def _test_resource(class_, basename, check, **kwargs):
"""Common code for testing the HTML and CSS classes."""
absolute_filename = resource_filename(basename)
absolute_path = Path(absolute_filename)
url = path2url(absolute_filename)
check(class_(absolute_filename, **kwargs))
check(class_(absolute_path, **kwargs))
check(class_(guess=absolute_filename, **kwargs))
check(class_(guess=absolute_path, **kwargs))
check(class_(filename=absolute_filename, **kwargs))
check(class_(filename=absolute_path, **kwargs))
check(class_(url, **kwargs))
check(class_(guess=url, **kwargs))
url = path2url(absolute_filename.encode('utf-8'))
check(class_(url=url, **kwargs))
with open(absolute_filename, 'rb') as fd:
check(class_(fd, **kwargs))
with open(absolute_filename, 'rb') as fd:
check(class_(guess=fd, **kwargs))
with open(absolute_filename, 'rb') as fd:
check(class_(file_obj=fd, **kwargs))
with open(absolute_filename, 'rb') as fd:
content = fd.read()
py.path.local(os.path.dirname(__file__)).chdir()
relative_filename = os.path.join('resources', basename)
relative_path = Path(relative_filename)
check(class_(relative_filename, **kwargs))
check(class_(relative_path, **kwargs))
kwargs.pop('base_url', None)
check(class_(string=content, base_url=relative_filename, **kwargs))
encoding = kwargs.get('encoding') or 'utf8'
check(class_(string=content.decode(encoding), # unicode
base_url=relative_filename, **kwargs))
with pytest.raises(TypeError):
class_(filename='foo', url='bar')
def add_css(self, font_config):
css_url = urls.path2url(self.design)
self.html.head.clear()
css_tag = BeautifulSoup(
'<title>{}</title><link rel="stylesheet" \
href="{}" type="text/css">'.format(self.title, css_url),
'html5lib')
self.html.head.insert(0, css_tag)
def test_embedded_files_attachments(tmpdir):
absolute_tmp_file = tmpdir.join('some_file.txt').strpath
adata = b'12345678'
with open(absolute_tmp_file, 'wb') as afile:
afile.write(adata)
absolute_url = path2url(absolute_tmp_file)
assert absolute_url.startswith('file://')
relative_tmp_file = tmpdir.join('äöü.txt').strpath
rdata = b'abcdefgh'
with open(relative_tmp_file, 'wb') as rfile:
rfile.write(rdata)
pdf = FakeHTML(
string='''
<title>Test document</title>
<meta charset="utf-8">
<link
rel="attachment"
title="some file attachment äöü"
href="data:,hi%20there">
<link rel="attachment" href="{0}">
<link rel="attachment" href="{1}">
<h1>Heading 1</h1>
<h2>Heading 2</h2>
'''.format(absolute_url, os.path.basename(relative_tmp_file)),
base_url=tmpdir.strpath,
).write_pdf(
attachments=[
Attachment('data:,oob attachment', description='Hello'),
'data:,raw URL',
io.BytesIO(b'file like obj')
]
)
assert (
'<{}>'.format(hashlib.md5(b'hi there').hexdigest()).encode('ascii')
in pdf)
assert b'/F ()' in pdf
assert b'/UF (attachment.bin)' in pdf
name = BOM_UTF16_BE + 'some file attachment äöü'.encode('utf-16-be')
assert b'/Desc <' + name.hex().encode('ascii') + b'>' in pdf
assert hashlib.md5(adata).hexdigest().encode('ascii') in pdf
assert os.path.basename(absolute_tmp_file).encode('ascii') in pdf
assert hashlib.md5(rdata).hexdigest().encode('ascii') in pdf
name = BOM_UTF16_BE + 'some file attachment äöü'.encode('utf-16-be')
assert b'/Desc <' + name.hex().encode('ascii') + b'>' in pdf
assert hashlib.md5(b'oob attachment').hexdigest().encode('ascii') in pdf
assert b'/Desc (Hello)' in pdf
assert hashlib.md5(b'raw URL').hexdigest().encode('ascii') in pdf
assert hashlib.md5(b'file like obj').hexdigest().encode('ascii') in pdf
assert b'/EmbeddedFiles' in pdf
assert b'/Outlines' in pdf
def on_post_page(self, output_content, page, config, **kwargs):
