path: root/__init__.py

# Copyright (C) 2008 Canonical Ltd
#
# 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 2 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, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA

r"""FastImport Plugin
=================

The fastimport plugin provides stream-based importing of data into Bazaar.
A bzr-fast-export.py script is also included providing exporting of data
out of Bazaar to the same format. As well as enabling interchange between
multiple VCS tools, fastimport/export can be useful for complex branch
operatons, e.g. partitioning off part of a code base in order to Open
Source it.

The normal import recipe is::

  bzr init-repo .
  front-end | bzr fast-import -

Numerous front-ends are provided in the exporters directory where
the plugin is installed. The list of known front-ends and their
status is documented on http://bazaar-vcs.org/BzrFastImport/FrontEnds.
For further details, see http://bazaar-vcs.org/BzrFastImport and the
online help for the commands::

  bzr help fast-import
  bzr help fast-import-info
  bzr help fast-import-query

To report bugs or publish enhancements, visit the bzr-fastimport project
page on Launchpad, https://launchpad.net/bzr-fastimport.
"""

from bzrlib.commands import Command, register_command
from bzrlib.option import Option, ListOption


def test_suite():
    import tests
    return tests.test_suite()


def _run(source, processor_factory, control, params, verbose):
    """Create and run a processor.
    
    :param source: a filename or '-' for standard input
    :param processor_factory: a callable for creating a processor
    :param control: the BzrDir of the destination or None if no
      destination is expected
    """
    import parser
    if source == '-':
        import sys
        stream = sys.stdin
        try:
            import msvcrt
            import os
            msvcrt.setmode(sys.stdin.fileno(), os.O_BINARY)
        except ImportError:
            pass
    else:
        stream = open(source, "rb")
    proc = processor_factory(control, params=params, verbose=verbose)
    p = parser.ImportParser(stream, verbose=verbose)
    return proc.process(p.iter_commands)


class cmd_fast_import(Command):
    """Backend for fast Bazaar data importers.

    This command reads a mixed command/data stream and
    creates branches in the current repository accordingly.
    To specify standard input as the input stream, use a
    source name of '-'.
    
    The usual recipe is::

      bzr init-repo .
      front-end | bzr fast-import -

    If run inside a branch using a shared repository, then
    the current branch is made the trunk and other branches,
    if any, are created in sister directories. If run inside
    a standalone tree, the current branch is also made the
    trunk, but warnings are output about other branches found.
    
    The stream format is upwardly compatible with git-fast-import
    so existing front-ends for that tool can typically be reused
    without changes. See http://bazaar-vcs.org/BzrFastImport for
    links to matching exporters from Subversion, CVS, Git,
    Mercurial, Darcs, Perforce and SCCS.
 
    While reusing an existing format with existing frontends is
    great, it does mean a slightly more complex recipe when
    importing large projects via exporters that reuse blob data
    across commits, namely::

      bzr init-repo .
      front-end > xxx.fi
      bzr fast-import-info -v xxx.fi > xxx.cfg
      bzr fast-import xxx.fi --info xxx.cfg

    In this scenario, the xxx.cfg file generated by the first pass
    holds caching hints that the second pass uses to lower memory
    usage.
    
    At checkpoints and on completion, the commit-id -> revision-id
    map is saved to a file called 'fastimport-id-map' in the control
    directory for the repository (e.g. .bzr/repository). If the import
    is interrupted or unexpectedly crashes, it can be started again
    and this file will be used to skip over already loaded revisions.
    As long as subsequent exports from the original source begin
    with exactly the same revisions, you can use this feature to
    maintain a mirror of a repository managed by a foreign tool.
    If and when Bazaar is used to manage the repository, this file
    can be safely deleted.

    If you wish to write a custom exporter for your project, see
    http://bazaar-vcs.org/BzrFastImport for the detailed protocol
    specification. In many cases, exporters can be written quite
    quickly using whatever scripting/programming language you like.

