/usr/lib/python2.7/dist-packages/docutils/nodes.py is in python-docutils 0.12+dfsg-1.
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 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 | # $Id: nodes.py 7595 2013-01-21 17:33:56Z milde $
# Author: David Goodger <goodger@python.org>
# Maintainer: docutils-develop@lists.sourceforge.net
# Copyright: This module has been placed in the public domain.
"""
Docutils document tree element class library.
Classes in CamelCase are abstract base classes or auxiliary classes. The one
exception is `Text`, for a text (PCDATA) node; uppercase is used to
differentiate from element classes. Classes in lower_case_with_underscores
are element classes, matching the XML element generic identifiers in the DTD_.
The position of each node (the level at which it can occur) is significant and
is represented by abstract base classes (`Root`, `Structural`, `Body`,
`Inline`, etc.). Certain transformations will be easier because we can use
``isinstance(node, base_class)`` to determine the position of the node in the
hierarchy.
.. _DTD: http://docutils.sourceforge.net/docs/ref/docutils.dtd
"""
__docformat__ = 'reStructuredText'
import sys
import os
import re
import warnings
import types
import unicodedata
# ==============================
# Functional Node Base Classes
# ==============================
class Node(object):
"""Abstract base class of nodes in a document tree."""
parent = None
"""Back-reference to the Node immediately containing this Node."""
document = None
"""The `document` node at the root of the tree containing this Node."""
source = None
"""Path or description of the input source which generated this Node."""
line = None
"""The line number (1-based) of the beginning of this Node in `source`."""
def __nonzero__(self):
"""
Node instances are always true, even if they're empty. A node is more
than a simple container. Its boolean "truth" does not depend on
having one or more subnodes in the doctree.
Use `len()` to check node length. Use `None` to represent a boolean
false value.
"""
return True
if sys.version_info < (3,):
# on 2.x, str(node) will be a byte string with Unicode
# characters > 255 escaped; on 3.x this is no longer necessary
def __str__(self):
return unicode(self).encode('raw_unicode_escape')
def asdom(self, dom=None):
"""Return a DOM **fragment** representation of this Node."""
if dom is None:
import xml.dom.minidom as dom
domroot = dom.Document()
return self._dom_node(domroot)
def pformat(self, indent=' ', level=0):
"""
Return an indented pseudo-XML representation, for test purposes.
Override in subclasses.
"""
raise NotImplementedError
def copy(self):
"""Return a copy of self."""
raise NotImplementedError
def deepcopy(self):
"""Return a deep copy of self (also copying children)."""
raise NotImplementedError
def setup_child(self, child):
child.parent = self
if self.document:
child.document = self.document
if child.source is None:
child.source = self.document.current_source
if child.line is None:
child.line = self.document.current_line
def walk(self, visitor):
"""
Traverse a tree of `Node` objects, calling the
`dispatch_visit()` method of `visitor` when entering each
node. (The `walkabout()` method is similar, except it also
calls the `dispatch_departure()` method before exiting each
node.)
This tree traversal supports limited in-place tree
modifications. Replacing one node with one or more nodes is
OK, as is removing an element. However, if the node removed
or replaced occurs after the current node, the old node will
still be traversed, and any new nodes will not.
Within ``visit`` methods (and ``depart`` methods for
`walkabout()`), `TreePruningException` subclasses may be raised
(`SkipChildren`, `SkipSiblings`, `SkipNode`, `SkipDeparture`).
Parameter `visitor`: A `NodeVisitor` object, containing a
``visit`` implementation for each `Node` subclass encountered.
Return true if we should stop the traversal.
"""
stop = False
visitor.document.reporter.debug(
'docutils.nodes.Node.walk calling dispatch_visit for %s'
% self.__class__.__name__)
try:
try:
visitor.dispatch_visit(self)
except (SkipChildren, SkipNode):
return stop
except SkipDeparture: # not applicable; ignore
pass
children = self.children
try:
for child in children[:]:
if child.walk(visitor):
stop = True
break
except SkipSiblings:
pass
except StopTraversal:
stop = True
return stop
def walkabout(self, visitor):
"""
Perform a tree traversal similarly to `Node.walk()` (which
see), except also call the `dispatch_departure()` method
before exiting each node.
Parameter `visitor`: A `NodeVisitor` object, containing a
``visit`` and ``depart`` implementation for each `Node`
subclass encountered.
Return true if we should stop the traversal.
"""
call_depart = True
stop = False
visitor.document.reporter.debug(
'docutils.nodes.Node.walkabout calling dispatch_visit for %s'
% self.__class__.__name__)
try:
try:
visitor.dispatch_visit(self)
except SkipNode:
return stop
except SkipDeparture:
call_depart = False
children = self.children
try:
for child in children[:]:
if child.walkabout(visitor):
stop = True
break
except SkipSiblings:
pass
except SkipChildren:
pass
except StopTraversal:
stop = True
if call_depart:
visitor.document.reporter.debug(
'docutils.nodes.Node.walkabout calling dispatch_departure '
'for %s' % self.__class__.__name__)
visitor.dispatch_departure(self)
return stop
def _fast_traverse(self, cls):
"""Specialized traverse() that only supports instance checks."""
result = []
if isinstance(self, cls):
result.append(self)
for child in self.children:
result.extend(child._fast_traverse(cls))
return result
def _all_traverse(self):
"""Specialized traverse() that doesn't check for a condition."""
result = []
result.append(self)
for child in self.children:
result.extend(child._all_traverse())
return result
def traverse(self, condition=None, include_self=True, descend=True,
siblings=False, ascend=False):
"""
Return an iterable containing
* self (if include_self is true)
* all descendants in tree traversal order (if descend is true)
* all siblings (if siblings is true) and their descendants (if
also descend is true)
* the siblings of the parent (if ascend is true) and their
descendants (if also descend is true), and so on
If `condition` is not None, the iterable contains only nodes
for which ``condition(node)`` is true. If `condition` is a
node class ``cls``, it is equivalent to a function consisting
of ``return isinstance(node, cls)``.
If ascend is true, assume siblings to be true as well.
For example, given the following tree::
<paragraph>
<emphasis> <--- emphasis.traverse() and
<strong> <--- strong.traverse() are called.
Foo
Bar
<reference name="Baz" refid="baz">
Baz
Then list(emphasis.traverse()) equals ::
[<emphasis>, <strong>, <#text: Foo>, <#text: Bar>]
and list(strong.traverse(ascend=True)) equals ::
[<strong>, <#text: Foo>, <#text: Bar>, <reference>, <#text: Baz>]
"""
if ascend:
siblings=True
# Check for special argument combinations that allow using an
# optimized version of traverse()
if include_self and descend and not siblings:
if condition is None:
return self._all_traverse()
elif isinstance(condition, (types.ClassType, type)):
return self._fast_traverse(condition)
# Check if `condition` is a class (check for TypeType for Python
# implementations that use only new-style classes, like PyPy).
if isinstance(condition, (types.ClassType, type)):
node_class = condition
def condition(node, node_class=node_class):
return isinstance(node, node_class)
r = []
if include_self and (condition is None or condition(self)):
r.append(self)
if descend and len(self.children):
for child in self:
r.extend(child.traverse(include_self=True, descend=True,
siblings=False, ascend=False,
condition=condition))
if siblings or ascend:
node = self
while node.parent:
index = node.parent.index(node)
for sibling in node.parent[index+1:]:
r.extend(sibling.traverse(include_self=True,
descend=descend,
siblings=False, ascend=False,
condition=condition))
if not ascend:
break
else:
node = node.parent
return r
def next_node(self, condition=None, include_self=False, descend=True,
siblings=False, ascend=False):
"""
Return the first node in the iterable returned by traverse(),
or None if the iterable is empty.
