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
|
# -*- coding: utf-8 -*-
"""
Python Markdown
A Python implementation of John Gruber's Markdown.
Documentation: https://python-markdown.github.io/
GitHub: https://github.com/Python-Markdown/markdown/
PyPI: https://pypi.org/project/Markdown/
Started by Manfred Stienstra (http://www.dwerg.net/).
Maintained for a few years by Yuri Takhteyev (http://www.freewisdom.org).
Currently maintained by Waylan Limberg (https://github.com/waylan),
Dmitry Shachnev (https://github.com/mitya57) and Isaac Muse (https://github.com/facelessuser).
Copyright 2007-2018 The Python Markdown Project (v. 1.7 and later)
Copyright 2004, 2005, 2006 Yuri Takhteyev (v. 0.2-1.6b)
Copyright 2004 Manfred Stienstra (the original version)
License: BSD (see LICENSE.md for details).
"""
from __future__ import unicode_literals
import re
import sys
from collections import namedtuple
from functools import wraps
import warnings
"""
Python 3 Stuff
=============================================================================
"""
PY3 = sys.version_info[0] == 3
if PY3: # pragma: no cover
string_type = str
text_type = str
int2str = chr
iterrange = range
else: # pragma: no cover
string_type = basestring # noqa
text_type = unicode # noqa
int2str = unichr # noqa
iterrange = xrange # noqa
"""
Constants you might want to modify
-----------------------------------------------------------------------------
"""
BLOCK_LEVEL_ELEMENTS = [
# Elements which are invalid to wrap in a `<p>` tag.
# See http://w3c.github.io/html/grouping-content.html#the-p-element
'address', 'article', 'aside', 'blockquote', 'details', 'div', 'dl',
'fieldset', 'figcaption', 'figure', 'footer', 'form', 'h1', 'h2', 'h3',
'h4', 'h5', 'h6', 'header', 'hr', 'main', 'menu', 'nav', 'ol', 'p', 'pre',
'section', 'table', 'ul',
# Other elements which Markdown should not be mucking up the contents of.
'canvas', 'dd', 'dt', 'group', 'iframe', 'li', 'math', 'noscript', 'output',
'progress', 'script', 'style', 'tbody', 'td', 'th', 'thead', 'tr', 'video'
]
# Placeholders
STX = '\u0002' # Use STX ("Start of text") for start-of-placeholder
ETX = '\u0003' # Use ETX ("End of text") for end-of-placeholder
INLINE_PLACEHOLDER_PREFIX = STX+"klzzwxh:"
INLINE_PLACEHOLDER = INLINE_PLACEHOLDER_PREFIX + "%s" + ETX
INLINE_PLACEHOLDER_RE = re.compile(INLINE_PLACEHOLDER % r'([0-9]+)')
AMP_SUBSTITUTE = STX+"amp"+ETX
HTML_PLACEHOLDER = STX + "wzxhzdk:%s" + ETX
HTML_PLACEHOLDER_RE = re.compile(HTML_PLACEHOLDER % r'([0-9]+)')
TAG_PLACEHOLDER = STX + "hzzhzkh:%s" + ETX
"""
Constants you probably do not need to change
-----------------------------------------------------------------------------
"""
RTL_BIDI_RANGES = (
('\u0590', '\u07FF'),
# Hebrew (0590-05FF), Arabic (0600-06FF),
# Syriac (0700-074F), Arabic supplement (0750-077F),
# Thaana (0780-07BF), Nko (07C0-07FF).
('\u2D30', '\u2D7F') # Tifinagh
)
# Extensions should use "markdown.util.etree" instead of "etree" (or do `from
# markdown.util import etree`). Do not import it by yourself.
try: # pragma: no cover
# Is the C implementation of ElementTree available?
import xml.etree.cElementTree as etree
from xml.etree.ElementTree import Comment
# Serializers (including ours) test with non-c Comment
etree.test_comment = Comment
if etree.VERSION < "1.0.5":
raise RuntimeError("cElementTree version 1.0.5 or higher is required.")
except (ImportError, RuntimeError): # pragma: no cover
# Use the Python implementation of ElementTree?
import xml.etree.ElementTree as etree
if etree.VERSION < "1.1":
raise RuntimeError("ElementTree version 1.1 or higher is required")
"""
AUXILIARY GLOBAL FUNCTIONS
=============================================================================
"""
def deprecated(message):
"""
Raise a DeprecationWarning when wrapped function/method is called.
