Python difflib.ndiff() Examples

def assertXMLEqual(self, xml1, xml2, msg=None):
        """
        Asserts that two XML snippets are semantically the same.
        Whitespace in most cases is ignored, and attribute ordering is not
        significant. The passed-in arguments must be valid XML.
        """
        try:
            result = compare_xml(xml1, xml2)
        except Exception as e:
            standardMsg = 'First or second argument is not valid XML\n%s' % e
            self.fail(self._formatMessage(msg, standardMsg))
        else:
            if not result:
                standardMsg = '%s != %s' % (safe_repr(xml1, True), safe_repr(xml2, True))
                diff = ('\n' + '\n'.join(
                    difflib.ndiff(
                        six.text_type(xml1).splitlines(),
                        six.text_type(xml2).splitlines(),
                    )
                ))
                standardMsg = self._truncateMessage(standardMsg, diff)
                self.fail(self._formatMessage(msg, standardMsg)) 

def assertMultiLineEqual(self, first, second, msg=None):
        """Assert that two multi-line strings are equal."""
        self.assertIsInstance(first, basestring,
                'First argument is not a string')
        self.assertIsInstance(second, basestring,
                'Second argument is not a string')

        if first != second:
            firstlines = first.splitlines(True)
            secondlines = second.splitlines(True)
            if len(firstlines) == 1 and first.strip('\r\n') == first:
                firstlines = [first + '\n']
                secondlines = [second + '\n']
            standardMsg = '%s != %s' % (safe_repr(first, True),
                                        safe_repr(second, True))
            diff = '\n' + ''.join(difflib.ndiff(firstlines, secondlines))
            standardMsg = self._truncateMessage(standardMsg, diff)
            self.fail(self._formatMessage(msg, standardMsg)) 

def assertHTMLEqual(self, html1, html2, msg=None):
        """
        Asserts that two HTML snippets are semantically the same.
        Whitespace in most cases is ignored, and attribute ordering is not
        significant. The passed-in arguments must be valid HTML.
        """
        dom1 = assert_and_parse_html(self, html1, msg,
            'First argument is not valid HTML:')
        dom2 = assert_and_parse_html(self, html2, msg,
            'Second argument is not valid HTML:')

        if dom1 != dom2:
            standardMsg = '%s != %s' % (
                safe_repr(dom1, True), safe_repr(dom2, True))
            diff = ('\n' + '\n'.join(difflib.ndiff(
                           six.text_type(dom1).splitlines(),
                           six.text_type(dom2).splitlines())))
            standardMsg = self._truncateMessage(standardMsg, diff)
            self.fail(self._formatMessage(msg, standardMsg)) 

def check_compiles(dsl_expr, code):
    types = ENV.__types__

    expr, functions = to_expr(dsl_expr)
    env = fn_types(functions)
    env.update(types['__root__'].__field_types__)

    expr = check(expr, types, env)

    # test eval
    lambda_expr = ExpressionCompiler.compile_lambda_expr(expr)
    eval(compile(lambda_expr, '<expr>', 'eval'))

    # test compile
    py_expr = ExpressionCompiler.compile_expr(expr)

    first = astor.to_source(py_expr).strip()
    second = dedent(code).strip()
    if first != second:
        msg = ('Compiled code is not equal:\n\n{}'
               .format('\n'.join(difflib.ndiff(first.splitlines(),
                                               second.splitlines()))))
        raise AssertionError(msg) 

def assertMultiLineEqual(self, first, second, msg=None):
        """Assert that two multi-line strings are equal."""
        self.assertIsInstance(first, basestring,
                'First argument is not a string')
        self.assertIsInstance(second, basestring,
                'Second argument is not a string')

