/usr/lib/python3/dist-packages/markdown/preprocessors.py is in python3-markdown 2.6.6-1.
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 | """
PRE-PROCESSORS
=============================================================================
Preprocessors work on source text before we start doing anything too
complicated.
"""
from __future__ import absolute_import
from __future__ import unicode_literals
from . import util
from . import odict
import re
def build_preprocessors(md_instance, **kwargs):
""" Build the default set of preprocessors used by Markdown. """
preprocessors = odict.OrderedDict()
preprocessors['normalize_whitespace'] = NormalizeWhitespace(md_instance)
if md_instance.safeMode != 'escape':
preprocessors["html_block"] = HtmlBlockPreprocessor(md_instance)
preprocessors["reference"] = ReferencePreprocessor(md_instance)
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 consistant 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.markdown.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."""
right_tag_patterns = ["</%s>", "%s>"]
attrs_pattern = r"""
\s+(?P<attr>[^>"'/= ]+)=(?P<q>['"])(?P<value>.*?)(?P=q) # attr="value"
| # OR
\s+(?P<attr1>[^>"'/= ]+)=(?P<value1>[^> ]+) # attr=value
| # OR
\s+(?P<attr2>[^>"'/= ]+) # attr
"""
left_tag_pattern = r'^\<(?P<tag>[^> ]+)(?P<attrs>(%s)*)\s*\/?\>?' % \
attrs_pattern
attrs_re = re.compile(attrs_pattern, re.VERBOSE)
left_tag_re = re.compile(left_tag_pattern, re.VERBOSE)
markdown_in_raw = False
def _get_left_tag(self, block):
m = self.left_tag_re.match(block)
if m:
tag = m.group('tag')
raw_attrs = m.group('attrs')
attrs = {}
if raw_attrs:
for ma in self.attrs_re.finditer(raw_attrs):
if ma.group('attr'):
if ma.group('value'):
attrs[ma.group('attr').strip()] = ma.group('value')
else:
attrs[ma.group('attr').strip()] = ""
elif ma.group('attr1'):
if ma.group('value1'):
attrs[ma.group('attr1').strip()] = ma.group(
'value1'
)
else:
attrs[ma.group('attr1').strip()] = ""
elif ma.group('attr2'):
attrs[ma.group('attr2').strip()] = ""
return tag, len(m.group(0)), attrs
else:
tag = block[1:].split(">", 1)[0].lower()
return tag, len(tag)+2, {}
def _recursive_tagfind(self, ltag, rtag, start_index, block):
while 1:
i = block.find(rtag, start_index)
if i == -1:
return -1
j = block.find(ltag, start_index)
# if no ltag, or rtag found before another ltag, return index
if (j > i or j == -1):
return i + len(rtag)
# another ltag found before rtag, use end of ltag as starting
# point and search again
j = block.find('>', j)
start_index = self._recursive_tagfind(ltag, rtag, j + 1, block)
if start_index == -1:
# HTML potentially malformed- ltag has no corresponding
# rtag
return -1
def _get_right_tag(self, left_tag, left_index, block):
for p in self.right_tag_patterns:
tag = p % left_tag
i = self._recursive_tagfind(
"<%s" % left_tag, tag, left_index, block
)
if i > 2:
return tag.lstrip("<").rstrip(">"), i
return block.rstrip()[-left_index:-1].lower(), len(block)
def _equal_tags(self, left_tag, right_tag):
if left_tag[0] in ['?', '@', '%']: # handle PHP, etc.
return True
if ("/" + left_tag) == right_tag:
return True
if (right_tag == "--" and left_tag == "--"):
return True
elif left_tag == right_tag[1:] and right_tag[0] == "/":
return True
else:
return False
def _is_oneliner(self, tag):
return (tag in ['hr', 'hr/'])
def _stringindex_to_listindex(self, stringindex, items):
"""
Same effect as concatenating the strings in items,
finding the character to which stringindex refers in that string,
and returning the index of the item in which that character resides.
"""
items.append('dummy')
i, count = 0, 0
while count <= stringindex:
count += len(items[i])
i += 1
return i - 1
def _nested_markdown_in_html(self, items):
"""Find and process html child elements of the given element block."""
