annotate tests/test-bdiff.py @ 43198:c16fe77e340a

pathcopies: give up any optimization based on `introrev`

Between 8a0136f69027 and d98fb3f42f33, we sped up the search for the
introduction revision during path copies. However, further checking show that
finding the introduction revision is still expensive and that we are better off
without it. So we simply drop it and only rely on the linkrev optimisation.

I ran `perfpathcopies` on 6989 pair of revision in the pypy
repository (`hg perfhelper-pathcopies`. The result is massively in favor of
dropping this condition. The result of the copy tracing are unchanged.

Attempt to use a smaller changes preserving linkrev usage were unsuccessful, it
can return wrong result. The following changesets broke test-mv-cp-st-diff.t

    -        if not f.isintroducedafter(limit):
    +        if limit >= 0 and f.linkrev() < limit:
                 return None


Here are various numbers (before this changeset/after this changesets)

            source       destination  before      after    saved-time  ratio
worth cases e66f24650daf 695dfb0f493b 1.062843 1.246369 -0.183526 1.172675
            c979853a3b6a 8d60fe293e79 1.036985 1.196414 -0.159429 1.153743
            22349fa2fc33 fbb1c9fd86c0 0.879926 1.038682 -0.158756 1.180420
            682b98f3e672 a4878080a536 0.909952 1.063801 -0.153849 1.169074
            5adabc9b9848 920958a93997 0.993622 1.147452 -0.153830 1.154817
worse  1%   dbfbfcf077e9 aea8f2fd3593 1.016595 1.082999 -0.066404 1.065320
worse  5%   c95f1ced15f2 7d29d5e39734 0.453694 0.471156 -0.017462 1.038488
worse 10%   3e144ed1d5b7 2aef0e942480 0.035140 0.037535 -0.002395 1.068156
worse 25%   321fc60db035 801748ba582a 0.009267 0.009325 -0.000058 1.006259
median      2088ce763fc2 e6991321d78b 0.000665 0.000651 0.000014 0.978947
best 25%    915631a97de6 385b31354be6 0.040743 0.040363 0.000380 0.990673
best 10%    ad495c36a765 19c10384d3e7 0.431658 0.411490 0.020168 0.953278
best  5%    d13ae7d283ae 813c99f810ac 1.141404 1.075346 0.066058 0.942126
best  1%    81593cb4a496 99ae11866969 1.833297 0.063823 1.769474 0.034813
best cases  c3b14617fbd7 743a0fcaa4eb 1101.811740 2.735970 1099.075770 0.002483
            c3b14617fbd7 9ba6ab77fd29 1116.753953 2.800729 1113.953224 0.002508
            058b99d6e81f 57e249b7a3ea 1246.128485 3.042762 1243.085723 0.002442
            9a8c361aab49 0354a250d371 1253.111894 3.085796 1250.026098 0.002463
            442dbbc53c68 3ec1002a818c 1261.786294 3.138607 1258.647687 0.002487


As one can see, the average case is not really impacted. However, the worth case
we get after this changeset are much better than the one we had before it. We
have 30 pairs where improvements are above 10 minutes.

This reflect in the combined time for all pairs
before: 26256s
after:   1300s (-95%)

If we remove these pathological 30 cases, we still see a significant improvements:
before:  1631s
after:   1245s (-24%)

from __future__ import absolute_import, print_function
import collections
import struct
import unittest

from mercurial import mdiff


class diffreplace(collections.namedtuple('diffreplace', 'start end from_ to')):
    def __repr__(self):
        return 'diffreplace(%r, %r, %r, %r)' % self


class BdiffTests(unittest.TestCase):
    def assert_bdiff_applies(self, a, b):
        d = mdiff.textdiff(a, b)
        c = a
        if d:
            c = mdiff.patches(a, [d])
        self.assertEqual(
            c,
            b,
            (
                "bad diff+patch result from\n  %r to\n  "
                "%r: \nbdiff: %r\npatched: %r" % (a, b, d, c[:200])
            ),
        )

    def assert_bdiff(self, a, b):
        self.assert_bdiff_applies(a, b)
        self.assert_bdiff_applies(b, a)

    def test_bdiff_basic(self):
        cases = [
            (b"a\nc\n\n\n\n", b"a\nb\n\n\n"),
            (b"a\nb\nc\n", b"a\nc\n"),
            (b"", b""),
            (b"a\nb\nc", b"a\nb\nc"),
            (b"a\nb\nc\nd\n", b"a\nd\n"),
            (b"a\nb\nc\nd\n", b"a\nc\ne\n"),
            (b"a\nb\nc\n", b"a\nc\n"),
            (b"a\n", b"c\na\nb\n"),
            (b"a\n", b""),
            (b"a\n", b"b\nc\n"),
            (b"a\n", b"c\na\n"),
            (b"", b"adjfkjdjksdhfksj"),
            (b"", b"ab"),
            (b"", b"abc"),
            (b"a", b"a"),
            (b"ab", b"ab"),
            (b"abc", b"abc"),
            (b"a\n", b"a\n"),
            (b"a\nb", b"a\nb"),
        ]
        for a, b in cases:
            self.assert_bdiff(a, b)

