Mercurial > hg
view tests/test-diff-unified.t @ 42621:99ebde4fec99
commit: improve the files field of changelog for merges
Currently, the files list of merge commits repeats all the deletions
(either actual deletions, or files that got renamed) that happened
between base and p2 of the merge. If p2 is the main branch, the list
can easily be much bigger than the change being merged.
This results in various problems worth improving:
- changelog is bigger than necessary
- `hg log directory` lists many unrelated merge commits, and `hg log
-v -r commit` frequently fills multiple screens worth of files
- it possibly slows down adjustlinkrev, by forcing it to read more
manifests, and that function can certainly be a bottleneck
- the server side of pulls can waste a lot of time simply opening the
filelogs for pointless files (the constant factors for opening even
a tiny filelog is apparently pretty bad)
So stop listing such files as described in the code. Impacted merge
commits and their descendants get a different hash than they would
have without this. This doesn't seem problematic, except for
convert. The previous commit helped with that in the hg->hg case (but
if you do svn->hg twice from scratch, hashes can still change).
The rest of the description is numbers. I don't have much to report,
because recreating the files list of existing repositories is not
easy:
- debugupgradeformat and bundle/unbundle don't recreate the list
- export/import tends to choke quickly applying patches or on
description that contain diffs,
- merge commits from the convert extension don't have the right files
list for reasons orthogonal to the current commit
- replaying the merge with hg update/hg merge/hg revert --all/hg
commit can end up failing in hg revert
- I wasn't sure that using debugsetparents + debugrebuilddirstate
would really build the right thing
I measured commit time before and after this change, in a case with no
files filtered out, several files filtered out (no difference) and 5k
files filtered out (+1% time).
Recreating the 100 more recent merges in a private repo, the
concatenated uncompressed files lists goes from 1.12MB to
0.52MB. Excluding 3 merges that are not representative, then the size
goes from 570k to 15k.
I converted part of mozilla-central, and observed file list shrinking
quite a bit too, starting at the very first merge, 733641d9feaf, going
from 550 files to 10 files (although they have relatively few merges,
so they probably wouldn't care).
Differential Revision: https://phab.mercurial-scm.org/D6613
author | Valentin Gatien-Baron <valentin.gatienbaron@gmail.com> |
---|---|
date | Tue, 02 Jul 2019 12:59:58 -0400 |
parents | 22f19da5736e |
children | df44bac9413d |
line wrap: on
line source
