-
-
Notifications
You must be signed in to change notification settings - Fork 640
/
reportlab_paragraph.py
1834 lines (1623 loc) · 67.7 KB
/
reportlab_paragraph.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
# -*- coding: utf-8 -*-
# Copyright ReportLab Europe Ltd. 2000-2008
# see license.txt for license details
# history http://www.reportlab.co.uk/cgi-bin/viewcvs.cgi/public/reportlab/trunk/reportlab/platypus/paragraph.py
# Modifications by Dirk Holtwick, 2008
from string import join, whitespace
from operator import truth
from reportlab.pdfbase.pdfmetrics import stringWidth, getAscentDescent
from reportlab.platypus.paraparser import ParaParser
from reportlab.platypus.flowables import Flowable
from reportlab.lib.colors import Color
from reportlab.lib.enums import TA_LEFT, TA_RIGHT, TA_CENTER, TA_JUSTIFY
from reportlab.lib.textsplit import ALL_CANNOT_START
from copy import deepcopy
from reportlab.lib.abag import ABag
import re
PARAGRAPH_DEBUG = False
LEADING_FACTOR = 1.0
_wsc_re_split = re.compile('[%s]+' % re.escape(''.join((
u'\u0009', # HORIZONTAL TABULATION
u'\u000A', # LINE FEED
u'\u000B', # VERTICAL TABULATION
u'\u000C', # FORM FEED
u'\u000D', # CARRIAGE RETURN
u'\u001C', # FILE SEPARATOR
u'\u001D', # GROUP SEPARATOR
u'\u001E', # RECORD SEPARATOR
u'\u001F', # UNIT SEPARATOR
u'\u0020', # SPACE
u'\u0085', # NEXT LINE
#u'\u00A0', # NO-BREAK SPACE
u'\u1680', # OGHAM SPACE MARK
u'\u2000', # EN QUAD
u'\u2001', # EM QUAD
u'\u2002', # EN SPACE
u'\u2003', # EM SPACE
u'\u2004', # THREE-PER-EM SPACE
u'\u2005', # FOUR-PER-EM SPACE
u'\u2006', # SIX-PER-EM SPACE
u'\u2007', # FIGURE SPACE
u'\u2008', # PUNCTUATION SPACE
u'\u2009', # THIN SPACE
u'\u200A', # HAIR SPACE
u'\u200B', # ZERO WIDTH SPACE
u'\u2028', # LINE SEPARATOR
u'\u2029', # PARAGRAPH SEPARATOR
u'\u202F', # NARROW NO-BREAK SPACE
u'\u205F', # MEDIUM MATHEMATICAL SPACE
u'\u3000', # IDEOGRAPHIC SPACE
)))).split
def split(text, delim=None):
if type(text) is str:
text = text.decode('utf8')
if type(delim) is str:
delim = delim.decode('utf8')
elif delim is None and u'\xa0' in text:
return [uword.encode('utf8') for uword in _wsc_re_split(text)]
return [uword.encode('utf8') for uword in text.split(delim)]
def strip(text):
if type(text) is str:
text = text.decode('utf8')
return text.strip().encode('utf8')
class ParaLines(ABag):
"""
class ParaLines contains the broken into lines representation of Paragraphs
kind=0 Simple
fontName, fontSize, textColor apply to whole Paragraph
lines [(extraSpace1,words1),....,(extraspaceN,wordsN)]
kind==1 Complex
lines [FragLine1,...,FragLineN]
"""
class FragLine(ABag):
"""
class FragLine contains a styled line (ie a line with more than one style)::
extraSpace unused space for justification only
wordCount 1+spaces in line for justification purposes
words [ParaFrags] style text lumps to be concatenated together
fontSize maximum fontSize seen on the line; not used at present,
but could be used for line spacing.
"""
#our one and only parser
# XXXXX if the parser has any internal state using only one is probably a BAD idea!
_parser = ParaParser()
def _lineClean(L):
return join(filter(truth, split(strip(L))))
def cleanBlockQuotedText(text, joiner=' '):
"""This is an internal utility which takes triple-
quoted text form within the document and returns
(hopefully) the paragraph the user intended originally."""
