Hi,
When using the "extra" extensions, some invalid markdowns (i think?) are causing exceptions rather than returning plaintext line.
Example:
txt = """
*[^1^]: This is going to crash if extra extension is enabled
"""
import markdown
ok = markdown.markdown(txt, extensions=[])
not_ok = markdown.markdown(txt, extensions=['extra'])
Is this expected behavior?
Full exception stack trace:
Cell In[29], line 7
5 import markdown
6 ok = markdown.markdown(txt, extensions=[])
----> 7 not_ok = markdown.markdown(txt, extensions=['extra'])
File lib/python3.10/site-packages/markdown/core.py:482, in markdown(text, **kwargs)
464 """
465 Convert a markdown string to HTML and return HTML as a Unicode string.
466
(...)
479
480 """
481 md = Markdown(**kwargs)
--> 482 return md.convert(text)
File lib/python3.10/site-packages/markdown/core.py:357, in Markdown.convert(self, source)
354 self.lines = prep.run(self.lines)
356 # Parse the high-level elements.
--> 357 root = self.parser.parseDocument(self.lines).getroot()
359 # Run the tree-processors
360 for treeprocessor in self.treeprocessors:
File lib/python3.10/site-packages/markdown/blockparser.py:117, in BlockParser.parseDocument(self, lines)
115 # Create an `ElementTree` from the lines
116 self.root = etree.Element(self.md.doc_tag)
--> 117 self.parseChunk(self.root, '\n'.join(lines))
118 return etree.ElementTree(self.root)
File lib/python3.10/site-packages/markdown/blockparser.py:136, in BlockParser.parseChunk(self, parent, text)
120 def parseChunk(self, parent: etree.Element, text: str) -> None:
121 """ Parse a chunk of Markdown text and attach to given `etree` node.
122
123 While the `text` argument is generally assumed to contain multiple
(...)
134
135 """
--> 136 self.parseBlocks(parent, text.split('\n\n'))
File lib/python3.10/site-packages/markdown/blockparser.py:158, in BlockParser.parseBlocks(self, parent, blocks)
156 for processor in self.blockprocessors:
157 if processor.test(parent, blocks[0]):
--> 158 if processor.run(parent, blocks) is not False:
159 # run returns True or None
160 break
File lib/python3.10/site-packages/markdown/extensions/abbr.py:61, in AbbrPreprocessor.run(self, parent, blocks)
58 abbr = m.group('abbr').strip()
59 title = m.group('title').strip()
60 self.parser.md.inlinePatterns.register(
---> 61 AbbrInlineProcessor(self._generate_pattern(abbr), title), 'abbr-%s' % abbr, 2
62 )
63 if block[m.end():].strip():
64 # Add any content after match back to blocks as separate block
65 blocks.insert(0, block[m.end():].lstrip('\n'))
File lib/python3.10/site-packages/markdown/extensions/abbr.py:94, in AbbrInlineProcessor.__init__(self, pattern, title)
93 def __init__(self, pattern: str, title: str):
---> 94 super().__init__(pattern)
95 self.title = title
File lib/python3.10/site-packages/markdown/inlinepatterns.py:297, in InlineProcessor.__init__(self, pattern, md)
287 """
288 Create an instant of an inline processor.
289
(...)
294
295 """
296 self.pattern = pattern
--> 297 self.compiled_re = re.compile(pattern, re.DOTALL | re.UNICODE)
299 # API for Markdown to pass `safe_mode` into instance
300 self.safe_mode = False
File lib/python3.10/re.py:251, in compile(pattern, flags)
249 def compile(pattern, flags=0):
250 "Compile a regular expression pattern, returning a Pattern object."
--> 251 return _compile(pattern, flags)
File lib/python3.10/re.py:303, in _compile(pattern, flags)
301 if not sre_compile.isstring(pattern):
302 raise TypeError("first argument must be string or compiled pattern")
--> 303 p = sre_compile.compile(pattern, flags)
304 if not (flags & DEBUG):
305 if len(_cache) >= _MAXCACHE:
306 # Drop the oldest item
File lib/python3.10/sre_compile.py:788, in compile(p, flags)
786 if isstring(p):
787 pattern = p
--> 788 p = sre_parse.parse(p, flags)
789 else:
790 pattern = None
File lib/python3.10/sre_parse.py:955, in parse(str, flags, state)
952 state.str = str
954 try:
--> 955 p = _parse_sub(source, state, flags & SRE_FLAG_VERBOSE, 0)
956 except Verbose:
957 # the VERBOSE flag was switched on inside the pattern. to be
958 # on the safe side, we'll parse the whole thing again...
959 state = State()
File lib/python3.10/sre_parse.py:444, in _parse_sub(source, state, verbose, nested)
442 start = source.tell()
443 while True:
--> 444 itemsappend(_parse(source, state, verbose, nested + 1,
445 not nested and not items))
446 if not sourcematch("|"):
447 break
File lib/python3.10/sre_parse.py:841, in _parse(source, state, verbose, nested, first)
838 raise source.error(err.msg, len(name) + 1) from None
839 sub_verbose = ((verbose or (add_flags & SRE_FLAG_VERBOSE)) and
840 not (del_flags & SRE_FLAG_VERBOSE))
--> 841 p = _parse_sub(source, state, sub_verbose, nested + 1)
842 if not source.match(")"):
843 raise source.error("missing ), unterminated subpattern",
844 source.tell() - start)
File lib/python3.10/sre_parse.py:444, in _parse_sub(source, state, verbose, nested)
442 start = source.tell()
443 while True:
--> 444 itemsappend(_parse(source, state, verbose, nested + 1,
445 not nested and not items))
446 if not sourcematch("|"):
447 break
File lib/python3.10/sre_parse.py:550, in _parse(source, state, verbose, nested, first)
548 this = sourceget()
549 if this is None:
--> 550 raise source.error("unterminated character set",
551 source.tell() - here)
552 if this == "]" and set:
553 break
error: unterminated character set at position 17
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