$ hg init repo $ cd repo $ cat > a <<EOF > c > c > a > a > b > a > a > c > c > EOF $ hg ci -Am adda adding a $ cat > a <<EOF > c > c > a > a > dd > a > a > c > c > EOF default context $ hg diff --nodates diff -r cf9f4ba66af2 a --- a/a +++ b/a @@ -2,7 +2,7 @@ c a a -b +dd a a c invalid --unified $ hg diff --nodates -U foo abort: diff context lines count must be an integer, not 'foo' [255] $ hg diff --nodates -U 2 diff -r cf9f4ba66af2 a --- a/a +++ b/a @@ -3,5 +3,5 @@ a a -b +dd a a $ hg --config diff.unified=2 diff --nodates diff -r cf9f4ba66af2 a --- a/a +++ b/a @@ -3,5 +3,5 @@ a a -b +dd a a $ hg diff --nodates -U 1 diff -r cf9f4ba66af2 a --- a/a +++ b/a @@ -4,3 +4,3 @@ a -b +dd a invalid diff.unified $ hg --config diff.unified=foo diff --nodates abort: diff context lines count must be an integer, not 'foo' [255] noprefix config and option $ hg --config diff.noprefix=True diff --nodates diff -r cf9f4ba66af2 a --- a +++ a @@ -2,7 +2,7 @@ c a a -b +dd a a c $ hg diff --noprefix --nodates diff -r cf9f4ba66af2 a --- a +++ a @@ -2,7 +2,7 @@ c a a -b +dd a a c noprefix config disabled in plain mode, but option still enabled $ HGPLAIN=1 hg --config diff.noprefix=True diff --nodates diff -r cf9f4ba66af2 a --- a/a +++ b/a @@ -2,7 +2,7 @@ c a a -b +dd a a c $ HGPLAIN=1 hg diff --noprefix --nodates diff -r cf9f4ba66af2 a --- a +++ a @@ -2,7 +2,7 @@ c a a -b +dd a a c $ cd .. 0 lines of context hunk header matches gnu diff hunk header $ hg init diffzero $ cd diffzero $ cat > f1 << EOF > c2 > c4 > c5 > EOF $ hg commit -Am0 adding f1 $ cat > f2 << EOF > c1 > c2 > c3 > c4 > EOF $ mv f2 f1 $ hg diff -U0 --nodates diff -r 55d8ff78db23 f1 --- a/f1 +++ b/f1 @@ -0,0 +1,1 @@ +c1 @@ -1,0 +3,1 @@ +c3 @@ -3,1 +4,0 @@ -c5 $ hg diff -U0 --nodates --git diff --git a/f1 b/f1 --- a/f1 +++ b/f1 @@ -0,0 +1,1 @@ +c1 @@ -1,0 +3,1 @@ +c3 @@ -3,1 +4,0 @@ -c5 $ hg diff -U0 --nodates -p diff -r 55d8ff78db23 f1 --- a/f1 +++ b/f1 @@ -0,0 +1,1 @@ +c1 @@ -1,0 +3,1 @@ c2 +c3 @@ -3,1 +4,0 @@ c4 -c5 $ echo a > f1 $ hg ci -m movef2 Test diff headers terminating with TAB when necessary (issue3357) Regular diff --nodates, file creation $ hg mv f1 'f 1' $ echo b > 'f 1' $ hg diff --nodates 'f 1' diff -r 7574207d0d15 f 1 --- /dev/null +++ b/f 1 @@ -0,0 +1,1 @@ +b Git diff, adding space $ hg diff --git diff --git a/f1 b/f 1 rename from f1 rename to f 1 --- a/f1 +++ b/f 1 @@ -1,1 +1,1 @@ -a +b Git diff, adding extended headers $ hg diff --git --config experimental.extendedheader.index=7 --config experimental.extendedheader.similarity=True diff --git a/f1 b/f 1 similarity index 0% rename from f1 rename to f 1 index 7898192..6178079 100644 --- a/f1 +++ b/f 1 @@ -1,1 +1,1 @@ -a +b $ hg diff --git --config experimental.extendedheader.index=-1 invalid length for extendedheader.index: '-1' diff --git a/f1 b/f 1 rename from f1 rename to f 1 --- a/f1 +++ b/f 1 @@ -1,1 +1,1 @@ -a +b $ hg diff --git --config experimental.extendedheader.index=whatever invalid value for extendedheader.index: 'whatever' diff --git a/f1 b/f 1 rename from f1 rename to f 1 --- a/f1 +++ b/f 1 @@ -1,1 +1,1 @@ -a +b Git diff with noprefix $ hg --config diff.noprefix=True diff --git --nodates diff --git f1 f 1 rename from f1 rename to f 1 --- f1 +++ f 1 @@ -1,1 +1,1 @@ -a +b noprefix config disabled in plain mode, but option still enabled $ HGPLAIN=1 hg --config diff.noprefix=True diff --git --nodates diff --git a/f1 b/f 1 rename from f1 rename to f 1 --- a/f1 +++ b/f 1 @@ -1,1 +1,1 @@ -a +b $ HGPLAIN=1 hg diff --git --noprefix --nodates diff --git f1 f 1 rename