L = filter(truth, map(_lineClean, split(text, '\n')))
return join(L, joiner)
def setXPos(tx, dx):
if dx > 1e-6 or dx < -1e-6:
tx.setXPos(dx)
def _leftDrawParaLine(tx, offset, extraspace, words, last=0):
setXPos(tx, offset)
tx._textOut(join(words), 1)
setXPos(tx, -offset)
return offset
def _centerDrawParaLine(tx, offset, extraspace, words, last=0):
m = offset + 0.5 * extraspace
setXPos(tx, m)
tx._textOut(join(words), 1)
setXPos(tx, -m)
return m
def _rightDrawParaLine(tx, offset, extraspace, words, last=0):
m = offset + extraspace
setXPos(tx, m)
tx._textOut(join(words), 1)
setXPos(tx, -m)
return m
def _justifyDrawParaLine(tx, offset, extraspace, words, last=0):
setXPos(tx, offset)
text = join(words)
if last:
#last one, left align
tx._textOut(text, 1)
else:
nSpaces = len(words) - 1
if nSpaces:
tx.setWordSpace(extraspace / float(nSpaces))
tx._textOut(text, 1)
tx.setWordSpace(0)
else:
tx._textOut(text, 1)
setXPos(tx, -offset)
return offset
def imgVRange(h, va, fontSize):
"""
return bottom,top offsets relative to baseline(0)
"""
if va == 'baseline':
iyo = 0
elif va in ('text-top', 'top'):
iyo = fontSize - h
elif va == 'middle':
iyo = fontSize - (1.2 * fontSize + h) * 0.5
elif va in ('text-bottom', 'bottom'):
iyo = fontSize - 1.2 * fontSize
elif va == 'super':
iyo = 0.5 * fontSize
elif va == 'sub':
iyo = -0.5 * fontSize
elif hasattr(va, 'normalizedValue'):
iyo = va.normalizedValue(fontSize)
else:
iyo = va
return iyo, iyo + h
_56 = 5. / 6
_16 = 1. / 6
def _putFragLine(cur_x, tx, line):
xs = tx.XtraState
cur_y = xs.cur_y
x0 = tx._x0
autoLeading = xs.autoLeading
leading = xs.leading
cur_x += xs.leftIndent
dal = autoLeading in ('min', 'max')
if dal:
if autoLeading == 'max':
ascent = max(_56 * leading, line.ascent)
descent = max(_16 * leading, -line.descent)
else:
ascent = line.ascent
descent = -line.descent
leading = ascent + descent
if tx._leading != leading:
tx.setLeading(leading)
if dal:
olb = tx._olb
if olb is not None:
xcy = olb - ascent
if tx._oleading != leading:
cur_y += leading - tx._oleading
if abs(xcy - cur_y) > 1e-8:
cur_y = xcy
tx.setTextOrigin(x0, cur_y)
xs.cur_y = cur_y
tx._olb = cur_y - descent
tx._oleading = leading
# Letter spacing
if xs.style.letterSpacing != 'normal':
tx.setCharSpace(int(xs.style.letterSpacing))
ws = getattr(tx, '_wordSpace', 0)
nSpaces = 0
words = line.words
for f in words:
if hasattr(f, 'cbDefn'):
cbDefn = f.cbDefn
kind = cbDefn.kind
if kind == 'img':
#draw image cbDefn,cur_y,cur_x
w = cbDefn.width
h = cbDefn.height
txfs = tx._fontsize
if txfs is None:
txfs = xs.style.fontSize
iy0, iy1 = imgVRange(h, cbDefn.valign, txfs)
cur_x_s = cur_x + nSpaces * ws
tx._canvas.drawImage(cbDefn.image.getImage(), cur_x_s, cur_y + iy0, w, h, mask='auto')
cur_x += w
cur_x_s += w
setXPos(tx, cur_x_s - tx._x0)
elif kind == 'barcode':
barcode = cbDefn.barcode
w = cbDefn.width
h = cbDefn.height
