/usr/lib/python3.5/xml/etree/ElementTree.py is in libpython3.5-stdlib 3.5.1-10.
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 | """Lightweight XML support for Python.
XML is an inherently hierarchical data format, and the most natural way to
represent it is with a tree. This module has two classes for this purpose:
1. ElementTree represents the whole XML document as a tree and
2. Element represents a single node in this tree.
Interactions with the whole document (reading and writing to/from files) are
usually done on the ElementTree level. Interactions with a single XML element
and its sub-elements are done on the Element level.
Element is a flexible container object designed to store hierarchical data
structures in memory. It can be described as a cross between a list and a
dictionary. Each Element has a number of properties associated with it:
'tag' - a string containing the element's name.
'attributes' - a Python dictionary storing the element's attributes.
'text' - a string containing the element's text content.
'tail' - an optional string containing text after the element's end tag.
And a number of child elements stored in a Python sequence.
To create an element instance, use the Element constructor,
or the SubElement factory function.
You can also use the ElementTree class to wrap an element structure
and convert it to and from XML.
"""
#---------------------------------------------------------------------
# Licensed to PSF under a Contributor Agreement.
# See http://www.python.org/psf/license for licensing details.
#
# ElementTree
# Copyright (c) 1999-2008 by Fredrik Lundh. All rights reserved.
#
# fredrik@pythonware.com
# http://www.pythonware.com
# --------------------------------------------------------------------
# The ElementTree toolkit is
#
# Copyright (c) 1999-2008 by Fredrik Lundh
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Secret Labs AB or the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------
__all__ = [
# public symbols
"Comment",
"dump",
"Element", "ElementTree",
"fromstring", "fromstringlist",
"iselement", "iterparse",
"parse", "ParseError",
"PI", "ProcessingInstruction",
"QName",
"SubElement",
"tostring", "tostringlist",
"TreeBuilder",
"VERSION",
"XML", "XMLID",
"XMLParser",
"register_namespace",
]
VERSION = "1.3.0"
import sys
import re
import warnings
import io
import contextlib
from . import ElementPath
class ParseError(SyntaxError):
"""An error when parsing an XML document.
In addition to its exception value, a ParseError contains
two extra attributes:
'code' - the specific exception code
'position' - the line and column of the error
"""
pass
# --------------------------------------------------------------------
def iselement(element):
"""Return True if *element* appears to be an Element."""
return hasattr(element, 'tag')
class Element:
"""An XML element.
This class is the reference implementation of the Element interface.
An element's length is its number of subelements. That means if you
want to check if an element is truly empty, you should check BOTH
its length AND its text attribute.
The element tag, attribute names, and attribute values can be either
bytes or strings.
*tag* is the element name. *attrib* is an optional dictionary containing
element attributes. *extra* are additional element attributes given as
keyword arguments.
Example form:
<tag attrib>text<child/>...</tag>tail
"""
tag = None
"""The element's name."""
attrib = None
"""Dictionary of the element's attributes."""
text = None
"""
Text before first subelement. This is either a string or the value None.
Note that if there is no text, this attribute may be either
None or the empty string, depending on the parser.
"""
tail = None
"""
Text after this element's end tag, but before the next sibling element's
start tag. This is either a string or the value None. Note that if there
was no text, this attribute may be either None or an empty string,
depending on the parser.
"""
def __init__(self, tag, attrib={}, **extra):
if not isinstance(attrib, dict):
raise TypeError("attrib must be dict, not %s" % (
attrib.__class__.__name__,))
attrib = attrib.copy()
attrib.update(extra)
self.tag = tag
self.attrib = attrib
self._children = []
def __repr__(self):
return "<%s %r at %#x>" % (self.__class__.__name__, self.tag, id(self))
def makeelement(self, tag, attrib):
"""Create a new element with the same type.
*tag* is a string containing the element name.
*attrib* is a dictionary containing the element attributes.
Do not call this method, use the SubElement factory function instead.
"""
return self.__class__(tag, attrib)
def copy(self):
"""Return copy of current element.
This creates a shallow copy. Subelements will be shared with the
original tree.
"""
elem = self.makeelement(self.tag, self.attrib)
elem.text = self.text
elem.tail = self.tail
elem[:] = self
return elem
def __len__(self):
return len(self._children)
def __bool__(self):
warnings.warn(
"The behavior of this method will change in future versions. "
"Use specific 'len(elem)' or 'elem is not None' test instead.",
FutureWarning, stacklevel=2
)
return len(self._children) != 0 # emulate old behaviour, for now
def __getitem__(self, index):
return self._children[index]
def __setitem__(self, index, element):
# if isinstance(index, slice):
# for elt in element:
# assert iselement(elt)
# else:
# assert iselement(element)
self._children[index] = element
def __delitem__(self, index):
del self._children[index]
def append(self, subelement):
"""Add *subelement* to the end of this element.
The new element will appear in document order after the last existing
subelement (or directly after the text, if it's the first subelement),
but before the end tag for this element.
