# coding: utf-8 """ weasyprint.tests.test_pdf ------------------------- Test PDF-related code, including metadata, bookmarks and hyperlinks. :copyright: Copyright 2011-2014 Simon Sapin and contributors, see AUTHORS. :license: BSD, see LICENSE for details. """ from __future__ import division, unicode_literals import hashlib import io import os import cairocffi import pytest from .. import CSS, Attachment from .. import pdf from ..images import CAIRO_HAS_MIME_DATA from ..urls import path2url from .testing_utils import ( assert_no_logs, resource_filename, TestHTML, capture_logs, temp_directory) @assert_no_logs def test_pdf_parser(): fileobj = io.BytesIO() surface = cairocffi.PDFSurface(fileobj, 1, 1) for width, height in [ (100, 100), (200, 10), (3.14, 987654321) ]: surface.set_size(width, height) surface.show_page() surface.finish() sizes = [page.get_value('MediaBox', '\[(.+?)\]').strip() for page in pdf.PDFFile(fileobj).pages] assert sizes == [b'0 0 100 100', b'0 0 200 10', b'0 0 3.14 987654321'] @assert_no_logs def test_page_size(): pdf_bytes = TestHTML(string='

Title 1

Title 2

Title 3

Title 4

Title 5

Title 6

Title 7

Title 8

Title 9

Title 10

Title 11

''') assert root == dict(Count=11, First=1, Last=10) assert bookmarks == [ dict(Count=0, First=None, Last=None, Next=2, Parent=0, Prev=None, label='Title 1', target=(0, 50, 950)), dict(Count=4, First=3, Last=6, Next=7, Parent=0, Prev=1, label='Title 2', target=(0, 50, 850)), dict(Count=0, First=None, Last=None, Next=4, Parent=2, Prev=None, label='Title 3', target=(0, 70, 750)), dict(Count=1, First=5, Last=5, Next=6, Parent=2, Prev=3, label='Title 4', target=(0, 50, 650)), dict(Count=0, First=None, Last=None, Next=None, Parent=4, Prev=None, label='Title 5', target=(0, 50, 550)), dict(Count=0, First=None, Last=None, Next=None, Parent=2, Prev=4, label='Title 6', target=(1, 50, 850)), dict(Count=2, First=8, Last=8, Next=10, Parent=0, Prev=2, label='Title 7', target=(1, 50, 750)), dict(Count=1, First=9, Last=9, Next=None, Parent=7, Prev=None, label='Title 8', target=(1, 50, 650)), dict(Count=0, First=None, Last=None, Next=None, Parent=8, Prev=None, label='Title 9', target=(1, 50, 550)), dict(Count=1, First=11, Last=11, Next=None, Parent=0, Prev=7, label='Title 10', target=(1, 50, 450)), dict(Count=0, First=None, Last=None, Next=None, Parent=10, Prev=None, label='Title 11', target=(1, 50, 350))] root, bookmarks = get_bookmarks('''

1

level 1

2

level 2

3

level 1

4

level 2

5

level 3 ''', structure_only=True) assert root == dict(Count=5, First=1, Last=3) assert bookmarks == [ dict(Count=1, First=2, Last=2, Next=3, Parent=0, Prev=None), dict(Count=0, First=None, Last=None, Next=None, Parent=1, Prev=None), dict(Count=2, First=4, Last=4, Next=None, Parent=0, Prev=1), dict(Count=1, First=5, Last=5, Next=None, Parent=3, Prev=None), dict(Count=0, First=None, Last=None, Next=None, Parent=4, Prev=None)] root, bookmarks = get_bookmarks('''

