def add_hyperlinks(self, links, anchors, context, scale):
"""Include hyperlinks in current page."""
if cairo.cairo_version() < 11504:
return
# We round floats to avoid locale problems, see
# https://github.com/Kozea/WeasyPrint/issues/742
# TODO: Instead of using rects, we could use the drawing rectangles
# defined by cairo when drawing targets. This would give a feeling
# similiar to what browsers do with links that span multiple lines.
for link in links:
link_type, link_target, rectangle = link
if link_type == 'external':
attributes = "rect=[{} {} {} {}] uri='{}'".format(
*([int(round(i * scale)) for i in rectangle] +
[link_target.replace("'", '%27')]))
elif link_type == 'internal':
attributes = "rect=[{} {} {} {}] dest='{}'".format(
*([int(round(i * scale)) for i in rectangle] +
[link_target.replace("'", '%27')]))
elif link_type == 'attachment':
# Attachments are handled in write_pdf_metadata
continue
context.tag_begin(cairo.TAG_LINK, attributes)
context.tag_end(cairo.TAG_LINK)
for anchor in anchors:
anchor_name, x, y = anchor
attributes = "name='{}' x={} y={}".format(
anchor_name.replace("'", '%27'), int(round(x * scale)),
int(round(y * scale)))
context.tag_begin(cairo.TAG_DEST, attributes)
context.tag_end(cairo.TAG_DEST)
def add_hyperlinks(self, links, anchors, context, scale):
"""Include hyperlinks in current page."""
if cairo.cairo_version() < 11504:
return
# TODO: Instead of using rects, we could use the drawing rectangles
# defined by cairo when drawing targets. This would give a feeling
# similiar to what browsers do with links that span multiple lines.
for link in links:
link_type, link_target, rectangle = link
if link_type == 'external':
attributes = "rect=[{} {} {} {}] uri='{}'".format(
*([i * scale for i in rectangle] + [link_target]))
elif link_type == 'internal':
attributes = "rect=[{} {} {} {}] dest='{}'".format(
*([i * scale for i in rectangle] + [link_target]))
elif link_type == 'attachment':
# Attachments are handled in write_pdf_metadata
continue
context.tag_begin(cairo.TAG_LINK, attributes)
context.tag_end(cairo.TAG_LINK)
for anchor in anchors:
anchor_name, x, y = anchor
attributes = "name='{}' x={} y={}".format(
anchor_name, x * scale, y * scale)
context.tag_begin(cairo.TAG_DEST, attributes)
context.tag_end(cairo.TAG_DEST)
def add_hyperlinks(self, links, anchors, context, scale):
"""Include hyperlinks in current page."""
if cairo.cairo_version() < 11504:
return
# TODO: Instead of using rects, we could use the drawing rectangles
# defined by cairo when drawing targets. This would give a feeling
# similiar to what browsers do with links that span multiple lines.
for link in links:
link_type, link_target, rectangle = link
if link_type == 'external':
attributes = "rect=[{} {} {} {}] uri='{}'".format(
*([_locale_float(i * scale)
for i in rectangle] + [link_target]))
elif link_type == 'internal':
attributes = "rect=[{} {} {} {}] dest='{}'".format(
*([_locale_float(i * scale)
for i in rectangle] + [link_target]))
elif link_type == 'attachment':
# Attachments are handled in write_pdf_metadata
continue
context.tag_begin(cairo.TAG_LINK, attributes)
context.tag_end(cairo.TAG_LINK)
for anchor in anchors:
anchor_name, x, y = anchor
attributes = "name='{}' x={} y={}".format(anchor_name,
_locale_float(x * scale),
_locale_float(y * scale))
context.tag_begin(cairo.TAG_DEST, attributes)
context.tag_end(cairo.TAG_DEST)
def test_navigator(tmpdir):
status, headers, body = wsgi_client(navigator, '/lipsum')
assert status == '404 Not Found'
status, headers, body = wsgi_client(navigator, '/')
body = body.decode('utf8')
assert status == '200 OK'
assert headers['Content-Type'].startswith('text/html;')
