# -*- coding: utf-8 -*-

# This program is free software: you can redistribute it and/or modify

# it under the terms of the GNU General Public License as published by

# 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.diffs

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

Set of diffing helpers, previously part of vcs

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: Dec 4, 2011

:author: marcink

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

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

"""

import difflib

import logging

import re

from tg.i18n import ugettext as _

from kallithea.lib import webutils

from kallithea.lib.utils2 import safe_str

from kallithea.lib.vcs.backends.base import EmptyChangeset

from kallithea.lib.vcs.exceptions import VCSError

from kallithea.lib.vcs.nodes import FileNode, SubModuleNode

log = logging.getLogger(__name__)

def _safe_id(idstring):

    r"""Make a string safe for including in an id attribute.

    The HTML spec says that id attributes 'must begin with

    a letter ([A-Za-z]) and may be followed by any number

    of letters, digits ([0-9]), hyphens ("-"), underscores

    ("_"), colons (":"), and periods (".")'. These regexps

    are slightly over-zealous, in that they remove colons

    and periods unnecessarily.

    Whitespace is transformed into underscores, and then

    anything which is not a hyphen or a character that

    matches \w (alphanumerics and underscore) is removed.

    """

    # Transform all whitespace to underscore

    idstring = re.sub(r'\s', "_", idstring)

    # Remove everything that is not a hyphen or a member of \w

    idstring = re.sub(r'(?!-)\W', "", idstring).lower()

    return idstring

            old_lineno_class='lineno old', new_lineno_class='lineno new',

            no_lineno_class='lineno',

    """

    Return given diff as html table with customized css classes

    """

    _html_empty = True

    _html = []

    _html.append('''<table class="%(table_class)s">\n''' % {

        'table_class': table_class

    })

    for file_info in parsed_lines:

        count_no_lineno = 0  # counter to allow comments on lines without new/old line numbers

        for chunk in file_info['chunks']:

            _html_empty = False

            for change in chunk:

                _html.append('''<tr class="%(lc)s %(action)s">\n''' % {

                    'lc': line_class,

                    'action': change['action']

                })

                if change['old_lineno'] or change['new_lineno']:

                    ###########################################################

                    # OLD LINE NUMBER

                    ###########################################################

                    anchor_old = "%(filename)s_o%(oldline_no)s" % {

                        'filename': _safe_id(file_info['filename']),

                        'oldline_no': change['old_lineno']

                    }

                    anchor_old_id = ''

                    if change['old_lineno']:

                        anchor_old_id = 'id="%s"' % anchor_old

                    _html.append('''\t<td %(a_id)s class="%(olc)s">''' % {

                        'a_id': anchor_old_id,

                        'olc': old_lineno_class,

                    })

                    _html.append('''<a href="%(url)s" data-pseudo-content="%(label)s"></a>''' % {

                        'label': change['old_lineno'],

                        'url': '#%s' % anchor_old,

                    })

                    _html.append('''</td>\n''')

                    ###########################################################

                    # NEW LINE NUMBER

                    ###########################################################

                    anchor_new = "%(filename)s_n%(newline_no)s" % {

                        'filename': _safe_id(file_info['filename']),

                        'newline_no': change['new_lineno']

                    }

                    anchor_new_id = ''

                    if change['new_lineno']:

                        anchor_new_id = 'id="%s"' % anchor_new

                    _html.append('''\t<td %(a_id)s class="%(nlc)s">''' % {

                        'a_id': anchor_new_id,

                        'nlc': new_lineno_class

                    })

                    _html.append('''<a href="%(url)s" data-pseudo-content="%(label)s"></a>''' % {

                        'label': change['new_lineno'],

                        'url': '#%s' % anchor_new,

                    })

                    _html.append('''</td>\n''')

                else:

                    ###########################################################

                    # NO LINE NUMBER

                    ###########################################################

                    anchor = "%(filename)s_%(count_no_lineno)s" % {

                        'filename': _safe_id(file_info['filename']),

                        'count_no_lineno': count_no_lineno,

                    }

                    count_no_lineno += 1

                    _html.append('''\t<td id="%(anchor)s" class="%(olc)s" colspan="2">''' % {

                        'anchor': anchor,

                        'olc': no_lineno_class,

                    })

                    _html.append('''</td>\n''')

