diffoscope 39__tar.gz

diffoscope-39/PKG-INFO

@@ -0,0 +1,103 @@
+Metadata-Version: 1.1
+Name: diffoscope
+Version: 39
+Summary: in-depth comparison of files, archives, and directories
+Home-page: https://diffoscope.org/
+Author: Lunar
+Author-email: lunar@debian.org
+License: GPL-3+
+Description: diffoscope
+        ==========
+        
+        diffoscope will try to get to the bottom of what makes files or
+        directories different. It will recursively unpack archives of many kinds
+        and transform various binary formats into more human readable form to
+        compare them. It can compare two tarballs, ISO images, or PDF just as
+        easily.
+        
+        It can be scripted through error codes, and a report can be produced
+        with the detected differences. The report can be text or HTML.
+        When no type of report has been selected, diffoscope defaults
+        to write a text report on the standard output.
+        
+        diffoscope will exit with 0 if there's no differences and 1 if there
+        are. An HTML report can be produced with the detected differences.
+        
+        diffoscope is developed as part of the `“reproducible builds” Debian
+        project <https://wiki.debian.org/ReproducibleBuilds>`_.
+        It is meant to be able to quickly understand why two builds of the same
+        package produce different outputs. diffoscope was previously named
+        debbindiff.
+        
+        Example
+        -------
+        
+        To compare two files in-depth and produce an HTML report, run something like::
+        
+            $ bin/diffoscope --html output.html build1.changes build2.changes
+        
+        *diffoscope* can also compare non-existent files::
+        
+            $ bin/diffoscope /nonexistent archive.zip
+        
+        To get all possible options, run::
+        
+            $ bin/diffoscope --help
+        
+        External dependencies
+        ---------------------
+        
+        diffoscope requires Python 3 and the following modules available on PyPI:
+        `libarchive-c <https://pypi.python.org/pypi/libarchive-c>`_,
+        `python-debian <https://pypi.python.org/pypi/python-debian>`_,
+        `python-magic <https://pypi.python.org/pypi/python-debian>`_.
+        
+        Optionally, the following modules will enhance it:
+        
+        * ``tlsh`` is used to recognize file renames.
+          It is build from `tlsh source
+          <https://github.com/trendmicro/tlsh>`_.
+          Available on Debian as ``python3-tlsh``.
+        * ``rpm-python`` is used to inspect RPM files.
+          It is built from `rpm
+          <http://rpm.org/>`_.
+          Available on Debian and Fedora as ``python3-rpm``.
+        * ``Magic-file-extension`` can be used instead of
+          ``python-magic``. It is built from `file
+          <http://www.darwinsys.com/file/>`_.
+          Available on Debian and Fedora as ``python3-magic``.
+        
+        The various comparators rely on external commands being available. To
+        get a list of them, please run::
+        
+            $ bin/diffoscope --list-tools
+        
+        Contributors
+        ------------
+        
+        Lunar, Reiner Herrmann, Chris Lamb, Helmut Grohne, Holger Levsen,
+        Mattia Rizzolo, Daniel Kahn Gillmor, Paul Gevers, Peter De Wachter,
+        Yasushi SHOJI.
+        
+        License
+        -------
+        
+        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 <http://www.gnu.org/licenses/>.
+        
+Platform: UNKNOWN
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)
+Classifier: Operating System :: POSIX
+Classifier: Topic :: Utilities

