/usr/share/pyshared/webhelpers/markdown.py is in python-webhelpers 1.3-4.
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 | #!/usr/bin/env python
version = "1.7"
version_info = (1,7,0,"rc-2")
__revision__ = "$Rev: 72 $"
"""
Python-Markdown
===============
Converts Markdown to HTML. Basic usage as a module:
import markdown
md = Markdown()
html = md.convert(your_text_string)
See http://www.freewisdom.org/projects/python-markdown/ for more
information and instructions on how to extend the functionality of the
script. (You might want to read that before you try modifying this
file.)
Started by [Manfred Stienstra](http://www.dwerg.net/). Continued and
maintained by [Yuri Takhteyev](http://www.freewisdom.org) and [Waylan
Limberg](http://achinghead.com/).
Contact: yuri [at] freewisdom.org
waylan [at] gmail.com
License: GPL 2 (http://www.gnu.org/copyleft/gpl.html) or BSD
"""
import re, sys, codecs
from logging import getLogger, StreamHandler, Formatter, \
DEBUG, INFO, WARN, ERROR, CRITICAL
MESSAGE_THRESHOLD = CRITICAL
# Configure debug message logger (the hard way - to support python 2.3)
logger = getLogger('MARKDOWN')
logger.setLevel(DEBUG) # This is restricted by handlers later
console_hndlr = StreamHandler()
formatter = Formatter('%(name)s-%(levelname)s: "%(message)s"')
console_hndlr.setFormatter(formatter)
console_hndlr.setLevel(MESSAGE_THRESHOLD)
logger.addHandler(console_hndlr)
def message(level, text):
''' A wrapper method for logging debug messages. '''
logger.log(level, text)
# --------------- CONSTANTS YOU MIGHT WANT TO MODIFY -----------------
TAB_LENGTH = 4 # expand tabs to this many spaces
ENABLE_ATTRIBUTES = True # @id = xyz -> <... id="xyz">
SMART_EMPHASIS = 1 # this_or_that does not become this<i>or</i>that
HTML_REMOVED_TEXT = "[HTML_REMOVED]" # text used instead of HTML in safe mode
RTL_BIDI_RANGES = ( (u'\u0590', u'\u07FF'),
# from Hebrew to Nko (includes Arabic, Syriac and Thaana)
(u'\u2D30', u'\u2D7F'),
# Tifinagh
)
# Unicode Reference Table:
# 0590-05FF - Hebrew
# 0600-06FF - Arabic
# 0700-074F - Syriac
# 0750-077F - Arabic Supplement
# 0780-07BF - Thaana
# 07C0-07FF - Nko
BOMS = { 'utf-8': (codecs.BOM_UTF8, ),
'utf-16': (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE),
#'utf-32': (codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE)
}
def removeBOM(text, encoding):
convert = isinstance(text, unicode)
for bom in BOMS[encoding]:
bom = convert and bom.decode(encoding) or bom
if text.startswith(bom):
return text.lstrip(bom)
return text
# The following constant specifies the name used in the usage
# statement displayed for python versions lower than 2.3. (With
# python2.3 and higher the usage statement is generated by optparse
# and uses the actual name of the executable called.)
EXECUTABLE_NAME_FOR_USAGE = "python markdown.py"
# --------------- CONSTANTS YOU _SHOULD NOT_ HAVE TO CHANGE ----------
# a template for html placeholders
HTML_PLACEHOLDER_PREFIX = "qaodmasdkwaspemas"
HTML_PLACEHOLDER = HTML_PLACEHOLDER_PREFIX + "%dajkqlsmdqpakldnzsdfls"
BLOCK_LEVEL_ELEMENTS = ['p', 'div', 'blockquote', 'pre', 'table',
'dl', 'ol', 'ul', 'script', 'noscript',
'form', 'fieldset', 'iframe', 'math', 'ins',
'del', 'hr', 'hr/', 'style']
def isBlockLevel (tag):
return ( (tag in BLOCK_LEVEL_ELEMENTS) or
(tag[0] == 'h' and tag[1] in "0123456789") )
"""
======================================================================
========================== NANODOM ===================================
======================================================================
The three classes below implement some of the most basic DOM
methods. I use this instead of minidom because I need a simpler
functionality and do not want to require additional libraries.
Importantly, NanoDom does not do normalization, which is what we
want. It also adds extra white space when converting DOM to string
"""
ENTITY_NORMALIZATION_EXPRESSIONS = [ (re.compile("&"), "&"),
(re.compile("<"), "<"),
(re.compile(">"), ">")]
ENTITY_NORMALIZATION_EXPRESSIONS_SOFT = [ (re.compile("&(?!\#)"), "&"),
(re.compile("<"), "<"),
(re.compile(">"), ">"),
(re.compile("\""), """)]
def getBidiType(text):
if not text: return None
ch = text[0]
if not isinstance(ch, unicode) or not ch.isalpha():
return None
else:
for min, max in RTL_BIDI_RANGES:
if ( ch >= min and ch <= max ):
return "rtl"
else:
return "ltr"
class Document:
def __init__ (self):
self.bidi = "ltr"
def appendChild(self, child):
self.documentElement = child
child.isDocumentElement = True
child.parent = self
self.entities = {}
def setBidi(self, bidi):
if bidi:
self.bidi = bidi
def createElement(self, tag, textNode=None):
el = Element(tag)
el.doc = self
if textNode:
el.appendChild(self.createTextNode(textNode))
return el
def createTextNode(self, text):
node = TextNode(text)
node.doc = self
return node
def createEntityReference(self, entity):
if entity not in self.entities:
self.entities[entity] = EntityReference(entity)
return self.entities[entity]
def createCDATA(self, text):
node = CDATA(text)
node.doc = self
return node
def toxml (self):
return self.documentElement.toxml()
def normalizeEntities(self, text, avoidDoubleNormalizing=False):
if avoidDoubleNormalizing:
regexps = ENTITY_NORMALIZATION_EXPRESSIONS_SOFT
else:
regexps = ENTITY_NORMALIZATION_EXPRESSIONS