                ###########################################################

                # CODE

                ###########################################################

                _html.append('''\t<td class="%(cc)s">''' % {

                    'cc': code_class,

                })

                _html.append('''\n\t\t<div class="add-bubble"><div>&nbsp;</div></div><pre>%(code)s</pre>\n''' % {

                    'code': change['line']

                })

                _html.append('''\t</td>''')

                _html.append('''\n</tr>\n''')

    _html.append('''</table>''')

    if _html_empty:

        return None

    return ''.join(_html)

def wrap_to_table(html):

    """Given a string with html, return it wrapped in a table, similar to what

    as_html returns."""

    return '''\

              <table class="code-difftable">

                <tr class="line">

                <td class="lineno new"></td>

                <td class="code"><pre>%s</pre></td>

                </tr>

              </table>''' % html

def html_diff(filenode_old, filenode_new, diff_limit=None,

                ignore_whitespace=True, line_context=3):

    """

    Returns a file diff as HTML wrapped into a table.

    Checks for diff_limit and presents a message if the diff is too big.

    """

    if filenode_old is None:

        filenode_old = FileNode(filenode_new.path, '', EmptyChangeset())

    op = None

    a_path = filenode_old.path # default, might be overriden by actual rename in diff

    if filenode_old.is_binary or filenode_new.is_binary:

        html_diff = wrap_to_table(_('Binary file'))

        stats = (0, 0)

    elif diff_limit != -1 and (

            diff_limit is None or

            (filenode_old.size < diff_limit and filenode_new.size < diff_limit)):

        raw_diff = get_gitdiff(filenode_old, filenode_new,

                                ignore_whitespace=ignore_whitespace,

                                context=line_context)

        diff_processor = DiffProcessor(raw_diff)

        if diff_processor.parsed: # there should be exactly one element, for the specified file

            f = diff_processor.parsed[0]

            op = f['operation']

            a_path = f['old_filename']

        html_diff = as_html(parsed_lines=diff_processor.parsed)

        stats = diff_processor.stat()

    else:

        html_diff = wrap_to_table(_('Changeset was too big and was cut off, use '

                               'diff menu to display this diff'))

        stats = (0, 0)

    if not html_diff:

        submodules = [o for o in [filenode_new, filenode_old] if isinstance(o, SubModuleNode)]

        if submodules:

            html_diff = wrap_to_table(webutils.escape('Submodule %r' % submodules[0]))

        else:

            html_diff = wrap_to_table(_('No changes detected'))

    cs1 = filenode_old.changeset.raw_id

    cs2 = filenode_new.changeset.raw_id

    return cs1, cs2, a_path, html_diff, stats, op

def get_gitdiff(filenode_old, filenode_new, ignore_whitespace=True, context=3):

    """

    Returns git style diff between given ``filenode_old`` and ``filenode_new``.

    """

    # make sure we pass in default context

    context = context or 3

    submodules = [o for o in [filenode_new, filenode_old] if isinstance(o, SubModuleNode)]

    if submodules:

        return b''

    for filenode in (filenode_old, filenode_new):

        if not isinstance(filenode, FileNode):

            raise VCSError("Given object should be FileNode object, not %s"

                % filenode.__class__)

    repo = filenode_new.changeset.repository

    old_raw_id = getattr(filenode_old.changeset, 'raw_id', repo.EMPTY_CHANGESET)

    new_raw_id = getattr(filenode_new.changeset, 'raw_id', repo.EMPTY_CHANGESET)

    vcs_gitdiff = get_diff(repo, old_raw_id, new_raw_id, filenode_new.path,

                           ignore_whitespace, context)

    return vcs_gitdiff

def get_diff(scm_instance, rev1, rev2, path=None, ignore_whitespace=False, context=3):

    """

    A thin wrapper around vcs lib get_diff.

    """

    try:

        return scm_instance.get_diff(rev1, rev2, path=path,

                                     ignore_whitespace=ignore_whitespace, context=context)

    except MemoryError:

        webutils.flash('MemoryError: Diff is too big', category='error')

        return b''

NEW_FILENODE = 1

DEL_FILENODE = 2

MOD_FILENODE = 3

RENAMED_FILENODE = 4

COPIED_FILENODE = 5

CHMOD_FILENODE = 6