fastannotate: initial import from Facebook's hg-experimental
I made as few changes as I could to get the tests to pass, but this
was a bit involved due to some churn in the blame code since someone
last gave fastannotate any TLC.
There's still follow-up work here to rip out support for old versions
of hg and to integrate the protocol with modern standards.
Some performance numbers (all on my 2016 MacBook Pro with a 2.6Ghz i7):
Mercurial mercurial/manifest.py
traditional blame
time: real 1.050 secs (user 0.990+0.000 sys 0.060+0.000)
build cache
time: real 5.900 secs (user 5.720+0.000 sys 0.110+0.000)
fastannotate
time: real 0.120 secs (user 0.100+0.000 sys 0.020+0.000)
Mercurial mercurial/localrepo.py
traditional blame
time: real 3.330 secs (user 3.220+0.000 sys 0.070+0.000)
build cache
time: real 30.610 secs (user 30.190+0.000 sys 0.230+0.000)
fastannotate
time: real 0.180 secs (user 0.160+0.000 sys 0.020+0.000)
mozilla-central dom/ipc/ContentParent.cpp
traditional blame
time: real 7.640 secs (user 7.210+0.000 sys 0.380+0.000)
build cache
time: real 98.650 secs (user 97.000+0.000 sys 0.950+0.000)
fastannotate
time: real 1.580 secs (user 1.340+0.000 sys 0.240+0.000)
mozilla-central dom/base/nsDocument.cpp
traditional blame
time: real 17.110 secs (user 16.490+0.000 sys 0.500+0.000)
build cache
time: real 399.750 secs (user 394.520+0.000 sys 2.610+0.000)
fastannotate
time: real 1.780 secs (user 1.530+0.000 sys 0.240+0.000)
So building the cache is expensive (but might be faster with xdiff
enabled), but the blame results are *way* faster.
Differential Revision: https://phab.mercurial-scm.org/D3994
from __future__ import absolute_import
import unittest
from mercurial import error, mdiff
# for readability, line numbers are 0-origin
text1 = b'''
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 = b'''
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], b'!'),
((3, 7, 2, 6), b'='),
([7, 12, 6, 12], b'!'),
((12, 12, 12, 12), b'='),
], 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__)