"""

        if line['action'] == 'del':

            old, new = line, next_

        else:

            old, new = next_, line

        oldwords = self._token_re.split(old['line'])

        newwords = self._token_re.split(new['line'])

        sequence = difflib.SequenceMatcher(None, oldwords, newwords)

        oldfragments, newfragments = [], []

        for tag, i1, i2, j1, j2 in sequence.get_opcodes():

            oldfrag = ''.join(oldwords[i1:i2])

            newfrag = ''.join(newwords[j1:j2])

            if tag != 'equal':

                if oldfrag:

                    oldfrag = '<del>%s</del>' % oldfrag

                if newfrag:

                    newfrag = '<ins>%s</ins>' % newfrag

            oldfragments.append(oldfrag)

            newfragments.append(newfrag)

        old['line'] = "".join(oldfragments)

        new['line'] = "".join(newfragments)

    def _highlight_line_udiff(self, line, next_):

        """

        Highlight inline changes in both lines.

        """

        start = 0

        limit = min(len(line['line']), len(next_['line']))

        while start < limit and line['line'][start] == next_['line'][start]:

            start += 1

        end = -1

        limit -= start

        while -end <= limit and line['line'][end] == next_['line'][end]:

            end -= 1

        end += 1

        if start or end:

            def do(l):

                last = end + len(l['line'])

                if l['action'] == 'add':

                    tag = 'ins'

                else:

                    tag = 'del'

                l['line'] = '%s<%s>%s</%s>%s' % (

                    l['line'][:start],

                    tag,

                    l['line'][start:last],

                    tag,

                    l['line'][last:]

                )

            do(line)

            do(next_)

    def _get_header(self, diff_chunk):

        """

        parses the diff header, and returns parts, and leftover diff

        parts consists of 14 elements::

            a_path, b_path, similarity_index, rename_from, rename_to,

            old_mode, new_mode, new_file_mode, deleted_file_mode,

            a_blob_id, b_blob_id, b_mode, a_file, b_file

        :param diff_chunk:

        """

        if self.vcs == 'git':

            match = self._git_header_re.match(diff_chunk)

            diff = diff_chunk[match.end():]

            return match.groupdict(), imap(self._escaper, diff.splitlines(1))

        elif self.vcs == 'hg':

            match = self._hg_header_re.match(diff_chunk)

            diff = diff_chunk[match.end():]

            return match.groupdict(), imap(self._escaper, diff.splitlines(1))

        else:

            raise Exception('VCS type %s is not supported' % self.vcs)

    def _clean_line(self, line, command):

        if command in ['+', '-', ' ']:

            #only modify the line if it's actually a diff thing

            line = line[1:]

        return line

    def _parse_gitdiff(self, inline_diff=True):

        _files = []

        diff_container = lambda arg: arg

        ##split the diff in chunks of separate --git a/file b/file chunks

        for raw_diff in ('\n' + self._diff).split('\ndiff --git')[1:]:

            head, diff = self._get_header(raw_diff)

            op = None

            stats = {

                'added': 0,

                'deleted': 0,

                'binary': False,

                'ops': {},

            }

            if head['deleted_file_mode']:

                op = 'D'

                stats['binary'] = True

                stats['ops'][DEL_FILENODE] = 'deleted file'

            elif head['new_file_mode']:

                op = 'A'

                stats['binary'] = True

                stats['ops'][NEW_FILENODE] = 'new file %s' % head['new_file_mode']

            else:  # modify operation, can be cp, rename, chmod

                # CHMOD

                if head['new_mode'] and head['old_mode']:

                    op = 'M'

                    stats['binary'] = True

                    stats['ops'][CHMOD_FILENODE] = ('modified file chmod %s => %s'

                                        % (head['old_mode'], head['new_mode']))

                # RENAME

                if (head['rename_from'] and head['rename_to']

                      and head['rename_from'] != head['rename_to']):

                    op = 'M'

                    stats['binary'] = True

                    stats['ops'][RENAMED_FILENODE] = ('file renamed from %s to %s'