Parameter list is the same as of traverse. Note that
include_self defaults to 0, though.
"""
iterable = self.traverse(condition=condition,
include_self=include_self, descend=descend,
siblings=siblings, ascend=ascend)
try:
return iterable[0]
except IndexError:
return None
if sys.version_info < (3,):
class reprunicode(unicode):
"""
A unicode sub-class that removes the initial u from unicode's repr.
"""
def __repr__(self):
return unicode.__repr__(self)[1:]
else:
reprunicode = unicode
def ensure_str(s):
"""
Failsave conversion of `unicode` to `str`.
"""
if sys.version_info < (3,) and isinstance(s, unicode):
return s.encode('ascii', 'backslashreplace')
return s
class Text(Node, reprunicode):
"""
Instances are terminal nodes (leaves) containing text only; no child
nodes or attributes. Initialize by passing a string to the constructor.
Access the text itself with the `astext` method.
"""
tagname = '#text'
children = ()
"""Text nodes have no children, and cannot have children."""
if sys.version_info > (3,):
def __new__(cls, data, rawsource=None):
"""Prevent the rawsource argument from propagating to str."""
if isinstance(data, bytes):
raise TypeError('expecting str data, not bytes')
return reprunicode.__new__(cls, data)
else:
def __new__(cls, data, rawsource=None):
"""Prevent the rawsource argument from propagating to str."""
return reprunicode.__new__(cls, data)
def __init__(self, data, rawsource=''):
self.rawsource = rawsource
"""The raw text from which this element was constructed."""
def shortrepr(self, maxlen=18):
data = self
if len(data) > maxlen:
data = data[:maxlen-4] + ' ...'
return '<%s: %r>' % (self.tagname, reprunicode(data))
def __repr__(self):
return self.shortrepr(maxlen=68)
def _dom_node(self, domroot):
return domroot.createTextNode(unicode(self))
def astext(self):
return reprunicode(self)
# Note about __unicode__: The implementation of __unicode__ here,
# and the one raising NotImplemented in the superclass Node had
# to be removed when changing Text to a subclass of unicode instead
# of UserString, since there is no way to delegate the __unicode__
# call to the superclass unicode:
# unicode itself does not have __unicode__ method to delegate to
# and calling unicode(self) or unicode.__new__ directly creates
# an infinite loop
def copy(self):
return self.__class__(reprunicode(self), rawsource=self.rawsource)
def deepcopy(self):
return self.copy()
def pformat(self, indent=' ', level=0):
result = []
indent = indent * level
for line in self.splitlines():
result.append(indent + line + '\n')
return ''.join(result)
# rstrip and lstrip are used by substitution definitions where
# they are expected to return a Text instance, this was formerly
# taken care of by UserString. Note that then and now the
# rawsource member is lost.
def rstrip(self, chars=None):
return self.__class__(reprunicode.rstrip(self, chars))
def lstrip(self, chars=None):
return self.__class__(reprunicode.lstrip(self, chars))
class Element(Node):
"""
`Element` is the superclass to all specific elements.
Elements contain attributes and child nodes. Elements emulate
dictionaries for attributes, indexing by attribute name (a string). To
set the attribute 'att' to 'value', do::
element['att'] = 'value'
There are two special attributes: 'ids' and 'names'. Both are
lists of unique identifiers, and names serve as human interfaces
to IDs. Names are case- and whitespace-normalized (see the
fully_normalize_name() function), and IDs conform to the regular
expression ``[a-z](-?[a-z0-9]+)*`` (see the make_id() function).
Elements also emulate lists for child nodes (element nodes and/or text
nodes), indexing by integer. To get the first child node, use::
element[0]
Elements may be constructed using the ``+=`` operator. To add one new
child node to element, do::
element += node
This is equivalent to ``element.append(node)``.
To add a list of multiple child nodes at once, use the same ``+=``
operator::
element += [node1, node2]
This is equivalent to ``element.extend([node1, node2])``.
"""
basic_attributes = ('ids', 'classes', 'names', 'dupnames')
"""List attributes which are defined for every Element-derived class
instance and can be safely transferred to a different node."""
local_attributes = ('backrefs',)
"""A list of class-specific attributes that should not be copied with the
standard attributes when replacing a node.
NOTE: Derived classes should override this value to prevent any of its
attributes being copied by adding to the value in its parent class."""
list_attributes = basic_attributes + local_attributes
"""List attributes, automatically initialized to empty lists for
all nodes."""
known_attributes = list_attributes + ('source',)
"""List attributes that are known to the Element base class."""
tagname = None
"""The element generic identifier. If None, it is set as an instance
attribute to the name of the class."""
child_text_separator = '\n\n'
"""Separator for child nodes, used by `astext()` method."""
def __init__(self, rawsource='', *children, **attributes):
self.rawsource = rawsource
"""The raw text from which this element was constructed."""
self.children = []
"""List of child nodes (elements and/or `Text`)."""
self.extend(children) # maintain parent info
self.attributes = {}
"""Dictionary of attribute {name: value}."""
# Initialize list attributes.
for att in self.list_attributes:
self.attributes[att] = []
for att, value in attributes.items():
att = att.lower()
if att in self.list_attributes:
# mutable list; make a copy for this node
self.attributes[att] = value[:]
else:
self.attributes[att] = value
if self.tagname is None:
self.tagname = self.__class__.__name__
def _dom_node(self, domroot):
element = domroot.createElement(self.tagname)
for attribute, value in self.attlist():
if isinstance(value, list):
value = ' '.join([serial_escape('%s' % (v,)) for v in value])
element.setAttribute(attribute, '%s' % value)
for child in self.children:
element.appendChild(child._dom_node(domroot))
return element
def __repr__(self):
data = ''
for c in self.children:
data += c.shortrepr()
if len(data) > 60:
data = data[:56] + ' ...'
break
if self['names']:
return '<%s "%s": %s>' % (self.__class__.__name__,
'; '.join([ensure_str(n) for n in self['names']]), data)
else:
return '<%s: %s>' % (self.__class__.__name__, data)
def shortrepr(self):
if self['names']:
return '<%s "%s"...>' % (self.__class__.__name__,
'; '.join([ensure_str(n) for n in self['names']]))
else:
return '<%s...>' % self.tagname
def __unicode__(self):
if self.children:
return u'%s%s%s' % (self.starttag(),
''.join([unicode(c) for c in self.children]),
self.endtag())
else:
return self.emptytag()
if sys.version_info > (3,):
# 2to3 doesn't convert __unicode__ to __str__
__str__ = __unicode__
def starttag(self, quoteattr=None):
# the optional arg is used by the docutils_xml writer
if quoteattr is None:
quoteattr = pseudo_quoteattr
parts = [self.tagname]
for name, value in self.attlist():
if value is None: # boolean attribute
parts.append(name)
continue
if isinstance(value, list):
values = [serial_escape('%s' % (v,)) for v in value]
value = ' '.join(values)
else:
value = unicode(value)
value = quoteattr(value)
parts.append(u'%s=%s' % (name, value))
return u'<%s>' % u' '.join(parts)
def endtag(self):
return '</%s>' % self.tagname
def emptytag(self):
return u'<%s/>' % u' '.join([self.tagname] +
['%s="%s"' % (n, v)
for n, v in self.attlist()])
def __len__(self):
return len(self.children)
def __contains__(self, key):
# support both membership test for children and attributes
# (has_key is translated to "in" by 2to3)
if isinstance(key, basestring):
return key in self.attributes
return key in self.children
def __getitem__(self, key):
if isinstance(key, basestring):
return self.attributes[key]
elif isinstance(key, int):
return self.children[key]
elif isinstance(key, types.SliceType):
assert key.step in (None, 1), 'cannot handle slice with stride'
return self.children[key.start:key.stop]
else:
raise TypeError, ('element index must be an integer, a slice, or '
'an attribute name string')
def __setitem__(self, key, item):
if isinstance(key, basestring):
self.attributes[str(key)] = item
elif isinstance(key, int):
self.setup_child(item)
self.children[key] = item
elif isinstance(key, types.SliceType):
assert key.step in (None, 1), 'cannot handle slice with stride'
for node in item:
self.setup_child(node)
self.children[key.start:key.stop] = item
else:
raise TypeError, ('element index must be an integer, a slice, or '
'an attribute name string')
def __delitem__(self, key):
if isinstance(key, basestring):
del self.attributes[key]
elif isinstance(key, int):
del self.children[key]
elif isinstance(key, types.SliceType):
assert key.step in (None, 1), 'cannot handle slice with stride'
del self.children[key.start:key.stop]
else:
raise TypeError, ('element index must be an integer, a simple '
'slice, or an attribute name string')
def __add__(self, other):
return self.children + other
def __radd__(self, other):
return other + self.children
def __iadd__(self, other):
"""Append a node or a list of nodes to `self.children`."""