"""
self._assert_is_element(subelement)
self._children.append(subelement)
def extend(self, elements):
"""Append subelements from a sequence.
*elements* is a sequence with zero or more elements.
"""
for element in elements:
self._assert_is_element(element)
self._children.extend(elements)
def insert(self, index, subelement):
"""Insert *subelement* at position *index*."""
self._assert_is_element(subelement)
self._children.insert(index, subelement)
def _assert_is_element(self, e):
# Need to refer to the actual Python implementation, not the
# shadowing C implementation.
if not isinstance(e, _Element_Py):
raise TypeError('expected an Element, not %s' % type(e).__name__)
def remove(self, subelement):
"""Remove matching subelement.
Unlike the find methods, this method compares elements based on
identity, NOT ON tag value or contents. To remove subelements by
other means, the easiest way is to use a list comprehension to
select what elements to keep, and then use slice assignment to update
the parent element.
ValueError is raised if a matching element could not be found.
"""
# assert iselement(element)
self._children.remove(subelement)
def getchildren(self):
"""(Deprecated) Return all subelements.
Elements are returned in document order.
"""
warnings.warn(
"This method will be removed in future versions. "
"Use 'list(elem)' or iteration over elem instead.",
DeprecationWarning, stacklevel=2
)
return self._children
def find(self, path, namespaces=None):
"""Find first matching element by tag name or path.
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return the first matching element, or None if no element was found.
"""
return ElementPath.find(self, path, namespaces)
def findtext(self, path, default=None, namespaces=None):
"""Find text for first matching element by tag name or path.
*path* is a string having either an element tag or an XPath,
*default* is the value to return if the element was not found,
*namespaces* is an optional mapping from namespace prefix to full name.
Return text content of first matching element, or default value if
none was found. Note that if an element is found having no text
content, the empty string is returned.
"""
return ElementPath.findtext(self, path, default, namespaces)
def findall(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Returns list containing all matching elements in document order.
"""
return ElementPath.findall(self, path, namespaces)
def iterfind(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return an iterable yielding all matching elements in document order.
"""
return ElementPath.iterfind(self, path, namespaces)
def clear(self):
"""Reset element.
This function removes all subelements, clears all attributes, and sets
the text and tail attributes to None.
"""
self.attrib.clear()
self._children = []
self.text = self.tail = None
def get(self, key, default=None):
"""Get element attribute.
Equivalent to attrib.get, but some implementations may handle this a
bit more efficiently. *key* is what attribute to look for, and
*default* is what to return if the attribute was not found.
Returns a string containing the attribute value, or the default if
attribute was not found.
"""
return self.attrib.get(key, default)
def set(self, key, value):
"""Set element attribute.
Equivalent to attrib[key] = value, but some implementations may handle
this a bit more efficiently. *key* is what attribute to set, and
*value* is the attribute value to set it to.
"""
self.attrib[key] = value
def keys(self):
"""Get list of attribute names.
Names are returned in an arbitrary order, just like an ordinary
Python dict. Equivalent to attrib.keys()
"""
return self.attrib.keys()
def items(self):
"""Get element attributes as a sequence.
The attributes are returned in arbitrary order. Equivalent to
attrib.items().
Return a list of (name, value) tuples.
"""
return self.attrib.items()
def iter(self, tag=None):
"""Create tree iterator.
The iterator loops over the element and all subelements in document
order, returning all elements with a matching tag.
If the tree structure is modified during iteration, new or removed
elements may or may not be included. To get a stable set, use the
list() function on the iterator, and loop over the resulting list.
*tag* is what tags to look for (default is to return all elements)
Return an iterator containing all the matching elements.
"""
if tag == "*":
tag = None
if tag is None or self.tag == tag:
yield self
for e in self._children:
yield from e.iter(tag)
# compatibility
def getiterator(self, tag=None):
# Change for a DeprecationWarning in 1.4
warnings.warn(
"This method will be removed in future versions. "
"Use 'elem.iter()' or 'list(elem.iter())' instead.",
PendingDeprecationWarning, stacklevel=2
)
return list(self.iter(tag))
def itertext(self):
"""Create text iterator.
The iterator loops over the element and all subelements in document
order, returning all inner text.
"""
tag = self.tag
if not isinstance(tag, str) and tag is not None:
return
t = self.text
if t:
yield t
for e in self:
yield from e.itertext()
t = e.tail
if t:
yield t
def SubElement(parent, tag, attrib={}, **extra):
"""Subelement factory which creates an element instance, and appends it
to an existing parent.
The element tag, attribute names, and attribute values can be either
bytes or Unicode strings.
*parent* is the parent element, *tag* is the subelements name, *attrib* is
an optional directory containing element attributes, *extra* are
additional attributes given as keyword arguments.
"""
attrib = attrib.copy()
attrib.update(extra)
element = parent.makeelement(tag, attrib)
parent.append(element)
return element
def Comment(text=None):
"""Comment element factory.
