diff options
Diffstat (limited to 'markdown/postprocessors.py')
-rw-r--r-- | markdown/postprocessors.py | 124 |
1 files changed, 92 insertions, 32 deletions
diff --git a/markdown/postprocessors.py b/markdown/postprocessors.py index 80227bb..498f7e8 100644 --- a/markdown/postprocessors.py +++ b/markdown/postprocessors.py @@ -1,4 +1,23 @@ """ +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). + POST-PROCESSORS ============================================================================= @@ -8,15 +27,20 @@ processing. """ +from collections import OrderedDict +from . import util +import re + -import markdown +def build_postprocessors(md, **kwargs): + """ Build the default postprocessors for Markdown. """ + postprocessors = util.Registry() + postprocessors.register(RawHtmlPostprocessor(md), 'raw_html', 30) + postprocessors.register(AndSubstitutePostprocessor(), 'amp_substitute', 20) + return postprocessors -class Processor: - def __init__(self, markdown_instance=None): - if markdown_instance: - self.markdown = markdown_instance -class Postprocessor(Processor): +class Postprocessor(util.Processor): """ Postprocessors are run after the ElementTree it converted back into text. @@ -34,44 +58,80 @@ class Postprocessor(Processor): (possibly modified) string. """ - pass + pass # pragma: no cover class RawHtmlPostprocessor(Postprocessor): """ Restore raw html to the document. """ + BLOCK_LEVEL_REGEX = re.compile(r'^\<\/?([^ >]+)') + def run(self, text): - """ Iterate over html stash and restore "safe" html. """ - for i in range(self.markdown.htmlStash.html_counter): - html, safe = self.markdown.htmlStash.rawHtmlBlocks[i] - if self.markdown.safeMode and not safe: - if str(self.markdown.safeMode).lower() == 'escape': - html = self.escape(html) - elif str(self.markdown.safeMode).lower() == 'remove': - html = '' + """ Iterate over html stash and restore html. """ + replacements = OrderedDict() + for i in range(self.md.htmlStash.html_counter): + html = self.stash_to_string(self.md.htmlStash.rawHtmlBlocks[i]) + if self.isblocklevel(html): + replacements["<p>{}</p>".format( + self.md.htmlStash.get_placeholder(i))] = html + replacements[self.md.htmlStash.get_placeholder(i)] = html + + def substitute_match(m): + key = m.group(0) + + if key not in replacements: + if key[3:-4] in replacements: + return f'<p>{ replacements[key[3:-4]] }</p>' else: - html = markdown.HTML_REMOVED_TEXT - if safe or not self.markdown.safeMode: - text = text.replace("<p>%s</p>" % - (markdown.preprocessors.HTML_PLACEHOLDER % i), - html + "\n") - text = text.replace(markdown.preprocessors.HTML_PLACEHOLDER % i, - html) - return text + return key + + return replacements[key] - def escape(self, html): - """ Basic html escaping """ - html = html.replace('&', '&') - html = html.replace('<', '<') - html = html.replace('>', '>') - return html.replace('"', '"') + if replacements: + base_placeholder = util.HTML_PLACEHOLDER % r'([0-9]+)' + pattern = re.compile(f'<p>{ base_placeholder }</p>|{ base_placeholder }') + processed_text = pattern.sub(substitute_match, text) + else: + return text + + if processed_text == text: + return processed_text + else: + return self.run(processed_text) + + def isblocklevel(self, html): + m = self.BLOCK_LEVEL_REGEX.match(html) + if m: + if m.group(1)[0] in ('!', '?', '@', '%'): + # Comment, php etc... + return True + return self.md.is_block_level(m.group(1)) + return False + + def stash_to_string(self, text): + """ Convert a stashed object to a string. """ + return str(text) class AndSubstitutePostprocessor(Postprocessor): """ Restore valid entities """ - def __init__(self): - pass def run(self, text): - text = text.replace(markdown.AMP_SUBSTITUTE, "&") + text = text.replace(util.AMP_SUBSTITUTE, "&") return text + + +@util.deprecated( + "This class will be removed in the future; " + "use 'treeprocessors.UnescapeTreeprocessor' instead." +) +class UnescapePostprocessor(Postprocessor): + """ Restore escaped chars """ + + RE = re.compile(r'{}(\d+){}'.format(util.STX, util.ETX)) + + def unescape(self, m): + return chr(int(m.group(1))) + + def run(self, text): + return self.RE.sub(self.unescape, text) |