for regexp, substitution in regexps:
text = regexp.sub(substitution, text)
return text
def find(self, test):
return self.documentElement.find(test)
def unlink(self):
self.documentElement.unlink()
self.documentElement = None
class CDATA:
type = "cdata"
def __init__ (self, text):
self.text = text
def handleAttributes(self):
pass
def toxml (self):
return "<![CDATA[" + self.text + "]]>"
class Element:
type = "element"
def __init__ (self, tag):
self.nodeName = tag
self.attributes = []
self.attribute_values = {}
self.childNodes = []
self.bidi = None
self.isDocumentElement = False
def setBidi(self, bidi):
if bidi:
orig_bidi = self.bidi
if not self.bidi or self.isDocumentElement:
# Once the bidi is set don't change it (except for doc element)
self.bidi = bidi
self.parent.setBidi(bidi)
def unlink(self):
for child in self.childNodes:
if child.type == "element":
child.unlink()
self.childNodes = None
def setAttribute(self, attr, value):
if not attr in self.attributes:
self.attributes.append(attr)
self.attribute_values[attr] = value
def insertChild(self, position, child):
self.childNodes.insert(position, child)
child.parent = self
def removeChild(self, child):
self.childNodes.remove(child)
def replaceChild(self, oldChild, newChild):
position = self.childNodes.index(oldChild)
self.removeChild(oldChild)
self.insertChild(position, newChild)
def appendChild(self, child):
self.childNodes.append(child)
child.parent = self
def handleAttributes(self):
pass
def find(self, test, depth=0):
""" Returns a list of descendants that pass the test function """
matched_nodes = []
for child in self.childNodes:
if test(child):
matched_nodes.append(child)
if child.type == "element":
matched_nodes += child.find(test, depth+1)
return matched_nodes
def toxml(self):
if ENABLE_ATTRIBUTES:
for child in self.childNodes:
child.handleAttributes()
buffer = ""
if self.nodeName in ['h1', 'h2', 'h3', 'h4']:
buffer += "\n"
elif self.nodeName in ['li']:
buffer += "\n "
# Process children FIRST, then do the attributes
childBuffer = ""
if self.childNodes or self.nodeName in ['blockquote']:
childBuffer += ">"
for child in self.childNodes:
childBuffer += child.toxml()
if self.nodeName == 'p':
childBuffer += "\n"
elif self.nodeName == 'li':
childBuffer += "\n "
childBuffer += "</%s>" % self.nodeName
else:
childBuffer += "/>"
buffer += "<" + self.nodeName
if self.nodeName in ['p', 'li', 'ul', 'ol',
'h1', 'h2', 'h3', 'h4', 'h5', 'h6']:
if not self.attribute_values.has_key("dir"):
if self.bidi:
bidi = self.bidi
else:
bidi = self.doc.bidi
if bidi=="rtl":
self.setAttribute("dir", "rtl")
for attr in self.attributes:
value = self.attribute_values[attr]
value = self.doc.normalizeEntities(value,
avoidDoubleNormalizing=True)
buffer += ' %s="%s"' % (attr, value)
# Now let's actually append the children
buffer += childBuffer
if self.nodeName in ['p', 'br ', 'li', 'ul', 'ol',
'h1', 'h2', 'h3', 'h4'] :
buffer += "\n"
return buffer
class TextNode:
type = "text"
attrRegExp = re.compile(r'\{@([^\}]*)=([^\}]*)}') # {@id=123}
def __init__ (self, text):
self.value = text
def attributeCallback(self, match):
self.parent.setAttribute(match.group(1), match.group(2))
def handleAttributes(self):
self.value = self.attrRegExp.sub(self.attributeCallback, self.value)
def toxml(self):
text = self.value
self.parent.setBidi(getBidiType(text))
if not text.startswith(HTML_PLACEHOLDER_PREFIX):
if self.parent.nodeName == "p":
text = text.replace("\n", "\n ")
elif (self.parent.nodeName == "li"
and self.parent.childNodes[0]==self):
text = "\n " + text.replace("\n", "\n ")
text = self.doc.normalizeEntities(text)
return text
class EntityReference:
type = "entity_ref"
def __init__(self, entity):
self.entity = entity
def handleAttributes(self):
pass
def toxml(self):
return "&" + self.entity + ";"
"""
======================================================================
========================== PRE-PROCESSORS ============================
======================================================================
Preprocessors munge source text before we start doing anything too
complicated.
There are two types of preprocessors: TextPreprocessor and Preprocessor.
"""
class TextPreprocessor:
'''
TextPreprocessors are run before the text is broken into lines.
Each TextPreprocessor implements a "run" method that takes a pointer to a
text string of the document, modifies it as necessary and returns
either the same pointer or a pointer to a new string.
TextPreprocessors must extend markdown.TextPreprocessor.
'''
def run(self, text):
pass
class Preprocessor:
'''
Preprocessors are run after the text is broken into lines.
Each preprocessor implements a "run" method that takes a pointer to a
list of lines of the document, modifies it as necessary and returns
either the same pointer or a pointer to a new list.
Preprocessors must extend markdown.Preprocessor.
'''
def run(self, lines):
pass
class HtmlBlockPreprocessor(TextPreprocessor):
"""Removes html blocks from the source text and stores it."""
def _get_left_tag(self, block):
return block[1:].replace(">", " ", 1).split()[0].lower()
def _get_right_tag(self, left_tag, block):
return block.rstrip()[-len(left_tag)-2:-1].lower()
def _equal_tags(self, left_tag, right_tag):
if left_tag == 'div' or left_tag[0] in ['?', '@', '%']: # handle PHP, etc.