txfs = tx._fontsize
if txfs is None:
txfs = xs.style.fontSize
iy0, iy1 = imgVRange(h, cbDefn.valign, txfs)
cur_x_s = cur_x + nSpaces * ws
barcode.draw(canvas=tx._canvas, xoffset=cur_x_s)
cur_x += w
cur_x_s += w
setXPos(tx, cur_x_s - tx._x0)
else:
name = cbDefn.name
if kind == 'anchor':
tx._canvas.bookmarkHorizontal(name, cur_x, cur_y + leading)
else:
func = getattr(tx._canvas, name, None)
if not func:
raise AttributeError("Missing %s callback attribute '%s'" % (kind, name))
func(tx._canvas, kind, cbDefn.label)
if f is words[-1]:
if not tx._fontname:
tx.setFont(xs.style.fontName, xs.style.fontSize)
tx._textOut('', 1)
elif kind == 'img':
tx._textOut('', 1)
else:
cur_x_s = cur_x + nSpaces * ws
if (tx._fontname, tx._fontsize) != (f.fontName, f.fontSize):
tx._setFont(f.fontName, f.fontSize)
if xs.textColor != f.textColor:
xs.textColor = f.textColor
tx.setFillColor(f.textColor)
if xs.rise != f.rise:
xs.rise = f.rise
tx.setRise(f.rise)
text = f.text
tx._textOut(text, f is words[-1]) # cheap textOut
# XXX Modified for XHTML2PDF
# Background colors (done like underline)
if hasattr(f, "backColor"):
if xs.backgroundColor != f.backColor or xs.backgroundFontSize != f.fontSize:
if xs.backgroundColor is not None:
xs.backgrounds.append((xs.background_x, cur_x_s, xs.backgroundColor, xs.backgroundFontSize))
xs.background_x = cur_x_s
xs.backgroundColor = f.backColor
xs.backgroundFontSize = f.fontSize
# Underline
if not xs.underline and f.underline:
xs.underline = 1
xs.underline_x = cur_x_s
xs.underlineColor = f.textColor
elif xs.underline:
if not f.underline:
xs.underline = 0
xs.underlines.append((xs.underline_x, cur_x_s, xs.underlineColor))
xs.underlineColor = None
elif xs.textColor != xs.underlineColor:
xs.underlines.append((xs.underline_x, cur_x_s, xs.underlineColor))
xs.underlineColor = xs.textColor
xs.underline_x = cur_x_s
# Strike
if not xs.strike and f.strike:
xs.strike = 1
xs.strike_x = cur_x_s
xs.strikeColor = f.textColor
# XXX Modified for XHTML2PDF
xs.strikeFontSize = f.fontSize
elif xs.strike:
if not f.strike:
xs.strike = 0
# XXX Modified for XHTML2PDF
xs.strikes.append((xs.strike_x, cur_x_s, xs.strikeColor, xs.strikeFontSize))
xs.strikeColor = None
xs.strikeFontSize = None
elif xs.textColor != xs.strikeColor:
xs.strikes.append((xs.strike_x, cur_x_s, xs.strikeColor, xs.strikeFontSize))
xs.strikeColor = xs.textColor
xs.strikeFontSize = f.fontSize
xs.strike_x = cur_x_s
if f.link and not xs.link:
if not xs.link:
xs.link = f.link
xs.link_x = cur_x_s
xs.linkColor = xs.textColor
elif xs.link:
if not f.link:
xs.links.append((xs.link_x, cur_x_s, xs.link, xs.linkColor))
xs.link = None
xs.linkColor = None
elif f.link != xs.link or xs.textColor != xs.linkColor:
xs.links.append((xs.link_x, cur_x_s, xs.link, xs.linkColor))
xs.link = f.link
xs.link_x = cur_x_s
xs.linkColor = xs.textColor