                                    % (head['rename_from'], head['rename_to']))

                # COPY

                if head.get('copy_from') and head.get('copy_to'):

                    op = 'M'

                    stats['binary'] = True

                    stats['ops'][COPIED_FILENODE] = ('file copied from %s to %s'

                                        % (head['copy_from'], head['copy_to']))

                # FALL BACK: detect missed old style add or remove

                if op is None:

                    if not head['a_file'] and head['b_file']:

                        op = 'A'

                        stats['binary'] = True

                        stats['ops'][NEW_FILENODE] = 'new file'

                    elif head['a_file'] and not head['b_file']:

                        op = 'D'

                        stats['binary'] = True

                        stats['ops'][DEL_FILENODE] = 'deleted file'

                # it's not ADD not DELETE

                if op is None:

                    op = 'M'

                    stats['binary'] = True

                    stats['ops'][MOD_FILENODE] = 'modified file'

            # a real non-binary diff

            if head['a_file'] or head['b_file']:

                try:

                    chunks, _stats = self._parse_lines(diff)

                    stats['binary'] = False

                    stats['added'] = _stats[0]

                    stats['deleted'] = _stats[1]

                    # explicit mark that it's a modified file

                    if op == 'M':

                        stats['ops'][MOD_FILENODE] = 'modified file'

                except DiffLimitExceeded:

                    diff_container = lambda _diff: \

                        LimitedDiffContainer(self.diff_limit,

                                            self.cur_diff_size, _diff)

                    break

            else:  # GIT binary patch (or empty diff)

                # GIT Binary patch

                if head['bin_patch']:

                    stats['ops'][BIN_FILENODE] = 'binary diff not shown'

                chunks = []

            if op == 'D' and chunks:

                # a way of seeing deleted content could perhaps be nice - but

                # not with the current UI

                chunks = []

            chunks.insert(0, [{

                'old_lineno': '',

                'new_lineno': '',

                'action':     'context',

                'line':       msg,

                } for _op, msg in stats['ops'].iteritems()

                  if _op not in [MOD_FILENODE]])

            _files.append({

                'filename':         head['b_path'],

                'old_revision':     head['a_blob_id'],

                'new_revision':     head['b_blob_id'],

                'chunks':           chunks,

                'operation':        op,

                'stats':            stats,

            })

        if not inline_diff:

        # highlight inline changes

        for diff_data in _files:

            for chunk in diff_data['chunks']:

                lineiter = iter(chunk)

                try:

                    while 1:

                        line = lineiter.next()

                        if line['action'] not in ['unmod', 'context']:

                            nextline = lineiter.next()

                            if nextline['action'] in ['unmod', 'context'] or \

                               nextline['action'] == line['action']:

                                continue

                            self.differ(line, nextline)

                except StopIteration:

                    pass

    def _parse_udiff(self, inline_diff=True):

        raise NotImplementedError()

    def _parse_lines(self, diff):

        """

        Parse the diff an return data for the template.

        """

        lineiter = iter(diff)

        stats = [0, 0]

        try:

            chunks = []

            line = lineiter.next()

            while line:

                lines = []

                chunks.append(lines)

                match = self._chunk_re.match(line)

                if not match:

                    break

                gr = match.groups()

                (old_line, old_end,

                 new_line, new_end) = [int(x or 1) for x in gr[:-1]]

                old_line -= 1

                new_line -= 1

                context = len(gr) == 5

                old_end += old_line

                new_end += new_line

                if context:

                    # skip context only if it's first line

                    if int(gr[0]) > 1:

                        lines.append({

                            'old_lineno': '...',

                            'new_lineno': '...',

                            'action':     'context',

                            'line':       line,

                        })

                line = lineiter.next()

                while old_line < old_end or new_line < new_end:

                    command = ' '

                    if line:

                        command = line[0]

                    affects_old = affects_new = False

                    # ignore those if we don't expect them

                    if command in '#@':