        if first != second:
            # don't use difflib if the strings are too long
            if (len(first) > self._diffThreshold or
                len(second) > self._diffThreshold):
                self._baseAssertEqual(first, second, msg)
            firstlines = first.splitlines(True)
            secondlines = second.splitlines(True)
            if len(firstlines) == 1 and first.strip('\r\n') == first:
                firstlines = [first + '\n']
                secondlines = [second + '\n']
            standardMsg = '%s != %s' % (safe_repr(first, True),
                                        safe_repr(second, True))
            diff = '\n' + ''.join(difflib.ndiff(firstlines, secondlines))
            standardMsg = self._truncateMessage(standardMsg, diff)
            self.fail(self._formatMessage(msg, standardMsg)) 

def assertMultiLineEqual(self, first, second, msg=None):
        """Assert that two multi-line strings are equal."""
        self.assertIsInstance(first, str, 'First argument is not a string')
        self.assertIsInstance(second, str, 'Second argument is not a string')

        if first != second:
            # don't use difflib if the strings are too long
            if (len(first) > self._diffThreshold or
                len(second) > self._diffThreshold):
                self._baseAssertEqual(first, second, msg)
            firstlines = first.splitlines(keepends=True)
            secondlines = second.splitlines(keepends=True)
            if len(firstlines) == 1 and first.strip('\r\n') == first:
                firstlines = [first + '\n']
                secondlines = [second + '\n']
            standardMsg = '%s != %s' % (safe_repr(first, True),
                                        safe_repr(second, True))
            diff = '\n' + ''.join(difflib.ndiff(firstlines, secondlines))
            standardMsg = self._truncateMessage(standardMsg, diff)
            self.fail(self._formatMessage(msg, standardMsg)) 

def assertHTMLEqual(self, html1, html2, msg=None):
        """
        Assert that two HTML snippets are semantically the same.
        Whitespace in most cases is ignored, and attribute ordering is not
        significant. The arguments must be valid HTML.
        """
        dom1 = assert_and_parse_html(self, html1, msg, 'First argument is not valid HTML:')
        dom2 = assert_and_parse_html(self, html2, msg, 'Second argument is not valid HTML:')

        if dom1 != dom2:
            standardMsg = '%s != %s' % (
                safe_repr(dom1, True), safe_repr(dom2, True))
            diff = ('\n' + '\n'.join(difflib.ndiff(
                str(dom1).splitlines(), str(dom2).splitlines(),
            )))
            standardMsg = self._truncateMessage(standardMsg, diff)
            self.fail(self._formatMessage(msg, standardMsg)) 

def assertXMLEqual(self, xml1, xml2, msg=None):
        """
        Assert that two XML snippets are semantically the same.
        Whitespace in most cases is ignored and attribute ordering is not
        significant. The arguments must be valid XML.
        """
        try:
            result = compare_xml(xml1, xml2)
        except Exception as e:
            standardMsg = 'First or second argument is not valid XML\n%s' % e
            self.fail(self._formatMessage(msg, standardMsg))
        else:
            if not result:
                standardMsg = '%s != %s' % (safe_repr(xml1, True), safe_repr(xml2, True))
                diff = ('\n' + '\n'.join(
                    difflib.ndiff(xml1.splitlines(), xml2.splitlines())
                ))
                standardMsg = self._truncateMessage(standardMsg, diff)
                self.fail(self._formatMessage(msg, standardMsg)) 

def assertMultiLineEqual(self, first, second, msg=None):
        """Assert that two multi-line strings are equal."""
        self.assertIsInstance(first, basestring,
                'First argument is not a string')
        self.assertIsInstance(second, basestring,
                'Second argument is not a string')

        if first != second:
            # don't use difflib if the strings are too long
            if (len(first) > self._diffThreshold or
                len(second) > self._diffThreshold):
                self._baseAssertEqual(first, second, msg)
            firstlines = first.splitlines(True)
            secondlines = second.splitlines(True)
            if len(firstlines) == 1 and first.strip('\r\n') == first:
                firstlines = [first + '\n']
                secondlines = [second + '\n']
            standardMsg = '%s != %s' % (safe_repr(first, True),
                                        safe_repr(second, True))
            diff = '\n' + ''.join(difflib.ndiff(firstlines, secondlines))
            standardMsg = self._truncateMessage(standardMsg, diff)
            self.fail(self._formatMessage(msg, standardMsg)) 

