/usr/lib/python2.7/dist-packages/sx/pisa3/reportlab_paragraph.py is in python-pisa 3.0.32-3.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 | # -*- 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
__version__=''' $Id: paragraph.py 3307 2008-10-13 15:28:30Z rgbecker $ '''
from string import join, whitespace
from operator import truth
from types import StringType, ListType
from reportlab.pdfbase.pdfmetrics import stringWidth, getFont, 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.utils import _className
from reportlab.lib.textsplit import wordSplit, 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
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
# print "draw", id(f), id(cbDefn.image), repr(dal), cur_y, iy0, iy1, h
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)
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)
# print "#", repr(f.text), f.fontSize, f.backColor, f.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)
# XXX Modified for XHTML2PDF
# !!! Important, don't import accelerators !!!
#try:
# from _rl_accel import _sameFrag
#except ImportError:
# try:
# from reportlab.lib._rl_accel import _sameFrag
# except ImportError:
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
#del f.text # we can't do this until we sort out splitting
# of paragraphs
if text!='':
if hangingStrip:
hangingStrip = False
text = text.lstrip()
#if type(text) is str:
# text = text.decode('utf8')
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 = lim - 1
nSpaces = 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)
# tx._canvas.rect(x1, y, x2 - x1, fs, 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',''))
leading = style.leading
if blPara.kind==1 and autoLeading not in ('','off'):
height = 0
if autoLeading=='max':
for l in blPara.lines:
height += max(l.ascent-l.descent,leading)
elif autoLeading=='min':
for l in blPara.lines:
height += l.ascent - l.descent
else:
raise ValueError('invalid autoLeading value %r' % autoLeading)
else:
if autoLeading=='max':
leading = max(leading,LEADING_FACTOR*style.fontSize)
elif autoLeading=='min':
leading = LEADING_FACTOR*style.fontSize
height = len(blPara.lines) * leading
self.height = height
return self.width, height
def minWidth(self):
'Attempt to determine a minimum sensible width'
frags = self.frags
nFrags= len(frags)
if not nFrags: return 0
if nFrags==1:
f = frags[0]
fS = f.fontSize
fN = f.fontName
words = hasattr(f,'text') and split(f.text, ' ') or f.words
func = lambda w, fS=fS, fN=fN: stringWidth(w,fN,fS)
else:
words = _getFragWords(frags)
func = lambda x: x[0]
return max(map(func,words))
def _get_split_blParaFunc(self):
return self.blPara.kind==0 and _split_blParaSimple or _split_blParaHard
def split(self,availWidth, availHeight):
if self.debug:
print id(self), "split"
if len(self.frags)<=0: return []
#the split information is all inside self.blPara
if not hasattr(self,'blPara'):
# return []
self.wrap(availWidth,availHeight)
blPara = self.blPara
style = self.style
autoLeading = getattr(self,'autoLeading',getattr(style,'autoLeading',''))
leading = style.leading
lines = blPara.lines
if blPara.kind==1 and autoLeading not in ('','off'):
s = height = 0
if autoLeading=='max':
for i,l in enumerate(blPara.lines):
h = max(l.ascent-l.descent,leading)
n = height+h
if n>availHeight+1e-8:
break
height = n
s = i+1
elif autoLeading=='min':
for i,l in enumerate(blPara.lines):
n = height+l.ascent-l.descent
if n>availHeight+1e-8:
break
height = n
s = i+1
else:
raise ValueError('invalid autoLeading value %r' % autoLeading)
else:
l = leading
if autoLeading=='max':
l = max(leading,LEADING_FACTOR*style.fontSize)
elif autoLeading=='min':
l = LEADING_FACTOR*style.fontSize
s = int(availHeight/l)
height = s*l
n = len(lines)
allowWidows = getattr(self,'allowWidows',getattr(self,'allowWidows',1))
allowOrphans = getattr(self,'allowOrphans',getattr(self,'allowOrphans',0))
if not allowOrphans:
if s<=1: #orphan?
