/usr/share/pyshared/gluon/contrib/markdown/markdown2.py is in python-gluon 1.99.7-1.
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 | #!/usr/bin/env python
# Copyright (c) 2007-2008 ActiveState Corp.
# License: MIT (http://www.opensource.org/licenses/mit-license.php)
r"""A fast and complete Python implementation of Markdown.
[from http://daringfireball.net/projects/markdown/]
> Markdown is a text-to-HTML filter; it translates an easy-to-read /
> easy-to-write structured text format into HTML. Markdown's text
> format is most similar to that of plain text email, and supports
> features such as headers, *emphasis*, code blocks, blockquotes, and
> links.
>
> Markdown's syntax is designed not as a generic markup language, but
> specifically to serve as a front-end to (X)HTML. You can use span-level
> HTML tags anywhere in a Markdown document, and you can use block level
> HTML tags (like <div> and <table> as well).
Module usage:
>>> import markdown2
>>> markdown2.markdown("*boo!*") # or use `html = markdown_path(PATH)`
u'<p><em>boo!</em></p>\n'
>>> markdowner = Markdown()
>>> markdowner.convert("*boo!*")
u'<p><em>boo!</em></p>\n'
>>> markdowner.convert("**boom!**")
u'<p><strong>boom!</strong></p>\n'
This implementation of Markdown implements the full "core" syntax plus a
number of extras (e.g., code syntax coloring, footnotes) as described on
<http://code.google.com/p/python-markdown2/wiki/Extras>.
"""
cmdln_desc = """A fast and complete Python implementation of Markdown, a
text-to-HTML conversion tool for web writers.
"""
# Dev Notes:
# - There is already a Python markdown processor
# (http://www.freewisdom.org/projects/python-markdown/).
# - Python's regex syntax doesn't have '\z', so I'm using '\Z'. I'm
# not yet sure if there implications with this. Compare 'pydoc sre'
# and 'perldoc perlre'.
__version_info__ = (1, 0, 1, 16) # first three nums match Markdown.pl
__version__ = '1.0.1.16'
__author__ = "Trent Mick"
import os
import sys
from pprint import pprint
import re
import logging
try:
from hashlib import md5
except ImportError:
from md5 import md5
import optparse
from random import random, randint
import codecs
from urllib import quote
#---- Python version compat
if sys.version_info[:2] < (2,4):
from sets import Set as set
def reversed(sequence):
for i in sequence[::-1]:
yield i
def _unicode_decode(s, encoding, errors='xmlcharrefreplace'):
return unicode(s, encoding, errors)
else:
def _unicode_decode(s, encoding, errors='strict'):
return s.decode(encoding, errors)
#---- globals
DEBUG = False
log = logging.getLogger("markdown")
DEFAULT_TAB_WIDTH = 4
try:
import uuid
except ImportError:
SECRET_SALT = str(randint(0, 1000000))
else:
SECRET_SALT = str(uuid.uuid4())
def _hash_ascii(s):
#return md5(s).hexdigest() # Markdown.pl effectively does this.
return 'md5-' + md5(SECRET_SALT + s).hexdigest()
def _hash_text(s):
return 'md5-' + md5(SECRET_SALT + s.encode("utf-8")).hexdigest()
# Table of hash values for escaped characters:
g_escape_table = dict([(ch, _hash_ascii(ch))
for ch in '\\`*_{}[]()>#+-.!'])
#---- exceptions
class MarkdownError(Exception):
pass
#---- public api
def markdown_path(path, encoding="utf-8",
html4tags=False, tab_width=DEFAULT_TAB_WIDTH,
safe_mode=None, extras=None, link_patterns=None,
use_file_vars=False):
fp = codecs.open(path, 'r', encoding)
try:
text = fp.read()
finally:
fp.close()
return Markdown(html4tags=html4tags, tab_width=tab_width,
safe_mode=safe_mode, extras=extras,
link_patterns=link_patterns,
use_file_vars=use_file_vars).convert(text)
def markdown(text, html4tags=False, tab_width=DEFAULT_TAB_WIDTH,
safe_mode=None, extras=None, link_patterns=None,
use_file_vars=False):
return Markdown(html4tags=html4tags, tab_width=tab_width,
safe_mode=safe_mode, extras=extras,
link_patterns=link_patterns,
use_file_vars=use_file_vars).convert(text)
class Markdown(object):
# The dict of "extras" to enable in processing -- a mapping of
# extra name to argument for the extra. Most extras do not have an
# argument, in which case the value is None.
#
# This can be set via (a) subclassing and (b) the constructor
# "extras" argument.
extras = None
urls = None
titles = None
html_blocks = None
html_spans = None
html_removed_text = "[HTML_REMOVED]" # for compat with markdown.py
# Used to track when we're inside an ordered or unordered list
# (see _ProcessListItems() for details):
list_level = 0
_ws_only_line_re = re.compile(r"^[ \t]+$", re.M)
def __init__(self, html4tags=False, tab_width=4, safe_mode=None,
extras=None, link_patterns=None, use_file_vars=False):
if html4tags:
self.empty_element_suffix = ">"
else:
self.empty_element_suffix = " />"
self.tab_width = tab_width
# For compatibility with earlier markdown2.py and with
# markdown.py's safe_mode being a boolean,
# safe_mode == True -> "replace"
if safe_mode is True:
self.safe_mode = "replace"
else:
self.safe_mode = safe_mode
if self.extras is None:
self.extras = {}
elif not isinstance(self.extras, dict):
self.extras = dict([(e, None) for e in self.extras])
if extras:
if not isinstance(extras, dict):
extras = dict([(e, None) for e in extras])
self.extras.update(extras)
assert isinstance(self.extras, dict)
self._instance_extras = self.extras.copy()
self.link_patterns = link_patterns
self.use_file_vars = use_file_vars
self._outdent_re = re.compile(r'^(\t|[ ]{1,%d})' % tab_width, re.M)
def reset(self):
self.urls = {}
self.titles = {}
self.html_blocks = {}
self.html_spans = {}
self.list_level = 0
self.extras = self._instance_extras.copy()
if "footnotes" in self.extras:
self.footnotes = {}
self.footnote_ids = []
def convert(self, text):
"""Convert the given text."""
# Main function. The order in which other subs are called here is
# essential. Link and image substitutions need to happen before
# _EscapeSpecialChars(), so that any *'s or _'s in the <a>
# and <img> tags get encoded.
# Clear the global hashes. If we don't clear these, you get conflicts
# from other articles when generating a page which contains more than
# one article (e.g. an index page that shows the N most recent
# articles):
self.reset()
if not isinstance(text, unicode):
#TODO: perhaps shouldn't presume UTF-8 for string input?