def assertMultiLineEqual(self, first, second, msg=None):
        """Assert that two multi-line strings are equal."""
        self.assertIsInstance(first, basestring,
                'First argument is not a string')
        self.assertIsInstance(second, basestring,
                'Second argument is not a string')

        if first != second:
            firstlines = first.splitlines(True)
            secondlines = second.splitlines(True)
            if len(firstlines) == 1 and first.strip('\r\n') == first:
                firstlines = [first + '\n']
                secondlines = [second + '\n']
            standardMsg = '%s != %s' % (safe_repr(first, True),
                                        safe_repr(second, True))
            diff = '\n' + ''.join(difflib.ndiff(firstlines, secondlines))
            standardMsg = self._truncateMessage(standardMsg, diff)
            self.fail(self._formatMessage(msg, standardMsg)) 

def assertMultiLineEqual(self, first, second, msg=None):
        """Assert that two multi-line strings are equal."""
        self.assertIsInstance(first, basestring,
                'First argument is not a string')
        self.assertIsInstance(second, basestring,
                'Second argument is not a string')

        if first != second:
            # don't use difflib if the strings are too long
            if (len(first) > self._diffThreshold or
                len(second) > self._diffThreshold):
                self._baseAssertEqual(first, second, msg)
            firstlines = first.splitlines(True)
            secondlines = second.splitlines(True)
            if len(firstlines) == 1 and first.strip('\r\n') == first:
                firstlines = [first + '\n']
                secondlines = [second + '\n']
            standardMsg = '%s != %s' % (safe_repr(first, True),
                                        safe_repr(second, True))
            diff = '\n' + ''.join(difflib.ndiff(firstlines, secondlines))
            standardMsg = self._truncateMessage(standardMsg, diff)
            self.fail(self._formatMessage(msg, standardMsg)) 

def assertMultiLineEqual(self, first, second, msg=None):
        """Assert that two multi-line strings are equal."""
        self.assertIsInstance(first, str, 'First argument is not a string')
        self.assertIsInstance(second, str, 'Second argument is not a string')

        if first != second:
            # don't use difflib if the strings are too long
            if (len(first) > self._diffThreshold or
                len(second) > self._diffThreshold):
                self._baseAssertEqual(first, second, msg)
            firstlines = first.splitlines(keepends=True)
            secondlines = second.splitlines(keepends=True)
            if len(firstlines) == 1 and first.strip('\r\n') == first:
                firstlines = [first + '\n']
                secondlines = [second + '\n']
            standardMsg = '%s != %s' % _common_shorten_repr(first, second)
            diff = '\n' + ''.join(difflib.ndiff(firstlines, secondlines))
            standardMsg = self._truncateMessage(standardMsg, diff)
            self.fail(self._formatMessage(msg, standardMsg)) 

def assertMultiLineEqual(self, first, second, msg=None):
        """Assert that two multi-line strings are equal."""
        self.assertIsInstance(first, str, 'First argument is not a string')
        self.assertIsInstance(second, str, 'Second argument is not a string')

        if first != second:
            # don't use difflib if the strings are too long
            if (len(first) > self._diffThreshold or
                len(second) > self._diffThreshold):
                self._baseAssertEqual(first, second, msg)
            firstlines = first.splitlines(keepends=True)
            secondlines = second.splitlines(keepends=True)
            if len(firstlines) == 1 and first.strip('\r\n') == first:
                firstlines = [first + '\n']
                secondlines = [second + '\n']
            standardMsg = '%s != %s' % _common_shorten_repr(first, second)
            diff = '\n' + ''.join(difflib.ndiff(firstlines, secondlines))
            standardMsg = self._truncateMessage(standardMsg, diff)
            self.fail(self._formatMessage(msg, standardMsg)) 