This function creates a special element which the standard serializer
serializes as an XML comment.
*text* is a string containing the comment string.
"""
element = Element(Comment)
element.text = text
return element
def ProcessingInstruction(target, text=None):
"""Processing Instruction element factory.
This function creates a special element which the standard serializer
serializes as an XML comment.
*target* is a string containing the processing instruction, *text* is a
string containing the processing instruction contents, if any.
"""
element = Element(ProcessingInstruction)
element.text = target
if text:
element.text = element.text + " " + text
return element
PI = ProcessingInstruction
class QName:
"""Qualified name wrapper.
This class can be used to wrap a QName attribute value in order to get
proper namespace handing on output.
*text_or_uri* is a string containing the QName value either in the form
{uri}local, or if the tag argument is given, the URI part of a QName.
*tag* is an optional argument which if given, will make the first
argument (text_or_uri) be interpreted as a URI, and this argument (tag)
be interpreted as a local name.
"""
def __init__(self, text_or_uri, tag=None):
if tag:
text_or_uri = "{%s}%s" % (text_or_uri, tag)
self.text = text_or_uri
def __str__(self):
return self.text
def __repr__(self):
return '<%s %r>' % (self.__class__.__name__, self.text)
def __hash__(self):
return hash(self.text)
def __le__(self, other):
if isinstance(other, QName):
return self.text <= other.text
return self.text <= other
def __lt__(self, other):
if isinstance(other, QName):
return self.text < other.text
return self.text < other
def __ge__(self, other):
if isinstance(other, QName):
return self.text >= other.text
return self.text >= other
def __gt__(self, other):
if isinstance(other, QName):
return self.text > other.text
return self.text > other
def __eq__(self, other):
if isinstance(other, QName):
return self.text == other.text
return self.text == other
# --------------------------------------------------------------------
class ElementTree:
"""An XML element hierarchy.
This class also provides support for serialization to and from
standard XML.
*element* is an optional root element node,
*file* is an optional file handle or file name of an XML file whose
contents will be used to initialize the tree with.
"""
def __init__(self, element=None, file=None):
# assert element is None or iselement(element)
self._root = element # first node
if file:
self.parse(file)
def getroot(self):
"""Return root element of this tree."""
return self._root
def _setroot(self, element):
"""Replace root element of this tree.
This will discard the current contents of the tree and replace it
with the given element. Use with care!
"""
# assert iselement(element)
self._root = element
def parse(self, source, parser=None):
"""Load external XML document into element tree.
*source* is a file name or file object, *parser* is an optional parser
instance that defaults to XMLParser.
ParseError is raised if the parser fails to parse the document.
Returns the root element of the given source document.
"""
close_source = False
if not hasattr(source, "read"):
source = open(source, "rb")
close_source = True
try:
if parser is None:
# If no parser was specified, create a default XMLParser
parser = XMLParser()
if hasattr(parser, '_parse_whole'):
# The default XMLParser, when it comes from an accelerator,
# can define an internal _parse_whole API for efficiency.
# It can be used to parse the whole source without feeding
# it with chunks.
self._root = parser._parse_whole(source)
return self._root
while True:
data = source.read(65536)
if not data:
break
parser.feed(data)
self._root = parser.close()
return self._root
finally:
if close_source:
source.close()
def iter(self, tag=None):
"""Create and return tree iterator for the root element.
The iterator loops over all elements in this tree, in document order.
*tag* is a string with the tag name to iterate over
(default is to return all elements).
"""
# assert self._root is not None
return self._root.iter(tag)
# compatibility
def getiterator(self, tag=None):
# Change for a DeprecationWarning in 1.4
warnings.warn(
"This method will be removed in future versions. "
"Use 'tree.iter()' or 'list(tree.iter())' instead.",
PendingDeprecationWarning, stacklevel=2
)
return list(self.iter(tag))
def find(self, path, namespaces=None):
"""Find first matching element by tag name or path.
Same as getroot().find(path), which is Element.find()
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return the first matching element, or None if no element was found.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.find(path, namespaces)
def findtext(self, path, default=None, namespaces=None):
"""Find first matching element by tag name or path.
Same as getroot().findtext(path), which is Element.findtext()
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return the first matching element, or None if no element was found.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.findtext(path, default, namespaces)
def findall(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
Same as getroot().findall(path), which is Element.findall().
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return list containing all matching elements in document order.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.findall(path, namespaces)
def iterfind(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
Same as getroot().iterfind(path), which is element.iterfind()
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return an iterable yielding all matching elements in document order.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.iterfind(path, namespaces)
def write(self, file_or_filename,
encoding=None,
xml_declaration=None,
default_namespace=None,
method=None, *,
short_empty_elements=True):
"""Write element tree to a file as XML.
