| Index: third_party/markdown/util.py
|
| diff --git a/third_party/markdown/util.py b/third_party/markdown/util.py
|
| new file mode 100644
|
| index 0000000000000000000000000000000000000000..1036197c47ce341f02edd168e27be1bc96cf2680
|
| --- /dev/null
|
| +++ b/third_party/markdown/util.py
|
| @@ -0,0 +1,136 @@
|
| +# -*- coding: utf-8 -*-
|
| +from __future__ import unicode_literals
|
| +import re
|
| +import sys
|
| +
|
| +
|
| +"""
|
| +Python 3 Stuff
|
| +=============================================================================
|
| +"""
|
| +PY3 = sys.version_info[0] == 3
|
| +
|
| +if PY3:
|
| + string_type = str
|
| + text_type = str
|
| + int2str = chr
|
| +else:
|
| + string_type = basestring
|
| + text_type = unicode
|
| + int2str = unichr
|
| +
|
| +
|
| +"""
|
| +Constants you might want to modify
|
| +-----------------------------------------------------------------------------
|
| +"""
|
| +
|
| +BLOCK_LEVEL_ELEMENTS = re.compile("^(p|div|h[1-6]|blockquote|pre|table|dl|ol|ul"
|
| + "|script|noscript|form|fieldset|iframe|math"
|
| + "|hr|hr/|style|li|dt|dd|thead|tbody"
|
| + "|tr|th|td|section|footer|header|group|figure"
|
| + "|figcaption|aside|article|canvas|output"
|
| + "|progress|video)$", re.IGNORECASE)
|
| +# Placeholders
|
| +STX = '\u0002' # Use STX ("Start of text") for start-of-placeholder
|
| +ETX = '\u0003' # Use ETX ("End of text") for end-of-placeholder
|
| +INLINE_PLACEHOLDER_PREFIX = STX+"klzzwxh:"
|
| +INLINE_PLACEHOLDER = INLINE_PLACEHOLDER_PREFIX + "%s" + ETX
|
| +INLINE_PLACEHOLDER_RE = re.compile(INLINE_PLACEHOLDER % r'([0-9]{4})')
|
| +AMP_SUBSTITUTE = STX+"amp"+ETX
|
| +
|
| +"""
|
| +Constants you probably do not need to change
|
| +-----------------------------------------------------------------------------
|
| +"""
|
| +
|
| +RTL_BIDI_RANGES = ( ('\u0590', '\u07FF'),
|
| + # Hebrew (0590-05FF), Arabic (0600-06FF),
|
| + # Syriac (0700-074F), Arabic supplement (0750-077F),
|
| + # Thaana (0780-07BF), Nko (07C0-07FF).
|
| + ('\u2D30', '\u2D7F'), # Tifinagh
|
| + )
|
| +
|
| +# Extensions should use "markdown.util.etree" instead of "etree" (or do `from
|
| +# markdown.util import etree`). Do not import it by yourself.
|
| +
|
| +try: # Is the C implemenation of ElementTree available?
|
| + import xml.etree.cElementTree as etree
|
| + from xml.etree.ElementTree import Comment
|
| + # Serializers (including ours) test with non-c Comment
|
| + etree.test_comment = Comment
|
| + if etree.VERSION < "1.0.5":
|
| + raise RuntimeError("cElementTree version 1.0.5 or higher is required.")
|
| +except (ImportError, RuntimeError):
|
| + # Use the Python implementation of ElementTree?
|
| + import xml.etree.ElementTree as etree
|
| + if etree.VERSION < "1.1":
|
| + raise RuntimeError("ElementTree version 1.1 or higher is required")
|
| +
|
| +
|
| +"""
|
| +AUXILIARY GLOBAL FUNCTIONS
|
| +=============================================================================
|
| +"""
|
| +
|
| +
|
| +def isBlockLevel(tag):
|
| + """Check if the tag is a block level HTML tag."""
|
| + if isinstance(tag, string_type):
|
| + return BLOCK_LEVEL_ELEMENTS.match(tag)
|
| + # Some ElementTree tags are not strings, so return False.
|
| + return False
|
| +
|
| +"""
|
| +MISC AUXILIARY CLASSES
|
| +=============================================================================
|
| +"""
|
| +
|
| +class AtomicString(text_type):
|
| + """A string which should not be further processed."""
|
| + pass
|
| +
|
| +
|
| +class Processor(object):
|
| + def __init__(self, markdown_instance=None):
|
| + if markdown_instance:
|
| + self.markdown = markdown_instance
|
| +
|
| +
|
| +class HtmlStash(object):
|
| + """
|
| + This class is used for stashing HTML objects that we extract
|
| + in the beginning and replace with place-holders.
|
| + """
|
| +
|
| + def __init__ (self):
|
| + """ Create a HtmlStash. """
|
| + self.html_counter = 0 # for counting inline html segments
|
| + self.rawHtmlBlocks=[]
|
| +
|
| + def store(self, html, safe=False):
|
| + """
|
| + Saves an HTML segment for later reinsertion. Returns a
|
| + placeholder string that needs to be inserted into the
|
| + document.
|
| +
|
| + Keyword arguments:
|
| +
|
| + * html: an html segment
|
| + * safe: label an html segment as safe for safemode
|
| +
|
| + Returns : a placeholder string
|
| +
|
| + """
|
| + self.rawHtmlBlocks.append((html, safe))
|
| + placeholder = self.get_placeholder(self.html_counter)
|
| + self.html_counter += 1
|
| + return placeholder
|
| +
|
| + def reset(self):
|
| + self.html_counter = 0
|
| + self.rawHtmlBlocks = []
|
| +
|
| + def get_placeholder(self, key):
|
| + return "%swzxhzdk:%d%s" % (STX, key, ETX)
|
| +
|
|
|