-
-
Notifications
You must be signed in to change notification settings - Fork 686
/
document.py
1496 lines (1330 loc) · 59.9 KB
/
document.py
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
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
"""Document generation management."""
import collections
import functools
import hashlib
import io
import math
import shutil
import struct
import zlib
from os.path import basename
from urllib.parse import unquote, urlsplit
import pydyf
from fontTools import subset
from fontTools.ttLib import TTFont, TTLibError, ttFont
from . import CSS, Attachment, __version__
from .css import get_all_computed_styles
from .css.counters import CounterStyle
from .css.targets import TargetCollector
from .draw import draw_page, stacked
from .formatting_structure import boxes
from .formatting_structure.build import build_formatting_structure
from .html import W3C_DATE_RE, get_html_metadata
from .images import get_image_from_uri as original_get_image_from_uri
from .layout import LayoutContext, layout_document
from .layout.percent import percentage
from .logger import LOGGER, PROGRESS_LOGGER
from .text.ffi import ffi, harfbuzz, pango
from .text.fonts import FontConfiguration
from .urls import URLFetchingError
def _w3c_date_to_pdf(string, attr_name):
"""Tranform W3C date to PDF format."""
if string is None:
return None
match = W3C_DATE_RE.match(string)
if match is None:
LOGGER.warning(f'Invalid {attr_name} date: {string!r}')
return None
groups = match.groupdict()
pdf_date = ''
found = groups['hour']
for key in ('second', 'minute', 'hour', 'day', 'month', 'year'):
if groups[key]:
found = True
pdf_date = groups[key] + pdf_date
elif found:
pdf_date = f'{(key in ("day", "month")):02d}{pdf_date}'
if groups['hour']:
assert groups['minute']
if groups['tz_hour']:
assert groups['tz_hour'].startswith(('+', '-'))
assert groups['tz_minute']
tz_hour = int(groups['tz_hour'])
tz_minute = int(groups['tz_minute'])
pdf_date += f"{tz_hour:+03d}'{tz_minute:02d}"
else:
pdf_date += 'Z'
return pdf_date
class Font:
def __init__(self, font_hash, file_content, pango_font, index):
pango_metrics = pango.pango_font_get_metrics(pango_font, ffi.NULL)
hb_font = pango.pango_font_get_hb_font(pango_font)
hb_face = harfbuzz.hb_font_get_face(hb_font)
self._font_description = pango.pango_font_describe(pango_font)
self.family = ffi.string(pango.pango_font_description_get_family(
self._font_description))
font_size = pango.pango_font_description_get_size(
self._font_description)
description_string = ffi.string(
pango.pango_font_description_to_string(self._font_description))
sha = hashlib.sha256()
sha.update(str(font_hash).encode())
sha.update(description_string)
self.file_content = file_content
self.index = index
self.file_hash = hash(file_content + bytes(index))
self.hash = ''.join(
chr(65 + letter % 26) for letter in sha.digest()[:6])
self.name = (
b'/' + self.hash.encode() + b'+' + self.family.replace(b' ', b''))
self.italic_angle = 0 # TODO: this should be different
if font_size:
self.ascent = int(
pango.pango_font_metrics_get_ascent(pango_metrics) /
font_size * 1000)
self.descent = -int(
pango.pango_font_metrics_get_descent(pango_metrics) /
font_size * 1000)
else:
self.ascent = self.descent = 0
self.upem = harfbuzz.hb_face_get_upem(hb_face)
self.png = harfbuzz.hb_ot_color_has_png(hb_face)
self.svg = harfbuzz.hb_ot_color_has_svg(hb_face)
self.stemv = 80
self.stemh = 80
self.bbox = [0, 0, 0, 0]
self.widths = {}
self.cmap = {}
@property
def flags(self):
flags = 2 ** (3 - 1) # Symbolic, custom character set
if pango.pango_font_description_get_style(self._font_description):
flags += 2 ** (7 - 1) # Italic
if b'Serif' in self.family.split():
flags += 2 ** (2 - 1) # Serif
widths = self.widths.values()
if len(widths) > 1 and len(set(widths)) == 1:
flags += 2 ** (1 - 1) # FixedPitch
return flags
class Stream(pydyf.Stream):
"""PDF stream object with context storing alpha states."""
