/usr/share/pyshared/reportlab/lib/xmllib.py is in python-reportlab 2.5-1.1build1.
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 | # A parser for XML, using the derived class as static DTD.
# Author: Sjoerd Mullender.
# sgmlop support added by fredrik@pythonware.com (May 19, 1998)
__version__=''' $Id: xmllib.py 3660 2010-02-08 18:17:33Z damian $ '''
__doc__='''From before xmllib was in the Python standard library.
Probably ought to be removed'''
import re
import string
try:
import sgmlop # this works for both builtin on the path or relative
except ImportError:
sgmlop = None
# standard entity defs
ENTITYDEFS = {
'lt': '<',
'gt': '>',
'amp': '&',
'quot': '"',
'apos': '\''
}
# XML parser base class -- find tags and call handler functions.
# Usage: p = XMLParser(); p.feed(data); ...; p.close().
# The dtd is defined by deriving a class which defines methods with
# special names to handle tags: start_foo and end_foo to handle <foo>
# and </foo>, respectively. The data between tags is passed to the
# parser by calling self.handle_data() with some data as argument (the
# data may be split up in arbutrary chunks). Entity references are
# passed by calling self.handle_entityref() with the entity reference
# as argument.
# --------------------------------------------------------------------
# original re-based XML parser
_S = '[ \t\r\n]+'
_opS = '[ \t\r\n]*'
_Name = '[a-zA-Z_:][-a-zA-Z0-9._:]*'
interesting = re.compile('[&<]')
incomplete = re.compile('&(' + _Name + '|#[0-9]*|#x[0-9a-fA-F]*)?|'
'<([a-zA-Z_:][^<>]*|'
'/([a-zA-Z_:][^<>]*)?|'
'![^<>]*|'
'\?[^<>]*)?')
ref = re.compile('&(' + _Name + '|#[0-9]+|#x[0-9a-fA-F]+);?')
entityref = re.compile('&(?P<name>' + _Name + ')[^-a-zA-Z0-9._:]')
charref = re.compile('&#(?P<char>[0-9]+[^0-9]|x[0-9a-fA-F]+[^0-9a-fA-F])')
space = re.compile(_S)
newline = re.compile('\n')
starttagopen = re.compile('<' + _Name)
endtagopen = re.compile('</')
starttagend = re.compile(_opS + '(?P<slash>/?)>')
endbracket = re.compile('>')
tagfind = re.compile(_Name)
cdataopen = re.compile('<!\[CDATA\[')
cdataclose = re.compile('\]\]>')
special = re.compile('<!(?P<special>[^<>]*)>')
procopen = re.compile('<\?(?P<proc>' + _Name + ')' + _S)
procclose = re.compile('\?>')
commentopen = re.compile('<!--')
commentclose = re.compile('-->')
doubledash = re.compile('--')
attrfind = re.compile(
_opS + '(?P<name>' + _Name + ')'
'(' + _opS + '=' + _opS +
'(?P<value>\'[^\']*\'|"[^"]*"|[-a-zA-Z0-9.:+*%?!()_#=~]+))')
class SlowXMLParser:
# Interface -- initialize and reset this instance
def __init__(self, verbose=0):
self.verbose = verbose
self.reset()
# Interface -- reset this instance. Loses all unprocessed data
def reset(self):
self.rawdata = ''
self.stack = []
self.lasttag = '???'
self.nomoretags = 0
self.literal = 0
self.lineno = 1
# For derived classes only -- enter literal mode (CDATA) till EOF
def setnomoretags(self):
self.nomoretags = self.literal = 1
# For derived classes only -- enter literal mode (CDATA)
def setliteral(self, *args):