assert '<title>WeasyPrint Navigator</title>' in body
assert '<img' not in body
assert '></a>' not in body
test_file = tmpdir.join('test.html')
test_file.write(b'''
<h1 id=foo><a href="http://weasyprint.org">Lorem ipsum</a></h1>
<h2><a href="#foo">bar</a></h2>
''')
url = path2url(test_file.strpath)
for status, headers, body in [
wsgi_client(navigator, '/view/' + url),
wsgi_client(navigator, '/', {'url': url}),
]:
body = body.decode('utf8')
assert status == '200 OK'
assert headers['Content-Type'].startswith('text/html;')
assert '<title>WeasyPrint Navigator</title>' in body
assert '<img src="data:image/png;base64,' in body
assert ' name="foo"></a>' in body
assert ' href="#foo"></a>' in body
assert ' href="/view/http://weasyprint.org"></a>' in body
status, headers, body = wsgi_client(navigator, '/pdf/' + url)
assert status == '200 OK'
assert headers['Content-Type'] == 'application/pdf'
assert body.startswith(b'%PDF')
if cairo.cairo_version() < 11504: # pragma: no cover
return
assert b'/URI (http://weasyprint.org)' in body
assert b'/Title (Lorem ipsum)' in body
status, headers, body = wsgi_client(navigator, '/pdf/' + url)
assert status == '200 OK'
assert headers['Content-Type'] == 'application/pdf'
assert body.startswith(b'%PDF')
with pytest.raises(URLFetchingError):
wsgi_client(navigator, '/pdf/' + 'test.example')
with pytest.raises(URLFetchingError):
wsgi_client(navigator, '/pdf/' + 'test.example', {'test': 'test'})
def export_plot(plot, graph):
"""
Export a bokeh plot based on Cairo version
"""
# export graph as a PNG or SVG depending on Cairo version is installed
# higher quality SVG only works with Cairo version >= 1.15.4
cairo_version = cairo.cairo_version()
if cairo_version < 11504:
filename = f"{graph}_graph.png"
full_filename = Path(output_path, filename)
export_png(plot, full_filename)
print("For a higher quality SVG image file, install Cairo 1.15.4")
else:
filename = f"{graph}_graph.svg"
full_filename = Path(output_path, filename)
export_svgs(plot, full_filename)
return filename
def add_hyperlinks(self, links, context, scale):
"""Include hyperlinks in current page."""
if cairo.cairo_version() < 11504:
return
# TODO: Instead of using rects, we could use the drawing rectangles
# defined by cairo when drawing targets. This would give a feeling
# similiar to what browsers do with links that span multiple lines.
for link in links:
link_type, link_target, rectangle = link
if link_type == 'external':
attributes = "rect=[{} {} {} {}] uri='{}'".format(
*([i * scale for i in rectangle] + [link_target]))
elif link_type == 'internal':
page, x, y = link_target
attributes = ('rect=[{} {} {} {}] page={} '
'pos=[{} {}]'.format(
*([i * scale for i in rectangle] +
[page + 1, x * scale, y * scale])))
elif link_type == 'attachment':
# Attachments are handled in write_pdf_metadata
continue
context.tag_begin(cairo.TAG_LINK, attributes)
import cairosvg.surface
from .urls import fetch, URLFetchingError
from .logger import LOGGER
from .compat import xrange
try:
from cairocffi import pixbuf
except OSError:
pixbuf = None
assert cairosvg.surface.cairo is cairocffi, (
'CairoSVG is using pycairo instead of cairocffi. '
'Make sure it is not imported before WeasyPrint.')
CAIRO_HAS_MIME_DATA = cairocffi.cairo_version() >= 11000
# Map values of the image-rendering property to cairo FILTER values:
# Values are normalized to lower case.
IMAGE_RENDERING_TO_FILTER = {
'auto': cairocffi.FILTER_BILINEAR,
'crisp-edges': cairocffi.FILTER_BEST,
'pixelated': cairocffi.FILTER_NEAREST,
}
class ImageLoadingError(ValueError):
"""An error occured when loading an image.
The image data is probably corrupted or in an invalid format.
Fetch and decode images in various formats.