if isinstance(other, Node):
self.append(other)
elif other is not None:
self.extend(other)
return self
def astext(self):
return self.child_text_separator.join(
[child.astext() for child in self.children])
def non_default_attributes(self):
atts = {}
for key, value in self.attributes.items():
if self.is_not_default(key):
atts[key] = value
return atts
def attlist(self):
attlist = self.non_default_attributes().items()
attlist.sort()
return attlist
def get(self, key, failobj=None):
return self.attributes.get(key, failobj)
def hasattr(self, attr):
return attr in self.attributes
def delattr(self, attr):
if attr in self.attributes:
del self.attributes[attr]
def setdefault(self, key, failobj=None):
return self.attributes.setdefault(key, failobj)
has_key = hasattr
# support operator ``in``
__contains__ = hasattr
def get_language_code(self, fallback=''):
"""Return node's language tag.
Look iteratively in self and parents for a class argument
starting with ``language-`` and return the remainder of it
(which should be a `BCP49` language tag) or the `fallback`.
"""
for cls in self.get('classes', []):
if cls.startswith('language-'):
return cls[9:]
try:
return self.parent.get_language(fallback)
except AttributeError:
return fallback
def append(self, item):
self.setup_child(item)
self.children.append(item)
def extend(self, item):
for node in item:
self.append(node)
def insert(self, index, item):
if isinstance(item, Node):
self.setup_child(item)
self.children.insert(index, item)
elif item is not None:
self[index:index] = item
def pop(self, i=-1):
return self.children.pop(i)
def remove(self, item):
self.children.remove(item)
def index(self, item):
return self.children.index(item)
def is_not_default(self, key):
if self[key] == [] and key in self.list_attributes:
return 0
else:
return 1
def update_basic_atts(self, dict_):
"""
Update basic attributes ('ids', 'names', 'classes',
'dupnames', but not 'source') from node or dictionary `dict_`.
"""
if isinstance(dict_, Node):
dict_ = dict_.attributes
for att in self.basic_attributes:
self.append_attr_list(att, dict_.get(att, []))
def append_attr_list(self, attr, values):
"""
For each element in values, if it does not exist in self[attr], append
it.
NOTE: Requires self[attr] and values to be sequence type and the
former should specifically be a list.
"""
# List Concatenation
for value in values:
if not value in self[attr]:
self[attr].append(value)
def coerce_append_attr_list(self, attr, value):
"""
First, convert both self[attr] and value to a non-string sequence
type; if either is not already a sequence, convert it to a list of one
element. Then call append_attr_list.
NOTE: self[attr] and value both must not be None.
"""
# List Concatenation
if not isinstance(self.get(attr), list):
self[attr] = [self[attr]]
if not isinstance(value, list):
value = [value]
self.append_attr_list(attr, value)
def replace_attr(self, attr, value, force = True):
"""
If self[attr] does not exist or force is True or omitted, set
self[attr] to value, otherwise do nothing.
"""
# One or the other
if force or self.get(attr) is None:
self[attr] = value
def copy_attr_convert(self, attr, value, replace = True):
"""
If attr is an attribute of self, set self[attr] to
[self[attr], value], otherwise set self[attr] to value.
NOTE: replace is not used by this function and is kept only for
compatibility with the other copy functions.
"""
if self.get(attr) is not value:
self.coerce_append_attr_list(attr, value)
def copy_attr_coerce(self, attr, value, replace):
"""
If attr is an attribute of self and either self[attr] or value is a
list, convert all non-sequence values to a sequence of 1 element and
then concatenate the two sequence, setting the result to self[attr].
If both self[attr] and value are non-sequences and replace is True or
self[attr] is None, replace self[attr] with value. Otherwise, do
nothing.
"""
if self.get(attr) is not value:
if isinstance(self.get(attr), list) or \
isinstance(value, list):
self.coerce_append_attr_list(attr, value)
else:
self.replace_attr(attr, value, replace)
def copy_attr_concatenate(self, attr, value, replace):
"""
If attr is an attribute of self and both self[attr] and value are
lists, concatenate the two sequences, setting the result to
self[attr]. If either self[attr] or value are non-sequences and
replace is True or self[attr] is None, replace self[attr] with value.
Otherwise, do nothing.
"""
if self.get(attr) is not value:
if isinstance(self.get(attr), list) and \
isinstance(value, list):
self.append_attr_list(attr, value)
else:
self.replace_attr(attr, value, replace)
def copy_attr_consistent(self, attr, value, replace):
"""
If replace is True or selfpattr] is None, replace self[attr] with
value. Otherwise, do nothing.
"""
if self.get(attr) is not value:
self.replace_attr(attr, value, replace)
def update_all_atts(self, dict_, update_fun = copy_attr_consistent,
replace = True, and_source = False):
"""
Updates all attributes from node or dictionary `dict_`.
Appends the basic attributes ('ids', 'names', 'classes',
'dupnames', but not 'source') and then, for all other attributes in
dict_, updates the same attribute in self. When attributes with the
same identifier appear in both self and dict_, the two values are
merged based on the value of update_fun. Generally, when replace is
True, the values in self are replaced or merged with the values in
dict_; otherwise, the values in self may be preserved or merged. When
and_source is True, the 'source' attribute is included in the copy.
NOTE: When replace is False, and self contains a 'source' attribute,
'source' is not replaced even when dict_ has a 'source'
attribute, though it may still be merged into a list depending
on the value of update_fun.
NOTE: It is easier to call the update-specific methods then to pass
the update_fun method to this function.
"""
if isinstance(dict_, Node):
dict_ = dict_.attributes
# Include the source attribute when copying?
if and_source:
filter_fun = self.is_not_list_attribute
else:
filter_fun = self.is_not_known_attribute
# Copy the basic attributes
self.update_basic_atts(dict_)
# Grab other attributes in dict_ not in self except the
# (All basic attributes should be copied already)
for att in filter(filter_fun, dict_):
update_fun(self, att, dict_[att], replace)
def update_all_atts_consistantly(self, dict_, replace = True,
and_source = False):
"""
Updates all attributes from node or dictionary `dict_`.