return True
if ("/" + left_tag) == right_tag:
return True
if (right_tag == "--" and left_tag == "--"):
return True
elif left_tag == right_tag[1:] \
and right_tag[0] != "<":
return True
else:
return False
def _is_oneliner(self, tag):
return (tag in ['hr', 'hr/'])
def run(self, text):
new_blocks = []
text = text.split("\n\n")
items = []
left_tag = ''
right_tag = ''
in_tag = False # flag
for block in text:
if block.startswith("\n"):
block = block[1:]
if not in_tag:
if block.startswith("<"):
left_tag = self._get_left_tag(block)
right_tag = self._get_right_tag(left_tag, block)
if not (isBlockLevel(left_tag) \
or block[1] in ["!", "?", "@", "%"]):
new_blocks.append(block)
continue
if self._is_oneliner(left_tag):
new_blocks.append(block.strip())
continue
if block[1] == "!":
# is a comment block
left_tag = "--"
right_tag = self._get_right_tag(left_tag, block)
# keep checking conditions below and maybe just append
if block.rstrip().endswith(">") \
and self._equal_tags(left_tag, right_tag):
new_blocks.append(
self.stash.store(block.strip()))
continue
else: #if not block[1] == "!":
# if is block level tag and is not complete
items.append(block.strip())
in_tag = True
continue
new_blocks.append(block)
else:
items.append(block.strip())
right_tag = self._get_right_tag(left_tag, block)
if self._equal_tags(left_tag, right_tag):
# if find closing tag
in_tag = False
new_blocks.append(
self.stash.store('\n\n'.join(items)))
items = []
if items:
new_blocks.append(self.stash.store('\n\n'.join(items)))
new_blocks.append('\n')
return "\n\n".join(new_blocks)
HTML_BLOCK_PREPROCESSOR = HtmlBlockPreprocessor()
class HeaderPreprocessor(Preprocessor):
"""
Replaces underlined headers with hashed headers to avoid
the need for lookahead later.
"""
def run (self, lines):
i = -1
while i+1 < len(lines):
i = i+1
if not lines[i].strip():
continue
if lines[i].startswith("#"):
lines.insert(i+1, "\n")
if (i+1 <= len(lines)
and lines[i+1]
and lines[i+1][0] in ['-', '=']):
underline = lines[i+1].strip()
if underline == "="*len(underline):
lines[i] = "# " + lines[i].strip()
lines[i+1] = ""
elif underline == "-"*len(underline):
lines[i] = "## " + lines[i].strip()
lines[i+1] = ""
return lines
HEADER_PREPROCESSOR = HeaderPreprocessor()
class LinePreprocessor(Preprocessor):
"""Deals with HR lines (needs to be done before processing lists)"""
blockquote_re = re.compile(r'^(> )+')
def run (self, lines):
for i in range(len(lines)):
prefix = ''
m = self.blockquote_re.search(lines[i])
if m : prefix = m.group(0)
if self._isLine(lines[i][len(prefix):]):
lines[i] = prefix + self.stash.store("<hr />", safe=True)
return lines
def _isLine(self, block):
"""Determines if a block should be replaced with an <HR>"""
if block.startswith(" "): return 0 # a code block
text = "".join([x for x in block if not x.isspace()])
if len(text) <= 2:
return 0
for pattern in ['isline1', 'isline2', 'isline3']:
m = RE.regExp[pattern].match(text)
if (m and m.group(1)):
return 1
else:
return 0
LINE_PREPROCESSOR = LinePreprocessor()
class ReferencePreprocessor(Preprocessor):
'''
Removes reference definitions from the text and stores them for later use.
'''
def run (self, lines):
new_text = [];
for line in lines:
m = RE.regExp['reference-def'].match(line)
if m:
id = m.group(2).strip().lower()
t = m.group(4).strip() # potential title
if not t:
self.references[id] = (m.group(3), t)
elif (len(t) >= 2
and (t[0] == t[-1] == "\""
or t[0] == t[-1] == "\'"
or (t[0] == "(" and t[-1] == ")") ) ):
self.references[id] = (m.group(3), t[1:-1])
else:
new_text.append(line)
else:
new_text.append(line)
return new_text #+ "\n"
REFERENCE_PREPROCESSOR = ReferencePreprocessor()
"""
======================================================================
========================== INLINE PATTERNS ===========================
======================================================================
Inline patterns such as *emphasis* are handled by means of auxiliary
objects, one per pattern. Pattern objects must be instances of classes
that extend markdown.Pattern. Each pattern object uses a single regular
expression and needs support the following methods:
pattern.getCompiledRegExp() - returns a regular expression
pattern.handleMatch(m, doc) - takes a match object and returns
a NanoDom node (as a part of the provided
doc) or None
All of python markdown's built-in patterns subclass from Patter,
but you can add additional patterns that don't.
Also note that all the regular expressions used by inline must
capture the whole block. For this reason, they all start with
'^(.*)' and end with '(.*)!'. In case with built-in expression
Pattern takes care of adding the "^(.*)" and "(.*)!".
Finally, the order in which regular expressions are applied is very
important - e.g. if we first replace http://.../ links with <a> tags
and _then_ try to replace inline html, we would end up with a mess.
So, we apply the expressions in the following order:
* escape and backticks have to go before everything else, so
that we can preempt any markdown patterns by escaping them.
* then we handle auto-links (must be done before inline html)
* then we handle inline HTML. At this point we will simply
replace all inline HTML strings with a placeholder and add
the actual HTML to a hash.
* then inline images (must be done before links)
* then bracketed links, first regular then reference-style
* finally we apply strong and emphasis
"""
NOBRACKET = r'[^\]\[]*'
BRK = ( r'\[('
+ (NOBRACKET + r'(\[')*6
+ (NOBRACKET+ r'\])*')*6
+ NOBRACKET + r')\]' )
NOIMG = r'(?<!\!)'