del self.blPara
return []
if n<=s: return [self]
if not allowWidows:
if n==s+1: #widow?
if (allowOrphans and n==3) or n>3:
s -= 1 #give the widow some company
else:
del self.blPara #no room for adjustment; force the whole para onwards
return []
func = self._get_split_blParaFunc()
P1=self.__class__(None,style,bulletText=self.bulletText,frags=func(blPara,0,s))
#this is a major hack
P1.blPara = ParaLines(kind=1,lines=blPara.lines[0:s],aH=availHeight,aW=availWidth)
P1._JustifyLast = 1
P1._splitpara = 1
P1.height = height
P1.width = availWidth
if style.firstLineIndent != 0:
style = deepcopy(style)
style.firstLineIndent = 0
P2=self.__class__(None,style,bulletText=None,frags=func(blPara,s,n))
for a in ('autoLeading', #possible attributes that might be directly on self.
):
if hasattr(self,a):
setattr(P1,a,getattr(self,a))
setattr(P2,a,getattr(self,a))
return [P1,P2]
def draw(self):
#call another method for historical reasons. Besides, I
#suspect I will be playing with alternate drawing routines
#so not doing it here makes it easier to switch.
self.drawPara(self.debug)
def breakLines(self, width):
"""
Returns a broken line structure. There are two cases
A) For the simple case of a single formatting input fragment the output is
A fragment specifier with
- kind = 0
- fontName, fontSize, leading, textColor
- lines= A list of lines
Each line has two items.
1. unused width in points
2. word list
B) When there is more than one input formatting fragment the output is
A fragment specifier with
- kind = 1
- lines= A list of fragments each having fields
- extraspace (needed for justified)
- fontSize
- words=word list
each word is itself a fragment with
various settings
This structure can be used to easily draw paragraphs with the various alignments.
You can supply either a single width or a list of widths; the latter will have its
last item repeated until necessary. A 2-element list is useful when there is a
different first line indent; a longer list could be created to facilitate custom wraps
around irregular objects."""
if self.debug:
print id(self), "breakLines"
if not isinstance(width,(tuple,list)): maxWidths = [width]
else: maxWidths = width
lines = []
lineno = 0
style = self.style
#for bullets, work out width and ensure we wrap the right amount onto line one
_handleBulletWidth(self.bulletText,style,maxWidths)
maxWidth = maxWidths[0]
self.height = 0
autoLeading = getattr(self,'autoLeading',getattr(style,'autoLeading',''))
calcBounds = autoLeading not in ('','off')
frags = self.frags
nFrags= len(frags)
if nFrags==1 and not hasattr(frags[0],'cbDefn'):
f = frags[0]
fontSize = f.fontSize
fontName = f.fontName
ascent, descent = getAscentDescent(fontName,fontSize)
words = hasattr(f,'text') and split(f.text, ' ') or f.words
spaceWidth = stringWidth(' ', fontName, fontSize, self.encoding)
cLine = []
currentWidth = -spaceWidth # hack to get around extra space for word 1
for word in words:
#this underscores my feeling that Unicode throughout would be easier!
