similar: sort files not by object id but by path for stable result
Perhaps the original implementation would want to sort added/removed files
alphabetically, but actually it did sort fctx objects by memory location.
This patch removes the use of set()s in order to preserve the order of
added/removed files. addedfiles.remove() becomes quadratic, but its cost
appears not dominant. Anyway, the quadratic behavior will be eliminated by
the next patch.
Benchmark with 50k added/removed files, on tmpfs:
$ mkdir src
$ for n in `seq 0 49`; do
> mkdir `printf src/%02d $n`
> done
$ for n in `seq 0 49999`; do
> f=`printf src/%02d/%05d $(($n/1000)) $n`
> dd if=/dev/urandom of=$f bs=8k count=1 status=none
> done
$ hg ci -qAm 'add 50k files of random content'
$ mv src dest
$ hg addremove --dry-run --time -q
original: real 16.550 secs (user 15.000+0.000 sys 1.540+0.000)
this patch: real 16.730 secs (user 15.280+0.000 sys 1.440+0.000)
from __future__ import absolute_import
import unittest
from mercurial import error, mdiff
# for readability, line numbers are 0-origin
text1 = '''
00 at OLD
01 at OLD
02 at OLD
02 at NEW, 03 at OLD
03 at NEW, 04 at OLD
04 at NEW, 05 at OLD
05 at NEW, 06 at OLD
07 at OLD
08 at OLD
09 at OLD
10 at OLD
11 at OLD
'''[1:] # strip initial LF
text2 = '''
00 at NEW
01 at NEW
02 at NEW, 03 at OLD
03 at NEW, 04 at OLD
04 at NEW, 05 at OLD
05 at NEW, 06 at OLD
06 at NEW
07 at NEW
08 at NEW
09 at NEW
10 at NEW
11 at NEW
'''[1:] # strip initial LF
def filteredblocks(blocks, rangeb):
"""return `rangea` extracted from `blocks` coming from
`mdiff.blocksinrange` along with the mask of blocks within rangeb.
"""
filtered, rangea = mdiff.blocksinrange(blocks, rangeb)
skipped = [b not in filtered for b in blocks]
return rangea, skipped
class blocksinrangetests(unittest.TestCase):
def setUp(self):
self.blocks = list(mdiff.allblocks(text1, text2))
assert self.blocks == [
([0, 3, 0, 2], '!'),
((3, 7, 2, 6), '='),
([7, 12, 6, 12], '!'),
((12, 12, 12, 12), '='),
], self.blocks
def testWithinEqual(self):
"""linerange within an "=" block"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^^
linerange2 = (3, 5)
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, (4, 6))
self.assertEqual(skipped, [True, False, True, True])
def testWithinEqualStrictly(self):
"""linerange matching exactly an "=" block"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^^^^
linerange2 = (2, 6)
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, (3, 7))
self.assertEqual(skipped, [True, False, True, True])
def testWithinEqualLowerbound(self):
"""linerange at beginning of an "=" block"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^^
linerange2 = (2, 4)
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, (3, 5))
self.assertEqual(skipped, [True, False, True, True])
def testWithinEqualLowerboundOneline(self):
"""oneline-linerange at beginning of an "=" block"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^
linerange2 = (2, 3)
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, (3, 4))
self.assertEqual(skipped, [True, False, True, True])
def testWithinEqualUpperbound(self):
"""linerange at end of an "=" block"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^^^
linerange2 = (3, 6)
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, (4, 7))
self.assertEqual(skipped, [True, False, True, True])
def testWithinEqualUpperboundOneLine(self):
"""oneline-linerange at end of an "=" block"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^
linerange2 = (5, 6)
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, (6, 7))
self.assertEqual(skipped, [True, False, True, True])
def testWithinFirstBlockNeq(self):
"""linerange within the first "!" block"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^
# | (empty)
# ^
# ^^
for linerange2 in [
(0, 1),
(1, 1),
(1, 2),
(0, 2),
]:
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, (0, 3))
self.assertEqual(skipped, [False, True, True, True])
def testWithinLastBlockNeq(self):
"""linerange within the last "!" block"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^
# ^
# | (empty)
# ^^^^^^
# ^
for linerange2 in [
(6, 7),
(7, 8),
(7, 7),
(6, 12),
(11, 12),
]:
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, (7, 12))
self.assertEqual(skipped, [True, True, False, True])
def testAccrossTwoBlocks(self):
"""linerange accross two blocks"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^^^^
linerange2 = (1, 5)
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, (0, 6))
self.assertEqual(skipped, [False, False, True, True])
def testCrossingSeveralBlocks(self):
"""linerange accross three blocks"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^^^^^^^
linerange2 = (1, 8)
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, (0, 12))
self.assertEqual(skipped, [False, False, False, True])
def testStartInEqBlock(self):
"""linerange starting in an "=" block"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^^^^
# ^^^^^^^
for linerange2, expectedlinerange1 in [
((5, 9), (6, 12)),
((4, 11), (5, 12)),
]:
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, expectedlinerange1)
self.assertEqual(skipped, [True, False, False, True])
def testEndInEqBlock(self):
"""linerange ending in an "=" block"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^^
# ^^^^^
for linerange2, expectedlinerange1 in [
((1, 3), (0, 4)),
((0, 4), (0, 5)),
]:
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, expectedlinerange1)
self.assertEqual(skipped, [False, False, True, True])
def testOutOfRange(self):
"""linerange exceeding file size"""
exctype = error.Abort
for linerange2 in [
(0, 34),
(15, 12),
]:
# Could be `with self.assertRaises(error.Abort)` but python2.6
# does not have assertRaises context manager.
try:
mdiff.blocksinrange(self.blocks, linerange2)
except exctype as exc:
self.assertTrue('line range exceeds file size' in str(exc))
else:
self.fail('%s not raised' % exctype.__name__)
if __name__ == '__main__':
import silenttestrunner
silenttestrunner.main(__name__)