txtlen = tx._canvas.stringWidth(text, tx._fontname, tx._fontsize)
cur_x += txtlen
nSpaces += text.count(' ')
cur_x_s = cur_x + (nSpaces - 1) * ws
# XXX Modified for XHTML2PDF
# Underline
if xs.underline:
xs.underlines.append((xs.underline_x, cur_x_s, xs.underlineColor))
# XXX Modified for XHTML2PDF
# Backcolor
if hasattr(f, "backColor"):
if xs.backgroundColor is not None:
xs.backgrounds.append((xs.background_x, cur_x_s, xs.backgroundColor, xs.backgroundFontSize))
# XXX Modified for XHTML2PDF
# Strike
if xs.strike:
xs.strikes.append((xs.strike_x, cur_x_s, xs.strikeColor, xs.strikeFontSize))
if xs.link:
xs.links.append((xs.link_x, cur_x_s, xs.link, xs.linkColor))
if tx._x0 != x0:
setXPos(tx, x0 - tx._x0)
def _leftDrawParaLineX( tx, offset, line, last=0):
setXPos(tx, offset)
_putFragLine(offset, tx, line)
setXPos(tx, -offset)
def _centerDrawParaLineX( tx, offset, line, last=0):
m = offset + 0.5 * line.extraSpace
setXPos(tx, m)
_putFragLine(m, tx, line)
setXPos(tx, -m)
def _rightDrawParaLineX( tx, offset, line, last=0):
m = offset + line.extraSpace
setXPos(tx, m)
_putFragLine(m, tx, line)
setXPos(tx, -m)
def _justifyDrawParaLineX( tx, offset, line, last=0):
setXPos(tx, offset)
extraSpace = line.extraSpace
nSpaces = line.wordCount - 1
if last or not nSpaces or abs(extraSpace) <= 1e-8 or line.lineBreak:
_putFragLine(offset, tx, line) # no space modification
else:
tx.setWordSpace(extraSpace / float(nSpaces))
_putFragLine(offset, tx, line)
tx.setWordSpace(0)
setXPos(tx, -offset)
def _sameFrag(f, g):
"""
returns 1 if two ParaFrags map out the same
"""
if (hasattr(f, 'cbDefn') or hasattr(g, 'cbDefn')
or hasattr(f, 'lineBreak') or hasattr(g, 'lineBreak')): return 0
for a in ('fontName', 'fontSize', 'textColor', 'backColor', 'rise', 'underline', 'strike', 'link'):
if getattr(f, a, None) != getattr(g, a, None): return 0
return 1
def _getFragWords(frags):
"""
given a Parafrag list return a list of fragwords
[[size, (f00,w00), ..., (f0n,w0n)],....,[size, (fm0,wm0), ..., (f0n,wmn)]]
each pair f,w represents a style and some string
each sublist represents a word
"""
R = []
W = []
n = 0
hangingStrip = False
for f in frags:
text = f.text
# of paragraphs
if text != '':
if hangingStrip:
hangingStrip = False
text = text.lstrip()
S = split(text)
if S == []:
S = ['']
if W != [] and text[0] in whitespace:
W.insert(0, n)
R.append(W)
W = []
n = 0
for w in S[:-1]:
W.append((f, w))
n += stringWidth(w, f.fontName, f.fontSize)
W.insert(0, n)
R.append(W)
W = []
n = 0
w = S[-1]
W.append((f, w))
n += stringWidth(w, f.fontName, f.fontSize)
if text and text[-1] in whitespace:
W.insert(0, n)
R.append(W)
W = []
n = 0
elif hasattr(f, 'cbDefn'):
w = getattr(f.cbDefn, 'width', 0)
if w:
if W != []:
W.insert(0, n)
R.append(W)
W = []
n = 0
R.append([w, (f, '')])
else:
W.append((f, ''))
elif hasattr(f, 'lineBreak'):
#pass the frag through. The line breaker will scan for it.
