1""" 2Python Markdown 3 4A Python implementation of John Gruber's Markdown. 5 6Documentation: https://python-markdown.github.io/ 7GitHub: https://github.com/Python-Markdown/markdown/ 8PyPI: https://pypi.org/project/Markdown/ 9 10Started by Manfred Stienstra (http://www.dwerg.net/). 11Maintained for a few years by Yuri Takhteyev (http://www.freewisdom.org). 12Currently maintained by Waylan Limberg (https://github.com/waylan), 13Dmitry Shachnev (https://github.com/mitya57) and Isaac Muse (https://github.com/facelessuser). 14 15Copyright 2007-2018 The Python Markdown Project (v. 1.7 and later) 16Copyright 2004, 2005, 2006 Yuri Takhteyev (v. 0.2-1.6b) 17Copyright 2004 Manfred Stienstra (the original version) 18 19License: BSD (see LICENSE.md for details). 20 21PRE-PROCESSORS 22============================================================================= 23 24Preprocessors work on source text before we start doing anything too 25complicated. 26""" 27 28from . import util 29from .htmlparser import HTMLExtractor 30import re 31 32 33def build_preprocessors(md, **kwargs): 34 """ Build the default set of preprocessors used by Markdown. """ 35 preprocessors = util.Registry() 36 preprocessors.register(NormalizeWhitespace(md), 'normalize_whitespace', 30) 37 preprocessors.register(HtmlBlockPreprocessor(md), 'html_block', 20) 38 return preprocessors 39 40 41class Preprocessor(util.Processor): 42 """ 43 Preprocessors are run after the text is broken into lines. 44 45 Each preprocessor implements a "run" method that takes a pointer to a 46 list of lines of the document, modifies it as necessary and returns 47 either the same pointer or a pointer to a new list. 48 49 Preprocessors must extend markdown.Preprocessor. 50 51 """ 52 def run(self, lines): 53 """ 54 Each subclass of Preprocessor should override the `run` method, which 55 takes the document as a list of strings split by newlines and returns 56 the (possibly modified) list of lines. 57 58 """ 59 pass # pragma: no cover 60 61 62class NormalizeWhitespace(Preprocessor): 63 """ Normalize whitespace for consistent parsing. """ 64 65 def run(self, lines): 66 source = '\n'.join(lines) 67 source = source.replace(util.STX, "").replace(util.ETX, "") 68 source = source.replace("\r\n", "\n").replace("\r", "\n") + "\n\n" 69 source = source.expandtabs(self.md.tab_length) 70 source = re.sub(r'(?<=\n) +\n', '\n', source) 71 return source.split('\n') 72 73 74class HtmlBlockPreprocessor(Preprocessor): 75 """Remove html blocks from the text and store them for later retrieval.""" 76 77 def run(self, lines): 78 source = '\n'.join(lines) 79 parser = HTMLExtractor(self.md) 80 parser.feed(source) 81 parser.close() 82 return ''.join(parser.cleandoc).split('\n') 83