self.literal = 1
# Interface -- feed some data to the parser. Call this as
# often as you want, with as little or as much text as you
# want (may include '\n'). (This just saves the text, all the
# processing is done by goahead().)
def feed(self, data):
self.rawdata = self.rawdata + data
self.goahead(0)
# Interface -- handle the remaining data
def close(self):
self.goahead(1)
# Interface -- translate references
def translate_references(self, data):
newdata = []
i = 0
while 1:
res = ref.search(data, i)
if res is None:
newdata.append(data[i:])
return string.join(newdata, '')
if data[res.end(0) - 1] != ';':
self.syntax_error(self.lineno,
'; missing after entity/char reference')
newdata.append(data[i:res.start(0)])
str = res.group(1)
if str[0] == '#':
if str[1] == 'x':
newdata.append(chr(string.atoi(str[2:], 16)))
else:
newdata.append(chr(string.atoi(str[1:])))
else:
try:
newdata.append(self.entitydefs[str])
except KeyError:
# can't do it, so keep the entity ref in
newdata.append('&' + str + ';')
i = res.end(0)
# Internal -- handle data as far as reasonable. May leave state
# and data to be processed by a subsequent call. If 'end' is
# true, force handling all data as if followed by EOF marker.
def goahead(self, end):
rawdata = self.rawdata
i = 0
n = len(rawdata)
while i < n:
if self.nomoretags:
data = rawdata[i:n]
self.handle_data(data)
self.lineno = self.lineno + string.count(data, '\n')
i = n
break
res = interesting.search(rawdata, i)
if res:
j = res.start(0)
else:
j = n
if i < j:
data = rawdata[i:j]
self.handle_data(data)
self.lineno = self.lineno + string.count(data, '\n')
i = j
if i == n: break
if rawdata[i] == '<':
if starttagopen.match(rawdata, i):
if self.literal:
data = rawdata[i]
self.handle_data(data)
self.lineno = self.lineno + string.count(data, '\n')
i = i+1
continue
k = self.parse_starttag(i)
if k < 0: break
self.lineno = self.lineno + string.count(rawdata[i:k], '\n')
i = k
continue
if endtagopen.match(rawdata, i):
k = self.parse_endtag(i)
if k < 0: break
self.lineno = self.lineno + string.count(rawdata[i:k], '\n')
i = k
self.literal = 0
continue
if commentopen.match(rawdata, i):
if self.literal:
data = rawdata[i]
self.handle_data(data)
self.lineno = self.lineno + string.count(data, '\n')
i = i+1
continue
k = self.parse_comment(i)
if k < 0: break
self.lineno = self.lineno + string.count(rawdata[i:k], '\n')
i = k
continue
if cdataopen.match(rawdata, i):
k = self.parse_cdata(i)
if k < 0: break
self.lineno = self.lineno + string.count(rawdata[i:i], '\n')
i = k
continue
res = procopen.match(rawdata, i)
if res:
k = self.parse_proc(i, res)
if k < 0: break
self.lineno = self.lineno + string.count(rawdata[i:k], '\n')
i = k
continue
res = special.match(rawdata, i)
if res:
if self.literal:
data = rawdata[i]
self.handle_data(data)
self.lineno = self.lineno + string.count(data, '\n')
i = i+1
continue
self.handle_special(res.group('special'))
self.lineno = self.lineno + string.count(res.group(0), '\n')
i = res.end(0)
continue
elif rawdata[i] == '&':
res = charref.match(rawdata, i)
if res is not None:
i = res.end(0)
if rawdata[i-1] != ';':
self.syntax_error(self.lineno, '; missing in charref')
i = i-1
self.handle_charref(res.group('char')[:-1])
self.lineno = self.lineno + string.count(res.group(0), '\n')
continue
res = entityref.match(rawdata, i)
if res is not None:
i = res.end(0)
if rawdata[i-1] != ';':
self.syntax_error(self.lineno, '; missing in entityref')
i = i-1
self.handle_entityref(res.group('name'))
self.lineno = self.lineno + string.count(res.group(0), '\n')
continue
else:
raise RuntimeError, 'neither < nor & ??'