                        continue

                    elif command == '+':

                        affects_new = True

                        action = 'add'

                        stats[0] += 1

                    elif command == '-':

                        affects_old = True

                        action = 'del'

                        stats[1] += 1

                    else:

                        affects_old = affects_new = True

                        action = 'unmod'

                    if not self._newline_marker.match(line):

                        old_line += affects_old

                        new_line += affects_new

                        lines.append({

                            'old_lineno':   affects_old and old_line or '',

                            'new_lineno':   affects_new and new_line or '',

                            'action':       action,

                            'line':         self._clean_line(line, command)

                        })

                    line = lineiter.next()

                    if self._newline_marker.match(line):

                        # we need to append to lines, since this is not

                        # counted in the line specs of diff

                        lines.append({

                            'old_lineno':   '...',

                            'new_lineno':   '...',

                            'action':       'context',

                            'line':         self._clean_line(line, command)

                        })

        except StopIteration:

            pass

        return chunks, stats

    def _safe_id(self, idstring):

        """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', "_", '%s' % idstring)

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

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

        return idstring

    def prepare(self, inline_diff=True):

        """

        Prepare the passed udiff for HTML rendering. It'l return a list

        of dicts with diff information

        """

        parsed = self._parser(inline_diff=inline_diff)

        self.parsed = True

        self.parsed_diff = parsed

        return parsed

    def as_raw(self, diff_lines=None):

        """

        Returns raw string diff

        """

        return self._diff

        #return u''.join(imap(self._line_counter, self._diff.splitlines(1)))

    def as_html(self, table_class='code-difftable', line_class='line',

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

                code_class='code', enable_comments=False, parsed_lines=None):

        """

        Return given diff as html table with customized css classes

        """

        def _link_to_if(condition, label, url):

            """

            Generates a link if condition is meet or just the label if not.

            """

            if condition:

                return '''<a href="%(url)s">%(label)s</a>''' % {

                    'url': url,

                    'label': label

                }

            else:

                return label

        if not self.parsed:

            self.prepare()

        diff_lines = self.parsed_diff

        if parsed_lines:

            diff_lines = parsed_lines

        _html_empty = True

        _html = []

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

            'table_class': table_class

        })

        for diff in diff_lines:

            for line in diff['chunks']:

                _html_empty = False

                for change in line:

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

                        'lc': line_class,

                        'action': change['action']

                    })

                    anchor_old_id = ''

                    anchor_new_id = ''

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

                        'filename': self._safe_id(diff['filename']),

                        'oldline_no': change['old_lineno']

                    }

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

                        'filename': self._safe_id(diff['filename']),

                        'oldline_no': change['new_lineno']

                    }

                    cond_old = (change['old_lineno'] != '...' and

                                change['old_lineno'])

                    cond_new = (change['new_lineno'] != '...' and

                                change['new_lineno'])

                    if cond_old:

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

                    if cond_new:

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

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

                    # OLD LINE NUMBER

from __future__ import with_statement

from kallithea.tests import *

from kallithea.lib.diffs import DiffProcessor, NEW_FILENODE, DEL_FILENODE, \

    MOD_FILENODE, RENAMED_FILENODE, CHMOD_FILENODE, BIN_FILENODE, COPIED_FILENODE

from kallithea.tests.fixture import Fixture

fixture = Fixture()