wordWidth = stringWidth(word, fontName, fontSize, self.encoding)
newWidth = currentWidth + spaceWidth + wordWidth
if newWidth <= maxWidth or not len(cLine):
# fit one more on this line
cLine.append(word)
currentWidth = newWidth
else:
if currentWidth > self.width: self.width = currentWidth
#end of line
lines.append((maxWidth - currentWidth, cLine))
cLine = [word]
currentWidth = wordWidth
lineno += 1
try:
maxWidth = maxWidths[lineno]
except IndexError:
maxWidth = maxWidths[-1] # use the last one
#deal with any leftovers on the final line
if cLine!=[]:
if currentWidth>self.width: self.width = currentWidth
lines.append((maxWidth - currentWidth, cLine))
return f.clone(kind=0, lines=lines,ascent=ascent,descent=descent,fontSize=fontSize)
elif nFrags<=0:
return ParaLines(kind=0, fontSize=style.fontSize, fontName=style.fontName,
textColor=style.textColor, ascent=style.fontSize,descent=-0.2*style.fontSize,
lines=[])
else:
if hasattr(self,'blPara') and getattr(self,'_splitpara',0):
#NB this is an utter hack that awaits the proper information
#preserving splitting algorithm
return self.blPara
n = 0
words = []
for w in _getFragWords(frags):
f=w[-1][0]
fontName = f.fontName
fontSize = f.fontSize
spaceWidth = stringWidth(' ',fontName, fontSize)
if not words:
currentWidth = -spaceWidth # hack to get around extra space for word 1
maxSize = fontSize
maxAscent, minDescent = getAscentDescent(fontName,fontSize)
wordWidth = w[0]
f = w[1][0]
if wordWidth>0:
newWidth = currentWidth + spaceWidth + wordWidth
else:
newWidth = currentWidth
#test to see if this frag is a line break. If it is we will only act on it
#if the current width is non-negative or the previous thing was a deliberate lineBreak
lineBreak = hasattr(f,'lineBreak')
endLine = (newWidth>maxWidth and n>0) or lineBreak
if not endLine:
if lineBreak: continue #throw it away
nText = w[1][1]
if nText: n += 1
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 words:
g = f.clone()
words = [g]
g.text = nText
elif not _sameFrag(g,f):
if currentWidth>0 and ((nText!='' and nText[0]!=' ') or hasattr(f,'cbDefn')):
if hasattr(g,'cbDefn'):
i = len(words)-1
while i>=0:
wi = words[i]
cbDefn = getattr(wi,'cbDefn',None)
if cbDefn:
if not getattr(cbDefn,'width',0):
i -= 1
continue
if not wi.text.endswith(' '):
wi.text += ' '
break
else:
if not g.text.endswith(' '):
g.text += ' '
g = f.clone()
words.append(g)
g.text = nText
else:
if nText!='' and nText[0]!=' ':
g.text += ' ' + nText
for i in w[2:]:
g = i[0].clone()
g.text=i[1]
words.append(g)
fontSize = g.fontSize
if calcBounds:
cbDefn = getattr(g,'cbDefn',None)
if getattr(cbDefn,'width',0):
descent,ascent = imgVRange(cbDefn.height,cbDefn.valign,fontSize)
else:
ascent, descent = getAscentDescent(g.fontName,fontSize)
else:
ascent, descent = getAscentDescent(g.fontName,fontSize)
maxSize = max(maxSize,fontSize)
maxAscent = max(maxAscent,ascent)
minDescent = min(minDescent,descent)
currentWidth = newWidth
else: #either it won't fit, or it's a lineBreak tag
if lineBreak:
g = f.clone()
#del g.lineBreak
words.append(g)
if currentWidth>self.width: self.width = currentWidth
#end of line
lines.append(FragLine(extraSpace=maxWidth-currentWidth, wordCount=n,
lineBreak=lineBreak, words=words, fontSize=maxSize, ascent=maxAscent, descent=minDescent))
#start new line
lineno += 1
try:
maxWidth = maxWidths[lineno]
except IndexError:
maxWidth = maxWidths[-1] # use the last one
if lineBreak:
n = 0
words = []
continue
currentWidth = wordWidth
n = 1
g = f.clone()
maxSize = g.fontSize
if calcBounds:
cbDefn = getattr(g,'cbDefn',None)
if getattr(cbDefn,'width',0):
minDescent,maxAscent = imgVRange(cbDefn.height,cbDefn.valign,maxSize)
else:
maxAscent, minDescent = getAscentDescent(g.fontName,maxSize)
else:
maxAscent, minDescent = getAscentDescent(g.fontName,maxSize)
words = [g]
g.text = w[1][1]
for i in w[2:]:
g = i[0].clone()
g.text=i[1]
words.append(g)
fontSize = g.fontSize
if calcBounds:
cbDefn = getattr(g,'cbDefn',None)
if getattr(cbDefn,'width',0):
descent,ascent = imgVRange(cbDefn.height,cbDefn.valign,fontSize)
else:
ascent, descent = getAscentDescent(g.fontName,fontSize)
else:
ascent, descent = getAscentDescent(g.fontName,fontSize)
maxSize = max(maxSize,fontSize)
maxAscent = max(maxAscent,ascent)
minDescent = min(minDescent,descent)
#deal with any leftovers on the final line
if words!=[]:
if currentWidth>self.width: self.width = currentWidth
lines.append(ParaLines(extraSpace=(maxWidth - currentWidth),wordCount=n,
words=words, fontSize=maxSize,ascent=maxAscent,descent=minDescent))
return ParaLines(kind=1, lines=lines)
return lines
def breakLinesCJK(self, width):
"""Initially, the dumbest possible wrapping algorithm.
