Python difflib.unified_diff() Examples

def get_diff_text(old, new, filename):
    """Return text of unified diff between old and new."""
    newline = '\n'
    diff = difflib.unified_diff(
        old, new,
        'original/' + filename,
        'fixed/' + filename,
        lineterm=newline)

    text = ''
    for line in diff:
        text += line

        # Work around missing newline (http://bugs.python.org/issue2142).
        if text and not line.endswith(newline):
            text += newline + r'\ No newline at end of file' + newline

    return text 

def get_diff_text(old, new, filename):
    """Return text of unified diff between old and new."""
    newline = '\n'
    diff = difflib.unified_diff(
        old, new,
        'original/' + filename,
        'fixed/' + filename,
        lineterm=newline)

    text = ''
    for line in diff:
        text += line

        # Work around missing newline (http://bugs.python.org/issue2142).
        if text and not line.endswith(newline):
            text += newline + r'\ No newline at end of file' + newline

    return text 

def test_05_package_to_api2(self):

        context = {"model": model,
                 "session": model.Session}

        pkg = model.Session.query(model.Package).filter_by(name='annakarenina').first()

        as_dict = pkg.as_dict(ref_package_by='id', ref_group_by='id')
        dictize = package_to_api2(pkg, context)

        as_dict_string = pformat(as_dict)
        dictize_string = pformat(dictize)
        print as_dict_string
        print dictize_string

        assert package_to_api2(pkg, context) == dictize, "\n".join(unified_diff(as_dict_string.split("\n"), dictize_string.split("\n"))) 

def get_diff_text(old, new, filename):
    """Return text of unified diff between old and new."""
    newline = '\n'
    diff = difflib.unified_diff(
        old, new,
        'original/' + filename,
        'fixed/' + filename,
        lineterm=newline)

    text = ''
    for line in diff:
        text += line

        # Work around missing newline (http://bugs.python.org/issue2142).
        if text and not line.endswith(newline):
            text += newline + r'\ No newline at end of file' + newline

    return text 

def test_06_package_to_api2_with_relationship(self):

        context = {"model": model,
                 "session": model.Session}

        pkg = model.Session.query(model.Package).filter_by(name='homer').one()

        as_dict = pkg.as_dict(ref_package_by='id', ref_group_by='id')
        as_dict['license_title'] = None
        as_dict['num_tags'] = 0
        as_dict['num_resources'] = 0
        dictize = package_to_api2(pkg, context)

        as_dict["relationships"].sort(key=lambda x:x.items())
        dictize["relationships"].sort(key=lambda x:x.items())

        # the is_dict method doesn't care about organizations
        del dictize['organization']
        as_dict_string = pformat(as_dict)
        dictize_string = pformat(dictize)
        print as_dict_string
        print dictize_string

        assert as_dict == dictize, "\n".join(unified_diff(as_dict_string.split("\n"), dictize_string.split("\n"))) 

def _assertSchemaEqual(expected, actual, testcase):
  """Utility method to dump diffs if the schema aren't equal.

  Args:
    expected: object, the expected results.
    actual: object, the actual results.
    testcase: unittest.TestCase, the test case this assertion is used within.
  """
  if expected != actual:
    expected_text = json.dumps(expected, indent=2, sort_keys=True)
    actual_text = json.dumps(actual, indent=2, sort_keys=True)
    diff = difflib.unified_diff(expected_text.splitlines(True),
                                actual_text.splitlines(True),
                                fromfile='expected.schema',
                                tofile='actual.schema')
    diff_text = ''.join(list(diff))
    testcase.fail('Schema differs from expected:\n%s' % diff_text) 

def main():

    usage = "usage: %prog [options] fromfile tofile"
    parser = optparse.OptionParser(usage)
    parser.add_option("-c", action="store_true", default=False, help='Produce a context format diff (default)')
    parser.add_option("-u", action="store_true", default=False, help='Produce a unified format diff')
    parser.add_option("-m", action="store_true", default=False, help='Produce HTML side by side diff (can use -c and -l in conjunction)')
    parser.add_option("-n", action="store_true", default=False, help='Produce a ndiff format diff')
    parser.add_option("-l", "--lines", type="int", default=3, help='Set number of context lines (default 3)')
    (options, args) = parser.parse_args()

    if len(args) == 0:
        parser.print_help()
        sys.exit(1)
    if len(args) != 2:
        parser.error("need to specify both a fromfile and tofile")

    n = options.lines
    fromfile, tofile = args

    fromdate = time.ctime(os.stat(fromfile).st_mtime)
    todate = time.ctime(os.stat(tofile).st_mtime)
    fromlines = open(fromfile, 'U').readlines()
    tolines = open(tofile, 'U').readlines()