# We get here only if incomplete matches but
# nothing else
res = incomplete.match(rawdata, i)
if not res:
data = rawdata[i]
self.handle_data(data)
self.lineno = self.lineno + string.count(data, '\n')
i = i+1
continue
j = res.end(0)
if j == n:
break # Really incomplete
self.syntax_error(self.lineno, 'bogus < or &')
data = res.group(0)
self.handle_data(data)
self.lineno = self.lineno + string.count(data, '\n')
i = j
# end while
if end and i < n:
data = rawdata[i:n]
self.handle_data(data)
self.lineno = self.lineno + string.count(data, '\n')
i = n
self.rawdata = rawdata[i:]
# XXX if end: check for empty stack
# Internal -- parse comment, return length or -1 if not terminated
def parse_comment(self, i):
rawdata = self.rawdata
if rawdata[i:i+4] != '<!--':
raise RuntimeError, 'unexpected call to handle_comment'
res = commentclose.search(rawdata, i+4)
if not res:
return -1
# doubledash search will succeed because it's a subset of commentclose
if doubledash.search(rawdata, i+4).start(0) < res.start(0):
self.syntax_error(self.lineno, "'--' inside comment")
self.handle_comment(rawdata[i+4: res.start(0)])
return res.end(0)
# Internal -- handle CDATA tag, return lenth or -1 if not terminated
def parse_cdata(self, i):
rawdata = self.rawdata
if rawdata[i:i+9] != '<![CDATA[':
raise RuntimeError, 'unexpected call to handle_cdata'
res = cdataclose.search(rawdata, i+9)
if not res:
return -1
self.handle_cdata(rawdata[i+9:res.start(0)])
return res.end(0)
def parse_proc(self, i, res):
rawdata = self.rawdata
if not res:
raise RuntimeError, 'unexpected call to parse_proc'
name = res.group('proc')
res = procclose.search(rawdata, res.end(0))
if not res:
return -1
self.handle_proc(name, rawdata[res.pos:res.start(0)])
return res.end(0)
# Internal -- handle starttag, return length or -1 if not terminated
def parse_starttag(self, i):
rawdata = self.rawdata
# i points to start of tag
end = endbracket.search(rawdata, i+1)
if not end:
return -1
j = end.start(0)
# Now parse the data between i+1 and j into a tag and attrs
attrdict = {}
res = tagfind.match(rawdata, i+1)
if not res:
raise RuntimeError, 'unexpected call to parse_starttag'
k = res.end(0)
tag = res.group(0)
if hasattr(self, tag + '_attributes'):
attrlist = getattr(self, tag + '_attributes')
else:
attrlist = None
self.lasttag = tag
while k < j:
res = attrfind.match(rawdata, k)
if not res: break
attrname, attrvalue = res.group('name', 'value')
if attrvalue is None:
self.syntax_error(self.lineno, 'no attribute value specified')
attrvalue = attrname
elif attrvalue[:1] == "'" == attrvalue[-1:] or \
attrvalue[:1] == '"' == attrvalue[-1:]:
attrvalue = attrvalue[1:-1]
else:
self.syntax_error(self.lineno, 'attribute value not quoted')
if attrlist is not None and attrname not in attrlist:
self.syntax_error(self.lineno,
'unknown attribute %s of element %s' %
(attrname, tag))
if attrname in attrdict:
self.syntax_error(self.lineno, 'attribute specified twice')
attrdict[attrname] = self.translate_references(attrvalue)
k = res.end(0)
res = starttagend.match(rawdata, k)
if not res:
self.syntax_error(self.lineno, 'garbage in start tag')
self.finish_starttag(tag, attrdict)
if res and res.group('slash') == '/':
self.finish_endtag(tag)
return end.end(0)
# Internal -- parse endtag
def parse_endtag(self, i):
rawdata = self.rawdata
end = endbracket.search(rawdata, i+1)
if not end:
return -1
res = tagfind.match(rawdata, i+2)
if not res:
self.syntax_error(self.lineno, 'no name specified in end tag')
tag = ''
k = i+2
else:
tag = res.group(0)
k = res.end(0)
if k != end.start(0):
# check that there is only white space at end of tag
res = space.match(rawdata, k)
if res is None or res.end(0) != end.start(0):
self.syntax_error(self.lineno, 'garbage in end tag')
self.finish_endtag(tag)
return end.end(0)
# Internal -- finish processing of start tag
# Return -1 for unknown tag, 1 for balanced tag
def finish_starttag(self, tag, attrs):
self.stack.append(tag)
try:
method = getattr(self, 'start_' + tag)
except AttributeError:
self.unknown_starttag(tag, attrs)
return -1
else:
self.handle_starttag(tag, method, attrs)
return 1
# Internal -- finish processing of end tag
def finish_endtag(self, tag):
if not tag:
found = len(self.stack) - 1