Cannot handle font variations."""
if self.debug:
print id(self), "breakLinesCJK"
if not isinstance(width,(list,tuple)): maxWidths = [width]
else: maxWidths = width
style = self.style
#for bullets, work out width and ensure we wrap the right amount onto line one
_handleBulletWidth(self.bulletText, style, maxWidths)
if len(self.frags)>1:
autoLeading = getattr(self,'autoLeading',getattr(style,'autoLeading',''))
calcBounds = autoLeading not in ('','off')
return cjkFragSplit(self.frags, maxWidths, calcBounds)
#raise ValueError('CJK Wordwrap can only handle one fragment per paragraph for now. Tried to handle:\ntext: %s\nfrags: %s' % (self.text, self.frags))
elif not len(self.frags):
return ParaLines(kind=0, fontSize=style.fontSize, fontName=style.fontName,
textColor=style.textColor, lines=[],ascent=style.fontSize,descent=-0.2*style.fontSize)
f = self.frags[0]
if 1 and hasattr(self,'blPara') and getattr(self,'_splitpara',0):
#NB this is an utter hack that awaits the proper information
#preserving splitting algorithm
return f.clone(kind=0, lines=self.blPara.lines)
lines = []
lineno = 0
self.height = 0
f = self.frags[0]
if hasattr(f,'text'):
text = f.text
else:
text = ''.join(getattr(f,'words',[]))
from reportlab.lib.textsplit import wordSplit
lines = wordSplit(text, maxWidths[0], f.fontName, f.fontSize)
#the paragraph drawing routine assumes multiple frags per line, so we need an
#extra list like this
# [space, [text]]
#
wrappedLines = [(sp, [line]) for (sp, line) in lines]
return f.clone(kind=0, lines=wrappedLines, ascent=f.fontSize, descent=-0.2*f.fontSize)
def beginText(self, x, y):
return self.canv.beginText(x, y)
def drawPara(self,debug=0):
"""Draws a paragraph according to the given style.
Returns the final y position at the bottom. Not safe for
paragraphs without spaces e.g. Japanese; wrapping
algorithm will go infinite."""