try:
abs_dest_path = page.file.abs_dest_path
src_path = page.file.src_path
except AttributeError:
abs_dest_path = page.abs_output_path
src_path = page.input_path
path = os.path.dirname(abs_dest_path)
os.makedirs(path, exist_ok=True)
filename = os.path.splitext(os.path.basename(src_path))[0]
base_url = urls.path2url(os.path.join(path, filename))
pdf_url = self.generator.add_article(output_content, page, base_url)
if pdf_url:
output_content = modify_html(output_content, pdf_url)
return output_content
def add_head(self):
lines = ['<title>{}</title>'.format(self.title)]
for key, val in (
("author", self.config['author'] or self.mkdconfig['site_author']),
("description", self.mkdconfig['site_description']),
):
if val:
lines.append('<meta name="{}" content="{}">'.format(key, val))
for css in (self.design, self.design_extra):
if css:
css_tmpl = '<link rel="stylesheet" href="{}" type="text/css">'
lines.append(css_tmpl.format(urls.path2url(css)))
head = BeautifulSoup('\n'.join(lines), 'html5lib')
self.html.head.clear()
self.html.head.insert(0, head)
def _soup_from_content(self, content: str, page):
soup = BeautifulSoup(content, 'html.parser')
try:
abs_dest_path = page.file.abs_dest_path
src_path = page.file.src_path
except AttributeError:
abs_dest_path = page.abs_output_path
src_path = page.input_path
path = os.path.dirname(abs_dest_path)
os.makedirs(path, exist_ok=True)
filename = os.path.splitext(os.path.basename(src_path))[0]
base_url = urls.path2url(os.path.join(path, filename))
return prep_combined(soup, base_url, page.file.url)
def test_image_image():
assert_pixels(
'test_image_image', 4, 4, '''
rBBB
BBBB
BBBB
BBBB
''', '''
<style>
@page { size: 4px 4px }
svg { display: block }
</style>
<svg width="4px" height="4px" xmlns="http://www.w3.org/2000/svg">
<image xlink:href="%s" />
</svg>
''' % path2url(resource_filename('pattern.png')))
def on_post_page(self, output_content, page, config):
if not self.enabled:
return output_content
start = timer()
self.num_files += 1
try:
abs_dest_path = page.file.abs_dest_path
src_path = page.file.src_path
except AttributeError:
# Support for mkdocs <1.0
abs_dest_path = page.abs_output_path
src_path = page.input_path
path = os.path.dirname(abs_dest_path)
os.makedirs(path, exist_ok=True)
filename = os.path.splitext(os.path.basename(src_path))[0]
from weasyprint import urls
base_url = urls.path2url(os.path.join(path, filename))
pdf_file = filename + '.pdf'
try:
if self.combined:
self.renderer.add_doc(output_content, base_url, page.file.url)
pdf_path = self.get_path_to_pdf_from(page.file.dest_path)
output_content = self.renderer.add_link(
output_content, pdf_path)
else:
self.renderer.write_pdf(output_content, base_url,
os.path.join(path, pdf_file))
output_content = self.renderer.add_link(
output_content, pdf_file)
except Exception as e:
print('Error converting {} to PDF: {}'.format(src_path, e),
file=sys.stderr)
self.num_errors += 1
end = timer()
self.total_time += (end - start)
return output_content
def test_command_line_render(tmpdir):
css = b'''
@page { margin: 2px; size: 8px; background: #fff }
@media screen { img { transform: rotate(-90deg) } }
body { margin: 0; font-size: 0 }
'''
html = b'<body><img src=pattern.png>'
combined = b'<style>' + css + b'</style>' + html
linked = b'<link rel=stylesheet href=style.css>' + html
py.path.local(resource_filename('')).chdir()
# Reference
html_obj = FakeHTML(string=combined, base_url='dummy.html')
pdf_bytes = html_obj.write_pdf()
rotated_pdf_bytes = FakeHTML(
string=combined, base_url='dummy.html',