    if options.u:
        diff = difflib.unified_diff(fromlines, tolines, fromfile, tofile, fromdate, todate, n=n)
    elif options.n:
        diff = difflib.ndiff(fromlines, tolines)
    elif options.m:
        diff = difflib.HtmlDiff().make_file(fromlines,tolines,fromfile,tofile,context=options.c,numlines=n)
    else:
        diff = difflib.context_diff(fromlines, tolines, fromfile, tofile, fromdate, todate, n=n)

    sys.stdout.writelines(diff) 

def test_bootstrap_copy(self):
        wf = OBSLocal.StagingWorkflow()

        fc = FreezeCommand(wf.api)

        fp = self._get_fixture_path('staging-meta-for-bootstrap-copy.xml')
        fixture = subprocess.check_output('/usr/bin/xmllint --format %s' % fp, shell=True).decode('utf-8')

        f = tempfile.NamedTemporaryFile(delete=False)
        f.write(fc.prj_meta_for_bootstrap_copy('openSUSE:Factory:Staging:A'))
        f.close()

        output = subprocess.check_output('/usr/bin/xmllint --format %s' % f.name, shell=True).decode('utf-8')

        for line in difflib.unified_diff(fixture.split("\n"), output.split("\n")):
            print(line)
        self.assertEqual(output, fixture) 

def assertLinesEqual(self, expected, actual, message):
        if actual != expected:
            if len(actual) < len(expected):
                sys.stderr.write(
                    dedent(
                        """\
                    WARNING: the actual text is shorter that the expected text.
                             Some information may be LOST!
                    """
                    )
                )
            for line in difflib.unified_diff(
                expected, actual, fromfile="<expected>", tofile="<actual>"
            ):
                if not line.endswith("\n"):
                    line += "\n"
                sys.stderr.write(line)
            self.fail(message) 

def _cache_tlds(self, tlds):
        '''Logs a diff of the new TLDs and caches them on disk, according to
        settings passed to __init__.'''
        if LOG.isEnabledFor(logging.DEBUG):
            import difflib
            snapshot_stream = pkg_resources.resource_stream(__name__, '.tld_set_snapshot')
            with closing(snapshot_stream) as snapshot_file:
                snapshot = sorted(
                    json.loads(snapshot_file.read().decode('utf-8'))
                )
            new = sorted(tlds)
            LOG.debug('computed TLD diff:\n' + '\n'.join(difflib.unified_diff(
                snapshot,
                new,
                fromfile=".tld_set_snapshot",
                tofile=self.cache_file
            )))

        if self.cache_file:
            try:
                with open(self.cache_file, 'w') as cache_file:
                    json.dump(tlds, cache_file)
            except IOError as ioe:
                LOG.warn("unable to cache TLDs in file %s: %s", self.cache_file, ioe) 

def get_correct_indentation_diff(code, filename):
    """
    Generate a diff to make code correctly indented.

    :param code: a string containing a file's worth of Python code
    :param filename: the filename being considered (used in diff generation only)
    :returns: a unified diff to make code correctly indented, or
              None if code is already correctedly indented
    """
    code_buffer = StringIO(code)
    output_buffer = StringIO()
    reindenter = reindent.Reindenter(code_buffer)
    reindenter.run()
    reindenter.write(output_buffer)
    reindent_output = output_buffer.getvalue()
    output_buffer.close()
    if code != reindent_output:
        diff_generator = difflib.unified_diff(code.splitlines(True), reindent_output.splitlines(True),
                                              fromfile=filename, tofile=filename + " (reindented)")
        # work around http://bugs.python.org/issue2142
        diff_tuple = map(clean_diff_line_for_python_bug_2142, diff_generator)
        diff = "".join(diff_tuple)
        return diff
    else:
        return None 

def _print_diff(self, diff, indent_level):
        if isinstance(diff, dict):
            try:
                diff = '\n'.join(difflib.unified_diff(diff['before'].splitlines(),
                                                      diff['after'].splitlines(),
                                                      fromfile=diff.get('before_header',
                                                                        'new_file'),
                                                      tofile=diff['after_header']))
            except AttributeError:
                diff = dict_diff(diff['before'], diff['after'])
        if diff:
            diff = colorize(diff, 'changed')
            print(self._indent_text(diff, indent_level+4)) 

def print_diffs(text1, text2):
    "Prints unified diffs for two texts"
    lines1 = text1.splitlines(True)
    lines2 = text2.splitlines(True)
    diffs = difflib.unified_diff(lines1, lines2, n=0, fromfile='expected',
                                 tofile='got')
    print '\n' + ''.join(diffs) 