def is_summary_prob(subtext: str, fulltext: str) -> float:
    """
    判断subtext是fulltext的摘要的概率。概率大于0.5可认为是。
    """
    sub_sentences = split_sentences(subtext)
    full_sentences = split_sentences(fulltext)
    if not sub_sentences:
        return 1.0 if full_sentences else 0.0
    elif not full_sentences:
        return 0.0
    num_sub = len(sub_sentences)
    num_full = len(full_sentences)
    if num_sub - num_full >= 0:
        return 0.0
    max_check = min(num_sub * 2 + 1, num_full)
    num_positive = 0
    for delta in difflib.ndiff(sub_sentences, full_sentences[:max_check]):
        diff_type = delta[0]
        if diff_type == ' ' or diff_type == '+':
            num_positive += 1
        elif diff_type == '-':
            num_positive -= 3
    return max(0.0, min(1.0, num_positive / max_check)) 

def assertMultiLineEqual(self, first, second, msg=None):
        """Assert that two multi-line strings are equal."""
        self.assertIsInstance(first, str, 'First argument is not a string')
        self.assertIsInstance(second, str, 'Second argument is not a string')

        if first != second:
            # don't use difflib if the strings are too long
            if (len(first) > self._diffThreshold or
                len(second) > self._diffThreshold):
                self._baseAssertEqual(first, second, msg)
            firstlines = first.splitlines(keepends=True)
            secondlines = second.splitlines(keepends=True)
            if len(firstlines) == 1 and first.strip('\r\n') == first:
                firstlines = [first + '\n']
                secondlines = [second + '\n']
            standardMsg = '%s != %s' % _common_shorten_repr(first, second)
            diff = '\n' + ''.join(difflib.ndiff(firstlines, secondlines))
            standardMsg = self._truncateMessage(standardMsg, diff)
            self.fail(self._formatMessage(msg, standardMsg)) 

def do_disassembly_test(self, func, expected):
        s = StringIO.StringIO()
        save_stdout = sys.stdout
        sys.stdout = s
        dis.dis(func)
        sys.stdout = save_stdout
        got = s.getvalue()
        # Trim trailing blanks (if any).
        lines = got.split('\n')
        lines = [line.rstrip() for line in lines]
        expected = expected.split("\n")
        import difflib
        if expected != lines:
            self.fail(
                "events did not match expectation:\n" +
                "\n".join(difflib.ndiff(expected,
                                        lines))) 

def assertHTMLEqual(self, html1, html2, msg=None):
        """
        Assert that two HTML snippets are semantically the same.
        Whitespace in most cases is ignored, and attribute ordering is not
        significant. The arguments must be valid HTML.
        """
        dom1 = assert_and_parse_html(self, html1, msg, 'First argument is not valid HTML:')
        dom2 = assert_and_parse_html(self, html2, msg, 'Second argument is not valid HTML:')

        if dom1 != dom2:
            standardMsg = '%s != %s' % (
                safe_repr(dom1, True), safe_repr(dom2, True))
            diff = ('\n' + '\n'.join(difflib.ndiff(
                str(dom1).splitlines(), str(dom2).splitlines(),
            )))
            standardMsg = self._truncateMessage(standardMsg, diff)
            self.fail(self._formatMessage(msg, standardMsg)) 

def assertXMLEqual(self, xml1, xml2, msg=None):
        """
        Assert that two XML snippets are semantically the same.
        Whitespace in most cases is ignored and attribute ordering is not
        significant. The arguments must be valid XML.
        """
        try:
            result = compare_xml(xml1, xml2)
        except Exception as e:
            standardMsg = 'First or second argument is not valid XML\n%s' % e
            self.fail(self._formatMessage(msg, standardMsg))
        else:
            if not result:
                standardMsg = '%s != %s' % (safe_repr(xml1, True), safe_repr(xml2, True))
                diff = ('\n' + '\n'.join(
                    difflib.ndiff(xml1.splitlines(), xml2.splitlines())
                ))
                standardMsg = self._truncateMessage(standardMsg, diff)
                self.fail(self._formatMessage(msg, standardMsg)) 