BACKTICK_RE = r'\`([^\`]*)\`' # `e= m*c^2`
DOUBLE_BACKTICK_RE = r'\`\`(.*)\`\`' # ``e=f("`")``
ESCAPE_RE = r'\\(.)' # \<
EMPHASIS_RE = r'\*([^\*]*)\*' # *emphasis*
STRONG_RE = r'\*\*(.*)\*\*' # **strong**
STRONG_EM_RE = r'\*\*\*([^_]*)\*\*\*' # ***strong***
if SMART_EMPHASIS:
EMPHASIS_2_RE = r'(?<!\S)_(\S[^_]*)_' # _emphasis_
else:
EMPHASIS_2_RE = r'_([^_]*)_' # _emphasis_
STRONG_2_RE = r'__([^_]*)__' # __strong__
STRONG_EM_2_RE = r'___([^_]*)___' # ___strong___
LINK_RE = NOIMG + BRK + r'\s*\(([^\)]*)\)' # [text](url)
LINK_ANGLED_RE = NOIMG + BRK + r'\s*\(<([^\)]*)>\)' # [text](<url>)
IMAGE_LINK_RE = r'\!' + BRK + r'\s*\(([^\)]*)\)' # ![alttxt](http://x.com/)
REFERENCE_RE = NOIMG + BRK+ r'\s*\[([^\]]*)\]' # [Google][3]
IMAGE_REFERENCE_RE = r'\!' + BRK + '\s*\[([^\]]*)\]' # ![alt text][2]
NOT_STRONG_RE = r'( \* )' # stand-alone * or _
AUTOLINK_RE = r'<(http://[^>]*)>' # <http://www.123.com>
AUTOMAIL_RE = r'<([^> \!]*@[^> ]*)>' # <me@example.com>
#HTML_RE = r'(\<[^\>]*\>)' # <...>
HTML_RE = r'(\<[a-zA-Z/][^\>]*\>)' # <...>
ENTITY_RE = r'(&[\#a-zA-Z0-9]*;)' # &
LINE_BREAK_RE = r' \n' # two spaces at end of line
LINE_BREAK_2_RE = r' $' # two spaces at end of text
class Pattern:
def __init__ (self, pattern):
self.pattern = pattern
self.compiled_re = re.compile("^(.*)%s(.*)$" % pattern, re.DOTALL)
def getCompiledRegExp (self):
return self.compiled_re
BasePattern = Pattern # for backward compatibility
class SimpleTextPattern (Pattern):
def handleMatch(self, m, doc):
return doc.createTextNode(m.group(2))
class SimpleTagPattern (Pattern):
def __init__ (self, pattern, tag):
Pattern.__init__(self, pattern)
self.tag = tag
def handleMatch(self, m, doc):
el = doc.createElement(self.tag)
el.appendChild(doc.createTextNode(m.group(2)))
return el
class SubstituteTagPattern (SimpleTagPattern):
def handleMatch (self, m, doc):
return doc.createElement(self.tag)
class BacktickPattern (Pattern):
def __init__ (self, pattern):
Pattern.__init__(self, pattern)
self.tag = "code"
def handleMatch(self, m, doc):
el = doc.createElement(self.tag)
text = m.group(2).strip()
#text = text.replace("&", "&")
el.appendChild(doc.createTextNode(text))
return el
class DoubleTagPattern (SimpleTagPattern):
def handleMatch(self, m, doc):
tag1, tag2 = self.tag.split(",")
el1 = doc.createElement(tag1)
el2 = doc.createElement(tag2)
el1.appendChild(el2)
el2.appendChild(doc.createTextNode(m.group(2)))
return el1
class HtmlPattern (Pattern):
def handleMatch (self, m, doc):
rawhtml = m.group(2)
inline = True
place_holder = self.stash.store(rawhtml)
return doc.createTextNode(place_holder)
class LinkPattern (Pattern):
def handleMatch(self, m, doc):
el = doc.createElement('a')
el.appendChild(doc.createTextNode(m.group(2)))
parts = m.group(9).split('"')
# We should now have [], [href], or [href, title]
if parts:
el.setAttribute('href', parts[0].strip())
else:
el.setAttribute('href', "")
if len(parts) > 1:
# we also got a title
title = '"' + '"'.join(parts[1:]).strip()
title = dequote(title) #.replace('"', """)
el.setAttribute('title', title)
return el
class ImagePattern (Pattern):
def handleMatch(self, m, doc):
el = doc.createElement('img')
src_parts = m.group(9).split()
if src_parts:
el.setAttribute('src', src_parts[0])
else:
el.setAttribute('src', "")
if len(src_parts) > 1:
el.setAttribute('title', dequote(" ".join(src_parts[1:])))
if ENABLE_ATTRIBUTES:
text = doc.createTextNode(m.group(2))
el.appendChild(text)
text.handleAttributes()
truealt = text.value
el.childNodes.remove(text)
else:
truealt = m.group(2)
el.setAttribute('alt', truealt)
return el
class ReferencePattern (Pattern):
def handleMatch(self, m, doc):
if m.group(9):
id = m.group(9).lower()
else:
# if we got something like "[Google][]"
# we'll use "google" as the id
id = m.group(2).lower()
if not self.references.has_key(id): # ignore undefined refs
return None
href, title = self.references[id]
text = m.group(2)
return self.makeTag(href, title, text, doc)
def makeTag(self, href, title, text, doc):
el = doc.createElement('a')
el.setAttribute('href', href)
if title:
el.setAttribute('title', title)
el.appendChild(doc.createTextNode(text))
return el
class ImageReferencePattern (ReferencePattern):
def makeTag(self, href, title, text, doc):
el = doc.createElement('img')
el.setAttribute('src', href)
if title:
el.setAttribute('title', title)
el.setAttribute('alt', text)
return el
class AutolinkPattern (Pattern):
def handleMatch(self, m, doc):
el = doc.createElement('a')
el.setAttribute('href', m.group(2))
el.appendChild(doc.createTextNode(m.group(2)))
return el
class AutomailPattern (Pattern):
def handleMatch(self, m, doc):
el = doc.createElement('a')
email = m.group(2)
if email.startswith("mailto:"):
email = email[len("mailto:"):]
for letter in email:
entity = doc.createEntityReference("#%d" % ord(letter))
el.appendChild(entity)
mailto = "mailto:" + email
mailto = "".join(['&#%d;' % ord(letter) for letter in mailto])
el.setAttribute('href', mailto)
return el
ESCAPE_PATTERN = SimpleTextPattern(ESCAPE_RE)
NOT_STRONG_PATTERN = SimpleTextPattern(NOT_STRONG_RE)
BACKTICK_PATTERN = BacktickPattern(BACKTICK_RE)
DOUBLE_BACKTICK_PATTERN = BacktickPattern(DOUBLE_BACKTICK_RE)
STRONG_PATTERN = SimpleTagPattern(STRONG_RE, 'strong')
STRONG_PATTERN_2 = SimpleTagPattern(STRONG_2_RE, 'strong')
EMPHASIS_PATTERN = SimpleTagPattern(EMPHASIS_RE, 'em')
EMPHASIS_PATTERN_2 = SimpleTagPattern(EMPHASIS_2_RE, 'em')
STRONG_EM_PATTERN = DoubleTagPattern(STRONG_EM_RE, 'strong,em')
STRONG_EM_PATTERN_2 = DoubleTagPattern(STRONG_EM_2_RE, 'strong,em')
LINE_BREAK_PATTERN = SubstituteTagPattern(LINE_BREAK_RE, 'br ')
LINE_BREAK_PATTERN_2 = SubstituteTagPattern(LINE_BREAK_2_RE, 'br ')
LINK_PATTERN = LinkPattern(LINK_RE)
LINK_ANGLED_PATTERN = LinkPattern(LINK_ANGLED_RE)
IMAGE_LINK_PATTERN = ImagePattern(IMAGE_LINK_RE)
IMAGE_REFERENCE_PATTERN = ImageReferencePattern(IMAGE_REFERENCE_RE)
REFERENCE_PATTERN = ReferencePattern(REFERENCE_RE)
HTML_PATTERN = HtmlPattern(HTML_RE)
ENTITY_PATTERN = HtmlPattern(ENTITY_RE)
AUTOLINK_PATTERN = AutolinkPattern(AUTOLINK_RE)
AUTOMAIL_PATTERN = AutomailPattern(AUTOMAIL_RE)
"""
======================================================================
========================== POST-PROCESSORS ===========================
======================================================================
Markdown also allows post-processors, which are similar to
preprocessors in that they need to implement a "run" method. However,
they are run after core processing.