    def showdiff(self, a, b):
        bin = mdiff.textdiff(a, b)
        pos = 0
        q = 0
        actions = []
        while pos < len(bin):
            p1, p2, l = struct.unpack(">lll", bin[pos : pos + 12])
            pos += 12
            if p1:
                actions.append(a[q:p1])
            actions.append(diffreplace(p1, p2, a[p1:p2], bin[pos : pos + l]))
            pos += l
            q = p2
        if q < len(a):
            actions.append(a[q:])
        return actions

    def test_issue1295(self):
        cases = [
            (
                b"x\n\nx\n\nx\n\nx\n\nz\n",
                b"x\n\nx\n\ny\n\nx\n\nx\n\nz\n",
                [
                    b'x\n\nx\n\n',
                    diffreplace(6, 6, b'', b'y\n\n'),
                    b'x\n\nx\n\nz\n',
                ],
            ),
            (
                b"x\n\nx\n\nx\n\nx\n\nz\n",
                b"x\n\nx\n\ny\n\nx\n\ny\n\nx\n\nz\n",
                [
                    b'x\n\nx\n\n',
                    diffreplace(6, 6, b'', b'y\n\n'),
                    b'x\n\n',
                    diffreplace(9, 9, b'', b'y\n\n'),
                    b'x\n\nz\n',
                ],
            ),
        ]
        for old, new, want in cases:
            self.assertEqual(self.showdiff(old, new), want)

    def test_issue1295_varies_on_pure(self):
        # we should pick up abbbc. rather than bc.de as the longest match
        got = self.showdiff(
            b"a\nb\nb\nb\nc\n.\nd\ne\n.\nf\n",
            b"a\nb\nb\na\nb\nb\nb\nc\n.\nb\nc\n.\nd\ne\nf\n",
        )
        want_c = [
            b'a\nb\nb\n',
            diffreplace(6, 6, b'', b'a\nb\nb\nb\nc\n.\n'),
            b'b\nc\n.\nd\ne\n',
            diffreplace(16, 18, b'.\n', b''),
            b'f\n',
        ]
        want_pure = [
            diffreplace(0, 0, b'', b'a\nb\nb\n'),
            b'a\nb\nb\nb\nc\n.\n',
            diffreplace(12, 12, b'', b'b\nc\n.\n'),
            b'd\ne\n',
            diffreplace(16, 18, b'.\n', b''),
            b'f\n',
        ]
        self.assertTrue(
            got in (want_c, want_pure),
            'got: %r, wanted either %r or %r' % (got, want_c, want_pure),
        )

    def test_fixws(self):
        cases = [
            (b" \ta\r b\t\n", b"ab\n", 1),
            (b" \ta\r b\t\n", b" a b\n", 0),
            (b"", b"", 1),
            (b"", b"", 0),
        ]
        for a, b, allws in cases:
            c = mdiff.fixws(a, allws)
            self.assertEqual(
                c, b, 'fixws(%r) want %r got %r (allws=%r)' % (a, b, c, allws)
            )

    def test_nice_diff_for_trivial_change(self):
        self.assertEqual(
            self.showdiff(
                b''.join(b'<%d\n-\n' % i for i in range(5)),
                b''.join(b'>%d\n-\n' % i for i in range(5)),
            ),
            [
                diffreplace(0, 3, b'<0\n', b'>0\n'),
                b'-\n',
                diffreplace(5, 8, b'<1\n', b'>1\n'),
                b'-\n',
                diffreplace(10, 13, b'<2\n', b'>2\n'),
                b'-\n',
                diffreplace(15, 18, b'<3\n', b'>3\n'),
                b'-\n',
                diffreplace(20, 23, b'<4\n', b'>4\n'),
                b'-\n',
            ],
        )

    def test_prefer_appending(self):
        # 1 line to 3 lines
        self.assertEqual(
            self.showdiff(b'a\n', b'a\n' * 3),
            [b'a\n', diffreplace(2, 2, b'', b'a\na\n')],
        )
        # 1 line to 5 lines
        self.assertEqual(
            self.showdiff(b'a\n', b'a\n' * 5),
            [b'a\n', diffreplace(2, 2, b'', b'a\na\na\na\n')],
        )

    def test_prefer_removing_trailing(self):
        # 3 lines to 1 line
        self.assertEqual(
            self.showdiff(b'a\n' * 3, b'a\n'),
            [b'a\n', diffreplace(2, 6, b'a\na\n', b'')],
        )
        # 5 lines to 1 line
        self.assertEqual(
            self.showdiff(b'a\n' * 5, b'a\n'),
            [b'a\n', diffreplace(2, 10, b'a\na\na\na\n', b'')],
        )


if __name__ == '__main__':
    import silenttestrunner

    silenttestrunner.main(__name__)