def ndiffAssertEqual(self, first, second):
        """Like failUnlessEqual except use ndiff for readable output."""
        if first != second:
            sfirst = unicode(first)
            ssecond = unicode(second)
            # Using the built-in .splitlines() method here will cause incorrect
            # results when splitting statements that have quoted CR/CR+LF
            # characters.
            sfirst = sqlparse.utils.split_unquoted_newlines(sfirst)
            ssecond = sqlparse.utils.split_unquoted_newlines(ssecond)
            diff = difflib.ndiff(sfirst, ssecond)
            fp = StringIO()
            fp.write(NL)
            fp.write(NL.join(diff))
            print fp.getvalue()
            raise self.failureException, fp.getvalue() 

def assertHTMLEqual(self, html1, html2, msg=None):
        """
        Asserts that two HTML snippets are semantically the same.
        Whitespace in most cases is ignored, and attribute ordering is not
        significant. The passed-in arguments must be valid HTML.
        """
        dom1 = assert_and_parse_html(self, html1, msg, 'First argument is not valid HTML:')
        dom2 = assert_and_parse_html(self, html2, msg, 'Second argument is not valid HTML:')

        if dom1 != dom2:
            standardMsg = '%s != %s' % (
                safe_repr(dom1, True), safe_repr(dom2, True))
            diff = ('\n' + '\n'.join(difflib.ndiff(
                six.text_type(dom1).splitlines(),
                six.text_type(dom2).splitlines(),
            )))
            standardMsg = self._truncateMessage(standardMsg, diff)
            self.fail(self._formatMessage(msg, standardMsg)) 

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 _compare_eq_iterable(
    left: Iterable[Any], right: Iterable[Any], verbose: int = 0
) -> List[str]:
    if not verbose:
        return ["Use -v to get the full diff"]
    # dynamic import to speedup pytest
    import difflib

    left_formatting = pprint.pformat(left).splitlines()
    right_formatting = pprint.pformat(right).splitlines()

    # Re-format for different output lengths.
    lines_left = len(left_formatting)
    lines_right = len(right_formatting)
    if lines_left != lines_right:
        left_formatting = _pformat_dispatch(left).splitlines()
        right_formatting = _pformat_dispatch(right).splitlines()

    if lines_left > 1 or lines_right > 1:
        _surrounding_parens_on_own_lines(left_formatting)
        _surrounding_parens_on_own_lines(right_formatting)

    explanation = ["Full diff:"]
    # "right" is the expected base against which we compare "left",
    # see https://github.com/pytest-dev/pytest/issues/3333
    explanation.extend(
        line.rstrip() for line in difflib.ndiff(right_formatting, left_formatting)
    )
    return explanation 

def compare(text1, text2):
    """Utility function for comparing text and returining differences."""
    diff = difflib.ndiff(text1.splitlines(True), text2.splitlines(True))
    return '\n' + '\n'.join(diff) 

def compare(text1, text2):
    """Utility function for comparing text and returining differences."""
    diff = difflib.ndiff(text1.splitlines(True), text2.splitlines(True))
    return '\n' + '\n'.join(diff) 

def main():

    parser = argparse.ArgumentParser()
    parser.add_argument('-c', action='store_true', default=False,
                        help='Produce a context format diff (default)')
    parser.add_argument('-u', action='store_true', default=False,
                        help='Produce a unified format diff')
    parser.add_argument('-m', action='store_true', default=False,
                        help='Produce HTML side by side diff '
                             '(can use -c and -l in conjunction)')
    parser.add_argument('-n', action='store_true', default=False,
                        help='Produce a ndiff format diff')
    parser.add_argument('-l', '--lines', type=int, default=3,
                        help='Set number of context lines (default 3)')
    parser.add_argument('fromfile')
    parser.add_argument('tofile')
    options = parser.parse_args()