diffoscope-39/README.rst

@@ -0,0 +1,88 @@
+diffoscope
+==========
+
+diffoscope will try to get to the bottom of what makes files or
+directories different. It will recursively unpack archives of many kinds
+and transform various binary formats into more human readable form to
+compare them. It can compare two tarballs, ISO images, or PDF just as
+easily.
+
+It can be scripted through error codes, and a report can be produced
+with the detected differences. The report can be text or HTML.
+When no type of report has been selected, diffoscope defaults
+to write a text report on the standard output.
+
+diffoscope will exit with 0 if there's no differences and 1 if there
+are. An HTML report can be produced with the detected differences.
+
+diffoscope is developed as part of the `“reproducible builds” Debian
+project <https://wiki.debian.org/ReproducibleBuilds>`_.
+It is meant to be able to quickly understand why two builds of the same
+package produce different outputs. diffoscope was previously named
+debbindiff.
+
+Example
+-------
+
+To compare two files in-depth and produce an HTML report, run something like::
+
+    $ bin/diffoscope --html output.html build1.changes build2.changes
+
+*diffoscope* can also compare non-existent files::
+
+    $ bin/diffoscope /nonexistent archive.zip
+
+To get all possible options, run::
+
+    $ bin/diffoscope --help
+
+External dependencies
+---------------------
+
+diffoscope requires Python 3 and the following modules available on PyPI:
+`libarchive-c <https://pypi.python.org/pypi/libarchive-c>`_,
+`python-debian <https://pypi.python.org/pypi/python-debian>`_,
+`python-magic <https://pypi.python.org/pypi/python-debian>`_.
+
+Optionally, the following modules will enhance it:
+
+* ``tlsh`` is used to recognize file renames.
+  It is build from `tlsh source
+  <https://github.com/trendmicro/tlsh>`_.
+  Available on Debian as ``python3-tlsh``.
+* ``rpm-python`` is used to inspect RPM files.
+  It is built from `rpm
+  <http://rpm.org/>`_.
+  Available on Debian and Fedora as ``python3-rpm``.
+* ``Magic-file-extension`` can be used instead of
+  ``python-magic``. It is built from `file
+  <http://www.darwinsys.com/file/>`_.
+  Available on Debian and Fedora as ``python3-magic``.
+
+The various comparators rely on external commands being available. To
+get a list of them, please run::
+
+    $ bin/diffoscope --list-tools
+
+Contributors
+------------
+
+Lunar, Reiner Herrmann, Chris Lamb, Helmut Grohne, Holger Levsen,
+Mattia Rizzolo, Daniel Kahn Gillmor, Paul Gevers, Peter De Wachter,
+Yasushi SHOJI.
+
+License
+-------
+
+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 <http://www.gnu.org/licenses/>.

