/usr/share/pyshared/markdown/treeprocessors.py is in python-markdown 2.1.1-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 | import re
import inlinepatterns
import util
import odict
def build_treeprocessors(md_instance, **kwargs):
""" Build the default treeprocessors for Markdown. """
treeprocessors = odict.OrderedDict()
treeprocessors["inline"] = InlineProcessor(md_instance)
treeprocessors["prettify"] = PrettifyTreeprocessor(md_instance)
return treeprocessors
def isString(s):
""" Check if it's string """
if not isinstance(s, util.AtomicString):
return isinstance(s, basestring)
return False
class Processor:
def __init__(self, markdown_instance=None):
if markdown_instance:
self.markdown = markdown_instance
class Treeprocessor(Processor):
"""
Treeprocessors are run on the ElementTree object before serialization.
Each Treeprocessor implements a "run" method that takes a pointer to an
ElementTree, modifies it as necessary and returns an ElementTree
object.
Treeprocessors must extend markdown.Treeprocessor.
"""
def run(self, root):
"""
Subclasses of Treeprocessor should implement a `run` method, which
takes a root ElementTree. This method can return another ElementTree
object, and the existing root ElementTree will be replaced, or it can
modify the current tree and return None.
"""
pass
class InlineProcessor(Treeprocessor):
"""
A Treeprocessor that traverses a tree, applying inline patterns.
"""
def __init__(self, md):
self.__placeholder_prefix = util.INLINE_PLACEHOLDER_PREFIX
self.__placeholder_suffix = util.ETX
self.__placeholder_length = 4 + len(self.__placeholder_prefix) \
+ len(self.__placeholder_suffix)
self.__placeholder_re = util.INLINE_PLACEHOLDER_RE
self.markdown = md
def __makePlaceholder(self, type):
""" Generate a placeholder """
id = "%04d" % len(self.stashed_nodes)
hash = util.INLINE_PLACEHOLDER % id
return hash, id
def __findPlaceholder(self, data, index):
"""
Extract id from data string, start from index
Keyword arguments:
* data: string
* index: index, from which we start search
Returns: placeholder id and string index, after the found placeholder.
"""
m = self.__placeholder_re.search(data, index)
if m:
return m.group(1), m.end()
else:
return None, index + 1
def __stashNode(self, node, type):
""" Add node to stash """
placeholder, id = self.__makePlaceholder(type)
self.stashed_nodes[id] = node
return placeholder
def __handleInline(self, data, patternIndex=0):
"""
Process string with inline patterns and replace it
with placeholders
Keyword arguments:
* data: A line of Markdown text
* patternIndex: The index of the inlinePattern to start with
Returns: String with placeholders.
"""
if not isinstance(data, util.AtomicString):
startIndex = 0
while patternIndex < len(self.markdown.inlinePatterns):
data, matched, startIndex = self.__applyPattern(
self.markdown.inlinePatterns.value_for_index(patternIndex),
data, patternIndex, startIndex)
if not matched:
patternIndex += 1
return data
def __processElementText(self, node, subnode, isText=True):
"""
Process placeholders in Element.text or Element.tail
of Elements popped from self.stashed_nodes.
Keywords arguments:
* node: parent node
* subnode: processing node
* isText: bool variable, True - it's text, False - it's tail
Returns: None
"""
if isText:
text = subnode.text
subnode.text = None
else:
text = subnode.tail
subnode.tail = None
childResult = self.__processPlaceholders(text, subnode)
if not isText and node is not subnode:
pos = node.getchildren().index(subnode)
node.remove(subnode)
else:
pos = 0
childResult.reverse()
for newChild in childResult:
node.insert(pos, newChild)
def __processPlaceholders(self, data, parent):
"""
Process string with placeholders and generate ElementTree tree.
Keyword arguments:
* data: string with placeholders instead of ElementTree elements.
* parent: Element, which contains processing inline data
Returns: list with ElementTree elements with applied inline patterns.