if W != []:
W.insert(0, n)
R.append(W)
W = []
n = 0
R.append([0, (f, '')])
hangingStrip = True
if W != []:
W.insert(0, n)
R.append(W)
return R
def _split_blParaSimple(blPara, start, stop):
f = blPara.clone()
for a in ('lines', 'kind', 'text'):
if hasattr(f, a): delattr(f, a)
f.words = []
for l in blPara.lines[start:stop]:
for w in l[1]:
f.words.append(w)
return [f]
def _split_blParaHard(blPara, start, stop):
f = []
lines = blPara.lines[start:stop]
for l in lines:
for w in l.words:
f.append(w)
if l is not lines[-1]:
i = len(f) - 1
while i >= 0 and hasattr(f[i], 'cbDefn') and not getattr(f[i].cbDefn, 'width', 0): i -= 1
if i >= 0:
g = f[i]
if not g.text:
g.text = ' '
elif g.text[-1] != ' ':
g.text += ' '
return f
def _drawBullet(canvas, offset, cur_y, bulletText, style):
"""
draw a bullet text could be a simple string or a frag list
"""
tx2 = canvas.beginText(style.bulletIndent, cur_y + getattr(style, "bulletOffsetY", 0))
tx2.setFont(style.bulletFontName, style.bulletFontSize)
tx2.setFillColor(hasattr(style, 'bulletColor') and style.bulletColor or style.textColor)
if isinstance(bulletText, basestring):
tx2.textOut(bulletText)
else:
for f in bulletText:
if hasattr(f, "image"):
image = f.image
width = image.drawWidth
height = image.drawHeight
gap = style.bulletFontSize * 0.25
img = image.getImage()
# print style.bulletIndent, offset, width
canvas.drawImage(
img,
style.leftIndent - width - gap,
cur_y + getattr(style, "bulletOffsetY", 0),
width,
height)
else:
tx2.setFont(f.fontName, f.fontSize)
tx2.setFillColor(f.textColor)
tx2.textOut(f.text)
canvas.drawText(tx2)
#AR making definition lists a bit less ugly
#bulletEnd = tx2.getX()
bulletEnd = tx2.getX() + style.bulletFontSize * 0.6
offset = max(offset, bulletEnd - style.leftIndent)
return offset
def _handleBulletWidth(bulletText, style, maxWidths):
"""
work out bullet width and adjust maxWidths[0] if neccessary
"""
if bulletText:
if isinstance(bulletText, basestring):
bulletWidth = stringWidth(bulletText, style.bulletFontName, style.bulletFontSize)
else:
#it's a list of fragments
bulletWidth = 0
for f in bulletText:
bulletWidth = bulletWidth + stringWidth(f.text, f.fontName, f.fontSize)
bulletRight = style.bulletIndent + bulletWidth + 0.6 * style.bulletFontSize
indent = style.leftIndent + style.firstLineIndent
if bulletRight > indent:
#..then it overruns, and we have less space available on line 1
maxWidths[0] -= (bulletRight - indent)
def splitLines0(frags, widths):
"""
given a list of ParaFrags we return a list of ParaLines
each ParaLine has
1) ExtraSpace
2) blankCount
3) [textDefns....]