media_type='screen').write_pdf()
tmpdir.chdir()
with open(resource_filename('pattern.png'), 'rb') as pattern_fd:
pattern_bytes = pattern_fd.read()
tmpdir.join('pattern.png').write_binary(pattern_bytes)
tmpdir.join('no_css.html').write_binary(html)
tmpdir.join('combined.html').write_binary(combined)
tmpdir.join('combined-UTF-16BE.html').write_binary(
combined.decode('ascii').encode('UTF-16BE'))
tmpdir.join('linked.html').write_binary(linked)
tmpdir.join('style.css').write_binary(css)
_run('combined.html out2.pdf')
assert tmpdir.join('out2.pdf').read_binary() == pdf_bytes
_run('combined-UTF-16BE.html out3.pdf --encoding UTF-16BE')
assert tmpdir.join('out3.pdf').read_binary() == pdf_bytes
_run(tmpdir.join('combined.html').strpath + ' out4.pdf')
assert tmpdir.join('out4.pdf').read_binary() == pdf_bytes
_run(path2url(tmpdir.join('combined.html').strpath) + ' out5.pdf')
assert tmpdir.join('out5.pdf').read_binary() == pdf_bytes
_run('linked.html --debug out6.pdf') # test relative URLs
assert tmpdir.join('out6.pdf').read_binary() == pdf_bytes
_run('combined.html --verbose out7')
_run('combined.html --quiet out8')
assert tmpdir.join('out7').read_binary() == pdf_bytes
assert tmpdir.join('out8').read_binary() == pdf_bytes
_run('no_css.html out9.pdf')
_run('no_css.html out10.pdf -s style.css')
assert tmpdir.join('out9.pdf').read_binary() != pdf_bytes
assert tmpdir.join('out10.pdf').read_binary() == pdf_bytes
stdout = _run('combined.html -')
assert stdout == pdf_bytes
_run('- out11.pdf', stdin=combined)
assert tmpdir.join('out11.pdf').read_binary() == pdf_bytes
stdout = _run('- -', stdin=combined)
assert stdout == pdf_bytes
_run('combined.html out13.pdf --media-type screen')
_run('combined.html out12.pdf -m screen')
_run('linked.html out14.pdf -m screen')
assert tmpdir.join('out12.pdf').read_binary() == rotated_pdf_bytes
assert tmpdir.join('out13.pdf').read_binary() == rotated_pdf_bytes
assert tmpdir.join('out14.pdf').read_binary() == rotated_pdf_bytes
stdout = _run('combined.html -')
assert stdout.count(b'attachment') == 0
stdout = _run('combined.html -')
assert stdout.count(b'attachment') == 0
stdout = _run('-a pattern.png combined.html -')
assert stdout.count(b'attachment') == 1
stdout = _run('-a style.css -a pattern.png combined.html -')
assert stdout.count(b'attachment') == 2
os.mkdir('subdirectory')
py.path.local('subdirectory').chdir()
with capture_logs() as logs:
stdout = _run('- -', stdin=combined)
assert len(logs) == 1
assert logs[0].startswith('ERROR: Failed to load image')
assert stdout.startswith(b'%PDF')
with capture_logs() as logs:
stdout = _run('--base-url= - -', stdin=combined)
assert len(logs) == 1
assert logs[0].startswith(
'ERROR: Relative URI reference without a base URI')
assert stdout.startswith(b'%PDF')
stdout = _run('--base-url .. - -', stdin=combined)
assert stdout == pdf_bytes
with pytest.raises(SystemExit):
_run('--info')
with pytest.raises(SystemExit):
_run('--version')
(1, 'I', (0, 150), 'open'),
]], False),
('<h1>é', [
[(1, 'é', (0, 0), 'open')]
], False),
('''
<h1 style="transform: translateX(50px)">!
''', [
[(1, '!', (50, 0), 'open')]
], False),
('''
<style>
img { display: block; bookmark-label: attr(alt); bookmark-level: 1 }
</style>
<img src="%s" alt="Chocolate" />
''' % path2url(resource_filename('pattern.png')),
[[(1, 'Chocolate', (0, 0), 'open')]], False),
('''
<h1 style="transform-origin: 0 0;
transform: rotate(90deg) translateX(50px)">!
''', [[(1, '!', (0, 50), 'open')]], True),
('''
<body style="transform-origin: 0 0; transform: rotate(90deg)">
<h1 style="transform: translateX(50px)">!