Appends the basic attributes ('ids', 'names', 'classes',
'dupnames', but not 'source') and then, for all other attributes in
dict_, updates the same attribute in self. When attributes with the
same identifier appear in both self and dict_ and replace is True, the
values in self are replaced with the values in dict_; otherwise, the
values in self are preserved. When and_source is True, the 'source'
attribute is included in the copy.
NOTE: When replace is False, and self contains a 'source' attribute,
'source' is not replaced even when dict_ has a 'source'
attribute, though it may still be merged into a list depending
on the value of update_fun.
"""
self.update_all_atts(dict_, Element.copy_attr_consistent, replace,
and_source)
def update_all_atts_concatenating(self, dict_, replace = True,
and_source = False):
"""
Updates all attributes from node or dictionary `dict_`.
Appends the basic attributes ('ids', 'names', 'classes',
'dupnames', but not 'source') and then, for all other attributes in
dict_, updates the same attribute in self. When attributes with the
same identifier appear in both self and dict_ whose values aren't each
lists and replace is True, the values in self are replaced with the
values in dict_; if the values from self and dict_ for the given
identifier are both of list type, then the two lists are concatenated
and the result stored in self; otherwise, the values in self are
preserved. When and_source is True, the 'source' attribute is
included in the copy.
NOTE: When replace is False, and self contains a 'source' attribute,
'source' is not replaced even when dict_ has a 'source'
attribute, though it may still be merged into a list depending
on the value of update_fun.
"""
self.update_all_atts(dict_, Element.copy_attr_concatenate, replace,
and_source)
def update_all_atts_coercion(self, dict_, replace = True,
and_source = False):
"""
Updates all attributes from node or dictionary `dict_`.
Appends the basic attributes ('ids', 'names', 'classes',
'dupnames', but not 'source') and then, for all other attributes in
dict_, updates the same attribute in self. When attributes with the
same identifier appear in both self and dict_ whose values are both
not lists and replace is True, the values in self are replaced with
the values in dict_; if either of the values from self and dict_ for
the given identifier are of list type, then first any non-lists are
converted to 1-element lists and then the two lists are concatenated
and the result stored in self; otherwise, the values in self are
preserved. When and_source is True, the 'source' attribute is
included in the copy.
NOTE: When replace is False, and self contains a 'source' attribute,
'source' is not replaced even when dict_ has a 'source'
attribute, though it may still be merged into a list depending
on the value of update_fun.
"""
self.update_all_atts(dict_, Element.copy_attr_coerce, replace,
and_source)
def update_all_atts_convert(self, dict_, and_source = False):
"""
Updates all attributes from node or dictionary `dict_`.
Appends the basic attributes ('ids', 'names', 'classes',
'dupnames', but not 'source') and then, for all other attributes in
dict_, updates the same attribute in self. When attributes with the
same identifier appear in both self and dict_ then first any non-lists
are converted to 1-element lists and then the two lists are
concatenated and the result stored in self; otherwise, the values in
self are preserved. When and_source is True, the 'source' attribute
is included in the copy.
NOTE: When replace is False, and self contains a 'source' attribute,
'source' is not replaced even when dict_ has a 'source'
attribute, though it may still be merged into a list depending
on the value of update_fun.
"""
self.update_all_atts(dict_, Element.copy_attr_convert,
and_source = and_source)
def clear(self):
self.children = []
def replace(self, old, new):
"""Replace one child `Node` with another child or children."""
index = self.index(old)
if isinstance(new, Node):
self.setup_child(new)
self[index] = new
elif new is not None:
self[index:index+1] = new
def replace_self(self, new):
"""
Replace `self` node with `new`, where `new` is a node or a
list of nodes.
"""
update = new
if not isinstance(new, Node):
# `new` is a list; update first child.
try:
update = new[0]
except IndexError:
update = None
if isinstance(update, Element):
update.update_basic_atts(self)
else:
# `update` is a Text node or `new` is an empty list.
# Assert that we aren't losing any attributes.
for att in self.basic_attributes:
assert not self[att], \
'Losing "%s" attribute: %s' % (att, self[att])
self.parent.replace(self, new)
def first_child_matching_class(self, childclass, start=0, end=sys.maxint):
"""
Return the index of the first child whose class exactly matches.
Parameters:
- `childclass`: A `Node` subclass to search for, or a tuple of `Node`
classes. If a tuple, any of the classes may match.
- `start`: Initial index to check.
- `end`: Initial index to *not* check.
"""
if not isinstance(childclass, tuple):
childclass = (childclass,)
for index in range(start, min(len(self), end)):
for c in childclass:
if isinstance(self[index], c):
return index
return None
def first_child_not_matching_class(self, childclass, start=0,
end=sys.maxint):
"""
Return the index of the first child whose class does *not* match.
Parameters:
- `childclass`: A `Node` subclass to skip, or a tuple of `Node`
classes. If a tuple, none of the classes may match.
- `start`: Initial index to check.
- `end`: Initial index to *not* check.
"""
if not isinstance(childclass, tuple):
childclass = (childclass,)
for index in range(start, min(len(self), end)):
for c in childclass:
if isinstance(self.children[index], c):
break
else:
return index
return None
def pformat(self, indent=' ', level=0):
return ''.join(['%s%s\n' % (indent * level, self.starttag())] +
[child.pformat(indent, level+1)
for child in self.children])
def copy(self):
return self.__class__(rawsource=self.rawsource, **self.attributes)
def deepcopy(self):
copy = self.copy()
copy.extend([child.deepcopy() for child in self.children])
return copy
def set_class(self, name):
"""Add a new class to the "classes" attribute."""
warnings.warn('docutils.nodes.Element.set_class deprecated; '
"append to Element['classes'] list attribute directly",
DeprecationWarning, stacklevel=2)
assert ' ' not in name
self['classes'].append(name.lower())
def note_referenced_by(self, name=None, id=None):
"""Note that this Element has been referenced by its name
`name` or id `id`."""
self.referenced = 1
# Element.expect_referenced_by_* dictionaries map names or ids
# to nodes whose ``referenced`` attribute is set to true as
# soon as this node is referenced by the given name or id.
# Needed for target propagation.
by_name = getattr(self, 'expect_referenced_by_name', {}).get(name)
by_id = getattr(self, 'expect_referenced_by_id', {}).get(id)
if by_name:
assert name is not None
by_name.referenced = 1
if by_id:
assert id is not None
by_id.referenced = 1
@classmethod
def is_not_list_attribute(cls, attr):
"""
Returns True if and only if the given attribute is NOT one of the
basic list attributes defined for all Elements.
"""
return attr not in cls.list_attributes
@classmethod
def is_not_known_attribute(cls, attr):
"""
Returns True if and only if the given attribute is NOT recognized by
this class.
"""
return attr not in cls.known_attributes
class TextElement(Element):
"""
An element which directly contains text.
Its children are all `Text` or `Inline` subclass nodes. You can
check whether an element's context is inline simply by checking whether
its immediate parent is a `TextElement` instance (including subclasses).
This is handy for nodes like `image` that can appear both inline and as
standalone body elements.
If passing children to `__init__()`, make sure to set `text` to
``''`` or some other suitable value.