There are two types of post-processors: Postprocessor and TextPostprocessor
"""
class Postprocessor:
'''
Postprocessors are run before the dom it converted back into text.
Each Postprocessor implements a "run" method that takes a pointer to a
NanoDom document, modifies it as necessary and returns a NanoDom
document.
Postprocessors must extend markdown.Postprocessor.
There are currently no standard post-processors, but the footnote
extension uses one.
'''
def run(self, dom):
pass
class TextPostprocessor:
'''
TextPostprocessors are run after the dom it converted back into text.
Each TextPostprocessor implements a "run" method that takes a pointer to a
text string, modifies it as necessary and returns a text string.
TextPostprocessors must extend markdown.TextPostprocessor.
'''
def run(self, text):
pass
class RawHtmlTextPostprocessor(TextPostprocessor):
def __init__(self):
pass
def run(self, text):
for i in range(self.stash.html_counter):
html, safe = self.stash.rawHtmlBlocks[i]
if self.safeMode and not safe:
if str(self.safeMode).lower() == 'escape':
html = self.escape(html)
elif str(self.safeMode).lower() == 'remove':
html = ''
else:
html = HTML_REMOVED_TEXT
text = text.replace("<p>%s\n</p>" % (HTML_PLACEHOLDER % i),
html + "\n")
text = text.replace(HTML_PLACEHOLDER % i, html)
return text
def escape(self, html):
''' Basic html escaping '''
html = html.replace('&', '&')
html = html.replace('<', '<')
html = html.replace('>', '>')
return html.replace('"', '"')
RAWHTMLTEXTPOSTPROCESSOR = RawHtmlTextPostprocessor()
"""
======================================================================
========================== MISC AUXILIARY CLASSES ====================
======================================================================
"""
class HtmlStash:
"""This class is used for stashing HTML objects that we extract
in the beginning and replace with place-holders."""
def __init__ (self):
self.html_counter = 0 # for counting inline html segments
self.rawHtmlBlocks=[]
def store(self, html, safe=False):
"""Saves an HTML segment for later reinsertion. Returns a
placeholder string that needs to be inserted into the
document.
@param html: an html segment
@param safe: label an html segment as safe for safemode
@param inline: label a segmant as inline html
@returns : a placeholder string """
self.rawHtmlBlocks.append((html, safe))
placeholder = HTML_PLACEHOLDER % self.html_counter
self.html_counter += 1
return placeholder
class BlockGuru:
def _findHead(self, lines, fn, allowBlank=0):
"""Functional magic to help determine boundaries of indented
blocks.
@param lines: an array of strings
@param fn: a function that returns a substring of a string
if the string matches the necessary criteria
@param allowBlank: specifies whether it's ok to have blank
lines between matching functions
@returns: a list of post processes items and the unused
remainder of the original list"""
items = []
item = -1
i = 0 # to keep track of where we are
for line in lines:
if not line.strip() and not allowBlank:
return items, lines[i:]
if not line.strip() and allowBlank:
# If we see a blank line, this _might_ be the end
i += 1
# Find the next non-blank line
for j in range(i, len(lines)):
if lines[j].strip():
next = lines[j]
break
else:
# There is no more text => this is the end
break
# Check if the next non-blank line is still a part of the list
part = fn(next)
if part:
items.append("")
continue
else:
break # found end of the list
part = fn(line)
if part:
items.append(part)
i += 1
continue
else:
return items, lines[i:]
else:
i += 1
return items, lines[i:]
def detabbed_fn(self, line):
""" An auxiliary method to be passed to _findHead """
m = RE.regExp['tabbed'].match(line)
if m:
return m.group(4)
else:
return None
def detectTabbed(self, lines):
return self._findHead(lines, self.detabbed_fn,
allowBlank = 1)
def print_error(string):
"""Print an error string to stderr"""
sys.stderr.write(string +'\n')
def dequote(string):
""" Removes quotes from around a string """
if ( ( string.startswith('"') and string.endswith('"'))
or (string.startswith("'") and string.endswith("'")) ):
return string[1:-1]
else:
return string
"""
======================================================================
========================== CORE MARKDOWN =============================
======================================================================
This stuff is ugly, so if you are thinking of extending the syntax,
see first if you can do it via pre-processors, post-processors,
inline patterns or a combination of the three.
"""
class CorePatterns:
"""This class is scheduled for removal as part of a refactoring
effort."""
patterns = {
'header': r'(#*)([^#]*)(#*)', # # A title
'reference-def': r'(\ ?\ ?\ ?)\[([^\]]*)\]:\s*([^ ]*)(.*)',
# [Google]: http://www.google.com/
'containsline': r'([-]*)$|^([=]*)', # -----, =====, etc.
'ol': r'[ ]{0,3}[\d]*\.\s+(.*)', # 1. text
'ul': r'[ ]{0,3}[*+-]\s+(.*)', # "* text"
'isline1': r'(\**)', # ***
'isline2': r'(\-*)', # ---
'isline3': r'(\_*)', # ___
'tabbed': r'((\t)|( ))(.*)', # an indented line
'quoted': r'> ?(.*)', # a quoted block ("> ...")
}
def __init__ (self):
self.regExp = {}
for key in self.patterns.keys():
self.regExp[key] = re.compile("^%s$" % self.patterns[key],
re.DOTALL)
self.regExp['containsline'] = re.compile(r'^([-]*)$|^([=]*)$', re.M)
RE = CorePatterns()
class Markdown:
""" Markdown formatter class for creating an html document from
Markdown text """
def __init__(self, source=None, # depreciated
extensions=[],
extension_configs=None,
safe_mode = False):
"""Creates a new Markdown instance.