DIFF_FIXTURES = {

    'hg_diff_add_single_binary_file.diff': [

        ('US Warszawa.jpg', 'A',

         {'added': 0,

          'deleted': 0,

          'binary': True,

          'ops': {NEW_FILENODE: 'new file 100755',

                  BIN_FILENODE: 'binary diff not shown'}}),

    ],

    'hg_diff_mod_single_binary_file.diff': [

        ('US Warszawa.jpg', 'M',

         {'added': 0,

          'deleted': 0,

          'binary': True,

          'ops': {MOD_FILENODE: 'modified file',

                  BIN_FILENODE: 'binary diff not shown'}}),

    ],

    'hg_diff_mod_single_file_and_rename_and_chmod.diff': [

        ('README', 'M',

         {'added': 3,

          'deleted': 0,

          'binary': False,

          'ops': {MOD_FILENODE: 'modified file',

                  RENAMED_FILENODE: 'file renamed from README.rst to README',

                  CHMOD_FILENODE: 'modified file chmod 100755 => 100644'}}),

    ],

    'hg_diff_mod_file_and_rename.diff': [

        ('README.rst', 'M',

         {'added': 3,

          'deleted': 0,

          'binary': False,

          'ops': {MOD_FILENODE: 'modified file',

                  RENAMED_FILENODE: 'file renamed from README to README.rst'}}),

    ],

    'hg_diff_del_single_binary_file.diff': [

        ('US Warszawa.jpg', 'D',

         {'added': 0,

          'deleted': 0,

          'binary': True,

          'ops': {DEL_FILENODE: 'deleted file',

                  BIN_FILENODE: 'binary diff not shown'}}),

    ],

    'hg_diff_chmod_and_mod_single_binary_file.diff': [

        ('gravatar.png', 'M',

         {'added': 0,

          'deleted': 0,

          'binary': True,

          'ops': {CHMOD_FILENODE: 'modified file chmod 100644 => 100755',

                  BIN_FILENODE: 'binary diff not shown'}}),

    ],

    'hg_diff_chmod.diff': [

        ('file', 'M',

         {'added': 0,

          'deleted': 0,

          'binary': True,

          'ops': {CHMOD_FILENODE: 'modified file chmod 100755 => 100644'}}),

    ],

    'hg_diff_rename_file.diff': [

        ('file_renamed', 'M',

         {'added': 0,

          'deleted': 0,

          'binary': True,

          'ops': {RENAMED_FILENODE: 'file renamed from file to file_renamed'}}),

    ],

    'hg_diff_rename_and_chmod_file.diff': [

        ('README', 'M',

         {'added': 0,

          'deleted': 0,

          'binary': True,

          'ops': {CHMOD_FILENODE: 'modified file chmod 100644 => 100755',

                  RENAMED_FILENODE: 'file renamed from README.rst to README'}}),

    ],

    'hg_diff_binary_and_normal.diff': [

        ('img/baseline-10px.png', 'A',

         {'added': 0,

          'deleted': 0,

          'binary': True,

          'ops': {NEW_FILENODE: 'new file 100644',

                  BIN_FILENODE: 'binary diff not shown'}}),

        ('js/jquery/hashgrid.js', 'A',

         {'added': 340,

          'deleted': 0,

          'binary': False,

          'ops': {NEW_FILENODE: 'new file 100755'}}),

        ('less/docs.less', 'M',

         {'added': 34,

          'deleted': 0,

          'binary': False,

          'ops': {MOD_FILENODE: 'modified file'}}),

        ('less/scaffolding.less', 'M',

         {'added': 1,

          'deleted': 3,

          'binary': False,

          'ops': {MOD_FILENODE: 'modified file'}}),

        ('readme.markdown', 'M',

         {'added': 1,

          'deleted': 10,

          'binary': False,

          'ops': {MOD_FILENODE: 'modified file'}}),

    ],

    'git_diff_chmod.diff': [

        ('work-horus.xls', 'M',

         {'added': 0,

          'deleted': 0,

          'binary': True,

          'ops': {CHMOD_FILENODE: 'modified file chmod 100644 => 100755'}})

    ],

    'git_diff_rename_file.diff': [

        ('file.xls', 'M',

         {'added': 0,

          'deleted': 0,

          'binary': True,

          'ops': {RENAMED_FILENODE: 'file renamed from work-horus.xls to file.xls'}})

