Mercurial > hg
view tests/test-cat.t @ 47965:f9e6f2bb721d
rhg: Don’t compare ambiguous files one byte at a time
Even though the use of `BufReader` reduces the number of syscalls to read
the file from disk, `.bytes()` yields a separate `Result` for every byte.
Creating those results and dispatching on them is most likely costly.
Instead, this commit opts for simplicity by reading the entire file into memory
and comparing a single pair of byte strings. Note that memory already needs to
contain the entire previous contents of the file, as read from the filelog.
So with an extremely large file this doubles memory use but does not make it
grow by orders of magnitude.
At first I wrote code that still avoids reading the entire file into memory
and compares one buffer at a time with `BufReader`. Find this code below for
posterity. However its correctness is subtle. I ended up preferring the
simplicity of the obviously-correct single comparison.
```rust
let mut reader = BufReader::new(fobj);
let mut expected = &contents_in_p1[..];
loop {
let buf = reader.fill_buf().when_reading_file(&fs_path)?;
if buf.is_empty() {
// Found EOF
return Ok(expected.is_empty());
} else if let Some(rest) = expected.drop_prefix(buf) {
// What we read so far matches the expected content, continue reading
let buf_len = buf.len();
reader.consume(buf_len);
expected = rest
} else {
// Found different content
return Ok(false);
}
}
```
Differential Revision: https://phab.mercurial-scm.org/D11412
author | Simon Sapin <simon.sapin@octobus.net> |
---|---|
date | Mon, 13 Sep 2021 18:48:48 +0200 |
parents | 34ba47117164 |
children | 55c6ebd11cb9 |
line wrap: on
line source
$ hg init $ echo 0 > a $ echo 0 > b $ hg ci -A -m m adding a adding b $ hg rm a $ hg cat a 0 $ hg cat --decode a # more tests in test-encode 0 $ echo 1 > b $ hg ci -m m $ echo 2 > b $ hg cat -r 0 a 0 $ hg cat -r 0 b 0 $ hg cat -r 1 a a: no such file in rev 7040230c159c [1] $ hg cat -r 1 b 1 Test multiple files $ echo 3 > c $ hg ci -Am addmore c $ hg cat b c 1 3 $ hg cat . 1 3 $ hg cat . c 1 3 Test fileset $ hg cat 'set:not(b) or a' 3 $ hg cat 'set:c or b' 1 3 $ mkdir tmp $ hg cat --output tmp/HH_%H c $ hg cat --output tmp/RR_%R c $ hg cat --output tmp/h_%h c $ hg cat --output tmp/r_%r c $ hg cat --output tmp/%s_s c $ hg cat --output tmp/%d%%_d c $ hg cat --output tmp/%p_p c $ hg log -r . --template "{rev}: {node|short}\n" 2: 45116003780e $ find tmp -type f | sort tmp/.%_d tmp/HH_45116003780e3678b333fb2c99fa7d559c8457e9 tmp/RR_2 tmp/c_p tmp/c_s tmp/h_45116003780e tmp/r_2 Test template output $ hg --cwd tmp cat ../b ../c -T '== {path|relpath} ({path}) r{rev} ==\n{data}' == ../b (b) r2 == 1 == ../c (c) r2 == 3 $ hg cat b c -Tjson --output - [ { "data": "1\n", "path": "b" }, { "data": "3\n", "path": "c" } ] $ hg cat b c -Tjson --output 'tmp/%p.json' $ cat tmp/b.json [ { "data": "1\n", "path": "b" } ] $ cat tmp/c.json [ { "data": "3\n", "path": "c" } ] Test working directory $ echo b-wdir > b $ hg cat -r 'wdir()' b b-wdir Environment variables are not visible by default $ PATTERN='t4' hg log -r '.' -T "{ifcontains('PATTERN', envvars, 'yes', 'no')}\n" no Environment variable visibility can be explicit $ PATTERN='t4' hg log -r '.' -T "{envvars % '{key} -> {value}\n'}" \ > --config "experimental.exportableenviron=PATTERN" PATTERN -> t4 Test behavior of output when directory structure does not already exist $ mkdir foo $ echo a > foo/a $ hg add foo/a $ hg commit -qm "add foo/a" $ hg cat --output "output/%p" foo/a $ cat output/foo/a a