''', [[(1, '!', (0, 50), 'open')]], True),
))
@assert_no_logs
def test_assert_bookmarks(html, expected_by_page, round_):
document = FakeHTML(string=html).render()
if round_:
_round_meta(document.pages)
}.items())
class FakeHTML(HTML):
"""Like weasyprint.HTML, but with a lighter UA stylesheet."""
def _ua_stylesheets(self):
return [TEST_UA_STYLESHEET]
def resource_filename(basename):
"""Return the absolute path of the resource called ``basename``."""
return os.path.join(os.path.dirname(__file__), 'resources', basename)
# Dummy filename, but in the right directory.
BASE_URL = path2url(resource_filename('<test>'))
class CallbackHandler(logging.Handler):
"""A logging handler that calls a function for every message."""
def __init__(self, callback):
logging.Handler.__init__(self)
self.emit = callback
@contextlib.contextmanager
def capture_logs():
"""Return a context manager that captures all logged messages."""
logger = LOGGER
messages = []
def test_annotate_document():
document = FakeHTML(resource_filename('doc1.html'))
document._ua_stylesheets = lambda: [CSS(resource_filename('mini_ua.css'))]
style_for = get_all_computed_styles(
document, user_stylesheets=[CSS(resource_filename('user.css'))])
# Element objects behave as lists of their children
_head, body = document.etree_element
h1, p, ul, div = body
li_0, _li_1 = ul
a, = li_0
span1, = div
span2, = span1
h1 = style_for(h1)
p = style_for(p)
ul = style_for(ul)
li_0 = style_for(li_0)
div = style_for(div)
after = style_for(a, 'after')
a = style_for(a)
span1 = style_for(span1)
span2 = style_for(span2)
assert h1['background_image'] == ((
'url', path2url(resource_filename('logo_small.png'))), )
assert h1['font_weight'] == 700
assert h1['font_size'] == 40 # 2em
# x-large * initial = 3/2 * 16 = 24
assert p['margin_top'] == (24, 'px')
assert p['margin_right'] == (0, 'px')
assert p['margin_bottom'] == (24, 'px')
assert p['margin_left'] == (0, 'px')
assert p['background_color'] == 'currentColor'
# 2em * 1.25ex = 2 * 20 * 1.25 * 0.8 = 40
# 2.5ex * 1.25ex = 2.5 * 0.8 * 20 * 1.25 * 0.8 = 40
# TODO: ex unit doesn't work with @font-face fonts, see computed_values.py
# assert ul['margin_top'] == (40, 'px')
# assert ul['margin_right'] == (40, 'px')
# assert ul['margin_bottom'] == (40, 'px')
# assert ul['margin_left'] == (40, 'px')
assert ul['font_weight'] == 400
# thick = 5px, 0.25 inches = 96*.25 = 24px
assert ul['border_top_width'] == 0
assert ul['border_right_width'] == 5
assert ul['border_bottom_width'] == 0
assert ul['border_left_width'] == 24
assert li_0['font_weight'] == 700
assert li_0['font_size'] == 8 # 6pt
assert li_0['margin_top'] == (16, 'px') # 2em
assert li_0['margin_right'] == (0, 'px')
assert li_0['margin_bottom'] == (16, 'px')
assert li_0['margin_left'] == (32, 'px') # 4em
assert a['text_decoration_line'] == {'underline'}
assert a['font_weight'] == 900
assert a['font_size'] == 24 # 300% of 8px
assert a['padding_top'] == (1, 'px')
assert a['padding_right'] == (2, 'px')
assert a['padding_bottom'] == (3, 'px')
assert a['padding_left'] == (4, 'px')
assert a['border_top_width'] == 42
assert a['border_bottom_width'] == 42
assert a['color'] == (1, 0, 0, 1)
assert a['border_top_color'] == 'currentColor'
assert div['font_size'] == 40 # 2 * 20px
assert span1['width'] == (160, 'px') # 10 * 16px (root default is 16px)
assert span1['height'] == (400, 'px') # 10 * (2 * 20px)
