annotate mercurial/graphmod.py @ 16719:e7bf09acd410

localrepo: add branchtip() method for faster single-branch lookups

For the PyPy repo with 744 branches and 843 branch heads, this brings
hg log -r default over NFS from:

   CallCount    Recursive    Total(ms)   Inline(ms) module:lineno(function)
        3249            0      1.3222      1.3222   <open>
        3244            0      0.6211      0.6211   <method 'close' of 'file' objects>
        3243            0      0.0800      0.0800   <method 'read' of 'file' objects>
        3241            0      0.0660      0.0660   <method 'seek' of 'file' objects>
        3905            0      0.0476      0.0476   <zlib.decompress>
        3281            0      2.6756      0.0472   mercurial.changelog:182(read)
       +3281            0      2.5256      0.0453   +mercurial.revlog:881(revision)
       +3276            0      0.0389      0.0196   +mercurial.changelog:28(decodeextra)
       +6562            0      0.0123      0.0123   +<method 'split' of 'str' objects>
       +6562            0      0.0408      0.0073   +mercurial.encoding:61(tolocal)
       +3281            0      0.0054      0.0054   +<method 'index' of 'str' objects>
        3241            0      2.2464      0.0456   mercurial.revlog:818(_loadchunk)
       +3241            0      0.6205      0.6205   +<method 'close' of 'file' objects>
       +3241            0      0.0765      0.0765   +<method 'read' of 'file' objects>
       +3241            0      0.0660      0.0660   +<method 'seek' of 'file' objects>
       +3241            0      1.4209      0.0135   +mercurial.store:374(__call__)
       +3241            0      0.0122      0.0107   +mercurial.revlog:810(_addchunk)
        3281            0      2.5256      0.0453   mercurial.revlog:881(revision)
       +3280            0      0.0175      0.0175   +mercurial.revlog:305(rev)
       +3281            0      2.2819      0.0119   +mercurial.revlog:847(_chunkraw)
       +3281            0      0.0603      0.0083   +mercurial.revlog:945(_checkhash)
       +3281            0      0.0051      0.0051   +mercurial.revlog:349(flags)
       +3281            0      0.0040      0.0040   +<mercurial.mpatch.patches>
       13682            0      0.0479      0.0248   <method 'decode' of 'str' objects>
       +7418            0      0.0228      0.0076   +encodings.utf_8:15(decode)
          +1            0      0.0003      0.0000   +encodings:71(search_function)
        3248            0      1.3995      0.0246   mercurial.scmutil:218(__call__)
       +3248            0      1.3222      1.3222   +<open>
       +3248            0      0.0235      0.0184   +os.path:80(split)
       +3248            0      0.0084      0.0068   +mercurial.scmutil:92(__call__)
Time: real 2.750 secs (user 0.680+0.000 sys 0.360+0.000)

down to:

   CallCount    Recursive    Total(ms)   Inline(ms) module:lineno(function)
          55           31      0.0197      0.0163   <__import__>
          +1            0      0.0006      0.0002   +mercurial.context:8(<module>)
          +1            0      0.0042      0.0001   +mercurial.revlog:12(<module>)
          +1            0      0.0002      0.0001   +mercurial.match:8(<module>)
          +1            0      0.0003      0.0001   +mercurial.dirstate:7(<module>)
          +1            0      0.0057      0.0001   +mercurial.changelog:8(<module>)
           1            0      0.0117      0.0032   mercurial.localrepo:525(_readbranchcache)
        +844            0      0.0015      0.0015   +<binascii.unhexlify>
        +845            0      0.0010      0.0010   +<method 'split' of 'str' objects>
        +843            0      0.0045      0.0009   +mercurial.encoding:61(tolocal)
        +843            0      0.0004      0.0004   +<method 'setdefault' of 'dict' objects>
          +1            0      0.0003      0.0003   +<method 'close' of 'file' objects>
           3            0      0.0029      0.0029   <method 'read' of 'file' objects>
           9            0      0.0018      0.0018   <open>
         990            0      0.0017      0.0017   <binascii.unhexlify>
          53            0      0.0016      0.0016   mercurial.demandimport:43(__init__)
         862            0      0.0015      0.0015   <_codecs.utf_8_decode>
         862            0      0.0037      0.0014   <method 'decode' of 'str' objects>
        +862            0      0.0023      0.0008   +encodings.utf_8:15(decode)
         981            0      0.0011      0.0011   <method 'split' of 'str' objects>
         861            0      0.0046      0.0009   mercurial.encoding:61(tolocal)
        +861            0      0.0037      0.0014   +<method 'decode' of 'str' objects>
         862            0      0.0023      0.0008   encodings.utf_8:15(decode)
        +862            0      0.0015      0.0015   +<_codecs.utf_8_decode>
           4            0      0.0008      0.0008   <method 'close' of 'file' objects>
         179          154      0.0202      0.0004   mercurial.demandimport:83(__getattribute__)
         +36           11      0.0199      0.0003   +mercurial.demandimport:55(_load)
         +72            0      0.0001      0.0001   +mercurial.demandimport:83(__getattribute__)
         +36            0      0.0000      0.0000   +<getattr>
           1            0      0.0015      0.0004   mercurial.tags:148(_readtagcache)
Time: real 0.060 secs (user 0.030+0.000 sys 0.010+0.000)

# Revision graph generator for Mercurial
#
# Copyright 2008 Dirkjan Ochtman <[e-mail]>
# Copyright 2007 Joel Rosdahl <[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.