def test_tab_delimiter(self):
        args = ['one', 'two', 'Original', 'Current',
            '2005-01-26 23:30:50', '2010-04-02 10:20:52']
        ud = difflib.unified_diff(*args, lineterm='')
        self.assertEqual(list(ud)[0:2], [
                           "--- Original\t2005-01-26 23:30:50",
                           "+++ Current\t2010-04-02 10:20:52"])
        cd = difflib.context_diff(*args, lineterm='')
        self.assertEqual(list(cd)[0:2], [
                           "*** Original\t2005-01-26 23:30:50",
                           "--- Current\t2010-04-02 10:20:52"]) 

def _print_diff(self, diff, indent_level):
        if isinstance(diff, dict):
            try:
                diff = '\n'.join(difflib.unified_diff(diff['before'].splitlines(),
                                                      diff['after'].splitlines(),
                                                      fromfile=diff.get('before_header',
                                                                        'new_file'),
                                                      tofile=diff['after_header']))
            except AttributeError:
                diff = dict_diff(diff['before'], diff['after'])
        if diff:
            diff = colorize(diff, 'changed')
            print(self._indent_text(diff, indent_level+4)) 

def _print_diff(self, diff, indent_level):
        if isinstance(diff, dict):
            try:
                diff = '\n'.join(difflib.unified_diff(diff['before'].splitlines(),
                                                      diff['after'].splitlines(),
                                                      fromfile=diff.get('before_header',
                                                                        'new_file'),
                                                      tofile=diff['after_header']))
            except AttributeError:
                diff = dict_diff(diff['before'], diff['after'])
        if diff:
            diff = colorize(diff, 'changed')
            print(self._indent_text(diff, indent_level+4)) 

def _show_diff(self, file_contents):
        for line in unified_diff(
            file_contents.splitlines(1),
            self.output.splitlines(1),
            fromfile=self.file_path + ':before',
            tofile=self.file_path + ':after',
            fromfiledate=str(datetime.fromtimestamp(os.path.getmtime(self.file_path))
                             if self.file_path else datetime.now()),
            tofiledate=str(datetime.now())
        ):
            sys.stdout.write(line) 

def compare_strings(left, right):
    left_str = left.replace(r'\n', '\n')
    right_str = right.replace(r'\n', '\n')
    diff = list(difflib.unified_diff(left_str.splitlines(), right_str.splitlines(), lineterm=''))
    if diff:
        return "    " + '\n    '.join([color_diff_line(line) for line in diff])
    else:
        return None 

def diff_texts(a, b, filename):
    """Return a unified diff of two strings."""
    a = a.splitlines()
    b = b.splitlines()
    return difflib.unified_diff(a, b, filename, filename,
                                "(original)", "(refactored)",
                                lineterm="") 

def test_04_package_to_api1_with_relationship(self):

        context = {"model": model,
                 "session": model.Session}

        create = CreateTestData

        create.create_family_test_data()
        pkg = model.Session.query(model.Package).filter_by(name='homer').one()

        as_dict = pkg.as_dict()
        as_dict['license_title'] = None
        as_dict['num_tags'] = 0
        as_dict['num_resources'] = 0
        dictize = package_to_api1(pkg, context)

        as_dict["relationships"].sort(key=lambda x:x.items())
        dictize["relationships"].sort(key=lambda x:x.items())

        # the is_dict method doesn't care about organizations
        del dictize['organization']
        as_dict_string = pformat(as_dict)
        dictize_string = pformat(dictize)
        print as_dict_string
        print dictize_string

        assert as_dict == dictize, "\n".join(unified_diff(as_dict_string.split("\n"), dictize_string.split("\n"))) 

def diff_html(self, html1, html2):
        return '\n'.join(unified_diff(html1.split('\n'),
                                      html2.split('\n'))) 

def _compare(formatted_code, expected_output_code):
    diff = "\n".join(
        difflib.unified_diff(
            expected_output_code.splitlines(), formatted_code.splitlines()
        )
    )
    assert formatted_code == expected_output_code, diff 

def _tree_invariant_check(input_code, formatted_code):
    input_code_parse_tree = parser.parse(input_code)
    formatted_code_parse_tree = parser.parse(formatted_code)
    loosen_tree_transformer = LoosenTreeTransformer()
    input_code_parse_tree = loosen_tree_transformer.transform(input_code_parse_tree)
    formatted_code_parse_tree = loosen_tree_transformer.transform(
        formatted_code_parse_tree
    )
    diff = "\n".join(
        difflib.unified_diff(
            str(input_code_parse_tree.pretty()).splitlines(),
            str(formatted_code_parse_tree.pretty()).splitlines(),
        )
    )
    assert input_code_parse_tree == formatted_code_parse_tree, diff 

def indent_files(files, diff=False, debug=False, level=0, inplace=False):
    output = []
    for f in files:
        dst = indent(f, debug=debug, level=level)
        output.append([f,dst])

