view tests/test-status-rev.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

Tests of 'hg status --rev <rev>' to make sure status between <rev> and '.' get
combined correctly with the dirstate status.

  $ hg init

First commit

  $ "$PYTHON" $TESTDIR/generate-working-copy-states.py state 2 1
  $ hg addremove --similarity 0
  adding content1_content1_content1-tracked
  adding content1_content1_content1-untracked
  adding content1_content1_content3-tracked
  adding content1_content1_content3-untracked
  adding content1_content1_missing-tracked
  adding content1_content1_missing-untracked
  adding content1_content2_content1-tracked
  adding content1_content2_content1-untracked
  adding content1_content2_content2-tracked
  adding content1_content2_content2-untracked
  adding content1_content2_content3-tracked
  adding content1_content2_content3-untracked
  adding content1_content2_missing-tracked
  adding content1_content2_missing-untracked
  adding content1_missing_content1-tracked
  adding content1_missing_content1-untracked
  adding content1_missing_content3-tracked
  adding content1_missing_content3-untracked
  adding content1_missing_missing-tracked
  adding content1_missing_missing-untracked
  $ hg commit -m first

Second commit

  $ "$PYTHON" $TESTDIR/generate-working-copy-states.py state 2 2
  $ hg addremove --similarity 0
  removing content1_missing_content1-tracked
  removing content1_missing_content1-untracked
  removing content1_missing_content3-tracked
  removing content1_missing_content3-untracked
  removing content1_missing_missing-tracked
  removing content1_missing_missing-untracked
  adding missing_content2_content2-tracked
  adding missing_content2_content2-untracked
  adding missing_content2_content3-tracked
  adding missing_content2_content3-untracked
  adding missing_content2_missing-tracked
  adding missing_content2_missing-untracked
  $ hg commit -m second

Working copy

  $ "$PYTHON" $TESTDIR/generate-working-copy-states.py state 2 wc
  $ hg addremove --similarity 0
  adding content1_missing_content1-tracked
  adding content1_missing_content1-untracked
  adding content1_missing_content3-tracked
  adding content1_missing_content3-untracked
  adding content1_missing_missing-tracked
  adding content1_missing_missing-untracked
  adding missing_missing_content3-tracked
  adding missing_missing_content3-untracked
  adding missing_missing_missing-tracked
  adding missing_missing_missing-untracked
  $ hg forget *_*_*-untracked
  $ rm *_*_missing-*

Status compared to parent of the working copy, i.e. the dirstate status

  $ hg status -A --rev 1 'glob:missing_content2_content3-tracked'
  M missing_content2_content3-tracked
  $ hg status -A --rev 1 'glob:missing_content2_content2-tracked'
  C missing_content2_content2-tracked
  $ hg status -A --rev 1 'glob:missing_missing_content3-tracked'
  A missing_missing_content3-tracked
  $ hg status -A --rev 1 'glob:missing_missing_content3-untracked'
  ? missing_missing_content3-untracked
  $ hg status -A --rev 1 'glob:missing_content2_*-untracked'
  R missing_content2_content2-untracked
  R missing_content2_content3-untracked
  R missing_content2_missing-untracked
  $ hg status -A --rev 1 'glob:missing_*_missing-tracked'
  ! missing_content2_missing-tracked
  ! missing_missing_missing-tracked

  $ hg status -A --rev 1 'glob:missing_missing_missing-untracked'
  missing_missing_missing-untracked: $ENOENT$

Status between first and second commit. Should ignore dirstate status.

  $ hg status -A --rev 0:1 'glob:content1_content2_*'
  M content1_content2_content1-tracked
  M content1_content2_content1-untracked
  M content1_content2_content2-tracked
  M content1_content2_content2-untracked
  M content1_content2_content3-tracked
  M content1_content2_content3-untracked
  M content1_content2_missing-tracked
  M content1_content2_missing-untracked
  $ hg status -A --rev 0:1 'glob:content1_content1_*'
  C content1_content1_content1-tracked
  C content1_content1_content1-untracked
  C content1_content1_content3-tracked
  C content1_content1_content3-untracked
  C content1_content1_missing-tracked
  C content1_content1_missing-untracked
  $ hg status -A --rev 0:1 'glob:missing_content2_*'
  A missing_content2_content2-tracked
  A missing_content2_content2-untracked
  A missing_content2_content3-tracked
  A missing_content2_content3-untracked
  A missing_content2_missing-tracked
  A missing_content2_missing-untracked
  $ hg status -A --rev 0:1 'glob:content1_missing_*'
  R content1_missing_content1-tracked
  R content1_missing_content1-untracked
  R content1_missing_content3-tracked
  R content1_missing_content3-untracked
  R content1_missing_missing-tracked
  R content1_missing_missing-untracked
  $ hg status -A --rev 0:1 'glob:missing_missing_*'

Status compared to one revision back, checking that the dirstate status
is correctly combined with the inter-revision status

  $ hg status -A --rev 0 'glob:content1_*_content[23]-tracked'
  M content1_content1_content3-tracked
  M content1_content2_content2-tracked
  M content1_content2_content3-tracked
  M content1_missing_content3-tracked
  $ hg status -A --rev 0 'glob:content1_*_content1-tracked'
  C content1_content1_content1-tracked
  C content1_content2_content1-tracked
  C content1_missing_content1-tracked
  $ hg status -A --rev 0 'glob:missing_*_content?-tracked'
  A missing_content2_content2-tracked
  A missing_content2_content3-tracked
  A missing_missing_content3-tracked
BROKEN: missing_content2_content[23]-untracked exist, so should be listed
  $ hg status -A --rev 0 'glob:missing_*_content?-untracked'
  ? missing_missing_content3-untracked
  $ hg status -A --rev 0 'glob:content1_*_*-untracked'
  R content1_content1_content1-untracked
  R content1_content1_content3-untracked
  R content1_content1_missing-untracked
  R content1_content2_content1-untracked
  R content1_content2_content2-untracked
  R content1_content2_content3-untracked
  R content1_content2_missing-untracked
  R content1_missing_content1-untracked
  R content1_missing_content3-untracked
  R content1_missing_missing-untracked
  $ hg status -A --rev 0 'glob:*_*_missing-tracked'
  ! content1_content1_missing-tracked
  ! content1_content2_missing-tracked
  ! content1_missing_missing-tracked
  ! missing_content2_missing-tracked
  ! missing_missing_missing-tracked
  $ hg status -A --rev 0 'glob:missing_*_missing-untracked'