each text definition is a (ParaFrag, start, limit) triplet
"""
#initialise the algorithm
lines = []
lineNum = 0
maxW = widths[lineNum]
i = -1
l = len(frags)
lim = start = 0
while 1:
#find a non whitespace character
while i < l:
while start < lim and text[start] == ' ': start += 1
if start == lim:
i += 1
if i == l: break
start = 0
f = frags[i]
text = f.text
lim = len(text)
else:
break # we found one
if start == lim: break # if we didn't find one we are done
#start of a line
g = (None, None, None)
line = []
cLen = 0
nSpaces = 0
while cLen < maxW:
j = text.find(' ', start)
if j < 0:
j == lim
w = stringWidth(text[start:j], f.fontName, f.fontSize)
cLen += w
if cLen > maxW and line != []:
cLen = cLen - w
#this is the end of the line
while g.text[lim] == ' ':
lim -= 1
nSpaces -= 1
break
if j < 0:
j = lim
if g[0] is f:
g[2] = j #extend
else:
g = (f, start, j)
line.append(g)
if j == lim:
i += 1
def _do_under_line(i, t_off, ws, tx, lm=-0.125):
y = tx.XtraState.cur_y - i * tx.XtraState.style.leading + lm * tx.XtraState.f.fontSize
textlen = tx._canvas.stringWidth(join(tx.XtraState.lines[i][1]), tx._fontname, tx._fontsize)
tx._canvas.line(t_off, y, t_off + textlen + ws, y)
_scheme_re = re.compile('^[a-zA-Z][-+a-zA-Z0-9]+$')
def _doLink(tx, link, rect):
if isinstance(link, unicode):
link = link.encode('utf8')
parts = link.split(':', 1)
scheme = len(parts) == 2 and parts[0].lower() or ''
if _scheme_re.match(scheme) and scheme != 'document':
kind = scheme.lower() == 'pdf' and 'GoToR' or 'URI'
if kind == 'GoToR': link = parts[1]
tx._canvas.linkURL(link, rect, relative=1, kind=kind)
else:
if link[0] == '#':
link = link[1:]
scheme = ''
tx._canvas.linkRect("", scheme != 'document' and link or parts[1], rect, relative=1)
def _do_link_line(i, t_off, ws, tx):
xs = tx.XtraState
leading = xs.style.leading
y = xs.cur_y - i * leading - xs.f.fontSize / 8.0 # 8.0 factor copied from para.py
text = join(xs.lines[i][1])
textlen = tx._canvas.stringWidth(text, tx._fontname, tx._fontsize)
_doLink(tx, xs.link, (t_off, y, t_off + textlen + ws, y + leading))
# XXX Modified for XHTML2PDF
def _do_post_text(tx):
"""
Try to find out what the variables mean:
tx A structure containing more informations about paragraph ???
leading Height of lines
ff 1/8 of the font size
y0 The "baseline" postion ???
y 1/8 below the baseline
"""
xs = tx.XtraState
leading = xs.style.leading
autoLeading = xs.autoLeading
f = xs.f
if autoLeading == 'max':
# leading = max(leading, f.fontSize)
leading = max(leading, LEADING_FACTOR * f.fontSize)
elif autoLeading == 'min':
leading = LEADING_FACTOR * f.fontSize
ff = 0.125 * f.fontSize
y0 = xs.cur_y
y = y0 - ff
# Background
for x1, x2, c, fs in xs.backgrounds:
inlineFF = fs * 0.125
gap = inlineFF * 1.25
tx._canvas.setFillColor(c)
tx._canvas.rect(x1, y - gap, x2 - x1, fs + 1, fill=1, stroke=0)
xs.backgrounds = []
xs.background = 0
xs.backgroundColor = None
xs.backgroundFontSize = None
# Underline
yUnderline = y0 - 1.5 * ff
tx._canvas.setLineWidth(ff * 0.75)
csc = None
for x1, x2, c in xs.underlines:
if c != csc:
tx._canvas.setStrokeColor(c)
csc = c
tx._canvas.line(x1, yUnderline, x2, yUnderline)
xs.underlines = []
xs.underline = 0
xs.underlineColor = None
# Strike
for x1, x2, c, fs in xs.strikes:
inlineFF = fs * 0.125
ys = y0 + 2 * inlineFF
if c != csc:
tx._canvas.setStrokeColor(c)
csc = c
tx._canvas.setLineWidth(inlineFF * 0.75)
tx._canvas.line(x1, ys, x2, ys)
xs.strikes = []
xs.strike = 0
xs.strikeColor = None
yl = y + leading
for x1, x2, link, c in xs.links:
# No automatic underlining for links, never!
_doLink(tx, link, (x1, y, x2, yl))
xs.links = []
xs.link = None
xs.linkColor = None
xs.cur_y -= leading
def textTransformFrags(frags, style):
tt = style.textTransform
if tt:
tt = tt.lower()
if tt == 'lowercase':
tt = unicode.lower
elif tt == 'uppercase':
tt = unicode.upper
elif tt == 'capitalize':
tt = unicode.title
elif tt == 'none':
return
else:
raise ValueError('ParaStyle.textTransform value %r is invalid' % style.textTransform)
n = len(frags)
if n == 1:
#single fragment the easy case
frags[0].text = tt(frags[0].text.decode('utf8')).encode('utf8')
elif tt is unicode.title:
pb = True
for f in frags:
t = f.text
if not t: continue
u = t.decode('utf8')
if u.startswith(u' ') or pb:
u = tt(u)
else:
i = u.find(u' ')
if i >= 0:
u = u[:i] + tt(u[i:])
pb = u.endswith(u' ')
f.text = u.encode('utf8')
else:
for f in frags:
t = f.text
if not t: continue
f.text = tt(t.decode('utf8')).encode('utf8')
class cjkU(unicode):
"""
simple class to hold the frag corresponding to a str
"""
def __new__(cls, value, frag, encoding):
self = unicode.__new__(cls, value)
self._frag = frag
if hasattr(frag, 'cbDefn'):
w = getattr(frag.cbDefn, 'width', 0)
self._width = w
else:
self._width = stringWidth(value, frag.fontName, frag.fontSize)
return self
frag = property(lambda self: self._frag)
width = property(lambda self: self._width)
def makeCJKParaLine(U, extraSpace, calcBounds):
words = []
CW = []
f0 = FragLine()
maxSize = maxAscent = minDescent = 0
for u in U:
f = u.frag
fontSize = f.fontSize
if calcBounds:
cbDefn = getattr(f, 'cbDefn', None)
if getattr(cbDefn, 'width', 0):
descent, ascent = imgVRange(cbDefn.height, cbDefn.valign, fontSize)
else:
ascent, descent = getAscentDescent(f.fontName, fontSize)
else:
ascent, descent = getAscentDescent(f.fontName, fontSize)
maxSize = max(maxSize, fontSize)
maxAscent = max(maxAscent, ascent)
minDescent = min(minDescent, descent)
if not _sameFrag(f0, f):
f0 = f0.clone()
f0.text = u''.join(CW)
words.append(f0)
CW = []
f0 = f
CW.append(u)
if CW:
f0 = f0.clone()
f0.text = u''.join(CW)
words.append(f0)
return FragLine(kind=1, extraSpace=extraSpace, wordCount=1, words=words[1:], fontSize=maxSize, ascent=maxAscent,
descent=minDescent)
def cjkFragSplit(frags, maxWidths, calcBounds, encoding='utf8'):
"""
This attempts to be wordSplit for frags using the dumb algorithm
"""
from reportlab.rl_config import _FUZZ
U = [] # get a list of single glyphs with their widths etc etc
for f in frags:
text = f.text
if not isinstance(text, unicode):
text = text.decode(encoding)
if text:
U.extend([cjkU(t, f, encoding) for t in text])
else:
U.append(cjkU(text, f, encoding))
lines = []
widthUsed = lineStartPos = 0
maxWidth = maxWidths[0]
for i, u in enumerate(U):
w = u.width
widthUsed += w
lineBreak = hasattr(u.frag, 'lineBreak')
endLine = (widthUsed > maxWidth + _FUZZ and widthUsed > 0) or lineBreak
if endLine:
if lineBreak: continue
extraSpace = maxWidth - widthUsed + w
#This is the most important of the Japanese typography rules.
#if next character cannot start a line, wrap it up to this line so it hangs
#in the right margin. We won't do two or more though - that's unlikely and
#would result in growing ugliness.
nextChar = U[i]
if nextChar in ALL_CANNOT_START:
extraSpace -= w
i += 1
lines.append(makeCJKParaLine(U[lineStartPos:i], extraSpace, calcBounds))
try:
maxWidth = maxWidths[len(lines)]
except IndexError:
maxWidth = maxWidths[-1] # use the last one
lineStartPos = i
widthUsed = w
i -= 1
#any characters left?
if widthUsed > 0:
lines.append(makeCJKParaLine(U[lineStartPos:], maxWidth - widthUsed, calcBounds))
return ParaLines(kind=1, lines=lines)
class Paragraph(Flowable):
"""
Paragraph(text, style, bulletText=None, caseSensitive=1)
text a string of stuff to go into the paragraph.
style is a style definition as in reportlab.lib.styles.
bulletText is an optional bullet defintion.
caseSensitive set this to 0 if you want the markup tags and their attributes to be case-insensitive.