1

h2 level 1

2

h4 level 2

3

h3 level 2
4
h5 level 3

5

h1 level 1

6

h2 level 2

7

h2 level 2

8

h4 level 3

9

h1 level 1 ''', structure_only=True) assert root == dict(Count=9, First=1, Last=9) assert bookmarks == [ dict(Count=3, First=2, Last=3, Next=5, Parent=0, Prev=None), dict(Count=0, First=None, Last=None, Next=3, Parent=1, Prev=None), dict(Count=1, First=4, Last=4, Next=None, Parent=1, Prev=2), dict(Count=0, First=None, Last=None, Next=None, Parent=3, Prev=None), dict(Count=3, First=6, Last=7, Next=9, Parent=0, Prev=1), dict(Count=0, First=None, Last=None, Next=7, Parent=5, Prev=None), dict(Count=1, First=8, Last=8, Next=None, Parent=5, Prev=6), dict(Count=0, First=None, Last=None, Next=None, Parent=7, Prev=None), dict(Count=0, First=None, Last=None, Next=None, Parent=0, Prev=5)] # Reference for the next test. zoom=1 root, bookmarks = get_bookmarks('

a

') assert root == dict(Count=1, First=1, Last=1) assert bookmarks == [ dict(Count=0, First=None, Last=None, Next=None, Parent=0, Prev=None, label='a', target=(0, 50, 950))] root, bookmarks = get_bookmarks('

a

', zoom=1.5) assert root == dict(Count=1, First=1, Last=1) assert bookmarks == [ dict(Count=0, First=None, Last=None, Next=None, Parent=0, Prev=None, label='a', target=(0, 75, 1425))] @assert_no_logs def test_links(): links = get_links('') assert links == [[]] links = get_links('''

Hello, World

''') assert links == [ [ # 30pt wide (like the image), 20pt high (like line-height) ('external', 'http://weasyprint.org', (50, 950, 80, 930)), # The image itself: 30*30pt ('external', 'http://weasyprint.org', (50, 950, 80, 920)), # 32pt wide (image + 2 * 1pt of border), 20pt high ('internal', (1, 50, 950), (60, 850, 92, 830)), # The image itself: 32*32pt ('internal', (1, 50, 950), (60, 850, 92, 818)), ], [ # 400pt wide (block), 30pt high ('internal', (0, 50, 750), (50, 950, 450, 920)), ] ] links = get_links( '', base_url='http://weasyprint.org/foo/bar/') assert links == [[('external', 'http://weasyprint.org/foo/lipsum', (50, 950, 450, 950))]] @assert_no_logs def test_relative_links(): # Relative URI reference without a base URI: not allowed with capture_logs() as logs: links = get_links( '', base_url=None) assert links == [[]] assert len(logs) == 1 assert 'WARNING: Relative URI reference without a base URI' in logs[0] with capture_logs() as logs: links = get_links( '
', base_url=None) assert links == [[]] assert len(logs) == 1 assert 'WARNING: Ignored `-weasy-link: url(../lipsum)`' in logs[0] assert 'Relative URI reference without a base URI' in logs[0] # Internal URI reference without a base URI: OK links = get_links( '', base_url=None) assert links == [[('internal', (0, 50, 950), (50, 950, 450, 950))]] links = get_links( '
', base_url=None) assert links == [[('internal', (0, 50, 950), (50, 950, 450, 950))]] @assert_no_logs def test_missing_links(): with capture_logs() as logs: links = get_links(''' ''', base_url=None) assert links == [[('internal', (0, 50, 935), (50, 950, 450, 935))]] assert len(logs) == 1 assert 'WARNING: No anchor #missing for internal URI reference' in logs[0] @assert_no_logs def test_jpeg(): if not CAIRO_HAS_MIME_DATA: pytest.xfail() def render(html): return TestHTML(base_url=resource_filename('dummy.html'), string=html).write_pdf() assert b'/Filter /DCTDecode' not in render('') # JPEG-encoded image, embedded in PDF: assert b'/Filter /DCTDecode' in render('') @assert_no_logs def test_document_info(): pdf_bytes = TestHTML(string=''' Test document