"""
def linkText(text):
if text:
if result:
if result[-1].tail:
result[-1].tail += text
else:
result[-1].tail = text
else:
if parent.text:
parent.text += text
else:
parent.text = text
result = []
strartIndex = 0
while data:
index = data.find(self.__placeholder_prefix, strartIndex)
if index != -1:
id, phEndIndex = self.__findPlaceholder(data, index)
if id in self.stashed_nodes:
node = self.stashed_nodes.get(id)
if index > 0:
text = data[strartIndex:index]
linkText(text)
if not isString(node): # it's Element
for child in [node] + node.getchildren():
if child.tail:
if child.tail.strip():
self.__processElementText(node, child,False)
if child.text:
if child.text.strip():
self.__processElementText(child, child)
else: # it's just a string
linkText(node)
strartIndex = phEndIndex
continue
strartIndex = phEndIndex
result.append(node)
else: # wrong placeholder
end = index + len(self.__placeholder_prefix)
linkText(data[strartIndex:end])
strartIndex = end
else:
text = data[strartIndex:]
if isinstance(data, util.AtomicString):
# We don't want to loose the AtomicString
text = util.AtomicString(text)
linkText(text)
data = ""
return result
def __applyPattern(self, pattern, data, patternIndex, startIndex=0):
"""
Check if the line fits the pattern, create the necessary
elements, add it to stashed_nodes.
Keyword arguments:
* data: the text to be processed
* pattern: the pattern to be checked
* patternIndex: index of current pattern
* startIndex: string index, from which we start searching
Returns: String with placeholders instead of ElementTree elements.
"""
match = pattern.getCompiledRegExp().match(data[startIndex:])
leftData = data[:startIndex]
if not match:
return data, False, 0
node = pattern.handleMatch(match)
if node is None:
return data, True, len(leftData)+match.span(len(match.groups()))[0]
if not isString(node):
if not isinstance(node.text, util.AtomicString):
# We need to process current node too
for child in [node] + node.getchildren():
if not isString(node):
if child.text:
child.text = self.__handleInline(child.text,
patternIndex + 1)
if child.tail:
child.tail = self.__handleInline(child.tail,
patternIndex)
placeholder = self.__stashNode(node, pattern.type())
return "%s%s%s%s" % (leftData,
match.group(1),
placeholder, match.groups()[-1]), True, 0
def run(self, tree):
"""Apply inline patterns to a parsed Markdown tree.
Iterate over ElementTree, find elements with inline tag, apply inline
patterns and append newly created Elements to tree. If you don't
want to process your data with inline paterns, instead of normal string,
use subclass AtomicString:
node.text = markdown.AtomicString("This will not be processed.")
Arguments:
* tree: ElementTree object, representing Markdown tree.
Returns: ElementTree object with applied inline patterns.
"""
self.stashed_nodes = {}
stack = [tree]
while stack:
currElement = stack.pop()
insertQueue = []
for child in currElement.getchildren():
if child.text and not isinstance(child.text, util.AtomicString):
text = child.text
child.text = None
lst = self.__processPlaceholders(self.__handleInline(
text), child)
stack += lst
insertQueue.append((child, lst))
if child.tail:
tail = self.__handleInline(child.tail)
dumby = util.etree.Element('d')
tailResult = self.__processPlaceholders(tail, dumby)
if dumby.text:
child.tail = dumby.text
else:
child.tail = None
pos = currElement.getchildren().index(child) + 1
tailResult.reverse()
for newChild in tailResult:
currElement.insert(pos, newChild)
if child.getchildren():
stack.append(child)
if self.markdown.enable_attributes:
for element, lst in insertQueue:
if element.text:
element.text = \
inlinepatterns.handleAttributes(element.text,
element)
i = 0
for newChild in lst:
# Processing attributes
if newChild.tail:
newChild.tail = \
inlinepatterns.handleAttributes(newChild.tail,
element)
if newChild.text:
newChild.text = \
inlinepatterns.handleAttributes(newChild.text,
newChild)
element.insert(i, newChild)
i += 1
return tree
class PrettifyTreeprocessor(Treeprocessor):
""" Add linebreaks to the html document. """
def _prettifyETree(self, elem):
""" Recursively add linebreaks to ElementTree children. """
i = "\n"
if util.isBlockLevel(elem.tag) and elem.tag not in ['code', 'pre']:
if (not elem.text or not elem.text.strip()) \
and len(elem) and util.isBlockLevel(elem[0].tag):
elem.text = i
for e in elem:
if util.isBlockLevel(e.tag):
self._prettifyETree(e)
if not elem.tail or not elem.tail.strip():
elem.tail = i
if not elem.tail or not elem.tail.strip():
elem.tail = i
def run(self, root):
""" Add linebreaks to ElementTree root object. """
self._prettifyETree(root)
# Do <br />'s seperately as they are often in the middle of
# inline content and missed by _prettifyETree.
brs = root.getiterator('br')
for br in brs:
if not br.tail or not br.tail.strip():
br.tail = '\n'
else:
br.tail = '\n%s' % br.tail
|