This class is a flowable that can format a block of text
into a paragraph with a given style.
The paragraph Text can contain XML-like markup including the tags:
<b> ... </b> - bold
<i> ... </i> - italics
<u> ... </u> - underline
<strike> ... </strike> - strike through
<super> ... </super> - superscript
<sub> ... </sub> - subscript
<font name=fontfamily/fontname color=colorname size=float>
<onDraw name=callable label="a label">
<link>link text</link>
attributes of links
size/fontSize=num
name/face/fontName=name
fg/textColor/color=color
backcolor/backColor/bgcolor=color
dest/destination/target/href/link=target
<a>anchor text</a>
attributes of anchors
fontSize=num
fontName=name
fg/textColor/color=color
backcolor/backColor/bgcolor=color
href=href
<a name="anchorpoint"/>
<unichar name="unicode character name"/>
<unichar value="unicode code point"/>
<img src="path" width="1in" height="1in" valign="bottom"/>
The whole may be surrounded by <para> </para> tags
The <b> and <i> tags will work for the built-in fonts (Helvetica
/Times / Courier). For other fonts you need to register a family
of 4 fonts using reportlab.pdfbase.pdfmetrics.registerFont; then
use the addMapping function to tell the library that these 4 fonts
form a family e.g.
from reportlab.lib.fonts import addMapping
addMapping('Vera', 0, 0, 'Vera') #normal
addMapping('Vera', 0, 1, 'Vera-Italic') #italic
addMapping('Vera', 1, 0, 'Vera-Bold') #bold
addMapping('Vera', 1, 1, 'Vera-BoldItalic') #italic and bold
It will also be able to handle any MathML specified Greek characters.
"""
def __init__(self, text, style, bulletText=None, frags=None, caseSensitive=1, encoding='utf8'):
self.caseSensitive = caseSensitive
self.encoding = encoding
self._setup(text, style, bulletText, frags, cleanBlockQuotedText)
def __repr__(self):
n = self.__class__.__name__
L = [n + "("]
keys = self.__dict__.keys()
for k in keys:
v = getattr(self, k)
rk = repr(k)
rv = repr(v)
rk = " " + rk.replace("\n", "\n ")
rv = " " + rk.replace("\n", "\n ")
L.append(rk)
L.append(rv)
L.append(") #" + n)
return '\n'.join(L)
def _setup(self, text, style, bulletText, frags, cleaner):
if frags is None:
text = cleaner(text)
_parser.caseSensitive = self.caseSensitive
style, frags, bulletTextFrags = _parser.parse(text, style)
if frags is None:
raise ValueError("xml parser error (%s) in paragraph beginning\n'%s'" \
% (_parser.errors[0], text[:min(30, len(text))]))
textTransformFrags(frags, style)
if bulletTextFrags: bulletText = bulletTextFrags
#AR hack
self.text = text
self.frags = frags
self.style = style
self.bulletText = bulletText
self.debug = PARAGRAPH_DEBUG # turn this on to see a pretty one with all the margins etc.
def wrap(self, availWidth, availHeight):
if self.debug:
print (id(self), "wrap")
try:
print (repr(self.getPlainText()[:80]))
except:
print ("???")
# work out widths array for breaking
self.width = availWidth
style = self.style
leftIndent = style.leftIndent
first_line_width = availWidth - (leftIndent + style.firstLineIndent) - style.rightIndent
later_widths = availWidth - leftIndent - style.rightIndent
if style.wordWrap == 'CJK':
#use Asian text wrap algorithm to break characters
blPara = self.breakLinesCJK([first_line_width, later_widths])
else:
blPara = self.breakLines([first_line_width, later_widths])
self.blPara = blPara
autoLeading = getattr(self, 'autoLeading', getattr(style, 'autoLeading', ''))