def __init__(self, document, page_rectangle, states, x_objects, patterns,
shadings, images, *args, **kwargs):
super().__init__(*args, **kwargs)
self.compress = True
self.page_rectangle = page_rectangle
self._document = document
self._states = states
self._x_objects = x_objects
self._patterns = patterns
self._shadings = shadings
self._images = images
self._current_color = self._current_color_stroke = None
self._current_alpha = self._current_alpha_stroke = None
self._current_font = self._current_font_size = None
self._old_font = self._old_font_size = None
self._ctm_stack = [Matrix()]
# These objects are used in text.show_first_line
self.length = ffi.new('unsigned int *')
self.ink_rect = ffi.new('PangoRectangle *')
self.logical_rect = ffi.new('PangoRectangle *')
@property
def ctm(self):
return self._ctm_stack[-1]
def push_state(self):
super().push_state()
self._ctm_stack.append(self.ctm)
def pop_state(self):
super().pop_state()
self._current_color = self._current_color_stroke = None
self._current_alpha = self._current_alpha_stroke = None
self._current_font = None
self._ctm_stack.pop()
assert self._ctm_stack
def transform(self, a=1, b=0, c=0, d=1, e=0, f=0):
super().transform(a, b, c, d, e, f)
self._ctm_stack[-1] = Matrix(a, b, c, d, e, f) @ self.ctm
def begin_text(self):
if self.stream and self.stream[-1] == b'ET':
self._current_font = self._old_font
self.stream.pop()
else:
super().begin_text()
def end_text(self):
self._old_font, self._current_font = self._current_font, None
super().end_text()
def set_color_rgb(self, r, g, b, stroke=False):
if stroke:
if (r, g, b) == self._current_color_stroke:
return
else:
self._current_color_stroke = (r, g, b)
else:
if (r, g, b) == self._current_color:
return
else:
self._current_color = (r, g, b)
super().set_color_rgb(r, g, b, stroke)
def set_font_size(self, font, size):
if (font, size) == self._current_font:
return
self._current_font = (font, size)
super().set_font_size(font, size)
def set_state(self, state):
key = f's{len(self._states)}'
self._states[key] = state
super().set_state(key)
def set_alpha(self, alpha, stroke=False, fill=None):
if fill is None:
fill = not stroke
if stroke:
key = f'A{alpha}'
if key != self._current_alpha_stroke:
self._current_alpha_stroke = key
if key not in self._states:
self._states[key] = pydyf.Dictionary({'CA': alpha})
super().set_state(key)
if fill:
key = f'a{alpha}'
if key != self._current_alpha:
self._current_alpha = key
if key not in self._states:
self._states[key] = pydyf.Dictionary({'ca': alpha})
super().set_state(key)
def add_font(self, font_hash, font_content, pango_font, index):
self._document.fonts[font_hash] = Font(
font_hash, font_content, pango_font, index)
return self._document.fonts[font_hash]
def get_fonts(self):
return self._document.fonts
def add_group(self, bounding_box):
states = pydyf.Dictionary()
x_objects = pydyf.Dictionary()
patterns = pydyf.Dictionary()
shadings = pydyf.Dictionary()
resources = pydyf.Dictionary({
'ExtGState': states,
'XObject': x_objects,
'Pattern': patterns,
'Shading': shadings,
'Font': None, # Will be set by _use_references
})
extra = pydyf.Dictionary({
'Type': '/XObject',
'Subtype': '/Form',
'BBox': pydyf.Array(bounding_box),
'Resources': resources,
'Group': pydyf.Dictionary({
'Type': '/Group',
'S': '/Transparency',
'I': 'true',
'CS': '/DeviceRGB',
}),
})
group = Stream(
self._document, self.page_rectangle, states, x_objects,
patterns, shadings, self._images, extra=extra)
group.id = f'x{len(self._x_objects)}'
self._x_objects[group.id] = group
return group
def _get_png_data(self, pillow_image, optimize):
image_file = io.BytesIO()
pillow_image.save(image_file, format='PNG', optimize=optimize)
# Read the PNG header, then discard it because we know it's a PNG. If
# this weren't just output from Pillow, we should actually check it.
image_file.seek(8)
png_data = b''
raw_chunk_length = image_file.read(4)
