tests/test-linelog.py
author Pierre-Yves David <pierre-yves.david@octobus.net>
Tue, 16 Apr 2019 17:26:38 +0200
changeset 42159 4f9a89837f07
parent 41365 876494fd967d
child 43076 2372284d9457
permissions -rw-r--r--
setdiscovery: stop limiting the number of local head we initially send In our testing this limitation provides now real gain and instead triggers pathological discovery timing for some repository with many heads. See inline documentation for details. Some timing below: Mozilla try repository, (~1M revs, ~35K heads), discovery between 2 clones with 100 head missing on each side before: ! wall 1.492111 comb 1.490000 user 1.450000 sys 0.040000 (best of 20) ! wall 1.813992 comb 1.820000 user 1.700000 sys 0.120000 (max of 20) ! wall 1.574326 comb 1.573500 user 1.522000 sys 0.051500 (avg of 20) ! wall 1.572583 comb 1.570000 user 1.520000 sys 0.050000 (median of 20) after: ! wall 1.147834 comb 1.150000 user 1.090000 sys 0.060000 (best of 20) ! wall 1.449144 comb 1.450000 user 1.330000 sys 0.120000 (max of 20) ! wall 1.204618 comb 1.202500 user 1.146500 sys 0.056000 (avg of 20) ! wall 1.194407 comb 1.190000 user 1.140000 sys 0.050000 (median of 20) pypy (~100 heads, 317 heads) discovery between clones with only 42 common heads before: ! wall 0.031653 comb 0.030000 user 0.030000 sys 0.000000 (best of 25) ! wall 0.055719 comb 0.050000 user 0.040000 sys 0.010000 (max of 25) ! wall 0.038939 comb 0.039600 user 0.038400 sys 0.001200 (avg of 25) ! wall 0.038660 comb 0.050000 user 0.040000 sys 0.010000 (median of 25) after: ! wall 0.018754 comb 0.020000 user 0.020000 sys 0.000000 (best of 49) ! wall 0.034505 comb 0.040000 user 0.030000 sys 0.010000 (max of 49) ! wall 0.019631 comb 0.019796 user 0.018367 sys 0.001429 (avg of 49) ! wall 0.019132 comb 0.020000 user 0.020000 sys 0.000000 (median of 49) Private repository (~1M revs, ~3K heads), discovery from a strip subset, about 100 changesets to be pulled. before: ! wall 1.837729 comb 1.840000 user 1.790000 sys 0.050000 (best of 20) ! wall 2.203468 comb 2.200000 user 2.100000 sys 0.100000 (max of 20) ! wall 2.049355 comb 2.048500 user 2.002500 sys 0.046000 (avg of 20) ! wall 2.035315 comb 2.040000 user 2.000000 sys 0.040000 (median of 20) after: ! wall 0.136598 comb 0.130000 user 0.110000 sys 0.020000 (best of 20) ! wall 0.330519 comb 0.330000 user 0.260000 sys 0.070000 (max of 20) ! wall 0.157254 comb 0.155500 user 0.123000 sys 0.032500 (avg of 20) ! wall 0.149870 comb 0.140000 user 0.110000 sys 0.030000 (median of 20) Same private repo, discovery between two clone with 500 different heads on each side: before: ! wall 2.372919 comb 2.370000 user 2.320000 sys 0.050000 (best of 20) ! wall 2.622422 comb 2.610000 user 2.510000 sys 0.100000 (max of 20) ! wall 2.450135 comb 2.450000 user 2.402000 sys 0.048000 (avg of 20) ! wall 2.443896 comb 2.450000 user 2.410000 sys 0.040000 (median of 20) after: ! wall 0.625497 comb 0.620000 user 0.570000 sys 0.050000 (best of 20) ! wall 0.834723 comb 0.820000 user 0.730000 sys 0.090000 (max of 20) ! wall 0.675725 comb 0.675500 user 0.628000 sys 0.047500 (avg of 20) ! wall 0.671614 comb 0.680000 user 0.640000 sys 0.040000 (median of 20)

