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

    return idstring

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

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

            no_lineno_class='lineno',

            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" data-pseudo-content="%(label)s"></a>''' % {

                'url': url,

                'label': label

            }

        else:

            return label

    _html_empty = True

    _html = []

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

        'table_class': table_class

    })

    for file_info in parsed_lines:

        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']

                })

                anchor_old_id = ''

                anchor_new_id = ''

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

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

                    'oldline_no': change['old_lineno']

                }

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

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

                    'newline_no': 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

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

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

                    'a_id': anchor_old_id,

                    'olc': no_lineno_class if no_lineno else old_lineno_class,

                    'colspan': 'colspan="2"' if no_lineno else ''

                })

                _html.append('''%(link)s''' % {

                    'link': _link_to_if(not no_lineno, change['old_lineno'],

                                        '#%s' % anchor_old)

                })

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

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

                # NEW LINE NUMBER

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

                if not no_lineno:

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

                        'a_id': anchor_new_id,

                        'nlc': new_lineno_class

                    })

                    _html.append('''%(link)s''' % {

                        'link': _link_to_if(True, change['new_lineno'],

                                            '#%s' % anchor_new)

                    })

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

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

                # CODE

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

                comments = '' if enable_comments else 'no-comment'

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

                    'cc': code_class,

                    'inc': comments

                })

                _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>''')

        raise Exception('diff not recognized as valid %s diff' % vcs)

    meta_info = {k: None if v is None else safe_str(v) for k, v in match.groupdict().items()}

    rest = diff_chunk[match.end():]

    if rest and _header_next_check.match(rest):

        raise Exception('cannot parse %s diff header: %r followed by %r' % (vcs, safe_str(bytes(diff_chunk[:match.end()])), safe_str(bytes(rest[:1000]))))

    diff_lines = (_escaper(m.group(0)) for m in re.finditer(br'.*\n|.+$', rest)) # don't split on \r as str.splitlines do

    return meta_info, diff_lines

_chunk_re = re.compile(r'^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@(.*)')

_newline_marker = re.compile(r'^\\ No newline at end of file')

def _parse_lines(diff_lines):

    """

    Given an iterator of diff body lines, parse them and return a dict per

    line and added/removed totals.

    """

    added = deleted = 0

    old_line = old_end = new_line = new_end = None

    chunks = []

    try:

        line = next(diff_lines)

        while True:

            lines = []

            chunks.append(lines)

            match = _chunk_re.match(line)

            if not match:

                raise Exception('error parsing diff @@ line %r' % line)

            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({

                        'action':     'context',

                        'line':       line,

                    })

            line = next(diff_lines)

            while old_line < old_end or new_line < new_end:

                if not line:

                    raise Exception('error parsing diff - empty line at -%s+%s' % (old_line, new_line))

                affects_old = affects_new = False

                command = line[0]

                if command == '+':

                    affects_new = True

                    action = 'add'

                    added += 1

                elif command == '-':

                    affects_old = True

                    action = 'del'

                    deleted += 1

                elif command == ' ':

                    affects_old = affects_new = True

                    action = 'unmod'

                else:

                    raise Exception('error parsing diff - unknown command in line %r at -%s+%s' % (line, old_line, new_line))

                if not _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':         line[1:],

                    })

                line = next(diff_lines)

                if _newline_marker.match(line):

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

                    # counted in the line specs of diff

                    lines.append({

                        'action':       'context',

                        'line':         line,

                    })

                    line = next(diff_lines)

            if old_line > old_end:

                raise Exception('error parsing diff - more than %s "-" lines at -%s+%s' % (old_end, old_line, new_line))

            if new_line > new_end:

                raise Exception('error parsing diff - more than %s "+" lines at -%s+%s' % (new_end, old_line, new_line))

    except StopIteration:

        pass

    if old_line != old_end or new_line != new_end:

        raise Exception('diff processing broken when old %s<>%s or new %s<>%s line %r' % (old_line, old_end, new_line, new_end, line))

    return chunks, added, deleted

# Used for inline highlighter word split, must match the substitutions in _escaper

_token_re = re.compile(r'()(&amp;|&lt;|&gt;|<u>\t</u>|<u class="cr"></u>| <i></i>|\W+?)')

def _highlight_inline_diff(old, new):

    """

    Highlight simple add/remove in two lines given as info dicts. They are

    modified in place and given markup with <del>/<ins>.

    """

    assert old['action'] == 'del'

    assert new['action'] == 'add'

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

    newwords = _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)

          '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', 'modified',

         {'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'}}),

    ],

    'hg_diff_rename_space_cr.diff': [

        ('oh yes', 'renamed',

         {'added': 3,

          'deleted': 2,

          'binary': False,

          'ops': {RENAMED_FILENODE: 'file renamed from oh no to oh yes'}}),

    ],

}

class TestDiffLib(base.TestController):

    @base.parametrize('diff_fixture', DIFF_FIXTURES)

    def test_diff(self, diff_fixture):

        raw_diff = fixture.load_resource(diff_fixture, strip=False)

        vcs = 'hg'

        if diff_fixture.startswith('git_'):

            vcs = 'git'

        diff_processor = DiffProcessor(raw_diff, vcs=vcs)

        data = [(x['filename'], x['operation'], x['stats']) for x in diff_processor.parsed]

        expected_data = DIFF_FIXTURES[diff_fixture]

        assert expected_data == data

    def test_diff_markup(self):

        raw_diff = fixture.load_resource('markuptest.diff', strip=False)

        diff_processor = DiffProcessor(raw_diff)

        chunks = diff_processor.parsed[0]['chunks']

        assert not chunks[0]

        #from pprint import pprint; pprint(chunks[1])

        l = ['\n']

        for d in chunks[1]:

            l.append('%(action)-7s %(new_lineno)3s %(old_lineno)3s %(line)r\n' % d)

        s = ''.join(l)

        assert s == r'''

unmod    51  51 '<u>\t</u>begin();\n'

unmod    52  52 '<u>\t</u>\n'

add      53     '<u>\t</u>int foo;<u class="cr"></u>\n'

add      54     '<u>\t</u>int bar; <u class="cr"></u>\n'

add      55     '<u>\t</u>int baz;<u>\t</u><u class="cr"></u>\n'

add      56     '<u>\t</u>int space; <i></i>'

add      57     '<u>\t</u>int tab;<u>\t</u>\n'

add      58     '<u>\t</u>\n'

unmod    59  53 ' <i></i>'

del          54 '<u>\t</u>#define MAX_STEPS (48)\n'

add      60     '<u>\t</u><u class="cr"></u>\n'

add      61     '<u>\t</u>#define MAX_STEPS (64)<u class="cr"></u>\n'

unmod    62  55 '\n'

del          56 '<u>\t</u>#define MIN_STEPS (<del>48</del>)\n'

add      63     '<u>\t</u>#define MIN_STEPS (<ins>42</ins>)\n'

'''