    Examples::

     cd /git/repo/path
     git-fast-export --signed-tags=warn | bzr fast-import -

        Import a Git repository into Bazaar.

     svn-fast-export.py /svn/repo/path | bzr fast-import -

        Import a Subversion repository into Bazaar.

     hg-fast-export.py -r /hg/repo/path | bzr fast-import -

        Import a Mercurial repository into Bazaar.
    """
    hidden = True
    _see_also = ['fast-import-info', 'fast-import-query']
    takes_args = ['source']
    takes_options = ['verbose',
                    Option('info', type=str,
                        help="Path to file containing caching hints.",
                        ),
                    Option('trees',
                        help="Update working trees.",
                        ),
                    Option('checkpoint', type=int,
                        help="Checkpoint automatically every N revisions.",
                        ),
                    Option('count', type=int,
                        help="Import this many revisions then exit.",
                        ),
                    Option('inv-cache', type=int,
                        help="Number of inventories to cache.",
                        ),
                    Option('experimental',
                        help="Enable experimental features.",
                        ),
                    Option('import-marks', type=str,
                        help="Import marks from file."),
                    Option('export-marks', type=str,
                        help="Export marks to file."),
                     ]
    aliases = []
    def run(self, source, verbose=False, info=None, trees=False,
        checkpoint=10000, count=-1, inv_cache=10,
        experimental=True, import_marks=None, export_marks=None):
        from bzrlib import bzrdir
        from bzrlib.plugins.fastimport.processors import generic_processor
        control, relpath = bzrdir.BzrDir.open_containing('.')
        params = {
            'info': info,
            'trees': trees,
            'checkpoint': checkpoint,
            'count': count,
            'inv-cache': inv_cache,
            'experimental': experimental,
            'import-marks': import_marks,
            'export-marks': export_marks,
            }
        return _run(source, generic_processor.GenericProcessor, control,
            params, verbose)


class cmd_fast_import_info(Command):
    """Output information about a fast-import stream.

    This command reads a fast-import stream and outputs
    statistics and interesting properties about what it finds.
    When run in verbose mode, the information is output as a
    configuration file that can be passed to fast-import to
    assist it in intelligently caching objects.

    To specify standard input as the input stream, use a source
    name of '-'.

    Examples::

     front-end | bzr fast-import-info -

        Display statistics about the import stream produced by front-end.

     front-end | bzr fast-import-info -v - > front-end.cfg

       Create a hints file for running fast-import on a large repository.
    """
    hidden = True
    _see_also = ['fast-import']
    takes_args = ['source']
    takes_options = ['verbose']
    aliases = []
    def run(self, source, verbose=False):
        from bzrlib.plugins.fastimport.processors import info_processor
        return _run(source, info_processor.InfoProcessor, None, {}, verbose)


class cmd_fast_import_query(Command):
    """Query a fast-import stream displaying selected commands.

    To specify standard input as the input stream, use a source
    name of '-'. To specify the commands to display, use the -C
    option one or more times. To specify just some fields for
    a command, use the syntax::

      command=field1,...

    By default, the nominated fields for the nominated commands
    are displayed tab separated. To see the information in
    a name:value format, use verbose mode.

    Note: Binary fields (e.g. data for blobs) are masked out
    so it is generally safe to view the output in a terminal.

    Examples::

      front-end > xxx.fi
      bzr fast-import-query xxx.fi -Creset -Ctag

        Show all the fields of the reset and tag commands.

      bzr fast-import-query xxx.fi -Ccommit=mark,merge

        Show the mark and merge fields of the commit commands.
    """
    hidden = True
    _see_also = ['fast-import']
    takes_args = ['source']
    takes_options = ['verbose',
                    ListOption('commands', short_name='C', type=str,
                        help="Display fields for these commands."
                        ),
                     ]
    aliases = []
    def run(self, source, verbose=False, commands=None):
        from bzrlib.plugins.fastimport.processors import query_processor
        from bzrlib.plugins.fastimport import helpers
        params = helpers.defines_to_dict(commands)
        return _run(source, query_processor.QueryProcessor, None, params,
            verbose)


register_command(cmd_fast_import)
register_command(cmd_fast_import_info)
register_command(cmd_fast_import_query)