mercurial/hgweb/webutil.py

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)

# hgweb/webutil.py - utility library for the web interface.
#
# Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
# Copyright 2005-2007 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 os, copy
from mercurial import match, patch, scmutil, error, ui, util
from mercurial.i18n import _
from mercurial.node import hex, nullid

def up(p):
    if p[0] != "/":
        p = "/" + p
    if p[-1] == "/":
        p = p[:-1]
    up = os.path.dirname(p)
    if up == "/":
        return "/"
    return up + "/"

def revnavgen(pos, pagelen, limit, nodefunc):
    def seq(factor, limit=None):
        if limit:
            yield limit
            if limit >= 20 and limit <= 40:
                yield 50
        else:
            yield 1 * factor
            yield 3 * factor
        for f in seq(factor * 10):
            yield f

    navbefore = []
    navafter = []

    last = 0
    for f in seq(1, pagelen):
        if f < pagelen or f <= last:
            continue
        if f > limit:
            break
        last = f
        if pos + f < limit:
            navafter.append(("+%d" % f, hex(nodefunc(pos + f).node())))
        if pos - f >= 0:
            navbefore.insert(0, ("-%d" % f, hex(nodefunc(pos - f).node())))

    navafter.append(("tip", "tip"))
    try:
        navbefore.insert(0, ("(0)", hex(nodefunc('0').node())))
    except error.RepoError:
        pass

    def gen(l):
        def f(**map):
            for label, node in l:
                yield {"label": label, "node": node}
        return f

    return (dict(before=gen(navbefore), after=gen(navafter)),)

def _siblings(siblings=[], hiderev=None):
    siblings = [s for s in siblings if s.node() != nullid]
    if len(siblings) == 1 and siblings[0].rev() == hiderev:
        return
    for s in siblings:
        d = {'node': s.hex(), 'rev': s.rev()}
        d['user'] = s.user()
        d['date'] = s.date()
        d['description'] = s.description()
        d['branch'] = s.branch()
        if util.safehasattr(s, 'path'):
            d['file'] = s.path()
        yield d

def parents(ctx, hide=None):
    return _siblings(ctx.parents(), hide)

def children(ctx, hide=None):
    return _siblings(ctx.children(), hide)

def renamelink(fctx):
    r = fctx.renamed()
    if r:
        return [dict(file=r[0], node=hex(r[1]))]
    return []

def nodetagsdict(repo, node):
    return [{"name": i} for i in repo.nodetags(node)]

def nodebookmarksdict(repo, node):
    return [{"name": i} for i in repo.nodebookmarks(node)]

def nodebranchdict(repo, ctx):
    branches = []
    branch = ctx.branch()
    # If this is an empty repo, ctx.node() == nullid,
    # ctx.branch() == 'default'.
    try:
        branchnode = repo.branchtip(branch)
    except error.RepoLookupError:
        branchnode = None
    if branchnode == ctx.node():
        branches.append({"name": branch})
    return branches

def nodeinbranch(repo, ctx):
    branches = []
    branch = ctx.branch()
    try:
        branchnode = repo.branchtip(branch)
    except error.RepoLookupError:
        branchnode = None
    if branch != 'default' and branchnode != ctx.node():
        branches.append({"name": branch})
    return branches

def nodebranchnodefault(ctx):
    branches = []
    branch = ctx.branch()
    if branch != 'default':
        branches.append({"name": branch})
    return branches

def showtag(repo, tmpl, t1, node=nullid, **args):
    for t in repo.nodetags(node):
        yield tmpl(t1, tag=t, **args)

def showbookmark(repo, tmpl, t1, node=nullid, **args):
    for t in repo.nodebookmarks(node):
        yield tmpl(t1, bookmark=t, **args)

def cleanpath(repo, path):
    path = path.lstrip('/')
    return scmutil.canonpath(repo.root, '', path)

def changectx(repo, req):
    changeid = "tip"
    if 'node' in req.form:
        changeid = req.form['node'][0]
    elif 'manifest' in req.form:
        changeid = req.form['manifest'][0]

    try:
        ctx = repo[changeid]
    except error.RepoError:
        man = repo.manifest
        ctx = repo[man.linkrev(man.rev(man.lookup(changeid)))]