if self.debug:
print id(self), "drawPara", self.blPara.kind
#stash the key facts locally for speed
canvas = self.canv
style = self.style
blPara = self.blPara
lines = blPara.lines
leading = style.leading
autoLeading = getattr(self,'autoLeading',getattr(style,'autoLeading',''))
#work out the origin for line 1
leftIndent = style.leftIndent
cur_x = leftIndent
if debug:
bw = 0.5
bc = Color(1,1,0)
bg = Color(0.9,0.9,0.9)
else:
bw = getattr(style,'borderWidth',None)
bc = getattr(style,'borderColor',None)
bg = style.backColor
#if has a background or border, draw it
if bg or (bc and bw):
canvas.saveState()
op = canvas.rect
kwds = dict(fill=0,stroke=0)
if bc and bw:
canvas.setStrokeColor(bc)
canvas.setLineWidth(bw)
kwds['stroke'] = 1
br = getattr(style,'borderRadius',0)
if br and not debug:
op = canvas.roundRect
kwds['radius'] = br
if bg:
canvas.setFillColor(bg)
kwds['fill'] = 1
bp = getattr(style,'borderPadding',0)
op(leftIndent-bp,
-bp,
self.width - (leftIndent+style.rightIndent)+2*bp,
self.height+2*bp,
**kwds)
canvas.restoreState()
nLines = len(lines)
bulletText = self.bulletText
if nLines > 0:
_offsets = getattr(self,'_offsets',[0])
_offsets += (nLines-len(_offsets))*[_offsets[-1]]
canvas.saveState()
#canvas.addLiteral('%% %s.drawPara' % _className(self))
alignment = style.alignment
offset = style.firstLineIndent+_offsets[0]
lim = nLines-1
noJustifyLast = not (hasattr(self,'_JustifyLast') and self._JustifyLast)
if blPara.kind==0:
if alignment == TA_LEFT:
dpl = _leftDrawParaLine
elif alignment == TA_CENTER:
dpl = _centerDrawParaLine
elif self.style.alignment == TA_RIGHT:
dpl = _rightDrawParaLine
elif self.style.alignment == TA_JUSTIFY:
dpl = _justifyDrawParaLine
f = blPara
cur_y = self.height - getattr(f,'ascent',f.fontSize) #TODO fix XPreformatted to remove this hack
if bulletText:
offset = _drawBullet(canvas,offset,cur_y,bulletText,style)
#set up the font etc.
canvas.setFillColor(f.textColor)
tx = self.beginText(cur_x, cur_y)
if autoLeading=='max':
leading = max(leading,LEADING_FACTOR*f.fontSize)
elif autoLeading=='min':
leading = LEADING_FACTOR*f.fontSize
#now the font for the rest of the paragraph
tx.setFont(f.fontName, f.fontSize, leading)
ws = lines[0][0]
t_off = dpl( tx, offset, ws, lines[0][1], noJustifyLast and nLines==1)
if f.underline or f.link or f.strike:
xs = tx.XtraState = ABag()
xs.cur_y = cur_y
xs.f = f
xs.style = style
xs.lines = lines
xs.underlines = []
xs.underlineColor = None
# XXX Modified for XHTML2PDF
xs.backgrounds = []
xs.backgroundColor = None
xs.backgroundFontSize = None
xs.strikes = []
xs.strikeColor = None
# XXX Modified for XHTML2PDF
xs.strikeFontSize = None
xs.links = []
xs.link = f.link
canvas.setStrokeColor(f.textColor)
dx = t_off + leftIndent
if dpl != _justifyDrawParaLine: ws = 0
# XXX Never underline!
underline = f.underline
strike = f.strike
link = f.link
if underline: _do_under_line(0, dx, ws, tx)
if strike: _do_under_line(0, dx, ws, tx, lm=0.125)
if link: _do_link_line(0, dx, ws, tx)
#now the middle of the paragraph, aligned with the left margin which is our origin.
for i in xrange(1, nLines):
ws = lines[i][0]
t_off = dpl( tx, _offsets[i], ws, lines[i][1], noJustifyLast and i==lim)
if dpl!=_justifyDrawParaLine: ws = 0
if underline: _do_under_line(i, t_off+leftIndent, ws, tx)
if strike: _do_under_line(i, t_off+leftIndent, ws, tx, lm=0.125)
if link: _do_link_line(i, t_off+leftIndent, ws, tx)
else:
for i in xrange(1, nLines):
dpl( tx, _offsets[i], lines[i][0], lines[i][1], noJustifyLast and i==lim)
else:
f = lines[0]
cur_y = self.height - getattr(f,'ascent',f.fontSize) #TODO fix XPreformatted to remove this hack
# default?
dpl = _leftDrawParaLineX
if bulletText:
oo = offset
offset = _drawBullet(canvas,offset,cur_y,bulletText,style)
if alignment == TA_LEFT:
dpl = _leftDrawParaLineX
elif alignment == TA_CENTER:
dpl = _centerDrawParaLineX
elif self.style.alignment == TA_RIGHT:
dpl = _rightDrawParaLineX
elif self.style.alignment == TA_JUSTIFY:
dpl = _justifyDrawParaLineX
else:
raise ValueError("bad align %s" % repr(alignment))
#set up the font etc.