from __future__ import absolute_import, print_function

import difflib
import random
import unittest

from mercurial import linelog

vecratio = 3 # number of replacelines / number of replacelines_vec
maxlinenum = 0xffffff
maxb1 = 0xffffff
maxdeltaa = 10
maxdeltab = 10

def _genedits(seed, endrev):
    lines = []
    random.seed(seed)
    for rev in range(0, endrev):
        n = len(lines)
        a1 = random.randint(0, n)
        a2 = random.randint(a1, min(n, a1 + maxdeltaa))
        b1 = random.randint(0, maxb1)
        b2 = random.randint(b1, b1 + maxdeltab)
        usevec = not bool(random.randint(0, vecratio))
        if usevec:
            blines = [(random.randint(0, rev), random.randint(0, maxlinenum))
                      for _ in range(b1, b2)]
        else:
            blines = [(rev, bidx) for bidx in range(b1, b2)]
        lines[a1:a2] = blines
        yield lines, rev, a1, a2, b1, b2, blines, usevec

class linelogtests(unittest.TestCase):
    def testlinelogencodedecode(self):
        program = [linelog._eof(0, 0),
                   linelog._jge(41, 42),
                   linelog._jump(0, 43),
                   linelog._eof(0, 0),
                   linelog._jl(44, 45),
                   linelog._line(46, 47),
                   ]
        ll = linelog.linelog(program, maxrev=100)
        enc = ll.encode()
        # round-trips okay
        self.assertEqual(linelog.linelog.fromdata(enc)._program, ll._program)
        self.assertEqual(linelog.linelog.fromdata(enc), ll)
        # This encoding matches the encoding used by hg-experimental's
        # linelog file, or is supposed to if it doesn't.
        self.assertEqual(enc, (b'\x00\x00\x01\x90\x00\x00\x00\x06'
                               b'\x00\x00\x00\xa4\x00\x00\x00*'
                               b'\x00\x00\x00\x00\x00\x00\x00+'
                               b'\x00\x00\x00\x00\x00\x00\x00\x00'
                               b'\x00\x00\x00\xb1\x00\x00\x00-'
                               b'\x00\x00\x00\xba\x00\x00\x00/'))

    def testsimpleedits(self):
        ll = linelog.linelog()
        # Initial revision: add lines 0, 1, and 2
        ll.replacelines(1, 0, 0, 0, 3)
        self.assertEqual([(l.rev, l.linenum) for l in ll.annotate(1)],
                         [(1, 0),
                          (1, 1),
                          (1, 2),
                         ])
        # Replace line 1 with a new line
        ll.replacelines(2, 1, 2, 1, 2)
        self.assertEqual([(l.rev, l.linenum) for l in ll.annotate(2)],
                         [(1, 0),
                          (2, 1),
                          (1, 2),
                         ])
        # delete a line out of 2
        ll.replacelines(3, 1, 2, 0, 0)
        self.assertEqual([(l.rev, l.linenum) for l in ll.annotate(3)],
                         [(1, 0),
                          (1, 2),
                         ])
        # annotation of 1 is unchanged
        self.assertEqual([(l.rev, l.linenum) for l in ll.annotate(1)],
                         [(1, 0),
                          (1, 1),
                          (1, 2),
                         ])
        ll.annotate(3) # set internal state to revision 3
        start = ll.getoffset(0)
        end = ll.getoffset(1)
        self.assertEqual(ll.getalllines(start, end), [
            (1, 0),
            (2, 1),
            (1, 1),
        ])
        self.assertEqual(ll.getalllines(), [
            (1, 0),
            (2, 1),
            (1, 1),
            (1, 2),
        ])