# PNG files consist of a series of chunks.
while len(raw_chunk_length) > 0:
# Each chunk begins with its data length (four bytes, may be zero),
# then its type (four ASCII characters), then the data, then four
# bytes of a CRC.
chunk_len, = struct.unpack('!I', raw_chunk_length)
chunk_type = image_file.read(4)
if chunk_type == b'IDAT':
png_data += image_file.read(chunk_len)
else:
image_file.seek(chunk_len, io.SEEK_CUR)
# We aren't checking the CRC, we assume this is a valid PNG.
image_file.seek(4, io.SEEK_CUR)
raw_chunk_length = image_file.read(4)
return png_data
def add_image(self, pillow_image, image_rendering, optimize_size):
image_name = f'i{pillow_image.id}'
self._x_objects[image_name] = None # Set by write_pdf
if image_name in self._images:
# Reuse image already stored in document
return image_name
if 'transparency' in pillow_image.info:
pillow_image = pillow_image.convert('RGBA')
elif pillow_image.mode in ('1', 'P', 'I'):
pillow_image = pillow_image.convert('RGB')
if pillow_image.mode in ('RGB', 'RGBA'):
color_space = '/DeviceRGB'
elif pillow_image.mode in ('L', 'LA'):
color_space = '/DeviceGray'
elif pillow_image.mode == 'CMYK':
color_space = '/DeviceCMYK'
else:
LOGGER.warning('Unknown image mode: %s', pillow_image.mode)
color_space = '/DeviceRGB'
interpolate = 'true' if image_rendering == 'auto' else 'false'
extra = pydyf.Dictionary({
'Type': '/XObject',
'Subtype': '/Image',
'Width': pillow_image.width,
'Height': pillow_image.height,
'ColorSpace': color_space,
'BitsPerComponent': 8,
'Interpolate': interpolate,
})
optimize = 'images' in optimize_size
if pillow_image.format == 'JPEG':
extra['Filter'] = '/DCTDecode'
image_file = io.BytesIO()
pillow_image.save(image_file, format='JPEG', optimize=optimize)
stream = [image_file.getvalue()]
else:
extra['Filter'] = '/FlateDecode'
extra['DecodeParms'] = pydyf.Dictionary({
# Predictor 15 specifies that we're providing PNG data,
# ostensibly using an "optimum predictor", but doesn't actually
# matter as long as the predictor value is 10+ according to the
# spec. (Other PNG predictor values assert that we're using
# specific predictors that we don't want to commit to, but
# "optimum" can vary.)
'Predictor': 15,
'Columns': pillow_image.width,
})
if pillow_image.mode in ('RGB', 'RGBA'):
# Defaults to 1.
extra['DecodeParms']['Colors'] = 3
if pillow_image.mode in ('RGBA', 'LA'):
alpha = pillow_image.getchannel('A')
pillow_image = pillow_image.convert(pillow_image.mode[:-1])
alpha_data = self._get_png_data(alpha, optimize)
extra['SMask'] = pydyf.Stream([alpha_data], extra={
'Filter': '/FlateDecode',
'Type': '/XObject',
'Subtype': '/Image',
'DecodeParms': pydyf.Dictionary({
'Predictor': 15,
'Columns': pillow_image.width,
}),
'Width': pillow_image.width,
'Height': pillow_image.height,
'ColorSpace': '/DeviceGray',
'BitsPerComponent': 8,
'Interpolate': interpolate,
})
stream = [self._get_png_data(pillow_image, optimize)]
xobject = pydyf.Stream(stream, extra=extra)
self._images[image_name] = xobject
return image_name
def add_pattern(self, width, height, repeat_width, repeat_height, matrix):
states = pydyf.Dictionary()
x_objects = pydyf.Dictionary()
patterns = pydyf.Dictionary()
shadings = pydyf.Dictionary()
resources = pydyf.Dictionary({
'ExtGState': states,
'XObject': x_objects,
'Pattern': patterns,
'Shading': shadings,
'Font': None, # Will be set by _use_references
})
extra = pydyf.Dictionary({
'Type': '/Pattern',
'PatternType': 1,
'BBox': pydyf.Array([0, 0, width, height]),
'XStep': repeat_width,
'YStep': repeat_height,
'TilingType': 1,
'PaintType': 1,
'Matrix': pydyf.Array(matrix.values),
'Resources': resources,
})
pattern = Stream(
self._document, self.page_rectangle, states, x_objects, patterns,
shadings, self._images, extra=extra)
pattern.id = f'p{len(self._patterns)}'
self._patterns[pattern.id] = pattern
return pattern
def add_shading(self):
shading = pydyf.Dictionary()
shading.id = f's{len(self._shadings)}'
self._shadings[shading.id] = shading
return shading
BookmarkSubtree = collections.namedtuple(
'BookmarkSubtree', ('label', 'destination', 'children', 'state'))
def _write_pdf_attachment(pdf, attachment, url_fetcher):
"""Write an attachment to the PDF stream.
