+82
-8
lines changedFilter options
+82
-8
lines changed Original file line number Diff line number Diff line change
@@ -30,10 +30,18 @@ markdown.markdown(src, extensions=[TableExtension(use_align_attribute=True)])
30 30 31 31
In addition, tests were moved to the modern test environment.
32 32 33 +
### Backslash unescaping moved to Treeprocessor (#1131).
34 + 35 +
Unescaping backslash escapes has been moved to a Treeprocessor. However, it is
36 +
recognized that various third-party extensions may be calling the old class at
37 +
`postprocessors.UnescapePostprocessor`. Therefore, the old class remains in the
38 +
code base, but has been deprecated and will be removed in a future release. The
39 +
new class `treeprocessors.UnescapeTreeprocessor` should be used instead.
40 + 33 41
### Previously deprecated objects have been removed
34 42 35 43
Various objects were deprecated in version 3.0 and began raising deprecation
36 -
warnings (see the [version 3.0 release notes] for details). Any of those object
44 +
warnings (see the [version 3.0 release notes] for details). Any of those objects
37 45
which remained in version 3.3 have been removed from the code base in version 3.4
38 46
and will now raise errors. A summary of the objects are provided below.
39 47
@@ -16,7 +16,7 @@
16 16
from . import Extension
17 17
from ..treeprocessors import Treeprocessor
18 18
from ..util import code_escape, parseBoolValue, AMP_SUBSTITUTE, HTML_PLACEHOLDER_RE, AtomicString
19 -
from ..postprocessors import UnescapePostprocessor
19 +
from ..treeprocessors import UnescapeTreeprocessor
20 20
import re
21 21
import html
22 22
import unicodedata
@@ -84,8 +84,8 @@ def _html_sub(m):
84 84 85 85
def unescape(text):
86 86
""" Unescape escaped text. """
87 -
c = UnescapePostprocessor()
88 -
return c.run(text)
87 +
c = UnescapeTreeprocessor()
88 +
return c.unescape(text)
89 89 90 90 91 91
def nest_toc_tokens(toc_list):
@@ -289,10 +289,10 @@ def run(self, doc):
289 289
toc_tokens.append({
290 290
'level': int(el.tag[-1]),
291 291
'id': el.attrib["id"],
292 -
'name': unescape(stashedHTML2text(
292 +
'name': stashedHTML2text(
293 293
code_escape(el.attrib.get('data-toc-label', text)),
294 294
self.md, strip_entities=False
295 -
))
295 +
)
296 296
})
297 297 298 298
# Remove the data-toc-label attribute as it is no longer needed
@@ -37,7 +37,6 @@ def build_postprocessors(md, **kwargs):
37 37
postprocessors = util.Registry()
38 38
postprocessors.register(RawHtmlPostprocessor(md), 'raw_html', 30)
39 39
postprocessors.register(AndSubstitutePostprocessor(), 'amp_substitute', 20)
40 -
postprocessors.register(UnescapePostprocessor(), 'unescape', 10)
41 40
return postprocessors
42 41 43 42
@@ -122,6 +121,10 @@ def run(self, text):
122 121
return text
123 122 124 123 124 +
@util.deprecated(
125 +
"This class will be removed in the future; "
126 +
"use 'treeprocessors.UnescapeTreeprocessor' instead."
127 +
)
125 128
class UnescapePostprocessor(Postprocessor):
126 129
""" Restore escaped chars """
127 130
@@ -19,6 +19,7 @@
19 19
License: BSD (see LICENSE.md for details).
20 20
"""
21 21 22 +
import re
22 23
import xml.etree.ElementTree as etree
23 24
from . import util
24 25
from . import inlinepatterns
@@ -29,6 +30,7 @@ def build_treeprocessors(md, **kwargs):
29 30
treeprocessors = util.Registry()
30 31
treeprocessors.register(InlineProcessor(md), 'inline', 20)
31 32
treeprocessors.register(PrettifyTreeprocessor(md), 'prettify', 10)
33 +
treeprocessors.register(UnescapeTreeprocessor(md), 'unescape', 0)
32 34
return treeprocessors
33 35 34 36
@@ -429,3 +431,28 @@ def run(self, root):
429 431
# Only prettify code containing text only
430 432
if not len(code) and code.text is not None:
431 433
code.text = util.AtomicString(code.text.rstrip() + '\n')
434 + 435 + 436 +
class UnescapeTreeprocessor(Treeprocessor):
437 +
""" Restore escaped chars """
438 + 439 +
RE = re.compile(r'{}(\d+){}'.format(util.STX, util.ETX))
440 + 441 +
def _unescape(self, m):
442 +
return chr(int(m.group(1)))
443 + 444 +
def unescape(self, text):
445 +
return self.RE.sub(self._unescape, text)
446 + 447 +
def run(self, root):
448 +
""" Loop over all elements and unescape all text. """
449 +
for elem in root.iter():
450 +
# Unescape text content
451 +
if elem.text and not elem.tag == 'code':
452 +
elem.text = self.unescape(elem.text)
453 +
# Unescape tail content
454 +
if elem.tail:
455 +
elem.tail = self.unescape(elem.tail)
456 +
# Unescape attribute values
457 +
for key, value in elem.items():
458 +
elem.set(key, self.unescape(value))
Original file line number Diff line number Diff line change
@@ -9,7 +9,7 @@
9 9
<p>Right bracket: ]</p>
10 10
<p>Left paren: (</p>
11 11
<p>Right paren: )</p>
12 -
<p>Greater-than: ></p>
12 +
<p>Greater-than: ></p>
13 13
<p>Hash: #</p>
14 14
<p>Period: .</p>
15 15
<p>Bang: !</p>
@@ -0,0 +1,36 @@
1 +
# -*- coding: utf-8 -*-
2 +
"""
3 +
Python Markdown
4 + 5 +
A Python implementation of John Gruber's Markdown.
6 + 7 +
Documentation: https://python-markdown.github.io/
8 +
GitHub: https://github.com/Python-Markdown/markdown/
9 +
PyPI: https://pypi.org/project/Markdown/
10 + 11 +
Started by Manfred Stienstra (http://www.dwerg.net/).
12 +
Maintained for a few years by Yuri Takhteyev (http://www.freewisdom.org).
13 +
Currently maintained by Waylan Limberg (https://github.com/waylan),
14 +
Dmitry Shachnev (https://github.com/mitya57) and Isaac Muse (https://github.com/facelessuser).
15 + 16 +
Copyright 2007-2022 The Python Markdown Project (v. 1.7 and later)
17 +
Copyright 2004, 2005, 2006 Yuri Takhteyev (v. 0.2-1.6b)
18 +
Copyright 2004 Manfred Stienstra (the original version)
19 + 20 +
License: BSD (see LICENSE.md for details).
21 +
"""
22 + 23 +
from markdown.test_tools import TestCase
24 + 25 + 26 +
class TestSmarty(TestCase):
27 + 28 +
default_kwargs = {'extensions': ['smarty']}
29 + 30 +
def test_escaped_attr(self):
31 +
self.assertMarkdownRenders(
32 +
'',
33 +
'<p><img alt="x"x" src="x" /></p>'
34 +
)
35 + 36 +
# TODO: Move rest of smarty tests here.
You can’t perform that action at this time.
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4