text = unicode(text, 'utf-8')
if self.use_file_vars:
# Look for emacs-style file variable hints.
emacs_vars = self._get_emacs_vars(text)
if "markdown-extras" in emacs_vars:
splitter = re.compile("[ ,]+")
for e in splitter.split(emacs_vars["markdown-extras"]):
if '=' in e:
ename, earg = e.split('=', 1)
try:
earg = int(earg)
except ValueError:
pass
else:
ename, earg = e, None
self.extras[ename] = earg
# Standardize line endings:
text = re.sub("\r\n|\r", "\n", text)
# Make sure $text ends with a couple of newlines:
text += "\n\n"
# Convert all tabs to spaces.
text = self._detab(text)
# Strip any lines consisting only of spaces and tabs.
# This makes subsequent regexen easier to write, because we can
# match consecutive blank lines with /\n+/ instead of something
# contorted like /[ \t]*\n+/ .
text = self._ws_only_line_re.sub("", text)
if self.safe_mode:
text = self._hash_html_spans(text)
# Turn block-level HTML blocks into hash entries
text = self._hash_html_blocks(text, raw=True)
# Strip link definitions, store in hashes.
if "footnotes" in self.extras:
# Must do footnotes first because an unlucky footnote defn
# looks like a link defn:
# [^4]: this "looks like a link defn"
text = self._strip_footnote_definitions(text)
text = self._strip_link_definitions(text)
text = self._run_block_gamut(text)
if "footnotes" in self.extras:
text = self._add_footnotes(text)
text = self._unescape_special_chars(text)
if self.safe_mode:
text = self._unhash_html_spans(text)
text += "\n"
return text
_emacs_oneliner_vars_pat = re.compile(r"-\*-\s*([^\r\n]*?)\s*-\*-", re.UNICODE)
# This regular expression is intended to match blocks like this:
# PREFIX Local Variables: SUFFIX
# PREFIX mode: Tcl SUFFIX
# PREFIX End: SUFFIX
# Some notes:
# - "[ \t]" is used instead of "\s" to specifically exclude newlines
# - "(\r\n|\n|\r)" is used instead of "$" because the sre engine does
# not like anything other than Unix-style line terminators.
_emacs_local_vars_pat = re.compile(r"""^
(?P<prefix>(?:[^\r\n|\n|\r])*?)
[\ \t]*Local\ Variables:[\ \t]*
(?P<suffix>.*?)(?:\r\n|\n|\r)
(?P<content>.*?\1End:)
""", re.IGNORECASE | re.MULTILINE | re.DOTALL | re.VERBOSE)
def _get_emacs_vars(self, text):
"""Return a dictionary of emacs-style local variables.
Parsing is done loosely according to this spec (and according to
some in-practice deviations from this):
http://www.gnu.org/software/emacs/manual/html_node/emacs/Specifying-File-Variables.html#Specifying-File-Variables
"""
emacs_vars = {}
SIZE = pow(2, 13) # 8kB
# Search near the start for a '-*-'-style one-liner of variables.
head = text[:SIZE]
if "-*-" in head:
match = self._emacs_oneliner_vars_pat.search(head)
if match:
emacs_vars_str = match.group(1)
assert '\n' not in emacs_vars_str
emacs_var_strs = [s.strip() for s in emacs_vars_str.split(';')
if s.strip()]
if len(emacs_var_strs) == 1 and ':' not in emacs_var_strs[0]:
# While not in the spec, this form is allowed by emacs:
# -*- Tcl -*-
# where the implied "variable" is "mode". This form
# is only allowed if there are no other variables.
emacs_vars["mode"] = emacs_var_strs[0].strip()
else:
for emacs_var_str in emacs_var_strs:
try:
variable, value = emacs_var_str.strip().split(':', 1)
except ValueError:
log.debug("emacs variables error: malformed -*- "
"line: %r", emacs_var_str)
continue
# Lowercase the variable name because Emacs allows "Mode"
# or "mode" or "MoDe", etc.
emacs_vars[variable.lower()] = value.strip()
tail = text[-SIZE:]
if "Local Variables" in tail:
match = self._emacs_local_vars_pat.search(tail)
if match:
prefix = match.group("prefix")
suffix = match.group("suffix")
lines = match.group("content").splitlines(0)
#print "prefix=%r, suffix=%r, content=%r, lines: %s"\
# % (prefix, suffix, match.group("content"), lines)
# Validate the Local Variables block: proper prefix and suffix
# usage.
for i, line in enumerate(lines):
if not line.startswith(prefix):
log.debug("emacs variables error: line '%s' "
"does not use proper prefix '%s'"
% (line, prefix))
return {}
# Don't validate suffix on last line. Emacs doesn't care,
# neither should we.
if i != len(lines)-1 and not line.endswith(suffix):
log.debug("emacs variables error: line '%s' "
"does not use proper suffix '%s'"
% (line, suffix))
return {}
# Parse out one emacs var per line.
continued_for = None
for line in lines[:-1]: # no var on the last line ("PREFIX End:")
if prefix: line = line[len(prefix):] # strip prefix
if suffix: line = line[:-len(suffix)] # strip suffix
line = line.strip()
if continued_for:
variable = continued_for
if line.endswith('\\'):
line = line[:-1].rstrip()
else:
continued_for = None
emacs_vars[variable] += ' ' + line
else:
try:
variable, value = line.split(':', 1)
except ValueError:
log.debug("local variables error: missing colon "
"in local variables entry: '%s'" % line)
continue
# Do NOT lowercase the variable name, because Emacs only
# allows "mode" (and not "Mode", "MoDe", etc.) in this block.
value = value.strip()
if value.endswith('\\'):
value = value[:-1].rstrip()
continued_for = variable
else:
continued_for = None
emacs_vars[variable] = value
# Unquote values.
for var, val in emacs_vars.items():
if len(val) > 1 and (val.startswith('"') and val.endswith('"')
or val.startswith('"') and val.endswith('"')):
emacs_vars[var] = val[1:-1]
return emacs_vars
# Cribbed from a post by Bart Lateur:
# <http://www.nntp.perl.org/group/perl.macperl.anyperl/154>
_detab_re = re.compile(r'(.*?)\t', re.M)
def _detab_sub(self, match):
g1 = match.group(1)
return g1 + (' ' * (self.tab_width - len(g1) % self.tab_width))
def _detab(self, text):
r"""Remove (leading?) tabs from a file.
>>> m = Markdown()
>>> m._detab("\tfoo")
' foo'
>>> m._detab(" \tfoo")
' foo'
>>> m._detab("\t foo")
' foo'
>>> m._detab(" foo")
' foo'
>>> m._detab(" foo\n\tbar\tblam")
' foo\n bar blam'
"""
if '\t' not in text:
return text
return self._detab_re.subn(self._detab_sub, text)[0]
_block_tags_a = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math|ins|del'
_strict_tag_block_re = re.compile(r"""
( # save in \1
^ # start of line (with re.M)
<(%s) # start tag = \2
\b # word break
(.*\n)*? # any number of lines, minimally matching
</\2> # the matching end tag
[ \t]* # trailing spaces/tabs
(?=\n+|\Z) # followed by a newline or end of document
)
""" % _block_tags_a,
re.X | re.M)
_block_tags_b = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math'
_liberal_tag_block_re = re.compile(r"""
( # save in \1
^ # start of line (with re.M)
<(%s) # start tag = \2
\b # word break
(.*\n)*? # any number of lines, minimally matching
.*</\2> # the matching end tag
[ \t]* # trailing spaces/tabs
(?=\n+|\Z) # followed by a newline or end of document
)
""" % _block_tags_b,
re.X | re.M)
def _hash_html_block_sub(self, match, raw=False):
html = match.group(1)
if raw and self.safe_mode:
html = self._sanitize_html(html)
key = _hash_text(html)
self.html_blocks[key] = html
return "\n\n" + key + "\n\n"
def _hash_html_blocks(self, text, raw=False):
"""Hashify HTML blocks
We only want to do this for block-level HTML tags, such as headers,
lists, and tables. That's because we still want to wrap <p>s around
"paragraphs" that are wrapped in non-block-level tags, such as anchors,
phrase emphasis, and spans. The list of tags we're looking for is
hard-coded.
@param raw {boolean} indicates if these are raw HTML blocks in
the original source. It makes a difference in "safe" mode.