for i, item in enumerate(items):
if self.left_tag_re.match(item):
left_tag, left_index, attrs = \
self._get_left_tag(''.join(items[i:]))
right_tag, data_index = self._get_right_tag(
left_tag, left_index, ''.join(items[i:]))
right_listindex = \
self._stringindex_to_listindex(data_index, items[i:]) + i
if 'markdown' in attrs.keys():
items[i] = items[i][left_index:] # remove opening tag
placeholder = self.markdown.htmlStash.store_tag(
left_tag, attrs, i + 1, right_listindex + 1)
items.insert(i, placeholder)
if len(items) - right_listindex <= 1: # last nest, no tail
right_listindex -= 1
items[right_listindex] = items[right_listindex][
:-len(right_tag) - 2] # remove closing tag
else: # raw html
if len(items) - right_listindex <= 1: # last element
right_listindex -= 1
if right_listindex <= i:
right_listindex = i + 1
placeholder = self.markdown.htmlStash.store('\n\n'.join(
items[i:right_listindex]))
del items[i:right_listindex]
items.insert(i, placeholder)
return items
def run(self, lines):
text = "\n".join(lines)
new_blocks = []
text = text.rsplit("\n\n")
items = []
left_tag = ''
right_tag = ''
in_tag = False # flag
while text:
block = text[0]
if block.startswith("\n"):
block = block[1:]
text = text[1:]
if block.startswith("\n"):
block = block[1:]
if not in_tag:
if block.startswith("<") and len(block.strip()) > 1:
if block[1:4] == "!--":
# is a comment block
left_tag, left_index, attrs = "--", 2, {}
else:
left_tag, left_index, attrs = self._get_left_tag(block)
right_tag, data_index = self._get_right_tag(left_tag,
left_index,
block)
# keep checking conditions below and maybe just append
if data_index < len(block) and (util.isBlockLevel(left_tag) or left_tag == '--'):
text.insert(0, block[data_index:])
block = block[:data_index]
if not (util.isBlockLevel(left_tag) or block[1] in ["!", "?", "@", "%"]):
new_blocks.append(block)
continue
if self._is_oneliner(left_tag):
new_blocks.append(block.strip())
continue
if block.rstrip().endswith(">") \
and self._equal_tags(left_tag, right_tag):
if self.markdown_in_raw and 'markdown' in attrs.keys():
block = block[left_index:-len(right_tag) - 2]
new_blocks.append(self.markdown.htmlStash.
store_tag(left_tag, attrs, 0, 2))
new_blocks.extend([block])
else:
new_blocks.append(
self.markdown.htmlStash.store(block.strip()))
continue
else:
# if is block level tag and is not complete
if (not self._equal_tags(left_tag, right_tag)) and \
(util.isBlockLevel(left_tag) or left_tag == "--"):
items.append(block.strip())
in_tag = True
else:
new_blocks.append(
self.markdown.htmlStash.store(block.strip())
)
continue
else:
new_blocks.append(block)
else:
items.append(block)
right_tag, data_index = self._get_right_tag(left_tag, 0, block)
if self._equal_tags(left_tag, right_tag):
# if find closing tag
if data_index < len(block):
# we have more text after right_tag
items[-1] = block[:data_index]
text.insert(0, block[data_index:])
in_tag = False
if self.markdown_in_raw and 'markdown' in attrs.keys():
items[0] = items[0][left_index:]
items[-1] = items[-1][:-len(right_tag) - 2]
if items[len(items) - 1]: # not a newline/empty string
right_index = len(items) + 3
else:
right_index = len(items) + 2
new_blocks.append(self.markdown.htmlStash.store_tag(
left_tag, attrs, 0, right_index))
placeholderslen = len(self.markdown.htmlStash.tag_data)
new_blocks.extend(
self._nested_markdown_in_html(items))
nests = len(self.markdown.htmlStash.tag_data) - \
placeholderslen
self.markdown.htmlStash.tag_data[-1 - nests][
'right_index'] += nests - 2
else:
new_blocks.append(
self.markdown.htmlStash.store('\n\n'.join(items)))
items = []
if items:
if self.markdown_in_raw and 'markdown' in attrs.keys():
items[0] = items[0][left_index:]
items[-1] = items[-1][:-len(right_tag) - 2]
if items[len(items) - 1]: # not a newline/empty string
right_index = len(items) + 3
else:
right_index = len(items) + 2
new_blocks.append(
self.markdown.htmlStash.store_tag(
left_tag, attrs, 0, right_index))
placeholderslen = len(self.markdown.htmlStash.tag_data)
new_blocks.extend(self._nested_markdown_in_html(items))
nests = len(self.markdown.htmlStash.tag_data) - placeholderslen
self.markdown.htmlStash.tag_data[-1 - nests][
'right_index'] += nests - 2
else:
new_blocks.append(
self.markdown.htmlStash.store('\n\n'.join(items)))
new_blocks.append('\n')
new_text = "\n\n".join(new_blocks)
return new_text.split("\n")
class ReferencePreprocessor(Preprocessor):
""" Remove reference definitions from text and store for later use. """
TITLE = r'[ ]*(\"(.*)\"|\'(.*)\'|\((.*)\))[ ]*'
RE = re.compile(
r'^[ ]{0,3}\[([^\]]*)\]:\s*([^ ]*)[ ]*(%s)?$' % TITLE, re.DOTALL
)
TITLE_RE = re.compile(r'^%s$' % TITLE)
def run(self, lines):
new_text = []
while lines:
line = lines.pop(0)
m = self.RE.match(line)
if m:
id = m.group(1).strip().lower()
link = m.group(2).lstrip('<').rstrip('>')
t = m.group(5) or m.group(6) or m.group(7)
if not t:
# Check next line for title
tm = self.TITLE_RE.match(lines[0])
if tm:
lines.pop(0)
t = tm.group(2) or tm.group(3) or tm.group(4)
self.markdown.references[id] = (link, t)
else:
new_text.append(line)
return new_text # + "\n"
|