:copyright: Copyright 2011-2014 Simon Sapin and contributors, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from __future__ import division, unicode_literals
from io import BytesIO
import math
import cairocffi
cairocffi.install_as_pycairo() # for CairoSVG
CAIRO_HAS_MIME_DATA = cairocffi.cairo_version() >= 11000
import cairosvg.parser
import cairosvg.surface
assert cairosvg.surface.cairo is cairocffi, (
'CairoSVG is using pycairo instead of cairocffi. '
'Make sure it is not imported before WeasyPrint.')
try:
from cairocffi import pixbuf
except OSError:
pixbuf = None
from .urls import fetch, URLFetchingError
from .logger import LOGGER
from .compat import xrange
def write_pdf(self, target=None, zoom=1, attachments=None):
"""Paint the pages in a PDF file, with meta-data.
PDF files written directly by cairo do not have meta-data such as
bookmarks/outlines and hyperlinks.
:type target: str, pathlib.Path or file object
:param target:
A filename where the PDF file is generated, a file object, or
:obj:`None`.
:type zoom: float
:param zoom:
The zoom factor in PDF units per CSS units. **Warning**:
All CSS units are affected, including physical units like
``cm`` and named sizes like ``A4``. For values other than
1, the physical CSS units will thus be "wrong".
:type attachments: list
:param attachments: A list of additional file attachments for the
generated PDF document or :obj:`None`. The list's elements are
:class:`Attachment` objects, filenames, URLs or file-like objects.
:returns:
The PDF as :obj:`bytes` if ``target`` is not provided or
:obj:`None`, otherwise :obj:`None` (the PDF is written to
``target``).
"""
# 0.75 = 72 PDF point (cairo units) per inch / 96 CSS pixel per inch
scale = zoom * 0.75
# Use an in-memory buffer. We will need to seek for metadata
# TODO: avoid this if target can seek? Benchmark first.
file_obj = io.BytesIO()
# (1, 1) is overridden by .set_size() below.
surface = cairo.PDFSurface(file_obj, 1, 1)
context = cairo.Context(surface)
PROGRESS_LOGGER.info('Step 6 - Drawing')
paged_links_and_anchors = list(self.resolve_links())
for page, links_and_anchors in zip(self.pages,
paged_links_and_anchors):
links, anchors = links_and_anchors
surface.set_size(
math.floor(
scale *
(page.width + page.bleed['left'] + page.bleed['right'])),
math.floor(
scale *
(page.height + page.bleed['top'] + page.bleed['bottom'])))
with stacked(context):
context.translate(page.bleed['left'] * scale,
page.bleed['top'] * scale)
page.paint(context, scale=scale)
self.add_hyperlinks(links, anchors, context, scale)
surface.show_page()
PROGRESS_LOGGER.info('Step 7 - Adding PDF metadata')
# TODO: overwrite producer when possible in cairo
if cairo.cairo_version() >= 11504:
# Set document information
for attr, key in (('title', cairo.PDF_METADATA_TITLE),
('description', cairo.PDF_METADATA_SUBJECT),
('generator', cairo.PDF_METADATA_CREATOR)):
value = getattr(self.metadata, attr)
if value is not None:
surface.set_metadata(key, value)
for attr, key in (('authors', cairo.PDF_METADATA_AUTHOR),
('keywords', cairo.PDF_METADATA_KEYWORDS)):
value = getattr(self.metadata, attr)
if value is not None:
surface.set_metadata(key, ', '.join(value))
for attr, key in (('created', cairo.PDF_METADATA_CREATE_DATE),
('modified', cairo.PDF_METADATA_MOD_DATE)):
value = getattr(self.metadata, attr)
if value is not None:
surface.set_metadata(key, _w3c_date_to_iso(value, attr))
# Set bookmarks
bookmarks = self.make_bookmark_tree()
levels = [cairo.PDF_OUTLINE_ROOT] * len(bookmarks)
while bookmarks:
bookmark = bookmarks.pop(0)
title = bookmark.label
destination = bookmark.destination
children = bookmark.children
state = bookmark.state
page, x, y = destination
