/brz/remove-bazaar

# Copyright (C) 2010 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

from bzrlib.lazy_import import lazy_import

lazy_import(globals(), """

import codecs

import cStringIO

from fnmatch import fnmatch

import os

import re

import string

from termcolor import color_string, re_color_string, FG

from bzrlib import bzrdir

from bzrlib.workingtree import WorkingTree

from bzrlib.revisionspec import RevisionSpec, RevisionSpec_revid, RevisionSpec_revno

from bzrlib import (

    errors,

    lazy_regex,

    osutils,

    textfile,

    trace,

    )

""")

_terminal_encoding = osutils.get_terminal_encoding()

_user_encoding = osutils.get_user_encoding()

class _RevisionNotLinear(Exception):

    """Raised when a revision is not on left-hand history."""

def _rev_on_mainline(rev_tuple):

    """returns True is rev tuple is on mainline"""

    if len(rev_tuple) == 1:

        return True

    return rev_tuple[1] == 0 and rev_tuple[2] == 0

# NOTE: _linear_view_revisions is basided on

# bzrlib.log._linear_view_revisions.

# This should probably be a common public API

def _linear_view_revisions(branch, start_rev_id, end_rev_id):

    # requires that start is older than end

    repo = branch.repository

    for revision_id in repo.iter_reverse_revision_history(end_rev_id):

        revno = branch.revision_id_to_dotted_revno(revision_id)

        revno_str = '.'.join(str(n) for n in revno)

        if revision_id == start_rev_id:

            yield revision_id, revno_str, 0

            break

        yield revision_id, revno_str, 0

# NOTE: _graph_view_revisions is copied from

# bzrlib.log._graph_view_revisions.

# This should probably be a common public API

def _graph_view_revisions(branch, start_rev_id, end_rev_id,

                          rebase_initial_depths=True):

    """Calculate revisions to view including merges, newest to oldest.

    :param branch: the branch

    :param start_rev_id: the lower revision-id

    :param end_rev_id: the upper revision-id

    :param rebase_initial_depth: should depths be rebased until a mainline

      revision is found?

    :return: An iterator of (revision_id, dotted_revno, merge_depth) tuples.

    """

    # requires that start is older than end

    view_revisions = branch.iter_merge_sorted_revisions(

        start_revision_id=end_rev_id, stop_revision_id=start_rev_id,

        stop_rule="with-merges")

    if not rebase_initial_depths:

        for (rev_id, merge_depth, revno, end_of_merge

             ) in view_revisions:

            yield rev_id, '.'.join(map(str, revno)), merge_depth

    else:

        # We're following a development line starting at a merged revision.

        # We need to adjust depths down by the initial depth until we find

        # a depth less than it. Then we use that depth as the adjustment.

        # If and when we reach the mainline, depth adjustment ends.

        depth_adjustment = None

        for (rev_id, merge_depth, revno, end_of_merge

             ) in view_revisions:

            if depth_adjustment is None:

                depth_adjustment = merge_depth

            if depth_adjustment:

                if merge_depth < depth_adjustment:

                    # From now on we reduce the depth adjustement, this can be

                    # surprising for users. The alternative requires two passes

                    # which breaks the fast display of the first revision

                    # though.

                    depth_adjustment = merge_depth

                merge_depth -= depth_adjustment

            yield rev_id, '.'.join(map(str, revno)), merge_depth

def compile_pattern(pattern, flags=0):

    patternc = None

    try:

        # use python's re.compile as we need to catch re.error in case of bad pattern

        lazy_regex.reset_compile()

        patternc = re.compile(pattern, flags)

    except re.error, e:

        raise errors.BzrError("Invalid pattern: '%s'" % pattern)

    return patternc

def is_fixed_string(s):

    if re.match("^([A-Za-z0-9_]|\s)*$", s):

        return True

    return False

def versioned_grep(opts):

    wt, branch, relpath = \

        bzrdir.BzrDir.open_containing_tree_or_branch('.')

    branch.lock_read()

    try:

        # res_cache is used to cache results for dir grep based on fid.

        # If the fid is does not change between results, it means that

        # the result will be the same apart from revno. In such a case

        # we avoid getting file chunks from repo and grepping. The result

        # is just printed by replacing old revno with new one.

        res_cache = {}

        start_rev = opts.revision[0]

        start_revid = start_rev.as_revision_id(branch)

        if start_revid == None:

            start_rev = RevisionSpec_revno.from_string("revno:1")

            start_revid = start_rev.as_revision_id(branch)

        srevno_tuple = branch.revision_id_to_dotted_revno(start_revid)

        if len(opts.revision) == 2:

            end_rev = opts.revision[1]

            end_revid = end_rev.as_revision_id(branch)

            if end_revid == None:

                end_revno, end_revid = branch.last_revision_info()

            erevno_tuple = branch.revision_id_to_dotted_revno(end_revid)

            grep_mainline = (_rev_on_mainline(srevno_tuple) and

                _rev_on_mainline(erevno_tuple))

            # ensure that we go in reverse order

            if srevno_tuple > erevno_tuple:

                srevno_tuple, erevno_tuple = erevno_tuple, srevno_tuple

                start_revid, end_revid = end_revid, start_revid

            # Optimization: Traversing the mainline in reverse order is much

            # faster when we don't want to look at merged revs. We try this

            # with _linear_view_revisions. If all revs are to be grepped we

            # use the slower _graph_view_revisions

            if opts.levels==1 and grep_mainline:

                given_revs = _linear_view_revisions(branch, start_revid, end_revid)

            else:

                given_revs = _graph_view_revisions(branch, start_revid, end_revid)

        else:

            # We do an optimization below. For grepping a specific revison

            # We don't need to call _graph_view_revisions which is slow.

            # We create the start_rev_tuple for only that specific revision.

            # _graph_view_revisions is used only for revision range.

            start_revno = '.'.join(map(str, srevno_tuple))

            start_rev_tuple = (start_revid, start_revno, 0)

            given_revs = [start_rev_tuple]

        # GZ 2010-06-02: Shouldn't be smuggling this on opts, but easy for now

        opts.line_writer = staticmethod(_make_line_writer(opts))

        for revid, revno, merge_depth in given_revs:

            if opts.levels == 1 and merge_depth != 0:

                # with level=1 show only top level

                continue

            rev = RevisionSpec_revid.from_string("revid:"+revid)

            tree = rev.as_tree(branch)

            for path in opts.path_list:

                path_for_id = osutils.pathjoin(relpath, path)

                id = tree.path2id(path_for_id)

                if not id:

                    trace.warning("Skipped unknown file '%s'." % path)

                    continue

                if osutils.isdir(path):

                    path_prefix = path

                    res_cache = dir_grep(tree, path, relpath, opts,

                        revno, path_prefix, res_cache)

                else:

                    versioned_file_grep(tree, id, '.', path, opts, revno)

    finally:

        branch.unlock()

def workingtree_grep(opts):

    revno = opts.print_revno = None # for working tree set revno to None

    tree, branch, relpath = \

        bzrdir.BzrDir.open_containing_tree_or_branch('.')

    if not tree:

        msg = ('Cannot search working tree. Working tree not found.\n'

            'To search for specific revision in history use the -r option.')

        raise errors.BzrCommandError(msg)

    # GZ 2010-06-02: Shouldn't be smuggling this on opts, but easy for now

    opts.line_writer = staticmethod(_make_line_writer(opts))

    tree.lock_read()

    try:

        for path in opts.path_list:

            if osutils.isdir(path):

                path_prefix = path

                dir_grep(tree, path, relpath, opts, revno, path_prefix)

            else:

                _file_grep(open(path).read(), path, opts, revno)

    finally:

        tree.unlock()

def _skip_file(include, exclude, path):

    if include and not _path_in_glob_list(path, include):

        return True

    if exclude and _path_in_glob_list(path, exclude):

        return True

    return False

def dir_grep(tree, path, relpath, opts, revno, path_prefix, res_cache={}):

    _revno_pattern = re.compile("\~[0-9.]+:")

    _revno_pattern_list_only = re.compile("\~[0-9.]+")

    dir_res = {}

    # setup relpath to open files relative to cwd

    rpath = relpath

    if relpath:

        rpath = osutils.pathjoin('..',relpath)

    from_dir = osutils.pathjoin(relpath, path)

    if opts.from_root:

        # start searching recursively from root

        from_dir=None

        recursive=True

    to_grep = []

    to_grep_append = to_grep.append

    outf_write = opts.outf.write

    for fp, fc, fkind, fid, entry in tree.list_files(include_root=False,

        from_dir=from_dir, recursive=opts.recursive):

        if _skip_file(opts.include, opts.exclude, fp):

            continue

        if fc == 'V' and fkind == 'file':

            if revno != None:

                # If old result is valid, print results immediately.

                # Otherwise, add file info to to_grep so that the

                # loop later will get chunks and grep them

                file_rev = tree.inventory[fid].revision

                old_res = res_cache.get(file_rev)

                if old_res != None:

                    res = []

                    res_append = res.append

                    if opts.files_with_matches or opts.files_without_match:

                        new_rev = '~' + revno

                    else:

                        new_rev = ('~%s:' % (revno,))

                    for line in old_res:

                        if opts.files_with_matches or opts.files_without_match:

                            s = _revno_pattern_list_only.sub(new_rev, line)

                        else:

                            s = _revno_pattern.sub(new_rev, line)

                        res_append(s)

                        outf_write(s)

                    dir_res[file_rev] = res

                else:

                    to_grep_append((fid, (fp, fid)))

            else:

                # we are grepping working tree.

                if from_dir == None:

                    from_dir = '.'

                path_for_file = osutils.pathjoin(tree.basedir, from_dir, fp)

                if opts.files_with_matches or opts.files_without_match:

                    # Optimize for wtree list-only as we don't need to read the

                    # entire file

                    file = codecs.open(path_for_file, 'r', buffering=4096)

                    _file_grep_list_only_wtree(file, fp, opts, path_prefix)

                else:

                    file_text = codecs.open(path_for_file, 'r').read()

                    _file_grep(file_text, fp, opts, revno, path_prefix)

    if revno != None: # grep versioned files

        for (path, fid), chunks in tree.iter_files_bytes(to_grep):

            path = _make_display_path(relpath, path)

            res = _file_grep(chunks[0], path, opts, revno, path_prefix)

            file_rev = tree.inventory[fid].revision

            dir_res[file_rev] = res

    return dir_res

def _make_display_path(relpath, path):

    """Return path string relative to user cwd.

    Take tree's 'relpath' and user supplied 'path', and return path

    that can be displayed to the user.

    """

    if relpath:

        # update path so to display it w.r.t cwd

        # handle windows slash separator

        path = osutils.normpath(osutils.pathjoin(relpath, path))

        path = path.replace('\\', '/')

        path = path.replace(relpath + '/', '', 1)

    return path

def versioned_file_grep(tree, id, relpath, path, opts, revno, path_prefix = None):

    """Create a file object for the specified id and pass it on to _file_grep.

    """

    path = _make_display_path(relpath, path)

    file_text = tree.get_file_text(id)

    _file_grep(file_text, path, opts, revno, path_prefix)

def _path_in_glob_list(path, glob_list):

    present = False

    for glob in glob_list:

        if fnmatch(path, glob):

            present = True

            break

    return present

def _file_grep_list_only_wtree(file, path, opts, path_prefix=None):

    # test and skip binary files

    if '\x00' in file.read(1024):

        if opts.verbose:

            trace.warning("Binary file '%s' skipped." % path)

            return

    file.seek(0) # search from beginning

    found = False

    if opts.fixed_string:

        pattern = opts.pattern.encode(_user_encoding, 'replace')

        for line in file:

            if pattern in line:

                found = True

                break

    else: # not fixed_string

        for line in file:

            if opts.patternc.search(line):

                found = True

                break

    if (opts.files_with_matches and found) or \

        (opts.files_without_match and not found):

        if path_prefix and path_prefix != '.':

            # user has passed a dir arg, show that as result prefix

            path = osutils.pathjoin(path_prefix, path)

        path = path.encode(_terminal_encoding, 'replace')

        s = path + opts.eol_marker

        opts.outf.write(s)

def _make_line_writer(opts):

    """Precalculate formatting and return function for writing output lines

    The idea here is to do this work only once per run, and return a function

    that will do the minimum amount possible for each match.

    It may be best to add another step that also preformats things that don't

    change across a file like the path and revno to leave the line writer

    even smaller.