Another title

''').write_pdf() assert (b'/Author (\xfe\xff\x00I\x00 \x00M\x00e\x00 \x00&\x00 \x00' b'M\x00y\x00s\x00e\x00l\x00f)' in pdf_bytes) assert (b'/Title (\xfe\xff\x00T\x00e\x00s\x00t\x00 \x00d\x00o\x00c' b'\x00u\x00m\x00e\x00n\x00t)' in pdf_bytes) assert (b'/Creator (\xfe\xff\x00H\x00u\x00m\x00a\x00n\x00\xa0\x00a' b'\x00f\x00t\x00e\x00r\x00\xa0\x00a\x00l\x00l)' in pdf_bytes) assert (b'/Keywords (\xfe\xff\x00h\x00t\x00m\x00l\x00,\x00 ' b'\x00c\x00s\x00s\x00,\x00 \x00p\x00d\x00f)' in pdf_bytes) assert b'/Subject (\xfe\xff\x00B\x00l\x00a\x00h &\x00 )' in pdf_bytes assert b'/CreationDate (D:201104)' in pdf_bytes assert b"/ModDate (D:20130721234600+01'00')" in pdf_bytes @assert_no_logs def test_embedded_files(): with temp_directory() as absolute_tmp_dir: absolute_tmp_file = os.path.join(absolute_tmp_dir, 'some_file.txt') 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://') with temp_directory() as relative_tmp_dir: relative_tmp_file = os.path.join(relative_tmp_dir, 'äöü.txt') rdata = b'abcdefgh' with open(relative_tmp_file, 'wb') as rfile: rfile.write(rdata) pdf_bytes = TestHTML( string=''' Test document

Heading 1

Heading 2

'''.format(absolute_url, os.path.basename(relative_tmp_file)), base_url=relative_tmp_dir, ).write_pdf( attachments=[ Attachment('data:,oob attachment', description='Hello'), 'data:,raw URL', io.BytesIO(b'file like obj') ] ) assert ((b'<' + hashlib.md5(b'hi there').hexdigest().encode('ascii') + b'>') in pdf_bytes) assert (b'/F ()' in pdf_bytes) assert (b'/UF (\xfe\xff\x00a\x00t\x00t\x00a\x00c\x00h\x00m\x00e\x00n' b'\x00t\x00.\x00b\x00i\x00n)' in pdf_bytes) assert (b'/Desc (\xfe\xff\x00s\x00o\x00m\x00e\x00 \x00f\x00i\x00l\x00e' b'\x00 \x00a\x00t\x00t\x00a\x00c\x00h\x00m\x00e\x00n\x00t\x00 ' b'\x00\xe4\x00\xf6\x00\xfc)' in pdf_bytes) assert hashlib.md5(adata).hexdigest().encode('ascii') in pdf_bytes assert (os.path.basename(absolute_tmp_file).encode('utf-16-be') in pdf_bytes) assert hashlib.md5(rdata).hexdigest().encode('ascii') in pdf_bytes assert (os.path.basename(relative_tmp_file).encode('utf-16-be') in pdf_bytes) assert (hashlib.md5(b'oob attachment').hexdigest().encode('ascii') in pdf_bytes) assert b'/Desc (\xfe\xff\x00H\x00e\x00l\x00l\x00o)' in pdf_bytes assert (hashlib.md5(b'raw URL').hexdigest().encode('ascii') in pdf_bytes) assert (hashlib.md5(b'file like obj').hexdigest().encode('ascii') in pdf_bytes) assert b'/EmbeddedFiles' in pdf_bytes assert b'/Outlines' in pdf_bytes pdf_bytes = TestHTML(string=''' Test document 2 ''').write_pdf() assert hashlib.md5(b'some data').hexdigest().encode('ascii') in pdf_bytes assert b'/EmbeddedFiles' in pdf_bytes assert b'/Outlines' not in pdf_bytes pdf_bytes = TestHTML(string=''' Test document 3

Heading

''').write_pdf() assert b'/EmbeddedFiles' not in pdf_bytes assert b'/Outlines' in pdf_bytes pdf_bytes = TestHTML(string=''' Test document 4 ''').write_pdf() assert b'/EmbeddedFiles' not in pdf_bytes assert b'/Outlines' not in pdf_bytes @assert_no_logs def test_annotation_files(): pdf_bytes = TestHTML(string=''' Test document A link that lets you download an attachment ''').write_pdf() assert hashlib.md5(b'some data').hexdigest().encode('ascii') in pdf_bytes assert b'/FileAttachment' in pdf_bytes assert b'/EmbeddedFiles' not in pdf_bytes