Arguments:
*file_or_filename* -- file name or a file object opened for writing
*encoding* -- the output encoding (default: US-ASCII)
*xml_declaration* -- bool indicating if an XML declaration should be
added to the output. If None, an XML declaration
is added if encoding IS NOT either of:
US-ASCII, UTF-8, or Unicode
*default_namespace* -- sets the default XML namespace (for "xmlns")
*method* -- either "xml" (default), "html, "text", or "c14n"
*short_empty_elements* -- controls the formatting of elements
that contain no content. If True (default)
they are emitted as a single self-closed
tag, otherwise they are emitted as a pair
of start/end tags
"""
if not method:
method = "xml"
elif method not in _serialize:
raise ValueError("unknown method %r" % method)
if not encoding:
if method == "c14n":
encoding = "utf-8"
else:
encoding = "us-ascii"
enc_lower = encoding.lower()
with _get_writer(file_or_filename, enc_lower) as write:
if method == "xml" and (xml_declaration or
(xml_declaration is None and
enc_lower not in ("utf-8", "us-ascii", "unicode"))):
declared_encoding = encoding
if enc_lower == "unicode":
# Retrieve the default encoding for the xml declaration
import locale
declared_encoding = locale.getpreferredencoding()
write("<?xml version='1.0' encoding='%s'?>\n" % (
declared_encoding,))
if method == "text":
_serialize_text(write, self._root)
else:
qnames, namespaces = _namespaces(self._root, default_namespace)
serialize = _serialize[method]
serialize(write, self._root, qnames, namespaces,
short_empty_elements=short_empty_elements)
def write_c14n(self, file):
# lxml.etree compatibility. use output method instead
return self.write(file, method="c14n")
# --------------------------------------------------------------------
# serialization support
@contextlib.contextmanager
def _get_writer(file_or_filename, encoding):
# returns text write method and release all resources after using
try:
write = file_or_filename.write
except AttributeError:
# file_or_filename is a file name
if encoding == "unicode":
file = open(file_or_filename, "w")
else:
file = open(file_or_filename, "w", encoding=encoding,
errors="xmlcharrefreplace")
with file:
yield file.write
else:
# file_or_filename is a file-like object
# encoding determines if it is a text or binary writer
if encoding == "unicode":
# use a text writer as is
yield write
else:
# wrap a binary writer with TextIOWrapper
with contextlib.ExitStack() as stack:
if isinstance(file_or_filename, io.BufferedIOBase):
file = file_or_filename
elif isinstance(file_or_filename, io.RawIOBase):
file = io.BufferedWriter(file_or_filename)
# Keep the original file open when the BufferedWriter is
# destroyed
stack.callback(file.detach)
else:
# This is to handle passed objects that aren't in the
# IOBase hierarchy, but just have a write method
file = io.BufferedIOBase()
file.writable = lambda: True
file.write = write
try:
# TextIOWrapper uses this methods to determine
# if BOM (for UTF-16, etc) should be added
file.seekable = file_or_filename.seekable
file.tell = file_or_filename.tell
except AttributeError:
pass
file = io.TextIOWrapper(file,
encoding=encoding,
errors="xmlcharrefreplace",
newline="\n")
# Keep the original file open when the TextIOWrapper is
# destroyed
stack.callback(file.detach)
yield file.write
def _namespaces(elem, default_namespace=None):
# identify namespaces used in this tree
# maps qnames to *encoded* prefix:local names
qnames = {None: None}
# maps uri:s to prefixes
namespaces = {}
if default_namespace:
namespaces[default_namespace] = ""
def add_qname(qname):
# calculate serialized qname representation
try:
if qname[:1] == "{":
uri, tag = qname[1:].rsplit("}", 1)
prefix = namespaces.get(uri)
if prefix is None:
prefix = _namespace_map.get(uri)
if prefix is None:
prefix = "ns%d" % len(namespaces)
if prefix != "xml":
namespaces[uri] = prefix
if prefix:
qnames[qname] = "%s:%s" % (prefix, tag)
else:
qnames[qname] = tag # default element
else:
if default_namespace:
# FIXME: can this be handled in XML 1.0?
raise ValueError(
"cannot use non-qualified names with "
"default_namespace option"
)
qnames[qname] = qname
except TypeError:
_raise_serialization_error(qname)
# populate qname and namespaces table
for elem in elem.iter():
tag = elem.tag
if isinstance(tag, QName):
if tag.text not in qnames:
add_qname(tag.text)
elif isinstance(tag, str):
if tag not in qnames:
add_qname(tag)
elif tag is not None and tag is not Comment and tag is not PI:
_raise_serialization_error(tag)
for key, value in elem.items():
if isinstance(key, QName):
key = key.text
if key not in qnames:
add_qname(key)
if isinstance(value, QName) and value.text not in qnames:
add_qname(value.text)
text = elem.text
if isinstance(text, QName) and text.text not in qnames:
add_qname(text.text)
return qnames, namespaces
def _serialize_xml(write, elem, qnames, namespaces,
short_empty_elements, **kwargs):
tag = elem.tag
text = elem.text
if tag is Comment:
write("<!--%s-->" % text)
elif tag is ProcessingInstruction:
write("<?%s?>" % text)
else:
tag = qnames[tag]
if tag is None:
if text:
write(_escape_cdata(text))
for e in elem:
_serialize_xml(write, e, qnames, None,
short_empty_elements=short_empty_elements)
else:
write("<" + tag)
items = list(elem.items())
if items or namespaces:
if namespaces:
for v, k in sorted(namespaces.items(),
key=lambda x: x[1]): # sort on prefix
if k:
k = ":" + k
write(" xmlns%s=\"%s\"" % (
k,
_escape_attrib(v)
))
for k, v in sorted(items): # lexical order
if isinstance(k, QName):
k = k.text
if isinstance(v, QName):
v = qnames[v.text]
else:
v = _escape_attrib(v)
write(" %s=\"%s\"" % (qnames[k], v))
if text or len(elem) or not short_empty_elements:
write(">")
if text:
write(_escape_cdata(text))
for e in elem:
_serialize_xml(write, e, qnames, None,
short_empty_elements=short_empty_elements)
write("</" + tag + ">")
else:
write(" />")
if elem.tail:
write(_escape_cdata(elem.tail))
HTML_EMPTY = ("area", "base", "basefont", "br", "col", "frame", "hr",
"img", "input", "isindex", "link", "meta", "param")
try:
HTML_EMPTY = set(HTML_EMPTY)
except NameError:
pass
def _serialize_html(write, elem, qnames, namespaces, **kwargs):
tag = elem.tag
text = elem.text
if tag is Comment:
write("<!--%s-->" % _escape_cdata(text))
elif tag is ProcessingInstruction:
write("<?%s?>" % _escape_cdata(text))
else:
tag = qnames[tag]
if tag is None:
if text:
write(_escape_cdata(text))
for e in elem:
_serialize_html(write, e, qnames, None)
else:
write("<" + tag)
items = list(elem.items())
if items or namespaces:
if namespaces:
for v, k in sorted(namespaces.items(),
key=lambda x: x[1]): # sort on prefix
if k:
k = ":" + k
write(" xmlns%s=\"%s\"" % (
k,
_escape_attrib(v)
))
for k, v in sorted(items): # lexical order
if isinstance(k, QName):
k = k.text
if isinstance(v, QName):
v = qnames[v.text]
else:
v = _escape_attrib_html(v)
# FIXME: handle boolean attributes
write(" %s=\"%s\"" % (qnames[k], v))
write(">")
ltag = tag.lower()
if text:
if ltag == "script" or ltag == "style":
write(text)
else:
write(_escape_cdata(text))
for e in elem:
_serialize_html(write, e, qnames, None)
if ltag not in HTML_EMPTY:
write("</" + tag + ">")
if elem.tail:
write(_escape_cdata(elem.tail))
def _serialize_text(write, elem):
for part in elem.itertext():
write(part)
if elem.tail:
write(elem.tail)
_serialize = {
"xml": _serialize_xml,
"html": _serialize_html,
"text": _serialize_text,
# this optional method is imported at the end of the module
# "c14n": _serialize_c14n,
}
def register_namespace(prefix, uri):
"""Register a namespace prefix.
The registry is global, and any existing mapping for either the
given prefix or the namespace URI will be removed.
*prefix* is the namespace prefix, *uri* is a namespace uri. Tags and
attributes in this namespace will be serialized with prefix if possible.
ValueError is raised if prefix is reserved or is invalid.
"""
if re.match("ns\d+$", prefix):
raise ValueError("Prefix format reserved for internal use")
for k, v in list(_namespace_map.items()):
if k == uri or v == prefix:
del _namespace_map[k]
_namespace_map[uri] = prefix
_namespace_map = {
# "well-known" namespace prefixes
"http://www.w3.org/XML/1998/namespace": "xml",
"http://www.w3.org/1999/xhtml": "html",
"http://www.w3.org/1999/02/22-rdf-syntax-ns#": "rdf",
"http://schemas.xmlsoap.org/wsdl/": "wsdl",
# xml schema
"http://www.w3.org/2001/XMLSchema": "xs",
"http://www.w3.org/2001/XMLSchema-instance": "xsi",
# dublin core
"http://purl.org/dc/elements/1.1/": "dc",
}
# For tests and troubleshooting
register_namespace._namespace_map = _namespace_map
def _raise_serialization_error(text):
raise TypeError(
"cannot serialize %r (type %s)" % (text, type(text).__name__)
)
def _escape_cdata(text):
# escape character data
try:
# it's worth avoiding do-nothing calls for strings that are
# shorter than 500 character, or so. assume that's, by far,
# the most common case in most applications.
if "&" in text:
text = text.replace("&", "&")
if "<" in text:
text = text.replace("<", "<")
if ">" in text:
text = text.replace(">", ">")
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_attrib(text):
# escape attribute value
try:
if "&" in text:
text = text.replace("&", "&")
if "<" in text:
text = text.replace("<", "<")
if ">" in text:
text = text.replace(">", ">")
if "\"" in text:
text = text.replace("\"", """)
if "\n" in text:
text = text.replace("\n", " ")
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_attrib_html(text):
# escape attribute value
try:
if "&" in text:
text = text.replace("&", "&")
if ">" in text:
text = text.replace(">", ">")
if "\"" in text:
text = text.replace("\"", """)
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
# --------------------------------------------------------------------
def tostring(element, encoding=None, method=None, *,
short_empty_elements=True):
"""Generate string representation of XML element.