:return:
the attachment PDF dictionary.
"""
# Attachments from document links like <link> or <a> can only be URLs.
# They're passed in as tuples
url = ''
if isinstance(attachment, tuple):
url, description = attachment
attachment = Attachment(
url=url, url_fetcher=url_fetcher, description=description)
elif not isinstance(attachment, Attachment):
attachment = Attachment(guess=attachment, url_fetcher=url_fetcher)
try:
with attachment.source as (source_type, source, url, _):
if isinstance(source, bytes):
source = io.BytesIO(source)
uncompressed_length = 0
stream = b''
md5 = hashlib.md5()
compress = zlib.compressobj()
for data in iter(lambda: source.read(4096), b''):
uncompressed_length += len(data)
md5.update(data)
compressed = compress.compress(data)
stream += compressed
compressed = compress.flush(zlib.Z_FINISH)
stream += compressed
file_extra = pydyf.Dictionary({
'Type': '/EmbeddedFile',
'Filter': '/FlateDecode',
'Params': pydyf.Dictionary({
'CheckSum': f'<{md5.hexdigest()}>',
'Size': uncompressed_length,
})
})
file_stream = pydyf.Stream([stream], file_extra)
pdf.add_object(file_stream)
except URLFetchingError as exception:
LOGGER.error('Failed to load attachment: %s', exception)
return
# TODO: Use the result object from a URL fetch operation to provide more
# details on the possible filename.
if url and urlsplit(url).path:
filename = basename(unquote(urlsplit(url).path))
else:
filename = 'attachment.bin'
attachment = pydyf.Dictionary({
'Type': '/Filespec',
'F': pydyf.String(),
'UF': pydyf.String(filename),
'EF': pydyf.Dictionary({'F': file_stream.reference}),
'Desc': pydyf.String(attachment.description or ''),
})
pdf.add_object(attachment)
return attachment
def create_bookmarks(bookmarks, pdf, parent=None):
count = len(bookmarks)
outlines = []
for title, (page, x, y), children, state in bookmarks:
destination = pydyf.Array((
pdf.objects[pdf.pages['Kids'][page * 3]].reference,
'/XYZ', x, y, 0))
outline = pydyf.Dictionary({
'Title': pydyf.String(title), 'Dest': destination})
pdf.add_object(outline)
children_outlines, children_count = create_bookmarks(
children, pdf, parent=outline)
outline['Count'] = children_count
if state == 'closed':
outline['Count'] *= -1
else:
count += children_count
if outlines:
outline['Prev'] = outlines[-1].reference
outlines[-1]['Next'] = outline.reference
if children_outlines:
outline['First'] = children_outlines[0].reference
outline['Last'] = children_outlines[-1].reference
if parent is not None:
outline['Parent'] = parent.reference
outlines.append(outline)
return outlines, count
def add_hyperlinks(links, anchors, matrix, pdf, page, names):
"""Include hyperlinks in current PDF page."""
for link in links:
link_type, link_target, rectangle, _ = link
x1, y1 = matrix.transform_point(*rectangle[:2])
x2, y2 = matrix.transform_point(*rectangle[2:])
if link_type in ('internal', 'external'):
annot = pydyf.Dictionary({
'Type': '/Annot',
'Subtype': '/Link',
'Rect': pydyf.Array([x1, y1, x2, y2]),
'BS': pydyf.Dictionary({'W': 0}),
})
if link_type == 'internal':
annot['Dest'] = pydyf.String(link_target)
else:
annot['A'] = pydyf.Dictionary({
'Type': '/Action',
'S': '/URI',
'URI': pydyf.String(link_target),
})
pdf.add_object(annot)
if 'Annots' not in page:
page['Annots'] = pydyf.Array()
page['Annots'].append(annot.reference)
for anchor in anchors:
anchor_name, x, y = anchor
x, y = matrix.transform_point(x, y)
names.append([
anchor_name, pydyf.Array([page.reference, '/XYZ', x, y, 0])])
def rectangle_aabb(matrix, pos_x, pos_y, width, height):
"""Apply a transformation matrix to an axis-aligned rectangle.