@param source: The text in Markdown format. Depreciated!
@param extensions: A list if extensions.
@param extension-configs: Configuration setting for extensions.
@param safe_mode: Disallow raw html. """
self.source = source
if source is not None:
message(WARN, "The `source` arg of Markdown.__init__() is depreciated and will be removed in the future. Use `instance.convert(source)` instead.")
self.safeMode = safe_mode
self.blockGuru = BlockGuru()
self.registeredExtensions = []
self.stripTopLevelTags = 1
self.docType = ""
self.textPreprocessors = [HTML_BLOCK_PREPROCESSOR]
self.preprocessors = [HEADER_PREPROCESSOR,
LINE_PREPROCESSOR,
# A footnote preprocessor will
# get inserted here
REFERENCE_PREPROCESSOR]
self.postprocessors = [] # a footnote postprocessor will get
# inserted later
self.textPostprocessors = [# a footnote postprocessor will get
# inserted here
RAWHTMLTEXTPOSTPROCESSOR]
self.prePatterns = []
self.inlinePatterns = [DOUBLE_BACKTICK_PATTERN,
BACKTICK_PATTERN,
ESCAPE_PATTERN,
REFERENCE_PATTERN,
LINK_ANGLED_PATTERN,
LINK_PATTERN,
IMAGE_LINK_PATTERN,
IMAGE_REFERENCE_PATTERN,
AUTOLINK_PATTERN,
AUTOMAIL_PATTERN,
LINE_BREAK_PATTERN_2,
LINE_BREAK_PATTERN,
HTML_PATTERN,
ENTITY_PATTERN,
NOT_STRONG_PATTERN,
STRONG_EM_PATTERN,
STRONG_EM_PATTERN_2,
STRONG_PATTERN,
STRONG_PATTERN_2,
EMPHASIS_PATTERN,
EMPHASIS_PATTERN_2
# The order of the handlers matters!!!
]
self.registerExtensions(extensions = extensions,
configs = extension_configs)
self.reset()
def registerExtensions(self, extensions, configs):
if not configs:
configs = {}
for ext in extensions:
extension_module_name = "mdx_" + ext
try:
module = __import__(extension_module_name)
except:
message(CRITICAL,
"couldn't load extension %s (looking for %s module)"
% (ext, extension_module_name) )
else:
if configs.has_key(ext):
configs_for_ext = configs[ext]
else:
configs_for_ext = []
extension = module.makeExtension(configs_for_ext)
extension.extendMarkdown(self, globals())
def registerExtension(self, extension):
""" This gets called by the extension """
self.registeredExtensions.append(extension)
def reset(self):
"""Resets all state variables so that we can start
with a new text."""
self.references={}
self.htmlStash = HtmlStash()
HTML_BLOCK_PREPROCESSOR.stash = self.htmlStash
LINE_PREPROCESSOR.stash = self.htmlStash
REFERENCE_PREPROCESSOR.references = self.references
HTML_PATTERN.stash = self.htmlStash
ENTITY_PATTERN.stash = self.htmlStash
REFERENCE_PATTERN.references = self.references
IMAGE_REFERENCE_PATTERN.references = self.references
RAWHTMLTEXTPOSTPROCESSOR.stash = self.htmlStash
RAWHTMLTEXTPOSTPROCESSOR.safeMode = self.safeMode
for extension in self.registeredExtensions:
extension.reset()
def _transform(self):
"""Transforms the Markdown text into a XHTML body document
@returns: A NanoDom Document """
# Setup the document
self.doc = Document()
self.top_element = self.doc.createElement("span")
self.top_element.appendChild(self.doc.createTextNode('\n'))
self.top_element.setAttribute('class', 'markdown')
self.doc.appendChild(self.top_element)
# Fixup the source text
text = self.source
text = text.replace("\r\n", "\n").replace("\r", "\n")
text += "\n\n"
text = text.expandtabs(TAB_LENGTH)
# Split into lines and run the preprocessors that will work with
# self.lines
self.lines = text.split("\n")
# Run the pre-processors on the lines
for prep in self.preprocessors :
self.lines = prep.run(self.lines)
# Create a NanoDom tree from the lines and attach it to Document
buffer = []
for line in self.lines:
if line.startswith("#"):
self._processSection(self.top_element, buffer)
buffer = [line]
else:
buffer.append(line)
self._processSection(self.top_element, buffer)
#self._processSection(self.top_element, self.lines)
# Not sure why I put this in but let's leave it for now.
self.top_element.appendChild(self.doc.createTextNode('\n'))
# Run the post-processors
for postprocessor in self.postprocessors:
postprocessor.run(self.doc)
return self.doc
def _processSection(self, parent_elem, lines,
inList = 0, looseList = 0):
"""Process a section of a source document, looking for high
level structural elements like lists, block quotes, code
segments, html blocks, etc. Some those then get stripped
of their high level markup (e.g. get unindented) and the
lower-level markup is processed recursively.
@param parent_elem: A NanoDom element to which the content
will be added
@param lines: a list of lines
@param inList: a level
@returns: None"""
# Loop through lines until none left.
while lines:
# Check if this section starts with a list, a blockquote or
# a code block
processFn = { 'ul': self._processUList,
'ol': self._processOList,
'quoted': self._processQuote,
'tabbed': self._processCodeBlock}
for regexp in ['ul', 'ol', 'quoted', 'tabbed']:
m = RE.regExp[regexp].match(lines[0])
if m:
processFn[regexp](parent_elem, lines, inList)
return
# We are NOT looking at one of the high-level structures like
# lists or blockquotes. So, it's just a regular paragraph
# (though perhaps nested inside a list or something else). If
# we are NOT inside a list, we just need to look for a blank
# line to find the end of the block. If we ARE inside a
# list, however, we need to consider that a sublist does not
# need to be separated by a blank line. Rather, the following
# markup is legal:
#
# * The top level list item
#
# Another paragraph of the list. This is where we are now.
# * Underneath we might have a sublist.
#
if inList:
start, lines = self._linesUntil(lines, (lambda line:
RE.regExp['ul'].match(line)
or RE.regExp['ol'].match(line)
or not line.strip()))
self._processSection(parent_elem, start,
inList - 1, looseList = looseList)
inList = inList-1
else: # Ok, so it's just a simple block
paragraph, lines = self._linesUntil(lines, lambda line:
not line.strip())
if len(paragraph) and paragraph[0].startswith('#'):
self._processHeader(parent_elem, paragraph)
elif paragraph:
self._processParagraph(parent_elem, paragraph,
inList, looseList)
if lines and not lines[0].strip():
lines = lines[1:] # skip the first (blank) line
def _processHeader(self, parent_elem, paragraph):
m = RE.regExp['header'].match(paragraph[0])
if m:
level = len(m.group(1))
h = self.doc.createElement("h%d" % level)
parent_elem.appendChild(h)
for item in self._handleInline(m.group(2).strip()):
h.appendChild(item)
else:
message(CRITICAL, "We've got a problem header!")