if found < 0:
self.unknown_endtag(tag)
return
else:
if tag not in self.stack:
try:
method = getattr(self, 'end_' + tag)
except AttributeError:
self.unknown_endtag(tag)
return
found = len(self.stack)
for i in range(found):
if self.stack[i] == tag: found = i
while len(self.stack) > found:
tag = self.stack[-1]
try:
method = getattr(self, 'end_' + tag)
except AttributeError:
method = None
if method:
self.handle_endtag(tag, method)
else:
self.unknown_endtag(tag)
del self.stack[-1]
# Overridable -- handle start tag
def handle_starttag(self, tag, method, attrs):
method(attrs)
# Overridable -- handle end tag
def handle_endtag(self, tag, method):
method()
# Example -- handle character reference, no need to override
def handle_charref(self, name):
try:
if name[0] == 'x':
n = string.atoi(name[1:], 16)
else:
n = string.atoi(name)
except string.atoi_error:
self.unknown_charref(name)
return
if not 0 <= n <= 255:
self.unknown_charref(name)
return
self.handle_data(chr(n))
# Definition of entities -- derived classes may override
entitydefs = ENTITYDEFS
# Example -- handle entity reference, no need to override
def handle_entityref(self, name):
table = self.entitydefs
if name in table:
self.handle_data(table[name])
else:
self.unknown_entityref(name)
return
# Example -- handle data, should be overridden
def handle_data(self, data):
pass
# Example -- handle cdata, could be overridden
def handle_cdata(self, data):
pass
# Example -- handle comment, could be overridden
def handle_comment(self, data):
pass
# Example -- handle processing instructions, could be overridden
def handle_proc(self, name, data):
pass
# Example -- handle special instructions, could be overridden
def handle_special(self, data):
pass
# Example -- handle relatively harmless syntax errors, could be overridden
def syntax_error(self, lineno, message):
raise RuntimeError, 'Syntax error at line %d: %s' % (lineno, message)
# To be overridden -- handlers for unknown objects
def unknown_starttag(self, tag, attrs): pass
def unknown_endtag(self, tag): pass
def unknown_charref(self, ref): pass
def unknown_entityref(self, ref): pass
# --------------------------------------------------------------------
# accelerated XML parser
class FastXMLParser:
# Interface -- initialize and reset this instance
def __init__(self, verbose=0):
self.verbose = verbose
self.reset()
# Interface -- reset this instance. Loses all unprocessed data
def reset(self):
self.rawdata = ''
self.stack = []
self.lasttag = '???'
self.nomoretags = 0
self.literal = 0
self.lineno = 1
self.parser = sgmlop.XMLParser()
self.feed = self.parser.feed
self.parser.register(self)
# For derived classes only -- enter literal mode (CDATA) till EOF
def setnomoretags(self):
self.nomoretags = self.literal = 1
# For derived classes only -- enter literal mode (CDATA)
def setliteral(self, *args):
self.literal = 1
# Interface -- feed some data to the parser. Call this as
# often as you want, with as little or as much text as you
# want (may include '\n'). (This just saves the text, all the
# processing is done by goahead().)
def feed(self, data): # overridden by reset
self.parser.feed(data)
# Interface -- handle the remaining data
def close(self):
try:
self.parser.close()
finally:
self.parser = None
# Interface -- translate references
def translate_references(self, data):
newdata = []
i = 0
while 1:
res = ref.search(data, i)
if res is None:
newdata.append(data[i:])
return string.join(newdata, '')
if data[res.end(0) - 1] != ';':
self.syntax_error(self.lineno,
'; missing after entity/char reference')
newdata.append(data[i:res.start(0)])
str = res.group(1)
if str[0] == '#':
if str[1] == 'x':
newdata.append(chr(string.atoi(str[2:], 16)))
else:
newdata.append(chr(string.atoi(str[1:])))
else:
try:
newdata.append(self.entitydefs[str])
except KeyError:
# can't do it, so keep the entity ref in
newdata.append('&' + str + ';')
i = res.end(0)
# Internal -- finish processing of start tag
# Return -1 for unknown tag, 1 for balanced tag
def finish_starttag(self, tag, attrs):
self.stack.append(tag)
try:
method = getattr(self, 'start_' + tag)
except AttributeError:
self.unknown_starttag(tag, attrs)
return -1
else:
self.handle_starttag(tag, method, attrs)
