tests/test-filelog.py

log: speed up single file log with hidden revs (issue4747)

On repos with lots of heads, the filelog() code could spend several
minutes decompressing manifests. This change instead tries to
efficiently scan the changelog for candidates and decompress as few
manifests as possible. This is a regression introduced in 3.3 by the
linkrev adjustment code. Prior to that, filelog was nearly instant.

For the repo in the bug report, this improves time of a simple log
command from ~3 minutes to ~.5 seconds, a 360x speedup.

For the main Mercurial repo, a log of commands.py slows down from
1.14s to 1.45s, a 27% slowdown. This is still faster than the file()
revset, which takes 2.1 seconds.

#!/usr/bin/env python
"""
Tests the behavior of filelog w.r.t. data starting with '\1\n'
"""
from mercurial import ui, hg
from mercurial.node import nullid, hex

myui = ui.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.'