def _processParagraph(self, parent_elem, paragraph, inList, looseList):
list = self._handleInline("\n".join(paragraph))
if ( parent_elem.nodeName == 'li'
and not (looseList or parent_elem.childNodes)):
# If this is the first paragraph inside "li", don't
# put <p> around it - append the paragraph bits directly
# onto parent_elem
el = parent_elem
else:
# Otherwise make a "p" element
el = self.doc.createElement("p")
parent_elem.appendChild(el)
for item in list:
el.appendChild(item)
def _processUList(self, parent_elem, lines, inList):
self._processList(parent_elem, lines, inList,
listexpr='ul', tag = 'ul')
def _processOList(self, parent_elem, lines, inList):
self._processList(parent_elem, lines, inList,
listexpr='ol', tag = 'ol')
def _processList(self, parent_elem, lines, inList, listexpr, tag):
"""Given a list of document lines starting with a list item,
finds the end of the list, breaks it up, and recursively
processes each list item and the remainder of the text file.
@param parent_elem: A dom element to which the content will be added
@param lines: a list of lines
@param inList: a level
@returns: None"""
ul = self.doc.createElement(tag) # ul might actually be '<ol>'
parent_elem.appendChild(ul)
looseList = 0
# Make a list of list items
items = []
item = -1
i = 0 # a counter to keep track of where we are
for line in lines:
loose = 0
if not line.strip():
# If we see a blank line, this _might_ be the end of the list
i += 1
loose = 1
# Find the next non-blank line
for j in range(i, len(lines)):
if lines[j].strip():
next = lines[j]
break
else:
# There is no more text => end of the list
break
# Check if the next non-blank line is still a part of the list
if ( RE.regExp['ul'].match(next) or
RE.regExp['ol'].match(next) or
RE.regExp['tabbed'].match(next) ):
# get rid of any white space in the line
items[item].append(line.strip())
looseList = loose or looseList
continue
else:
break # found end of the list
# Now we need to detect list items (at the current level)
# while also detabing child elements if necessary
for expr in ['ul', 'ol', 'tabbed']:
m = RE.regExp[expr].match(line)
if m:
if expr in ['ul', 'ol']: # We are looking at a new item
#if m.group(1) :
# Removed the check to allow for a blank line
# at the beginning of the list item
items.append([m.group(1)])
item += 1
elif expr == 'tabbed': # This line needs to be detabbed
items[item].append(m.group(4)) #after the 'tab'
i += 1
break
else:
items[item].append(line) # Just regular continuation
i += 1 # added on 2006.02.25
else:
i += 1
# Add the dom elements
for item in items:
li = self.doc.createElement("li")
ul.appendChild(li)
self._processSection(li, item, inList + 1, looseList = looseList)
# Process the remaining part of the section
self._processSection(parent_elem, lines[i:], inList)
def _linesUntil(self, lines, condition):
""" A utility function to break a list of lines upon the
first line that satisfied a condition. The condition
argument should be a predicate function.
"""
i = -1
for line in lines:
i += 1
if condition(line): break
else:
i += 1
return lines[:i], lines[i:]
def _processQuote(self, parent_elem, lines, inList):
"""Given a list of document lines starting with a quote finds
the end of the quote, unindents it and recursively
processes the body of the quote and the remainder of the
text file.
@param parent_elem: DOM element to which the content will be added
@param lines: a list of lines
@param inList: a level
@returns: None """
dequoted = []
i = 0
blank_line = False # allow one blank line between paragraphs
for line in lines:
m = RE.regExp['quoted'].match(line)
if m:
dequoted.append(m.group(1))
i += 1
blank_line = False
elif not blank_line and line.strip() != '':
dequoted.append(line)
i += 1
elif not blank_line and line.strip() == '':
dequoted.append(line)
i += 1
blank_line = True
else:
break
blockquote = self.doc.createElement('blockquote')
parent_elem.appendChild(blockquote)
self._processSection(blockquote, dequoted, inList)
self._processSection(parent_elem, lines[i:], inList)
def _processCodeBlock(self, parent_elem, lines, inList):
"""Given a list of document lines starting with a code block
finds the end of the block, puts it into the dom verbatim
wrapped in ("<pre><code>") and recursively processes the
the remainder of the text file.
@param parent_elem: DOM element to which the content will be added
@param lines: a list of lines
@param inList: a level
@returns: None"""
detabbed, theRest = self.blockGuru.detectTabbed(lines)
pre = self.doc.createElement('pre')
code = self.doc.createElement('code')
parent_elem.appendChild(pre)
pre.appendChild(code)
text = "\n".join(detabbed).rstrip()+"\n"
#text = text.replace("&", "&")
code.appendChild(self.doc.createTextNode(text))
self._processSection(parent_elem, theRest, inList)
def _handleInline (self, line, patternIndex=0):
"""Transform a Markdown line with inline elements to an XHTML
fragment.
This function uses auxiliary objects called inline patterns.
See notes on inline patterns above.
@param line: A line of Markdown text
@param patternIndex: The index of the inlinePattern to start with
@return: A list of NanoDom nodes """
parts = [line]
while patternIndex < len(self.inlinePatterns):
i = 0
while i < len(parts):
x = parts[i]
if isinstance(x, (str, unicode)):
result = self._applyPattern(x, \
self.inlinePatterns[patternIndex], \
patternIndex)
if result:
i -= 1
parts.remove(x)
for y in result:
parts.insert(i+1,y)
i += 1
patternIndex += 1
for i in range(len(parts)):
x = parts[i]
if isinstance(x, (str, unicode)):
parts[i] = self.doc.createTextNode(x)
return parts
def _applyPattern(self, line, pattern, patternIndex):
""" Given a pattern name, this function checks if the line
fits the pattern, creates the necessary elements, and returns
back a list consisting of NanoDom elements and/or strings.