diffoscope-39/diffoscope/__init__.py

@@ -0,0 +1,116 @@
+# -*- coding: utf-8 -*-
+#
+# diffoscope: in-depth comparison of files, archives, and directories
+#
+# Copyright © 2014-2015 Jérémy Bobbio <lunar@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 <http://www.gnu.org/licenses/>.
+
+from functools import wraps
+import logging
+from distutils.spawn import find_executable
+import os
+
+VERSION = "39"
+
+logger = logging.getLogger("diffoscope")
+logger.setLevel(logging.WARNING)
+ch = logging.StreamHandler()
+ch.setLevel(logging.DEBUG)
+logger.addHandler(ch)
+formatter = logging.Formatter('%(levelname)8s %(message)s')
+ch.setFormatter(formatter)
+
+
+class RequiredToolNotFound(Exception):
+    PROVIDERS = { 'ar':         { 'debian': 'binutils-multiarch' }
+                , 'bzip2':      { 'debian': 'bzip2' }
+                , 'cbfstool':   {}
+                , 'cmp':        { 'debian': 'diffutils' }
+                , 'cpio':       { 'debian': 'cpio' }
+                , 'diff':       { 'debian': 'diffutils' }
+                , 'file':       { 'debian': 'file' }
+                , 'find':       { 'debian': 'findutils' }
+                , 'getfacl':    { 'debian': 'acl' }
+                , 'ghc':        { 'debian': 'ghc' }
+                , 'gpg':        { 'debian': 'gnupg' }
+                , 'gzip':       { 'debian': 'gzip' }
+                , 'isoinfo':    { 'debian': 'genisoimage' }
+                , 'javap':      { 'debian': 'default-jdk | java-sdk' }
+                , 'ls':         { 'debian': 'coreutils' }
+                , 'lsattr':     { 'debian': 'e2fsprogs' }
+                , 'msgunfmt':   { 'debian': 'gettext' }
+                , 'objdump':    { 'debian': 'binutils-multiarch' }
+                , 'pdftk':      { 'debian': 'pdftk' }
+                , 'pdftotext':  { 'debian': 'poppler-utils' }
+                , 'pedump':     { 'debian': 'mono-utils' }
+                , 'ppudump':    { 'debian': 'fp-utils' }
+                , 'readelf':    { 'debian': 'binutils-multiarch' }
+                , 'rpm2cpio':   { 'debian': 'rpm2cpio' }
+                , 'showttf':    { 'debian': 'fontforge-extras' }
+                , 'sng':        { 'debian': 'sng' }
+                , 'stat':       { 'debian': 'coreutils' }
+                , 'sqlite3':    { 'debian': 'sqlite3'}
+                , 'tar':        { 'debian': 'tar'}
+                , 'unsquashfs': { 'debian': 'squashfs-tools' }
+                , 'xxd':        { 'debian': 'vim-common' }
+                , 'xz':         { 'debian': 'xz-utils' }
+                , 'zipinfo':    { 'debian': 'unzip' }
+              }
+
+    def __init__(self, command):
+        self.command = command
+
+    def get_package(self):
+        providers = RequiredToolNotFound.PROVIDERS.get(self.command, None)
+        if not providers:
+            return None
+        # XXX: hardcode Debian for now
+        return providers['debian']
+
+
+# decorator that checks if the specified tool is installed
+def tool_required(command):
+    if not hasattr(tool_required, 'all'):
+        tool_required.all = set()
+    tool_required.all.add(command)
+    def wrapper(original_function):
+        if find_executable(command):
+            @wraps(original_function)
+            def tool_check(*args, **kwargs):
+                return original_function(*args, **kwargs)
+        else:
+            @wraps(original_function)
+            def tool_check(*args, **kwargs):
+                raise RequiredToolNotFound(command)
+        return tool_check
+    return wrapper
+
+
+def set_locale():
+    """Normalize locale so external tool gives us stable and properly
+    encoded output"""
+
+    for var in ['LANGUAGE', 'LC_ALL']:
+        if var in os.environ:
+            del os.environ[var]
+    for var in ['LANG', 'LC_NUMERIC', 'LC_TIME', 'LC_COLLATE', 'LC_MONETARY',
+                'LC_MESSAGES', 'LC_PAPER', 'LC_NAME', 'LC_ADDRESS',
+                'LC_TELEPHONE', 'LC_MEASUREMENT', 'LC_IDENTIFICATION']:
+        os.environ[var] = 'C'
+    os.environ['LC_CTYPE'] = 'C.UTF-8'
+    os.environ['TZ'] = 'UTC'
+
+
+