"""
child_text_separator = ''
"""Separator for child nodes, used by `astext()` method."""
def __init__(self, rawsource='', text='', *children, **attributes):
if text != '':
textnode = Text(text)
Element.__init__(self, rawsource, textnode, *children,
**attributes)
else:
Element.__init__(self, rawsource, *children, **attributes)
class FixedTextElement(TextElement):
"""An element which directly contains preformatted text."""
def __init__(self, rawsource='', text='', *children, **attributes):
TextElement.__init__(self, rawsource, text, *children, **attributes)
self.attributes['xml:space'] = 'preserve'
# ========
# Mixins
# ========
class Resolvable:
resolved = 0
class BackLinkable:
def add_backref(self, refid):
self['backrefs'].append(refid)
# ====================
# Element Categories
# ====================
class Root: pass
class Titular: pass
class PreBibliographic:
"""Category of Node which may occur before Bibliographic Nodes."""
class Bibliographic: pass
class Decorative(PreBibliographic): pass
class Structural: pass
class Body: pass
class General(Body): pass
class Sequential(Body):
"""List-like elements."""
class Admonition(Body): pass
class Special(Body):
"""Special internal body elements."""
class Invisible(PreBibliographic):
"""Internal elements that don't appear in output."""
class Part: pass
class Inline: pass
class Referential(Resolvable): pass
class Targetable(Resolvable):
referenced = 0
indirect_reference_name = None
"""Holds the whitespace_normalized_name (contains mixed case) of a target.
Required for MoinMoin/reST compatibility."""
class Labeled:
"""Contains a `label` as its first element."""
# ==============
# Root Element
# ==============
class document(Root, Structural, Element):
"""
The document root element.
Do not instantiate this class directly; use
`docutils.utils.new_document()` instead.
"""
def __init__(self, settings, reporter, *args, **kwargs):
Element.__init__(self, *args, **kwargs)
self.current_source = None
"""Path to or description of the input source being processed."""
self.current_line = None
"""Line number (1-based) of `current_source`."""
self.settings = settings
"""Runtime settings data record."""
self.reporter = reporter
"""System message generator."""
self.indirect_targets = []
"""List of indirect target nodes."""
self.substitution_defs = {}
"""Mapping of substitution names to substitution_definition nodes."""
self.substitution_names = {}
"""Mapping of case-normalized substitution names to case-sensitive
names."""
self.refnames = {}
"""Mapping of names to lists of referencing nodes."""
self.refids = {}
"""Mapping of ids to lists of referencing nodes."""
self.nameids = {}
"""Mapping of names to unique id's."""
self.nametypes = {}
"""Mapping of names to hyperlink type (boolean: True => explicit,
False => implicit."""
self.ids = {}
"""Mapping of ids to nodes."""
self.footnote_refs = {}
"""Mapping of footnote labels to lists of footnote_reference nodes."""
self.citation_refs = {}
"""Mapping of citation labels to lists of citation_reference nodes."""
self.autofootnotes = []
"""List of auto-numbered footnote nodes."""
self.autofootnote_refs = []
"""List of auto-numbered footnote_reference nodes."""
self.symbol_footnotes = []
"""List of symbol footnote nodes."""
self.symbol_footnote_refs = []
"""List of symbol footnote_reference nodes."""
self.footnotes = []
"""List of manually-numbered footnote nodes."""
self.citations = []
"""List of citation nodes."""
self.autofootnote_start = 1
"""Initial auto-numbered footnote number."""
self.symbol_footnote_start = 0
"""Initial symbol footnote symbol index."""
self.id_start = 1
"""Initial ID number."""
self.parse_messages = []
"""System messages generated while parsing."""
self.transform_messages = []
"""System messages generated while applying transforms."""
import docutils.transforms
self.transformer = docutils.transforms.Transformer(self)
"""Storage for transforms to be applied to this document."""
self.decoration = None
"""Document's `decoration` node."""
self.document = self
def __getstate__(self):
"""
Return dict with unpicklable references removed.
"""
state = self.__dict__.copy()
state['reporter'] = None
state['transformer'] = None
return state
def asdom(self, dom=None):
"""Return a DOM representation of this document."""
if dom is None:
import xml.dom.minidom as dom
domroot = dom.Document()
domroot.appendChild(self._dom_node(domroot))
return domroot
def set_id(self, node, msgnode=None):
for id in node['ids']:
if id in self.ids and self.ids[id] is not node:
msg = self.reporter.severe('Duplicate ID: "%s".' % id)
if msgnode != None:
msgnode += msg
if not node['ids']:
for name in node['names']:
id = self.settings.id_prefix + make_id(name)
if id and id not in self.ids:
break
else:
id = ''
while not id or id in self.ids:
id = (self.settings.id_prefix +
self.settings.auto_id_prefix + str(self.id_start))
self.id_start += 1
node['ids'].append(id)
self.ids[id] = node
return id
def set_name_id_map(self, node, id, msgnode=None, explicit=None):
"""
`self.nameids` maps names to IDs, while `self.nametypes` maps names to
booleans representing hyperlink type (True==explicit,
False==implicit). This method updates the mappings.
The following state transition table shows how `self.nameids` ("ids")
and `self.nametypes` ("types") change with new input (a call to this
method), and what actions are performed ("implicit"-type system
messages are INFO/1, and "explicit"-type system messages are ERROR/3):
==== ===== ======== ======== ======= ==== ===== =====
Old State Input Action New State Notes
----------- -------- ----------------- ----------- -----
ids types new type sys.msg. dupname ids types
==== ===== ======== ======== ======= ==== ===== =====
- - explicit - - new True
- - implicit - - new False
None False explicit - - new True
old False explicit implicit old new True
None True explicit explicit new None True
old True explicit explicit new,old None True [#]_
None False implicit implicit new None False
old False implicit implicit new,old None False
None True implicit implicit new None True
old True implicit implicit new old True
==== ===== ======== ======== ======= ==== ===== =====
.. [#] Do not clear the name-to-id map or invalidate the old target if
both old and new targets are external and refer to identical URIs.
The new target is invalidated regardless.
"""
for name in node['names']:
if name in self.nameids:
self.set_duplicate_name_id(node, id, name, msgnode, explicit)
else:
self.nameids[name] = id
self.nametypes[name] = explicit
def set_duplicate_name_id(self, node, id, name, msgnode, explicit):
old_id = self.nameids[name]
old_explicit = self.nametypes[name]
self.nametypes[name] = old_explicit or explicit
if explicit:
if old_explicit:
level = 2
if old_id is not None:
old_node = self.ids[old_id]
if 'refuri' in node:
refuri = node['refuri']
if old_node['names'] \
and 'refuri' in old_node \
and old_node['refuri'] == refuri:
level = 1 # just inform if refuri's identical
if level > 1:
dupname(old_node, name)
self.nameids[name] = None
msg = self.reporter.system_message(
level, 'Duplicate explicit target name: "%s".' % name,
backrefs=[id], base_node=node)
if msgnode != None:
msgnode += msg
dupname(node, name)
else:
self.nameids[name] = id
if old_id is not None:
old_node = self.ids[old_id]
dupname(old_node, name)
else:
if old_id is not None and not old_explicit:
self.nameids[name] = None
old_node = self.ids[old_id]
dupname(old_node, name)
dupname(node, name)
if not explicit or (not old_explicit and old_id is not None):
msg = self.reporter.info(
'Duplicate implicit target name: "%s".' % name,
backrefs=[id], base_node=node)
if msgnode != None:
msgnode += msg
def has_name(self, name):