# We round floats to avoid locale problems, see
# https://github.com/Kozea/WeasyPrint/issues/742
link_attribs = 'page={} pos=[{} {}]'.format(
page + 1, int(round(x * scale)), int(round(y * scale)))
outline = surface.add_outline(
levels.pop(), title, link_attribs,
cairo.PDF_OUTLINE_FLAG_OPEN if state == 'open' else 0)
levels.extend([outline] * len(children))
bookmarks = children + bookmarks
surface.finish()
# Add extra PDF metadata: attachments, embedded files
attachment_links = [[
link for link in page_links if link[0] == 'attachment'
] for page_links, page_anchors in paged_links_and_anchors]
# Write extra PDF metadata only when there is a least one from:
# - attachments in metadata
# - attachments as function parameters
# - attachments as PDF links
# - bleed boxes
condition = (self.metadata.attachments or attachments
or any(attachment_links)
or any(any(page.bleed.values()) for page in self.pages))
if condition:
write_pdf_metadata(file_obj, scale, self.url_fetcher,
self.metadata.attachments + (attachments or []),
attachment_links, self.pages)
if target is None:
return file_obj.getvalue()
else:
file_obj.seek(0)
if hasattr(target, 'write'):
shutil.copyfileobj(file_obj, target)
else:
with open(target, 'wb') as fd:
shutil.copyfileobj(file_obj, fd)
from . import CSS
from .css import get_all_computed_styles
from .css.targets import TargetCollector
from .draw import draw_page, stacked
from .fonts import FontConfiguration
from .formatting_structure import boxes
from .formatting_structure.build import build_formatting_structure
from .html import W3C_DATE_RE
from .images import get_image_from_uri as original_get_image_from_uri
from .layout import layout_document
from .layout.backgrounds import percentage
from .logger import LOGGER, PROGRESS_LOGGER
from .pdf import write_pdf_metadata
if cairo.cairo_version() < 11504:
warnings.warn(
'There are known rendering problems and missing features with '
'cairo < 1.15.4. WeasyPrint may work with older versions, but please '
'read the note about the needed cairo version on the "Install" page '
'of the documentation before reporting bugs. '
'http://weasyprint.readthedocs.io/en/latest/install.html')
def _get_matrix(box):
"""Return the matrix for the CSS transforms on this box.
:returns: a :class:`cairocffi.Matrix` object or :obj:`None`.
"""
# "Transforms apply to block-level and atomic inline-level elements,
from __future__ import division
import re
import warnings
import cairocffi as cairo
import cffi
import pyphen
from .compat import basestring
from .logger import LOGGER
# XXX No unicode_literals, cffi likes native strings
if cairo.cairo_version() <= 11400:
warnings.warn('There are known rendering problems with Cairo <= 1.14.0')
PANGO_ATTR_FONT_FEATURES_CACHE = {}
ffi = cffi.FFI()
ffi.cdef('''
// Cairo
typedef enum {
CAIRO_FONT_TYPE_TOY,
CAIRO_FONT_TYPE_FT,
CAIRO_FONT_TYPE_WIN32,
CAIRO_FONT_TYPE_QUARTZ,
CAIRO_FONT_TYPE_USER
} cairo_font_type_t;
def write_pdf(self, target=None, zoom=1, attachments=None):
"""Paint the pages in a PDF file, with meta-data.
PDF files written directly by cairo do not have meta-data such as
bookmarks/outlines and hyperlinks.
:param target:
A filename, file-like object, or :obj:`None`.
:type zoom: float
:param zoom:
The zoom factor in PDF units per CSS units. **Warning**:
All CSS units are affected, including physical units like
``cm`` and named sizes like ``A4``. For values other than
1, the physical CSS units will thus be “wrong”.
:param attachments: A list of additional file attachments for the
generated PDF document or :obj:`None`. The list's elements are
:class:`Attachment` objects, filenames, URLs, or file-like objects.
:returns:
The PDF as byte string if :obj:`target` is :obj:`None`, otherwise
:obj:`None` (the PDF is written to :obj:`target`).