"""supports walking the history as DAGs suitable for graphical output

The most basic format we use is that of::

  (id, type, data, [parentids])

The node and parent ids are arbitrary integers which identify a node in the
context of the graph returned. Type is a constant specifying the node type.
Data depends on type.
"""

from mercurial.node import nullrev
import util

CHANGESET = 'C'

def dagwalker(repo, revs):
    """cset DAG generator yielding (id, CHANGESET, ctx, [parentids]) tuples

    This generator function walks through revisions (which should be ordered
    from bigger to lower). It returns a tuple for each node. The node and parent
    ids are arbitrary integers which identify a node in the context of the graph
    returned.
    """
    if not revs:
        return

    cl = repo.changelog
    lowestrev = min(revs)
    gpcache = {}

    knownrevs = set(revs)
    for rev in revs:
        ctx = repo[rev]
        parents = sorted(set([p.rev() for p in ctx.parents()
                              if p.rev() in knownrevs]))
        mpars = [p.rev() for p in ctx.parents() if
                 p.rev() != nullrev and p.rev() not in parents]

        for mpar in mpars:
            gp = gpcache.get(mpar)
            if gp is None:
                gp = gpcache[mpar] = grandparent(cl, lowestrev, revs, mpar)
            if not gp:
                parents.append(mpar)
            else:
                parents.extend(g for g in gp if g not in parents)

        yield (ctx.rev(), CHANGESET, ctx, parents)

def nodes(repo, nodes):
    """cset DAG generator yielding (id, CHANGESET, ctx, [parentids]) tuples

    This generator function walks the given nodes. It only returns parents
    that are in nodes, too.
    """
    include = set(nodes)
    for node in nodes:
        ctx = repo[node]
        parents = set([p.rev() for p in ctx.parents() if p.node() in include])
        yield (ctx.rev(), CHANGESET, ctx, sorted(parents))

def colored(dag, repo):
    """annotates a DAG with colored edge information

    For each DAG node this function emits tuples::

      (id, type, data, (col, color), [(col, nextcol, color)])

    with the following new elements:

      - Tuple (col, color) with column and color index for the current node
      - A list of tuples indicating the edges between the current node and its
        parents.
    """
    seen = []
    colors = {}
    newcolor = 1
    config = {}

    for key, val in repo.ui.configitems('graph'):
        if '.' in key:
            branch, setting = key.rsplit('.', 1)
            # Validation
            if setting == "width" and val.isdigit():
                config.setdefault(branch, {})[setting] = int(val)
            elif setting == "color" and val.isalnum():
                config.setdefault(branch, {})[setting] = val

    if config:
        getconf = util.lrucachefunc(
            lambda rev: config.get(repo[rev].branch(), {}))
    else:
        getconf = lambda rev: {}

    for (cur, type, data, parents) in dag:

        # Compute seen and next
        if cur not in seen:
            seen.append(cur) # new head
            colors[cur] = newcolor
            newcolor += 1

        col = seen.index(cur)
        color = colors.pop(cur)
        next = seen[:]

        # Add parents to next
        addparents = [p for p in parents if p not in next]
        next[col:col + 1] = addparents

        # Set colors for the parents
        for i, p in enumerate(addparents):
            if not i:
                colors[p] = color
            else:
                colors[p] = newcolor
                newcolor += 1

        # Add edges to the graph
        edges = []
        for ecol, eid in enumerate(seen):
            if eid in next:
                bconf = getconf(eid)
                edges.append((
                    ecol, next.index(eid), colors[eid],
                    bconf.get('width', -1),
                    bconf.get('color', '')))
            elif eid == cur:
                for p in parents:
                    bconf = getconf(p)
                    edges.append((
                        ecol, next.index(p), color,
                        bconf.get('width', -1),
                        bconf.get('color', '')))

        # Yield and move on
        yield (cur, type, data, (col, color), edges)
        seen = next

def grandparent(cl, lowestrev, roots, head):
    """Return all ancestors of head in roots which revision is
    greater or equal to lowestrev.
    """
    pending = set([head])
    seen = set()
    kept = set()
    llowestrev = max(nullrev, lowestrev)
    while pending:
        r = pending.pop()
        if r >= llowestrev and r not in seen:
            if r in roots:
                kept.add(r)
            else:
                pending.update([p for p in cl.parentrevs(r)])
            seen.add(r)
    return sorted(kept)