mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Test for file splitting
This commit is contained in:
Kovid Goyal
parent
aadbcf2299
commit
58bed7e3de
@ -158,14 +158,19 @@ class SplitLinkReplacer(object):
|
|||||||
self.replaced = True
|
self.replaced = True
|
||||||
return url
|
return url
|
||||||
|
|
||||||
def split(container, name, loc):
|
def split(container, name, loc_or_xpath, before=True):
|
||||||
|
''' Split the file specified by name at the position specified by loc_or_xpath. '''
|
||||||
|
|
||||||
root = container.parsed(name)
|
root = container.parsed(name)
|
||||||
split_point = node_from_loc(root, loc)
|
if isinstance(loc_or_xpath, type('')):
|
||||||
|
split_point = root.xpath(loc_or_xpath)[0]
|
||||||
|
else:
|
||||||
|
split_point = node_from_loc(root, loc_or_xpath)
|
||||||
if in_table(split_point):
|
if in_table(split_point):
|
||||||
raise ValueError('Cannot split inside tables')
|
raise ValueError('Cannot split inside tables')
|
||||||
if split_point.tag.endswith('}body'):
|
if split_point.tag.endswith('}body'):
|
||||||
raise ValueError('Cannot split on the <body> tag')
|
raise ValueError('Cannot split on the <body> tag')
|
||||||
tree1, tree2 = do_split(split_point, container.log)
|
tree1, tree2 = do_split(split_point, container.log, before=before)
|
||||||
root1, root2 = tree1.getroot(), tree2.getroot()
|
root1, root2 = tree1.getroot(), tree2.getroot()
|
||||||
anchors_in_top = frozenset(root1.xpath('//*/@id')) | frozenset(root1.xpath('//*/@name')) | {''}
|
anchors_in_top = frozenset(root1.xpath('//*/@id')) | frozenset(root1.xpath('//*/@name')) | {''}
|
||||||
anchors_in_bottom = frozenset(root2.xpath('//*/@id')) | frozenset(root2.xpath('//*/@name'))
|
anchors_in_bottom = frozenset(root2.xpath('//*/@id')) | frozenset(root2.xpath('//*/@name'))
|
||||||
|
|||||||
@ -55,6 +55,22 @@ def get_simple_book(fmt='epub'):
|
|||||||
os.remove(x)
|
os.remove(x)
|
||||||
return ans
|
return ans
|
||||||
|
|
||||||
|
def get_split_book(fmt='epub'):
|
||||||
|
cache = get_cache()
|
||||||
|
ans = os.path.join(cache, 'split.'+fmt)
|
||||||
|
src = os.path.join(os.path.dirname(__file__), 'split.html')
|
||||||
|
if needs_recompile(ans, src):
|
||||||
|
x = src.replace('split.html', 'index.html')
|
||||||
|
raw = open(src, 'rb').read().decode('utf-8')
|
||||||
|
try:
|
||||||
|
with open(x, 'wb') as f:
|
||||||
|
f.write(raw.encode('utf-8'))
|
||||||
|
build_book(x, ans, args=['--level1-toc=//h:h2', '--language=en', '--authors=Kovid Goyal',
|
||||||
|
'--cover=' + I('lt.png')])
|
||||||
|
finally:
|
||||||
|
os.remove(x)
|
||||||
|
return ans
|
||||||
|
|
||||||
devnull = DevNull()
|
devnull = DevNull()
|
||||||
|
|
||||||
class BaseTest(unittest.TestCase):
|
class BaseTest(unittest.TestCase):
|
||||||
|
|||||||
@ -8,10 +8,11 @@ __copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
|
|||||||
|
|
||||||
import os, subprocess
|
import os, subprocess
|
||||||
|
|
||||||
from calibre.ebooks.oeb.polish.tests.base import BaseTest, get_simple_book
|
from calibre.ebooks.oeb.polish.tests.base import BaseTest, get_simple_book, get_split_book
|
||||||
|
|
||||||
from calibre.ebooks.oeb.polish.container import get_container as _gc, clone_container, OCF_NS
|
from calibre.ebooks.oeb.polish.container import get_container as _gc, clone_container, OCF_NS
|
||||||
from calibre.ebooks.oeb.polish.replace import rename_files
|
from calibre.ebooks.oeb.polish.replace import rename_files
|
||||||
|
from calibre.ebooks.oeb.polish.split import split
|
||||||
from calibre.utils.filenames import nlinks_file
|
from calibre.utils.filenames import nlinks_file