Return its axis-aligned bounding box as ``(x1, y1, x2, y2)``.
"""
transform_point = matrix.transform_point
x1, y1 = transform_point(pos_x, pos_y)
x2, y2 = transform_point(pos_x + width, pos_y)
x3, y3 = transform_point(pos_x, pos_y + height)
x4, y4 = transform_point(pos_x + width, pos_y + height)
box_x1 = min(x1, x2, x3, x4)
box_y1 = min(y1, y2, y3, y4)
box_x2 = max(x1, x2, x3, x4)
box_y2 = max(y1, y2, y3, y4)
return box_x1, box_y1, box_x2, box_y2
def resolve_links(pages):
"""Resolve internal hyperlinks.
Links to a missing anchor are removed with a warning.
If multiple anchors have the same name, the first one is used.
:returns:
A generator yielding lists (one per page) like :attr:`Page.links`,
except that ``target`` for internal hyperlinks is
``(page_number, x, y)`` instead of an anchor name.
The page number is a 0-based index into the :attr:`pages` list,
and ``x, y`` are in CSS pixels from the top-left of the page.
"""
anchors = set()
paged_anchors = []
for i, page in enumerate(pages):
paged_anchors.append([])
for anchor_name, (point_x, point_y) in page.anchors.items():
if anchor_name not in anchors:
paged_anchors[-1].append((anchor_name, point_x, point_y))
anchors.add(anchor_name)
for page in pages:
page_links = []
for link in page.links:
link_type, anchor_name, rectangle, _ = link
if link_type == 'internal':
if anchor_name not in anchors:
LOGGER.error(
'No anchor #%s for internal URI reference',
anchor_name)
else:
page_links.append(
(link_type, anchor_name, rectangle, None))
else:
# External link
page_links.append(link)
yield page_links, paged_anchors.pop(0)
class Matrix(list):
def __init__(self, a=1, b=0, c=0, d=1, e=0, f=0, matrix=None):
if matrix is None:
matrix = [[a, b, 0], [c, d, 0], [e, f, 1]]
super().__init__(matrix)
def __matmul__(self, other):
assert len(self[0]) == len(other) == len(other[0]) == 3
return Matrix(matrix=[
[sum(self[i][k] * other[k][j] for k in range(3)) for j in range(3)]
for i in range(len(self))])
@property
def invert(self):
d = self.determinant
return Matrix(matrix=[
[
(self[1][1] * self[2][2] - self[1][2] * self[2][1]) / d,
(self[0][1] * self[2][2] - self[0][2] * self[2][1]) / -d,
(self[0][1] * self[1][2] - self[0][2] * self[1][1]) / d,
],
[
(self[1][0] * self[2][2] - self[1][2] * self[2][0]) / -d,
(self[0][0] * self[2][2] - self[0][2] * self[2][0]) / d,
(self[0][0] * self[1][2] - self[0][2] * self[1][0]) / -d,
],
[
(self[1][0] * self[2][1] - self[1][1] * self[2][0]) / d,
(self[0][0] * self[2][1] - self[0][1] * self[2][0]) / -d,
(self[0][0] * self[1][1] - self[0][1] * self[1][0]) / d,
],
])
@property
def determinant(self):
assert len(self) == len(self[0]) == 3
return (
self[0][0] * (self[1][1] * self[2][2] - self[1][2] * self[2][1]) -
self[1][0] * (self[0][1] * self[2][2] - self[0][2] * self[2][1]) +
self[2][0] * (self[0][1] * self[1][2] - self[0][2] * self[1][1]))
def transform_point(self, x, y):
return (Matrix(matrix=[[x, y, 1]]) @ self)[0][:2]
@property
def values(self):
(a, b), (c, d), (e, f) = [column[:2] for column in self]
return a, b, c, d, e, f
class Page:
"""Represents a single rendered page.
.. versionadded:: 0.15
Should be obtained from :attr:`Document.pages` but not
instantiated directly.