All subelements are included. If encoding is "unicode", a string
is returned. Otherwise a bytestring is returned.
*element* is an Element instance, *encoding* is an optional output
encoding defaulting to US-ASCII, *method* is an optional output which can
be one of "xml" (default), "html", "text" or "c14n".
Returns an (optionally) encoded string containing the XML data.
"""
stream = io.StringIO() if encoding == 'unicode' else io.BytesIO()
ElementTree(element).write(stream, encoding, method=method,
short_empty_elements=short_empty_elements)
return stream.getvalue()
class _ListDataStream(io.BufferedIOBase):
"""An auxiliary stream accumulating into a list reference."""
def __init__(self, lst):
self.lst = lst
def writable(self):
return True
def seekable(self):
return True
def write(self, b):
self.lst.append(b)
def tell(self):
return len(self.lst)
def tostringlist(element, encoding=None, method=None, *,
short_empty_elements=True):
lst = []
stream = _ListDataStream(lst)
ElementTree(element).write(stream, encoding, method=method,
short_empty_elements=short_empty_elements)
return lst
def dump(elem):
"""Write element tree or element structure to sys.stdout.
This function should be used for debugging only.
*elem* is either an ElementTree, or a single Element. The exact output
format is implementation dependent. In this version, it's written as an
ordinary XML file.
"""
# debugging
if not isinstance(elem, ElementTree):
elem = ElementTree(elem)
elem.write(sys.stdout, encoding="unicode")
tail = elem.getroot().tail
if not tail or tail[-1] != "\n":
sys.stdout.write("\n")
# --------------------------------------------------------------------
# parsing
def parse(source, parser=None):
"""Parse XML document into element tree.
*source* is a filename or file object containing XML data,
*parser* is an optional parser instance defaulting to XMLParser.
Return an ElementTree instance.
"""
tree = ElementTree()
tree.parse(source, parser)
return tree
def iterparse(source, events=None, parser=None):
"""Incrementally parse XML document into ElementTree.
This class also reports what's going on to the user based on the
*events* it is initialized with. The supported events are the strings
"start", "end", "start-ns" and "end-ns" (the "ns" events are used to get
detailed namespace information). If *events* is omitted, only
"end" events are reported.
*source* is a filename or file object containing XML data, *events* is
a list of events to report back, *parser* is an optional parser instance.
Returns an iterator providing (event, elem) pairs.
"""
close_source = False
if not hasattr(source, "read"):
source = open(source, "rb")
close_source = True
try:
return _IterParseIterator(source, events, parser, close_source)
except:
if close_source:
source.close()
raise
class XMLPullParser:
def __init__(self, events=None, *, _parser=None):
# The _parser argument is for internal use only and must not be relied
# upon in user code. It will be removed in a future release.
# See http://bugs.python.org/issue17741 for more details.
# _elementtree.c expects a list, not a deque
self._events_queue = []
self._index = 0
self._parser = _parser or XMLParser(target=TreeBuilder())
# wire up the parser for event reporting
if events is None:
events = ("end",)
self._parser._setevents(self._events_queue, events)
def feed(self, data):
"""Feed encoded data to parser."""
if self._parser is None:
raise ValueError("feed() called after end of stream")
if data:
try:
self._parser.feed(data)
except SyntaxError as exc:
self._events_queue.append(exc)
def _close_and_return_root(self):
# iterparse needs this to set its root attribute properly :(
root = self._parser.close()
self._parser = None
return root
def close(self):
"""Finish feeding data to parser.
Unlike XMLParser, does not return the root element. Use
read_events() to consume elements from XMLPullParser.
"""
self._close_and_return_root()
def read_events(self):
"""Return an iterator over currently available (event, elem) pairs.
Events are consumed from the internal event queue as they are
retrieved from the iterator.