diffoscope-39/diffoscope/__main__.py

@@ -0,0 +1,158 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+#
+# diffoscope: in-depth comparison of files, archives, and directories
+#
+# Copyright © 2014-2015 Jérémy Bobbio <lunar@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 <http://www.gnu.org/licenses/>.
+
+import argparse
+from contextlib import contextmanager
+import logging
+import codecs
+import os
+import signal
+import sys
+import traceback
+try:
+    import tlsh
+except ImportError:
+    tlsh = None
+from diffoscope import logger, VERSION, set_locale
+import diffoscope.comparators
+from diffoscope.config import Config
+from diffoscope.presenters.html import output_html
+from diffoscope.presenters.text import output_text
+
+
+def create_parser():
+    parser = argparse.ArgumentParser(
+        description='Highlight differences between two builds '
+                    'of Debian packages')
+    parser.add_argument('--version', action='version',
+                        version='diffoscope %s' % VERSION)
+    parser.add_argument('--list-tools', nargs=0, action=ListToolsAction,
+                        help='show external tools required and exit')
+    parser.add_argument('--debug', dest='debug', action='store_true',
+                        default=False, help='display debug messages')
+    parser.add_argument('--debugger', action='store_true',
+                        help='Open the python debugger in case of crashes.')
+    parser.add_argument('--html', metavar='output', dest='html_output',
+                        help='write HTML report to given file (use - for stdout)')
+    parser.add_argument('--text', metavar='output', dest='text_output',
+                        help='write plain text output to given file (use - for stdout)')
+    parser.add_argument('--max-report-size', metavar='BYTES',
+                        dest='max_report_size', type=int,
+                        help='maximum bytes written in report (default: %d)' %
+                        Config.general.max_report_size,
+                        default=Config.general.max_report_size)
+    parser.add_argument('--max-diff-block-lines', dest='max_diff_block_lines', type=int,
+                        help='maximum number of lines per diff block (default: %d)' %
+                        Config.general.max_diff_block_lines,
+                        default=Config.general.max_diff_block_lines)
+    parser.add_argument('--max-diff-input-lines', dest='max_diff_input_lines', type=int,
+                        help='maximum number of lines fed to diff (default: %d)' %
+                        Config.general.max_diff_input_lines,
+                        default=Config.general.max_diff_input_lines)
+    parser.add_argument('--fuzzy-threshold', dest='fuzzy_threshold', type=int,
+                        help='threshold for fuzzy-matching '
+                             '(0 to disable, %d is default, 400 is high fuzziness)' %
+                             (Config.general.fuzzy_threshold),
+                        default=Config.general.fuzzy_threshold)
+    parser.add_argument('--new-file', dest='new_file', action='store_true',
+                        help='treat absent files as empty')
+    parser.add_argument('--css', metavar='url', dest='css_url',
+                        help='link to an extra CSS for the HTML report')
+    parser.add_argument('file1', help='first file to compare')
+    parser.add_argument('file2', help='second file to compare')
+    if not tlsh:
+        parser.epilog = 'File renaming detection based on fuzzy-matching is currently disabled. It can be enabled by installing the “tlsh” module available at https://github.com/trendmicro/tlsh'
+    return parser
+
+
+@contextmanager
+def make_printer(path):
+    if path == '-':
+        output = sys.stdout
+    else:
+        output = codecs.open(path, 'w', encoding='utf-8')
+    def print_func(*args, **kwargs):
+        kwargs['file'] = output
+        print(*args, **kwargs)
+    yield print_func
+    if path != '-':
+        output.close()
+
+
+class ListToolsAction(argparse.Action):
+    def __call__(self, parser, namespace, values, option_string=None):
+        from diffoscope import tool_required, RequiredToolNotFound
+        print("External tools required:")
+        print(', '.join(tool_required.all))
+        print()
+        print("Available in packages:")
+        print(', '.join(sorted(filter(None, { RequiredToolNotFound.PROVIDERS[k].get('debian', None) for k in tool_required.all }))))
+        sys.exit(0)
+
+
+def run_diffoscope(parsed_args):
+    if not tlsh and Config.general.fuzzy_threshold != parsed_args.fuzzy_threshold:
+        logger.warning('Fuzzy-matching is currently disabled as the “tlsh” module is unavailable.')
+    Config.general.max_diff_block_lines = parsed_args.max_diff_block_lines
+    Config.general.max_diff_input_lines = parsed_args.max_diff_input_lines
+    Config.general.max_report_size = parsed_args.max_report_size
+    Config.general.fuzzy_threshold = parsed_args.fuzzy_threshold
+    Config.general.new_file = parsed_args.new_file
+    if parsed_args.debug:
+        logger.setLevel(logging.DEBUG)
+    set_locale()
+    difference = diffoscope.comparators.compare_root_paths(
+        parsed_args.file1, parsed_args.file2)
+    if difference:
+        if parsed_args.html_output:
+            with make_printer(parsed_args.html_output) as print_func:
+                output_html(difference, css_url=parsed_args.css_url, print_func=print_func)
+        if (parsed_args.text_output and parsed_args.text_output != parsed_args.html_output) or not parsed_args.html_output:
+            with make_printer(parsed_args.text_output or '-') as print_func:
+                output_text(difference, print_func=print_func)
+        return 1
+    return 0
+
+
+def sigterm_handler(signo, stack_frame):
+    sys.exit(2)
+
+
+def main(args=None):
+    if args is None:
+        args = sys.argv[1:]
+    signal.signal(signal.SIGTERM, sigterm_handler)
+    parsed_args = None
+    try:
+        parser = create_parser()
+        parsed_args = parser.parse_args(args)
+        sys.exit(run_diffoscope(parsed_args))
+    except KeyboardInterrupt:
+        logger.info('Keyboard Interrupt')
+        sys.exit(2)
+    except Exception:
+        traceback.print_exc()
+        if parsed_args and parsed_args.debugger:
+            import pdb
+            pdb.post_mortem()
+        sys.exit(2)
+
+if __name__ == '__main__':
+    main()