"""
def __init__(self, page_box):
#: The page width, including margins, in CSS pixels.
self.width = page_box.margin_width()
#: The page height, including margins, in CSS pixels.
self.height = page_box.margin_height()
#: The page bleed widths as a :obj:`dict` with ``'top'``, ``'right'``,
#: ``'bottom'`` and ``'left'`` as keys, and values in CSS pixels.
self.bleed = {
side: page_box.style[f'bleed_{side}'].value
for side in ('top', 'right', 'bottom', 'left')}
#: The :obj:`list` of ``(bookmark_level, bookmark_label, target)``
#: :obj:`tuples <tuple>`. ``bookmark_level`` and ``bookmark_label``
#: are respectively an :obj:`int` and a :obj:`string <str>`, based on
#: the CSS properties of the same names. ``target`` is an ``(x, y)``
#: point in CSS pixels from the top-left of the page.
self.bookmarks = []
#: The :obj:`list` of ``(link_type, target, rectangle)`` :obj:`tuples
#: <tuple>`. A ``rectangle`` is ``(x, y, width, height)``, in CSS
#: pixels from the top-left of the page. ``link_type`` is one of three
#: strings:
#:
#: * ``'external'``: ``target`` is an absolute URL
#: * ``'internal'``: ``target`` is an anchor name (see
#: :attr:`Page.anchors`).
#: The anchor might be defined in another page,
#: in multiple pages (in which case the first occurence is used),
#: or not at all.
#: * ``'attachment'``: ``target`` is an absolute URL and points
#: to a resource to attach to the document.
self.links = []
#: The :obj:`dict` mapping each anchor name to its target, an
#: ``(x, y)`` point in CSS pixels from the top-left of the page.
self.anchors = {}
self._gather_links_and_bookmarks(page_box)
self._page_box = page_box
def _gather_links_and_bookmarks(self, box, parent_matrix=None):
# Get box transformation matrix.
# "Transforms apply to block-level and atomic inline-level elements,
# but do not apply to elements which may be split into
# multiple inline-level boxes."
# http://www.w3.org/TR/css3-2d-transforms/#introduction
if box.style['transform'] and not isinstance(box, boxes.InlineBox):
border_width = box.border_width()
border_height = box.border_height()
origin_x, origin_y = box.style['transform_origin']
offset_x = percentage(origin_x, border_width)
offset_y = percentage(origin_y, border_height)
origin_x = box.border_box_x() + offset_x
origin_y = box.border_box_y() + offset_y
matrix = Matrix(e=origin_x, f=origin_y)
for name, args in box.style['transform']:
a, b, c, d, e, f = 1, 0, 0, 1, 0, 0
if name == 'scale':
a, d = args
elif name == 'rotate':
a = d = math.cos(args)
b = math.sin(args)
c = -b
elif name == 'translate':
e = percentage(args[0], border_width)
f = percentage(args[1], border_height)
elif name == 'skew':
b, c = math.tan(args[1]), math.tan(args[0])
else:
assert name == 'matrix'
a, b, c, d, e, f = args
matrix = Matrix(a, b, c, d, e, f) @ matrix
box.transformation_matrix = (
Matrix(e=-origin_x, f=-origin_y) @ matrix)
if parent_matrix:
matrix = box.transformation_matrix @ parent_matrix
else:
matrix = box.transformation_matrix
else:
matrix = parent_matrix
bookmark_label = box.bookmark_label
if box.style['bookmark_level'] == 'none':
bookmark_level = None
else:
bookmark_level = box.style['bookmark_level']
state = box.style['bookmark_state']
link = box.style['link']
anchor_name = box.style['anchor']
has_bookmark = bookmark_label and bookmark_level
# 'link' is inherited but redundant on text boxes
has_link = link and not isinstance(box, (boxes.TextBox, boxes.LineBox))
