contrib/bdiff-torture.py

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

# Randomized torture test generation for bdiff

from __future__ import absolute_import, print_function
import random
import sys

from mercurial import (
    mdiff,
    pycompat,
)


def reducetest(a, b):
    tries = 0
    reductions = 0
    print("reducing...")
    while tries < 1000:
        a2 = (
            "\n".join(l for l in a.splitlines() if random.randint(0, 100) > 0)
            + "\n"
        )
        b2 = (
            "\n".join(l for l in b.splitlines() if random.randint(0, 100) > 0)
            + "\n"
        )
        if a2 == a and b2 == b:
            continue
        if a2 == b2:
            continue
        tries += 1

        try:
            test1(a, b)
        except Exception:
            reductions += 1
            tries = 0
            a = a2
            b = b2

    print("reduced:", reductions, len(a) + len(b), repr(a), repr(b))
    try:
        test1(a, b)
    except Exception as inst:
        print("failed:", inst)

    sys.exit(0)


def test1(a, b):
    d = mdiff.textdiff(a, b)
    if not d:
        raise ValueError("empty")
    c = mdiff.patches(a, [d])
    if c != b:
        raise ValueError("bad")


def testwrap(a, b):
    try:
        test1(a, b)
        return
    except Exception as inst:
        print("exception:", inst)
    reducetest(a, b)


def test(a, b):
    testwrap(a, b)
    testwrap(b, a)


def rndtest(size, noise):
    a = []
    src = "                aaaaaaaabbbbccd"
    for x in pycompat.xrange(size):
        a.append(src[random.randint(0, len(src) - 1)])

    while True:
        b = [c for c in a if random.randint(0, 99) > noise]
        b2 = []
        for c in b:
            b2.append(c)
            while random.randint(0, 99) < noise:
                b2.append(src[random.randint(0, len(src) - 1)])
        if b2 != a:
            break

    a = "\n".join(a) + "\n"
    b = "\n".join(b2) + "\n"

    test(a, b)


maxvol = 10000
startsize = 2
while True:
    size = startsize
    count = 0
    while size < maxvol:
        print(size)
        volume = 0
        while volume < maxvol:
            rndtest(size, 2)
            volume += size
            count += 2
        size *= 2
    maxvol *= 4
    startsize *= 4