tests/test-filelog.py

revset: fix order of nested 'or' expression (BC)

This fixes the order of 'x & (y + z)' where 'y' and 'z' are not trivial.

The follow-order 'or' operation is slower than the ordered operation if
an input set is large:

       #0           #1           #2           #3
    0) 0.002968     0.002980     0.002982     0.073042
    1) 0.004513     0.004485     0.012029     0.075261

    #0: 0:4000 & (0:1099 + 1000:2099 + 2000:3099)
    #1: 4000:0 & (0:1099 + 1000:2099 + 2000:3099)
    #2: 10000:0 & (0:1099 + 1000:2099 + 2000:3099)
    #3: file("path:hg") & (0:1099 + 1000:2099 + 2000:3099)

I've tried another implementation, but which appeared to be slower than
this version.

    ss = [getset(repo, fullreposet(repo), x) for x in xs]
    return subset.filter(lambda r: any(r in s for s in ss), cache=False)

#!/usr/bin/env python
"""
Tests the behavior of filelog w.r.t. data starting with '\1\n'
"""
from __future__ import absolute_import, print_function

from mercurial.node import (
    hex,
    nullid,
)
from mercurial import (
    hg,
    ui as uimod,
)

myui = uimod.ui()
repo = hg.repository(myui, path='.', create=True)

fl = repo.file('foobar')

def addrev(text, renamed=False):
    if renamed:
        # data doesn't matter. Just make sure filelog.renamed() returns True
        meta = {'copyrev': hex(nullid), 'copy': 'bar'}
    else:
        meta = {}

    lock = t = None
    try:
        lock = repo.lock()
        t = repo.transaction('commit')
        node = fl.add(text, meta, t, 0, nullid, nullid)
        return node
    finally:
        if t:
            t.close()
        if lock:
            lock.release()

def error(text):
    print('ERROR: ' + text)

textwith = '\1\nfoo'
without = 'foo'

node = addrev(textwith)
if not textwith == fl.read(node):
    error('filelog.read for data starting with \\1\\n')
if fl.cmp(node, textwith) or not fl.cmp(node, without):
    error('filelog.cmp for data starting with \\1\\n')
if fl.size(0) != len(textwith):
    error('FIXME: This is a known failure of filelog.size for data starting '
        'with \\1\\n')

node = addrev(textwith, renamed=True)
if not textwith == fl.read(node):
    error('filelog.read for a renaming + data starting with \\1\\n')
if fl.cmp(node, textwith) or not fl.cmp(node, without):
    error('filelog.cmp for a renaming + data starting with \\1\\n')
if fl.size(1) != len(textwith):
    error('filelog.size for a renaming + data starting with \\1\\n')

print('OK.')