return name in self.nameids
# "note" here is an imperative verb: "take note of".
def note_implicit_target(self, target, msgnode=None):
id = self.set_id(target, msgnode)
self.set_name_id_map(target, id, msgnode, explicit=None)
def note_explicit_target(self, target, msgnode=None):
id = self.set_id(target, msgnode)
self.set_name_id_map(target, id, msgnode, explicit=True)
def note_refname(self, node):
self.refnames.setdefault(node['refname'], []).append(node)
def note_refid(self, node):
self.refids.setdefault(node['refid'], []).append(node)
def note_indirect_target(self, target):
self.indirect_targets.append(target)
if target['names']:
self.note_refname(target)
def note_anonymous_target(self, target):
self.set_id(target)
def note_autofootnote(self, footnote):
self.set_id(footnote)
self.autofootnotes.append(footnote)
def note_autofootnote_ref(self, ref):
self.set_id(ref)
self.autofootnote_refs.append(ref)
def note_symbol_footnote(self, footnote):
self.set_id(footnote)
self.symbol_footnotes.append(footnote)
def note_symbol_footnote_ref(self, ref):
self.set_id(ref)
self.symbol_footnote_refs.append(ref)
def note_footnote(self, footnote):
self.set_id(footnote)
self.footnotes.append(footnote)
def note_footnote_ref(self, ref):
self.set_id(ref)
self.footnote_refs.setdefault(ref['refname'], []).append(ref)
self.note_refname(ref)
def note_citation(self, citation):
self.citations.append(citation)
def note_citation_ref(self, ref):
self.set_id(ref)
self.citation_refs.setdefault(ref['refname'], []).append(ref)
self.note_refname(ref)
def note_substitution_def(self, subdef, def_name, msgnode=None):
name = whitespace_normalize_name(def_name)
if name in self.substitution_defs:
msg = self.reporter.error(
'Duplicate substitution definition name: "%s".' % name,
base_node=subdef)
if msgnode != None:
msgnode += msg
oldnode = self.substitution_defs[name]
dupname(oldnode, name)
# keep only the last definition:
self.substitution_defs[name] = subdef
# case-insensitive mapping:
self.substitution_names[fully_normalize_name(name)] = name
def note_substitution_ref(self, subref, refname):
subref['refname'] = whitespace_normalize_name(refname)
def note_pending(self, pending, priority=None):
self.transformer.add_pending(pending, priority)
def note_parse_message(self, message):
self.parse_messages.append(message)
def note_transform_message(self, message):
self.transform_messages.append(message)
def note_source(self, source, offset):
self.current_source = source
if offset is None:
self.current_line = offset
else:
self.current_line = offset + 1
def copy(self):
return self.__class__(self.settings, self.reporter,
**self.attributes)
def get_decoration(self):
if not self.decoration:
self.decoration = decoration()
index = self.first_child_not_matching_class(Titular)
if index is None:
self.append(self.decoration)
else:
self.insert(index, self.decoration)
return self.decoration
# ================
# Title Elements
# ================
class title(Titular, PreBibliographic, TextElement): pass
class subtitle(Titular, PreBibliographic, TextElement): pass
class rubric(Titular, TextElement): pass
# ========================
# Bibliographic Elements
# ========================
class docinfo(Bibliographic, Element): pass
class author(Bibliographic, TextElement): pass
class authors(Bibliographic, Element): pass
class organization(Bibliographic, TextElement): pass
class address(Bibliographic, FixedTextElement): pass
class contact(Bibliographic, TextElement): pass
class version(Bibliographic, TextElement): pass
class revision(Bibliographic, TextElement): pass
class status(Bibliographic, TextElement): pass
class date(Bibliographic, TextElement): pass
class copyright(Bibliographic, TextElement): pass
# =====================
# Decorative Elements
# =====================
class decoration(Decorative, Element):
def get_header(self):
if not len(self.children) or not isinstance(self.children[0], header):
self.insert(0, header())
return self.children[0]
def get_footer(self):
if not len(self.children) or not isinstance(self.children[-1], footer):
self.append(footer())
return self.children[-1]
class header(Decorative, Element): pass
class footer(Decorative, Element): pass
# =====================
# Structural Elements
# =====================
class section(Structural, Element): pass
class topic(Structural, Element):
"""
Topics are terminal, "leaf" mini-sections, like block quotes with titles,
or textual figures. A topic is just like a section, except that it has no
subsections, and it doesn't have to conform to section placement rules.
Topics are allowed wherever body elements (list, table, etc.) are allowed,
but only at the top level of a section or document. Topics cannot nest
inside topics, sidebars, or body elements; you can't have a topic inside a
table, list, block quote, etc.
"""
class sidebar(Structural, Element):
"""
Sidebars are like miniature, parallel documents that occur inside other
documents, providing related or reference material. A sidebar is
typically offset by a border and "floats" to the side of the page; the
document's main text may flow around it. Sidebars can also be likened to
super-footnotes; their content is outside of the flow of the document's
main text.
Sidebars are allowed wherever body elements (list, table, etc.) are
allowed, but only at the top level of a section or document. Sidebars
cannot nest inside sidebars, topics, or body elements; you can't have a
sidebar inside a table, list, block quote, etc.
"""
class transition(Structural, Element): pass
# ===============
# Body Elements
# ===============
class paragraph(General, TextElement): pass
class compound(General, Element): pass
class container(General, Element): pass
class bullet_list(Sequential, Element): pass
class enumerated_list(Sequential, Element): pass
class list_item(Part, Element): pass
class definition_list(Sequential, Element): pass
class definition_list_item(Part, Element): pass
class term(Part, TextElement): pass
class classifier(Part, TextElement): pass
class definition(Part, Element): pass
class field_list(Sequential, Element): pass
class field(Part, Element): pass
class field_name(Part, TextElement): pass
class field_body(Part, Element): pass
class option(Part, Element):
child_text_separator = ''
class option_argument(Part, TextElement):
def astext(self):
return self.get('delimiter', ' ') + TextElement.astext(self)
class option_group(Part, Element):
child_text_separator = ', '
class option_list(Sequential, Element): pass
class option_list_item(Part, Element):
child_text_separator = ' '
class option_string(Part, TextElement): pass
class description(Part, Element): pass
class literal_block(General, FixedTextElement): pass
class doctest_block(General, FixedTextElement): pass
class math_block(General, FixedTextElement): pass
class line_block(General, Element): pass
class line(Part, TextElement):
indent = None
class block_quote(General, Element): pass
class attribution(Part, TextElement): pass
class attention(Admonition, Element): pass
class caution(Admonition, Element): pass
class danger(Admonition, Element): pass
class error(Admonition, Element): pass
class important(Admonition, Element): pass
class note(Admonition, Element): pass
class tip(Admonition, Element): pass
class hint(Admonition, Element): pass
class warning(Admonition, Element): pass
class admonition(Admonition, Element): pass
class comment(Special, Invisible, FixedTextElement): pass
class substitution_definition(Special, Invisible, TextElement): pass
class target(Special, Invisible, Inline, TextElement, Targetable): pass
class footnote(General, BackLinkable, Element, Labeled, Targetable): pass
class citation(General, BackLinkable, Element, Labeled, Targetable): pass
class label(Part, TextElement): pass
class figure(General, Element): pass
class caption(Part, TextElement): pass
class legend(Part, Element): pass
class table(General, Element): pass
class tgroup(Part, Element): pass
class colspec(Part, Element): pass
class thead(Part, Element): pass
class tbody(Part, Element): pass
class row(Part, Element): pass
class entry(Part, Element): pass
class system_message(Special, BackLinkable, PreBibliographic, Element):
"""
System message element.
Do not instantiate this class directly; use
``document.reporter.info/warning/error/severe()`` instead.