"""
if '<' not in text:
return text
# Pass `raw` value into our calls to self._hash_html_block_sub.
hash_html_block_sub = _curry(self._hash_html_block_sub, raw=raw)
# First, look for nested blocks, e.g.:
# <div>
# <div>
# tags for inner block must be indented.
# </div>
# </div>
#
# The outermost tags must start at the left margin for this to match, and
# the inner nested divs must be indented.
# We need to do this before the next, more liberal match, because the next
# match will start at the first `<div>` and stop at the first `</div>`.
text = self._strict_tag_block_re.sub(hash_html_block_sub, text)
# Now match more liberally, simply from `\n<tag>` to `</tag>\n`
text = self._liberal_tag_block_re.sub(hash_html_block_sub, text)
# Special case just for <hr />. It was easier to make a special
# case than to make the other regex more complicated.
if "<hr" in text:
_hr_tag_re = _hr_tag_re_from_tab_width(self.tab_width)
text = _hr_tag_re.sub(hash_html_block_sub, text)
# Special case for standalone HTML comments:
if "<!--" in text:
start = 0
while True:
# Delimiters for next comment block.
try:
start_idx = text.index("<!--", start)
except ValueError, ex:
break
try:
end_idx = text.index("-->", start_idx) + 3
except ValueError, ex:
break
# Start position for next comment block search.
start = end_idx
# Validate whitespace before comment.
if start_idx:
# - Up to `tab_width - 1` spaces before start_idx.
for i in range(self.tab_width - 1):
if text[start_idx - 1] != ' ':
break
start_idx -= 1
if start_idx == 0:
break
# - Must be preceded by 2 newlines or hit the start of
# the document.
if start_idx == 0:
pass
elif start_idx == 1 and text[0] == '\n':
start_idx = 0 # to match minute detail of Markdown.pl regex
elif text[start_idx-2:start_idx] == '\n\n':
pass
else:
break
# Validate whitespace after comment.
# - Any number of spaces and tabs.
while end_idx < len(text):
if text[end_idx] not in ' \t':
break
end_idx += 1
# - Must be following by 2 newlines or hit end of text.
if text[end_idx:end_idx+2] not in ('', '\n', '\n\n'):
continue
# Escape and hash (must match `_hash_html_block_sub`).
html = text[start_idx:end_idx]
if raw and self.safe_mode:
html = self._sanitize_html(html)
key = _hash_text(html)
self.html_blocks[key] = html
text = text[:start_idx] + "\n\n" + key + "\n\n" + text[end_idx:]
if "xml" in self.extras:
# Treat XML processing instructions and namespaced one-liner
# tags as if they were block HTML tags. E.g., if standalone
# (i.e. are their own paragraph), the following do not get
# wrapped in a <p> tag:
# <?foo bar?>
#
# <xi:include xmlns:xi="http://www.w3.org/2001/XInclude" href="chapter_1.md"/>
_xml_oneliner_re = _xml_oneliner_re_from_tab_width(self.tab_width)
text = _xml_oneliner_re.sub(hash_html_block_sub, text)
return text
def _strip_link_definitions(self, text):
# Strips link definitions from text, stores the URLs and titles in
# hash references.
less_than_tab = self.tab_width - 1
# Link defs are in the form:
# [id]: url "optional title"
_link_def_re = re.compile(r"""
^[ ]{0,%d}\[(.+)\]: # id = \1
[ \t]*
\n? # maybe *one* newline
[ \t]*
<?(.+?)>? # url = \2
[ \t]*
(?:
\n? # maybe one newline
[ \t]*
(?<=\s) # lookbehind for whitespace
['"(]
([^\n]*) # title = \3
['")]
[ \t]*
)? # title is optional
(?:\n+|\Z)
""" % less_than_tab, re.X | re.M | re.U)
return _link_def_re.sub(self._extract_link_def_sub, text)
def _extract_link_def_sub(self, match):
id, url, title = match.groups()
key = id.lower() # Link IDs are case-insensitive
self.urls[key] = self._encode_amps_and_angles(url)
if title:
self.titles[key] = title.replace('"', '"')
return ""
def _extract_footnote_def_sub(self, match):
id, text = match.groups()
text = _dedent(text, skip_first_line=not text.startswith('\n')).strip()
normed_id = re.sub(r'\W', '-', id)
# Ensure footnote text ends with a couple newlines (for some
# block gamut matches).
self.footnotes[normed_id] = text + "\n\n"
return ""
def _strip_footnote_definitions(self, text):
"""A footnote definition looks like this:
[^note-id]: Text of the note.
May include one or more indented paragraphs.
Where,
- The 'note-id' can be pretty much anything, though typically it
is the number of the footnote.
- The first paragraph may start on the next line, like so:
[^note-id]:
Text of the note.
"""
less_than_tab = self.tab_width - 1
footnote_def_re = re.compile(r'''
^[ ]{0,%d}\[\^(.+)\]: # id = \1
[ \t]*
( # footnote text = \2
# First line need not start with the spaces.
(?:\s*.*\n+)
(?:
(?:[ ]{%d} | \t) # Subsequent lines must be indented.
.*\n+
)*
)
# Lookahead for non-space at line-start, or end of doc.
(?:(?=^[ ]{0,%d}\S)|\Z)
''' % (less_than_tab, self.tab_width, self.tab_width),
re.X | re.M)
return footnote_def_re.sub(self._extract_footnote_def_sub, text)
_hr_res = [
re.compile(r"^[ ]{0,2}([ ]?\*[ ]?){3,}[ \t]*$", re.M),
re.compile(r"^[ ]{0,2}([ ]?\-[ ]?){3,}[ \t]*$", re.M),
re.compile(r"^[ ]{0,2}([ ]?\_[ ]?){3,}[ \t]*$", re.M),
]
def _run_block_gamut(self, text):
# These are all the transformations that form block-level
# tags like paragraphs, headers, and list items.
text = self._do_headers(text)
# Do Horizontal Rules:
hr = "\n<hr"+self.empty_element_suffix+"\n"
for hr_re in self._hr_res:
text = hr_re.sub(hr, text)
text = self._do_lists(text)
if "pyshell" in self.extras:
text = self._prepare_pyshell_blocks(text)
text = self._do_code_blocks(text)
text = self._do_block_quotes(text)
# We already ran _HashHTMLBlocks() before, in Markdown(), but that
# was to escape raw HTML in the original Markdown source. This time,
# we're escaping the markup we've just created, so that we don't wrap
# <p> tags around block-level tags.
text = self._hash_html_blocks(text)
text = self._form_paragraphs(text)
return text
def _pyshell_block_sub(self, match):
lines = match.group(0).splitlines(0)
_dedentlines(lines)
indent = ' ' * self.tab_width
s = ('\n' # separate from possible cuddled paragraph
+ indent + ('\n'+indent).join(lines)
+ '\n\n')
return s
def _prepare_pyshell_blocks(self, text):
"""Ensure that Python interactive shell sessions are put in
code blocks -- even if not properly indented.
"""
if ">>>" not in text:
return text
less_than_tab = self.tab_width - 1
_pyshell_block_re = re.compile(r"""
^([ ]{0,%d})>>>[ ].*\n # first line
^(\1.*\S+.*\n)* # any number of subsequent lines
^\n # ends with a blank line
""" % less_than_tab, re.M | re.X)
return _pyshell_block_re.sub(self._pyshell_block_sub, text)
def _run_span_gamut(self, text):
# These are all the transformations that occur *within* block-level
# tags like paragraphs, headers, and list items.
text = self._do_code_spans(text)
text = self._escape_special_chars(text)
# Process anchor and image tags.
text = self._do_links(text)
# Make links out of things like `<http://example.com/>`
# Must come after _do_links(), because you can use < and >
# delimiters in inline links like [this](<url>).
text = self._do_auto_links(text)
if "link-patterns" in self.extras:
text = self._do_link_patterns(text)
text = self._encode_amps_and_angles(text)
text = self._do_italics_and_bold(text)
# Do hard breaks:
text = re.sub(r" {2,}\n", " <br%s\n" % self.empty_element_suffix, text)
return text
# "Sorta" because auto-links are identified as "tag" tokens.
_sorta_html_tokenize_re = re.compile(r"""
(
# tag
</?
