view mercurial/ancestor.py @ 14076:924c82157d46

url: move URL parsing functions into util to improve startup time

The introduction of the new URL parsing code has created a startup
time regression. This is mainly due to the use of url.hasscheme() in
the ui class. It ends up importing many libraries that the url module
requires.

This fix helps marginally, but if we can get rid of the urllib import
in the URL parser all together, startup time will go back to normal.

perfstartup time before the URL refactoring (8796fb6af67e):

! wall 0.050692 comb 0.000000 user 0.000000 sys 0.000000 (best of 100)

current startup time (139fb11210bb):

! wall 0.070685 comb 0.000000 user 0.000000 sys 0.000000 (best of 100)

after this change:

! wall 0.064667 comb 0.000000 user 0.000000 sys 0.000000 (best of 100)

# ancestor.py - generic DAG ancestor algorithm for mercurial
#
# Copyright 2006 Matt Mackall <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

import heapq

def ancestor(a, b, pfunc):
    """
    Returns the common ancestor of a and b that is furthest from a
    root (as measured by longest path) or None if no ancestor is
    found. If there are multiple common ancestors at the same
    distance, the first one found is returned.

    pfunc must return a list of parent vertices for a given vertex
    """

    if a == b:
        return a

    a, b = sorted([a, b])

    # find depth from root of all ancestors
    # depth is stored as a negative for heapq
    parentcache = {}
    visit = [a, b]
    depth = {}
    while visit:
        vertex = visit[-1]
        pl = pfunc(vertex)
        parentcache[vertex] = pl
        if not pl:
            depth[vertex] = 0
            visit.pop()
        else:
            for p in pl:
                if p == a or p == b: # did we find a or b as a parent?
                    return p # we're done
                if p not in depth:
                    visit.append(p)
            if visit[-1] == vertex:
                # -(maximum distance of parents + 1)
                depth[vertex] = min([depth[p] for p in pl]) - 1
                visit.pop()

    # traverse ancestors in order of decreasing distance from root
    def ancestors(vertex):
        h = [(depth[vertex], vertex)]
        seen = set()
        while h:
            d, n = heapq.heappop(h)
            if n not in seen:
                seen.add(n)
                yield (d, n)
                for p in parentcache[n]:
                    heapq.heappush(h, (depth[p], p))

    def generations(vertex):
        sg, s = None, set()
        for g, v in ancestors(vertex):
            if g != sg:
                if sg:
                    yield sg, s
                sg, s = g, set((v,))
            else:
                s.add(v)
        yield sg, s

    x = generations(a)
    y = generations(b)
    gx = x.next()
    gy = y.next()

    # increment each ancestor list until it is closer to root than
    # the other, or they match
    try:
        while 1:
            if gx[0] == gy[0]:
                for v in gx[1]:
                    if v in gy[1]:
                        return v
                gy = y.next()
                gx = x.next()
            elif gx[0] > gy[0]:
                gy = y.next()
            else:
                gx = x.next()
    except StopIteration:
        return None