tx = self.beginText(cur_x, cur_y)
xs = tx.XtraState = ABag()
xs.textColor = None
# XXX Modified for XHTML2PDF
xs.backColor = None
xs.rise = 0
xs.underline = 0
xs.underlines = []
xs.underlineColor = None
# XXX Modified for XHTML2PDF
xs.background = 0
xs.backgrounds = []
xs.backgroundColor = None
xs.backgroundFontSize = None
xs.strike = 0
xs.strikes = []
xs.strikeColor = None
# XXX Modified for XHTML2PDF
xs.strikeFontSize = None
xs.links = []
xs.link = None
xs.leading = style.leading
xs.leftIndent = leftIndent
tx._leading = None
tx._olb = None
xs.cur_y = cur_y
xs.f = f
xs.style = style
xs.autoLeading = autoLeading
tx._fontname,tx._fontsize = None, None
dpl( tx, offset, lines[0], noJustifyLast and nLines==1)
_do_post_text(tx)
#now the middle of the paragraph, aligned with the left margin which is our origin.
for i in xrange(1, nLines):
f = lines[i]
dpl( tx, _offsets[i], f, noJustifyLast and i==lim)
_do_post_text(tx)
canvas.drawText(tx)
canvas.restoreState()
def getPlainText(self,identify=None):
"""Convenience function for templates which want access
to the raw text, without XML tags. """
frags = getattr(self,'frags',None)
if frags:
plains = []
for frag in frags:
if hasattr(frag, 'text'):
plains.append(frag.text)
return join(plains, '')
elif identify:
text = getattr(self,'text',None)
if text is None: text = repr(self)
return text
else:
return ''
def getActualLineWidths0(self):
"""Convenience function; tells you how wide each line
actually is. For justified styles, this will be
the same as the wrap width; for others it might be
useful for seeing if paragraphs will fit in spaces."""
assert hasattr(self, 'width'), "Cannot call this method before wrap()"
if self.blPara.kind:
func = lambda frag, w=self.width: w - frag.extraSpace
else:
func = lambda frag, w=self.width: w - frag[0]
return map(func,self.blPara.lines)
if __name__=='__main__': #NORUNTESTS
def dumpParagraphLines(P):
print 'dumpParagraphLines(<Paragraph @ %d>)' % id(P)
lines = P.blPara.lines
for l,line in enumerate(lines):
line = lines[l]
if hasattr(line,'words'):
words = line.words
else:
words = line[1]
nwords = len(words)
print 'line%d: %d(%s)\n ' % (l,nwords,str(getattr(line,'wordCount','Unknown'))),
for w in xrange(nwords):
print "%d:'%s'"%(w,getattr(words[w],'text',words[w])),
print
def fragDump(w):
R= ["'%s'" % w[1]]
for a in ('fontName', 'fontSize', 'textColor', 'rise', 'underline', 'strike', 'link', 'cbDefn','lineBreak'):
if hasattr(w[0],a):
R.append('%s=%r' % (a,getattr(w[0],a)))
return ', '.join(R)
def dumpParagraphFrags(P):
print 'dumpParagraphFrags(<Paragraph @ %d>) minWidth() = %.2f' % (id(P), P.minWidth())
frags = P.frags
n =len(frags)
for l in xrange(n):
print "frag%d: '%s' %s" % (l, frags[l].text,' '.join(['%s=%s' % (k,getattr(frags[l],k)) for k in frags[l].__dict__ if k!=text]))
l = 0
cum = 0
for W in _getFragWords(frags):
cum += W[0]
print "fragword%d: cum=%3d size=%d" % (l, cum, W[0]),
for w in W[1:]:
print '(%s)' % fragDump(w),
print
l += 1
from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
from reportlab.lib.units import cm
import sys
TESTS = sys.argv[1:]
if TESTS==[]: TESTS=['4']
def flagged(i,TESTS=TESTS):
return 'all' in TESTS or '*' in TESTS or str(i) in TESTS
styleSheet = getSampleStyleSheet()
B = styleSheet['BodyText']
style = ParagraphStyle("discussiontext", parent=B)
style.fontName= 'Helvetica'
if flagged(1):
text='''The <font name=courier color=green>CMYK</font> or subtractive method follows the way a printer
mixes three pigments (cyan, magenta, and yellow) to form colors.