"""
# 0.75 = 72 PDF point (cairo units) per inch / 96 CSS pixel per inch
scale = zoom * 0.75
# Use an in-memory buffer. We will need to seek for metadata
# TODO: avoid this if target can seek? Benchmark first.
file_obj = io.BytesIO()
# (1, 1) is overridden by .set_size() below.
surface = cairo.PDFSurface(file_obj, 1, 1)
context = cairo.Context(surface)
LOGGER.info('Step 6 - Drawing')
paged_links_and_anchors = list(self.resolve_links())
for page, links_and_anchors in zip(
self.pages, paged_links_and_anchors):
links, anchors = links_and_anchors
surface.set_size(
math.floor(scale * (
page.width + page.bleed['left'] + page.bleed['right'])),
math.floor(scale * (
page.height + page.bleed['top'] + page.bleed['bottom'])))
with stacked(context):
context.translate(
page.bleed['left'] * scale, page.bleed['top'] * scale)
page.paint(context, scale=scale)
self.add_hyperlinks(links, anchors, context, scale)
surface.show_page()
LOGGER.info('Step 7 - Adding PDF metadata')
# TODO: overwrite producer when possible in cairo
if cairo.cairo_version() >= 11504:
# Set document information
for attr, key in (
('title', cairo.PDF_METADATA_TITLE),
('description', cairo.PDF_METADATA_SUBJECT),
('generator', cairo.PDF_METADATA_CREATOR)):
value = getattr(self.metadata, attr)
if value is not None:
surface.set_metadata(key, value)
for attr, key in (
('authors', cairo.PDF_METADATA_AUTHOR),
('keywords', cairo.PDF_METADATA_KEYWORDS)):
value = getattr(self.metadata, attr)
if value is not None:
surface.set_metadata(key, ', '.join(value))
for attr, key in (
('created', cairo.PDF_METADATA_CREATE_DATE),
('modified', cairo.PDF_METADATA_MOD_DATE)):
value = getattr(self.metadata, attr)
if value is not None:
surface.set_metadata(key, _w3c_date_to_iso(value, attr))
# Set bookmarks
bookmarks = self.make_bookmark_tree()
levels = [cairo.PDF_OUTLINE_ROOT] * len(bookmarks)
while bookmarks:
title, destination, children = bookmarks.pop(0)
page, x, y = destination
link_attribs = 'page={} pos=[{} {}]'.format(
page + 1, x * scale, y * scale)
outline = surface.add_outline(
levels.pop(), title, link_attribs, 0)
levels.extend([outline] * len(children))
bookmarks = children + bookmarks
surface.finish()
# Add extra PDF metadata: attachments, embedded files
attachment_links = [
[link for link in page_links if link[0] == 'attachment']
for page_links, page_anchors in paged_links_and_anchors]
# Write extra PDF metadata only when there is a least one from:
# - attachments in metadata
# - attachments as function parameters
# - attachments as PDF links
# - bleed boxes
condition = (
self.metadata.attachments or
attachments or
any(attachment_links) or
any(any(page.bleed.values()) for page in self.pages))
if condition:
write_pdf_metadata(
file_obj, scale, self.url_fetcher,
self.metadata.attachments + (attachments or []),
attachment_links, self.pages)
if target is None:
return file_obj.getvalue()
else:
file_obj.seek(0)
if hasattr(target, 'write'):
shutil.copyfileobj(file_obj, target)
else:
with open(target, 'wb') as fd:
shutil.copyfileobj(file_obj, fd)
from . import CSS
from .css import get_all_computed_styles
from .css.targets import TargetCollector
from .draw import draw_page, stacked
from .fonts import FontConfiguration
from .formatting_structure import boxes
from .formatting_structure.build import build_formatting_structure
from .html import W3C_DATE_RE
from .images import get_image_from_uri as original_get_image_from_uri
from .layout import layout_document
from .layout.backgrounds import percentage
from .logger import LOGGER
from .pdf import write_pdf_metadata
if cairo.cairo_version() < 11504:
warnings.warn(
'There are known rendering problems and missing features with '
'cairo < 1.15.4. WeasyPrint may work with older versions, but please '
'read the note about the needed cairo version on the "Install" page '
'of the documentation before reporting bugs. '
'http://weasyprint.readthedocs.io/en/latest/install.html')
def _get_matrix(box):
"""Return the matrix for the CSS transforms on this box.
:returns: a :class:`cairocffi.Matrix` object or :obj:`None`.
"""
# "Transforms apply to block-level and atomic inline-level elements,