    def testparseclinelogfile(self):
        # This data is what the replacements in testsimpleedits
        # produce when fed to the original linelog.c implementation.
        data = (b'\x00\x00\x00\x0c\x00\x00\x00\x0f'
                b'\x00\x00\x00\x00\x00\x00\x00\x02'
                b'\x00\x00\x00\x05\x00\x00\x00\x06'
                b'\x00\x00\x00\x06\x00\x00\x00\x00'
                b'\x00\x00\x00\x00\x00\x00\x00\x07'
                b'\x00\x00\x00\x06\x00\x00\x00\x02'
                b'\x00\x00\x00\x00\x00\x00\x00\x00'
                b'\x00\x00\x00\t\x00\x00\x00\t'
                b'\x00\x00\x00\x00\x00\x00\x00\x0c'
                b'\x00\x00\x00\x08\x00\x00\x00\x05'
                b'\x00\x00\x00\x06\x00\x00\x00\x01'
                b'\x00\x00\x00\x00\x00\x00\x00\x05'
                b'\x00\x00\x00\x0c\x00\x00\x00\x05'
                b'\x00\x00\x00\n\x00\x00\x00\x01'
                b'\x00\x00\x00\x00\x00\x00\x00\t')
        llc = linelog.linelog.fromdata(data)
        self.assertEqual([(l.rev, l.linenum) for l in llc.annotate(1)],
                         [(1, 0),
                          (1, 1),
                          (1, 2),
                         ])
        self.assertEqual([(l.rev, l.linenum) for l in llc.annotate(2)],
                         [(1, 0),
                          (2, 1),
                          (1, 2),
                         ])
        self.assertEqual([(l.rev, l.linenum) for l in llc.annotate(3)],
                         [(1, 0),
                          (1, 2),
                         ])
        # Check we emit the same bytecode.
        ll = linelog.linelog()
        # Initial revision: add lines 0, 1, and 2
        ll.replacelines(1, 0, 0, 0, 3)
        # Replace line 1 with a new line
        ll.replacelines(2, 1, 2, 1, 2)
        # delete a line out of 2
        ll.replacelines(3, 1, 2, 0, 0)
        diff = '\n   ' + '\n   '.join(difflib.unified_diff(
            ll.debugstr().splitlines(), llc.debugstr().splitlines(),
            'python', 'c', lineterm=''))
        self.assertEqual(ll._program, llc._program, 'Program mismatch: ' + diff)
        # Done as a secondary step so we get a better result if the
        # program is where the mismatch is.
        self.assertEqual(ll, llc)
        self.assertEqual(ll.encode(), data)

    def testanothersimplecase(self):
        ll = linelog.linelog()
        ll.replacelines(3, 0, 0, 0, 2)
        ll.replacelines(4, 0, 2, 0, 0)
        self.assertEqual([(l.rev, l.linenum) for l in ll.annotate(4)],
                         [])
        self.assertEqual([(l.rev, l.linenum) for l in ll.annotate(3)],
                         [(3, 0), (3, 1)])
        # rev 2 is empty because contents were only ever introduced in rev 3
        self.assertEqual([(l.rev, l.linenum) for l in ll.annotate(2)],
                         [])

    def testrandomedits(self):
        # Inspired by original linelog tests.
        seed = random.random()
        numrevs = 2000
        ll = linelog.linelog()
        # Populate linelog
        for lines, rev, a1, a2, b1, b2, blines, usevec in _genedits(
                seed, numrevs):
            if usevec:
                ll.replacelines_vec(rev, a1, a2, blines)
            else:
                ll.replacelines(rev, a1, a2, b1, b2)
            ar = ll.annotate(rev)
            self.assertEqual(ll.annotateresult, lines)
        # Verify we can get back these states by annotating each rev
        for lines, rev, a1, a2, b1, b2, blines, usevec in _genedits(
                seed, numrevs):
            ar = ll.annotate(rev)
            self.assertEqual([(l.rev, l.linenum) for l in ar], lines)

    def testinfinitebadprogram(self):
        ll = linelog.linelog.fromdata(
            b'\x00\x00\x00\x00\x00\x00\x00\x02'  # header
            b'\x00\x00\x00\x00\x00\x00\x00\x01'  # JUMP to self
        )
        with self.assertRaises(linelog.LineLogError):
            # should not be an infinite loop and raise
            ll.annotate(1)

if __name__ == '__main__':
    import silenttestrunner
    silenttestrunner.main(__name__)