# In case of duplicate IDs, only the first is an anchor.
has_anchor = anchor_name and anchor_name not in self.anchors
if has_bookmark or has_link or has_anchor:
pos_x, pos_y, width, height = box.hit_area()
if has_link:
token_type, link = link
assert token_type == 'url'
link_type, target = link
assert isinstance(target, str)
if link_type == 'external' and box.is_attachment:
link_type = 'attachment'
if matrix:
link = (
link_type, target,
rectangle_aabb(matrix, pos_x, pos_y, width, height),
box.download_name)
else:
link = (
link_type, target,
(pos_x, pos_y, pos_x + width, pos_y + height),
box.download_name)
self.links.append(link)
if matrix and (has_bookmark or has_anchor):
pos_x, pos_y = matrix.transform_point(pos_x, pos_y)
if has_bookmark:
self.bookmarks.append(
(bookmark_level, bookmark_label, (pos_x, pos_y), state))
if has_anchor:
self.anchors[anchor_name] = pos_x, pos_y
for child in box.all_children():
self._gather_links_and_bookmarks(child, matrix)
def paint(self, stream, left_x=0, top_y=0, scale=1, clip=False):
"""Paint the page into the PDF file.
:type stream: ``document.Stream``
:param stream:
A document stream.
:param float left_x:
X coordinate of the left of the page, in PDF points.
:param float top_y:
Y coordinate of the top of the page, in PDF points.
:param float scale:
Zoom scale.
:param bool clip:
Whether to clip/cut content outside the page. If false or
not provided, content can overflow.
"""
with stacked(stream):
# Make (0, 0) the top-left corner, and make user units CSS pixels:
stream.transform(a=scale, d=scale, e=left_x, f=top_y)
if clip:
stream.rectangle(0, 0, self.width, self.height)
stream.clip()
draw_page(self._page_box, stream)
class DocumentMetadata:
"""Meta-information belonging to a whole :class:`Document`.
.. versionadded:: 0.20
New attributes may be added in future versions of WeasyPrint.
"""
def __init__(self, title=None, authors=None, description=None,
keywords=None, generator=None, created=None, modified=None,
attachments=None):
#: The title of the document, as a string or :obj:`None`.
#: Extracted from the ``<title>`` element in HTML
#: and written to the ``/Title`` info field in PDF.
self.title = title
#: The authors of the document, as a list of strings.
#: (Defaults to the empty list.)
#: Extracted from the ``<meta name=author>`` elements in HTML
#: and written to the ``/Author`` info field in PDF.
self.authors = authors or []
#: The description of the document, as a string or :obj:`None`.
#: Extracted from the ``<meta name=description>`` element in HTML
#: and written to the ``/Subject`` info field in PDF.
self.description = description
#: Keywords associated with the document, as a list of strings.
#: (Defaults to the empty list.)
#: Extracted from ``<meta name=keywords>`` elements in HTML
#: and written to the ``/Keywords`` info field in PDF.
self.keywords = keywords or []
#: The name of one of the software packages
#: used to generate the document, as a string or :obj:`None`.
#: Extracted from the ``<meta name=generator>`` element in HTML
#: and written to the ``/Creator`` info field in PDF.
self.generator = generator
#: The creation date of the document, as a string or :obj:`None`.
#: Dates are in one of the six formats specified in
#: `W3C’s profile of ISO 8601 <http://www.w3.org/TR/NOTE-datetime>`_.
#: Extracted from the ``<meta name=dcterms.created>`` element in HTML
#: and written to the ``/CreationDate`` info field in PDF.
self.created = created
#: The modification date of the document, as a string or :obj:`None`.
#: Dates are in one of the six formats specified in
#: `W3C’s profile of ISO 8601 <http://www.w3.org/TR/NOTE-datetime>`_.
#: Extracted from the ``<meta name=dcterms.modified>`` element in HTML
#: and written to the ``/ModDate`` info field in PDF.
self.modified = modified
#: File attachments, as a list of tuples of URL and a description or
#: :obj:`None`. (Defaults to the empty list.)
#: Extracted from the ``<link rel=attachment>`` elements in HTML
#: and written to the ``/EmbeddedFiles`` dictionary in PDF.
#:
#: .. versionadded:: 0.22
self.attachments = attachments or []
class Document:
"""A rendered document ready to be painted in a pydyf stream.
Typically obtained from :meth:`HTML.render() <weasyprint.HTML.render>`, but
can also be instantiated directly with a list of :class:`pages <Page>`, a
set of :class:`metadata <DocumentMetadata>`, a :func:`url_fetcher
<weasyprint.default_url_fetcher>` function, and a :class:`font_config
<weasyprint.text.fonts.FontConfiguration>`.
