This file is indexed.

/usr/share/pyshared/markdown/preprocessors.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
"""
PRE-PROCESSORS
=============================================================================

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

import re
import util
import odict


def build_preprocessors(md_instance, **kwargs):
    """ Build the default set of preprocessors used by Markdown. """
    preprocessors = odict.OrderedDict()
    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


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 run(self, lines):
        text = "\n".join(lines)
        new_blocks = []
        text = text.split("\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] == "!":
                        # 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():
                            start = re.sub(r'\smarkdown(=[\'"]?[^> ]*[\'"]?)?', 
                                           '', block[:left_index])
                            end = block[-len(right_tag)-2:]
                            block = block[left_index:-len(right_tag)-2]
                            new_blocks.append(
                                self.markdown.htmlStash.store(start))
                            new_blocks.append(block)
                            new_blocks.append(
                                self.markdown.htmlStash.store(end))
                        else:
                            new_blocks.append(
                                self.markdown.htmlStash.store(block.strip()))
                        continue
                    else: 
                        # if is block level tag and is not complete

                        if util.isBlockLevel(left_tag) or left_tag == "--" \
                            and not block.rstrip().endswith(">"):
                            items.append(block.strip())
                            in_tag = True
                        else:
                            new_blocks.append(
                            self.markdown.htmlStash.store(block.strip()))

                        continue

                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():
                        start = re.sub(r'\smarkdown(=[\'"]?[^> ]*[\'"]?)?', 
                                       '', items[0][:left_index])
                        items[0] = items[0][left_index:]
                        end = items[-1][-len(right_tag)-2:]
                        items[-1] = items[-1][:-len(right_tag)-2]
                        new_blocks.append(
                            self.markdown.htmlStash.store(start))
                        new_blocks.extend(items)
                        new_blocks.append(
                            self.markdown.htmlStash.store(end))
                    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():
                start = re.sub(r'\smarkdown(=[\'"]?[^> ]*[\'"]?)?', 
                               '', items[0][:left_index])
                items[0] = items[0][left_index:]
                end = items[-1][-len(right_tag)-2:]
                items[-1] = items[-1][:-len(right_tag)-2]
                new_blocks.append(
                    self.markdown.htmlStash.store(start))
                new_blocks.extend(items)
                if end.strip():
                    new_blocks.append(
                        self.markdown.htmlStash.store(end))
            else:
                new_blocks.append(
                    self.markdown.htmlStash.store('\n\n'.join(items)))
            #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. """

    RE = re.compile(r'^(\ ?\ ?\ ?)\[([^\]]*)\]:\s*([^ ]*)(.*)$', re.DOTALL)

    def run (self, lines):
        new_text = [];
        for line in lines:
            m = self.RE.match(line)
            if m:
                id = m.group(2).strip().lower()
                link = m.group(3).lstrip('<').rstrip('>')
                t = m.group(4).strip()  # potential title
                if not t:
                    self.markdown.references[id] = (link, t)
                elif (len(t) >= 2
                      and (t[0] == t[-1] == "\""
                           or t[0] == t[-1] == "\'"
                           or (t[0] == "(" and t[-1] == ")") ) ):
                    self.markdown.references[id] = (link, t[1:-1])
                else:
                    new_text.append(line)
            else:
                new_text.append(line)

        return new_text #+ "\n"