manifest>'
spine = ['<itemref idref="cover-page"/>', '<itemref idref="title-page"/>', '<itemref idref="nav"/>']
for i in range(len(chapters)):
spine.append(f'<itemref idref="chap{i}" linear="yes"/>')
spine.append('<itemref idref="index" linear="yes"/>')
spine.append('<itemref idref="colophon" linear="no"/>')
spine_xml = f'<spine>{"".join(spine)}</spine>'
pkg_lang = "zh-Hant-TW-u-ca-gregory" if mode == "torture" else "en"
pkg_dir = "rtl" if mode == "torture" else "ltr"
return ('<?xml version="1.0" encoding="UTF-8"?>\n'
'<package xmlns="http://www.idpf.org/2007/opf" version="3.0" unique-identifier="pub-id" '
f'xml:lang="{pkg_lang}" dir="{pkg_dir}">{metadata}{manifest_xml}{spine_xml}</package>')
def index_xhtml(mode, rng, chapters, words):
entries = []
for i, (_, h, _) in enumerate(chapters):
entries.append(f'<li><a href="{h}#p1">{esc(words[i])}</a><span>{i + 1}</span></li>')
if mode == "torture":
entries.append(f'<li>{esc("index of indexes")} - see <a href="{chapters[0][1]}#p1">{esc(words[0])}</a></li>')
body = f'<section epub:type="index"><h1>{esc("Index")}</h1><ul class="index">{"\n".join(entries)}</ul></section>'
return xhtml("Index", body, body_type="backmatter")
def colophon_xhtml(mode, uid, now):
text = ("This ebook was generated by epubgen for testing EPUB readers and validators. "
f"Identifier: {uid}. Generated: {now}. Mode: {mode}.")
body = f'<section epub:type="colophon"><h1>{esc("Colophon")}</h1><p>{esc(text)}</p></section>'
return xhtml("Colophon", body, body_type="backmatter")
def css(mode):
base = (
'body{margin:5% auto;max-width:34em;font-family:Georgia,"Times New Roman",serif;line-height:1.5}\n'
'h1{font-size:1.8em;line-height:1.2}\n'
'h2{font-size:1.3em}\n'
'p{text-indent:1.2em;margin:0.4em 0}\n'
'p:first-of-type{text-indent:0}\n'
'blockquote{font-style:italic;border-left:3px solid #999;margin:1em 2em;padding-left:1em}\n'
'footer{font-size:0.85em;color:#555;text-align:center;margin-top:2em}\n'
'.index li{list-style:none;margin:0.2em 0}\n'
'.index li span{color:#999;margin-left:0.5em}\n'
'pre{white-space:pre-wrap;font-family:monospace}\n'
)
if mode == "torture":
base = ('@import url("http://example.invalid/legacy.css");\n' + base +
'p:first-of-type{text-indent:0!important}\n'
'pre[lang]{white-space:pre!important}\n'
'@media screen and (min-width:1px){h1{-webkit-hyphens:auto;-ms-hyphens:auto;hyphens:auto}}\n'
'h1::before{content:"\\00a7\\2002"}\n'
'table{border-collapse:collapse}\n'
'td,th{border:1px solid #ccc;padding:0.2em 0.5em}\n'
'@page{margin:5%}\n')
return base
def make_cover_png(w=600, h=800):
rows = []
for y in range(h):
row = bytearray(b"\x00")
for x in range(w):
row += bytes((min(255, int(90 + 165 * x / w)),
min(255, int(60 + 120 * y / h)),
min(255, int(150 + 60 * (x + y) / (w + h)))))
rows.append(bytes(row))
raw = b"".join(rows)
def chunk(tag, data):
return (struct.pack(">I", len(data)) + tag + data +
struct.pack(">I", zlib.crc32(tag + data) & 0xFFFFFFFF))
ihdr = struct.pack(">IIBBBBB", w, h, 8, 2, 0, 0, 0)
return (b"\x89PNG\r\n\x1a\n" + chunk(b"IHDR", ihdr) +
chunk(b"IDAT", zlib.compress(raw, 9)) + chunk(b"IEND", b""))
# ---------------------------------------------------------------------------
# orchestration
# ---------------------------------------------------------------------------
def check_xml(label, data):
try:
ET.fromstring(data)
except Exception as ex:
print("ERROR: %s is not well-formed XML: %s" % (label, ex), file=sys.stderr)
sys.exit(1)
def build_zip(out, files):
os.makedirs(os.path.dirname(os.path.abspath(out)) or ".", exist_ok=True)
with zipfile.ZipFile(out, "w") as zf:
for name, data in files:
zi = zipfile.ZipInfo(name, date_time=(1980, 1, 1, 0, 0, 0))
zi.compress_type = zipfile.ZIP_STORED if name == "mimetype" else zipfile.ZIP_DEFLATED
zi.external_attr = 0o644 << 16
zf.writestr(zi, data)
with zipfile.ZipFile(out) as zf:
names = zf.namelist()
if (not names or names[0] != "mimetype" or
zf.getinfo("mimetype").compress_type != zipfile.ZIP_STORED or
zf.read("mimetype") != b"application/epub+zip"):
print("ERROR: mimetype entry violates the OCF spec", file=sys.stderr)
sys.exit(1)
for i in zf.infolist():
print(" %-42s %8d bytes %s" % (
i.filename, i.file_size,
"STORED" if i.compress_type == zipfile.ZIP_STORED else "DEFLATED"))