|
||||||
from calibre.ptempfile import TemporaryFile
|
from calibre.ptempfile import TemporaryFile
|
||||||
|
|
||||||
@ -175,3 +176,15 @@ class ContainerTests(BaseTest):
|
|||||||
self.assertNotIn(name, {x[0] for x in c.spine_names})
|
self.assertNotIn(name, {x[0] for x in c.spine_names})
|
||||||
|
|
||||||
self.check_links(c)
|
self.check_links(c)
|
||||||
|
|
||||||
|
def test_split_file(self):
|
||||||
|
' Test splitting of files '
|
||||||
|
book = get_split_book()
|
||||||
|
c = get_container(book)
|
||||||
|
name = 'index.html'
|
||||||
|
nname = split(c, name, '//*[@id="page2"]')
|
||||||
|
root = c.parsed(nname)
|
||||||
|
troot = c.parsed(name)
|
||||||
|
self.assertEqual(1, len(root.xpath('//*[@id="container"]')), 'Split point was not adjusted')
|
||||||
|
self.assertEqual(0, len(troot.xpath('//*[@id="container"]')), 'Split point was not adjusted')
|
||||||
|
self.check_links(c)
|
||||||
|
|||||||
54
src/calibre/ebooks/oeb/polish/tests/split.html
Normal file
54
src/calibre/ebooks/oeb/polish/tests/split.html
Normal file
@ -0,0 +1,54 @@
|
|||||||
|
<!DOCTYPE html>
|
||||||
|
<html>
|
||||||
|
<head>
|
||||||
|
<title>split</title>
|
||||||
|
<meta http-equiv="content-type" content="text/html; charset=utf-8"/>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<h3 id="page1">Page One</h3>
|
||||||
|
<!--lorem-->
|
||||||
|
<p>Or pursues or desires to obtain pain of itself, because it is pain, but
|
||||||
|
because occasionally circumstances occur in which toil and pain can procure him
|
||||||
|
some great pleasure. To take a trivial example, which of us ever undertakes
|
||||||
|
laborious physical exercise, except to obtain some advantage from it? But who
|
||||||
|
has any right to find fault with a man who chooses to enjoy a pleasure that has
|
||||||
|
no annoying consequences, or one who avoids a pain that produces no resultant
|
||||||
|
pleasure?</p>
|
||||||
|
|
||||||
|
<p>On the other hand, we denounce with righteous indignation and dislike men
|
||||||
|
who are so beguiled and demoralized by the.</p>
|
||||||
|
<!--/lorem-->
|
||||||
|
|
||||||
|
<p>
|
||||||
|
<a href="#page1">Link to page one</a>
|
||||||
|
<a href="#page2">Link to page two</a>
|
||||||
|
<a href="index.html#page1">Link to page one</a>
|
||||||
|
<a href="index.html#page2">Link to page two</a>
|
||||||
|
</p>
|
||||||
|
|
||||||
|
<div id="container">
|
||||||
|
<h3 id="page2">Page Two</h3>
|
||||||
|
<!--lorem-->
|
||||||
|
<p>Same as saying through shrinking from toil and pain. These cases are
|
||||||
|
perfectly simple and easy to distinguish. In a free hour, when our power of
|
||||||
|
choice is untrammelled and when nothing prevents our being able to do what we
|
||||||
|
like best, every pleasure is to be welcomed and every pain avoided.</p>
|
||||||
|
|
||||||
|
<p>But in certain circumstances and owing to the claims of duty or the
|
||||||
|
obligations of business it will frequently occur that pleasures have to be
|
||||||
|
repudiated and annoyances accepted. The wise man therefore always holds in
|
||||||
|
these matters to this principle of selection: he rejects pleasures to secure
|
||||||
|
other greater.</p>
|
||||||
|
<!--/lorem-->
|
||||||
|
|
||||||
|
<p>
|
||||||
|
<a href="#page1">Link to page one</a>
|
||||||
|
<a href="#page2">Link to page two</a>
|
||||||
|
<a href="index.html#page1">Link to page one</a>
|
||||||
|
<a href="index.html#page2">Link to page two</a>
|
||||||
|
</p>
|
||||||
|
|
||||||
|
</div>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
|
|
||||||
Loading…
x
Reference in New Issue
Block a user