# the Free Software Foundation, either version 3 of the License, or

# (at your option) any later version.

#

# This program is distributed in the hope that it will be useful,

# but WITHOUT ANY WARRANTY; without even the implied warranty of

# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

# GNU General Public License for more details.

#

# You should have received a copy of the GNU General Public License

# along with this program.  If not, see <http://www.gnu.org/licenses/>.

"""

kallithea.lib.markup_renderer

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Renderer for markup languages with ability to parse using rst or markdown

This file was forked by the Kallithea project in July 2014.

Original author and date, and relevant copyright and licensing information is below:

:created_on: Oct 27, 2011

:author: marcink

:copyright: (c) 2013 RhodeCode GmbH, and others.

:license: GPLv3, see LICENSE.md for more details.

"""

import re

import logging

import traceback

import markdown as markdown_mod

import bleach

from kallithea.lib.utils2 import safe_unicode, MENTIONS_REGEX

log = logging.getLogger(__name__)

url_re = re.compile(r'''\bhttps?://(?:[\da-zA-Z0-9@:.-]+)'''

                    r'''(?:[/a-zA-Z0-9_=@#~&+%.,:;?!*()-]*[/a-zA-Z0-9_=@#~])?''')

class MarkupRenderer(object):

    RESTRUCTUREDTEXT_DISALLOWED_DIRECTIVES = ['include', 'meta', 'raw']

    MARKDOWN_PAT = re.compile(r'md|mkdn?|mdown|markdown', re.IGNORECASE)

    RST_PAT = re.compile(r're?st', re.IGNORECASE)

    PLAIN_PAT = re.compile(r'readme', re.IGNORECASE)

        """

        runs detection of what renderer should be used for generating html

        from a markup language

        filename can be also explicitly a renderer name

        """

    @classmethod

    def _flavored_markdown(cls, text):

        """

        Github style flavored markdown

        :param text:

        """

        from hashlib import md5

        # Extract pre blocks.

        extractions = {}

        def pre_extraction_callback(matchobj):

            digest = md5(matchobj.group(0)).hexdigest()

            extractions[digest] = matchobj.group(0)

            return "{gfm-extraction-%s}" % digest

        pattern = re.compile(r'<pre>.*?</pre>', re.MULTILINE | re.DOTALL)

        text = re.sub(pattern, pre_extraction_callback, text)

        # Prevent foo_bar_baz from ending up with an italic word in the middle.

        def italic_callback(matchobj):

            s = matchobj.group(0)

            if list(s).count('_') >= 2:

                return s.replace('_', '\_')

            return s

        text = re.sub(r'^(?! {4}|\t)\w+_\w+_\w[\w_]*', italic_callback, text)

        # In very clear cases, let newlines become <br /> tags.

        def newline_callback(matchobj):

            if len(matchobj.group(1)) == 1:

                return matchobj.group(0).rstrip() + '  \n'

            else:

                return matchobj.group(0)

        pattern = re.compile(r'^[\w\<][^\n]*(\n+)', re.MULTILINE)

        text = re.sub(pattern, newline_callback, text)

        # Insert pre block extractions.

        def pre_insert_callback(matchobj):

            return '\n\n' + extractions[matchobj.group(1)]

        text = re.sub(r'{gfm-extraction-([0-9a-f]{32})\}',

                      pre_insert_callback, text)

        return text

        """

        Renders a given filename using detected renderer

        it detects renderers based on file extension or mimetype.

        At last it will just do a simple html replacing new lines with <br/>

        """

        readme_data = renderer(source)

        # Allow most HTML, while preventing XSS issues:

        # no <script> tags, no onclick attributes, no javascript

        # "protocol", and also limit styling to prevent defacing.

        return bleach.clean(readme_data,

            tags=['a', 'abbr', 'b', 'blockquote', 'br', 'code', 'dd',

                  'div', 'dl', 'dt', 'em', 'h1', 'h2', 'h3', 'h4', 'h5',

                  'h6', 'hr', 'i', 'img', 'li', 'ol', 'p', 'pre', 'span',

                  'strong', 'sub', 'sup', 'table', 'tbody', 'td', 'th',

                  'thead', 'tr', 'ul'],

            attributes=['class', 'id', 'style', 'label', 'title', 'alt', 'href', 'src'],

            styles=['color'],

            protocols=['http', 'https', 'mailto'],

            )

    @classmethod

    def plain(cls, source, universal_newline=True):

        source = safe_unicode(source)

        if universal_newline:

            newline = '\n'

            source = newline.join(source.splitlines())

        def url_func(match_obj):

            url_full = match_obj.group(0)

            return '<a href="%(url)s">%(url)s</a>' % ({'url': url_full})

        source = url_re.sub(url_func, source)

        return '<br />' + source.replace("\n", '<br />')

    @classmethod

    def markdown(cls, source, safe=True, flavored=False):

        """

        Convert Markdown (possibly GitHub Flavored) to XSS safe HTML, possibly

        with "safe" fall-back to plaintext.

        >>> MarkupRenderer.markdown('''<img id="a" style="margin-top:-1000px;color:red" src="http://example.com/test.jpg">''')

        u'<p><img id="a" src="http://example.com/test.jpg" style="color: red;"></p>'

        >>> MarkupRenderer.markdown('''<img class="c d" src="file://localhost/test.jpg">''')

        u'<p><img class="c d"></p>'

        >>> MarkupRenderer.markdown('''<a href="foo">foo</a>''')

        u'<p><a href="foo">foo</a></p>'

        >>> MarkupRenderer.markdown('''<script>alert(1)</script>''')

        u'<script>alert(1)</script>'

        >>> MarkupRenderer.markdown('''<div onclick="alert(2)">yo</div>''')

        u'<div>yo</div>'

        >>> MarkupRenderer.markdown('''<a href="javascript:alert(3)">yo</a>''')

        u'<p><a>yo</a></p>'

        """

        source = safe_unicode(source)