    """

    write = opts.outf.write

    pattern = opts.pattern.encode(_user_encoding, 'replace')

    patternc = opts.patternc

    eol = opts.eol_marker

    if opts.show_color:

        path_start = FG.MAGENTA

        sep = color_string(':', FG.BOLD_CYAN)

        rev_sep = color_string('~', FG.BOLD_YELLOW)

    else:

        path_start = ""

        sep = ":"

        rev_sep = "~"

    if opts.files_with_matches or opts.files_without_match:

        if opts.print_revno:

            format = "%s%%(path)s%s%%(revno)s%s" % (path_start, rev_sep, eol)

        else:

            format = "%s%%(path)s%s" % (path_start, eol)

    elif opts.print_revno and opts.line_number:

        format = "%s%%(path)s%s%%(revno)s%s%%(lineno)d%s%%(line)s%s" % (

            path_start, rev_sep, sep, sep, eol)

    elif opts.print_revno:

        format = "%s%%(path)s%s%%(revno)s%s%%(line)s%s" % (

            path_start, rev_sep, sep, eol)

    elif opts.line_number:

        format = "%s%%(path)s%s%%(lineno)d%s%%(line)s%s" % (

            path_start, sep, sep, eol)

    else:

        format = "%s%%(path)s%s%%(line)s%s" % (path_start, sep, eol)

    def _line_writer(**kwargs):

        """Write formatted line from arguments given by underlying opts"""

        line = format % kwargs

        write(line)

        # GZ 2010-06-02: Need to return line for the 'res_cache' hack to

        #                avoiding checking the same file twice, clean this

        #                up later by changing that mechanism.

        return line

    if not opts.show_color:

        return _line_writer

    if not opts.fixed_string:

        sub = re.compile(pattern.join(("((?:",")+)")), patternc.flags).sub

        highlight = color_string("\\1", FG.BOLD_RED)

        def _line_writer_regexp_highlighted(line, **kwargs):

            """Write formatted line with matched pattern highlighted"""

            return _line_writer(line=sub(highlight, line), **kwargs)

        return _line_writer_regexp_highlighted

    highlighted = color_string(pattern, FG.BOLD_RED)

    def _line_writer_fixed_highlighted(line, **kwargs):

        """Write formatted line with string searched for highlighted"""

        return _line_writer(line=line.replace(pattern, highlighted), **kwargs)

    return _line_writer_fixed_highlighted

def _file_grep(file_text, path, opts, revno, path_prefix=None):

    res = []

    res_append = res.append

    pattern = opts.pattern.encode(_user_encoding, 'replace')

    patternc = opts.patternc

    # test and skip binary files

    if '\x00' in file_text[:1024]:

        if opts.verbose:

            trace.warning("Binary file '%s' skipped." % path)

        return res

    if path_prefix and path_prefix != '.':

        # user has passed a dir arg, show that as result prefix

        path = osutils.pathjoin(path_prefix, path)

    path = path.encode(_terminal_encoding, 'replace')

    writeline = opts.line_writer

    if opts.files_with_matches or opts.files_without_match:

        # While printing files with matches we only have two case

        # print file name or print file name with revno.

        found = False

        if opts.fixed_string:

            for line in file_text.splitlines():

                if pattern in line:

                    found = True

                    break

        else:

            for line in file_text.splitlines():

                if patternc.search(line):

                    found = True

                    break

        if (opts.files_with_matches and found) or \

                (opts.files_without_match and not found):

            res_append(writeline(path=path, revno=revno))

        return res # return from files_with|without_matches

    if opts.line_number:

        if opts.fixed_string:

            for index, line in enumerate(file_text.splitlines()):

                if pattern in line:

                    res_append(writeline(path=path, revno=revno,

                        lineno=index+1, line=line))

        else:

            for index, line in enumerate(file_text.splitlines()):

                if patternc.search(line):

                    res_append(writeline(path=path, revno=revno,

                        lineno=index+1, line=line))

    else:

        if opts.fixed_string:

            for line in file_text.splitlines():

                if pattern in line:

                    res_append(writeline(path=path, revno=revno, line=line))

        else:

            for line in file_text.splitlines():

                if patternc.search(line):

                    res_append(writeline(path=path, revno=revno, line=line))

    return res