# 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

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)

    def _detect_renderer(self, source, filename=None):

        """

        runs detection of what renderer should be used for generating html

        from a markup language

        filename can be also explicitly a renderer name

        :param source:

        :param filename:

        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 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" style="margin-top:-1000px;color:red" src="http://example.com/test.jpg"></p>'

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

        u'<p><img class="c d" src="file://localhost/test.jpg"></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 onclick="alert(2)">yo</div>'

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

        u'<p><a href="javascript:alert(3)">yo</a></p>'

        """

        source = safe_unicode(source)

        try:

            if flavored:

                source = cls._flavored_markdown(source)

        except Exception:

            log.error(traceback.format_exc())

            if safe:

                log.debug('Falling back to render in plain mode')

                return cls.plain(source)

            else:

                raise

    @classmethod

    def rst(cls, source, safe=True):

        source = safe_unicode(source)

        try:

            from docutils.core import publish_parts

            from docutils.parsers.rst import directives

            docutils_settings = dict([(alias, None) for alias in

                                cls.RESTRUCTUREDTEXT_DISALLOWED_DIRECTIVES])

            docutils_settings.update({'input_encoding': 'unicode',

                                      'report_level': 4})

            for k, v in docutils_settings.iteritems():

                directives.register_directive(k, v)

            parts = publish_parts(source=source,