assert span2['font_size'] == 32
# The href attr should be as in the source, not made absolute.
assert after['content'] == (('string', ' ['), ('string', 'home.html'),
('string', ']'))
assert after['background_color'] == (1, 0, 0, 1)
assert after['border_top_width'] == 42
assert after['border_bottom_width'] == 3
def test_command_line_render(tmpdir):
css = b'''
@page { margin: 2px; size: 8px; background: #fff }
@media screen { img { transform: rotate(-90deg) } }
body { margin: 0; font-size: 0 }
'''
html = b'<body><img src=pattern.png>'
combined = b'<style>' + css + b'</style>' + html
linked = b'<link rel=stylesheet href=style.css>' + html
not_optimized = b'<body>a<img src="not-optimized.jpg">'
tmpdir.chdir()
for name in ('pattern.png', 'not-optimized.jpg'):
pattern_bytes = Path(resource_filename(name)).read_bytes()
tmpdir.join(name).write_binary(pattern_bytes)
# Reference
html_obj = FakeHTML(string=combined, base_url='dummy.html')
pdf_bytes = html_obj.write_pdf()
rotated_pdf_bytes = FakeHTML(string=combined,
base_url='dummy.html',
media_type='screen').write_pdf()
tmpdir.join('no_css.html').write_binary(html)
tmpdir.join('combined.html').write_binary(combined)
tmpdir.join('combined-UTF-16BE.html').write_binary(
combined.decode('ascii').encode('UTF-16BE'))
tmpdir.join('linked.html').write_binary(linked)
tmpdir.join('not_optimized.html').write_binary(not_optimized)
tmpdir.join('style.css').write_binary(css)
_run('combined.html out2.pdf')
assert tmpdir.join('out2.pdf').read_binary() == pdf_bytes
_run('combined-UTF-16BE.html out3.pdf --encoding UTF-16BE')
assert tmpdir.join('out3.pdf').read_binary() == pdf_bytes
_run(tmpdir.join('combined.html').strpath + ' out4.pdf')
assert tmpdir.join('out4.pdf').read_binary() == pdf_bytes
_run(path2url(tmpdir.join('combined.html').strpath) + ' out5.pdf')
assert tmpdir.join('out5.pdf').read_binary() == pdf_bytes
_run('linked.html --debug out6.pdf') # test relative URLs
assert tmpdir.join('out6.pdf').read_binary() == pdf_bytes
_run('combined.html --verbose out7')
_run('combined.html --quiet out8')
assert tmpdir.join('out7').read_binary() == pdf_bytes
assert tmpdir.join('out8').read_binary() == pdf_bytes
_run('no_css.html out9.pdf')
_run('no_css.html out10.pdf -s style.css')
assert tmpdir.join('out9.pdf').read_binary() != pdf_bytes
assert tmpdir.join('out10.pdf').read_binary() == pdf_bytes
stdout = _run('combined.html -')
assert stdout == pdf_bytes
_run('- out11.pdf', stdin=combined)
assert tmpdir.join('out11.pdf').read_binary() == pdf_bytes
stdout = _run('- -', stdin=combined)
assert stdout == pdf_bytes
_run('combined.html out13.pdf --media-type screen')
_run('combined.html out12.pdf -m screen')
_run('linked.html out14.pdf -m screen')
assert tmpdir.join('out12.pdf').read_binary() == rotated_pdf_bytes
assert tmpdir.join('out13.pdf').read_binary() == rotated_pdf_bytes
assert tmpdir.join('out14.pdf').read_binary() == rotated_pdf_bytes
_run('not_optimized.html out15.pdf')
_run('not_optimized.html out16.pdf -O images')
_run('not_optimized.html out17.pdf -O fonts')
_run('not_optimized.html out18.pdf -O fonts -O images')
_run('not_optimized.html out19.pdf -O all')
_run('not_optimized.html out20.pdf -O none')
_run('not_optimized.html out21.pdf -O none -O all')
_run('not_optimized.html out22.pdf -O all -O none')
# TODO: test that equivalent CLI options give equivalent PDF sizes,
# unfortunately font optimization makes PDF generation not reproducible
assert (len(tmpdir.join('out16.pdf').read_binary()) < len(
tmpdir.join('out15.pdf').read_binary()) < len(
tmpdir.join('out20.pdf').read_binary()))
stdout = _run('combined.html -')
assert stdout.count(b'attachment') == 0
stdout = _run('combined.html -')
assert stdout.count(b'attachment') == 0
stdout = _run('-a pattern.png combined.html -')
assert stdout.count(b'attachment') == 1
stdout = _run('-a style.css -a pattern.png combined.html -')
assert stdout.count(b'attachment') == 2
os.mkdir('subdirectory')
py.path.local('subdirectory').chdir()
with capture_logs() as logs:
stdout = _run('- -', stdin=combined)
assert len(logs) == 1
assert logs[0].startswith('ERROR: Failed to load image')
assert stdout.startswith(b'%PDF')
with capture_logs() as logs:
stdout = _run('--base-url= - -', stdin=combined)
assert len(logs) == 1
assert logs[0].startswith(
'ERROR: Relative URI reference without a base URI')
assert stdout.startswith(b'%PDF')
stdout = _run('--base-url .. - -', stdin=combined)
assert stdout == pdf_bytes
with pytest.raises(SystemExit):
_run('--info')
with pytest.raises(SystemExit):
_run('--version')