    return ctx

def filectx(repo, req):
    path = cleanpath(repo, req.form['file'][0])
    if 'node' in req.form:
        changeid = req.form['node'][0]
    else:
        changeid = req.form['filenode'][0]
    try:
        fctx = repo[changeid][path]
    except error.RepoError:
        fctx = repo.filectx(path, fileid=changeid)

    return fctx

def listfilediffs(tmpl, files, node, max):
    for f in files[:max]:
        yield tmpl('filedifflink', node=hex(node), file=f)
    if len(files) > max:
        yield tmpl('fileellipses')

def diffs(repo, tmpl, ctx, files, parity, style):

    def countgen():
        start = 1
        while True:
            yield start
            start += 1

    blockcount = countgen()
    def prettyprintlines(diff, blockno):
        for lineno, l in enumerate(diff.splitlines(True)):
            lineno = "%d.%d" % (blockno, lineno + 1)
            if l.startswith('+'):
                ltype = "difflineplus"
            elif l.startswith('-'):
                ltype = "difflineminus"
            elif l.startswith('@'):
                ltype = "difflineat"
            else:
                ltype = "diffline"
            yield tmpl(ltype,
                       line=l,
                       lineid="l%s" % lineno,
                       linenumber="% 8s" % lineno)

    if files:
        m = match.exact(repo.root, repo.getcwd(), files)
    else:
        m = match.always(repo.root, repo.getcwd())

    diffopts = patch.diffopts(repo.ui, untrusted=True)
    parents = ctx.parents()
    node1 = parents and parents[0].node() or nullid
    node2 = ctx.node()

    block = []
    for chunk in patch.diff(repo, node1, node2, m, opts=diffopts):
        if chunk.startswith('diff') and block:
            blockno = blockcount.next()
            yield tmpl('diffblock', parity=parity.next(), blockno=blockno,
                       lines=prettyprintlines(''.join(block), blockno))
            block = []
        if chunk.startswith('diff') and style != 'raw':
            chunk = ''.join(chunk.splitlines(True)[1:])
        block.append(chunk)
    blockno = blockcount.next()
    yield tmpl('diffblock', parity=parity.next(), blockno=blockno,
               lines=prettyprintlines(''.join(block), blockno))

def diffstatgen(ctx):
    '''Generator function that provides the diffstat data.'''

    stats = patch.diffstatdata(util.iterlines(ctx.diff()))
    maxname, maxtotal, addtotal, removetotal, binary = patch.diffstatsum(stats)
    while True:
        yield stats, maxname, maxtotal, addtotal, removetotal, binary

def diffsummary(statgen):
    '''Return a short summary of the diff.'''

    stats, maxname, maxtotal, addtotal, removetotal, binary = statgen.next()
    return _(' %d files changed, %d insertions(+), %d deletions(-)\n') % (
             len(stats), addtotal, removetotal)

def diffstat(tmpl, ctx, statgen, parity):
    '''Return a diffstat template for each file in the diff.'''

    stats, maxname, maxtotal, addtotal, removetotal, binary = statgen.next()
    files = ctx.files()

    def pct(i):
        if maxtotal == 0:
            return 0
        return (float(i) / maxtotal) * 100

    fileno = 0
    for filename, adds, removes, isbinary in stats:
        template = filename in files and 'diffstatlink' or 'diffstatnolink'
        total = adds + removes
        fileno += 1
        yield tmpl(template, node=ctx.hex(), file=filename, fileno=fileno,
                   total=total, addpct=pct(adds), removepct=pct(removes),
                   parity=parity.next())

class sessionvars(object):
    def __init__(self, vars, start='?'):
        self.start = start
        self.vars = vars
    def __getitem__(self, key):
        return self.vars[key]
    def __setitem__(self, key, value):
        self.vars[key] = value
    def __copy__(self):
        return sessionvars(copy.copy(self.vars), self.start)
    def __iter__(self):
        separator = self.start
        for key, value in self.vars.iteritems():
            yield {'name': key, 'value': str(value), 'separator': separator}
            separator = '&'

class wsgiui(ui.ui):
    # default termwidth breaks under mod_wsgi
    def termwidth(self):
        return 80