(?:\w+) # tag name
(?:\s+(?:[\w-]+:)?[\w-]+=(?:".*?"|'.*?'))* # attributes
\s*/?>
|
# auto-link (e.g., <http://www.activestate.com/>)
<\w+[^>]*>
|
<!--.*?--> # comment
|
<\?.*?\?> # processing instruction
)
""", re.X)
def _escape_special_chars(self, text):
# Python markdown note: the HTML tokenization here differs from
# that in Markdown.pl, hence the behaviour for subtle cases can
# differ (I believe the tokenizer here does a better job because
# it isn't susceptible to unmatched '<' and '>' in HTML tags).
# Note, however, that '>' is not allowed in an auto-link URL
# here.
escaped = []
is_html_markup = False
for token in self._sorta_html_tokenize_re.split(text):
if is_html_markup:
# Within tags/HTML-comments/auto-links, encode * and _
# so they don't conflict with their use in Markdown for
# italics and strong. We're replacing each such
# character with its corresponding MD5 checksum value;
# this is likely overkill, but it should prevent us from
# colliding with the escape values by accident.
escaped.append(token.replace('*', g_escape_table['*'])
.replace('_', g_escape_table['_']))
else:
escaped.append(self._encode_backslash_escapes(token))
is_html_markup = not is_html_markup
return ''.join(escaped)
def _hash_html_spans(self, text):
# Used for safe_mode.
def _is_auto_link(s):
if ':' in s and self._auto_link_re.match(s):
return True
elif '@' in s and self._auto_email_link_re.match(s):
return True
return False
tokens = []
is_html_markup = False
for token in self._sorta_html_tokenize_re.split(text):
if is_html_markup and not _is_auto_link(token):
sanitized = self._sanitize_html(token)
key = _hash_text(sanitized)
self.html_spans[key] = sanitized
tokens.append(key)
else:
tokens.append(token)
is_html_markup = not is_html_markup
return ''.join(tokens)
def _unhash_html_spans(self, text):
for key, sanitized in self.html_spans.items():
text = text.replace(key, sanitized)
return text
def _sanitize_html(self, s):
if self.safe_mode == "replace":
return self.html_removed_text
elif self.safe_mode == "escape":
replacements = [
('&', '&'),
('<', '<'),
('>', '>'),
]
for before, after in replacements:
s = s.replace(before, after)
return s
else:
raise MarkdownError("invalid value for 'safe_mode': %r (must be "
"'escape' or 'replace')" % self.safe_mode)
_tail_of_inline_link_re = re.compile(r'''
# Match tail of: [text](/url/) or [text](/url/ "title")
\( # literal paren
[ \t]*
(?P<url> # \1
<.*?>
|
.*?
)
[ \t]*
( # \2
(['"]) # quote char = \3
(?P<title>.*?)
\3 # matching quote
)? # title is optional
\)
''', re.X | re.S)
_tail_of_reference_link_re = re.compile(r'''
# Match tail of: [text][id]
[ ]? # one optional space
(?:\n[ ]*)? # one optional newline followed by spaces
\[
(?P<id>.*?)
\]
''', re.X | re.S)
def _do_links(self, text):
"""Turn Markdown link shortcuts into XHTML <a> and <img> tags.
This is a combination of Markdown.pl's _DoAnchors() and
_DoImages(). They are done together because that simplified the
approach. It was necessary to use a different approach than
Markdown.pl because of the lack of atomic matching support in
Python's regex engine used in $g_nested_brackets.
"""
MAX_LINK_TEXT_SENTINEL = 3000 # markdown2 issue 24
# `anchor_allowed_pos` is used to support img links inside
# anchors, but not anchors inside anchors. An anchor's start
# pos must be `>= anchor_allowed_pos`.
anchor_allowed_pos = 0
curr_pos = 0
while True: # Handle the next link.
# The next '[' is the start of:
# - an inline anchor: [text](url "title")
# - a reference anchor: [text][id]
# - an inline img: ![text](url "title")
# - a reference img: ![text][id]
# - a footnote ref: [^id]
# (Only if 'footnotes' extra enabled)
# - a footnote defn: [^id]: ...
# (Only if 'footnotes' extra enabled) These have already
# been stripped in _strip_footnote_definitions() so no
# need to watch for them.
# - a link definition: [id]: url "title"
# These have already been stripped in
# _strip_link_definitions() so no need to watch for them.
# - not markup: [...anything else...
try:
start_idx = text.index('[', curr_pos)
except ValueError:
break
text_length = len(text)
# Find the matching closing ']'.
# Markdown.pl allows *matching* brackets in link text so we
# will here too. Markdown.pl *doesn't* currently allow
# matching brackets in img alt text -- we'll differ in that
# regard.
bracket_depth = 0
for p in range(start_idx+1, min(start_idx+MAX_LINK_TEXT_SENTINEL,
text_length)):
ch = text[p]
if ch == ']':
bracket_depth -= 1
if bracket_depth < 0:
break
elif ch == '[':
bracket_depth += 1
else:
# Closing bracket not found within sentinel length.
# This isn't markup.
curr_pos = start_idx + 1
continue
link_text = text[start_idx+1:p]
# Possibly a footnote ref?
if "footnotes" in self.extras and link_text.startswith("^"):
normed_id = re.sub(r'\W', '-', link_text[1:])
if normed_id in self.footnotes:
self.footnote_ids.append(normed_id)
result = '<sup class="footnote-ref" id="fnref-%s">' \
'<a href="#fn-%s">%s</a></sup>' \
% (normed_id, normed_id, len(self.footnote_ids))
text = text[:start_idx] + result + text[p+1:]
else:
# This id isn't defined, leave the markup alone.
curr_pos = p+1
continue
# Now determine what this is by the remainder.
p += 1
if p == text_length:
return text
# Inline anchor or img?
if text[p] == '(': # attempt at perf improvement
match = self._tail_of_inline_link_re.match(text, p)
if match:
# Handle an inline anchor or img.
is_img = start_idx > 0 and text[start_idx-1] == "!"
if is_img:
start_idx -= 1
url, title = match.group("url"), match.group("title")
if url and url[0] == '<':
url = url[1:-1] # '<url>' -> 'url'
# We've got to encode these to avoid conflicting
# with italics/bold.
url = url.replace('*', g_escape_table['*']) \
.replace('_', g_escape_table['_'])
if title:
title_str = ' title="%s"' \
% title.replace('*', g_escape_table['*']) \
.replace('_', g_escape_table['_']) \
.replace('"', '"')
else:
title_str = ''
if is_img:
result = '<img src="%s" alt="%s"%s%s' \
% (url.replace('"', '"'),
link_text.replace('"', '"'),
title_str, self.empty_element_suffix)
curr_pos = start_idx + len(result)
text = text[:start_idx] + result + text[match.end():]
elif start_idx >= anchor_allowed_pos:
result_head = '<a href="%s"%s>' % (url, title_str)
result = '%s%s</a>' % (result_head, link_text)
# <img> allowed from curr_pos on, <a> from
# anchor_allowed_pos on.
curr_pos = start_idx + len(result_head)
anchor_allowed_pos = start_idx + len(result)
text = text[:start_idx] + result + text[match.end():]
else:
# Anchor not allowed here.
curr_pos = start_idx + 1
continue
# Reference anchor or img?
else:
match = self._tail_of_reference_link_re.match(text, p)
if match:
# Handle a reference-style anchor or img.
is_img = start_idx > 0 and text[start_idx-1] == "!"