def load_texts(path, lorem, rng, count):
if lorem:
return lorem_texts(rng, count)
for p in (path, DEFAULT_FILE):
if p and os.path.exists(p):
with open(p, encoding="utf-8") as f:
lines = [ln.strip() for ln in f if ln.strip()]
if lines:
return lines
print("WARNING: no paragraph text file found; generating lorem ipsum instead",
file=sys.stderr)
return lorem_texts(rng, count)
def generate(out, rng, texts, title, author, mode, nchap, npar, ncx, seed):
now = datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ")
uid = "urn:uuid:%s" % uuid.uuid4()
if mode == "torture":
title = torture_text(title, rng)
chapters, words = [], []
for i in range(1, nchap + 1):
fname = "chap %02d & tale.xhtml" % i if mode == "torture" else "chap%02d.xhtml" % i
href = quote(fname)
ctitle = "Chapter %d" % i if mode == "normal" else torture_text("Chapter %d" % i, rng)
chapters.append((fname, href, ctitle))
words.append(first_word(texts, rng))
first_href = chapters[0][1]
back_hrefs = [("index.xhtml", "Index"), ("colophon.xhtml", "Colophon")]
docs = {
"META-INF/container.xml": container_xml(),
"OEBPS/content.opf": opf_xml(mode, rng, title, author, uid, now, chapters, ncx),
"OEBPS/nav.xhtml": nav_xhtml(first_href, chapters, back_hrefs),
"OEBPS/style.css": css(mode),
"OEBPS/cover.xhtml": cover_xhtml(),
"OEBPS/title.xhtml": title_xhtml(title, author),
"OEBPS/index.xhtml": index_xhtml(mode, rng, chapters, words),
"OEBPS/colophon.xhtml": colophon_xhtml(mode, uid, now),
}
if ncx:
docs["OEBPS/toc.ncx"] = ncx_xml(mode, rng, title, chapters, uid)
for i, (fname, href, ctitle) in enumerate(chapters, 1):
docs["OEBPS/" + fname] = chapter_xhtml(mode, rng, i, nchap, npar, ctitle, texts)
for label, data in docs.items():
if label.endswith(".xml") or label.endswith((".opf", ".ncx", ".xhtml")):
check_xml(label, data)
files = [("mimetype", b"application/epub+zip")]
files += [("META-INF/container.xml", docs["META-INF/container.xml"])]
files += [(name, data) for name, data in docs.items() if name.startswith("OEBPS/")]
files += [("OEBPS/cover.png", make_cover_png())]
build_zip(out, files)
print("OK: %s (%d chapters x %d paragraphs, mode=%s, seed=%s)" %
(out, nchap, npar, mode, seed if seed is not None else "random"))
def resolve_out_paths(out, mode):
if mode != "both":
return [out or f"{mode}.epub"]
stem = out[:-5] if out and out.lower().endswith(".epub") else (out or "")
base = f"{stem}." if stem else ""
return [f"{base}normal.epub", f"{base}torture.epub"]
def main():
ap = argparse.ArgumentParser(
description="Generate spec-perfect EPUB 3.3 files for testing readers and validators.",
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
ap.add_argument("-o", "--out", default=None,
help="output .epub path (single mode) or name prefix (both mode)")
ap.add_argument("-m", "--mode", choices=["normal", "torture", "both"], default="both",
help="normal = clean; torture = hostile-but-valid; both = one of each (default)")
ap.add_argument("-c", "--chapters", type=int, default=5, help="number of chapters")
ap.add_argument("-p", "--paragraphs", type=int, default=10, help="paragraphs per chapter")
ap.add_argument("-t", "--title", default="The Testing EPUB")
ap.add_argument("-a", "--author", default="Test Author")
ap.add_argument("--seed", type=int, default=None, help="RNG seed for reproducibility")
ap.add_argument("--texts", default=None, help="file with one paragraph per line")
ap.add_argument("--lorem", action="store_true",
help="generate lorem ipsum text instead of reading a file "
"(default source: paragraphs.txt)")
ap.add_argument("--no-ncx", action="store_true", help="omit the EPUB2 NCX fallback")
ap.add_argument("-v", "--version", action="version", version="epubgen %s" % VERSION)
args = ap.parse_args()
if args.chapters < 1 or args.paragraphs < 1:
print("ERROR: chapters and paragraphs must be >= 1", file=sys.stderr)
sys.exit(1)
rng = random.Random(args.seed)
texts = load_texts(args.texts, args.lorem, rng, args.chapters * args.paragraphs)
ncx = not args.no_ncx
modes = ["normal", "torture"] if args.mode == "both" else [args.mode]
for mode, path in zip(modes, resolve_out_paths(args.out, args.mode)):
generate(path, rng, texts, args.title, args.author,
mode, args.chapters, args.paragraphs, ncx, args.seed)
if __name__ == "__main__":
main()
|