@param line: the text to be processed
@param pattern: the pattern to be checked
@returns: the appropriate newly created NanoDom element if the
pattern matches, None otherwise.
"""
# match the line to pattern's pre-compiled reg exp.
# if no match, move on.
m = pattern.getCompiledRegExp().match(line)
if not m:
return None
# if we got a match let the pattern make us a NanoDom node
# if it doesn't, move on
node = pattern.handleMatch(m, self.doc)
# check if any of this nodes have children that need processing
if isinstance(node, Element):
if not node.nodeName in ["code", "pre"]:
for child in node.childNodes:
if isinstance(child, TextNode):
result = self._handleInline(child.value, patternIndex+1)
if result:
if result == [child]:
continue
result.reverse()
#to make insertion easier
position = node.childNodes.index(child)
node.removeChild(child)
for item in result:
if isinstance(item, (str, unicode)):
if len(item) > 0:
node.insertChild(position,
self.doc.createTextNode(item))
else:
node.insertChild(position, item)
if node:
# Those are in the reverse order!
return ( m.groups()[-1], # the string to the left
node, # the new node
m.group(1)) # the string to the right of the match
else:
return None
def convert (self, source = None):
"""Return the document in XHTML format.
@returns: A serialized XHTML body."""
if source is not None: #Allow blank string
self.source = source
if not self.source:
return u""
try:
self.source = unicode(self.source)
except UnicodeDecodeError:
message(CRITICAL, 'UnicodeDecodeError: Markdown only accepts unicode or ascii input.')
return u""
for pp in self.textPreprocessors:
self.source = pp.run(self.source)
doc = self._transform()
xml = doc.toxml()
# Return everything but the top level tag
if self.stripTopLevelTags:
xml = xml.strip()[23:-7] + "\n"
for pp in self.textPostprocessors:
xml = pp.run(xml)
return (self.docType + xml).strip()
def __str__(self):
''' Report info about instance. Markdown always returns unicode. '''
if self.source is None:
status = 'in which no source text has been assinged.'
else:
status = 'which contains %d chars and %d line(s) of source.'%\
(len(self.source), self.source.count('\n')+1)
return 'An instance of "%s" %s'% (self.__class__, status)
__unicode__ = convert # markdown should always return a unicode string
# ====================================================================
def markdownFromFile(input = None,
output = None,
extensions = [],
encoding = None,
message_threshold = CRITICAL,
safe = False):
global console_hndlr
console_hndlr.setLevel(message_threshold)
message(DEBUG, "input file: %s" % input)
if not encoding:
encoding = "utf-8"
input_file = codecs.open(input, mode="r", encoding=encoding)
text = input_file.read()
input_file.close()
text = removeBOM(text, encoding)
new_text = markdown(text, extensions, safe_mode = safe)
if output:
output_file = codecs.open(output, "w", encoding=encoding)
output_file.write(new_text)
output_file.close()
else:
sys.stdout.write(new_text.encode(encoding))
def markdown(text,
extensions = [],
safe_mode = False):
message(DEBUG, "in markdown.markdown(), received text:\n%s" % text)
extension_names = []
extension_configs = {}
for ext in extensions:
pos = ext.find("(")
if pos == -1:
extension_names.append(ext)
else:
name = ext[:pos]
extension_names.append(name)
pairs = [x.split("=") for x in ext[pos+1:-1].split(",")]
configs = [(x.strip(), y.strip()) for (x, y) in pairs]
extension_configs[name] = configs
md = Markdown(extensions=extension_names,
extension_configs=extension_configs,
safe_mode = safe_mode)
return md.convert(text)
class Extension:
def __init__(self, configs = {}):
self.config = configs
def getConfig(self, key):
if self.config.has_key(key):
return self.config[key][0]
else:
return ""
def getConfigInfo(self):
return [(key, self.config[key][1]) for key in self.config.keys()]
def setConfig(self, key, value):
self.config[key][0] = value
OPTPARSE_WARNING = """
Python 2.3 or higher required for advanced command line options.
For lower versions of Python use:
%s INPUT_FILE > OUTPUT_FILE
""" % EXECUTABLE_NAME_FOR_USAGE
def parse_options():
try:
optparse = __import__("optparse")
except:
if len(sys.argv) == 2:
return {'input': sys.argv[1],
'output': None,
'message_threshold': CRITICAL,
'safe': False,
'extensions': [],
'encoding': None }
else:
print OPTPARSE_WARNING
return None
parser = optparse.OptionParser(usage="%prog INPUTFILE [options]")
parser.add_option("-f", "--file", dest="filename",
help="write output to OUTPUT_FILE",
metavar="OUTPUT_FILE")
parser.add_option("-e", "--encoding", dest="encoding",
help="encoding for input and output files",)
parser.add_option("-q", "--quiet", default = CRITICAL,
action="store_const", const=60, dest="verbose",
help="suppress all messages")
parser.add_option("-v", "--verbose",
action="store_const", const=INFO, dest="verbose",
help="print info messages")
parser.add_option("-s", "--safe", dest="safe", default=False,
metavar="SAFE_MODE",
help="same mode ('replace', 'remove' or 'escape' user's HTML tag)")
parser.add_option("--noisy",
action="store_const", const=DEBUG, dest="verbose",
help="print debug messages")
parser.add_option("-x", "--extension", action="append", dest="extensions",
help = "load extension EXTENSION", metavar="EXTENSION")
(options, args) = parser.parse_args()
if not len(args) == 1:
parser.print_help()
return None
else:
input_file = args[0]
if not options.extensions:
options.extensions = []
return {'input': input_file,
'output': options.filename,
'message_threshold': options.verbose,
'safe': options.safe,
'extensions': options.extensions,
'encoding': options.encoding }
if __name__ == '__main__':
""" Run Markdown from the command line. """
options = parse_options()
#if os.access(inFile, os.R_OK):
if not options:
sys.exit(0)
markdownFromFile(**options)
|