if is_img:
start_idx -= 1
link_id = match.group("id").lower()
if not link_id:
link_id = link_text.lower() # for links like [this][]
if link_id in self.urls:
url = self.urls[link_id]
# We've got to encode these to avoid conflicting
# with italics/bold.
url = url.replace('*', g_escape_table['*']) \
.replace('_', g_escape_table['_'])
title = self.titles.get(link_id)
if title:
title = title.replace('*', g_escape_table['*']) \
.replace('_', g_escape_table['_'])
title_str = ' title="%s"' % title
else:
title_str = ''
if is_img:
result = '<img src="%s" alt="%s"%s%s' \
% (url.replace('"', '"'),
link_text.replace('"', '"'),
title_str, self.empty_element_suffix)
curr_pos = start_idx + len(result)
text = text[:start_idx] + result + text[match.end():]
elif start_idx >= anchor_allowed_pos:
result = '<a href="%s"%s>%s</a>' \
% (url, title_str, link_text)
result_head = '<a href="%s"%s>' % (url, title_str)
result = '%s%s</a>' % (result_head, link_text)
# <img> allowed from curr_pos on, <a> from
# anchor_allowed_pos on.
curr_pos = start_idx + len(result_head)
anchor_allowed_pos = start_idx + len(result)
text = text[:start_idx] + result + text[match.end():]
else:
# Anchor not allowed here.
curr_pos = start_idx + 1
else:
# This id isn't defined, leave the markup alone.
curr_pos = match.end()
continue
# Otherwise, it isn't markup.
curr_pos = start_idx + 1
return text
_setext_h_re = re.compile(r'^(.+)[ \t]*\n(=+|-+)[ \t]*\n+', re.M)
def _setext_h_sub(self, match):
n = {"=": 1, "-": 2}[match.group(2)[0]]
demote_headers = self.extras.get("demote-headers")
if demote_headers:
n = min(n + demote_headers, 6)
return "<h%d>%s</h%d>\n\n" \
% (n, self._run_span_gamut(match.group(1)), n)
_atx_h_re = re.compile(r'''
^(\#{1,6}) # \1 = string of #'s
[ \t]*
(.+?) # \2 = Header text
[ \t]*
(?<!\\) # ensure not an escaped trailing '#'
\#* # optional closing #'s (not counted)
\n+
''', re.X | re.M)
def _atx_h_sub(self, match):
n = len(match.group(1))
demote_headers = self.extras.get("demote-headers")
if demote_headers:
n = min(n + demote_headers, 6)
return "<h%d>%s</h%d>\n\n" \
% (n, self._run_span_gamut(match.group(2)), n)
def _do_headers(self, text):
# Setext-style headers:
# Header 1
# ========
#
# Header 2
# --------
text = self._setext_h_re.sub(self._setext_h_sub, text)
# atx-style headers:
# # Header 1
# ## Header 2
# ## Header 2 with closing hashes ##
# ...
# ###### Header 6
text = self._atx_h_re.sub(self._atx_h_sub, text)
return text
_marker_ul_chars = '*+-'
_marker_any = r'(?:[%s]|\d+\.)' % _marker_ul_chars
_marker_ul = '(?:[%s])' % _marker_ul_chars
_marker_ol = r'(?:\d+\.)'
def _list_sub(self, match):
lst = match.group(1)
lst_type = match.group(3) in self._marker_ul_chars and "ul" or "ol"
result = self._process_list_items(lst)
if self.list_level:
return "<%s>\n%s</%s>\n" % (lst_type, result, lst_type)
else:
return "<%s>\n%s</%s>\n\n" % (lst_type, result, lst_type)
def _do_lists(self, text):
# Form HTML ordered (numbered) and unordered (bulleted) lists.
for marker_pat in (self._marker_ul, self._marker_ol):
# Re-usable pattern to match any entire ul or ol list:
less_than_tab = self.tab_width - 1
whole_list = r'''
( # \1 = whole list
( # \2
[ ]{0,%d}
(%s) # \3 = first list item marker
[ \t]+
)
(?:.+?)
( # \4
\Z
|
\n{2,}
(?=\S)
(?! # Negative lookahead for another list item marker
[ \t]*
%s[ \t]+
)
)
)
''' % (less_than_tab, marker_pat, marker_pat)
# We use a different prefix before nested lists than top-level lists.
# See extended comment in _process_list_items().
#
# Note: There's a bit of duplication here. My original implementation
# created a scalar regex pattern as the conditional result of the test on
# $g_list_level, and then only ran the $text =~ s{...}{...}egmx
# substitution once, using the scalar as the pattern. This worked,
# everywhere except when running under MT on my hosting account at Pair
# Networks. There, this caused all rebuilds to be killed by the reaper (or
# perhaps they crashed, but that seems incredibly unlikely given that the
# same script on the same server ran fine *except* under MT. I've spent
# more time trying to figure out why this is happening than I'd like to
# admit. My only guess, backed up by the fact that this workaround works,
# is that Perl optimizes the substition when it can figure out that the
# pattern will never change, and when this optimization isn't on, we run
# afoul of the reaper. Thus, the slightly redundant code to that uses two
# static s/// patterns rather than one conditional pattern.
if self.list_level:
sub_list_re = re.compile("^"+whole_list, re.X | re.M | re.S)
text = sub_list_re.sub(self._list_sub, text)
else:
list_re = re.compile(r"(?:(?<=\n\n)|\A\n?)"+whole_list,
re.X | re.M | re.S)
text = list_re.sub(self._list_sub, text)
return text
_list_item_re = re.compile(r'''
(\n)? # leading line = \1
(^[ \t]*) # leading whitespace = \2
(%s) [ \t]+ # list marker = \3
((?:.+?) # list item text = \4
(\n{1,2})) # eols = \5
(?= \n* (\Z | \2 (%s) [ \t]+))
''' % (_marker_any, _marker_any),
re.M | re.X | re.S)
_last_li_endswith_two_eols = False
def _list_item_sub(self, match):
item = match.group(4)
leading_line = match.group(1)
leading_space = match.group(2)
if leading_line or "\n\n" in item or self._last_li_endswith_two_eols:
item = self._run_block_gamut(self._outdent(item))
else:
# Recursion for sub-lists:
item = self._do_lists(self._outdent(item))
if item.endswith('\n'):
item = item[:-1]
item = self._run_span_gamut(item)
self._last_li_endswith_two_eols = (len(match.group(5)) == 2)
return "<li>%s</li>\n" % item
def _process_list_items(self, list_str):
# Process the contents of a single ordered or unordered list,
# splitting it into individual list items.
# The $g_list_level global keeps track of when we're inside a list.
# Each time we enter a list, we increment it; when we leave a list,
# we decrement. If it's zero, we're not in a list anymore.
#
# We do this because when we're not inside a list, we want to treat
# something like this:
#
# I recommend upgrading to version
# 8. Oops, now this line is treated
# as a sub-list.
#
# As a single paragraph, despite the fact that the second line starts
# with a digit-period-space sequence.
#
# Whereas when we're inside a list (or sub-list), that line will be
# treated as the start of a sub-list. What a kludge, huh? This is
# an aspect of Markdown's syntax that's hard to parse perfectly
# without resorting to mind-reading. Perhaps the solution is to
# change the syntax rules such that sub-lists must start with a
# starting cardinal number; e.g. "1." or "a.".
self.list_level += 1
self._last_li_endswith_two_eols = False
list_str = list_str.rstrip('\n') + '\n'
list_str = self._list_item_re.sub(self._list_item_sub, list_str)
self.list_level -= 1
return list_str
def _get_pygments_lexer(self, lexer_name):
try:
from pygments import lexers, util
except ImportError:
return None
try:
return lexers.get_lexer_by_name(lexer_name)
except util.ClassNotFound:
return None
def _color_with_pygments(self, codeblock, lexer, **formatter_opts):
import pygments
import pygments.formatters
class HtmlCodeFormatter(pygments.formatters.HtmlFormatter):
def _wrap_code(self, inner):
"""A function for use in a Pygments Formatter which
wraps in <code> tags.