Because mixing chemicals is more difficult than combining light there
is a fourth parameter for darkness. For example a chemical
combination of the <font name=courier color=green>CMY</font> pigments generally never makes a perfect
black -- instead producing a muddy color -- so, to get black printers
don't use the <font name=courier color=green>CMY</font> pigments but use a direct black ink. Because
<font name=courier color=green>CMYK</font> maps more directly to the way printer hardware works it may
be the case that &| & | colors specified in <font name=courier color=green>CMYK</font> will provide better fidelity
and better control when printed.
'''
P=Paragraph(text,style)
dumpParagraphFrags(P)
aW, aH = 456.0, 42.8
w,h = P.wrap(aW, aH)
dumpParagraphLines(P)
S = P.split(aW,aH)
for s in S:
s.wrap(aW,aH)
dumpParagraphLines(s)
aH = 500
if flagged(2):
P=Paragraph("""Price<super><font color="red">*</font></super>""", styleSheet['Normal'])
dumpParagraphFrags(P)
w,h = P.wrap(24, 200)
dumpParagraphLines(P)
if flagged(3):
text = """Dieses Kapitel bietet eine schnelle <b><font color=red>Programme :: starten</font></b>
<onDraw name=myIndex label="Programme :: starten">
<b><font color=red>Eingabeaufforderung :: (>>>)</font></b>
<onDraw name=myIndex label="Eingabeaufforderung :: (>>>)">
<b><font color=red>>>> (Eingabeaufforderung)</font></b>
<onDraw name=myIndex label=">>> (Eingabeaufforderung)">
Einführung in Python <b><font color=red>Python :: Einführung</font></b>
<onDraw name=myIndex label="Python :: Einführung">.
Das Ziel ist, die grundlegenden Eigenschaften von Python darzustellen, ohne
sich zu sehr in speziellen Regeln oder Details zu verstricken. Dazu behandelt
dieses Kapitel kurz die wesentlichen Konzepte wie Variablen, Ausdrücke,
Kontrollfluss, Funktionen sowie Ein- und Ausgabe. Es erhebt nicht den Anspruch,
umfassend zu sein."""
P=Paragraph(text, styleSheet['Code'])
dumpParagraphFrags(P)
w,h = P.wrap(6*72, 9.7*72)
dumpParagraphLines(P)
if flagged(4):
text='''Die eingebaute Funktion <font name=Courier>range(i, j [, stride])</font><onDraw name=myIndex label="eingebaute Funktionen::range()"><onDraw name=myIndex label="range() (Funktion)"><onDraw name=myIndex label="Funktionen::range()"> erzeugt eine Liste von Ganzzahlen und füllt sie mit Werten <font name=Courier>k</font>, für die gilt: <font name=Courier>i <= k < j</font>. Man kann auch eine optionale Schrittweite angeben. Die eingebaute Funktion <font name=Courier>xrange()</font><onDraw name=myIndex label="eingebaute Funktionen::xrange()"><onDraw name=myIndex label="xrange() (Funktion)"><onDraw name=myIndex label="Funktionen::xrange()"> erfüllt einen ähnlichen Zweck, gibt aber eine unveränderliche Sequenz vom Typ <font name=Courier>XRangeType</font><onDraw name=myIndex label="XRangeType"> zurück. Anstatt alle Werte in der Liste abzuspeichern, berechnet diese Liste ihre Werte, wann immer sie angefordert werden. Das ist sehr viel speicherschonender, wenn mit sehr langen Listen von Ganzzahlen gearbeitet wird. <font name=Courier>XRangeType</font> kennt eine einzige Methode, <font name=Courier>s.tolist()</font><onDraw name=myIndex label="XRangeType::tolist() (Methode)"><onDraw name=myIndex label="s.tolist() (Methode)"><onDraw name=myIndex label="Methoden::s.tolist()">, die seine Werte in eine Liste umwandelt.'''
