from rhodecode.lib.compat import BytesIO

from rhodecode.lib.vcs.exceptions import VCSError

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

from rhodecode.lib.helpers import escape

from rhodecode.lib.utils import EmptyChangeset, make_ui

def wrap_to_table(str_):

    return '''<table class="code-difftable">

                <tr class="line no-comment">

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

                <td class="code no-comment"><pre>%s</pre></td>

                </tr>

              </table>''' % str_

def wrapped_diff(filenode_old, filenode_new, cut_off_limit=None,

                ignore_whitespace=True, line_context=3,

                enable_comments=False):

    """

    returns a wrapped diff into a table, checks for cut_off_limit and presents

    proper message

    """

    if filenode_old is None:

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

    if filenode_old.is_binary or filenode_new.is_binary:

        diff = wrap_to_table(_('binary file'))

        stats = (0, 0)

        size = 0

    elif cut_off_limit != -1 and (cut_off_limit is None or

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

        f_gitdiff = get_gitdiff(filenode_old, filenode_new,

                                ignore_whitespace=ignore_whitespace,

                                context=line_context)

        diff_processor = DiffProcessor(f_gitdiff, format='gitdiff')

        diff = diff_processor.as_html(enable_comments=enable_comments)

        stats = diff_processor.stat()

        size = len(diff or '')

    else:

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

                               'diff menu to display this diff'))

        stats = (0, 0)

        size = 0

    if not diff:

        submodules = filter(lambda o: isinstance(o, SubModuleNode),

                            [filenode_new, filenode_old])

        if submodules:

            diff = wrap_to_table(escape('Submodule %r' % submodules[0]))

        else:

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

    cs1 = filenode_old.changeset.raw_id

    cs2 = filenode_new.changeset.raw_id

    return size, cs1, cs2, diff, stats

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

    """

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

    :param ignore_whitespace: ignore whitespaces in diff

    """

    # make sure we pass in default context

    context = context or 3

    submodules = filter(lambda o: isinstance(o, SubModuleNode),

                        [filenode_new, filenode_old])

    if submodules:

        return ''

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

                                 ignore_whitespace, context)

    return vcs_gitdiff

class DiffProcessor(object):

    """

    Give it a unified diff and it returns a list of the files that were

    mentioned in the diff together with a dict of meta information that

    can be used to render it in a HTML template.

    """

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

    def __init__(self, diff, differ='diff', format='gitdiff'):

        """

        :param diff:   a text in diff format or generator

        :param format: format of diff passed, `udiff` or `gitdiff`

        """

        if isinstance(diff, basestring):

            diff = [diff]

        self.__udiff = diff

        self.__format = format

        self.adds = 0

        self.removes = 0

        if isinstance(self.__udiff, basestring):

            self.lines = iter(self.__udiff.splitlines(1))

        elif self.__format == 'gitdiff':

            udiff_copy = self.copy_iterator()

            self.lines = imap(self.escaper, self._parse_gitdiff(udiff_copy))

        else:

            udiff_copy = self.copy_iterator()

            self.lines = imap(self.escaper, udiff_copy)

        # Select a differ.

        if differ == 'difflib':

            self.differ = self._highlight_line_difflib

        else:

            self.differ = self._highlight_line_udiff

    def escaper(self, string):

        return markupsafe.escape(string)

    def copy_iterator(self):

        """

        make a fresh copy of generator, we should not iterate thru

        an original as it's needed for repeating operations on

        this instance of DiffProcessor

        """

        self.__udiff, iterator_copy = tee(self.__udiff)

        return iterator_copy

    def _extract_rev(self, line1, line2):

        """

        Extract the operation (A/M/D), filename and revision hint from a line.

        """

        try:

            if line1.startswith('--- ') and line2.startswith('+++ '):

                l1 = line1[4:].split(None, 1)

                old_filename = (l1[0].replace('a/', '', 1)

                                if len(l1) >= 1 else None)

                old_rev = l1[1] if len(l1) == 2 else 'old'

                l2 = line2[4:].split(None, 1)

                new_filename = (l2[0].replace('b/', '', 1)

                                if len(l1) >= 1 else None)

                new_rev = l2[1] if len(l2) == 2 else 'new'

                filename = (old_filename

                            if old_filename != '/dev/null' else new_filename)

                operation = 'D' if new_filename == '/dev/null' else None

                if not operation:

                    operation = 'M' if old_filename != '/dev/null' else 'A'

                return operation, filename, new_rev, old_rev

        except (ValueError, IndexError):

            pass

        return None, None, None, None

    def _parse_gitdiff(self, diffiterator):

        def line_decoder(l):

            if l.startswith('+') and not l.startswith('+++'):

                self.adds += 1

            elif l.startswith('-') and not l.startswith('---'):

                self.removes += 1

            return l.decode('utf8', 'replace')

        output = list(diffiterator)

        size = len(output)

        if size == 2:

            l = []

            l.extend([output[0]])

            l.extend(output[1].splitlines(1))

            return map(line_decoder, l)

        elif size == 1:

            return  map(line_decoder, output[0].splitlines(1))

        elif size == 0:

            return []

        raise Exception('wrong size of diff %s' % size)

    def _highlight_line_difflib(self, line, next_):

                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 _parse_udiff(self, inline_diff=True):

        """

        Parse the diff an return data for the template.

        """

        lineiter = self.lines

        files = []

        try:

            line = lineiter.next()

            while 1:

                # continue until we found the old file

                if not line.startswith('--- '):

                    line = lineiter.next()

                    continue

                chunks = []

                stats = [0, 0]

                operation, filename, old_rev, new_rev = \

                    self._extract_rev(line, lineiter.next())

                files.append({

                    'filename':         filename,

                    'old_revision':     old_rev,

                    'new_revision':     new_rev,

                    'chunks':           chunks,

                    'operation':        operation,

                    'stats':            stats,

                })

                line = lineiter.next()

                while line:

                    match = self._chunk_re.match(line)

                    if not match:

                        break

                    lines = []

                    chunks.append(lines)

                    old_line, old_end, new_line, new_end = \

                        [int(x or 1) for x in match.groups()[:-1]]

                    old_line -= 1

                    new_line -= 1

                    gr = match.groups()

                    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:

                        if line:

                        else:

                            command = ' '

                        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'

                            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

                            })

                        line = lineiter.next()

        except StopIteration:

            pass

        sorter = lambda info: {'A': 0, 'M': 1, 'D': 2}.get(info['operation'])

        if inline_diff is False:

            return sorted(files, key=sorter)

        # 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

        return sorted(files, key=sorter)

    def prepare(self, inline_diff=True):

        """

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

        of dicts

        """

        return self._parse_udiff(inline_diff=inline_diff)

    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 raw_diff(self):

        """

        Returns raw string as udiff

        """

        udiff_copy = self.copy_iterator()

        if self.__format == 'gitdiff':

            udiff_copy = self._parse_gitdiff(udiff_copy)

        return u''.join(udiff_copy)

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

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

                code_class='code', enable_comments=False, diff_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 diff_lines is None:

            diff_lines = self.prepare()

        _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']

                    })