"""
yield 0, "<code>"
for tup in inner:
yield tup
yield 0, "</code>"
def wrap(self, source, outfile):
"""Return the source with a code, pre, and div."""
return self._wrap_div(self._wrap_pre(self._wrap_code(source)))
formatter = HtmlCodeFormatter(cssclass="codehilite", **formatter_opts)
return pygments.highlight(codeblock, lexer, formatter)
def _code_block_sub(self, match):
codeblock = match.group(1)
codeblock = self._outdent(codeblock)
codeblock = self._detab(codeblock)
codeblock = codeblock.lstrip('\n') # trim leading newlines
codeblock = codeblock.rstrip() # trim trailing whitespace
if "code-color" in self.extras and codeblock.startswith(":::"):
lexer_name, rest = codeblock.split('\n', 1)
lexer_name = lexer_name[3:].strip()
lexer = self._get_pygments_lexer(lexer_name)
codeblock = rest.lstrip("\n") # Remove lexer declaration line.
if lexer:
formatter_opts = self.extras['code-color'] or {}
colored = self._color_with_pygments(codeblock, lexer,
**formatter_opts)
return "\n\n%s\n\n" % colored
codeblock = self._encode_code(codeblock)
return "\n\n<pre><code>%s\n</code></pre>\n\n" % codeblock
def _do_code_blocks(self, text):
"""Process Markdown `<pre><code>` blocks."""
code_block_re = re.compile(r'''
(?:\n\n|\A)
( # $1 = the code block -- one or more lines, starting with a space/tab
(?:
(?:[ ]{%d} | \t) # Lines must start with a tab or a tab-width of spaces
.*\n+
)+
)
((?=^[ ]{0,%d}\S)|\Z) # Lookahead for non-space at line-start, or end of doc
''' % (self.tab_width, self.tab_width),
re.M | re.X)
return code_block_re.sub(self._code_block_sub, text)
# Rules for a code span:
# - backslash escapes are not interpreted in a code span
# - to include one or or a run of more backticks the delimiters must
# be a longer run of backticks
# - cannot start or end a code span with a backtick; pad with a
# space and that space will be removed in the emitted HTML
# See `test/tm-cases/escapes.text` for a number of edge-case
# examples.
_code_span_re = re.compile(r'''
(?<!\\)
(`+) # \1 = Opening run of `
(?!`) # See Note A test/tm-cases/escapes.text
(.+?) # \2 = The code block
(?<!`)
\1 # Matching closer
(?!`)
''', re.X | re.S)
def _code_span_sub(self, match):
c = match.group(2).strip(" \t")
c = self._encode_code(c)
return "<code>%s</code>" % c
def _do_code_spans(self, text):
# * Backtick quotes are used for <code></code> spans.
#
# * You can use multiple backticks as the delimiters if you want to
# include literal backticks in the code span. So, this input:
#
# Just type ``foo `bar` baz`` at the prompt.
#
# Will translate to:
#
# <p>Just type <code>foo `bar` baz</code> at the prompt.</p>
#
# There's no arbitrary limit to the number of backticks you
# can use as delimters. If you need three consecutive backticks
# in your code, use four for delimiters, etc.
#
# * You can use spaces to get literal backticks at the edges:
#
# ... type `` `bar` `` ...
#
# Turns to:
#
# ... type <code>`bar`</code> ...
return self._code_span_re.sub(self._code_span_sub, text)
def _encode_code(self, text):
"""Encode/escape certain characters inside Markdown code runs.
The point is that in code, these characters are literals,
and lose their special Markdown meanings.
"""
replacements = [
# Encode all ampersands; HTML entities are not
# entities within a Markdown code span.
('&', '&'),
# Do the angle bracket song and dance:
('<', '<'),
('>', '>'),
# Now, escape characters that are magic in Markdown:
('*', g_escape_table['*']),
('_', g_escape_table['_']),
('{', g_escape_table['{']),
('}', g_escape_table['}']),
('[', g_escape_table['[']),
(']', g_escape_table[']']),
('\\', g_escape_table['\\']),
]
for before, after in replacements:
text = text.replace(before, after)
return text
_strong_re = re.compile(r"(?<!\w)(\*\*|__)(?=\S)(.+?[*_]*)(?<=\S)\1(?!\w)", re.S)
_em_re = re.compile(r"(?<!\w)(\*|_)(?=\S)(.+?)(?<=\S)\1(?!\w)", re.S)
_code_friendly_strong_re = re.compile(r"\*\*(?=\S)(.+?[*_]*)(?<=\S)\*\*", re.S)
_code_friendly_em_re = re.compile(r"\*(?=\S)(.+?)(?<=\S)\*", re.S)
def _do_italics_and_bold(self, text):
# <strong> must go first:
if "code-friendly" in self.extras:
text = self._code_friendly_strong_re.sub(r"<strong>\1</strong>", text)
text = self._code_friendly_em_re.sub(r"<em>\1</em>", text)
else:
text = self._strong_re.sub(r"<strong>\2</strong>", text)
text = self._em_re.sub(r"<em>\2</em>", text)
return text
_block_quote_re = re.compile(r'''
( # Wrap whole match in \1
(
^[ \t]*>[ \t]? # '>' at the start of a line
.+\n # rest of the first line
(.+\n)* # subsequent consecutive lines
\n* # blanks
)+
)
''', re.M | re.X)
_bq_one_level_re = re.compile('^[ \t]*>[ \t]?', re.M);
_html_pre_block_re = re.compile(r'(\s*<pre>.+?</pre>)', re.S)
def _dedent_two_spaces_sub(self, match):
return re.sub(r'(?m)^ ', '', match.group(1))
def _block_quote_sub(self, match):
bq = match.group(1)
bq = self._bq_one_level_re.sub('', bq) # trim one level of quoting
bq = self._ws_only_line_re.sub('', bq) # trim whitespace-only lines
bq = self._run_block_gamut(bq) # recurse
bq = re.sub('(?m)^', ' ', bq)
# These leading spaces screw with <pre> content, so we need to fix that:
bq = self._html_pre_block_re.sub(self._dedent_two_spaces_sub, bq)
return "<blockquote>\n%s\n</blockquote>\n\n" % bq
def _do_block_quotes(self, text):
if '>' not in text:
return text
return self._block_quote_re.sub(self._block_quote_sub, text)
def _form_paragraphs(self, text):
# Strip leading and trailing lines:
text = text.strip('\n')
# Wrap <p> tags.
grafs = re.split(r"\n{2,}", text)
for i, graf in enumerate(grafs):
if graf in self.html_blocks:
# Unhashify HTML blocks
grafs[i] = self.html_blocks[graf]
else:
# Wrap <p> tags.
graf = self._run_span_gamut(graf)
grafs[i] = "<p>" + graf.lstrip(" \t") + "</p>"
return "\n\n".join(grafs)
def _add_footnotes(self, text):
if self.footnotes:
footer = [
'<div class="footnotes">',
'<hr' + self.empty_element_suffix,
'<ol>',
]
for i, id in enumerate(self.footnote_ids):
if i != 0:
footer.append('')
footer.append('<li id="fn-%s">' % id)
footer.append(self._run_block_gamut(self.footnotes[id]))
backlink = ('<a href="#fnref-%s" '
'class="footnoteBackLink" '
'title="Jump back to footnote %d in the text.">'
'↩</a>' % (id, i+1))
if footer[-1].endswith("</p>"):
footer[-1] = footer[-1][:-len("</p>")] \
+ ' ' + backlink + "</p>"
else:
footer.append("\n<p>%s</p>" % backlink)
footer.append('</li>')
footer.append('</ol>')
footer.append('</div>')
return text + '\n\n' + '\n'.join(footer)
else:
return text
# Ampersand-encoding based entirely on Nat Irons's Amputator MT plugin:
# http://bumppo.net/projects/amputator/
_ampersand_re = re.compile(r'&(?!#?[xX]?(?:[0-9a-fA-F]+|\w+);)')
_naked_lt_re = re.compile(r'<(?![a-z/?\$!])', re.I)
_naked_gt_re = re.compile(r'''(?<![a-z?!/'"-])>''', re.I)
def _encode_amps_and_angles(self, text):
# Smart processing for ampersands and angle brackets that need
# to be encoded.
text = self._ampersand_re.sub('&', text)
# Encode naked <'s
text = self._naked_lt_re.sub('<', text)
# Encode naked >'s
# Note: Other markdown implementations (e.g. Markdown.pl, PHP
# Markdown) don't do this.
text = self._naked_gt_re.sub('>', text)
return text
def _encode_backslash_escapes(self, text):
for ch, escape in g_escape_table.items():
text = text.replace("\\"+ch, escape)
return text
_auto_link_re = re.compile(r'<((https?|ftp):[^\'">\s]+)>', re.I)
def _auto_link_sub(self, match):
g1 = match.group(1)
return '<a href="%s">%s</a>' % (g1, g1)
_auto_email_link_re = re.compile(r"""
<
(?:mailto:)?
(
[-.\w]+
\@
[-\w]+(\.[-\w]+)*\.[a-z]+
)
>
""", re.I | re.X | re.U)
def _auto_email_link_sub(self, match):
return self._encode_email_address(
self._unescape_special_chars(match.group(1)))
def _do_auto_links(self, text):
text = self._auto_link_re.sub(self._auto_link_sub, text)
text = self._auto_email_link_re.sub(self._auto_email_link_sub, text)
return text
def _encode_email_address(self, addr):
# Input: an email address, e.g. "foo@example.com"
#
# Output: the email address as a mailto link, with each character
# of the address encoded as either a decimal or hex entity, in
# the hopes of foiling most address harvesting spam bots. E.g.:
#
# <a href="mailto:foo@e
# xample.com">foo
# @example.com</a>
#
# Based on a filter by Matthew Wickline, posted to the BBEdit-Talk
# mailing list: <http://tinyurl.com/yu7ue>
chars = [_xml_encode_email_char_at_random(ch)
for ch in "mailto:" + addr]
# Strip the mailto: from the visible part.
addr = '<a href="%s">%s</a>' \
% (''.join(chars), ''.join(chars[7:]))
return addr
def _do_link_patterns(self, text):
"""Caveat emptor: there isn't much guarding against link
patterns being formed inside other standard Markdown links, e.g.
inside a [link def][like this].
Dev Notes: *Could* consider prefixing regexes with a negative
lookbehind assertion to attempt to guard against this.
"""
link_from_hash = {}
for regex, repl in self.link_patterns:
replacements = []
for match in regex.finditer(text):
if hasattr(repl, "__call__"):
href = repl(match)
else:
href = match.expand(repl)
replacements.append((match.span(), href))
for (start, end), href in reversed(replacements):
escaped_href = (
href.replace('"', '"') # b/c of attr quote
# To avoid markdown <em> and <strong>:
.replace('*', g_escape_table['*'])
.replace('_', g_escape_table['_']))
link = '<a href="%s">%s</a>' % (escaped_href, text[start:end])
hash = _hash_text(link)
link_from_hash[hash] = link
text = text[:start] + hash + text[end:]
for hash, link in link_from_hash.items():
text = text.replace(hash, link)
return text
def _unescape_special_chars(self, text):
# Swap back in all the special characters we've hidden.
for ch, hash in g_escape_table.items():
text = text.replace(hash, ch)
return text
def _outdent(self, text):
# Remove one level of line-leading tabs or spaces
return self._outdent_re.sub('', text)
class MarkdownWithExtras(Markdown):
"""A markdowner class that enables most extras:
- footnotes
- code-color (only has effect if 'pygments' Python module on path)
These are not included:
- pyshell (specific to Python-related documenting)
- code-friendly (because it *disables* part of the syntax)
- link-patterns (because you need to specify some actual
link-patterns anyway)
"""
extras = ["footnotes", "code-color"]
#---- internal support functions
# From http://aspn.activestate.com/ASPN/Cookbook/Python/Recipe/52549
def _curry(*args, **kwargs):
function, args = args[0], args[1:]
def result(*rest, **kwrest):
combined = kwargs.copy()
combined.update(kwrest)
return function(*args + rest, **combined)
return result
# Recipe: regex_from_encoded_pattern (1.0)
def _regex_from_encoded_pattern(s):
"""'foo' -> re.compile(re.escape('foo'))
'/foo/' -> re.compile('foo')
'/foo/i' -> re.compile('foo', re.I)
"""
if s.startswith('/') and s.rfind('/') != 0:
# Parse it: /PATTERN/FLAGS
idx = s.rfind('/')
pattern, flags_str = s[1:idx], s[idx+1:]
flag_from_char = {
"i": re.IGNORECASE,
"l": re.LOCALE,
"s": re.DOTALL,
"m": re.MULTILINE,
"u": re.UNICODE,
}
flags = 0
for char in flags_str:
try:
flags |= flag_from_char[char]
except KeyError:
raise ValueError("unsupported regex flag: '%s' in '%s' "
"(must be one of '%s')"
% (char, s, ''.join(flag_from_char.keys())))
return re.compile(s[1:idx], flags)
else: # not an encoded regex
return re.compile(re.escape(s))
# Recipe: dedent (0.1.2)
def _dedentlines(lines, tabsize=8, skip_first_line=False):
"""_dedentlines(lines, tabsize=8, skip_first_line=False) -> dedented lines
"lines" is a list of lines to dedent.
"tabsize" is the tab width to use for indent width calculations.
"skip_first_line" is a boolean indicating if the first line should
be skipped for calculating the indent width and for dedenting.
This is sometimes useful for docstrings and similar.
Same as dedent() except operates on a sequence of lines. Note: the
lines list is modified **in-place**.
"""
DEBUG = False
if DEBUG:
print "dedent: dedent(..., tabsize=%d, skip_first_line=%r)"\
% (tabsize, skip_first_line)
indents = []
margin = None
for i, line in enumerate(lines):
if i == 0 and skip_first_line: continue
indent = 0
for ch in line:
if ch == ' ':
indent += 1
elif ch == '\t':
indent += tabsize - (indent % tabsize)
elif ch in '\r\n':
continue # skip all-whitespace lines
else:
break
else:
continue # skip all-whitespace lines
if DEBUG: print "dedent: indent=%d: %r" % (indent, line)
if margin is None:
margin = indent
else:
margin = min(margin, indent)
if DEBUG: print "dedent: margin=%r" % margin
if margin is not None and margin > 0:
for i, line in enumerate(lines):
if i == 0 and skip_first_line: continue
removed = 0
for j, ch in enumerate(line):
if ch == ' ':
removed += 1
elif ch == '\t':
removed += tabsize - (removed % tabsize)
elif ch in '\r\n':
if DEBUG: print "dedent: %r: EOL -> strip up to EOL" % line
lines[i] = lines[i][j:]
break
else:
raise ValueError("unexpected non-whitespace char %r in "
"line %r while removing %d-space margin"
% (ch, line, margin))
if DEBUG:
print "dedent: %r: %r -> removed %d/%d"\
% (line, ch, removed, margin)
if removed == margin:
lines[i] = lines[i][j+1:]
break
elif removed > margin:
lines[i] = ' '*(removed-margin) + lines[i][j+1:]
break
else:
if removed:
lines[i] = lines[i][removed:]
return lines
def _dedent(text, tabsize=8, skip_first_line=False):
"""_dedent(text, tabsize=8, skip_first_line=False) -> dedented text
"text" is the text to dedent.