"""
@classmethod
def _build_layout_context(cls, html, stylesheets,
presentational_hints=False,
optimize_size=('fonts',), font_config=None,
counter_style=None, image_cache=None):
if font_config is None:
font_config = FontConfiguration()
if counter_style is None:
counter_style = CounterStyle()
target_collector = TargetCollector()
page_rules = []
user_stylesheets = []
image_cache = {} if image_cache is None else image_cache
for css in stylesheets or []:
if not hasattr(css, 'matcher'):
css = CSS(
guess=css, media_type=html.media_type,
font_config=font_config, counter_style=counter_style)
user_stylesheets.append(css)
style_for = get_all_computed_styles(
html, user_stylesheets, presentational_hints, font_config,
counter_style, page_rules, target_collector)
get_image_from_uri = functools.partial(
original_get_image_from_uri, cache=image_cache,
url_fetcher=html.url_fetcher, optimize_size=optimize_size)
PROGRESS_LOGGER.info('Step 4 - Creating formatting structure')
context = LayoutContext(
style_for, get_image_from_uri, font_config, counter_style,
target_collector)
return context
@classmethod
def _render(cls, html, stylesheets, presentational_hints=False,
optimize_size=('fonts',), font_config=None, counter_style=None,
image_cache=None):
if font_config is None:
font_config = FontConfiguration()
if counter_style is None:
counter_style = CounterStyle()
context = cls._build_layout_context(
html, stylesheets, presentational_hints, optimize_size,
font_config, counter_style, image_cache)
root_box = build_formatting_structure(
html.etree_element, context.style_for, context.get_image_from_uri,
html.base_url, context.target_collector, counter_style,
context.footnotes)
page_boxes = layout_document(html, root_box, context)
rendering = cls(
[Page(page_box) for page_box in page_boxes],
DocumentMetadata(**get_html_metadata(html)),
html.url_fetcher, font_config, optimize_size)
return rendering
def _reference_resources(self, pdf, resources, images, fonts):
if 'Font' in resources:
assert resources['Font'] is None
resources['Font'] = fonts
self._use_references(pdf, resources, images)
pdf.add_object(resources)
return resources.reference
def _use_references(self, pdf, resources, images):
# XObjects
for key, x_object in resources.get('XObject', {}).items():
# Images
if x_object is None:
x_object = images[key]
if x_object.number is not None:
# Image already added to PDF
resources['XObject'][key] = x_object.reference
continue
pdf.add_object(x_object)
resources['XObject'][key] = x_object.reference
# Masks
if 'SMask' in x_object.extra:
pdf.add_object(x_object.extra['SMask'])
x_object.extra['SMask'] = x_object.extra['SMask'].reference
# Resources
if 'Resources' in x_object.extra:
x_object.extra['Resources'] = self._reference_resources(
pdf, x_object.extra['Resources'], images,
resources['Font'])
# Patterns
for key, pattern in resources.get('Pattern', {}).items():
pdf.add_object(pattern)
resources['Pattern'][key] = pattern.reference
if 'Resources' in pattern.extra:
pattern.extra['Resources'] = self._reference_resources(
pdf, pattern.extra['Resources'], images, resources['Font'])
# Shadings
for key, shading in resources.get('Shading', {}).items():
pdf.add_object(shading)
resources['Shading'][key] = shading.reference
# Alpha states
for key, alpha in resources.get('ExtGState', {}).items():
if 'SMask' in alpha and 'G' in alpha['SMask']:
alpha['SMask']['G'] = alpha['SMask']['G'].reference
def __init__(self, pages, metadata, url_fetcher, font_config,
optimize_size):
#: A list of :class:`Page` objects.
self.pages = pages
#: A :class:`DocumentMetadata` object.
#: Contains information that does not belong to a specific page
#: but to the whole document.
self.metadata = metadata
#: A function or other callable with the same signature as
#: :func:`weasyprint.default_url_fetcher` called to fetch external
#: resources such as stylesheets and images. (See :ref:`URL Fetchers`.)
self.url_fetcher = url_fetcher
#: A :obj:`dict` of fonts used by the document. Keys are hashes used to
#: identify fonts, values are ``Font`` objects.
self.fonts = {}
# Keep a reference to font_config to avoid its garbage collection until
# rendering is destroyed. This is needed as font_config.__del__ removes
# fonts that may be used when rendering
self._font_config = font_config
# Set of flags for PDF size optimization. Can contain "images" and
# "fonts".