    # First, copy to inplace
    if inplace:
        for src,dst in output:
            shutil.copyfile(dst,src)
        return True

    # now, compare
    failed = []
    for src,dst in output:
        if filecmp.cmp(src,dst) == 0:
            failed.append([src, dst])
    if len(failed) > 0:
        if not diff:
            print 'Found %u badly indented files:' % len(failed)
            for src,dst in failed:
                print '  ' + src
        else:
            for src,dst in failed:
                s = open(src, 'r').readlines()
                d = open(dst, 'r').readlines()
                for line in difflib.unified_diff(s, d, fromfile=src, tofile=dst):
                    sys.stdout.write(line)
        return False
    return True 

def get_diff(
            cls, a, b, fromfile='', tofile='', fromfiledate='', tofiledate='',
            n=10):

        lines = difflib.unified_diff(
            a, b, fromfile, tofile, fromfiledate, tofiledate, n)
        lines = [line.rstrip() for line in lines]

        if lines:
            return cls(lines=lines)
        else:
            return Text(text='No differences') 

def is_same_file(fname1, fname2, ignore_regexp=None, replace_regexp=None, replace_what='.', replace_with='.',
                 diff=None, is_binary=False, strip_blanks=True):
    """ Test if two files are the same.

    If ignore_regexp is passed, it must be a Regular Expression
    which will ignore matched lines on both files.

    If replace_regexp is passed, all lines matching RE (string) will perform
    a string substitution of A into B. This if done *AFTER* ignoreLinesRE.
    """
    if fname1 == fname2:
        return True

    if not os.path.exists(fname1) and not os.path.exists(fname2):
        return True

    if not os.path.exists(fname1) or not os.path.exists(fname2):
        return False

    if is_binary:
        return open(fname1, 'rb').read() == open(fname2, 'rb').read()

    r1 = get_file_lines(fname1, ignore_regexp, replace_regexp, replace_what, replace_with, strip_blanks)
    r2 = get_file_lines(fname2, ignore_regexp, replace_regexp, replace_what, replace_with, strip_blanks)
    result = (r1 == r2)

    if not result:
        if diff is None:
            diff = []
        diff.extend(difflib.unified_diff(r1, r2, fname1, fname2))

    if PRINT_DIFF and not result:
        if VIM_DIFF:
            systemExec('gvimdiff %s %s' % (fname1, fname2))
        else:
            sys.stdout.write(''.join(diff))

    return result 

def indent_files(files, diff=False, debug=False, level=0, inplace=False):
    output = []
    for f in files:
        dst = indent(f, debug=debug, level=level)
        output.append([f,dst])

    # First, copy to inplace
    if inplace:
        for src,dst in output:
            shutil.copyfile(dst,src)
        return True

    # now, compare
    failed = []
    for src,dst in output:
        if filecmp.cmp(src,dst) == 0:
            failed.append([src, dst])
    if len(failed) > 0:
        if not diff:
            print 'Found %u badly indented files:' % len(failed)
            for src,dst in failed:
                print '  ' + src
        else:
            for src,dst in failed:
                s = open(src, 'r').readlines()
                d = open(dst, 'r').readlines()
                for line in difflib.unified_diff(s, d, fromfile=src, tofile=dst):
                    sys.stdout.write(line)
        return False
    return True 

def generate_diff(a, b):
        """Generates unified diff of a and b."""
        a, b = list(a.splitlines(True)), list(b.splitlines(True))
        diff = difflib.unified_diff(a, b, fromfile="expected",
                                    tofile="actual")
        return diff 

def compare_text(left, right):
    if not isinstance(left, str):
        left = left.decode("utf-8")
    if not isinstance(right, str):
        right = right.decode("utf-8")
    diff = list(difflib.unified_diff(left.splitlines(), right.splitlines(), lineterm=''))
    if diff:
        return "    " + '\n    '.join([color_diff_line(line) for line in diff])
    else:
        return None 

def __init__(self, label_from, label_to, from_file, to_file):
    import difflib
    self.seen_change = False
    fromlines = open(from_file, 'U').readlines()
    tolines = open(to_file, 'U').readlines()
    self.diff = difflib.unified_diff(fromlines, tolines,
                                     label_from, label_to)