"tabsize" is the tab width to use for indent width calculations.
"skip_first_line" is a boolean indicating if the first line should
be skipped for calculating the indent width and for dedenting.
This is sometimes useful for docstrings and similar.
textwrap.dedent(s), but don't expand tabs to spaces
"""
lines = text.splitlines(1)
_dedentlines(lines, tabsize=tabsize, skip_first_line=skip_first_line)
return ''.join(lines)
class _memoized(object):
"""Decorator that caches a function's return value each time it is called.
If called later with the same arguments, the cached value is returned, and
not re-evaluated.
http://wiki.python.org/moin/PythonDecoratorLibrary
"""
def __init__(self, func):
self.func = func
self.cache = {}
def __call__(self, *args):
try:
return self.cache[args]
except KeyError:
self.cache[args] = value = self.func(*args)
return value
except TypeError:
# uncachable -- for instance, passing a list as an argument.
# Better to not cache than to blow up entirely.
return self.func(*args)
def __repr__(self):
"""Return the function's docstring."""
return self.func.__doc__
def _xml_oneliner_re_from_tab_width(tab_width):
"""Standalone XML processing instruction regex."""
return re.compile(r"""
(?:
(?<=\n\n) # Starting after a blank line
| # or
\A\n? # the beginning of the doc
)
( # save in $1
[ ]{0,%d}
(?:
<\?\w+\b\s+.*?\?> # XML processing instruction
|
<\w+:\w+\b\s+.*?/> # namespaced single tag
)
[ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
""" % (tab_width - 1), re.X)
_xml_oneliner_re_from_tab_width = _memoized(_xml_oneliner_re_from_tab_width)
def _hr_tag_re_from_tab_width(tab_width):
return re.compile(r"""
(?:
(?<=\n\n) # Starting after a blank line
| # or
\A\n? # the beginning of the doc
)
( # save in \1
[ ]{0,%d}
<(hr) # start tag = \2
\b # word break
([^<>])*? #
/?> # the matching end tag
[ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
""" % (tab_width - 1), re.X)
_hr_tag_re_from_tab_width = _memoized(_hr_tag_re_from_tab_width)
def _xml_encode_email_char_at_random(ch):
r = random()
# Roughly 10% raw, 45% hex, 45% dec.
# '@' *must* be encoded. I [John Gruber] insist.
# Issue 26: '_' must be encoded.
if r > 0.9 and ch not in "@_":
return ch
elif r < 0.45:
# The [1:] is to drop leading '0': 0x63 -> x63
return '&#%s;' % hex(ord(ch))[1:]
else:
return '&#%s;' % ord(ch)
#---- mainline
class _NoReflowFormatter(optparse.IndentedHelpFormatter):
"""An optparse formatter that does NOT reflow the description."""
def format_description(self, description):
return description or ""
def _test():
import doctest
doctest.testmod()
def main(argv=None):
if argv is None:
argv = sys.argv
if not logging.root.handlers:
logging.basicConfig()
usage = "usage: %prog [PATHS...]"
version = "%prog "+__version__
parser = optparse.OptionParser(prog="markdown2", usage=usage,
version=version, description=cmdln_desc,
formatter=_NoReflowFormatter())
parser.add_option("-v", "--verbose", dest="log_level",
action="store_const", const=logging.DEBUG,
help="more verbose output")
parser.add_option("--encoding",
help="specify encoding of text content")
parser.add_option("--html4tags", action="store_true", default=False,
help="use HTML 4 style for empty element tags")
parser.add_option("-s", "--safe", metavar="MODE", dest="safe_mode",
help="sanitize literal HTML: 'escape' escapes "
"HTML meta chars, 'replace' replaces with an "
"[HTML_REMOVED] note")
parser.add_option("-x", "--extras", action="append",
help="Turn on specific extra features (not part of "
"the core Markdown spec). Supported values: "
"'code-friendly' disables _/__ for emphasis; "
"'code-color' adds code-block syntax coloring; "
"'link-patterns' adds auto-linking based on patterns; "
"'footnotes' adds the footnotes syntax;"
"'xml' passes one-liner processing instructions and namespaced XML tags;"
"'pyshell' to put unindented Python interactive shell sessions in a <code> block.")
parser.add_option("--use-file-vars",
help="Look for and use Emacs-style 'markdown-extras' "
"file var to turn on extras. See "
"<http://code.google.com/p/python-markdown2/wiki/Extras>.")
parser.add_option("--link-patterns-file",
help="path to a link pattern file")
parser.add_option("--self-test", action="store_true",
help="run internal self-tests (some doctests)")
parser.add_option("--compare", action="store_true",
help="run against Markdown.pl as well (for testing)")
parser.set_defaults(log_level=logging.INFO, compare=False,
encoding="utf-8", safe_mode=None, use_file_vars=False)
opts, paths = parser.parse_args()
log.setLevel(opts.log_level)
if opts.self_test:
return _test()
if opts.extras:
extras = {}
for s in opts.extras:
splitter = re.compile("[,;: ]+")
for e in splitter.split(s):
if '=' in e:
ename, earg = e.split('=', 1)
try:
earg = int(earg)
except ValueError:
pass
else:
ename, earg = e, None
extras[ename] = earg
else:
extras = None
if opts.link_patterns_file:
link_patterns = []
f = open(opts.link_patterns_file)
try:
for i, line in enumerate(f.readlines()):
if not line.strip(): continue
if line.lstrip().startswith("#"): continue
try:
pat, href = line.rstrip().rsplit(None, 1)
except ValueError:
raise MarkdownError("%s:%d: invalid link pattern line: %r"
% (opts.link_patterns_file, i+1, line))
link_patterns.append(
(_regex_from_encoded_pattern(pat), href))
finally:
f.close()
else:
link_patterns = None
from os.path import join, dirname, abspath, exists
markdown_pl = join(dirname(dirname(abspath(__file__))), "test",
"Markdown.pl")
for path in paths:
if opts.compare:
print "==== Markdown.pl ===="
perl_cmd = 'perl %s "%s"' % (markdown_pl, path)
o = os.popen(perl_cmd)
perl_html = o.read()
o.close()
sys.stdout.write(perl_html)
print "==== markdown2.py ===="
html = markdown_path(path, encoding=opts.encoding,
html4tags=opts.html4tags,
safe_mode=opts.safe_mode,
extras=extras, link_patterns=link_patterns,
use_file_vars=opts.use_file_vars)
sys.stdout.write(
html.encode(sys.stdout.encoding or "utf-8", 'xmlcharrefreplace'))
if opts.compare:
test_dir = join(dirname(dirname(abspath(__file__))), "test")
if exists(join(test_dir, "test_markdown2.py")):
sys.path.insert(0, test_dir)
from test_markdown2 import norm_html_from_html
norm_html = norm_html_from_html(html)
norm_perl_html = norm_html_from_html(perl_html)
else:
norm_html = html
norm_perl_html = perl_html
print "==== match? %r ====" % (norm_perl_html == norm_html)
if __name__ == "__main__":
sys.exit( main(sys.argv) )
|