    n = options.lines
    fromfile = options.fromfile
    tofile = options.tofile

    fromdate = file_mtime(fromfile)
    todate = file_mtime(tofile)
    with open(fromfile) as ff:
        fromlines = ff.readlines()
    with open(tofile) as tf:
        tolines = tf.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 diff_plan(migration):
    plan_dbs = {doc.db_name for doc in migration.shard_plan}
    db_allocations = [
        doc
        for db_name, doc in get_db_allocations(migration.target_couch_config).items()
        if db_name in plan_dbs
    ]
    l1 = get_shard_table(_get_aliased_allocation_docs(migration))
    l2 = get_shard_table(db_allocations)
    difflines = list(difflib.ndiff(l1, l2))
    has_diff = any(d for d in difflines if d[0] in '+-')
    if has_diff:
        return '\n'.join(difflines) 

def assertDictEqual(self, d1, d2, msg=None):
        self.assertIsInstance(d1, dict, 'First argument is not a dictionary')
        self.assertIsInstance(d2, dict, 'Second argument is not a dictionary')

        if d1 != d2:
            standardMsg = '%s != %s' % _common_shorten_repr(d1, d2)
            diff = ('\n' + '\n'.join(difflib.ndiff(
                           pprint.pformat(d1).splitlines(),
                           pprint.pformat(d2).splitlines())))
            standardMsg = self._truncateMessage(standardMsg, diff)
            self.fail(self._formatMessage(msg, standardMsg)) 

def testAssertSequenceEqualMaxDiff(self):
        self.assertEqual(self.maxDiff, 80*8)
        seq1 = 'a' + 'x' * 80**2
        seq2 = 'b' + 'x' * 80**2
        diff = '\n'.join(difflib.ndiff(pprint.pformat(seq1).splitlines(),
                                       pprint.pformat(seq2).splitlines()))
        # the +1 is the leading \n added by assertSequenceEqual
        omitted = unittest.case.DIFF_OMITTED % (len(diff) + 1,)

        self.maxDiff = len(diff)//2
        try:

            self.assertSequenceEqual(seq1, seq2)
        except self.failureException as e:
            msg = e.args[0]
        else:
            self.fail('assertSequenceEqual did not fail.')
        self.assertLess(len(msg), len(diff))
        self.assertIn(omitted, msg)

        self.maxDiff = len(diff) * 2
        try:
            self.assertSequenceEqual(seq1, seq2)
        except self.failureException as e:
            msg = e.args[0]
        else:
            self.fail('assertSequenceEqual did not fail.')
        self.assertGreater(len(msg), len(diff))
        self.assertNotIn(omitted, msg)

        self.maxDiff = None
        try:
            self.assertSequenceEqual(seq1, seq2)
        except self.failureException as e:
            msg = e.args[0]
        else:
            self.fail('assertSequenceEqual did not fail.')
        self.assertGreater(len(msg), len(diff))
        self.assertNotIn(omitted, msg) 

def compare_events(self, line_offset, events, expected_events):
        events = [(l - line_offset, e) for (l, e) in events]
        if events != expected_events:
            self.fail(
                "events did not match expectation:\n" +
                "\n".join(difflib.ndiff([str(x) for x in expected_events],
                                        [str(x) for x in events]))) 

def fcompare(f1name, f2name):
    f1 = fopen(f1name)
    f2 = fopen(f2name)
    if not f1 or not f2:
        return 0

    a = f1.readlines(); f1.close()
    b = f2.readlines(); f2.close()
    for line in difflib.ndiff(a, b):
        print(line, end=' ')

    return 1

# crack args (sys.argv[1:] is normal) & compare;
# return false iff a problem