"""
events = self._events_queue
while True:
index = self._index
try:
event = events[self._index]
# Avoid retaining references to past events
events[self._index] = None
except IndexError:
break
index += 1
# Compact the list in a O(1) amortized fashion
# As noted above, _elementree.c needs a list, not a deque
if index * 2 >= len(events):
events[:index] = []
self._index = 0
else:
self._index = index
if isinstance(event, Exception):
raise event
else:
yield event
class _IterParseIterator:
def __init__(self, source, events, parser, close_source=False):
# Use the internal, undocumented _parser argument for now; When the
# parser argument of iterparse is removed, this can be killed.
self._parser = XMLPullParser(events=events, _parser=parser)
self._file = source
self._close_file = close_source
self.root = self._root = None
def __next__(self):
try:
while 1:
for event in self._parser.read_events():
return event
if self._parser._parser is None:
break
# load event buffer
data = self._file.read(16 * 1024)
if data:
self._parser.feed(data)
else:
self._root = self._parser._close_and_return_root()
self.root = self._root
except:
if self._close_file:
self._file.close()
raise
if self._close_file:
self._file.close()
raise StopIteration
def __iter__(self):
return self
def XML(text, parser=None):
"""Parse XML document from string constant.
This function can be used to embed "XML Literals" in Python code.
*text* is a string containing XML data, *parser* is an
optional parser instance, defaulting to the standard XMLParser.
Returns an Element instance.
"""
if not parser:
parser = XMLParser(target=TreeBuilder())
parser.feed(text)
return parser.close()
def XMLID(text, parser=None):
"""Parse XML document from string constant for its IDs.
*text* is a string containing XML data, *parser* is an
optional parser instance, defaulting to the standard XMLParser.
Returns an (Element, dict) tuple, in which the
dict maps element id:s to elements.
"""
if not parser:
parser = XMLParser(target=TreeBuilder())
parser.feed(text)
tree = parser.close()
ids = {}
for elem in tree.iter():
id = elem.get("id")
if id:
ids[id] = elem
return tree, ids
# Parse XML document from string constant. Alias for XML().
fromstring = XML
def fromstringlist(sequence, parser=None):
"""Parse XML document from sequence of string fragments.
*sequence* is a list of other sequence, *parser* is an optional parser
instance, defaulting to the standard XMLParser.
Returns an Element instance.
"""
if not parser:
parser = XMLParser(target=TreeBuilder())
for text in sequence:
parser.feed(text)
return parser.close()
# --------------------------------------------------------------------
class TreeBuilder:
"""Generic element structure builder.
This builder converts a sequence of start, data, and end method
calls to a well-formed element structure.
You can use this class to build an element structure using a custom XML
parser, or a parser for some other XML-like format.
*element_factory* is an optional element factory which is called
to create new Element instances, as necessary.
"""
def __init__(self, element_factory=None):
self._data = [] # data collector
self._elem = [] # element stack
self._last = None # last element
self._tail = None # true if we're after an end tag
if element_factory is None:
element_factory = Element
self._factory = element_factory
def close(self):
"""Flush builder buffers and return toplevel document Element."""
assert len(self._elem) == 0, "missing end tags"
assert self._last is not None, "missing toplevel element"
return self._last
def _flush(self):
if self._data:
if self._last is not None:
text = "".join(self._data)
if self._tail:
assert self._last.tail is None, "internal error (tail)"
self._last.tail = text
else:
assert self._last.text is None, "internal error (text)"
self._last.text = text
self._data = []
def data(self, data):
"""Add text to current element."""
self._data.append(data)
def start(self, tag, attrs):
"""Open new element and return it.
*tag* is the element name, *attrs* is a dict containing element
attributes.
"""
self._flush()
self._last = elem = self._factory(tag, attrs)
if self._elem:
self._elem[-1].append(elem)
self._elem.append(elem)
self._tail = 0
return elem
def end(self, tag):
"""Close and return current Element.
*tag* is the element name.
"""
self._flush()
self._last = self._elem.pop()
assert self._last.tag == tag,\
"end tag mismatch (expected %s, got %s)" % (
self._last.tag, tag)
self._tail = 1
return self._last
# also see ElementTree and TreeBuilder
class XMLParser:
"""Element structure builder for XML source data based on the expat parser.
*html* are predefined HTML entities (not supported currently),
*target* is an optional target object which defaults to an instance of the
standard TreeBuilder class, *encoding* is an optional encoding string
which if given, overrides the encoding specified in the XML file:
http://www.iana.org/assignments/character-sets
"""
def __init__(self, html=0, target=None, encoding=None):
try:
from xml.parsers import expat
except ImportError:
try:
import pyexpat as expat
except ImportError:
raise ImportError(
"No module named expat; use SimpleXMLTreeBuilder instead"
)
parser = expat.ParserCreate(encoding, "}")
if target is None:
target = TreeBuilder()
# underscored names are provided for compatibility only
self.parser = self._parser = parser
self.target = self._target = target
self._error = expat.error
self._names = {} # name memo cache
# main callbacks
parser.DefaultHandlerExpand = self._default
if hasattr(target, 'start'):
parser.StartElementHandler = self._start
if hasattr(target, 'end'):
parser.EndElementHandler = self._end
if hasattr(target, 'data'):
parser.CharacterDataHandler = target.data
# miscellaneous callbacks
if hasattr(target, 'comment'):
parser.CommentHandler = target.comment
if hasattr(target, 'pi'):
parser.ProcessingInstructionHandler = target.pi
# Configure pyexpat: buffering, new-style attribute handling.
parser.buffer_text = 1
parser.ordered_attributes = 1
parser.specified_attributes = 1
self._doctype = None
self.entity = {}
try:
self.version = "Expat %d.%d.%d" % expat.version_info
except AttributeError:
pass # unknown
def _setevents(self, events_queue, events_to_report):