Borrowed from https://stackoverflow.com/a/48632082/866026
"""
def deprecated_decorator(func):
@wraps(func)
def deprecated_func(*args, **kwargs):
warnings.warn(
"'{}' is deprecated. {}".format(func.__name__, message),
category=DeprecationWarning,
stacklevel=2
)
return func(*args, **kwargs)
return deprecated_func
return deprecated_decorator
@deprecated("Use 'Markdown.is_block_level' instead.")
def isBlockLevel(tag):
"""Check if the tag is a block level HTML tag."""
if isinstance(tag, string_type):
return tag.lower().rstrip('/') in BLOCK_LEVEL_ELEMENTS
# Some ElementTree tags are not strings, so return False.
return False
def parseBoolValue(value, fail_on_errors=True, preserve_none=False):
"""Parses a string representing bool value. If parsing was successful,
returns True or False. If preserve_none=True, returns True, False,
or None. If parsing was not successful, raises ValueError, or, if
fail_on_errors=False, returns None."""
if not isinstance(value, string_type):
if preserve_none and value is None:
return value
return bool(value)
elif preserve_none and value.lower() == 'none':
return None
elif value.lower() in ('true', 'yes', 'y', 'on', '1'):
return True
elif value.lower() in ('false', 'no', 'n', 'off', '0', 'none'):
return False
elif fail_on_errors:
raise ValueError('Cannot parse bool value: %r' % value)
def code_escape(text):
"""Escape code."""
if "&" in text:
text = text.replace("&", "&")
if "<" in text:
text = text.replace("<", "<")
if ">" in text:
text = text.replace(">", ">")
return text
"""
MISC AUXILIARY CLASSES
=============================================================================
"""
class AtomicString(text_type):
"""A string which should not be further processed."""
pass
class Processor(object):
def __init__(self, md=None):
self.md = md
@property
@deprecated("Use 'md' instead.")
def markdown(self):
# TODO: remove this later
return self.md
class HtmlStash(object):
"""
This class is used for stashing HTML objects that we extract
in the beginning and replace with place-holders.
"""
def __init__(self):
""" Create a HtmlStash. """
self.html_counter = 0 # for counting inline html segments
self.rawHtmlBlocks = []
self.tag_counter = 0
self.tag_data = [] # list of dictionaries in the order tags appear
def store(self, html):
"""
Saves an HTML segment for later reinsertion. Returns a
placeholder string that needs to be inserted into the
document.
Keyword arguments:
* html: an html segment
Returns : a placeholder string
"""
self.rawHtmlBlocks.append(html)
placeholder = self.get_placeholder(self.html_counter)
self.html_counter += 1
return placeholder
def reset(self):
self.html_counter = 0
self.rawHtmlBlocks = []
def get_placeholder(self, key):
return HTML_PLACEHOLDER % key
def store_tag(self, tag, attrs, left_index, right_index):
"""Store tag data and return a placeholder."""
self.tag_data.append({'tag': tag, 'attrs': attrs,
'left_index': left_index,
'right_index': right_index})
placeholder = TAG_PLACEHOLDER % str(self.tag_counter)
self.tag_counter += 1 # equal to the tag's index in self.tag_data
return placeholder
# Used internally by `Registry` for each item in its sorted list.
# Provides an easier to read API when editing the code later.
# For example, `item.name` is more clear than `item[0]`.
_PriorityItem = namedtuple('PriorityItem', ['name', 'priority'])
class Registry(object):
"""
A priority sorted registry.
A `Registry` instance provides two public methods to alter the data of the
registry: `register` and `deregister`. Use `register` to add items and
`deregister` to remove items. See each method for specifics.
When registering an item, a "name" and a "priority" must be provided. All
items are automatically sorted by "priority" from highest to lowest. The
"name" is used to remove ("deregister") and get items.
A `Registry` instance it like a list (which maintains order) when reading
data. You may iterate over the items, get an item and get a count (length)
of all items. You may also check that the registry contains an item.
When getting an item you may use either the index of the item or the
string-based "name". For example:
registry = Registry()
registry.register(SomeItem(), 'itemname', 20)
# Get the item by index
item = registry[0]
# Get the item by name
item = registry['itemname']
When checking that the registry contains an item, you may use either the
string-based "name", or a reference to the actual item. For example:
someitem = SomeItem()
registry.register(someitem, 'itemname', 20)
# Contains the name
assert 'itemname' in registry
# Contains the item instance
assert someitem in registry
The method `get_index_for_name` is also available to obtain the index of
an item using that item's assigned "name".