return 1
# Internal -- finish processing of end tag
def finish_endtag(self, tag):
if not tag:
found = len(self.stack) - 1
if found < 0:
self.unknown_endtag(tag)
return
else:
if tag not in self.stack:
try:
method = getattr(self, 'end_' + tag)
except AttributeError:
self.unknown_endtag(tag)
return
found = len(self.stack)
for i in range(found):
if self.stack[i] == tag: found = i
while len(self.stack) > found:
tag = self.stack[-1]
try:
method = getattr(self, 'end_' + tag)
except AttributeError:
method = None
if method:
self.handle_endtag(tag, method)
else:
self.unknown_endtag(tag)
del self.stack[-1]
# Overridable -- handle start tag
def handle_starttag(self, tag, method, attrs):
method(attrs)
# Overridable -- handle end tag
def handle_endtag(self, tag, method):
method()
# Example -- handle character reference, no need to override
def handle_charref(self, name):
try:
if name[0] == 'x':
n = string.atoi(name[1:], 16)
else:
n = string.atoi(name)
except string.atoi_error:
self.unknown_charref(name)
return
if not 0 <= n <= 255:
self.unknown_charref(name)
return
self.handle_data(chr(n))
# Definition of entities -- derived classes may override
entitydefs = ENTITYDEFS
# Example -- handle entity reference, no need to override
def handle_entityref(self, name):
table = self.entitydefs
if name in table:
self.handle_data(table[name])
else:
self.unknown_entityref(name)
return
# Example -- handle data, should be overridden
def handle_data(self, data):
pass
# Example -- handle cdata, could be overridden
def handle_cdata(self, data):
pass
# Example -- handle comment, could be overridden
def handle_comment(self, data):
pass
# Example -- handle processing instructions, could be overridden
def handle_proc(self, name, data):
pass
# Example -- handle special instructions, could be overridden
def handle_special(self, data):
pass
# Example -- handle relatively harmless syntax errors, could be overridden
def syntax_error(self, lineno, message):
raise RuntimeError, 'Syntax error at line %d: %s' % (lineno, message)
# To be overridden -- handlers for unknown objects
def unknown_starttag(self, tag, attrs): pass
def unknown_endtag(self, tag): pass
def unknown_charref(self, ref): pass
def unknown_entityref(self, ref): pass
#sgmlop = None
# pick a suitable parser
if sgmlop:
XMLParser = FastXMLParser
else:
XMLParser = SlowXMLParser
# --------------------------------------------------------------------
# test stuff
class TestXMLParser(XMLParser):
def __init__(self, verbose=0):
self.testdata = ""
XMLParser.__init__(self, verbose)
def handle_data(self, data):
self.testdata = self.testdata + data
if len(repr(self.testdata)) >= 70:
self.flush()
def flush(self):
data = self.testdata
if data:
self.testdata = ""
print 'data:', repr(data)
def handle_cdata(self, data):
self.flush()
print 'cdata:', repr(data)
def handle_proc(self, name, data):
self.flush()
print 'processing:',name,repr(data)
def handle_special(self, data):
self.flush()
print 'special:',repr(data)
def handle_comment(self, data):
self.flush()
r = repr(data)
if len(r) > 68:
r = r[:32] + '...' + r[-32:]
print 'comment:', r
def syntax_error(self, lineno, message):
print 'error at line %d:' % lineno, message
def unknown_starttag(self, tag, attrs):
self.flush()
if not attrs:
print 'start tag: <' + tag + '>'
else:
print 'start tag: <' + tag,
for name, value in attrs.items():
print name + '=' + '"' + value + '"',
print '>'
def unknown_endtag(self, tag):
self.flush()
print 'end tag: </' + tag + '>'
def unknown_entityref(self, ref):
self.flush()
print '*** unknown entity ref: &' + ref + ';'
def unknown_charref(self, ref):
self.flush()
print '*** unknown char ref: &#' + ref + ';'
def close(self):
XMLParser.close(self)
self.flush()
def test(args = None):
import sys
if not args:
args = sys.argv[1:]
if args and args[0] == '-s':
args = args[1:]
klass = XMLParser
else:
klass = TestXMLParser
if args:
file = args[0]
else:
file = 'test.xml'
if file == '-':
f = sys.stdin
else:
try:
f = open(file, 'r')
except IOError, msg:
print file, ":", msg
sys.exit(1)
data = f.read()
if f is not sys.stdin:
f.close()
x = klass()
for c in data:
x.feed(c)
x.close()
if __name__ == '__main__': #NO_REPORTLAB_TEST
test()
|