from f1 rename to f 1 --- f1 +++ f 1 @@ -1,1 +1,1 @@ -a +b Regular diff --nodates, file deletion $ hg ci -m addspace $ hg mv 'f 1' f1 $ echo a > f1 $ hg diff --nodates 'f 1' diff -r ca50fe67c9c7 f 1 --- a/f 1 +++ /dev/null @@ -1,1 +0,0 @@ -b Git diff, removing space $ hg diff --git diff --git a/f 1 b/f1 rename from f 1 rename to f1 --- a/f 1 +++ b/f1 @@ -1,1 +1,1 @@ -b +a showfunc diff $ cat > f1 << EOF > int main() { > int a = 0; > int b = 1; > int c = 2; > int d = 3; > return a + b + c + d; > } > EOF $ hg commit -m addfunction $ cat > f1 << EOF > int main() { > int a = 0; > int b = 1; > int c = 2; > int e = 3; > return a + b + c + e; > } > EOF $ hg diff --git diff --git a/f1 b/f1 --- a/f1 +++ b/f1 @@ -2,6 +2,6 @@ int a = 0; int b = 1; int c = 2; - int d = 3; - return a + b + c + d; + int e = 3; + return a + b + c + e; } $ hg diff --config diff.showfunc=True --git diff --git a/f1 b/f1 --- a/f1 +++ b/f1 @@ -2,6 +2,6 @@ int main() { int a = 0; int b = 1; int c = 2; - int d = 3; - return a + b + c + d; + int e = 3; + return a + b + c + e; } If [diff] git is set to true, but the user says --no-git, we should *not* get git diffs $ hg diff --nodates --config diff.git=1 --no-git diff -r f2c7c817fa55 f1 --- a/f1 +++ b/f1 @@ -2,6 +2,6 @@ int a = 0; int b = 1; int c = 2; - int d = 3; - return a + b + c + d; + int e = 3; + return a + b + c + e; } $ cd .. Long function names should be abbreviated, but multi-byte character shouldn't be broken up $ hg init longfunc $ cd longfunc >>> with open('a', 'wb') as f: ... f.write(b'a' * 39 + b'bb' + b'\n') and None ... f.write(b' .\n' * 3) and None ... f.write(b' 0 b\n') and None ... f.write(b' .\n' * 3) and None ... f.write(b'a' * 39 + b'\xc3\xa0' + b'\n') and None ... f.write(b' .\n' * 3) and None ... f.write(b' 0 a with grave (single code point)\n') and None ... f.write(b' .\n' * 3) and None ... f.write(b'a' * 39 + b'a\xcc\x80' + b'\n') and None ... f.write(b' .\n' * 3) and None ... f.write(b' 0 a with grave (composition)\n') and None ... f.write(b' .\n' * 3) and None $ hg ci -qAm0 >>> with open('a', 'wb') as f: ... f.write(b'a' * 39 + b'bb' + b'\n') and None ... f.write(b' .\n' * 3) and None ... f.write(b' 1 b\n') and None ... f.write(b' .\n' * 3) and None ... f.write(b'a' * 39 + b'\xc3\xa0' + b'\n') and None ... f.write(b' .\n' * 3) and None ... f.write(b' 1 a with grave (single code point)\n') and None ... f.write(b' .\n' * 3) and None ... f.write(b'a' * 39 + b'a\xcc\x80' + b'\n') and None ... f.write(b' .\n' * 3) and None ... f.write(b' 1 a with grave (composition)\n') and None ... f.write(b' .\n' * 3) and None $ hg ci -m1 $ hg diff -c1 --nodates --show-function diff -r 3e92dd6fa812 -r a256341606cb a --- a/a +++ b/a @@ -2,7 +2,7 @@ aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaab . . . - 0 b + 1 b . . . @@ -10,7 +10,7 @@ aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa\xc3\xa0 (esc) . . . - 0 a with grave (single code point) + 1 a with grave (single code point) . . . @@ -18,7 +18,7 @@ aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa\xcc\x80 (esc) . . . - 0 a with grave (composition) + 1 a with grave (composition) . . . $ cd ..