    ],

    'git_diff_mod_single_binary_file.diff': [

        ('US Warszawa.jpg', 'M',

         {'added': 0,

          'deleted': 0,

          'binary': True,

          'ops': {MOD_FILENODE: 'modified file',

                  BIN_FILENODE: 'binary diff not shown'}})

    ],

    'git_diff_binary_and_normal.diff': [

        ('img/baseline-10px.png', 'A',

         {'added': 0,

          'deleted': 0,

          'binary': True,

          'ops': {NEW_FILENODE: 'new file 100644',

                  BIN_FILENODE: 'binary diff not shown'}}),

        ('js/jquery/hashgrid.js', 'A',

         {'added': 340,

          'deleted': 0,

          'binary': False,

          'ops': {NEW_FILENODE: 'new file 100755'}}),

        ('less/docs.less', 'M',

         {'added': 34,

          'deleted': 0,

          'binary': False,

          'ops': {MOD_FILENODE: 'modified file'}}),

        ('less/scaffolding.less', 'M',

         {'added': 1,

          'deleted': 3,

          'binary': False,

          'ops': {MOD_FILENODE: 'modified file'}}),

        ('readme.markdown', 'M',

         {'added': 1,

          'deleted': 10,

          'binary': False,

          'ops': {MOD_FILENODE: 'modified file'}}),

    ],

    'diff_with_diff_data.diff': [

        ('vcs/backends/base.py', 'M',

         {'added': 18,

          'deleted': 2,

          'binary': False,

          'ops': {MOD_FILENODE: 'modified file'}}),

        ('vcs/backends/git/repository.py', 'M',

         {'added': 46,

          'deleted': 15,

          'binary': False,

          'ops': {MOD_FILENODE: 'modified file'}}),

        ('vcs/backends/hg.py', 'M',

         {'added': 22,

          'deleted': 3,

          'binary': False,

          'ops': {MOD_FILENODE: 'modified file'}}),

        ('vcs/tests/test_git.py', 'M',

         {'added': 5,

          'deleted': 5,

          'binary': False,

          'ops': {MOD_FILENODE: 'modified file'}}),

        ('vcs/tests/test_repository.py', 'M',

         {'added': 174,

          'deleted': 2,

          'binary': False,

          'ops': {MOD_FILENODE: 'modified file'}}),

    ],

    'hg_diff_copy_file.diff': [

        ('file2', 'M',

         {'added': 0,

          'deleted': 0,

          'binary': True,

          'ops': {COPIED_FILENODE: 'file copied from file1 to file2'}}),

    ],

    'hg_diff_copy_and_modify_file.diff': [

        ('file3', 'M',

         {'added': 1,

          'deleted': 0,

          'binary': False,

          'ops': {COPIED_FILENODE: 'file copied from file2 to file3',

                  MOD_FILENODE: 'modified file'}}),

    ],

    'hg_diff_copy_and_chmod_file.diff': [

        ('file4', 'M',

         {'added': 0,

          'deleted': 0,

          'binary': True,

          'ops': {COPIED_FILENODE: 'file copied from file3 to file4',

                  CHMOD_FILENODE: 'modified file chmod 100644 => 100755'}}),

    ],

    'hg_diff_copy_chmod_and_edit_file.diff': [

        ('file5', 'M',

         {'added': 2,

          'deleted': 1,

          'binary': False,

          'ops': {COPIED_FILENODE: 'file copied from file4 to file5',

                  CHMOD_FILENODE: 'modified file chmod 100755 => 100644',

                  MOD_FILENODE: 'modified file'}}),

    ]

}

class DiffLibTest(BaseTestCase):

    @parameterized.expand([(x,) for x in DIFF_FIXTURES])

    def test_diff(self, diff_fixture):

        diff = fixture.load_resource(diff_fixture)

        diff_proc = DiffProcessor(diff)

        diff_proc_d = diff_proc.prepare()

        data = [(x['filename'], x['operation'], x['stats']) for x in diff_proc_d]

        expected_data = DIFF_FIXTURES[diff_fixture]

        self.assertListEqual(expected_data, data)