# Internal API for XMLPullParser
# events_to_report: a list of events to report during parsing (same as
# the *events* of XMLPullParser's constructor.
# events_queue: a list of actual parsing events that will be populated
# by the underlying parser.
#
parser = self._parser
append = events_queue.append
for event_name in events_to_report:
if event_name == "start":
parser.ordered_attributes = 1
parser.specified_attributes = 1
def handler(tag, attrib_in, event=event_name, append=append,
start=self._start):
append((event, start(tag, attrib_in)))
parser.StartElementHandler = handler
elif event_name == "end":
def handler(tag, event=event_name, append=append,
end=self._end):
append((event, end(tag)))
parser.EndElementHandler = handler
elif event_name == "start-ns":
def handler(prefix, uri, event=event_name, append=append):
append((event, (prefix or "", uri or "")))
parser.StartNamespaceDeclHandler = handler
elif event_name == "end-ns":
def handler(prefix, event=event_name, append=append):
append((event, None))
parser.EndNamespaceDeclHandler = handler
else:
raise ValueError("unknown event %r" % event_name)
def _raiseerror(self, value):
err = ParseError(value)
err.code = value.code
err.position = value.lineno, value.offset
raise err
def _fixname(self, key):
# expand qname, and convert name string to ascii, if possible
try:
name = self._names[key]
except KeyError:
name = key
if "}" in name:
name = "{" + name
self._names[key] = name
return name
def _start(self, tag, attr_list):
# Handler for expat's StartElementHandler. Since ordered_attributes
# is set, the attributes are reported as a list of alternating
# attribute name,value.
fixname = self._fixname
tag = fixname(tag)
attrib = {}
if attr_list:
for i in range(0, len(attr_list), 2):
attrib[fixname(attr_list[i])] = attr_list[i+1]
return self.target.start(tag, attrib)
def _end(self, tag):
return self.target.end(self._fixname(tag))
def _default(self, text):
prefix = text[:1]
if prefix == "&":
# deal with undefined entities
try:
data_handler = self.target.data
except AttributeError:
return
try:
data_handler(self.entity[text[1:-1]])
except KeyError:
from xml.parsers import expat
err = expat.error(
"undefined entity %s: line %d, column %d" %
(text, self.parser.ErrorLineNumber,
self.parser.ErrorColumnNumber)
)
err.code = 11 # XML_ERROR_UNDEFINED_ENTITY
err.lineno = self.parser.ErrorLineNumber
err.offset = self.parser.ErrorColumnNumber
raise err
elif prefix == "<" and text[:9] == "<!DOCTYPE":
self._doctype = [] # inside a doctype declaration
elif self._doctype is not None:
# parse doctype contents
if prefix == ">":
self._doctype = None
return
text = text.strip()
if not text:
return
self._doctype.append(text)
n = len(self._doctype)
if n > 2:
type = self._doctype[1]
if type == "PUBLIC" and n == 4:
name, type, pubid, system = self._doctype
if pubid:
pubid = pubid[1:-1]
elif type == "SYSTEM" and n == 3:
name, type, system = self._doctype
pubid = None
else:
return
if hasattr(self.target, "doctype"):
self.target.doctype(name, pubid, system[1:-1])
elif self.doctype != self._XMLParser__doctype:
# warn about deprecated call
self._XMLParser__doctype(name, pubid, system[1:-1])
self.doctype(name, pubid, system[1:-1])
self._doctype = None
def doctype(self, name, pubid, system):
"""(Deprecated) Handle doctype declaration
*name* is the Doctype name, *pubid* is the public identifier,
and *system* is the system identifier.
"""
warnings.warn(
"This method of XMLParser is deprecated. Define doctype() "
"method on the TreeBuilder target.",
DeprecationWarning,
)
# sentinel, if doctype is redefined in a subclass
__doctype = doctype
def feed(self, data):
"""Feed encoded data to parser."""
try:
self.parser.Parse(data, 0)
except self._error as v:
self._raiseerror(v)
def close(self):
"""Finish feeding data to parser and return element structure."""
try:
self.parser.Parse("", 1) # end of data
except self._error as v:
self._raiseerror(v)
try:
close_handler = self.target.close
except AttributeError:
pass
else:
return close_handler()
finally:
# get rid of circular references
del self.parser, self._parser
del self.target, self._target
# Import the C accelerators
try:
# Element is going to be shadowed by the C implementation. We need to keep
# the Python version of it accessible for some "creative" by external code
# (see tests)
_Element_Py = Element
# Element, SubElement, ParseError, TreeBuilder, XMLParser
from _elementtree import *
except ImportError:
pass
|