Commit bb2ff3b8 authored by Chris Lamb's avatar Chris Lamb 👀
Browse files

Add --exclude option. (Closes: #854783) 



Signed-off-by: Chris Lamb's avatarChris Lamb <lamby@debian.org>
parent acebcc0b

diffoscope/comparators/directory.py

+2 −0
Original line number Diff line number Diff line
@@ -25,6 +25,7 @@ import subprocess 
from diffoscope.exc import RequiredToolNotFound

from diffoscope.tools import tool_required

from diffoscope.progress import Progress

from diffoscope.excludes import filter_excludes

from diffoscope.difference import Difference



from .binary import FilesystemFile
@@ -167,6 +168,7 @@ class FilesystemDirectory(object): 
        my_names = my_container.get_member_names()

        other_names = other_container.get_member_names()

        to_compare = set(my_names).intersection(other_names)

        to_compare = set(filter_excludes(to_compare))

        with Progress(len(to_compare)) as p:

            for name in sorted(to_compare):

                my_file = my_container.get_member(name)

diffoscope/comparators/utils/compare.py

+6 −0
Original line number Diff line number Diff line
@@ -26,6 +26,7 @@ import binascii 
from diffoscope.tools import tool_required

from diffoscope.exc import RequiredToolNotFound

from diffoscope.config import Config

from diffoscope.excludes import any_excluded

from diffoscope.profiling import profile

from diffoscope.difference import Difference
@@ -52,6 +53,8 @@ def compare_root_paths(path1, path2): 


    if not Config().new_file:

        bail_if_non_existing(path1, path2)

    if any_excluded(path1, path2):

        return None

    if os.path.isdir(path1) and os.path.isdir(path2):

        return compare_directories(path1, path2)

    container1 = FilesystemDirectory(os.path.dirname(path1)).as_container
@@ -69,6 +72,9 @@ def compare_files(file1, file2, source=None): 
        file2.__class__.__name__,

    )



    if any_excluded(file1.name, file2.name):

        return None



    with profile('has_same_content_as', file1):

        if file1.has_same_content_as(file2):

            logger.debug("has_same_content_as returned True; skipping further comparisons")

diffoscope/comparators/utils/libarchive.py

+5 −0
Original line number Diff line number Diff line
@@ -25,6 +25,7 @@ import logging 
import libarchive

import collections



from diffoscope.excludes import any_excluded

from diffoscope.tempfiles import get_temporary_directory



from ..device import Device
@@ -212,6 +213,10 @@ class LibarchiveContainer(Archive): 
                if entry.isdir:

                    continue



                # Save extracting excluded files

                if any_excluded(entry.pathname):

                    continue



                # Maintain a mapping of archive path to the extracted path,

                # avoiding the need to sanitise filenames.

                dst = os.path.join(tmpdir, '{}'.format(idx))

diffoscope/config.py

+1 −0
Original line number Diff line number Diff line
@@ -33,6 +33,7 @@ class Config(object): 
    new_file = False

    fuzzy_threshold = 60

    enforce_constraints = True

    excludes = ()



    _singleton = {}

diffoscope/excludes.py

0 → 100644
+42 −0
Original line number Diff line number Diff line 
# -*- coding: utf-8 -*-

#

# diffoscope: in-depth comparison of files, archives, and directories

#

# Copyright © 2017 Chris Lamb <lamby@debian.org>

#

# diffoscope 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 3 of the License, or

# (at your option) any later version.

#

# diffoscope 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 diffoscope.  If not, see <https://www.gnu.org/licenses/>.



import fnmatch

import logging



from diffoscope.config import Config



logger = logging.getLogger(__name__)





def filter_excludes(filenames):

    result = []



    for x in filenames:

        for y in Config().excludes:

            if fnmatch.fnmatchcase(x, y):

                logger.debug("Excluding %s as it matches pattern '%s'", x, y)

                break

        else:

            result.append(x)



    return result



def any_excluded(*filenames):

    return len(filter_excludes(filenames)) != len(filenames)