Gecko [ tsuru-no-tsurugi.tokyo ]

Name	Size	Permission	Date
__pycache__	[ DIR ]	drwxr-xr-x	2024-09-07 23:28
extensions	[ DIR ]	drwxr-xr-x	2024-09-07 23:28
__init__.py	2.02 KB	-rw-r--r--	2021-11-18 00:59
__main__.py	5.67 KB	-rw-r--r--	2021-11-18 00:59
__meta__.py	1.59 KB	-rw-r--r--	2021-11-18 00:59
blockparser.py	4.18 KB	-rw-r--r--	2021-11-18 00:59
blockprocessors.py	24.31 KB	-rw-r--r--	2021-11-18 00:59
core.py	15.04 KB	-rw-r--r--	2021-11-18 00:59
htmlparser.py	12.73 KB	-rw-r--r--	2021-11-18 00:59
inlinepatterns.py	29.08 KB	-rw-r--r--	2021-11-18 00:59
pep562.py	8.71 KB	-rw-r--r--	2021-11-18 00:59
postprocessors.py	4.16 KB	-rw-r--r--	2021-11-18 00:59
preprocessors.py	2.68 KB	-rw-r--r--	2021-11-18 00:59
serializers.py	6.39 KB	-rw-r--r--	2021-11-18 00:59
test_tools.py	8.17 KB	-rw-r--r--	2021-11-18 00:59
treeprocessors.py	15.07 KB	-rw-r--r--	2021-11-18 00:59
util.py	15.69 KB	-rw-r--r--	2021-11-18 00:59

Rename

"""
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).

License: BSD (see LICENSE.md for details).

PRE-PROCESSORS
=============================================================================

Preprocessors work on source text before we start doing anything too
complicated.
"""

from . import util
from .htmlparser import HTMLExtractor
import re

def build_preprocessors(md, **kwargs):
    """ Build the default set of preprocessors used by Markdown. """
    preprocessors = util.Registry()
    preprocessors.register(NormalizeWhitespace(md), 'normalize_whitespace', 30)
    preprocessors.register(HtmlBlockPreprocessor(md), 'html_block', 20)
    return preprocessors

class Preprocessor(util.Processor):
    """
    Preprocessors are run after the text is broken into lines.

Each preprocessor implements a "run" method that takes a pointer to a
    list of lines of the document, modifies it as necessary and returns
    either the same pointer or a pointer to a new list.

Preprocessors must extend markdown.Preprocessor.

"""
    def run(self, lines):
        """
        Each subclass of Preprocessor should override the `run` method, which
        takes the document as a list of strings split by newlines and returns
        the (possibly modified) list of lines.

"""
        pass  # pragma: no cover

class NormalizeWhitespace(Preprocessor):
    """ Normalize whitespace for consistent parsing. """

def run(self, lines):
        source = '\n'.join(lines)
        source = source.replace(util.STX, "").replace(util.ETX, "")
        source = source.replace("\r\n", "\n").replace("\r", "\n") + "\n\n"
        source = source.expandtabs(self.md.tab_length)
        source = re.sub(r'(?<=\n) +\n', '\n', source)
        return source.split('\n')

class HtmlBlockPreprocessor(Preprocessor):
    """Remove html blocks from the text and store them for later retrieval."""

def run(self, lines):
        source = '\n'.join(lines)
        parser = HTMLExtractor(self.md)
        parser.feed(source)
        parser.close()
        return ''.join(parser.cleandoc).split('\n')