aW = 420
aH = 64.4
P=Paragraph(text, B)
dumpParagraphFrags(P)
w,h = P.wrap(aW,aH)
print 'After initial wrap',w,h
dumpParagraphLines(P)
S = P.split(aW,aH)
dumpParagraphFrags(S[0])
w0,h0 = S[0].wrap(aW,aH)
print 'After split wrap',w0,h0
dumpParagraphLines(S[0])
if flagged(5):
text = '<para> %s <![CDATA[</font></b>& %s < >]]></para>' % (chr(163),chr(163))
P=Paragraph(text, styleSheet['Code'])
dumpParagraphFrags(P)
w,h = P.wrap(6*72, 9.7*72)
dumpParagraphLines(P)
if flagged(6):
for text in ['''Here comes <FONT FACE="Helvetica" SIZE="14pt">Helvetica 14</FONT> with <STRONG>strong</STRONG> <EM>emphasis</EM>.''',
'''Here comes <font face="Helvetica" size="14pt">Helvetica 14</font> with <Strong>strong</Strong> <em>emphasis</em>.''',
'''Here comes <font face="Courier" size="3cm">Courier 3cm</font> and normal again.''',
]:
P=Paragraph(text, styleSheet['Normal'], caseSensitive=0)
dumpParagraphFrags(P)
w,h = P.wrap(6*72, 9.7*72)
dumpParagraphLines(P)
if flagged(7):
text = """<para align="CENTER" fontSize="24" leading="30"><b>Generated by:</b>Dilbert</para>"""
P=Paragraph(text, styleSheet['Code'])
dumpParagraphFrags(P)
w,h = P.wrap(6*72, 9.7*72)
dumpParagraphLines(P)
if flagged(8):
text ="""- bullet 0<br/>- bullet 1<br/>- bullet 2<br/>- bullet 3<br/>- bullet 4<br/>- bullet 5"""
P=Paragraph(text, styleSheet['Normal'])
dumpParagraphFrags(P)
w,h = P.wrap(6*72, 9.7*72)
dumpParagraphLines(P)
S = P.split(6*72,h/2.0)
print len(S)
dumpParagraphLines(S[0])
dumpParagraphLines(S[1])
if flagged(9):
text="""Furthermore, the fundamental error of
regarding <img src="../docs/images/testimg.gif" width="3" height="7"/> functional notions as
categorial delimits a general
convention regarding the forms of the<br/>
grammar. I suggested that these results
would follow from the assumption that"""
P=Paragraph(text,ParagraphStyle('aaa',parent=styleSheet['Normal'],align=TA_JUSTIFY))
dumpParagraphFrags(P)
w,h = P.wrap(6*cm-12, 9.7*72)
dumpParagraphLines(P)
if flagged(10):
text="""a b c\xc2\xa0d e f"""
P=Paragraph(text,ParagraphStyle('aaa',parent=styleSheet['Normal'],align=TA_JUSTIFY))
dumpParagraphFrags(P)
w,h = P.wrap(6*cm-12, 9.7*72)
dumpParagraphLines(P)
|