"""
def __init__(self, message=None, *children, **attributes):
if message:
p = paragraph('', message)
children = (p,) + children
try:
Element.__init__(self, '', *children, **attributes)
except:
print 'system_message: children=%r' % (children,)
raise
def astext(self):
line = self.get('line', '')
return u'%s:%s: (%s/%s) %s' % (self['source'], line, self['type'],
self['level'], Element.astext(self))
class pending(Special, Invisible, Element):
"""
The "pending" element is used to encapsulate a pending operation: the
operation (transform), the point at which to apply it, and any data it
requires. Only the pending operation's location within the document is
stored in the public document tree (by the "pending" object itself); the
operation and its data are stored in the "pending" object's internal
instance attributes.
For example, say you want a table of contents in your reStructuredText
document. The easiest way to specify where to put it is from within the
document, with a directive::
.. contents::
But the "contents" directive can't do its work until the entire document
has been parsed and possibly transformed to some extent. So the directive
code leaves a placeholder behind that will trigger the second phase of its
processing, something like this::
<pending ...public attributes...> + internal attributes
Use `document.note_pending()` so that the
`docutils.transforms.Transformer` stage of processing can run all pending
transforms.
"""
def __init__(self, transform, details=None,
rawsource='', *children, **attributes):
Element.__init__(self, rawsource, *children, **attributes)
self.transform = transform
"""The `docutils.transforms.Transform` class implementing the pending
operation."""
self.details = details or {}
"""Detail data (dictionary) required by the pending operation."""
def pformat(self, indent=' ', level=0):
internals = [
'.. internal attributes:',
' .transform: %s.%s' % (self.transform.__module__,
self.transform.__name__),
' .details:']
details = self.details.items()
details.sort()
for key, value in details:
if isinstance(value, Node):
internals.append('%7s%s:' % ('', key))
internals.extend(['%9s%s' % ('', line)
for line in value.pformat().splitlines()])
elif value and isinstance(value, list) \
and isinstance(value[0], Node):
internals.append('%7s%s:' % ('', key))
for v in value:
internals.extend(['%9s%s' % ('', line)
for line in v.pformat().splitlines()])
else:
internals.append('%7s%s: %r' % ('', key, value))
return (Element.pformat(self, indent, level)
+ ''.join([(' %s%s\n' % (indent * level, line))
for line in internals]))
def copy(self):
return self.__class__(self.transform, self.details, self.rawsource,
**self.attributes)
class raw(Special, Inline, PreBibliographic, FixedTextElement):
"""
Raw data that is to be passed untouched to the Writer.
"""
pass
# =================
# Inline Elements
# =================
class emphasis(Inline, TextElement): pass
class strong(Inline, TextElement): pass
class literal(Inline, TextElement): pass
class reference(General, Inline, Referential, TextElement): pass
class footnote_reference(Inline, Referential, TextElement): pass
class citation_reference(Inline, Referential, TextElement): pass
class substitution_reference(Inline, TextElement): pass
class title_reference(Inline, TextElement): pass
class abbreviation(Inline, TextElement): pass
class acronym(Inline, TextElement): pass
class superscript(Inline, TextElement): pass
class subscript(Inline, TextElement): pass
class math(Inline, TextElement): pass
class image(General, Inline, Element):
def astext(self):
return self.get('alt', '')
class inline(Inline, TextElement): pass
class problematic(Inline, TextElement): pass
class generated(Inline, TextElement): pass
# ========================================
# Auxiliary Classes, Functions, and Data
# ========================================
node_class_names = """
Text
abbreviation acronym address admonition attention attribution author
authors
block_quote bullet_list
caption caution citation citation_reference classifier colspec comment
compound contact container copyright
danger date decoration definition definition_list definition_list_item
description docinfo doctest_block document
emphasis entry enumerated_list error
field field_body field_list field_name figure footer
footnote footnote_reference
generated
header hint
image important inline
label legend line line_block list_item literal literal_block
math math_block
note
option option_argument option_group option_list option_list_item
option_string organization
paragraph pending problematic
raw reference revision row rubric
section sidebar status strong subscript substitution_definition
substitution_reference subtitle superscript system_message
table target tbody term tgroup thead tip title title_reference topic
transition
version
warning""".split()
"""A list of names of all concrete Node subclasses."""
class NodeVisitor:
"""
"Visitor" pattern [GoF95]_ abstract superclass implementation for
document tree traversals.
Each node class has corresponding methods, doing nothing by
default; override individual methods for specific and useful
behaviour. The `dispatch_visit()` method is called by
`Node.walk()` upon entering a node. `Node.walkabout()` also calls
the `dispatch_departure()` method before exiting a node.
The dispatch methods call "``visit_`` + node class name" or
"``depart_`` + node class name", resp.
This is a base class for visitors whose ``visit_...`` & ``depart_...``
methods should be implemented for *all* node types encountered (such as
for `docutils.writers.Writer` subclasses). Unimplemented methods will
raise exceptions.
For sparse traversals, where only certain node types are of interest,
subclass `SparseNodeVisitor` instead. When (mostly or entirely) uniform
processing is desired, subclass `GenericNodeVisitor`.
.. [GoF95] Gamma, Helm, Johnson, Vlissides. *Design Patterns: Elements of
Reusable Object-Oriented Software*. Addison-Wesley, Reading, MA, USA,
1995.
"""
optional = ()
"""
Tuple containing node class names (as strings).
No exception will be raised if writers do not implement visit
or departure functions for these node classes.
Used to ensure transitional compatibility with existing 3rd-party writers.
"""
def __init__(self, document):
self.document = document
def dispatch_visit(self, node):
"""
Call self."``visit_`` + node class name" with `node` as
parameter. If the ``visit_...`` method does not exist, call
self.unknown_visit.
"""
node_name = node.__class__.__name__
method = getattr(self, 'visit_' + node_name, self.unknown_visit)
self.document.reporter.debug(
'docutils.nodes.NodeVisitor.dispatch_visit calling %s for %s'
% (method.__name__, node_name))
return method(node)
def dispatch_departure(self, node):
"""
Call self."``depart_`` + node class name" with `node` as
parameter. If the ``depart_...`` method does not exist, call
self.unknown_departure.
"""
node_name = node.__class__.__name__
method = getattr(self, 'depart_' + node_name, self.unknown_departure)
self.document.reporter.debug(
'docutils.nodes.NodeVisitor.dispatch_departure calling %s for %s'
% (method.__name__, node_name))
return method(node)
def unknown_visit(self, node):
"""
Called when entering unknown `Node` types.
Raise an exception unless overridden.
"""
if (self.document.settings.strict_visitor
or node.__class__.__name__ not in self.optional):
raise NotImplementedError(
'%s visiting unknown node type: %s'
% (self.__class__, node.__class__.__name__))
def unknown_departure(self, node):
"""
Called before exiting unknown `Node` types.
Raise exception unless overridden.
"""
if (self.document.settings.strict_visitor
or node.__class__.__name__ not in self.optional):
raise NotImplementedError(
'%s departing unknown node type: %s'
% (self.__class__, node.__class__.__name__))
class SparseNodeVisitor(NodeVisitor):
"""
Base class for sparse traversals, where only certain node types are of
interest. When ``visit_...`` & ``depart_...`` methods should be
implemented for *all* node types (such as for `docutils.writers.Writer`
subclasses), subclass `NodeVisitor` instead.
"""
class GenericNodeVisitor(NodeVisitor):
"""
Generic "Visitor" abstract superclass, for simple traversals.
Unless overridden, each ``visit_...`` method calls `default_visit()`, and
each ``depart_...`` method (when using `Node.walkabout()`) calls
`default_departure()`. `default_visit()` (and `default_departure()`) must
be overridden in subclasses.
Define fully generic visitors by overriding `default_visit()` (and
`default_departure()`) only. Define semi-generic visitors by overriding
individual ``visit_...()`` (and ``depart_...()``) methods also.