"""
def __init__(self):
self._data = {}
self._priority = []
self._is_sorted = False
def __contains__(self, item):
if isinstance(item, string_type):
# Check if an item exists by this name.
return item in self._data.keys()
# Check if this instance exists.
return item in self._data.values()
def __iter__(self):
self._sort()
return iter([self._data[k] for k, p in self._priority])
def __getitem__(self, key):
self._sort()
if isinstance(key, slice):
data = Registry()
for k, p in self._priority[key]:
data.register(self._data[k], k, p)
return data
if isinstance(key, int):
return self._data[self._priority[key].name]
return self._data[key]
def __len__(self):
return len(self._priority)
def __repr__(self):
return '<{0}({1})>'.format(self.__class__.__name__, list(self))
def get_index_for_name(self, name):
"""
Return the index of the given name.
"""
if name in self:
self._sort()
return self._priority.index(
[x for x in self._priority if x.name == name][0]
)
raise ValueError('No item named "{0}" exists.'.format(name))
def register(self, item, name, priority):
"""
Add an item to the registry with the given name and priority.
Parameters:
* `item`: The item being registered.
* `name`: A string used to reference the item.
* `priority`: An integer or float used to sort against all items.
If an item is registered with a "name" which already exists, the
existing item is replaced with the new item. Tread carefully as the
old item is lost with no way to recover it. The new item will be
sorted according to its priority and will **not** retain the position
of the old item.
"""
if name in self:
# Remove existing item of same name first
self.deregister(name)
self._is_sorted = False
self._data[name] = item
self._priority.append(_PriorityItem(name, priority))
def deregister(self, name, strict=True):
"""
Remove an item from the registry.
Set `strict=False` to fail silently.
"""
try:
index = self.get_index_for_name(name)
del self._priority[index]
del self._data[name]
except ValueError:
if strict:
raise
def _sort(self):
"""
Sort the registry by priority from highest to lowest.
This method is called internally and should never be explicitly called.
"""
if not self._is_sorted:
self._priority.sort(key=lambda item: item.priority, reverse=True)
self._is_sorted = True
# Deprecated Methods which provide a smooth transition from OrderedDict
def __setitem__(self, key, value):
""" Register item with priorty 5 less than lowest existing priority. """
if isinstance(key, string_type):
warnings.warn(
'Using setitem to register a processor or pattern is deprecated. '
'Use the `register` method instead.', DeprecationWarning
)
if key in self:
# Key already exists, replace without altering priority
self._data[key] = value
return
if len(self) == 0:
# This is the first item. Set priority to 50.
priority = 50
else:
self._sort()
priority = self._priority[-1].priority - 5
self.register(value, key, priority)
else:
raise TypeError
def __delitem__(self, key):
""" Deregister an item by name. """
if key in self:
self.deregister(key)
warnings.warn(
'Using del to remove a processor or pattern is deprecated. '
'Use the `deregister` method instead.', DeprecationWarning
)
else:
raise TypeError
def add(self, key, value, location):
""" Register a key by location. """
if len(self) == 0:
# This is the first item. Set priority to 50.
priority = 50
elif location == '_begin':
self._sort()
# Set priority 5 greater than highest existing priority
priority = self._priority[0].priority + 5
elif location == '_end':
self._sort()
# Set priority 5 less than lowest existing priority
priority = self._priority[-1].priority - 5
elif location.startswith('<') or location.startswith('>'):
# Set priority halfway between existing priorities.
i = self.get_index_for_name(location[1:])
if location.startswith('<'):
after = self._priority[i].priority
if i > 0:
before = self._priority[i-1].priority
else:
# Location is first item`
before = after + 10
else:
# location.startswith('>')
before = self._priority[i].priority
if i < len(self) - 1:
after = self._priority[i+1].priority
else:
# location is last item
after = before - 10
priority = before - ((before - after) / 2)
else:
raise ValueError('Not a valid location: "%s". Location key '
'must start with a ">" or "<".' % location)
self.register(value, key, priority)
warnings.warn(
'Using the add method to register a processor or pattern is deprecated. '
'Use the `register` method instead.', DeprecationWarning
)
|