`NodeVisitor.unknown_visit()` (`NodeVisitor.unknown_departure()`) should
be overridden for default behavior.
"""
def default_visit(self, node):
"""Override for generic, uniform traversals."""
raise NotImplementedError
def default_departure(self, node):
"""Override for generic, uniform traversals."""
raise NotImplementedError
def _call_default_visit(self, node):
self.default_visit(node)
def _call_default_departure(self, node):
self.default_departure(node)
def _nop(self, node):
pass
def _add_node_class_names(names):
"""Save typing with dynamic assignments:"""
for _name in names:
setattr(GenericNodeVisitor, "visit_" + _name, _call_default_visit)
setattr(GenericNodeVisitor, "depart_" + _name, _call_default_departure)
setattr(SparseNodeVisitor, 'visit_' + _name, _nop)
setattr(SparseNodeVisitor, 'depart_' + _name, _nop)
_add_node_class_names(node_class_names)
class TreeCopyVisitor(GenericNodeVisitor):
"""
Make a complete copy of a tree or branch, including element attributes.
"""
def __init__(self, document):
GenericNodeVisitor.__init__(self, document)
self.parent_stack = []
self.parent = []
def get_tree_copy(self):
return self.parent[0]
def default_visit(self, node):
"""Copy the current node, and make it the new acting parent."""
newnode = node.copy()
self.parent.append(newnode)
self.parent_stack.append(self.parent)
self.parent = newnode
def default_departure(self, node):
"""Restore the previous acting parent."""
self.parent = self.parent_stack.pop()
class TreePruningException(Exception):
"""
Base class for `NodeVisitor`-related tree pruning exceptions.
Raise subclasses from within ``visit_...`` or ``depart_...`` methods
called from `Node.walk()` and `Node.walkabout()` tree traversals to prune
the tree traversed.
"""
pass
class SkipChildren(TreePruningException):
"""
Do not visit any children of the current node. The current node's
siblings and ``depart_...`` method are not affected.
"""
pass
class SkipSiblings(TreePruningException):
"""
Do not visit any more siblings (to the right) of the current node. The
current node's children and its ``depart_...`` method are not affected.
"""
pass
class SkipNode(TreePruningException):
"""
Do not visit the current node's children, and do not call the current
node's ``depart_...`` method.
"""
pass
class SkipDeparture(TreePruningException):
"""
Do not call the current node's ``depart_...`` method. The current node's
children and siblings are not affected.
"""
pass
class NodeFound(TreePruningException):
"""
Raise to indicate that the target of a search has been found. This
exception must be caught by the client; it is not caught by the traversal
code.
"""
pass
class StopTraversal(TreePruningException):
"""
Stop the traversal alltogether. The current node's ``depart_...`` method
is not affected. The parent nodes ``depart_...`` methods are also called
as usual. No other nodes are visited. This is an alternative to
NodeFound that does not cause exception handling to trickle up to the
caller.
"""
pass
def make_id(string):
"""
Convert `string` into an identifier and return it.
Docutils identifiers will conform to the regular expression
``[a-z](-?[a-z0-9]+)*``. For CSS compatibility, identifiers (the "class"
and "id" attributes) should have no underscores, colons, or periods.
Hyphens may be used.
- The `HTML 4.01 spec`_ defines identifiers based on SGML tokens:
ID and NAME tokens must begin with a letter ([A-Za-z]) and may be
followed by any number of letters, digits ([0-9]), hyphens ("-"),
underscores ("_"), colons (":"), and periods (".").
- However the `CSS1 spec`_ defines identifiers based on the "name" token,
a tighter interpretation ("flex" tokenizer notation; "latin1" and
"escape" 8-bit characters have been replaced with entities)::
unicode \\[0-9a-f]{1,4}
latin1 [¡-ÿ]
escape {unicode}|\\[ -~¡-ÿ]
nmchar [-a-z0-9]|{latin1}|{escape}
name {nmchar}+
The CSS1 "nmchar" rule does not include underscores ("_"), colons (":"),
or periods ("."), therefore "class" and "id" attributes should not contain
these characters. They should be replaced with hyphens ("-"). Combined
with HTML's requirements (the first character must be a letter; no
"unicode", "latin1", or "escape" characters), this results in the
``[a-z](-?[a-z0-9]+)*`` pattern.
.. _HTML 4.01 spec: http://www.w3.org/TR/html401
.. _CSS1 spec: http://www.w3.org/TR/REC-CSS1
"""
id = string.lower()
if not isinstance(id, unicode):
id = id.decode()
id = id.translate(_non_id_translate_digraphs)
id = id.translate(_non_id_translate)
# get rid of non-ascii characters.
# 'ascii' lowercase to prevent problems with turkish locale.
id = unicodedata.normalize('NFKD', id).\
encode('ascii', 'ignore').decode('ascii')
# shrink runs of whitespace and replace by hyphen
id = _non_id_chars.sub('-', ' '.join(id.split()))
id = _non_id_at_ends.sub('', id)
return str(id)
_non_id_chars = re.compile('[^a-z0-9]+')
_non_id_at_ends = re.compile('^[-0-9]+|-+$')
_non_id_translate = {
0x00f8: u'o', # o with stroke
0x0111: u'd', # d with stroke
0x0127: u'h', # h with stroke
0x0131: u'i', # dotless i
0x0142: u'l', # l with stroke
0x0167: u't', # t with stroke
0x0180: u'b', # b with stroke
0x0183: u'b', # b with topbar
0x0188: u'c', # c with hook
0x018c: u'd', # d with topbar
0x0192: u'f', # f with hook
0x0199: u'k', # k with hook
0x019a: u'l', # l with bar
0x019e: u'n', # n with long right leg
0x01a5: u'p', # p with hook
0x01ab: u't', # t with palatal hook
0x01ad: u't', # t with hook
0x01b4: u'y', # y with hook
0x01b6: u'z', # z with stroke
0x01e5: u'g', # g with stroke
0x0225: u'z', # z with hook
0x0234: u'l', # l with curl
0x0235: u'n', # n with curl
0x0236: u't', # t with curl
0x0237: u'j', # dotless j
0x023c: u'c', # c with stroke
0x023f: u's', # s with swash tail
0x0240: u'z', # z with swash tail
0x0247: u'e', # e with stroke
0x0249: u'j', # j with stroke
0x024b: u'q', # q with hook tail
0x024d: u'r', # r with stroke
0x024f: u'y', # y with stroke
}
_non_id_translate_digraphs = {
0x00df: u'sz', # ligature sz
0x00e6: u'ae', # ae
0x0153: u'oe', # ligature oe
0x0238: u'db', # db digraph
0x0239: u'qp', # qp digraph
}
def dupname(node, name):
node['dupnames'].append(name)
node['names'].remove(name)
# Assume that this method is referenced, even though it isn't; we
# don't want to throw unnecessary system_messages.
node.referenced = 1
def fully_normalize_name(name):
"""Return a case- and whitespace-normalized name."""
return ' '.join(name.lower().split())
def whitespace_normalize_name(name):
"""Return a whitespace-normalized name."""
return ' '.join(name.split())
def serial_escape(value):
"""Escape string values that are elements of a list, for serialization."""
return value.replace('\\', r'\\').replace(' ', r'\ ')
def pseudo_quoteattr(value):
"""Quote attributes for pseudo-xml"""
return '"%s"' % value
#
#
# Local Variables:
# indent-tabs-mode: nil
# sentence-end-double-space: t
# fill-column: 78
# End:
|